Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- checkpoint-1000/README.md +202 -0
- checkpoint-1000/adapter_config.json +34 -0
- checkpoint-1000/adapter_model.safetensors +3 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state_0.pth +3 -0
- checkpoint-1000/rng_state_1.pth +3 -0
- checkpoint-1000/rng_state_2.pth +3 -0
- checkpoint-1000/rng_state_3.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/special_tokens_map.json +24 -0
- checkpoint-1000/tokenizer.json +0 -0
- checkpoint-1000/tokenizer.model +3 -0
- checkpoint-1000/tokenizer_config.json +45 -0
- checkpoint-1000/trainer_state.json +733 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-1500/README.md +202 -0
- checkpoint-1500/adapter_config.json +34 -0
- checkpoint-1500/adapter_model.safetensors +3 -0
- checkpoint-1500/optimizer.pt +3 -0
- checkpoint-1500/rng_state_0.pth +3 -0
- checkpoint-1500/rng_state_1.pth +3 -0
- checkpoint-1500/rng_state_2.pth +3 -0
- checkpoint-1500/rng_state_3.pth +3 -0
- checkpoint-1500/scheduler.pt +3 -0
- checkpoint-1500/special_tokens_map.json +24 -0
- checkpoint-1500/tokenizer.json +0 -0
- checkpoint-1500/tokenizer.model +3 -0
- checkpoint-1500/tokenizer_config.json +45 -0
- checkpoint-1500/trainer_state.json +1083 -0
- checkpoint-1500/training_args.bin +3 -0
- checkpoint-2000/README.md +202 -0
- checkpoint-2000/adapter_config.json +34 -0
- checkpoint-2000/adapter_model.safetensors +3 -0
- checkpoint-2000/optimizer.pt +3 -0
- checkpoint-2000/rng_state_0.pth +3 -0
- checkpoint-2000/rng_state_1.pth +3 -0
- checkpoint-2000/rng_state_2.pth +3 -0
- checkpoint-2000/rng_state_3.pth +3 -0
- checkpoint-2000/scheduler.pt +3 -0
- checkpoint-2000/special_tokens_map.json +24 -0
- checkpoint-2000/tokenizer.json +0 -0
- checkpoint-2000/tokenizer.model +3 -0
- checkpoint-2000/tokenizer_config.json +45 -0
- checkpoint-2000/trainer_state.json +1433 -0
- checkpoint-2000/training_args.bin +3 -0
- checkpoint-2500/README.md +202 -0
- checkpoint-2500/adapter_config.json +34 -0
- checkpoint-2500/adapter_model.safetensors +3 -0
- checkpoint-2500/optimizer.pt +3 -0
- checkpoint-2500/rng_state_0.pth +3 -0
checkpoint-1000/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: /root/autodl-tmp/models/Mistral-7B-Instruct-v0.2
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.11.1
|
checkpoint-1000/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/root/autodl-tmp/models/Mistral-7B-Instruct-v0.2",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"gate_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
+
"up_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"down_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-1000/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36493aa53f02e6c045259325dec12e6d58eae8ff543f6b7d6b301c532ae8a6b7
|
| 3 |
+
size 167832240
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d41e552237937d09bb91d0ec7441722d04d5967f46edf3f6453a183f702a921b
|
| 3 |
+
size 335922386
|
checkpoint-1000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92cc13315f24c28015d695b6cde08bb1cd6fea4cbc435998485ed6fbe4c91285
|
| 3 |
+
size 15024
|
checkpoint-1000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4c154b6a63e0b1f98f7d2847944398f99f1657d35e8eddf7fdf0ae2c24b0552
|
| 3 |
+
size 15024
|
checkpoint-1000/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f784c6a9507b51189f2caffbd178ea9882103b75852e31c15f47fdae6a43af1d
|
| 3 |
+
size 15024
|
checkpoint-1000/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34b023e05bc2d12b91dc436d4922b990d50ec8dc56d40dc3e36b3bb34fc81341
|
| 3 |
+
size 15024
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8b49173ee7e55afc15a08f5ddc568f3bb084867641a56b87732140f191e2918
|
| 3 |
+
size 1064
|
checkpoint-1000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-1000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
checkpoint-1000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"additional_special_tokens": [],
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '<s>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '[INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": true,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"split_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
+
"unk_token": "<unk>",
|
| 44 |
+
"use_default_system_prompt": false
|
| 45 |
+
}
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,733 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.4618937644341801,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.004618937644341801,
|
| 13 |
+
"grad_norm": 10.975909233093262,
|
| 14 |
+
"learning_rate": 3.4642032332563515e-07,
|
| 15 |
+
"loss": 2.4942,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.009237875288683603,
|
| 20 |
+
"grad_norm": 9.186948776245117,
|
| 21 |
+
"learning_rate": 9.237875288683603e-07,
|
| 22 |
+
"loss": 2.7582,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.013856812933025405,
|
| 27 |
+
"grad_norm": 10.907584190368652,
|
| 28 |
+
"learning_rate": 1.443418013856813e-06,
|
| 29 |
+
"loss": 2.6814,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.018475750577367205,
|
| 34 |
+
"grad_norm": 9.531168937683105,
|
| 35 |
+
"learning_rate": 2.0207852193995383e-06,
|
| 36 |
+
"loss": 2.6982,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.023094688221709007,
|
| 41 |
+
"grad_norm": 14.727725982666016,
|
| 42 |
+
"learning_rate": 2.5981524249422633e-06,
|
| 43 |
+
"loss": 2.0218,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.02771362586605081,
|
| 48 |
+
"grad_norm": 8.314309120178223,
|
| 49 |
+
"learning_rate": 3.117782909930716e-06,
|
| 50 |
+
"loss": 1.5595,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03233256351039261,
|
| 55 |
+
"grad_norm": 4.944284915924072,
|
| 56 |
+
"learning_rate": 3.6951501154734412e-06,
|
| 57 |
+
"loss": 1.02,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.03695150115473441,
|
| 62 |
+
"grad_norm": 10.882843971252441,
|
| 63 |
+
"learning_rate": 4.272517321016166e-06,
|
| 64 |
+
"loss": 1.0419,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04157043879907621,
|
| 69 |
+
"grad_norm": 12.310320854187012,
|
| 70 |
+
"learning_rate": 4.849884526558892e-06,
|
| 71 |
+
"loss": 1.0801,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.046189376443418015,
|
| 76 |
+
"grad_norm": 6.49992036819458,
|
| 77 |
+
"learning_rate": 5.427251732101616e-06,
|
| 78 |
+
"loss": 0.8444,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.050808314087759814,
|
| 83 |
+
"grad_norm": 2.89493465423584,
|
| 84 |
+
"learning_rate": 6.004618937644342e-06,
|
| 85 |
+
"loss": 0.8884,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.05542725173210162,
|
| 90 |
+
"grad_norm": 3.966763734817505,
|
| 91 |
+
"learning_rate": 6.581986143187067e-06,
|
| 92 |
+
"loss": 0.8672,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06004618937644342,
|
| 97 |
+
"grad_norm": 4.442293167114258,
|
| 98 |
+
"learning_rate": 7.159353348729793e-06,
|
| 99 |
+
"loss": 0.8037,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.06466512702078522,
|
| 104 |
+
"grad_norm": 2.506918430328369,
|
| 105 |
+
"learning_rate": 7.736720554272519e-06,
|
| 106 |
+
"loss": 0.724,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.06928406466512702,
|
| 111 |
+
"grad_norm": 5.733686447143555,
|
| 112 |
+
"learning_rate": 8.314087759815242e-06,
|
| 113 |
+
"loss": 0.7692,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.07390300230946882,
|
| 118 |
+
"grad_norm": 4.161188125610352,
|
| 119 |
+
"learning_rate": 8.891454965357968e-06,
|
| 120 |
+
"loss": 0.7413,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.07852193995381063,
|
| 125 |
+
"grad_norm": 3.9434962272644043,
|
| 126 |
+
"learning_rate": 9.468822170900693e-06,
|
| 127 |
+
"loss": 0.7386,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.08314087759815242,
|
| 132 |
+
"grad_norm": 2.9100701808929443,
|
| 133 |
+
"learning_rate": 1.0046189376443418e-05,
|
| 134 |
+
"loss": 0.6942,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.08775981524249422,
|
| 139 |
+
"grad_norm": 5.367318153381348,
|
| 140 |
+
"learning_rate": 1.0623556581986144e-05,
|
| 141 |
+
"loss": 0.8011,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.09237875288683603,
|
| 146 |
+
"grad_norm": 3.1690614223480225,
|
| 147 |
+
"learning_rate": 1.1200923787528869e-05,
|
| 148 |
+
"loss": 0.6816,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.09699769053117784,
|
| 153 |
+
"grad_norm": 4.35976505279541,
|
| 154 |
+
"learning_rate": 1.1778290993071595e-05,
|
| 155 |
+
"loss": 0.7408,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.10161662817551963,
|
| 160 |
+
"grad_norm": 3.330937623977661,
|
| 161 |
+
"learning_rate": 1.235565819861432e-05,
|
| 162 |
+
"loss": 0.7159,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.10623556581986143,
|
| 167 |
+
"grad_norm": 5.761129379272461,
|
| 168 |
+
"learning_rate": 1.2933025404157046e-05,
|
| 169 |
+
"loss": 0.6838,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.11085450346420324,
|
| 174 |
+
"grad_norm": 7.05668830871582,
|
| 175 |
+
"learning_rate": 1.351039260969977e-05,
|
| 176 |
+
"loss": 0.7135,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.11547344110854503,
|
| 181 |
+
"grad_norm": 3.7135939598083496,
|
| 182 |
+
"learning_rate": 1.4087759815242497e-05,
|
| 183 |
+
"loss": 0.6385,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.12009237875288684,
|
| 188 |
+
"grad_norm": 5.477907657623291,
|
| 189 |
+
"learning_rate": 1.4665127020785218e-05,
|
| 190 |
+
"loss": 0.6292,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.12471131639722864,
|
| 195 |
+
"grad_norm": 6.577059268951416,
|
| 196 |
+
"learning_rate": 1.5242494226327944e-05,
|
| 197 |
+
"loss": 0.6921,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.12933025404157045,
|
| 202 |
+
"grad_norm": 3.6328892707824707,
|
| 203 |
+
"learning_rate": 1.581986143187067e-05,
|
| 204 |
+
"loss": 0.6621,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.13394919168591224,
|
| 209 |
+
"grad_norm": 4.084783554077148,
|
| 210 |
+
"learning_rate": 1.6397228637413393e-05,
|
| 211 |
+
"loss": 0.6667,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.13856812933025403,
|
| 216 |
+
"grad_norm": 3.8719701766967773,
|
| 217 |
+
"learning_rate": 1.697459584295612e-05,
|
| 218 |
+
"loss": 0.6692,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.14318706697459585,
|
| 223 |
+
"grad_norm": 7.860931873321533,
|
| 224 |
+
"learning_rate": 1.7551963048498846e-05,
|
| 225 |
+
"loss": 0.6251,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.14780600461893764,
|
| 230 |
+
"grad_norm": 4.381837368011475,
|
| 231 |
+
"learning_rate": 1.812933025404157e-05,
|
| 232 |
+
"loss": 0.6297,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.15242494226327943,
|
| 237 |
+
"grad_norm": 3.7145886421203613,
|
| 238 |
+
"learning_rate": 1.8706697459584295e-05,
|
| 239 |
+
"loss": 0.6483,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.15704387990762125,
|
| 244 |
+
"grad_norm": 2.609006643295288,
|
| 245 |
+
"learning_rate": 1.9284064665127023e-05,
|
| 246 |
+
"loss": 0.6149,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.16166281755196305,
|
| 251 |
+
"grad_norm": 4.774081230163574,
|
| 252 |
+
"learning_rate": 1.9861431870669748e-05,
|
| 253 |
+
"loss": 0.6034,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.16628175519630484,
|
| 258 |
+
"grad_norm": 7.305100440979004,
|
| 259 |
+
"learning_rate": 2.0438799076212473e-05,
|
| 260 |
+
"loss": 0.6496,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.17090069284064666,
|
| 265 |
+
"grad_norm": 5.507181644439697,
|
| 266 |
+
"learning_rate": 2.1016166281755197e-05,
|
| 267 |
+
"loss": 0.643,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.17551963048498845,
|
| 272 |
+
"grad_norm": 4.033135890960693,
|
| 273 |
+
"learning_rate": 2.1593533487297922e-05,
|
| 274 |
+
"loss": 0.6186,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.18013856812933027,
|
| 279 |
+
"grad_norm": 3.903007745742798,
|
| 280 |
+
"learning_rate": 2.217090069284065e-05,
|
| 281 |
+
"loss": 0.6041,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.18475750577367206,
|
| 286 |
+
"grad_norm": 4.785562992095947,
|
| 287 |
+
"learning_rate": 2.2748267898383374e-05,
|
| 288 |
+
"loss": 0.5527,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.18937644341801385,
|
| 293 |
+
"grad_norm": 3.4289231300354004,
|
| 294 |
+
"learning_rate": 2.3325635103926096e-05,
|
| 295 |
+
"loss": 0.5936,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.19399538106235567,
|
| 300 |
+
"grad_norm": 2.384840965270996,
|
| 301 |
+
"learning_rate": 2.3903002309468824e-05,
|
| 302 |
+
"loss": 0.5421,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.19861431870669746,
|
| 307 |
+
"grad_norm": 4.025755882263184,
|
| 308 |
+
"learning_rate": 2.448036951501155e-05,
|
| 309 |
+
"loss": 0.5839,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.20323325635103925,
|
| 314 |
+
"grad_norm": 4.832013130187988,
|
| 315 |
+
"learning_rate": 2.5057736720554276e-05,
|
| 316 |
+
"loss": 0.5938,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.20785219399538107,
|
| 321 |
+
"grad_norm": 3.66886305809021,
|
| 322 |
+
"learning_rate": 2.5635103926096998e-05,
|
| 323 |
+
"loss": 0.5607,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.21247113163972287,
|
| 328 |
+
"grad_norm": 3.7285852432250977,
|
| 329 |
+
"learning_rate": 2.6212471131639726e-05,
|
| 330 |
+
"loss": 0.5457,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.21709006928406466,
|
| 335 |
+
"grad_norm": 3.755711555480957,
|
| 336 |
+
"learning_rate": 2.678983833718245e-05,
|
| 337 |
+
"loss": 0.5721,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.22170900692840648,
|
| 342 |
+
"grad_norm": 4.016116619110107,
|
| 343 |
+
"learning_rate": 2.7367205542725178e-05,
|
| 344 |
+
"loss": 0.59,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.22632794457274827,
|
| 349 |
+
"grad_norm": 6.123377799987793,
|
| 350 |
+
"learning_rate": 2.79445727482679e-05,
|
| 351 |
+
"loss": 0.6236,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.23094688221709006,
|
| 356 |
+
"grad_norm": 3.77093505859375,
|
| 357 |
+
"learning_rate": 2.8521939953810624e-05,
|
| 358 |
+
"loss": 0.6306,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.23556581986143188,
|
| 363 |
+
"grad_norm": 5.101199626922607,
|
| 364 |
+
"learning_rate": 2.9099307159353352e-05,
|
| 365 |
+
"loss": 0.5806,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.24018475750577367,
|
| 370 |
+
"grad_norm": 4.425400257110596,
|
| 371 |
+
"learning_rate": 2.9676674364896073e-05,
|
| 372 |
+
"loss": 0.5644,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.24480369515011546,
|
| 377 |
+
"grad_norm": 3.661381244659424,
|
| 378 |
+
"learning_rate": 3.02540415704388e-05,
|
| 379 |
+
"loss": 0.538,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.24942263279445728,
|
| 384 |
+
"grad_norm": 3.271655559539795,
|
| 385 |
+
"learning_rate": 3.0831408775981526e-05,
|
| 386 |
+
"loss": 0.5927,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.2540415704387991,
|
| 391 |
+
"grad_norm": 4.603795051574707,
|
| 392 |
+
"learning_rate": 3.140877598152425e-05,
|
| 393 |
+
"loss": 0.5772,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.2586605080831409,
|
| 398 |
+
"grad_norm": 3.379786968231201,
|
| 399 |
+
"learning_rate": 3.1986143187066975e-05,
|
| 400 |
+
"loss": 0.5577,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.2632794457274827,
|
| 405 |
+
"grad_norm": 3.3702409267425537,
|
| 406 |
+
"learning_rate": 3.25635103926097e-05,
|
| 407 |
+
"loss": 0.6258,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.2678983833718245,
|
| 412 |
+
"grad_norm": 3.1498706340789795,
|
| 413 |
+
"learning_rate": 3.3140877598152424e-05,
|
| 414 |
+
"loss": 0.5631,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.27251732101616627,
|
| 419 |
+
"grad_norm": 4.846761703491211,
|
| 420 |
+
"learning_rate": 3.3718244803695156e-05,
|
| 421 |
+
"loss": 0.5944,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.27713625866050806,
|
| 426 |
+
"grad_norm": 4.397818088531494,
|
| 427 |
+
"learning_rate": 3.4295612009237874e-05,
|
| 428 |
+
"loss": 0.5698,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.2817551963048499,
|
| 433 |
+
"grad_norm": 2.2724201679229736,
|
| 434 |
+
"learning_rate": 3.4872979214780605e-05,
|
| 435 |
+
"loss": 0.5468,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.2863741339491917,
|
| 440 |
+
"grad_norm": 4.73584508895874,
|
| 441 |
+
"learning_rate": 3.545034642032333e-05,
|
| 442 |
+
"loss": 0.5697,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.2909930715935335,
|
| 447 |
+
"grad_norm": 3.557711124420166,
|
| 448 |
+
"learning_rate": 3.6027713625866054e-05,
|
| 449 |
+
"loss": 0.5195,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.2956120092378753,
|
| 454 |
+
"grad_norm": 4.273311614990234,
|
| 455 |
+
"learning_rate": 3.660508083140878e-05,
|
| 456 |
+
"loss": 0.5561,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.3002309468822171,
|
| 461 |
+
"grad_norm": 3.6489686965942383,
|
| 462 |
+
"learning_rate": 3.7182448036951504e-05,
|
| 463 |
+
"loss": 0.566,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.30484988452655887,
|
| 468 |
+
"grad_norm": 3.4011149406433105,
|
| 469 |
+
"learning_rate": 3.775981524249423e-05,
|
| 470 |
+
"loss": 0.5468,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.3094688221709007,
|
| 475 |
+
"grad_norm": 3.517822742462158,
|
| 476 |
+
"learning_rate": 3.833718244803695e-05,
|
| 477 |
+
"loss": 0.5834,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.3140877598152425,
|
| 482 |
+
"grad_norm": 2.7577602863311768,
|
| 483 |
+
"learning_rate": 3.891454965357968e-05,
|
| 484 |
+
"loss": 0.5489,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.3187066974595843,
|
| 489 |
+
"grad_norm": 2.856598138809204,
|
| 490 |
+
"learning_rate": 3.94919168591224e-05,
|
| 491 |
+
"loss": 0.4906,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.3233256351039261,
|
| 496 |
+
"grad_norm": 4.136464595794678,
|
| 497 |
+
"learning_rate": 4.0069284064665133e-05,
|
| 498 |
+
"loss": 0.5705,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.3279445727482679,
|
| 503 |
+
"grad_norm": 4.121008396148682,
|
| 504 |
+
"learning_rate": 4.064665127020785e-05,
|
| 505 |
+
"loss": 0.6241,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.3325635103926097,
|
| 510 |
+
"grad_norm": 3.611814498901367,
|
| 511 |
+
"learning_rate": 4.122401847575058e-05,
|
| 512 |
+
"loss": 0.5034,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.3371824480369515,
|
| 517 |
+
"grad_norm": 3.4624834060668945,
|
| 518 |
+
"learning_rate": 4.18013856812933e-05,
|
| 519 |
+
"loss": 0.5643,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.3418013856812933,
|
| 524 |
+
"grad_norm": 3.3586976528167725,
|
| 525 |
+
"learning_rate": 4.237875288683603e-05,
|
| 526 |
+
"loss": 0.5439,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3464203233256351,
|
| 531 |
+
"grad_norm": 2.5129313468933105,
|
| 532 |
+
"learning_rate": 4.2956120092378757e-05,
|
| 533 |
+
"loss": 0.5062,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.3510392609699769,
|
| 538 |
+
"grad_norm": 3.0052690505981445,
|
| 539 |
+
"learning_rate": 4.353348729792148e-05,
|
| 540 |
+
"loss": 0.5219,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.3556581986143187,
|
| 545 |
+
"grad_norm": 3.7070388793945312,
|
| 546 |
+
"learning_rate": 4.4110854503464206e-05,
|
| 547 |
+
"loss": 0.5425,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.36027713625866054,
|
| 552 |
+
"grad_norm": 2.8378756046295166,
|
| 553 |
+
"learning_rate": 4.468822170900693e-05,
|
| 554 |
+
"loss": 0.5208,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.3648960739030023,
|
| 559 |
+
"grad_norm": 2.3988196849823,
|
| 560 |
+
"learning_rate": 4.5265588914549655e-05,
|
| 561 |
+
"loss": 0.5149,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.3695150115473441,
|
| 566 |
+
"grad_norm": 2.2305569648742676,
|
| 567 |
+
"learning_rate": 4.584295612009238e-05,
|
| 568 |
+
"loss": 0.5028,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.3741339491916859,
|
| 573 |
+
"grad_norm": 3.0817391872406006,
|
| 574 |
+
"learning_rate": 4.6420323325635104e-05,
|
| 575 |
+
"loss": 0.5419,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.3787528868360277,
|
| 580 |
+
"grad_norm": 2.767381429672241,
|
| 581 |
+
"learning_rate": 4.699769053117783e-05,
|
| 582 |
+
"loss": 0.5036,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.3833718244803695,
|
| 587 |
+
"grad_norm": 2.8563129901885986,
|
| 588 |
+
"learning_rate": 4.757505773672056e-05,
|
| 589 |
+
"loss": 0.5079,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.38799076212471134,
|
| 594 |
+
"grad_norm": 4.459218978881836,
|
| 595 |
+
"learning_rate": 4.815242494226328e-05,
|
| 596 |
+
"loss": 0.4891,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.39260969976905313,
|
| 601 |
+
"grad_norm": 2.825631856918335,
|
| 602 |
+
"learning_rate": 4.872979214780601e-05,
|
| 603 |
+
"loss": 0.4921,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.3972286374133949,
|
| 608 |
+
"grad_norm": 2.835643768310547,
|
| 609 |
+
"learning_rate": 4.9307159353348734e-05,
|
| 610 |
+
"loss": 0.4736,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.4018475750577367,
|
| 615 |
+
"grad_norm": 3.237922430038452,
|
| 616 |
+
"learning_rate": 4.988452655889146e-05,
|
| 617 |
+
"loss": 0.5254,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.4064665127020785,
|
| 622 |
+
"grad_norm": 3.913771390914917,
|
| 623 |
+
"learning_rate": 4.9999870022388165e-05,
|
| 624 |
+
"loss": 0.5212,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.4110854503464203,
|
| 629 |
+
"grad_norm": 4.357654094696045,
|
| 630 |
+
"learning_rate": 4.999934199065641e-05,
|
| 631 |
+
"loss": 0.6004,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.41570438799076215,
|
| 636 |
+
"grad_norm": 2.1519246101379395,
|
| 637 |
+
"learning_rate": 4.999840778977644e-05,
|
| 638 |
+
"loss": 0.5106,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.42032332563510394,
|
| 643 |
+
"grad_norm": 3.196580410003662,
|
| 644 |
+
"learning_rate": 4.9997067434926386e-05,
|
| 645 |
+
"loss": 0.4708,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.42494226327944573,
|
| 650 |
+
"grad_norm": 3.0933518409729004,
|
| 651 |
+
"learning_rate": 4.9995320947883265e-05,
|
| 652 |
+
"loss": 0.5228,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.4295612009237875,
|
| 657 |
+
"grad_norm": 2.5883092880249023,
|
| 658 |
+
"learning_rate": 4.999316835702259e-05,
|
| 659 |
+
"loss": 0.54,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.4341801385681293,
|
| 664 |
+
"grad_norm": 2.738126277923584,
|
| 665 |
+
"learning_rate": 4.9990609697317916e-05,
|
| 666 |
+
"loss": 0.4965,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.4387990762124711,
|
| 671 |
+
"grad_norm": 2.903364419937134,
|
| 672 |
+
"learning_rate": 4.998764501034028e-05,
|
| 673 |
+
"loss": 0.4732,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.44341801385681295,
|
| 678 |
+
"grad_norm": 1.895765781402588,
|
| 679 |
+
"learning_rate": 4.998427434425753e-05,
|
| 680 |
+
"loss": 0.4857,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.44803695150115475,
|
| 685 |
+
"grad_norm": 5.765718936920166,
|
| 686 |
+
"learning_rate": 4.998049775383353e-05,
|
| 687 |
+
"loss": 0.4901,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.45265588914549654,
|
| 692 |
+
"grad_norm": 3.9257349967956543,
|
| 693 |
+
"learning_rate": 4.997631530042727e-05,
|
| 694 |
+
"loss": 0.493,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.45727482678983833,
|
| 699 |
+
"grad_norm": 2.3068912029266357,
|
| 700 |
+
"learning_rate": 4.997172705199189e-05,
|
| 701 |
+
"loss": 0.5061,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.4618937644341801,
|
| 706 |
+
"grad_norm": 2.966820001602173,
|
| 707 |
+
"learning_rate": 4.996673308307355e-05,
|
| 708 |
+
"loss": 0.4557,
|
| 709 |
+
"step": 1000
|
| 710 |
+
}
|
| 711 |
+
],
|
| 712 |
+
"logging_steps": 10,
|
| 713 |
+
"max_steps": 8660,
|
| 714 |
+
"num_input_tokens_seen": 0,
|
| 715 |
+
"num_train_epochs": 4,
|
| 716 |
+
"save_steps": 500,
|
| 717 |
+
"stateful_callbacks": {
|
| 718 |
+
"TrainerControl": {
|
| 719 |
+
"args": {
|
| 720 |
+
"should_epoch_stop": false,
|
| 721 |
+
"should_evaluate": false,
|
| 722 |
+
"should_log": false,
|
| 723 |
+
"should_save": true,
|
| 724 |
+
"should_training_stop": false
|
| 725 |
+
},
|
| 726 |
+
"attributes": {}
|
| 727 |
+
}
|
| 728 |
+
},
|
| 729 |
+
"total_flos": 2.714316759199908e+17,
|
| 730 |
+
"train_batch_size": 1,
|
| 731 |
+
"trial_name": null,
|
| 732 |
+
"trial_params": null
|
| 733 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3759d15eeba226e23a6befbba0a7c35a73e6f4c92500ed4ddd24b6c972af08e7
|
| 3 |
+
size 5368
|
checkpoint-1500/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: /root/autodl-tmp/models/Mistral-7B-Instruct-v0.2
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.11.1
|
checkpoint-1500/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/root/autodl-tmp/models/Mistral-7B-Instruct-v0.2",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"gate_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
+
"up_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"down_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-1500/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:952a32c85191bf74435c9a79040da937ca07727476b52948e27fa194434540f8
|
| 3 |
+
size 167832240
|
checkpoint-1500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f114620d634a3996e618545005dfa16843836cd6e81bd7301c966fda578c95f1
|
| 3 |
+
size 335922386
|
checkpoint-1500/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92cc13315f24c28015d695b6cde08bb1cd6fea4cbc435998485ed6fbe4c91285
|
| 3 |
+
size 15024
|
checkpoint-1500/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4c154b6a63e0b1f98f7d2847944398f99f1657d35e8eddf7fdf0ae2c24b0552
|
| 3 |
+
size 15024
|
checkpoint-1500/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f784c6a9507b51189f2caffbd178ea9882103b75852e31c15f47fdae6a43af1d
|
| 3 |
+
size 15024
|
checkpoint-1500/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34b023e05bc2d12b91dc436d4922b990d50ec8dc56d40dc3e36b3bb34fc81341
|
| 3 |
+
size 15024
|
checkpoint-1500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6edfeab850ab15d09308c0f95492dbb9b389fc1d4595c74772678fcf6218b34
|
| 3 |
+
size 1064
|
checkpoint-1500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-1500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1500/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
checkpoint-1500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"additional_special_tokens": [],
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '<s>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '[INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": true,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"split_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
+
"unk_token": "<unk>",
|
| 44 |
+
"use_default_system_prompt": false
|
| 45 |
+
}
|
checkpoint-1500/trainer_state.json
ADDED
|
@@ -0,0 +1,1083 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.6928406466512702,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.004618937644341801,
|
| 13 |
+
"grad_norm": 10.975909233093262,
|
| 14 |
+
"learning_rate": 3.4642032332563515e-07,
|
| 15 |
+
"loss": 2.4942,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.009237875288683603,
|
| 20 |
+
"grad_norm": 9.186948776245117,
|
| 21 |
+
"learning_rate": 9.237875288683603e-07,
|
| 22 |
+
"loss": 2.7582,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.013856812933025405,
|
| 27 |
+
"grad_norm": 10.907584190368652,
|
| 28 |
+
"learning_rate": 1.443418013856813e-06,
|
| 29 |
+
"loss": 2.6814,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.018475750577367205,
|
| 34 |
+
"grad_norm": 9.531168937683105,
|
| 35 |
+
"learning_rate": 2.0207852193995383e-06,
|
| 36 |
+
"loss": 2.6982,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.023094688221709007,
|
| 41 |
+
"grad_norm": 14.727725982666016,
|
| 42 |
+
"learning_rate": 2.5981524249422633e-06,
|
| 43 |
+
"loss": 2.0218,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.02771362586605081,
|
| 48 |
+
"grad_norm": 8.314309120178223,
|
| 49 |
+
"learning_rate": 3.117782909930716e-06,
|
| 50 |
+
"loss": 1.5595,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03233256351039261,
|
| 55 |
+
"grad_norm": 4.944284915924072,
|
| 56 |
+
"learning_rate": 3.6951501154734412e-06,
|
| 57 |
+
"loss": 1.02,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.03695150115473441,
|
| 62 |
+
"grad_norm": 10.882843971252441,
|
| 63 |
+
"learning_rate": 4.272517321016166e-06,
|
| 64 |
+
"loss": 1.0419,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04157043879907621,
|
| 69 |
+
"grad_norm": 12.310320854187012,
|
| 70 |
+
"learning_rate": 4.849884526558892e-06,
|
| 71 |
+
"loss": 1.0801,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.046189376443418015,
|
| 76 |
+
"grad_norm": 6.49992036819458,
|
| 77 |
+
"learning_rate": 5.427251732101616e-06,
|
| 78 |
+
"loss": 0.8444,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.050808314087759814,
|
| 83 |
+
"grad_norm": 2.89493465423584,
|
| 84 |
+
"learning_rate": 6.004618937644342e-06,
|
| 85 |
+
"loss": 0.8884,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.05542725173210162,
|
| 90 |
+
"grad_norm": 3.966763734817505,
|
| 91 |
+
"learning_rate": 6.581986143187067e-06,
|
| 92 |
+
"loss": 0.8672,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06004618937644342,
|
| 97 |
+
"grad_norm": 4.442293167114258,
|
| 98 |
+
"learning_rate": 7.159353348729793e-06,
|
| 99 |
+
"loss": 0.8037,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.06466512702078522,
|
| 104 |
+
"grad_norm": 2.506918430328369,
|
| 105 |
+
"learning_rate": 7.736720554272519e-06,
|
| 106 |
+
"loss": 0.724,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.06928406466512702,
|
| 111 |
+
"grad_norm": 5.733686447143555,
|
| 112 |
+
"learning_rate": 8.314087759815242e-06,
|
| 113 |
+
"loss": 0.7692,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.07390300230946882,
|
| 118 |
+
"grad_norm": 4.161188125610352,
|
| 119 |
+
"learning_rate": 8.891454965357968e-06,
|
| 120 |
+
"loss": 0.7413,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.07852193995381063,
|
| 125 |
+
"grad_norm": 3.9434962272644043,
|
| 126 |
+
"learning_rate": 9.468822170900693e-06,
|
| 127 |
+
"loss": 0.7386,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.08314087759815242,
|
| 132 |
+
"grad_norm": 2.9100701808929443,
|
| 133 |
+
"learning_rate": 1.0046189376443418e-05,
|
| 134 |
+
"loss": 0.6942,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.08775981524249422,
|
| 139 |
+
"grad_norm": 5.367318153381348,
|
| 140 |
+
"learning_rate": 1.0623556581986144e-05,
|
| 141 |
+
"loss": 0.8011,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.09237875288683603,
|
| 146 |
+
"grad_norm": 3.1690614223480225,
|
| 147 |
+
"learning_rate": 1.1200923787528869e-05,
|
| 148 |
+
"loss": 0.6816,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.09699769053117784,
|
| 153 |
+
"grad_norm": 4.35976505279541,
|
| 154 |
+
"learning_rate": 1.1778290993071595e-05,
|
| 155 |
+
"loss": 0.7408,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.10161662817551963,
|
| 160 |
+
"grad_norm": 3.330937623977661,
|
| 161 |
+
"learning_rate": 1.235565819861432e-05,
|
| 162 |
+
"loss": 0.7159,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.10623556581986143,
|
| 167 |
+
"grad_norm": 5.761129379272461,
|
| 168 |
+
"learning_rate": 1.2933025404157046e-05,
|
| 169 |
+
"loss": 0.6838,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.11085450346420324,
|
| 174 |
+
"grad_norm": 7.05668830871582,
|
| 175 |
+
"learning_rate": 1.351039260969977e-05,
|
| 176 |
+
"loss": 0.7135,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.11547344110854503,
|
| 181 |
+
"grad_norm": 3.7135939598083496,
|
| 182 |
+
"learning_rate": 1.4087759815242497e-05,
|
| 183 |
+
"loss": 0.6385,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.12009237875288684,
|
| 188 |
+
"grad_norm": 5.477907657623291,
|
| 189 |
+
"learning_rate": 1.4665127020785218e-05,
|
| 190 |
+
"loss": 0.6292,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.12471131639722864,
|
| 195 |
+
"grad_norm": 6.577059268951416,
|
| 196 |
+
"learning_rate": 1.5242494226327944e-05,
|
| 197 |
+
"loss": 0.6921,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.12933025404157045,
|
| 202 |
+
"grad_norm": 3.6328892707824707,
|
| 203 |
+
"learning_rate": 1.581986143187067e-05,
|
| 204 |
+
"loss": 0.6621,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.13394919168591224,
|
| 209 |
+
"grad_norm": 4.084783554077148,
|
| 210 |
+
"learning_rate": 1.6397228637413393e-05,
|
| 211 |
+
"loss": 0.6667,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.13856812933025403,
|
| 216 |
+
"grad_norm": 3.8719701766967773,
|
| 217 |
+
"learning_rate": 1.697459584295612e-05,
|
| 218 |
+
"loss": 0.6692,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.14318706697459585,
|
| 223 |
+
"grad_norm": 7.860931873321533,
|
| 224 |
+
"learning_rate": 1.7551963048498846e-05,
|
| 225 |
+
"loss": 0.6251,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.14780600461893764,
|
| 230 |
+
"grad_norm": 4.381837368011475,
|
| 231 |
+
"learning_rate": 1.812933025404157e-05,
|
| 232 |
+
"loss": 0.6297,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.15242494226327943,
|
| 237 |
+
"grad_norm": 3.7145886421203613,
|
| 238 |
+
"learning_rate": 1.8706697459584295e-05,
|
| 239 |
+
"loss": 0.6483,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.15704387990762125,
|
| 244 |
+
"grad_norm": 2.609006643295288,
|
| 245 |
+
"learning_rate": 1.9284064665127023e-05,
|
| 246 |
+
"loss": 0.6149,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.16166281755196305,
|
| 251 |
+
"grad_norm": 4.774081230163574,
|
| 252 |
+
"learning_rate": 1.9861431870669748e-05,
|
| 253 |
+
"loss": 0.6034,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.16628175519630484,
|
| 258 |
+
"grad_norm": 7.305100440979004,
|
| 259 |
+
"learning_rate": 2.0438799076212473e-05,
|
| 260 |
+
"loss": 0.6496,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.17090069284064666,
|
| 265 |
+
"grad_norm": 5.507181644439697,
|
| 266 |
+
"learning_rate": 2.1016166281755197e-05,
|
| 267 |
+
"loss": 0.643,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.17551963048498845,
|
| 272 |
+
"grad_norm": 4.033135890960693,
|
| 273 |
+
"learning_rate": 2.1593533487297922e-05,
|
| 274 |
+
"loss": 0.6186,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.18013856812933027,
|
| 279 |
+
"grad_norm": 3.903007745742798,
|
| 280 |
+
"learning_rate": 2.217090069284065e-05,
|
| 281 |
+
"loss": 0.6041,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.18475750577367206,
|
| 286 |
+
"grad_norm": 4.785562992095947,
|
| 287 |
+
"learning_rate": 2.2748267898383374e-05,
|
| 288 |
+
"loss": 0.5527,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.18937644341801385,
|
| 293 |
+
"grad_norm": 3.4289231300354004,
|
| 294 |
+
"learning_rate": 2.3325635103926096e-05,
|
| 295 |
+
"loss": 0.5936,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.19399538106235567,
|
| 300 |
+
"grad_norm": 2.384840965270996,
|
| 301 |
+
"learning_rate": 2.3903002309468824e-05,
|
| 302 |
+
"loss": 0.5421,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.19861431870669746,
|
| 307 |
+
"grad_norm": 4.025755882263184,
|
| 308 |
+
"learning_rate": 2.448036951501155e-05,
|
| 309 |
+
"loss": 0.5839,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.20323325635103925,
|
| 314 |
+
"grad_norm": 4.832013130187988,
|
| 315 |
+
"learning_rate": 2.5057736720554276e-05,
|
| 316 |
+
"loss": 0.5938,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.20785219399538107,
|
| 321 |
+
"grad_norm": 3.66886305809021,
|
| 322 |
+
"learning_rate": 2.5635103926096998e-05,
|
| 323 |
+
"loss": 0.5607,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.21247113163972287,
|
| 328 |
+
"grad_norm": 3.7285852432250977,
|
| 329 |
+
"learning_rate": 2.6212471131639726e-05,
|
| 330 |
+
"loss": 0.5457,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.21709006928406466,
|
| 335 |
+
"grad_norm": 3.755711555480957,
|
| 336 |
+
"learning_rate": 2.678983833718245e-05,
|
| 337 |
+
"loss": 0.5721,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.22170900692840648,
|
| 342 |
+
"grad_norm": 4.016116619110107,
|
| 343 |
+
"learning_rate": 2.7367205542725178e-05,
|
| 344 |
+
"loss": 0.59,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.22632794457274827,
|
| 349 |
+
"grad_norm": 6.123377799987793,
|
| 350 |
+
"learning_rate": 2.79445727482679e-05,
|
| 351 |
+
"loss": 0.6236,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.23094688221709006,
|
| 356 |
+
"grad_norm": 3.77093505859375,
|
| 357 |
+
"learning_rate": 2.8521939953810624e-05,
|
| 358 |
+
"loss": 0.6306,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.23556581986143188,
|
| 363 |
+
"grad_norm": 5.101199626922607,
|
| 364 |
+
"learning_rate": 2.9099307159353352e-05,
|
| 365 |
+
"loss": 0.5806,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.24018475750577367,
|
| 370 |
+
"grad_norm": 4.425400257110596,
|
| 371 |
+
"learning_rate": 2.9676674364896073e-05,
|
| 372 |
+
"loss": 0.5644,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.24480369515011546,
|
| 377 |
+
"grad_norm": 3.661381244659424,
|
| 378 |
+
"learning_rate": 3.02540415704388e-05,
|
| 379 |
+
"loss": 0.538,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.24942263279445728,
|
| 384 |
+
"grad_norm": 3.271655559539795,
|
| 385 |
+
"learning_rate": 3.0831408775981526e-05,
|
| 386 |
+
"loss": 0.5927,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.2540415704387991,
|
| 391 |
+
"grad_norm": 4.603795051574707,
|
| 392 |
+
"learning_rate": 3.140877598152425e-05,
|
| 393 |
+
"loss": 0.5772,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.2586605080831409,
|
| 398 |
+
"grad_norm": 3.379786968231201,
|
| 399 |
+
"learning_rate": 3.1986143187066975e-05,
|
| 400 |
+
"loss": 0.5577,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.2632794457274827,
|
| 405 |
+
"grad_norm": 3.3702409267425537,
|
| 406 |
+
"learning_rate": 3.25635103926097e-05,
|
| 407 |
+
"loss": 0.6258,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.2678983833718245,
|
| 412 |
+
"grad_norm": 3.1498706340789795,
|
| 413 |
+
"learning_rate": 3.3140877598152424e-05,
|
| 414 |
+
"loss": 0.5631,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.27251732101616627,
|
| 419 |
+
"grad_norm": 4.846761703491211,
|
| 420 |
+
"learning_rate": 3.3718244803695156e-05,
|
| 421 |
+
"loss": 0.5944,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.27713625866050806,
|
| 426 |
+
"grad_norm": 4.397818088531494,
|
| 427 |
+
"learning_rate": 3.4295612009237874e-05,
|
| 428 |
+
"loss": 0.5698,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.2817551963048499,
|
| 433 |
+
"grad_norm": 2.2724201679229736,
|
| 434 |
+
"learning_rate": 3.4872979214780605e-05,
|
| 435 |
+
"loss": 0.5468,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.2863741339491917,
|
| 440 |
+
"grad_norm": 4.73584508895874,
|
| 441 |
+
"learning_rate": 3.545034642032333e-05,
|
| 442 |
+
"loss": 0.5697,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.2909930715935335,
|
| 447 |
+
"grad_norm": 3.557711124420166,
|
| 448 |
+
"learning_rate": 3.6027713625866054e-05,
|
| 449 |
+
"loss": 0.5195,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.2956120092378753,
|
| 454 |
+
"grad_norm": 4.273311614990234,
|
| 455 |
+
"learning_rate": 3.660508083140878e-05,
|
| 456 |
+
"loss": 0.5561,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.3002309468822171,
|
| 461 |
+
"grad_norm": 3.6489686965942383,
|
| 462 |
+
"learning_rate": 3.7182448036951504e-05,
|
| 463 |
+
"loss": 0.566,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.30484988452655887,
|
| 468 |
+
"grad_norm": 3.4011149406433105,
|
| 469 |
+
"learning_rate": 3.775981524249423e-05,
|
| 470 |
+
"loss": 0.5468,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.3094688221709007,
|
| 475 |
+
"grad_norm": 3.517822742462158,
|
| 476 |
+
"learning_rate": 3.833718244803695e-05,
|
| 477 |
+
"loss": 0.5834,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.3140877598152425,
|
| 482 |
+
"grad_norm": 2.7577602863311768,
|
| 483 |
+
"learning_rate": 3.891454965357968e-05,
|
| 484 |
+
"loss": 0.5489,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.3187066974595843,
|
| 489 |
+
"grad_norm": 2.856598138809204,
|
| 490 |
+
"learning_rate": 3.94919168591224e-05,
|
| 491 |
+
"loss": 0.4906,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.3233256351039261,
|
| 496 |
+
"grad_norm": 4.136464595794678,
|
| 497 |
+
"learning_rate": 4.0069284064665133e-05,
|
| 498 |
+
"loss": 0.5705,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.3279445727482679,
|
| 503 |
+
"grad_norm": 4.121008396148682,
|
| 504 |
+
"learning_rate": 4.064665127020785e-05,
|
| 505 |
+
"loss": 0.6241,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.3325635103926097,
|
| 510 |
+
"grad_norm": 3.611814498901367,
|
| 511 |
+
"learning_rate": 4.122401847575058e-05,
|
| 512 |
+
"loss": 0.5034,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.3371824480369515,
|
| 517 |
+
"grad_norm": 3.4624834060668945,
|
| 518 |
+
"learning_rate": 4.18013856812933e-05,
|
| 519 |
+
"loss": 0.5643,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.3418013856812933,
|
| 524 |
+
"grad_norm": 3.3586976528167725,
|
| 525 |
+
"learning_rate": 4.237875288683603e-05,
|
| 526 |
+
"loss": 0.5439,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3464203233256351,
|
| 531 |
+
"grad_norm": 2.5129313468933105,
|
| 532 |
+
"learning_rate": 4.2956120092378757e-05,
|
| 533 |
+
"loss": 0.5062,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.3510392609699769,
|
| 538 |
+
"grad_norm": 3.0052690505981445,
|
| 539 |
+
"learning_rate": 4.353348729792148e-05,
|
| 540 |
+
"loss": 0.5219,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.3556581986143187,
|
| 545 |
+
"grad_norm": 3.7070388793945312,
|
| 546 |
+
"learning_rate": 4.4110854503464206e-05,
|
| 547 |
+
"loss": 0.5425,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.36027713625866054,
|
| 552 |
+
"grad_norm": 2.8378756046295166,
|
| 553 |
+
"learning_rate": 4.468822170900693e-05,
|
| 554 |
+
"loss": 0.5208,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.3648960739030023,
|
| 559 |
+
"grad_norm": 2.3988196849823,
|
| 560 |
+
"learning_rate": 4.5265588914549655e-05,
|
| 561 |
+
"loss": 0.5149,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.3695150115473441,
|
| 566 |
+
"grad_norm": 2.2305569648742676,
|
| 567 |
+
"learning_rate": 4.584295612009238e-05,
|
| 568 |
+
"loss": 0.5028,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.3741339491916859,
|
| 573 |
+
"grad_norm": 3.0817391872406006,
|
| 574 |
+
"learning_rate": 4.6420323325635104e-05,
|
| 575 |
+
"loss": 0.5419,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.3787528868360277,
|
| 580 |
+
"grad_norm": 2.767381429672241,
|
| 581 |
+
"learning_rate": 4.699769053117783e-05,
|
| 582 |
+
"loss": 0.5036,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.3833718244803695,
|
| 587 |
+
"grad_norm": 2.8563129901885986,
|
| 588 |
+
"learning_rate": 4.757505773672056e-05,
|
| 589 |
+
"loss": 0.5079,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.38799076212471134,
|
| 594 |
+
"grad_norm": 4.459218978881836,
|
| 595 |
+
"learning_rate": 4.815242494226328e-05,
|
| 596 |
+
"loss": 0.4891,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.39260969976905313,
|
| 601 |
+
"grad_norm": 2.825631856918335,
|
| 602 |
+
"learning_rate": 4.872979214780601e-05,
|
| 603 |
+
"loss": 0.4921,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.3972286374133949,
|
| 608 |
+
"grad_norm": 2.835643768310547,
|
| 609 |
+
"learning_rate": 4.9307159353348734e-05,
|
| 610 |
+
"loss": 0.4736,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.4018475750577367,
|
| 615 |
+
"grad_norm": 3.237922430038452,
|
| 616 |
+
"learning_rate": 4.988452655889146e-05,
|
| 617 |
+
"loss": 0.5254,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.4064665127020785,
|
| 622 |
+
"grad_norm": 3.913771390914917,
|
| 623 |
+
"learning_rate": 4.9999870022388165e-05,
|
| 624 |
+
"loss": 0.5212,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.4110854503464203,
|
| 629 |
+
"grad_norm": 4.357654094696045,
|
| 630 |
+
"learning_rate": 4.999934199065641e-05,
|
| 631 |
+
"loss": 0.6004,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.41570438799076215,
|
| 636 |
+
"grad_norm": 2.1519246101379395,
|
| 637 |
+
"learning_rate": 4.999840778977644e-05,
|
| 638 |
+
"loss": 0.5106,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.42032332563510394,
|
| 643 |
+
"grad_norm": 3.196580410003662,
|
| 644 |
+
"learning_rate": 4.9997067434926386e-05,
|
| 645 |
+
"loss": 0.4708,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.42494226327944573,
|
| 650 |
+
"grad_norm": 3.0933518409729004,
|
| 651 |
+
"learning_rate": 4.9995320947883265e-05,
|
| 652 |
+
"loss": 0.5228,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.4295612009237875,
|
| 657 |
+
"grad_norm": 2.5883092880249023,
|
| 658 |
+
"learning_rate": 4.999316835702259e-05,
|
| 659 |
+
"loss": 0.54,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.4341801385681293,
|
| 664 |
+
"grad_norm": 2.738126277923584,
|
| 665 |
+
"learning_rate": 4.9990609697317916e-05,
|
| 666 |
+
"loss": 0.4965,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.4387990762124711,
|
| 671 |
+
"grad_norm": 2.903364419937134,
|
| 672 |
+
"learning_rate": 4.998764501034028e-05,
|
| 673 |
+
"loss": 0.4732,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.44341801385681295,
|
| 678 |
+
"grad_norm": 1.895765781402588,
|
| 679 |
+
"learning_rate": 4.998427434425753e-05,
|
| 680 |
+
"loss": 0.4857,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.44803695150115475,
|
| 685 |
+
"grad_norm": 5.765718936920166,
|
| 686 |
+
"learning_rate": 4.998049775383353e-05,
|
| 687 |
+
"loss": 0.4901,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.45265588914549654,
|
| 692 |
+
"grad_norm": 3.9257349967956543,
|
| 693 |
+
"learning_rate": 4.997631530042727e-05,
|
| 694 |
+
"loss": 0.493,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.45727482678983833,
|
| 699 |
+
"grad_norm": 2.3068912029266357,
|
| 700 |
+
"learning_rate": 4.997172705199189e-05,
|
| 701 |
+
"loss": 0.5061,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.4618937644341801,
|
| 706 |
+
"grad_norm": 2.966820001602173,
|
| 707 |
+
"learning_rate": 4.996673308307355e-05,
|
| 708 |
+
"loss": 0.4557,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.4665127020785219,
|
| 713 |
+
"grad_norm": 3.704120397567749,
|
| 714 |
+
"learning_rate": 4.996133347481021e-05,
|
| 715 |
+
"loss": 0.5302,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.47113163972286376,
|
| 720 |
+
"grad_norm": 2.066206216812134,
|
| 721 |
+
"learning_rate": 4.9955528314930376e-05,
|
| 722 |
+
"loss": 0.5035,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.47575057736720555,
|
| 727 |
+
"grad_norm": 3.7750158309936523,
|
| 728 |
+
"learning_rate": 4.9949317697751596e-05,
|
| 729 |
+
"loss": 0.5327,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.48036951501154734,
|
| 734 |
+
"grad_norm": 2.5127952098846436,
|
| 735 |
+
"learning_rate": 4.9942701724178965e-05,
|
| 736 |
+
"loss": 0.4929,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.48498845265588914,
|
| 741 |
+
"grad_norm": 2.594442367553711,
|
| 742 |
+
"learning_rate": 4.9935680501703485e-05,
|
| 743 |
+
"loss": 0.4795,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.4896073903002309,
|
| 748 |
+
"grad_norm": 4.830276966094971,
|
| 749 |
+
"learning_rate": 4.992825414440032e-05,
|
| 750 |
+
"loss": 0.5268,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.4942263279445728,
|
| 755 |
+
"grad_norm": 2.404269218444824,
|
| 756 |
+
"learning_rate": 4.9920422772926933e-05,
|
| 757 |
+
"loss": 0.5199,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.49884526558891457,
|
| 762 |
+
"grad_norm": 2.622856378555298,
|
| 763 |
+
"learning_rate": 4.991218651452114e-05,
|
| 764 |
+
"loss": 0.4928,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.5034642032332564,
|
| 769 |
+
"grad_norm": 2.660313844680786,
|
| 770 |
+
"learning_rate": 4.9903545502999014e-05,
|
| 771 |
+
"loss": 0.516,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.5080831408775982,
|
| 776 |
+
"grad_norm": 2.2060108184814453,
|
| 777 |
+
"learning_rate": 4.9894499878752744e-05,
|
| 778 |
+
"loss": 0.474,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.5127020785219399,
|
| 783 |
+
"grad_norm": 2.774624824523926,
|
| 784 |
+
"learning_rate": 4.988504978874835e-05,
|
| 785 |
+
"loss": 0.5053,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.5173210161662818,
|
| 790 |
+
"grad_norm": 2.0086095333099365,
|
| 791 |
+
"learning_rate": 4.987519538652326e-05,
|
| 792 |
+
"loss": 0.4478,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.5219399538106235,
|
| 797 |
+
"grad_norm": 2.7462918758392334,
|
| 798 |
+
"learning_rate": 4.986493683218386e-05,
|
| 799 |
+
"loss": 0.4872,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.5265588914549654,
|
| 804 |
+
"grad_norm": 2.2208642959594727,
|
| 805 |
+
"learning_rate": 4.985427429240286e-05,
|
| 806 |
+
"loss": 0.4617,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.5311778290993071,
|
| 811 |
+
"grad_norm": 3.3714964389801025,
|
| 812 |
+
"learning_rate": 4.984320794041662e-05,
|
| 813 |
+
"loss": 0.5293,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.535796766743649,
|
| 818 |
+
"grad_norm": 2.732804298400879,
|
| 819 |
+
"learning_rate": 4.98317379560223e-05,
|
| 820 |
+
"loss": 0.4582,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.5404157043879908,
|
| 825 |
+
"grad_norm": 3.4411492347717285,
|
| 826 |
+
"learning_rate": 4.981986452557495e-05,
|
| 827 |
+
"loss": 0.5359,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.5450346420323325,
|
| 832 |
+
"grad_norm": 2.5346171855926514,
|
| 833 |
+
"learning_rate": 4.9807587841984494e-05,
|
| 834 |
+
"loss": 0.438,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.5496535796766744,
|
| 839 |
+
"grad_norm": 2.068873882293701,
|
| 840 |
+
"learning_rate": 4.9794908104712586e-05,
|
| 841 |
+
"loss": 0.4541,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.5542725173210161,
|
| 846 |
+
"grad_norm": 3.7652342319488525,
|
| 847 |
+
"learning_rate": 4.978182551976939e-05,
|
| 848 |
+
"loss": 0.5372,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.558891454965358,
|
| 853 |
+
"grad_norm": 2.7133548259735107,
|
| 854 |
+
"learning_rate": 4.976834029971017e-05,
|
| 855 |
+
"loss": 0.4949,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.5635103926096998,
|
| 860 |
+
"grad_norm": 2.7093558311462402,
|
| 861 |
+
"learning_rate": 4.975445266363191e-05,
|
| 862 |
+
"loss": 0.4484,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.5681293302540416,
|
| 867 |
+
"grad_norm": 2.551117420196533,
|
| 868 |
+
"learning_rate": 4.974016283716974e-05,
|
| 869 |
+
"loss": 0.4865,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.5727482678983834,
|
| 874 |
+
"grad_norm": 3.5680108070373535,
|
| 875 |
+
"learning_rate": 4.9725471052493225e-05,
|
| 876 |
+
"loss": 0.512,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.5773672055427251,
|
| 881 |
+
"grad_norm": 3.1270763874053955,
|
| 882 |
+
"learning_rate": 4.9710377548302636e-05,
|
| 883 |
+
"loss": 0.4658,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.581986143187067,
|
| 888 |
+
"grad_norm": 2.7450294494628906,
|
| 889 |
+
"learning_rate": 4.9694882569825045e-05,
|
| 890 |
+
"loss": 0.5726,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.5866050808314087,
|
| 895 |
+
"grad_norm": 2.192270040512085,
|
| 896 |
+
"learning_rate": 4.967898636881039e-05,
|
| 897 |
+
"loss": 0.456,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.5912240184757506,
|
| 902 |
+
"grad_norm": 3.5508313179016113,
|
| 903 |
+
"learning_rate": 4.9662689203527304e-05,
|
| 904 |
+
"loss": 0.4363,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.5958429561200924,
|
| 909 |
+
"grad_norm": 3.789588212966919,
|
| 910 |
+
"learning_rate": 4.964599133875899e-05,
|
| 911 |
+
"loss": 0.3894,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.6004618937644342,
|
| 916 |
+
"grad_norm": 2.185136556625366,
|
| 917 |
+
"learning_rate": 4.9628893045798905e-05,
|
| 918 |
+
"loss": 0.4388,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.605080831408776,
|
| 923 |
+
"grad_norm": 3.9445693492889404,
|
| 924 |
+
"learning_rate": 4.961139460244631e-05,
|
| 925 |
+
"loss": 0.4761,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.6096997690531177,
|
| 930 |
+
"grad_norm": 2.027426242828369,
|
| 931 |
+
"learning_rate": 4.95934962930018e-05,
|
| 932 |
+
"loss": 0.4726,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.6143187066974596,
|
| 937 |
+
"grad_norm": 2.555227518081665,
|
| 938 |
+
"learning_rate": 4.957519840826268e-05,
|
| 939 |
+
"loss": 0.4546,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.6189376443418014,
|
| 944 |
+
"grad_norm": 3.800353765487671,
|
| 945 |
+
"learning_rate": 4.955650124551823e-05,
|
| 946 |
+
"loss": 0.4657,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.6235565819861432,
|
| 951 |
+
"grad_norm": 1.877545952796936,
|
| 952 |
+
"learning_rate": 4.953740510854485e-05,
|
| 953 |
+
"loss": 0.46,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.628175519630485,
|
| 958 |
+
"grad_norm": 2.205172538757324,
|
| 959 |
+
"learning_rate": 4.9517910307601204e-05,
|
| 960 |
+
"loss": 0.4845,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.6327944572748267,
|
| 965 |
+
"grad_norm": 4.207221031188965,
|
| 966 |
+
"learning_rate": 4.949801715942306e-05,
|
| 967 |
+
"loss": 0.4784,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.6374133949191686,
|
| 972 |
+
"grad_norm": 2.3010756969451904,
|
| 973 |
+
"learning_rate": 4.947772598721828e-05,
|
| 974 |
+
"loss": 0.4679,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.6420323325635104,
|
| 979 |
+
"grad_norm": 1.776963233947754,
|
| 980 |
+
"learning_rate": 4.9457037120661455e-05,
|
| 981 |
+
"loss": 0.4405,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.6466512702078522,
|
| 986 |
+
"grad_norm": 2.8734822273254395,
|
| 987 |
+
"learning_rate": 4.9435950895888604e-05,
|
| 988 |
+
"loss": 0.474,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.651270207852194,
|
| 993 |
+
"grad_norm": 3.049509286880493,
|
| 994 |
+
"learning_rate": 4.9414467655491695e-05,
|
| 995 |
+
"loss": 0.4334,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.6558891454965358,
|
| 1000 |
+
"grad_norm": 3.274083375930786,
|
| 1001 |
+
"learning_rate": 4.9392587748513105e-05,
|
| 1002 |
+
"loss": 0.4519,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.6605080831408776,
|
| 1007 |
+
"grad_norm": 2.149959087371826,
|
| 1008 |
+
"learning_rate": 4.937031153043991e-05,
|
| 1009 |
+
"loss": 0.4625,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.6651270207852193,
|
| 1014 |
+
"grad_norm": 2.3562982082366943,
|
| 1015 |
+
"learning_rate": 4.934763936319814e-05,
|
| 1016 |
+
"loss": 0.4487,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.6697459584295612,
|
| 1021 |
+
"grad_norm": 2.5950613021850586,
|
| 1022 |
+
"learning_rate": 4.932457161514689e-05,
|
| 1023 |
+
"loss": 0.4979,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.674364896073903,
|
| 1028 |
+
"grad_norm": 2.4045233726501465,
|
| 1029 |
+
"learning_rate": 4.9301108661072315e-05,
|
| 1030 |
+
"loss": 0.4442,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.6789838337182448,
|
| 1035 |
+
"grad_norm": 2.833594799041748,
|
| 1036 |
+
"learning_rate": 4.9277250882181575e-05,
|
| 1037 |
+
"loss": 0.4408,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.6836027713625866,
|
| 1042 |
+
"grad_norm": 1.7960981130599976,
|
| 1043 |
+
"learning_rate": 4.9252998666096625e-05,
|
| 1044 |
+
"loss": 0.4672,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.6882217090069284,
|
| 1049 |
+
"grad_norm": 2.261974811553955,
|
| 1050 |
+
"learning_rate": 4.922835240684792e-05,
|
| 1051 |
+
"loss": 0.3947,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.6928406466512702,
|
| 1056 |
+
"grad_norm": 2.966799020767212,
|
| 1057 |
+
"learning_rate": 4.9203312504867994e-05,
|
| 1058 |
+
"loss": 0.4546,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
}
|
| 1061 |
+
],
|
| 1062 |
+
"logging_steps": 10,
|
| 1063 |
+
"max_steps": 8660,
|
| 1064 |
+
"num_input_tokens_seen": 0,
|
| 1065 |
+
"num_train_epochs": 4,
|
| 1066 |
+
"save_steps": 500,
|
| 1067 |
+
"stateful_callbacks": {
|
| 1068 |
+
"TrainerControl": {
|
| 1069 |
+
"args": {
|
| 1070 |
+
"should_epoch_stop": false,
|
| 1071 |
+
"should_evaluate": false,
|
| 1072 |
+
"should_log": false,
|
| 1073 |
+
"should_save": true,
|
| 1074 |
+
"should_training_stop": false
|
| 1075 |
+
},
|
| 1076 |
+
"attributes": {}
|
| 1077 |
+
}
|
| 1078 |
+
},
|
| 1079 |
+
"total_flos": 4.102925424714056e+17,
|
| 1080 |
+
"train_batch_size": 1,
|
| 1081 |
+
"trial_name": null,
|
| 1082 |
+
"trial_params": null
|
| 1083 |
+
}
|
checkpoint-1500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3759d15eeba226e23a6befbba0a7c35a73e6f4c92500ed4ddd24b6c972af08e7
|
| 3 |
+
size 5368
|
checkpoint-2000/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: /root/autodl-tmp/models/Mistral-7B-Instruct-v0.2
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.11.1
|
checkpoint-2000/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/root/autodl-tmp/models/Mistral-7B-Instruct-v0.2",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"gate_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
+
"up_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"down_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-2000/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a24570c68a74655d64ae84d4efbaa0ce31075ab5066c1b57b17a3f2b878e22b8
|
| 3 |
+
size 167832240
|
checkpoint-2000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afd894e7e3c6628069ae03de1ddfcf6cff3262605e2de4dc52381950f15a788e
|
| 3 |
+
size 335922386
|
checkpoint-2000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92cc13315f24c28015d695b6cde08bb1cd6fea4cbc435998485ed6fbe4c91285
|
| 3 |
+
size 15024
|
checkpoint-2000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4c154b6a63e0b1f98f7d2847944398f99f1657d35e8eddf7fdf0ae2c24b0552
|
| 3 |
+
size 15024
|
checkpoint-2000/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f784c6a9507b51189f2caffbd178ea9882103b75852e31c15f47fdae6a43af1d
|
| 3 |
+
size 15024
|
checkpoint-2000/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34b023e05bc2d12b91dc436d4922b990d50ec8dc56d40dc3e36b3bb34fc81341
|
| 3 |
+
size 15024
|
checkpoint-2000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4036b81488ab2c5c954d4f11db1e2f9ea7c7860752b76b3c77345bf402f99995
|
| 3 |
+
size 1064
|
checkpoint-2000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-2000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2000/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
checkpoint-2000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"additional_special_tokens": [],
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '<s>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '[INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": true,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"split_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
+
"unk_token": "<unk>",
|
| 44 |
+
"use_default_system_prompt": false
|
| 45 |
+
}
|
checkpoint-2000/trainer_state.json
ADDED
|
@@ -0,0 +1,1433 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9237875288683602,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.004618937644341801,
|
| 13 |
+
"grad_norm": 10.975909233093262,
|
| 14 |
+
"learning_rate": 3.4642032332563515e-07,
|
| 15 |
+
"loss": 2.4942,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.009237875288683603,
|
| 20 |
+
"grad_norm": 9.186948776245117,
|
| 21 |
+
"learning_rate": 9.237875288683603e-07,
|
| 22 |
+
"loss": 2.7582,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.013856812933025405,
|
| 27 |
+
"grad_norm": 10.907584190368652,
|
| 28 |
+
"learning_rate": 1.443418013856813e-06,
|
| 29 |
+
"loss": 2.6814,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.018475750577367205,
|
| 34 |
+
"grad_norm": 9.531168937683105,
|
| 35 |
+
"learning_rate": 2.0207852193995383e-06,
|
| 36 |
+
"loss": 2.6982,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.023094688221709007,
|
| 41 |
+
"grad_norm": 14.727725982666016,
|
| 42 |
+
"learning_rate": 2.5981524249422633e-06,
|
| 43 |
+
"loss": 2.0218,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.02771362586605081,
|
| 48 |
+
"grad_norm": 8.314309120178223,
|
| 49 |
+
"learning_rate": 3.117782909930716e-06,
|
| 50 |
+
"loss": 1.5595,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03233256351039261,
|
| 55 |
+
"grad_norm": 4.944284915924072,
|
| 56 |
+
"learning_rate": 3.6951501154734412e-06,
|
| 57 |
+
"loss": 1.02,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.03695150115473441,
|
| 62 |
+
"grad_norm": 10.882843971252441,
|
| 63 |
+
"learning_rate": 4.272517321016166e-06,
|
| 64 |
+
"loss": 1.0419,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04157043879907621,
|
| 69 |
+
"grad_norm": 12.310320854187012,
|
| 70 |
+
"learning_rate": 4.849884526558892e-06,
|
| 71 |
+
"loss": 1.0801,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.046189376443418015,
|
| 76 |
+
"grad_norm": 6.49992036819458,
|
| 77 |
+
"learning_rate": 5.427251732101616e-06,
|
| 78 |
+
"loss": 0.8444,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.050808314087759814,
|
| 83 |
+
"grad_norm": 2.89493465423584,
|
| 84 |
+
"learning_rate": 6.004618937644342e-06,
|
| 85 |
+
"loss": 0.8884,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.05542725173210162,
|
| 90 |
+
"grad_norm": 3.966763734817505,
|
| 91 |
+
"learning_rate": 6.581986143187067e-06,
|
| 92 |
+
"loss": 0.8672,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06004618937644342,
|
| 97 |
+
"grad_norm": 4.442293167114258,
|
| 98 |
+
"learning_rate": 7.159353348729793e-06,
|
| 99 |
+
"loss": 0.8037,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.06466512702078522,
|
| 104 |
+
"grad_norm": 2.506918430328369,
|
| 105 |
+
"learning_rate": 7.736720554272519e-06,
|
| 106 |
+
"loss": 0.724,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.06928406466512702,
|
| 111 |
+
"grad_norm": 5.733686447143555,
|
| 112 |
+
"learning_rate": 8.314087759815242e-06,
|
| 113 |
+
"loss": 0.7692,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.07390300230946882,
|
| 118 |
+
"grad_norm": 4.161188125610352,
|
| 119 |
+
"learning_rate": 8.891454965357968e-06,
|
| 120 |
+
"loss": 0.7413,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.07852193995381063,
|
| 125 |
+
"grad_norm": 3.9434962272644043,
|
| 126 |
+
"learning_rate": 9.468822170900693e-06,
|
| 127 |
+
"loss": 0.7386,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.08314087759815242,
|
| 132 |
+
"grad_norm": 2.9100701808929443,
|
| 133 |
+
"learning_rate": 1.0046189376443418e-05,
|
| 134 |
+
"loss": 0.6942,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.08775981524249422,
|
| 139 |
+
"grad_norm": 5.367318153381348,
|
| 140 |
+
"learning_rate": 1.0623556581986144e-05,
|
| 141 |
+
"loss": 0.8011,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.09237875288683603,
|
| 146 |
+
"grad_norm": 3.1690614223480225,
|
| 147 |
+
"learning_rate": 1.1200923787528869e-05,
|
| 148 |
+
"loss": 0.6816,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.09699769053117784,
|
| 153 |
+
"grad_norm": 4.35976505279541,
|
| 154 |
+
"learning_rate": 1.1778290993071595e-05,
|
| 155 |
+
"loss": 0.7408,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.10161662817551963,
|
| 160 |
+
"grad_norm": 3.330937623977661,
|
| 161 |
+
"learning_rate": 1.235565819861432e-05,
|
| 162 |
+
"loss": 0.7159,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.10623556581986143,
|
| 167 |
+
"grad_norm": 5.761129379272461,
|
| 168 |
+
"learning_rate": 1.2933025404157046e-05,
|
| 169 |
+
"loss": 0.6838,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.11085450346420324,
|
| 174 |
+
"grad_norm": 7.05668830871582,
|
| 175 |
+
"learning_rate": 1.351039260969977e-05,
|
| 176 |
+
"loss": 0.7135,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.11547344110854503,
|
| 181 |
+
"grad_norm": 3.7135939598083496,
|
| 182 |
+
"learning_rate": 1.4087759815242497e-05,
|
| 183 |
+
"loss": 0.6385,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.12009237875288684,
|
| 188 |
+
"grad_norm": 5.477907657623291,
|
| 189 |
+
"learning_rate": 1.4665127020785218e-05,
|
| 190 |
+
"loss": 0.6292,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.12471131639722864,
|
| 195 |
+
"grad_norm": 6.577059268951416,
|
| 196 |
+
"learning_rate": 1.5242494226327944e-05,
|
| 197 |
+
"loss": 0.6921,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.12933025404157045,
|
| 202 |
+
"grad_norm": 3.6328892707824707,
|
| 203 |
+
"learning_rate": 1.581986143187067e-05,
|
| 204 |
+
"loss": 0.6621,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.13394919168591224,
|
| 209 |
+
"grad_norm": 4.084783554077148,
|
| 210 |
+
"learning_rate": 1.6397228637413393e-05,
|
| 211 |
+
"loss": 0.6667,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.13856812933025403,
|
| 216 |
+
"grad_norm": 3.8719701766967773,
|
| 217 |
+
"learning_rate": 1.697459584295612e-05,
|
| 218 |
+
"loss": 0.6692,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.14318706697459585,
|
| 223 |
+
"grad_norm": 7.860931873321533,
|
| 224 |
+
"learning_rate": 1.7551963048498846e-05,
|
| 225 |
+
"loss": 0.6251,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.14780600461893764,
|
| 230 |
+
"grad_norm": 4.381837368011475,
|
| 231 |
+
"learning_rate": 1.812933025404157e-05,
|
| 232 |
+
"loss": 0.6297,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.15242494226327943,
|
| 237 |
+
"grad_norm": 3.7145886421203613,
|
| 238 |
+
"learning_rate": 1.8706697459584295e-05,
|
| 239 |
+
"loss": 0.6483,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.15704387990762125,
|
| 244 |
+
"grad_norm": 2.609006643295288,
|
| 245 |
+
"learning_rate": 1.9284064665127023e-05,
|
| 246 |
+
"loss": 0.6149,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.16166281755196305,
|
| 251 |
+
"grad_norm": 4.774081230163574,
|
| 252 |
+
"learning_rate": 1.9861431870669748e-05,
|
| 253 |
+
"loss": 0.6034,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.16628175519630484,
|
| 258 |
+
"grad_norm": 7.305100440979004,
|
| 259 |
+
"learning_rate": 2.0438799076212473e-05,
|
| 260 |
+
"loss": 0.6496,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.17090069284064666,
|
| 265 |
+
"grad_norm": 5.507181644439697,
|
| 266 |
+
"learning_rate": 2.1016166281755197e-05,
|
| 267 |
+
"loss": 0.643,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.17551963048498845,
|
| 272 |
+
"grad_norm": 4.033135890960693,
|
| 273 |
+
"learning_rate": 2.1593533487297922e-05,
|
| 274 |
+
"loss": 0.6186,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.18013856812933027,
|
| 279 |
+
"grad_norm": 3.903007745742798,
|
| 280 |
+
"learning_rate": 2.217090069284065e-05,
|
| 281 |
+
"loss": 0.6041,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.18475750577367206,
|
| 286 |
+
"grad_norm": 4.785562992095947,
|
| 287 |
+
"learning_rate": 2.2748267898383374e-05,
|
| 288 |
+
"loss": 0.5527,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.18937644341801385,
|
| 293 |
+
"grad_norm": 3.4289231300354004,
|
| 294 |
+
"learning_rate": 2.3325635103926096e-05,
|
| 295 |
+
"loss": 0.5936,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.19399538106235567,
|
| 300 |
+
"grad_norm": 2.384840965270996,
|
| 301 |
+
"learning_rate": 2.3903002309468824e-05,
|
| 302 |
+
"loss": 0.5421,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.19861431870669746,
|
| 307 |
+
"grad_norm": 4.025755882263184,
|
| 308 |
+
"learning_rate": 2.448036951501155e-05,
|
| 309 |
+
"loss": 0.5839,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.20323325635103925,
|
| 314 |
+
"grad_norm": 4.832013130187988,
|
| 315 |
+
"learning_rate": 2.5057736720554276e-05,
|
| 316 |
+
"loss": 0.5938,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.20785219399538107,
|
| 321 |
+
"grad_norm": 3.66886305809021,
|
| 322 |
+
"learning_rate": 2.5635103926096998e-05,
|
| 323 |
+
"loss": 0.5607,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.21247113163972287,
|
| 328 |
+
"grad_norm": 3.7285852432250977,
|
| 329 |
+
"learning_rate": 2.6212471131639726e-05,
|
| 330 |
+
"loss": 0.5457,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.21709006928406466,
|
| 335 |
+
"grad_norm": 3.755711555480957,
|
| 336 |
+
"learning_rate": 2.678983833718245e-05,
|
| 337 |
+
"loss": 0.5721,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.22170900692840648,
|
| 342 |
+
"grad_norm": 4.016116619110107,
|
| 343 |
+
"learning_rate": 2.7367205542725178e-05,
|
| 344 |
+
"loss": 0.59,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.22632794457274827,
|
| 349 |
+
"grad_norm": 6.123377799987793,
|
| 350 |
+
"learning_rate": 2.79445727482679e-05,
|
| 351 |
+
"loss": 0.6236,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.23094688221709006,
|
| 356 |
+
"grad_norm": 3.77093505859375,
|
| 357 |
+
"learning_rate": 2.8521939953810624e-05,
|
| 358 |
+
"loss": 0.6306,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.23556581986143188,
|
| 363 |
+
"grad_norm": 5.101199626922607,
|
| 364 |
+
"learning_rate": 2.9099307159353352e-05,
|
| 365 |
+
"loss": 0.5806,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.24018475750577367,
|
| 370 |
+
"grad_norm": 4.425400257110596,
|
| 371 |
+
"learning_rate": 2.9676674364896073e-05,
|
| 372 |
+
"loss": 0.5644,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.24480369515011546,
|
| 377 |
+
"grad_norm": 3.661381244659424,
|
| 378 |
+
"learning_rate": 3.02540415704388e-05,
|
| 379 |
+
"loss": 0.538,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.24942263279445728,
|
| 384 |
+
"grad_norm": 3.271655559539795,
|
| 385 |
+
"learning_rate": 3.0831408775981526e-05,
|
| 386 |
+
"loss": 0.5927,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.2540415704387991,
|
| 391 |
+
"grad_norm": 4.603795051574707,
|
| 392 |
+
"learning_rate": 3.140877598152425e-05,
|
| 393 |
+
"loss": 0.5772,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.2586605080831409,
|
| 398 |
+
"grad_norm": 3.379786968231201,
|
| 399 |
+
"learning_rate": 3.1986143187066975e-05,
|
| 400 |
+
"loss": 0.5577,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.2632794457274827,
|
| 405 |
+
"grad_norm": 3.3702409267425537,
|
| 406 |
+
"learning_rate": 3.25635103926097e-05,
|
| 407 |
+
"loss": 0.6258,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.2678983833718245,
|
| 412 |
+
"grad_norm": 3.1498706340789795,
|
| 413 |
+
"learning_rate": 3.3140877598152424e-05,
|
| 414 |
+
"loss": 0.5631,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.27251732101616627,
|
| 419 |
+
"grad_norm": 4.846761703491211,
|
| 420 |
+
"learning_rate": 3.3718244803695156e-05,
|
| 421 |
+
"loss": 0.5944,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.27713625866050806,
|
| 426 |
+
"grad_norm": 4.397818088531494,
|
| 427 |
+
"learning_rate": 3.4295612009237874e-05,
|
| 428 |
+
"loss": 0.5698,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.2817551963048499,
|
| 433 |
+
"grad_norm": 2.2724201679229736,
|
| 434 |
+
"learning_rate": 3.4872979214780605e-05,
|
| 435 |
+
"loss": 0.5468,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.2863741339491917,
|
| 440 |
+
"grad_norm": 4.73584508895874,
|
| 441 |
+
"learning_rate": 3.545034642032333e-05,
|
| 442 |
+
"loss": 0.5697,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.2909930715935335,
|
| 447 |
+
"grad_norm": 3.557711124420166,
|
| 448 |
+
"learning_rate": 3.6027713625866054e-05,
|
| 449 |
+
"loss": 0.5195,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.2956120092378753,
|
| 454 |
+
"grad_norm": 4.273311614990234,
|
| 455 |
+
"learning_rate": 3.660508083140878e-05,
|
| 456 |
+
"loss": 0.5561,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.3002309468822171,
|
| 461 |
+
"grad_norm": 3.6489686965942383,
|
| 462 |
+
"learning_rate": 3.7182448036951504e-05,
|
| 463 |
+
"loss": 0.566,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.30484988452655887,
|
| 468 |
+
"grad_norm": 3.4011149406433105,
|
| 469 |
+
"learning_rate": 3.775981524249423e-05,
|
| 470 |
+
"loss": 0.5468,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.3094688221709007,
|
| 475 |
+
"grad_norm": 3.517822742462158,
|
| 476 |
+
"learning_rate": 3.833718244803695e-05,
|
| 477 |
+
"loss": 0.5834,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.3140877598152425,
|
| 482 |
+
"grad_norm": 2.7577602863311768,
|
| 483 |
+
"learning_rate": 3.891454965357968e-05,
|
| 484 |
+
"loss": 0.5489,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.3187066974595843,
|
| 489 |
+
"grad_norm": 2.856598138809204,
|
| 490 |
+
"learning_rate": 3.94919168591224e-05,
|
| 491 |
+
"loss": 0.4906,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.3233256351039261,
|
| 496 |
+
"grad_norm": 4.136464595794678,
|
| 497 |
+
"learning_rate": 4.0069284064665133e-05,
|
| 498 |
+
"loss": 0.5705,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.3279445727482679,
|
| 503 |
+
"grad_norm": 4.121008396148682,
|
| 504 |
+
"learning_rate": 4.064665127020785e-05,
|
| 505 |
+
"loss": 0.6241,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.3325635103926097,
|
| 510 |
+
"grad_norm": 3.611814498901367,
|
| 511 |
+
"learning_rate": 4.122401847575058e-05,
|
| 512 |
+
"loss": 0.5034,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.3371824480369515,
|
| 517 |
+
"grad_norm": 3.4624834060668945,
|
| 518 |
+
"learning_rate": 4.18013856812933e-05,
|
| 519 |
+
"loss": 0.5643,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.3418013856812933,
|
| 524 |
+
"grad_norm": 3.3586976528167725,
|
| 525 |
+
"learning_rate": 4.237875288683603e-05,
|
| 526 |
+
"loss": 0.5439,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3464203233256351,
|
| 531 |
+
"grad_norm": 2.5129313468933105,
|
| 532 |
+
"learning_rate": 4.2956120092378757e-05,
|
| 533 |
+
"loss": 0.5062,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.3510392609699769,
|
| 538 |
+
"grad_norm": 3.0052690505981445,
|
| 539 |
+
"learning_rate": 4.353348729792148e-05,
|
| 540 |
+
"loss": 0.5219,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.3556581986143187,
|
| 545 |
+
"grad_norm": 3.7070388793945312,
|
| 546 |
+
"learning_rate": 4.4110854503464206e-05,
|
| 547 |
+
"loss": 0.5425,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.36027713625866054,
|
| 552 |
+
"grad_norm": 2.8378756046295166,
|
| 553 |
+
"learning_rate": 4.468822170900693e-05,
|
| 554 |
+
"loss": 0.5208,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.3648960739030023,
|
| 559 |
+
"grad_norm": 2.3988196849823,
|
| 560 |
+
"learning_rate": 4.5265588914549655e-05,
|
| 561 |
+
"loss": 0.5149,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.3695150115473441,
|
| 566 |
+
"grad_norm": 2.2305569648742676,
|
| 567 |
+
"learning_rate": 4.584295612009238e-05,
|
| 568 |
+
"loss": 0.5028,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.3741339491916859,
|
| 573 |
+
"grad_norm": 3.0817391872406006,
|
| 574 |
+
"learning_rate": 4.6420323325635104e-05,
|
| 575 |
+
"loss": 0.5419,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.3787528868360277,
|
| 580 |
+
"grad_norm": 2.767381429672241,
|
| 581 |
+
"learning_rate": 4.699769053117783e-05,
|
| 582 |
+
"loss": 0.5036,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.3833718244803695,
|
| 587 |
+
"grad_norm": 2.8563129901885986,
|
| 588 |
+
"learning_rate": 4.757505773672056e-05,
|
| 589 |
+
"loss": 0.5079,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.38799076212471134,
|
| 594 |
+
"grad_norm": 4.459218978881836,
|
| 595 |
+
"learning_rate": 4.815242494226328e-05,
|
| 596 |
+
"loss": 0.4891,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.39260969976905313,
|
| 601 |
+
"grad_norm": 2.825631856918335,
|
| 602 |
+
"learning_rate": 4.872979214780601e-05,
|
| 603 |
+
"loss": 0.4921,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.3972286374133949,
|
| 608 |
+
"grad_norm": 2.835643768310547,
|
| 609 |
+
"learning_rate": 4.9307159353348734e-05,
|
| 610 |
+
"loss": 0.4736,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.4018475750577367,
|
| 615 |
+
"grad_norm": 3.237922430038452,
|
| 616 |
+
"learning_rate": 4.988452655889146e-05,
|
| 617 |
+
"loss": 0.5254,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.4064665127020785,
|
| 622 |
+
"grad_norm": 3.913771390914917,
|
| 623 |
+
"learning_rate": 4.9999870022388165e-05,
|
| 624 |
+
"loss": 0.5212,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.4110854503464203,
|
| 629 |
+
"grad_norm": 4.357654094696045,
|
| 630 |
+
"learning_rate": 4.999934199065641e-05,
|
| 631 |
+
"loss": 0.6004,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.41570438799076215,
|
| 636 |
+
"grad_norm": 2.1519246101379395,
|
| 637 |
+
"learning_rate": 4.999840778977644e-05,
|
| 638 |
+
"loss": 0.5106,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.42032332563510394,
|
| 643 |
+
"grad_norm": 3.196580410003662,
|
| 644 |
+
"learning_rate": 4.9997067434926386e-05,
|
| 645 |
+
"loss": 0.4708,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.42494226327944573,
|
| 650 |
+
"grad_norm": 3.0933518409729004,
|
| 651 |
+
"learning_rate": 4.9995320947883265e-05,
|
| 652 |
+
"loss": 0.5228,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.4295612009237875,
|
| 657 |
+
"grad_norm": 2.5883092880249023,
|
| 658 |
+
"learning_rate": 4.999316835702259e-05,
|
| 659 |
+
"loss": 0.54,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.4341801385681293,
|
| 664 |
+
"grad_norm": 2.738126277923584,
|
| 665 |
+
"learning_rate": 4.9990609697317916e-05,
|
| 666 |
+
"loss": 0.4965,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.4387990762124711,
|
| 671 |
+
"grad_norm": 2.903364419937134,
|
| 672 |
+
"learning_rate": 4.998764501034028e-05,
|
| 673 |
+
"loss": 0.4732,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.44341801385681295,
|
| 678 |
+
"grad_norm": 1.895765781402588,
|
| 679 |
+
"learning_rate": 4.998427434425753e-05,
|
| 680 |
+
"loss": 0.4857,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.44803695150115475,
|
| 685 |
+
"grad_norm": 5.765718936920166,
|
| 686 |
+
"learning_rate": 4.998049775383353e-05,
|
| 687 |
+
"loss": 0.4901,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.45265588914549654,
|
| 692 |
+
"grad_norm": 3.9257349967956543,
|
| 693 |
+
"learning_rate": 4.997631530042727e-05,
|
| 694 |
+
"loss": 0.493,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.45727482678983833,
|
| 699 |
+
"grad_norm": 2.3068912029266357,
|
| 700 |
+
"learning_rate": 4.997172705199189e-05,
|
| 701 |
+
"loss": 0.5061,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.4618937644341801,
|
| 706 |
+
"grad_norm": 2.966820001602173,
|
| 707 |
+
"learning_rate": 4.996673308307355e-05,
|
| 708 |
+
"loss": 0.4557,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.4665127020785219,
|
| 713 |
+
"grad_norm": 3.704120397567749,
|
| 714 |
+
"learning_rate": 4.996133347481021e-05,
|
| 715 |
+
"loss": 0.5302,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.47113163972286376,
|
| 720 |
+
"grad_norm": 2.066206216812134,
|
| 721 |
+
"learning_rate": 4.9955528314930376e-05,
|
| 722 |
+
"loss": 0.5035,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.47575057736720555,
|
| 727 |
+
"grad_norm": 3.7750158309936523,
|
| 728 |
+
"learning_rate": 4.9949317697751596e-05,
|
| 729 |
+
"loss": 0.5327,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.48036951501154734,
|
| 734 |
+
"grad_norm": 2.5127952098846436,
|
| 735 |
+
"learning_rate": 4.9942701724178965e-05,
|
| 736 |
+
"loss": 0.4929,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.48498845265588914,
|
| 741 |
+
"grad_norm": 2.594442367553711,
|
| 742 |
+
"learning_rate": 4.9935680501703485e-05,
|
| 743 |
+
"loss": 0.4795,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.4896073903002309,
|
| 748 |
+
"grad_norm": 4.830276966094971,
|
| 749 |
+
"learning_rate": 4.992825414440032e-05,
|
| 750 |
+
"loss": 0.5268,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.4942263279445728,
|
| 755 |
+
"grad_norm": 2.404269218444824,
|
| 756 |
+
"learning_rate": 4.9920422772926933e-05,
|
| 757 |
+
"loss": 0.5199,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.49884526558891457,
|
| 762 |
+
"grad_norm": 2.622856378555298,
|
| 763 |
+
"learning_rate": 4.991218651452114e-05,
|
| 764 |
+
"loss": 0.4928,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.5034642032332564,
|
| 769 |
+
"grad_norm": 2.660313844680786,
|
| 770 |
+
"learning_rate": 4.9903545502999014e-05,
|
| 771 |
+
"loss": 0.516,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.5080831408775982,
|
| 776 |
+
"grad_norm": 2.2060108184814453,
|
| 777 |
+
"learning_rate": 4.9894499878752744e-05,
|
| 778 |
+
"loss": 0.474,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.5127020785219399,
|
| 783 |
+
"grad_norm": 2.774624824523926,
|
| 784 |
+
"learning_rate": 4.988504978874835e-05,
|
| 785 |
+
"loss": 0.5053,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.5173210161662818,
|
| 790 |
+
"grad_norm": 2.0086095333099365,
|
| 791 |
+
"learning_rate": 4.987519538652326e-05,
|
| 792 |
+
"loss": 0.4478,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.5219399538106235,
|
| 797 |
+
"grad_norm": 2.7462918758392334,
|
| 798 |
+
"learning_rate": 4.986493683218386e-05,
|
| 799 |
+
"loss": 0.4872,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.5265588914549654,
|
| 804 |
+
"grad_norm": 2.2208642959594727,
|
| 805 |
+
"learning_rate": 4.985427429240286e-05,
|
| 806 |
+
"loss": 0.4617,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.5311778290993071,
|
| 811 |
+
"grad_norm": 3.3714964389801025,
|
| 812 |
+
"learning_rate": 4.984320794041662e-05,
|
| 813 |
+
"loss": 0.5293,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.535796766743649,
|
| 818 |
+
"grad_norm": 2.732804298400879,
|
| 819 |
+
"learning_rate": 4.98317379560223e-05,
|
| 820 |
+
"loss": 0.4582,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.5404157043879908,
|
| 825 |
+
"grad_norm": 3.4411492347717285,
|
| 826 |
+
"learning_rate": 4.981986452557495e-05,
|
| 827 |
+
"loss": 0.5359,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.5450346420323325,
|
| 832 |
+
"grad_norm": 2.5346171855926514,
|
| 833 |
+
"learning_rate": 4.9807587841984494e-05,
|
| 834 |
+
"loss": 0.438,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.5496535796766744,
|
| 839 |
+
"grad_norm": 2.068873882293701,
|
| 840 |
+
"learning_rate": 4.9794908104712586e-05,
|
| 841 |
+
"loss": 0.4541,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.5542725173210161,
|
| 846 |
+
"grad_norm": 3.7652342319488525,
|
| 847 |
+
"learning_rate": 4.978182551976939e-05,
|
| 848 |
+
"loss": 0.5372,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.558891454965358,
|
| 853 |
+
"grad_norm": 2.7133548259735107,
|
| 854 |
+
"learning_rate": 4.976834029971017e-05,
|
| 855 |
+
"loss": 0.4949,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.5635103926096998,
|
| 860 |
+
"grad_norm": 2.7093558311462402,
|
| 861 |
+
"learning_rate": 4.975445266363191e-05,
|
| 862 |
+
"loss": 0.4484,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.5681293302540416,
|
| 867 |
+
"grad_norm": 2.551117420196533,
|
| 868 |
+
"learning_rate": 4.974016283716974e-05,
|
| 869 |
+
"loss": 0.4865,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.5727482678983834,
|
| 874 |
+
"grad_norm": 3.5680108070373535,
|
| 875 |
+
"learning_rate": 4.9725471052493225e-05,
|
| 876 |
+
"loss": 0.512,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.5773672055427251,
|
| 881 |
+
"grad_norm": 3.1270763874053955,
|
| 882 |
+
"learning_rate": 4.9710377548302636e-05,
|
| 883 |
+
"loss": 0.4658,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.581986143187067,
|
| 888 |
+
"grad_norm": 2.7450294494628906,
|
| 889 |
+
"learning_rate": 4.9694882569825045e-05,
|
| 890 |
+
"loss": 0.5726,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.5866050808314087,
|
| 895 |
+
"grad_norm": 2.192270040512085,
|
| 896 |
+
"learning_rate": 4.967898636881039e-05,
|
| 897 |
+
"loss": 0.456,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.5912240184757506,
|
| 902 |
+
"grad_norm": 3.5508313179016113,
|
| 903 |
+
"learning_rate": 4.9662689203527304e-05,
|
| 904 |
+
"loss": 0.4363,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.5958429561200924,
|
| 909 |
+
"grad_norm": 3.789588212966919,
|
| 910 |
+
"learning_rate": 4.964599133875899e-05,
|
| 911 |
+
"loss": 0.3894,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.6004618937644342,
|
| 916 |
+
"grad_norm": 2.185136556625366,
|
| 917 |
+
"learning_rate": 4.9628893045798905e-05,
|
| 918 |
+
"loss": 0.4388,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.605080831408776,
|
| 923 |
+
"grad_norm": 3.9445693492889404,
|
| 924 |
+
"learning_rate": 4.961139460244631e-05,
|
| 925 |
+
"loss": 0.4761,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.6096997690531177,
|
| 930 |
+
"grad_norm": 2.027426242828369,
|
| 931 |
+
"learning_rate": 4.95934962930018e-05,
|
| 932 |
+
"loss": 0.4726,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.6143187066974596,
|
| 937 |
+
"grad_norm": 2.555227518081665,
|
| 938 |
+
"learning_rate": 4.957519840826268e-05,
|
| 939 |
+
"loss": 0.4546,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.6189376443418014,
|
| 944 |
+
"grad_norm": 3.800353765487671,
|
| 945 |
+
"learning_rate": 4.955650124551823e-05,
|
| 946 |
+
"loss": 0.4657,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.6235565819861432,
|
| 951 |
+
"grad_norm": 1.877545952796936,
|
| 952 |
+
"learning_rate": 4.953740510854485e-05,
|
| 953 |
+
"loss": 0.46,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.628175519630485,
|
| 958 |
+
"grad_norm": 2.205172538757324,
|
| 959 |
+
"learning_rate": 4.9517910307601204e-05,
|
| 960 |
+
"loss": 0.4845,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.6327944572748267,
|
| 965 |
+
"grad_norm": 4.207221031188965,
|
| 966 |
+
"learning_rate": 4.949801715942306e-05,
|
| 967 |
+
"loss": 0.4784,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.6374133949191686,
|
| 972 |
+
"grad_norm": 2.3010756969451904,
|
| 973 |
+
"learning_rate": 4.947772598721828e-05,
|
| 974 |
+
"loss": 0.4679,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.6420323325635104,
|
| 979 |
+
"grad_norm": 1.776963233947754,
|
| 980 |
+
"learning_rate": 4.9457037120661455e-05,
|
| 981 |
+
"loss": 0.4405,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.6466512702078522,
|
| 986 |
+
"grad_norm": 2.8734822273254395,
|
| 987 |
+
"learning_rate": 4.9435950895888604e-05,
|
| 988 |
+
"loss": 0.474,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.651270207852194,
|
| 993 |
+
"grad_norm": 3.049509286880493,
|
| 994 |
+
"learning_rate": 4.9414467655491695e-05,
|
| 995 |
+
"loss": 0.4334,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.6558891454965358,
|
| 1000 |
+
"grad_norm": 3.274083375930786,
|
| 1001 |
+
"learning_rate": 4.9392587748513105e-05,
|
| 1002 |
+
"loss": 0.4519,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.6605080831408776,
|
| 1007 |
+
"grad_norm": 2.149959087371826,
|
| 1008 |
+
"learning_rate": 4.937031153043991e-05,
|
| 1009 |
+
"loss": 0.4625,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.6651270207852193,
|
| 1014 |
+
"grad_norm": 2.3562982082366943,
|
| 1015 |
+
"learning_rate": 4.934763936319814e-05,
|
| 1016 |
+
"loss": 0.4487,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.6697459584295612,
|
| 1021 |
+
"grad_norm": 2.5950613021850586,
|
| 1022 |
+
"learning_rate": 4.932457161514689e-05,
|
| 1023 |
+
"loss": 0.4979,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.674364896073903,
|
| 1028 |
+
"grad_norm": 2.4045233726501465,
|
| 1029 |
+
"learning_rate": 4.9301108661072315e-05,
|
| 1030 |
+
"loss": 0.4442,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.6789838337182448,
|
| 1035 |
+
"grad_norm": 2.833594799041748,
|
| 1036 |
+
"learning_rate": 4.9277250882181575e-05,
|
| 1037 |
+
"loss": 0.4408,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.6836027713625866,
|
| 1042 |
+
"grad_norm": 1.7960981130599976,
|
| 1043 |
+
"learning_rate": 4.9252998666096625e-05,
|
| 1044 |
+
"loss": 0.4672,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.6882217090069284,
|
| 1049 |
+
"grad_norm": 2.261974811553955,
|
| 1050 |
+
"learning_rate": 4.922835240684792e-05,
|
| 1051 |
+
"loss": 0.3947,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.6928406466512702,
|
| 1056 |
+
"grad_norm": 2.966799020767212,
|
| 1057 |
+
"learning_rate": 4.9203312504867994e-05,
|
| 1058 |
+
"loss": 0.4546,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.6974595842956121,
|
| 1063 |
+
"grad_norm": 2.1086158752441406,
|
| 1064 |
+
"learning_rate": 4.9177879366984985e-05,
|
| 1065 |
+
"loss": 0.4226,
|
| 1066 |
+
"step": 1510
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.7020785219399538,
|
| 1070 |
+
"grad_norm": 2.4200305938720703,
|
| 1071 |
+
"learning_rate": 4.915205340641601e-05,
|
| 1072 |
+
"loss": 0.4481,
|
| 1073 |
+
"step": 1520
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.7066974595842956,
|
| 1077 |
+
"grad_norm": 2.486839771270752,
|
| 1078 |
+
"learning_rate": 4.912583504276045e-05,
|
| 1079 |
+
"loss": 0.4594,
|
| 1080 |
+
"step": 1530
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.7113163972286374,
|
| 1084 |
+
"grad_norm": 1.7007755041122437,
|
| 1085 |
+
"learning_rate": 4.9099224701993115e-05,
|
| 1086 |
+
"loss": 0.4472,
|
| 1087 |
+
"step": 1540
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.7159353348729792,
|
| 1091 |
+
"grad_norm": 1.6047892570495605,
|
| 1092 |
+
"learning_rate": 4.907222281645739e-05,
|
| 1093 |
+
"loss": 0.4734,
|
| 1094 |
+
"step": 1550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.7205542725173211,
|
| 1098 |
+
"grad_norm": 3.141820192337036,
|
| 1099 |
+
"learning_rate": 4.904482982485813e-05,
|
| 1100 |
+
"loss": 0.4777,
|
| 1101 |
+
"step": 1560
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.7251732101616628,
|
| 1105 |
+
"grad_norm": 2.6380691528320312,
|
| 1106 |
+
"learning_rate": 4.901704617225455e-05,
|
| 1107 |
+
"loss": 0.4438,
|
| 1108 |
+
"step": 1570
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.7297921478060047,
|
| 1112 |
+
"grad_norm": 2.238063335418701,
|
| 1113 |
+
"learning_rate": 4.898887231005306e-05,
|
| 1114 |
+
"loss": 0.4424,
|
| 1115 |
+
"step": 1580
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.7344110854503464,
|
| 1119 |
+
"grad_norm": 2.1911888122558594,
|
| 1120 |
+
"learning_rate": 4.896030869599983e-05,
|
| 1121 |
+
"loss": 0.437,
|
| 1122 |
+
"step": 1590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.7390300230946882,
|
| 1126 |
+
"grad_norm": 2.0892059803009033,
|
| 1127 |
+
"learning_rate": 4.893135579417345e-05,
|
| 1128 |
+
"loss": 0.4341,
|
| 1129 |
+
"step": 1600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.74364896073903,
|
| 1133 |
+
"grad_norm": 1.727277398109436,
|
| 1134 |
+
"learning_rate": 4.8902014074977295e-05,
|
| 1135 |
+
"loss": 0.4428,
|
| 1136 |
+
"step": 1610
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.7482678983833718,
|
| 1140 |
+
"grad_norm": 2.6759467124938965,
|
| 1141 |
+
"learning_rate": 4.8872284015131965e-05,
|
| 1142 |
+
"loss": 0.411,
|
| 1143 |
+
"step": 1620
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.7528868360277137,
|
| 1147 |
+
"grad_norm": 3.616370439529419,
|
| 1148 |
+
"learning_rate": 4.8842166097667505e-05,
|
| 1149 |
+
"loss": 0.4376,
|
| 1150 |
+
"step": 1630
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.7575057736720554,
|
| 1154 |
+
"grad_norm": 1.77035653591156,
|
| 1155 |
+
"learning_rate": 4.881166081191555e-05,
|
| 1156 |
+
"loss": 0.4217,
|
| 1157 |
+
"step": 1640
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.7621247113163973,
|
| 1161 |
+
"grad_norm": 2.7078516483306885,
|
| 1162 |
+
"learning_rate": 4.878076865350136e-05,
|
| 1163 |
+
"loss": 0.4451,
|
| 1164 |
+
"step": 1650
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.766743648960739,
|
| 1168 |
+
"grad_norm": 1.7627867460250854,
|
| 1169 |
+
"learning_rate": 4.874949012433584e-05,
|
| 1170 |
+
"loss": 0.4399,
|
| 1171 |
+
"step": 1660
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.7713625866050808,
|
| 1175 |
+
"grad_norm": 1.7273634672164917,
|
| 1176 |
+
"learning_rate": 4.871782573260729e-05,
|
| 1177 |
+
"loss": 0.4202,
|
| 1178 |
+
"step": 1670
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.7759815242494227,
|
| 1182 |
+
"grad_norm": 2.0963988304138184,
|
| 1183 |
+
"learning_rate": 4.868577599277322e-05,
|
| 1184 |
+
"loss": 0.4447,
|
| 1185 |
+
"step": 1680
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.7806004618937644,
|
| 1189 |
+
"grad_norm": 2.144355297088623,
|
| 1190 |
+
"learning_rate": 4.865334142555196e-05,
|
| 1191 |
+
"loss": 0.4387,
|
| 1192 |
+
"step": 1690
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.7852193995381063,
|
| 1196 |
+
"grad_norm": 2.0202884674072266,
|
| 1197 |
+
"learning_rate": 4.862052255791419e-05,
|
| 1198 |
+
"loss": 0.4124,
|
| 1199 |
+
"step": 1700
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.789838337182448,
|
| 1203 |
+
"grad_norm": 1.6518304347991943,
|
| 1204 |
+
"learning_rate": 4.858731992307441e-05,
|
| 1205 |
+
"loss": 0.4222,
|
| 1206 |
+
"step": 1710
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.7944572748267898,
|
| 1210 |
+
"grad_norm": 1.3399207592010498,
|
| 1211 |
+
"learning_rate": 4.855373406048226e-05,
|
| 1212 |
+
"loss": 0.4713,
|
| 1213 |
+
"step": 1720
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.7990762124711316,
|
| 1217 |
+
"grad_norm": 1.7980890274047852,
|
| 1218 |
+
"learning_rate": 4.8519765515813744e-05,
|
| 1219 |
+
"loss": 0.4484,
|
| 1220 |
+
"step": 1730
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.8036951501154734,
|
| 1224 |
+
"grad_norm": 3.4402995109558105,
|
| 1225 |
+
"learning_rate": 4.8485414840962384e-05,
|
| 1226 |
+
"loss": 0.3777,
|
| 1227 |
+
"step": 1740
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.8083140877598153,
|
| 1231 |
+
"grad_norm": 1.9399069547653198,
|
| 1232 |
+
"learning_rate": 4.845068259403024e-05,
|
| 1233 |
+
"loss": 0.3942,
|
| 1234 |
+
"step": 1750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.812933025404157,
|
| 1238 |
+
"grad_norm": 1.8960610628128052,
|
| 1239 |
+
"learning_rate": 4.841556933931886e-05,
|
| 1240 |
+
"loss": 0.3738,
|
| 1241 |
+
"step": 1760
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.8175519630484989,
|
| 1245 |
+
"grad_norm": 2.6203131675720215,
|
| 1246 |
+
"learning_rate": 4.838007564732008e-05,
|
| 1247 |
+
"loss": 0.4725,
|
| 1248 |
+
"step": 1770
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.8221709006928406,
|
| 1252 |
+
"grad_norm": 2.441143274307251,
|
| 1253 |
+
"learning_rate": 4.834420209470679e-05,
|
| 1254 |
+
"loss": 0.4287,
|
| 1255 |
+
"step": 1780
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.8267898383371824,
|
| 1259 |
+
"grad_norm": 3.31255841255188,
|
| 1260 |
+
"learning_rate": 4.830794926432355e-05,
|
| 1261 |
+
"loss": 0.4215,
|
| 1262 |
+
"step": 1790
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.8314087759815243,
|
| 1266 |
+
"grad_norm": 2.7491471767425537,
|
| 1267 |
+
"learning_rate": 4.827131774517709e-05,
|
| 1268 |
+
"loss": 0.4301,
|
| 1269 |
+
"step": 1800
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.836027713625866,
|
| 1273 |
+
"grad_norm": 1.9549751281738281,
|
| 1274 |
+
"learning_rate": 4.8234308132426807e-05,
|
| 1275 |
+
"loss": 0.4379,
|
| 1276 |
+
"step": 1810
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.8406466512702079,
|
| 1280 |
+
"grad_norm": 2.4840948581695557,
|
| 1281 |
+
"learning_rate": 4.819692102737505e-05,
|
| 1282 |
+
"loss": 0.4474,
|
| 1283 |
+
"step": 1820
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.8452655889145496,
|
| 1287 |
+
"grad_norm": 2.865260601043701,
|
| 1288 |
+
"learning_rate": 4.815915703745734e-05,
|
| 1289 |
+
"loss": 0.4608,
|
| 1290 |
+
"step": 1830
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.8498845265588915,
|
| 1294 |
+
"grad_norm": 2.3620669841766357,
|
| 1295 |
+
"learning_rate": 4.812101677623254e-05,
|
| 1296 |
+
"loss": 0.4311,
|
| 1297 |
+
"step": 1840
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.8545034642032333,
|
| 1301 |
+
"grad_norm": 3.4287946224212646,
|
| 1302 |
+
"learning_rate": 4.808250086337284e-05,
|
| 1303 |
+
"loss": 0.4035,
|
| 1304 |
+
"step": 1850
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.859122401847575,
|
| 1308 |
+
"grad_norm": 1.6560109853744507,
|
| 1309 |
+
"learning_rate": 4.8043609924653745e-05,
|
| 1310 |
+
"loss": 0.4004,
|
| 1311 |
+
"step": 1860
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.8637413394919169,
|
| 1315 |
+
"grad_norm": 2.310784339904785,
|
| 1316 |
+
"learning_rate": 4.800434459194386e-05,
|
| 1317 |
+
"loss": 0.4219,
|
| 1318 |
+
"step": 1870
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.8683602771362586,
|
| 1322 |
+
"grad_norm": 1.660062313079834,
|
| 1323 |
+
"learning_rate": 4.796470550319465e-05,
|
| 1324 |
+
"loss": 0.4102,
|
| 1325 |
+
"step": 1880
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.8729792147806005,
|
| 1329 |
+
"grad_norm": 2.578974723815918,
|
| 1330 |
+
"learning_rate": 4.792469330243007e-05,
|
| 1331 |
+
"loss": 0.4375,
|
| 1332 |
+
"step": 1890
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.8775981524249422,
|
| 1336 |
+
"grad_norm": 2.095388412475586,
|
| 1337 |
+
"learning_rate": 4.788430863973607e-05,
|
| 1338 |
+
"loss": 0.4385,
|
| 1339 |
+
"step": 1900
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.8822170900692841,
|
| 1343 |
+
"grad_norm": 2.4962880611419678,
|
| 1344 |
+
"learning_rate": 4.7843552171250085e-05,
|
| 1345 |
+
"loss": 0.4399,
|
| 1346 |
+
"step": 1910
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.8868360277136259,
|
| 1350 |
+
"grad_norm": 2.8000426292419434,
|
| 1351 |
+
"learning_rate": 4.780242455915036e-05,
|
| 1352 |
+
"loss": 0.4344,
|
| 1353 |
+
"step": 1920
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.8914549653579676,
|
| 1357 |
+
"grad_norm": 2.0987462997436523,
|
| 1358 |
+
"learning_rate": 4.776092647164516e-05,
|
| 1359 |
+
"loss": 0.3961,
|
| 1360 |
+
"step": 1930
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.8960739030023095,
|
| 1364 |
+
"grad_norm": 3.531191825866699,
|
| 1365 |
+
"learning_rate": 4.771905858296195e-05,
|
| 1366 |
+
"loss": 0.4463,
|
| 1367 |
+
"step": 1940
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.9006928406466512,
|
| 1371 |
+
"grad_norm": 2.8484129905700684,
|
| 1372 |
+
"learning_rate": 4.767682157333643e-05,
|
| 1373 |
+
"loss": 0.4993,
|
| 1374 |
+
"step": 1950
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.9053117782909931,
|
| 1378 |
+
"grad_norm": 2.164492607116699,
|
| 1379 |
+
"learning_rate": 4.7634216129001453e-05,
|
| 1380 |
+
"loss": 0.4545,
|
| 1381 |
+
"step": 1960
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.9099307159353349,
|
| 1385 |
+
"grad_norm": 2.37625789642334,
|
| 1386 |
+
"learning_rate": 4.7591242942175924e-05,
|
| 1387 |
+
"loss": 0.3965,
|
| 1388 |
+
"step": 1970
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.9145496535796767,
|
| 1392 |
+
"grad_norm": 2.488903284072876,
|
| 1393 |
+
"learning_rate": 4.7547902711053535e-05,
|
| 1394 |
+
"loss": 0.4459,
|
| 1395 |
+
"step": 1980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.9191685912240185,
|
| 1399 |
+
"grad_norm": 3.028672933578491,
|
| 1400 |
+
"learning_rate": 4.7504196139791405e-05,
|
| 1401 |
+
"loss": 0.452,
|
| 1402 |
+
"step": 1990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.9237875288683602,
|
| 1406 |
+
"grad_norm": 2.084078073501587,
|
| 1407 |
+
"learning_rate": 4.746012393849866e-05,
|
| 1408 |
+
"loss": 0.4078,
|
| 1409 |
+
"step": 2000
|
| 1410 |
+
}
|
| 1411 |
+
],
|
| 1412 |
+
"logging_steps": 10,
|
| 1413 |
+
"max_steps": 8660,
|
| 1414 |
+
"num_input_tokens_seen": 0,
|
| 1415 |
+
"num_train_epochs": 4,
|
| 1416 |
+
"save_steps": 500,
|
| 1417 |
+
"stateful_callbacks": {
|
| 1418 |
+
"TrainerControl": {
|
| 1419 |
+
"args": {
|
| 1420 |
+
"should_epoch_stop": false,
|
| 1421 |
+
"should_evaluate": false,
|
| 1422 |
+
"should_log": false,
|
| 1423 |
+
"should_save": true,
|
| 1424 |
+
"should_training_stop": false
|
| 1425 |
+
},
|
| 1426 |
+
"attributes": {}
|
| 1427 |
+
}
|
| 1428 |
+
},
|
| 1429 |
+
"total_flos": 5.4846778836097434e+17,
|
| 1430 |
+
"train_batch_size": 1,
|
| 1431 |
+
"trial_name": null,
|
| 1432 |
+
"trial_params": null
|
| 1433 |
+
}
|
checkpoint-2000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3759d15eeba226e23a6befbba0a7c35a73e6f4c92500ed4ddd24b6c972af08e7
|
| 3 |
+
size 5368
|
checkpoint-2500/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: /root/autodl-tmp/models/Mistral-7B-Instruct-v0.2
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.11.1
|
checkpoint-2500/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/root/autodl-tmp/models/Mistral-7B-Instruct-v0.2",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"gate_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
+
"up_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"down_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-2500/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2f61086fcbe1aca812632fb52cc0220794762672baa47e9475ec5643aabf8a6
|
| 3 |
+
size 167832240
|
checkpoint-2500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a57dce67242cce34123388b9c5dea7df3f8a6d3e726579e2a92c095ff0bda75b
|
| 3 |
+
size 335922386
|
checkpoint-2500/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bbe0d720c4c75a6a04213fa3b64bacbe794718a53e2b56ebb67a1a795014dfad
|
| 3 |
+
size 15024
|