Commit
•
ed94ae7
1
Parent(s):
01dfada
Upload 12 files
Browse files- README.md +202 -0
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
- trainer_state.json +3461 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: mistralai/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 0.9.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 64,
|
| 13 |
+
"lora_dropout": 0.05,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 32,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"k_proj",
|
| 23 |
+
"v_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"lm_head",
|
| 26 |
+
"q_proj"
|
| 27 |
+
],
|
| 28 |
+
"task_type": "CAUSAL_LM",
|
| 29 |
+
"use_dora": false,
|
| 30 |
+
"use_rslora": false
|
| 31 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:654149890d38e918b7f5a6d4a802e31ee4daba060f3d957b3f0626b93c0b9bf2
|
| 3 |
+
size 373540904
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:464b5e9e4f8837e80679960f66f248464c05d31fdf6df305fc10ca80acc73ac0
|
| 3 |
+
size 222941370
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4489f567d09435d07c31f877076c234e80ddf940d0c62468fd8249c682d4543
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9eedbcb65caa7c8006c723f97f303ecf341c9f945d5a94fd23c213880b4a861f
|
| 3 |
+
size 1064
|
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 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% 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 |
+
"sp_model_kwargs": {},
|
| 39 |
+
"spaces_between_special_tokens": false,
|
| 40 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 41 |
+
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": false
|
| 43 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3461 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.7583963425356075,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 40000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"grad_norm": 1.3358560800552368,
|
| 14 |
+
"learning_rate": 2.9999642387366694e-06,
|
| 15 |
+
"loss": 1.8182,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01,
|
| 20 |
+
"grad_norm": 1.0696768760681152,
|
| 21 |
+
"learning_rate": 2.999856956651834e-06,
|
| 22 |
+
"loss": 1.5829,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"grad_norm": 1.1315983533859253,
|
| 28 |
+
"learning_rate": 2.9996781588608853e-06,
|
| 29 |
+
"loss": 1.5088,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.02,
|
| 34 |
+
"grad_norm": 1.2688828706741333,
|
| 35 |
+
"learning_rate": 2.9994278538892026e-06,
|
| 36 |
+
"loss": 1.4755,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"grad_norm": 1.3950492143630981,
|
| 42 |
+
"learning_rate": 2.999106053671749e-06,
|
| 43 |
+
"loss": 1.44,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.02,
|
| 48 |
+
"eval_loss": 1.4453312158584595,
|
| 49 |
+
"eval_runtime": 1866.1237,
|
| 50 |
+
"eval_samples_per_second": 5.137,
|
| 51 |
+
"eval_steps_per_second": 0.643,
|
| 52 |
+
"step": 500
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.03,
|
| 56 |
+
"grad_norm": 1.4245915412902832,
|
| 57 |
+
"learning_rate": 2.9987127735525e-06,
|
| 58 |
+
"loss": 1.428,
|
| 59 |
+
"step": 600
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.03,
|
| 63 |
+
"grad_norm": 1.3934013843536377,
|
| 64 |
+
"learning_rate": 2.9982480322837146e-06,
|
| 65 |
+
"loss": 1.4205,
|
| 66 |
+
"step": 700
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.04,
|
| 70 |
+
"grad_norm": 1.345449447631836,
|
| 71 |
+
"learning_rate": 2.99771185202504e-06,
|
| 72 |
+
"loss": 1.4117,
|
| 73 |
+
"step": 800
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.04,
|
| 77 |
+
"grad_norm": 1.4815948009490967,
|
| 78 |
+
"learning_rate": 2.9971042583424534e-06,
|
| 79 |
+
"loss": 1.4029,
|
| 80 |
+
"step": 900
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.04,
|
| 84 |
+
"grad_norm": 1.416758418083191,
|
| 85 |
+
"learning_rate": 2.996425280207045e-06,
|
| 86 |
+
"loss": 1.4103,
|
| 87 |
+
"step": 1000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.04,
|
| 91 |
+
"eval_loss": 1.4033704996109009,
|
| 92 |
+
"eval_runtime": 1866.432,
|
| 93 |
+
"eval_samples_per_second": 5.136,
|
| 94 |
+
"eval_steps_per_second": 0.642,
|
| 95 |
+
"step": 1000
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.05,
|
| 99 |
+
"grad_norm": 1.5439317226409912,
|
| 100 |
+
"learning_rate": 2.995674949993636e-06,
|
| 101 |
+
"loss": 1.3992,
|
| 102 |
+
"step": 1100
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.05,
|
| 106 |
+
"grad_norm": 1.6817480325698853,
|
| 107 |
+
"learning_rate": 2.9948533034792356e-06,
|
| 108 |
+
"loss": 1.3857,
|
| 109 |
+
"step": 1200
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.06,
|
| 113 |
+
"grad_norm": 1.5548583269119263,
|
| 114 |
+
"learning_rate": 2.993960379841333e-06,
|
| 115 |
+
"loss": 1.3889,
|
| 116 |
+
"step": 1300
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.06,
|
| 120 |
+
"grad_norm": 1.800005316734314,
|
| 121 |
+
"learning_rate": 2.992996221656031e-06,
|
| 122 |
+
"loss": 1.3798,
|
| 123 |
+
"step": 1400
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.07,
|
| 127 |
+
"grad_norm": 1.5900113582611084,
|
| 128 |
+
"learning_rate": 2.9919608748960165e-06,
|
| 129 |
+
"loss": 1.3915,
|
| 130 |
+
"step": 1500
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.07,
|
| 134 |
+
"eval_loss": 1.3856122493743896,
|
| 135 |
+
"eval_runtime": 1867.7341,
|
| 136 |
+
"eval_samples_per_second": 5.132,
|
| 137 |
+
"eval_steps_per_second": 0.642,
|
| 138 |
+
"step": 1500
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.07,
|
| 142 |
+
"grad_norm": 1.593215823173523,
|
| 143 |
+
"learning_rate": 2.990854388928367e-06,
|
| 144 |
+
"loss": 1.3707,
|
| 145 |
+
"step": 1600
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.07,
|
| 149 |
+
"grad_norm": 1.6342238187789917,
|
| 150 |
+
"learning_rate": 2.9896768165121967e-06,
|
| 151 |
+
"loss": 1.3909,
|
| 152 |
+
"step": 1700
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.08,
|
| 156 |
+
"grad_norm": 1.7908762693405151,
|
| 157 |
+
"learning_rate": 2.9884282137961426e-06,
|
| 158 |
+
"loss": 1.3758,
|
| 159 |
+
"step": 1800
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.08,
|
| 163 |
+
"grad_norm": 1.5925847291946411,
|
| 164 |
+
"learning_rate": 2.987108640315685e-06,
|
| 165 |
+
"loss": 1.3816,
|
| 166 |
+
"step": 1900
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.09,
|
| 170 |
+
"grad_norm": 1.8841816186904907,
|
| 171 |
+
"learning_rate": 2.9857181589903103e-06,
|
| 172 |
+
"loss": 1.383,
|
| 173 |
+
"step": 2000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.09,
|
| 177 |
+
"eval_loss": 1.3752671480178833,
|
| 178 |
+
"eval_runtime": 1867.3688,
|
| 179 |
+
"eval_samples_per_second": 5.133,
|
| 180 |
+
"eval_steps_per_second": 0.642,
|
| 181 |
+
"step": 2000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.09,
|
| 185 |
+
"grad_norm": 1.688745379447937,
|
| 186 |
+
"learning_rate": 2.984256836120511e-06,
|
| 187 |
+
"loss": 1.3796,
|
| 188 |
+
"step": 2100
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.1,
|
| 192 |
+
"grad_norm": 1.676340103149414,
|
| 193 |
+
"learning_rate": 2.9827247413846217e-06,
|
| 194 |
+
"loss": 1.3742,
|
| 195 |
+
"step": 2200
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.1,
|
| 199 |
+
"grad_norm": 2.0635907649993896,
|
| 200 |
+
"learning_rate": 2.981121947835501e-06,
|
| 201 |
+
"loss": 1.3712,
|
| 202 |
+
"step": 2300
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.11,
|
| 206 |
+
"grad_norm": 1.799085021018982,
|
| 207 |
+
"learning_rate": 2.979448531897045e-06,
|
| 208 |
+
"loss": 1.3694,
|
| 209 |
+
"step": 2400
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.11,
|
| 213 |
+
"grad_norm": 1.8315014839172363,
|
| 214 |
+
"learning_rate": 2.9777045733605437e-06,
|
| 215 |
+
"loss": 1.3558,
|
| 216 |
+
"step": 2500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.11,
|
| 220 |
+
"eval_loss": 1.3671655654907227,
|
| 221 |
+
"eval_runtime": 1867.272,
|
| 222 |
+
"eval_samples_per_second": 5.134,
|
| 223 |
+
"eval_steps_per_second": 0.642,
|
| 224 |
+
"step": 2500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.11,
|
| 228 |
+
"grad_norm": 1.8167532682418823,
|
| 229 |
+
"learning_rate": 2.9758901553808787e-06,
|
| 230 |
+
"loss": 1.3579,
|
| 231 |
+
"step": 2600
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.12,
|
| 235 |
+
"grad_norm": 1.8836266994476318,
|
| 236 |
+
"learning_rate": 2.9740053644725552e-06,
|
| 237 |
+
"loss": 1.3714,
|
| 238 |
+
"step": 2700
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.12,
|
| 242 |
+
"grad_norm": 1.823400855064392,
|
| 243 |
+
"learning_rate": 2.972050290505579e-06,
|
| 244 |
+
"loss": 1.3609,
|
| 245 |
+
"step": 2800
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.13,
|
| 249 |
+
"grad_norm": 1.8716390132904053,
|
| 250 |
+
"learning_rate": 2.970025026701169e-06,
|
| 251 |
+
"loss": 1.3685,
|
| 252 |
+
"step": 2900
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.13,
|
| 256 |
+
"grad_norm": 1.7368168830871582,
|
| 257 |
+
"learning_rate": 2.967929669627316e-06,
|
| 258 |
+
"loss": 1.3665,
|
| 259 |
+
"step": 3000
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.13,
|
| 263 |
+
"eval_loss": 1.3610810041427612,
|
| 264 |
+
"eval_runtime": 1867.7829,
|
| 265 |
+
"eval_samples_per_second": 5.132,
|
| 266 |
+
"eval_steps_per_second": 0.642,
|
| 267 |
+
"step": 3000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.14,
|
| 271 |
+
"grad_norm": 1.8250432014465332,
|
| 272 |
+
"learning_rate": 2.9657643191941737e-06,
|
| 273 |
+
"loss": 1.3549,
|
| 274 |
+
"step": 3100
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.14,
|
| 278 |
+
"grad_norm": 1.9420477151870728,
|
| 279 |
+
"learning_rate": 2.9635290786492985e-06,
|
| 280 |
+
"loss": 1.3531,
|
| 281 |
+
"step": 3200
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.15,
|
| 285 |
+
"grad_norm": 2.0373518466949463,
|
| 286 |
+
"learning_rate": 2.9612240545727255e-06,
|
| 287 |
+
"loss": 1.3619,
|
| 288 |
+
"step": 3300
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.15,
|
| 292 |
+
"grad_norm": 1.9139854907989502,
|
| 293 |
+
"learning_rate": 2.9588493568718843e-06,
|
| 294 |
+
"loss": 1.3665,
|
| 295 |
+
"step": 3400
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.15,
|
| 299 |
+
"grad_norm": 1.9374817609786987,
|
| 300 |
+
"learning_rate": 2.9564050987763614e-06,
|
| 301 |
+
"loss": 1.3619,
|
| 302 |
+
"step": 3500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.15,
|
| 306 |
+
"eval_loss": 1.3560757637023926,
|
| 307 |
+
"eval_runtime": 1867.3981,
|
| 308 |
+
"eval_samples_per_second": 5.133,
|
| 309 |
+
"eval_steps_per_second": 0.642,
|
| 310 |
+
"step": 3500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.16,
|
| 314 |
+
"grad_norm": 1.8168325424194336,
|
| 315 |
+
"learning_rate": 2.9538913968325007e-06,
|
| 316 |
+
"loss": 1.3527,
|
| 317 |
+
"step": 3600
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.16,
|
| 321 |
+
"grad_norm": 1.948146939277649,
|
| 322 |
+
"learning_rate": 2.951308370897845e-06,
|
| 323 |
+
"loss": 1.3496,
|
| 324 |
+
"step": 3700
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.17,
|
| 328 |
+
"grad_norm": 2.068612575531006,
|
| 329 |
+
"learning_rate": 2.948656144135421e-06,
|
| 330 |
+
"loss": 1.358,
|
| 331 |
+
"step": 3800
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.17,
|
| 335 |
+
"grad_norm": 1.9631004333496094,
|
| 336 |
+
"learning_rate": 2.945934843007869e-06,
|
| 337 |
+
"loss": 1.3504,
|
| 338 |
+
"step": 3900
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.18,
|
| 342 |
+
"grad_norm": 2.0034778118133545,
|
| 343 |
+
"learning_rate": 2.9431445972714102e-06,
|
| 344 |
+
"loss": 1.3582,
|
| 345 |
+
"step": 4000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.18,
|
| 349 |
+
"eval_loss": 1.3521347045898438,
|
| 350 |
+
"eval_runtime": 1867.5478,
|
| 351 |
+
"eval_samples_per_second": 5.133,
|
| 352 |
+
"eval_steps_per_second": 0.642,
|
| 353 |
+
"step": 4000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.18,
|
| 357 |
+
"grad_norm": 1.872603178024292,
|
| 358 |
+
"learning_rate": 2.940285539969662e-06,
|
| 359 |
+
"loss": 1.3483,
|
| 360 |
+
"step": 4100
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.18,
|
| 364 |
+
"grad_norm": 1.8477139472961426,
|
| 365 |
+
"learning_rate": 2.9373578074272917e-06,
|
| 366 |
+
"loss": 1.3623,
|
| 367 |
+
"step": 4200
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.19,
|
| 371 |
+
"grad_norm": 2.0872058868408203,
|
| 372 |
+
"learning_rate": 2.9343615392435187e-06,
|
| 373 |
+
"loss": 1.3483,
|
| 374 |
+
"step": 4300
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.19,
|
| 378 |
+
"grad_norm": 1.931931495666504,
|
| 379 |
+
"learning_rate": 2.931296878285457e-06,
|
| 380 |
+
"loss": 1.3499,
|
| 381 |
+
"step": 4400
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.2,
|
| 385 |
+
"grad_norm": 1.9555952548980713,
|
| 386 |
+
"learning_rate": 2.928163970681304e-06,
|
| 387 |
+
"loss": 1.3525,
|
| 388 |
+
"step": 4500
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.2,
|
| 392 |
+
"eval_loss": 1.348177433013916,
|
| 393 |
+
"eval_runtime": 1865.9442,
|
| 394 |
+
"eval_samples_per_second": 5.137,
|
| 395 |
+
"eval_steps_per_second": 0.643,
|
| 396 |
+
"step": 4500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.2,
|
| 400 |
+
"grad_norm": 1.9107462167739868,
|
| 401 |
+
"learning_rate": 2.9249629658133703e-06,
|
| 402 |
+
"loss": 1.3446,
|
| 403 |
+
"step": 4600
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.21,
|
| 407 |
+
"grad_norm": 2.1549768447875977,
|
| 408 |
+
"learning_rate": 2.9216940163109613e-06,
|
| 409 |
+
"loss": 1.3485,
|
| 410 |
+
"step": 4700
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.21,
|
| 414 |
+
"grad_norm": 1.9788259267807007,
|
| 415 |
+
"learning_rate": 2.9183572780430938e-06,
|
| 416 |
+
"loss": 1.3386,
|
| 417 |
+
"step": 4800
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.22,
|
| 421 |
+
"grad_norm": 2.008772850036621,
|
| 422 |
+
"learning_rate": 2.9149529101110707e-06,
|
| 423 |
+
"loss": 1.3449,
|
| 424 |
+
"step": 4900
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.22,
|
| 428 |
+
"grad_norm": 1.932020664215088,
|
| 429 |
+
"learning_rate": 2.9114810748408887e-06,
|
| 430 |
+
"loss": 1.3471,
|
| 431 |
+
"step": 5000
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.22,
|
| 435 |
+
"eval_loss": 1.3448920249938965,
|
| 436 |
+
"eval_runtime": 1866.903,
|
| 437 |
+
"eval_samples_per_second": 5.135,
|
| 438 |
+
"eval_steps_per_second": 0.642,
|
| 439 |
+
"step": 5000
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.22,
|
| 443 |
+
"grad_norm": 1.780934453010559,
|
| 444 |
+
"learning_rate": 2.9079419377755016e-06,
|
| 445 |
+
"loss": 1.3408,
|
| 446 |
+
"step": 5100
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.23,
|
| 450 |
+
"grad_norm": 2.0991992950439453,
|
| 451 |
+
"learning_rate": 2.904335667666926e-06,
|
| 452 |
+
"loss": 1.3377,
|
| 453 |
+
"step": 5200
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.23,
|
| 457 |
+
"grad_norm": 1.7961390018463135,
|
| 458 |
+
"learning_rate": 2.9006624364681955e-06,
|
| 459 |
+
"loss": 1.3446,
|
| 460 |
+
"step": 5300
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.24,
|
| 464 |
+
"grad_norm": 1.951217770576477,
|
| 465 |
+
"learning_rate": 2.896922419325161e-06,
|
| 466 |
+
"loss": 1.3434,
|
| 467 |
+
"step": 5400
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.24,
|
| 471 |
+
"grad_norm": 1.9937087297439575,
|
| 472 |
+
"learning_rate": 2.89311579456814e-06,
|
| 473 |
+
"loss": 1.3383,
|
| 474 |
+
"step": 5500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.24,
|
| 478 |
+
"eval_loss": 1.3420648574829102,
|
| 479 |
+
"eval_runtime": 1864.5499,
|
| 480 |
+
"eval_samples_per_second": 5.141,
|
| 481 |
+
"eval_steps_per_second": 0.643,
|
| 482 |
+
"step": 5500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.25,
|
| 486 |
+
"grad_norm": 1.9863967895507812,
|
| 487 |
+
"learning_rate": 2.889242743703412e-06,
|
| 488 |
+
"loss": 1.3553,
|
| 489 |
+
"step": 5600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.25,
|
| 493 |
+
"grad_norm": 2.026629686355591,
|
| 494 |
+
"learning_rate": 2.8853034514045667e-06,
|
| 495 |
+
"loss": 1.3384,
|
| 496 |
+
"step": 5700
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.25,
|
| 500 |
+
"grad_norm": 2.1524720191955566,
|
| 501 |
+
"learning_rate": 2.8812981055036967e-06,
|
| 502 |
+
"loss": 1.339,
|
| 503 |
+
"step": 5800
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.26,
|
| 507 |
+
"grad_norm": 2.011669635772705,
|
| 508 |
+
"learning_rate": 2.8772268969824412e-06,
|
| 509 |
+
"loss": 1.3449,
|
| 510 |
+
"step": 5900
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.26,
|
| 514 |
+
"grad_norm": 1.96876060962677,
|
| 515 |
+
"learning_rate": 2.87309001996288e-06,
|
| 516 |
+
"loss": 1.3352,
|
| 517 |
+
"step": 6000
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.26,
|
| 521 |
+
"eval_loss": 1.3392791748046875,
|
| 522 |
+
"eval_runtime": 1863.5996,
|
| 523 |
+
"eval_samples_per_second": 5.144,
|
| 524 |
+
"eval_steps_per_second": 0.643,
|
| 525 |
+
"step": 6000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.27,
|
| 529 |
+
"grad_norm": 2.030050754547119,
|
| 530 |
+
"learning_rate": 2.868887671698278e-06,
|
| 531 |
+
"loss": 1.3473,
|
| 532 |
+
"step": 6100
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.27,
|
| 536 |
+
"grad_norm": 1.9417366981506348,
|
| 537 |
+
"learning_rate": 2.8646200525636784e-06,
|
| 538 |
+
"loss": 1.3467,
|
| 539 |
+
"step": 6200
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.28,
|
| 543 |
+
"grad_norm": 1.8963119983673096,
|
| 544 |
+
"learning_rate": 2.860287366046351e-06,
|
| 545 |
+
"loss": 1.3298,
|
| 546 |
+
"step": 6300
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.28,
|
| 550 |
+
"grad_norm": 2.0446488857269287,
|
| 551 |
+
"learning_rate": 2.855889818736086e-06,
|
| 552 |
+
"loss": 1.3364,
|
| 553 |
+
"step": 6400
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.29,
|
| 557 |
+
"grad_norm": 1.9520761966705322,
|
| 558 |
+
"learning_rate": 2.8514276203153476e-06,
|
| 559 |
+
"loss": 1.3328,
|
| 560 |
+
"step": 6500
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.29,
|
| 564 |
+
"eval_loss": 1.3369933366775513,
|
| 565 |
+
"eval_runtime": 1864.5392,
|
| 566 |
+
"eval_samples_per_second": 5.141,
|
| 567 |
+
"eval_steps_per_second": 0.643,
|
| 568 |
+
"step": 6500
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.29,
|
| 572 |
+
"grad_norm": 1.9833135604858398,
|
| 573 |
+
"learning_rate": 2.846900983549272e-06,
|
| 574 |
+
"loss": 1.3461,
|
| 575 |
+
"step": 6600
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.29,
|
| 579 |
+
"grad_norm": 1.8837144374847412,
|
| 580 |
+
"learning_rate": 2.8423101242755264e-06,
|
| 581 |
+
"loss": 1.3354,
|
| 582 |
+
"step": 6700
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.3,
|
| 586 |
+
"grad_norm": 1.9261667728424072,
|
| 587 |
+
"learning_rate": 2.837655261394013e-06,
|
| 588 |
+
"loss": 1.3349,
|
| 589 |
+
"step": 6800
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.3,
|
| 593 |
+
"grad_norm": 1.8928134441375732,
|
| 594 |
+
"learning_rate": 2.832936616856434e-06,
|
| 595 |
+
"loss": 1.3247,
|
| 596 |
+
"step": 6900
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.31,
|
| 600 |
+
"grad_norm": 2.0842361450195312,
|
| 601 |
+
"learning_rate": 2.828154415655711e-06,
|
| 602 |
+
"loss": 1.3396,
|
| 603 |
+
"step": 7000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.31,
|
| 607 |
+
"eval_loss": 1.3346595764160156,
|
| 608 |
+
"eval_runtime": 1864.6191,
|
| 609 |
+
"eval_samples_per_second": 5.141,
|
| 610 |
+
"eval_steps_per_second": 0.643,
|
| 611 |
+
"step": 7000
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.31,
|
| 615 |
+
"grad_norm": 2.0268609523773193,
|
| 616 |
+
"learning_rate": 2.823308885815251e-06,
|
| 617 |
+
"loss": 1.3577,
|
| 618 |
+
"step": 7100
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.32,
|
| 622 |
+
"grad_norm": 1.9914246797561646,
|
| 623 |
+
"learning_rate": 2.8184002583780802e-06,
|
| 624 |
+
"loss": 1.3273,
|
| 625 |
+
"step": 7200
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.32,
|
| 629 |
+
"grad_norm": 2.065075159072876,
|
| 630 |
+
"learning_rate": 2.813428767395822e-06,
|
| 631 |
+
"loss": 1.3449,
|
| 632 |
+
"step": 7300
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.33,
|
| 636 |
+
"grad_norm": 2.0914437770843506,
|
| 637 |
+
"learning_rate": 2.8083946499175413e-06,
|
| 638 |
+
"loss": 1.3415,
|
| 639 |
+
"step": 7400
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.33,
|
| 643 |
+
"grad_norm": 1.9424386024475098,
|
| 644 |
+
"learning_rate": 2.803298145978439e-06,
|
| 645 |
+
"loss": 1.3316,
|
| 646 |
+
"step": 7500
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.33,
|
| 650 |
+
"eval_loss": 1.3324897289276123,
|
| 651 |
+
"eval_runtime": 1864.3018,
|
| 652 |
+
"eval_samples_per_second": 5.142,
|
| 653 |
+
"eval_steps_per_second": 0.643,
|
| 654 |
+
"step": 7500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.33,
|
| 658 |
+
"grad_norm": 2.083033561706543,
|
| 659 |
+
"learning_rate": 2.7981394985884074e-06,
|
| 660 |
+
"loss": 1.3213,
|
| 661 |
+
"step": 7600
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.34,
|
| 665 |
+
"grad_norm": 1.8912067413330078,
|
| 666 |
+
"learning_rate": 2.792918953720444e-06,
|
| 667 |
+
"loss": 1.3284,
|
| 668 |
+
"step": 7700
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.34,
|
| 672 |
+
"grad_norm": 1.8995610475540161,
|
| 673 |
+
"learning_rate": 2.7876367602989206e-06,
|
| 674 |
+
"loss": 1.3256,
|
| 675 |
+
"step": 7800
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.35,
|
| 679 |
+
"grad_norm": 1.9921075105667114,
|
| 680 |
+
"learning_rate": 2.7822931701877186e-06,
|
| 681 |
+
"loss": 1.3339,
|
| 682 |
+
"step": 7900
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.35,
|
| 686 |
+
"grad_norm": 1.9593900442123413,
|
| 687 |
+
"learning_rate": 2.7768884381782147e-06,
|
| 688 |
+
"loss": 1.3357,
|
| 689 |
+
"step": 8000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.35,
|
| 693 |
+
"eval_loss": 1.3304702043533325,
|
| 694 |
+
"eval_runtime": 1863.8735,
|
| 695 |
+
"eval_samples_per_second": 5.143,
|
| 696 |
+
"eval_steps_per_second": 0.643,
|
| 697 |
+
"step": 8000
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.36,
|
| 701 |
+
"grad_norm": 2.0294156074523926,
|
| 702 |
+
"learning_rate": 2.7714228219771354e-06,
|
| 703 |
+
"loss": 1.3248,
|
| 704 |
+
"step": 8100
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.36,
|
| 708 |
+
"grad_norm": 1.9358181953430176,
|
| 709 |
+
"learning_rate": 2.765896582194267e-06,
|
| 710 |
+
"loss": 1.3321,
|
| 711 |
+
"step": 8200
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.36,
|
| 715 |
+
"grad_norm": 1.9804461002349854,
|
| 716 |
+
"learning_rate": 2.7603099823300316e-06,
|
| 717 |
+
"loss": 1.328,
|
| 718 |
+
"step": 8300
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.37,
|
| 722 |
+
"grad_norm": 1.9724797010421753,
|
| 723 |
+
"learning_rate": 2.754663288762921e-06,
|
| 724 |
+
"loss": 1.3313,
|
| 725 |
+
"step": 8400
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.37,
|
| 729 |
+
"grad_norm": 2.1071040630340576,
|
| 730 |
+
"learning_rate": 2.748956770736796e-06,
|
| 731 |
+
"loss": 1.3164,
|
| 732 |
+
"step": 8500
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.37,
|
| 736 |
+
"eval_loss": 1.3289612531661987,
|
| 737 |
+
"eval_runtime": 1864.6483,
|
| 738 |
+
"eval_samples_per_second": 5.141,
|
| 739 |
+
"eval_steps_per_second": 0.643,
|
| 740 |
+
"step": 8500
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.38,
|
| 744 |
+
"grad_norm": 1.8682750463485718,
|
| 745 |
+
"learning_rate": 2.743190700348048e-06,
|
| 746 |
+
"loss": 1.3318,
|
| 747 |
+
"step": 8600
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.38,
|
| 751 |
+
"grad_norm": 2.1705667972564697,
|
| 752 |
+
"learning_rate": 2.7373653525326257e-06,
|
| 753 |
+
"loss": 1.3203,
|
| 754 |
+
"step": 8700
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.39,
|
| 758 |
+
"grad_norm": 2.2123374938964844,
|
| 759 |
+
"learning_rate": 2.7314810050529265e-06,
|
| 760 |
+
"loss": 1.3279,
|
| 761 |
+
"step": 8800
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.39,
|
| 765 |
+
"grad_norm": 2.0958218574523926,
|
| 766 |
+
"learning_rate": 2.7255379384845483e-06,
|
| 767 |
+
"loss": 1.332,
|
| 768 |
+
"step": 8900
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.4,
|
| 772 |
+
"grad_norm": 2.0944671630859375,
|
| 773 |
+
"learning_rate": 2.7195364362029173e-06,
|
| 774 |
+
"loss": 1.3231,
|
| 775 |
+
"step": 9000
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.4,
|
| 779 |
+
"eval_loss": 1.3273080587387085,
|
| 780 |
+
"eval_runtime": 1864.6036,
|
| 781 |
+
"eval_samples_per_second": 5.141,
|
| 782 |
+
"eval_steps_per_second": 0.643,
|
| 783 |
+
"step": 9000
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.4,
|
| 787 |
+
"grad_norm": 2.045405149459839,
|
| 788 |
+
"learning_rate": 2.713476784369771e-06,
|
| 789 |
+
"loss": 1.3179,
|
| 790 |
+
"step": 9100
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.4,
|
| 794 |
+
"grad_norm": 1.985823392868042,
|
| 795 |
+
"learning_rate": 2.7073592719195155e-06,
|
| 796 |
+
"loss": 1.3318,
|
| 797 |
+
"step": 9200
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.41,
|
| 801 |
+
"grad_norm": 2.064948081970215,
|
| 802 |
+
"learning_rate": 2.7011841905454495e-06,
|
| 803 |
+
"loss": 1.3181,
|
| 804 |
+
"step": 9300
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.41,
|
| 808 |
+
"grad_norm": 2.136582612991333,
|
| 809 |
+
"learning_rate": 2.694951834685854e-06,
|
| 810 |
+
"loss": 1.3181,
|
| 811 |
+
"step": 9400
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.42,
|
| 815 |
+
"grad_norm": 2.394834041595459,
|
| 816 |
+
"learning_rate": 2.6886625015099553e-06,
|
| 817 |
+
"loss": 1.3287,
|
| 818 |
+
"step": 9500
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.42,
|
| 822 |
+
"eval_loss": 1.3257533311843872,
|
| 823 |
+
"eval_runtime": 1871.6529,
|
| 824 |
+
"eval_samples_per_second": 5.122,
|
| 825 |
+
"eval_steps_per_second": 0.641,
|
| 826 |
+
"step": 9500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.42,
|
| 830 |
+
"grad_norm": 2.0295205116271973,
|
| 831 |
+
"learning_rate": 2.682316490903753e-06,
|
| 832 |
+
"loss": 1.3316,
|
| 833 |
+
"step": 9600
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.43,
|
| 837 |
+
"grad_norm": 1.883170247077942,
|
| 838 |
+
"learning_rate": 2.6759141054557214e-06,
|
| 839 |
+
"loss": 1.345,
|
| 840 |
+
"step": 9700
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.43,
|
| 844 |
+
"grad_norm": 2.172785997390747,
|
| 845 |
+
"learning_rate": 2.6694556504423836e-06,
|
| 846 |
+
"loss": 1.3197,
|
| 847 |
+
"step": 9800
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.44,
|
| 851 |
+
"grad_norm": 2.065781354904175,
|
| 852 |
+
"learning_rate": 2.662941433813754e-06,
|
| 853 |
+
"loss": 1.3165,
|
| 854 |
+
"step": 9900
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.44,
|
| 858 |
+
"grad_norm": 1.825239896774292,
|
| 859 |
+
"learning_rate": 2.6563717661786536e-06,
|
| 860 |
+
"loss": 1.3308,
|
| 861 |
+
"step": 10000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.44,
|
| 865 |
+
"eval_loss": 1.324156641960144,
|
| 866 |
+
"eval_runtime": 1865.6117,
|
| 867 |
+
"eval_samples_per_second": 5.138,
|
| 868 |
+
"eval_steps_per_second": 0.643,
|
| 869 |
+
"step": 10000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.44,
|
| 873 |
+
"grad_norm": 2.128471612930298,
|
| 874 |
+
"learning_rate": 2.649746960789902e-06,
|
| 875 |
+
"loss": 1.3176,
|
| 876 |
+
"step": 10100
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 0.45,
|
| 880 |
+
"grad_norm": 1.994718074798584,
|
| 881 |
+
"learning_rate": 2.6430673335293788e-06,
|
| 882 |
+
"loss": 1.3245,
|
| 883 |
+
"step": 10200
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 0.45,
|
| 887 |
+
"grad_norm": 2.0164434909820557,
|
| 888 |
+
"learning_rate": 2.6363332028929633e-06,
|
| 889 |
+
"loss": 1.3179,
|
| 890 |
+
"step": 10300
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.46,
|
| 894 |
+
"grad_norm": 1.879969835281372,
|
| 895 |
+
"learning_rate": 2.629544889975348e-06,
|
| 896 |
+
"loss": 1.3346,
|
| 897 |
+
"step": 10400
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.46,
|
| 901 |
+
"grad_norm": 1.9689232110977173,
|
| 902 |
+
"learning_rate": 2.6227027184547265e-06,
|
| 903 |
+
"loss": 1.311,
|
| 904 |
+
"step": 10500
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 0.46,
|
| 908 |
+
"eval_loss": 1.3230102062225342,
|
| 909 |
+
"eval_runtime": 1865.9111,
|
| 910 |
+
"eval_samples_per_second": 5.137,
|
| 911 |
+
"eval_steps_per_second": 0.643,
|
| 912 |
+
"step": 10500
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.47,
|
| 916 |
+
"grad_norm": 2.0227608680725098,
|
| 917 |
+
"learning_rate": 2.615807014577363e-06,
|
| 918 |
+
"loss": 1.3226,
|
| 919 |
+
"step": 10600
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.47,
|
| 923 |
+
"grad_norm": 1.9242812395095825,
|
| 924 |
+
"learning_rate": 2.608858107142033e-06,
|
| 925 |
+
"loss": 1.3254,
|
| 926 |
+
"step": 10700
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.47,
|
| 930 |
+
"grad_norm": 1.9587324857711792,
|
| 931 |
+
"learning_rate": 2.601856327484348e-06,
|
| 932 |
+
"loss": 1.3219,
|
| 933 |
+
"step": 10800
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.48,
|
| 937 |
+
"grad_norm": 2.0176897048950195,
|
| 938 |
+
"learning_rate": 2.594802009460957e-06,
|
| 939 |
+
"loss": 1.3133,
|
| 940 |
+
"step": 10900
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.48,
|
| 944 |
+
"grad_norm": 1.871654987335205,
|
| 945 |
+
"learning_rate": 2.5876954894336257e-06,
|
| 946 |
+
"loss": 1.3242,
|
| 947 |
+
"step": 11000
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.48,
|
| 951 |
+
"eval_loss": 1.321611762046814,
|
| 952 |
+
"eval_runtime": 1864.3465,
|
| 953 |
+
"eval_samples_per_second": 5.142,
|
| 954 |
+
"eval_steps_per_second": 0.643,
|
| 955 |
+
"step": 11000
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.49,
|
| 959 |
+
"grad_norm": 2.1732594966888428,
|
| 960 |
+
"learning_rate": 2.580537106253199e-06,
|
| 961 |
+
"loss": 1.3123,
|
| 962 |
+
"step": 11100
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.49,
|
| 966 |
+
"grad_norm": 1.9368730783462524,
|
| 967 |
+
"learning_rate": 2.5733272012434456e-06,
|
| 968 |
+
"loss": 1.323,
|
| 969 |
+
"step": 11200
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.5,
|
| 973 |
+
"grad_norm": 2.197732448577881,
|
| 974 |
+
"learning_rate": 2.56606611818478e-06,
|
| 975 |
+
"loss": 1.316,
|
| 976 |
+
"step": 11300
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.5,
|
| 980 |
+
"grad_norm": 2.0765159130096436,
|
| 981 |
+
"learning_rate": 2.5587542032978735e-06,
|
| 982 |
+
"loss": 1.326,
|
| 983 |
+
"step": 11400
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.51,
|
| 987 |
+
"grad_norm": 1.9759124517440796,
|
| 988 |
+
"learning_rate": 2.551391805227145e-06,
|
| 989 |
+
"loss": 1.319,
|
| 990 |
+
"step": 11500
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.51,
|
| 994 |
+
"eval_loss": 1.3201991319656372,
|
| 995 |
+
"eval_runtime": 1867.1093,
|
| 996 |
+
"eval_samples_per_second": 5.134,
|
| 997 |
+
"eval_steps_per_second": 0.642,
|
| 998 |
+
"step": 11500
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 0.51,
|
| 1002 |
+
"grad_norm": 2.119062900543213,
|
| 1003 |
+
"learning_rate": 2.5439792750241362e-06,
|
| 1004 |
+
"loss": 1.319,
|
| 1005 |
+
"step": 11600
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.51,
|
| 1009 |
+
"grad_norm": 1.9623346328735352,
|
| 1010 |
+
"learning_rate": 2.5365169661307723e-06,
|
| 1011 |
+
"loss": 1.3188,
|
| 1012 |
+
"step": 11700
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 0.52,
|
| 1016 |
+
"grad_norm": 2.069474935531616,
|
| 1017 |
+
"learning_rate": 2.529005234362512e-06,
|
| 1018 |
+
"loss": 1.3236,
|
| 1019 |
+
"step": 11800
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 0.52,
|
| 1023 |
+
"grad_norm": 1.8530821800231934,
|
| 1024 |
+
"learning_rate": 2.521444437891378e-06,
|
| 1025 |
+
"loss": 1.3172,
|
| 1026 |
+
"step": 11900
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.53,
|
| 1030 |
+
"grad_norm": 2.1172099113464355,
|
| 1031 |
+
"learning_rate": 2.513834937228883e-06,
|
| 1032 |
+
"loss": 1.3183,
|
| 1033 |
+
"step": 12000
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 0.53,
|
| 1037 |
+
"eval_loss": 1.31929349899292,
|
| 1038 |
+
"eval_runtime": 1867.4942,
|
| 1039 |
+
"eval_samples_per_second": 5.133,
|
| 1040 |
+
"eval_steps_per_second": 0.642,
|
| 1041 |
+
"step": 12000
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.53,
|
| 1045 |
+
"grad_norm": 1.981194019317627,
|
| 1046 |
+
"learning_rate": 2.5061770952088354e-06,
|
| 1047 |
+
"loss": 1.3278,
|
| 1048 |
+
"step": 12100
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.54,
|
| 1052 |
+
"grad_norm": 1.9915848970413208,
|
| 1053 |
+
"learning_rate": 2.4984712769700423e-06,
|
| 1054 |
+
"loss": 1.3143,
|
| 1055 |
+
"step": 12200
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.54,
|
| 1059 |
+
"grad_norm": 2.114997625350952,
|
| 1060 |
+
"learning_rate": 2.490717849938897e-06,
|
| 1061 |
+
"loss": 1.3207,
|
| 1062 |
+
"step": 12300
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.55,
|
| 1066 |
+
"grad_norm": 1.9648516178131104,
|
| 1067 |
+
"learning_rate": 2.4829171838118613e-06,
|
| 1068 |
+
"loss": 1.3129,
|
| 1069 |
+
"step": 12400
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.55,
|
| 1073 |
+
"grad_norm": 1.9119199514389038,
|
| 1074 |
+
"learning_rate": 2.4750696505378355e-06,
|
| 1075 |
+
"loss": 1.3211,
|
| 1076 |
+
"step": 12500
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.55,
|
| 1080 |
+
"eval_loss": 1.3180123567581177,
|
| 1081 |
+
"eval_runtime": 1866.9983,
|
| 1082 |
+
"eval_samples_per_second": 5.134,
|
| 1083 |
+
"eval_steps_per_second": 0.642,
|
| 1084 |
+
"step": 12500
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 0.55,
|
| 1088 |
+
"grad_norm": 2.158143997192383,
|
| 1089 |
+
"learning_rate": 2.4671756243004243e-06,
|
| 1090 |
+
"loss": 1.3124,
|
| 1091 |
+
"step": 12600
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.56,
|
| 1095 |
+
"grad_norm": 2.059196949005127,
|
| 1096 |
+
"learning_rate": 2.4592354815000963e-06,
|
| 1097 |
+
"loss": 1.3229,
|
| 1098 |
+
"step": 12700
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.56,
|
| 1102 |
+
"grad_norm": 1.9812512397766113,
|
| 1103 |
+
"learning_rate": 2.451249600736235e-06,
|
| 1104 |
+
"loss": 1.3159,
|
| 1105 |
+
"step": 12800
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.57,
|
| 1109 |
+
"grad_norm": 1.9367738962173462,
|
| 1110 |
+
"learning_rate": 2.4432183627890867e-06,
|
| 1111 |
+
"loss": 1.3101,
|
| 1112 |
+
"step": 12900
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.57,
|
| 1116 |
+
"grad_norm": 2.1279842853546143,
|
| 1117 |
+
"learning_rate": 2.4351421506016047e-06,
|
| 1118 |
+
"loss": 1.3158,
|
| 1119 |
+
"step": 13000
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.57,
|
| 1123 |
+
"eval_loss": 1.3169833421707153,
|
| 1124 |
+
"eval_runtime": 1870.0395,
|
| 1125 |
+
"eval_samples_per_second": 5.126,
|
| 1126 |
+
"eval_steps_per_second": 0.641,
|
| 1127 |
+
"step": 13000
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 0.58,
|
| 1131 |
+
"grad_norm": 2.213517189025879,
|
| 1132 |
+
"learning_rate": 2.4270213492611903e-06,
|
| 1133 |
+
"loss": 1.3113,
|
| 1134 |
+
"step": 13100
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 0.58,
|
| 1138 |
+
"grad_norm": 2.060974597930908,
|
| 1139 |
+
"learning_rate": 2.41885634598133e-06,
|
| 1140 |
+
"loss": 1.3248,
|
| 1141 |
+
"step": 13200
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 0.58,
|
| 1145 |
+
"grad_norm": 2.004950523376465,
|
| 1146 |
+
"learning_rate": 2.4106475300831343e-06,
|
| 1147 |
+
"loss": 1.321,
|
| 1148 |
+
"step": 13300
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 0.59,
|
| 1152 |
+
"grad_norm": 2.081263303756714,
|
| 1153 |
+
"learning_rate": 2.402395292976772e-06,
|
| 1154 |
+
"loss": 1.3058,
|
| 1155 |
+
"step": 13400
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 0.59,
|
| 1159 |
+
"grad_norm": 2.141289472579956,
|
| 1160 |
+
"learning_rate": 2.394100028142809e-06,
|
| 1161 |
+
"loss": 1.3054,
|
| 1162 |
+
"step": 13500
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 0.59,
|
| 1166 |
+
"eval_loss": 1.3159672021865845,
|
| 1167 |
+
"eval_runtime": 1868.4185,
|
| 1168 |
+
"eval_samples_per_second": 5.131,
|
| 1169 |
+
"eval_steps_per_second": 0.642,
|
| 1170 |
+
"step": 13500
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 0.6,
|
| 1174 |
+
"grad_norm": 2.041181802749634,
|
| 1175 |
+
"learning_rate": 2.3857621311134457e-06,
|
| 1176 |
+
"loss": 1.324,
|
| 1177 |
+
"step": 13600
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 0.6,
|
| 1181 |
+
"grad_norm": 1.9553183317184448,
|
| 1182 |
+
"learning_rate": 2.3773819994536564e-06,
|
| 1183 |
+
"loss": 1.3115,
|
| 1184 |
+
"step": 13700
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 0.61,
|
| 1188 |
+
"grad_norm": 2.0408129692077637,
|
| 1189 |
+
"learning_rate": 2.368960032742235e-06,
|
| 1190 |
+
"loss": 1.3007,
|
| 1191 |
+
"step": 13800
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 0.61,
|
| 1195 |
+
"grad_norm": 2.0877633094787598,
|
| 1196 |
+
"learning_rate": 2.36049663255274e-06,
|
| 1197 |
+
"loss": 1.3174,
|
| 1198 |
+
"step": 13900
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 0.62,
|
| 1202 |
+
"grad_norm": 2.013047218322754,
|
| 1203 |
+
"learning_rate": 2.35199220243435e-06,
|
| 1204 |
+
"loss": 1.3249,
|
| 1205 |
+
"step": 14000
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 0.62,
|
| 1209 |
+
"eval_loss": 1.3149954080581665,
|
| 1210 |
+
"eval_runtime": 1864.575,
|
| 1211 |
+
"eval_samples_per_second": 5.141,
|
| 1212 |
+
"eval_steps_per_second": 0.643,
|
| 1213 |
+
"step": 14000
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.62,
|
| 1217 |
+
"grad_norm": 1.9625511169433594,
|
| 1218 |
+
"learning_rate": 2.3434471478926168e-06,
|
| 1219 |
+
"loss": 1.3053,
|
| 1220 |
+
"step": 14100
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.62,
|
| 1224 |
+
"grad_norm": 1.9895579814910889,
|
| 1225 |
+
"learning_rate": 2.334861876370135e-06,
|
| 1226 |
+
"loss": 1.3097,
|
| 1227 |
+
"step": 14200
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.63,
|
| 1231 |
+
"grad_norm": 2.0086371898651123,
|
| 1232 |
+
"learning_rate": 2.3262367972271126e-06,
|
| 1233 |
+
"loss": 1.3075,
|
| 1234 |
+
"step": 14300
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.63,
|
| 1238 |
+
"grad_norm": 2.0822415351867676,
|
| 1239 |
+
"learning_rate": 2.317572321721851e-06,
|
| 1240 |
+
"loss": 1.3122,
|
| 1241 |
+
"step": 14400
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.64,
|
| 1245 |
+
"grad_norm": 2.1191747188568115,
|
| 1246 |
+
"learning_rate": 2.3088688629911378e-06,
|
| 1247 |
+
"loss": 1.3029,
|
| 1248 |
+
"step": 14500
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.64,
|
| 1252 |
+
"eval_loss": 1.313984990119934,
|
| 1253 |
+
"eval_runtime": 1868.3094,
|
| 1254 |
+
"eval_samples_per_second": 5.131,
|
| 1255 |
+
"eval_steps_per_second": 0.642,
|
| 1256 |
+
"step": 14500
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.64,
|
| 1260 |
+
"grad_norm": 2.0153069496154785,
|
| 1261 |
+
"learning_rate": 2.3001268360305446e-06,
|
| 1262 |
+
"loss": 1.31,
|
| 1263 |
+
"step": 14600
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.65,
|
| 1267 |
+
"grad_norm": 2.031879425048828,
|
| 1268 |
+
"learning_rate": 2.2913466576746433e-06,
|
| 1269 |
+
"loss": 1.3113,
|
| 1270 |
+
"step": 14700
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.65,
|
| 1274 |
+
"grad_norm": 1.9688141345977783,
|
| 1275 |
+
"learning_rate": 2.2825287465771276e-06,
|
| 1276 |
+
"loss": 1.3114,
|
| 1277 |
+
"step": 14800
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.66,
|
| 1281 |
+
"grad_norm": 2.0744152069091797,
|
| 1282 |
+
"learning_rate": 2.2736735231908515e-06,
|
| 1283 |
+
"loss": 1.3068,
|
| 1284 |
+
"step": 14900
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.66,
|
| 1288 |
+
"grad_norm": 2.004817485809326,
|
| 1289 |
+
"learning_rate": 2.2647814097477816e-06,
|
| 1290 |
+
"loss": 1.3148,
|
| 1291 |
+
"step": 15000
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.66,
|
| 1295 |
+
"eval_loss": 1.3130929470062256,
|
| 1296 |
+
"eval_runtime": 1864.9246,
|
| 1297 |
+
"eval_samples_per_second": 5.14,
|
| 1298 |
+
"eval_steps_per_second": 0.643,
|
| 1299 |
+
"step": 15000
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.66,
|
| 1303 |
+
"grad_norm": 2.018002510070801,
|
| 1304 |
+
"learning_rate": 2.2558528302388663e-06,
|
| 1305 |
+
"loss": 1.318,
|
| 1306 |
+
"step": 15100
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.67,
|
| 1310 |
+
"grad_norm": 2.0592522621154785,
|
| 1311 |
+
"learning_rate": 2.2468882103938155e-06,
|
| 1312 |
+
"loss": 1.3139,
|
| 1313 |
+
"step": 15200
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 0.67,
|
| 1317 |
+
"grad_norm": 1.9203455448150635,
|
| 1318 |
+
"learning_rate": 2.237887977660804e-06,
|
| 1319 |
+
"loss": 1.3163,
|
| 1320 |
+
"step": 15300
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 0.68,
|
| 1324 |
+
"grad_norm": 2.1021227836608887,
|
| 1325 |
+
"learning_rate": 2.2288525611860886e-06,
|
| 1326 |
+
"loss": 1.3182,
|
| 1327 |
+
"step": 15400
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 0.68,
|
| 1331 |
+
"grad_norm": 2.050011396408081,
|
| 1332 |
+
"learning_rate": 2.219782391793547e-06,
|
| 1333 |
+
"loss": 1.3036,
|
| 1334 |
+
"step": 15500
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 0.68,
|
| 1338 |
+
"eval_loss": 1.312229871749878,
|
| 1339 |
+
"eval_runtime": 1865.3014,
|
| 1340 |
+
"eval_samples_per_second": 5.139,
|
| 1341 |
+
"eval_steps_per_second": 0.643,
|
| 1342 |
+
"step": 15500
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 0.69,
|
| 1346 |
+
"grad_norm": 2.0257480144500732,
|
| 1347 |
+
"learning_rate": 2.2106779019641336e-06,
|
| 1348 |
+
"loss": 1.2984,
|
| 1349 |
+
"step": 15600
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 0.69,
|
| 1353 |
+
"grad_norm": 1.9984742403030396,
|
| 1354 |
+
"learning_rate": 2.2015395258152596e-06,
|
| 1355 |
+
"loss": 1.3206,
|
| 1356 |
+
"step": 15700
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 0.69,
|
| 1360 |
+
"grad_norm": 2.094935417175293,
|
| 1361 |
+
"learning_rate": 2.1923676990800927e-06,
|
| 1362 |
+
"loss": 1.3157,
|
| 1363 |
+
"step": 15800
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 0.7,
|
| 1367 |
+
"grad_norm": 2.0469040870666504,
|
| 1368 |
+
"learning_rate": 2.1831628590867812e-06,
|
| 1369 |
+
"loss": 1.3048,
|
| 1370 |
+
"step": 15900
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 0.7,
|
| 1374 |
+
"grad_norm": 2.0622622966766357,
|
| 1375 |
+
"learning_rate": 2.1739254447376006e-06,
|
| 1376 |
+
"loss": 1.3138,
|
| 1377 |
+
"step": 16000
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.7,
|
| 1381 |
+
"eval_loss": 1.3114036321640015,
|
| 1382 |
+
"eval_runtime": 1865.761,
|
| 1383 |
+
"eval_samples_per_second": 5.138,
|
| 1384 |
+
"eval_steps_per_second": 0.643,
|
| 1385 |
+
"step": 16000
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.71,
|
| 1389 |
+
"grad_norm": 2.0791163444519043,
|
| 1390 |
+
"learning_rate": 2.1646558964880277e-06,
|
| 1391 |
+
"loss": 1.3108,
|
| 1392 |
+
"step": 16100
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.71,
|
| 1396 |
+
"grad_norm": 2.027860403060913,
|
| 1397 |
+
"learning_rate": 2.1553546563257362e-06,
|
| 1398 |
+
"loss": 1.3116,
|
| 1399 |
+
"step": 16200
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.72,
|
| 1403 |
+
"grad_norm": 2.0047738552093506,
|
| 1404 |
+
"learning_rate": 2.146022167749525e-06,
|
| 1405 |
+
"loss": 1.3048,
|
| 1406 |
+
"step": 16300
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.72,
|
| 1410 |
+
"grad_norm": 2.213186025619507,
|
| 1411 |
+
"learning_rate": 2.136658875748169e-06,
|
| 1412 |
+
"loss": 1.3071,
|
| 1413 |
+
"step": 16400
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.73,
|
| 1417 |
+
"grad_norm": 2.0164272785186768,
|
| 1418 |
+
"learning_rate": 2.1272652267792036e-06,
|
| 1419 |
+
"loss": 1.314,
|
| 1420 |
+
"step": 16500
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.73,
|
| 1424 |
+
"eval_loss": 1.310592532157898,
|
| 1425 |
+
"eval_runtime": 1865.0707,
|
| 1426 |
+
"eval_samples_per_second": 5.14,
|
| 1427 |
+
"eval_steps_per_second": 0.643,
|
| 1428 |
+
"step": 16500
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 0.73,
|
| 1432 |
+
"grad_norm": 2.063606023788452,
|
| 1433 |
+
"learning_rate": 2.117841668747633e-06,
|
| 1434 |
+
"loss": 1.3171,
|
| 1435 |
+
"step": 16600
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 0.73,
|
| 1439 |
+
"grad_norm": 2.066218137741089,
|
| 1440 |
+
"learning_rate": 2.1083886509845794e-06,
|
| 1441 |
+
"loss": 1.3095,
|
| 1442 |
+
"step": 16700
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.74,
|
| 1446 |
+
"grad_norm": 2.00728702545166,
|
| 1447 |
+
"learning_rate": 2.098906624225852e-06,
|
| 1448 |
+
"loss": 1.3082,
|
| 1449 |
+
"step": 16800
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.74,
|
| 1453 |
+
"grad_norm": 1.946075439453125,
|
| 1454 |
+
"learning_rate": 2.089396040590459e-06,
|
| 1455 |
+
"loss": 1.3106,
|
| 1456 |
+
"step": 16900
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.75,
|
| 1460 |
+
"grad_norm": 2.2883059978485107,
|
| 1461 |
+
"learning_rate": 2.079857353559047e-06,
|
| 1462 |
+
"loss": 1.3045,
|
| 1463 |
+
"step": 17000
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.75,
|
| 1467 |
+
"eval_loss": 1.3099678754806519,
|
| 1468 |
+
"eval_runtime": 1865.3447,
|
| 1469 |
+
"eval_samples_per_second": 5.139,
|
| 1470 |
+
"eval_steps_per_second": 0.643,
|
| 1471 |
+
"step": 17000
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 0.75,
|
| 1475 |
+
"grad_norm": 1.9902862310409546,
|
| 1476 |
+
"learning_rate": 2.070291017952282e-06,
|
| 1477 |
+
"loss": 1.3188,
|
| 1478 |
+
"step": 17100
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 0.76,
|
| 1482 |
+
"grad_norm": 2.0283963680267334,
|
| 1483 |
+
"learning_rate": 2.0606974899091596e-06,
|
| 1484 |
+
"loss": 1.3115,
|
| 1485 |
+
"step": 17200
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 0.76,
|
| 1489 |
+
"grad_norm": 2.249575138092041,
|
| 1490 |
+
"learning_rate": 2.0510772268652563e-06,
|
| 1491 |
+
"loss": 1.3095,
|
| 1492 |
+
"step": 17300
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 0.76,
|
| 1496 |
+
"grad_norm": 2.022587537765503,
|
| 1497 |
+
"learning_rate": 2.0414306875309195e-06,
|
| 1498 |
+
"loss": 1.2989,
|
| 1499 |
+
"step": 17400
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 0.77,
|
| 1503 |
+
"grad_norm": 2.3016037940979004,
|
| 1504 |
+
"learning_rate": 2.0317583318693924e-06,
|
| 1505 |
+
"loss": 1.303,
|
| 1506 |
+
"step": 17500
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 0.77,
|
| 1510 |
+
"eval_loss": 1.3091822862625122,
|
| 1511 |
+
"eval_runtime": 1863.7921,
|
| 1512 |
+
"eval_samples_per_second": 5.143,
|
| 1513 |
+
"eval_steps_per_second": 0.643,
|
| 1514 |
+
"step": 17500
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.77,
|
| 1518 |
+
"grad_norm": 2.1690895557403564,
|
| 1519 |
+
"learning_rate": 2.022060621074887e-06,
|
| 1520 |
+
"loss": 1.3057,
|
| 1521 |
+
"step": 17600
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.78,
|
| 1525 |
+
"grad_norm": 2.1167852878570557,
|
| 1526 |
+
"learning_rate": 2.012338017550587e-06,
|
| 1527 |
+
"loss": 1.297,
|
| 1528 |
+
"step": 17700
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.78,
|
| 1532 |
+
"grad_norm": 2.035123109817505,
|
| 1533 |
+
"learning_rate": 2.0025909848866085e-06,
|
| 1534 |
+
"loss": 1.305,
|
| 1535 |
+
"step": 17800
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.79,
|
| 1539 |
+
"grad_norm": 1.931913137435913,
|
| 1540 |
+
"learning_rate": 1.9928199878378854e-06,
|
| 1541 |
+
"loss": 1.2938,
|
| 1542 |
+
"step": 17900
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.79,
|
| 1546 |
+
"grad_norm": 2.0481088161468506,
|
| 1547 |
+
"learning_rate": 1.983025492302016e-06,
|
| 1548 |
+
"loss": 1.2977,
|
| 1549 |
+
"step": 18000
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.79,
|
| 1553 |
+
"eval_loss": 1.3084911108016968,
|
| 1554 |
+
"eval_runtime": 1866.3126,
|
| 1555 |
+
"eval_samples_per_second": 5.136,
|
| 1556 |
+
"eval_steps_per_second": 0.642,
|
| 1557 |
+
"step": 18000
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.8,
|
| 1561 |
+
"grad_norm": 1.9030753374099731,
|
| 1562 |
+
"learning_rate": 1.973207965297045e-06,
|
| 1563 |
+
"loss": 1.3115,
|
| 1564 |
+
"step": 18100
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.8,
|
| 1568 |
+
"grad_norm": 1.9687721729278564,
|
| 1569 |
+
"learning_rate": 1.963367874939198e-06,
|
| 1570 |
+
"loss": 1.3026,
|
| 1571 |
+
"step": 18200
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.8,
|
| 1575 |
+
"grad_norm": 2.2594008445739746,
|
| 1576 |
+
"learning_rate": 1.9535056904205588e-06,
|
| 1577 |
+
"loss": 1.3134,
|
| 1578 |
+
"step": 18300
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.81,
|
| 1582 |
+
"grad_norm": 2.038999080657959,
|
| 1583 |
+
"learning_rate": 1.943621881986696e-06,
|
| 1584 |
+
"loss": 1.3039,
|
| 1585 |
+
"step": 18400
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.81,
|
| 1589 |
+
"grad_norm": 1.9501850605010986,
|
| 1590 |
+
"learning_rate": 1.933716920914245e-06,
|
| 1591 |
+
"loss": 1.3096,
|
| 1592 |
+
"step": 18500
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.81,
|
| 1596 |
+
"eval_loss": 1.3078255653381348,
|
| 1597 |
+
"eval_runtime": 1865.4912,
|
| 1598 |
+
"eval_samples_per_second": 5.139,
|
| 1599 |
+
"eval_steps_per_second": 0.643,
|
| 1600 |
+
"step": 18500
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 0.82,
|
| 1604 |
+
"grad_norm": 2.107854127883911,
|
| 1605 |
+
"learning_rate": 1.923791279488435e-06,
|
| 1606 |
+
"loss": 1.307,
|
| 1607 |
+
"step": 18600
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 0.82,
|
| 1611 |
+
"grad_norm": 2.067185640335083,
|
| 1612 |
+
"learning_rate": 1.913845430980567e-06,
|
| 1613 |
+
"loss": 1.3225,
|
| 1614 |
+
"step": 18700
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 0.83,
|
| 1618 |
+
"grad_norm": 1.9632668495178223,
|
| 1619 |
+
"learning_rate": 1.9038798496254518e-06,
|
| 1620 |
+
"loss": 1.3095,
|
| 1621 |
+
"step": 18800
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 0.83,
|
| 1625 |
+
"grad_norm": 2.140648603439331,
|
| 1626 |
+
"learning_rate": 1.8938950105987948e-06,
|
| 1627 |
+
"loss": 1.2998,
|
| 1628 |
+
"step": 18900
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 0.84,
|
| 1632 |
+
"grad_norm": 1.9392528533935547,
|
| 1633 |
+
"learning_rate": 1.8838913899945394e-06,
|
| 1634 |
+
"loss": 1.3073,
|
| 1635 |
+
"step": 19000
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 0.84,
|
| 1639 |
+
"eval_loss": 1.3071683645248413,
|
| 1640 |
+
"eval_runtime": 1864.0962,
|
| 1641 |
+
"eval_samples_per_second": 5.142,
|
| 1642 |
+
"eval_steps_per_second": 0.643,
|
| 1643 |
+
"step": 19000
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 0.84,
|
| 1647 |
+
"grad_norm": 2.2147011756896973,
|
| 1648 |
+
"learning_rate": 1.8738694648021666e-06,
|
| 1649 |
+
"loss": 1.3017,
|
| 1650 |
+
"step": 19100
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 0.84,
|
| 1654 |
+
"grad_norm": 2.112633228302002,
|
| 1655 |
+
"learning_rate": 1.863829712883951e-06,
|
| 1656 |
+
"loss": 1.312,
|
| 1657 |
+
"step": 19200
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 0.85,
|
| 1661 |
+
"grad_norm": 2.0416507720947266,
|
| 1662 |
+
"learning_rate": 1.8537726129521755e-06,
|
| 1663 |
+
"loss": 1.3036,
|
| 1664 |
+
"step": 19300
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 0.85,
|
| 1668 |
+
"grad_norm": 1.988303303718567,
|
| 1669 |
+
"learning_rate": 1.8436986445463049e-06,
|
| 1670 |
+
"loss": 1.3009,
|
| 1671 |
+
"step": 19400
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 0.86,
|
| 1675 |
+
"grad_norm": 2.023023843765259,
|
| 1676 |
+
"learning_rate": 1.8336082880101228e-06,
|
| 1677 |
+
"loss": 1.3137,
|
| 1678 |
+
"step": 19500
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 0.86,
|
| 1682 |
+
"eval_loss": 1.3065180778503418,
|
| 1683 |
+
"eval_runtime": 1866.3466,
|
| 1684 |
+
"eval_samples_per_second": 5.136,
|
| 1685 |
+
"eval_steps_per_second": 0.642,
|
| 1686 |
+
"step": 19500
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 0.86,
|
| 1690 |
+
"grad_norm": 2.112020254135132,
|
| 1691 |
+
"learning_rate": 1.8235020244688246e-06,
|
| 1692 |
+
"loss": 1.3037,
|
| 1693 |
+
"step": 19600
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 0.87,
|
| 1697 |
+
"grad_norm": 2.056504249572754,
|
| 1698 |
+
"learning_rate": 1.8133803358060798e-06,
|
| 1699 |
+
"loss": 1.3141,
|
| 1700 |
+
"step": 19700
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 0.87,
|
| 1704 |
+
"grad_norm": 2.0338857173919678,
|
| 1705 |
+
"learning_rate": 1.8032437046410528e-06,
|
| 1706 |
+
"loss": 1.3012,
|
| 1707 |
+
"step": 19800
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 0.87,
|
| 1711 |
+
"grad_norm": 2.071561098098755,
|
| 1712 |
+
"learning_rate": 1.7930926143053926e-06,
|
| 1713 |
+
"loss": 1.3063,
|
| 1714 |
+
"step": 19900
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 0.88,
|
| 1718 |
+
"grad_norm": 2.080360174179077,
|
| 1719 |
+
"learning_rate": 1.7829275488201849e-06,
|
| 1720 |
+
"loss": 1.3083,
|
| 1721 |
+
"step": 20000
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 0.88,
|
| 1725 |
+
"eval_loss": 1.3060280084609985,
|
| 1726 |
+
"eval_runtime": 1870.2241,
|
| 1727 |
+
"eval_samples_per_second": 5.126,
|
| 1728 |
+
"eval_steps_per_second": 0.641,
|
| 1729 |
+
"step": 20000
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 0.88,
|
| 1733 |
+
"grad_norm": 2.0536909103393555,
|
| 1734 |
+
"learning_rate": 1.7727489928728747e-06,
|
| 1735 |
+
"loss": 1.3115,
|
| 1736 |
+
"step": 20100
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 0.89,
|
| 1740 |
+
"grad_norm": 2.07513689994812,
|
| 1741 |
+
"learning_rate": 1.762557431794155e-06,
|
| 1742 |
+
"loss": 1.3028,
|
| 1743 |
+
"step": 20200
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 0.89,
|
| 1747 |
+
"grad_norm": 2.2155916690826416,
|
| 1748 |
+
"learning_rate": 1.7523533515348249e-06,
|
| 1749 |
+
"loss": 1.3061,
|
| 1750 |
+
"step": 20300
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 0.9,
|
| 1754 |
+
"grad_norm": 2.2243480682373047,
|
| 1755 |
+
"learning_rate": 1.7421372386426185e-06,
|
| 1756 |
+
"loss": 1.312,
|
| 1757 |
+
"step": 20400
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 0.9,
|
| 1761 |
+
"grad_norm": 2.010845184326172,
|
| 1762 |
+
"learning_rate": 1.7319095802390087e-06,
|
| 1763 |
+
"loss": 1.3199,
|
| 1764 |
+
"step": 20500
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 0.9,
|
| 1768 |
+
"eval_loss": 1.3053687810897827,
|
| 1769 |
+
"eval_runtime": 1865.2464,
|
| 1770 |
+
"eval_samples_per_second": 5.139,
|
| 1771 |
+
"eval_steps_per_second": 0.643,
|
| 1772 |
+
"step": 20500
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 0.91,
|
| 1776 |
+
"grad_norm": 1.9459248781204224,
|
| 1777 |
+
"learning_rate": 1.7216708639959744e-06,
|
| 1778 |
+
"loss": 1.3091,
|
| 1779 |
+
"step": 20600
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 0.91,
|
| 1783 |
+
"grad_norm": 2.0189294815063477,
|
| 1784 |
+
"learning_rate": 1.711421578112754e-06,
|
| 1785 |
+
"loss": 1.2958,
|
| 1786 |
+
"step": 20700
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 0.91,
|
| 1790 |
+
"grad_norm": 2.0753591060638428,
|
| 1791 |
+
"learning_rate": 1.701162211292561e-06,
|
| 1792 |
+
"loss": 1.3041,
|
| 1793 |
+
"step": 20800
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 0.92,
|
| 1797 |
+
"grad_norm": 2.1882078647613525,
|
| 1798 |
+
"learning_rate": 1.6908932527192886e-06,
|
| 1799 |
+
"loss": 1.3104,
|
| 1800 |
+
"step": 20900
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 0.92,
|
| 1804 |
+
"grad_norm": 2.0360772609710693,
|
| 1805 |
+
"learning_rate": 1.6806151920341779e-06,
|
| 1806 |
+
"loss": 1.31,
|
| 1807 |
+
"step": 21000
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 0.92,
|
| 1811 |
+
"eval_loss": 1.3050304651260376,
|
| 1812 |
+
"eval_runtime": 1868.8769,
|
| 1813 |
+
"eval_samples_per_second": 5.129,
|
| 1814 |
+
"eval_steps_per_second": 0.642,
|
| 1815 |
+
"step": 21000
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.93,
|
| 1819 |
+
"grad_norm": 2.137718439102173,
|
| 1820 |
+
"learning_rate": 1.6703285193124748e-06,
|
| 1821 |
+
"loss": 1.3027,
|
| 1822 |
+
"step": 21100
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.93,
|
| 1826 |
+
"grad_norm": 2.0401344299316406,
|
| 1827 |
+
"learning_rate": 1.660033725040063e-06,
|
| 1828 |
+
"loss": 1.3037,
|
| 1829 |
+
"step": 21200
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.94,
|
| 1833 |
+
"grad_norm": 1.9637211561203003,
|
| 1834 |
+
"learning_rate": 1.649731300090074e-06,
|
| 1835 |
+
"loss": 1.2974,
|
| 1836 |
+
"step": 21300
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.94,
|
| 1840 |
+
"grad_norm": 2.090510368347168,
|
| 1841 |
+
"learning_rate": 1.6394217356994827e-06,
|
| 1842 |
+
"loss": 1.2934,
|
| 1843 |
+
"step": 21400
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.95,
|
| 1847 |
+
"grad_norm": 2.3479647636413574,
|
| 1848 |
+
"learning_rate": 1.6291055234456859e-06,
|
| 1849 |
+
"loss": 1.3201,
|
| 1850 |
+
"step": 21500
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.95,
|
| 1854 |
+
"eval_loss": 1.3043450117111206,
|
| 1855 |
+
"eval_runtime": 1866.4601,
|
| 1856 |
+
"eval_samples_per_second": 5.136,
|
| 1857 |
+
"eval_steps_per_second": 0.642,
|
| 1858 |
+
"step": 21500
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.95,
|
| 1862 |
+
"grad_norm": 2.1579744815826416,
|
| 1863 |
+
"learning_rate": 1.6187831552230603e-06,
|
| 1864 |
+
"loss": 1.2983,
|
| 1865 |
+
"step": 21600
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.95,
|
| 1869 |
+
"grad_norm": 2.2169971466064453,
|
| 1870 |
+
"learning_rate": 1.608455123219511e-06,
|
| 1871 |
+
"loss": 1.3011,
|
| 1872 |
+
"step": 21700
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.96,
|
| 1876 |
+
"grad_norm": 1.9283170700073242,
|
| 1877 |
+
"learning_rate": 1.5981219198929995e-06,
|
| 1878 |
+
"loss": 1.3036,
|
| 1879 |
+
"step": 21800
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.96,
|
| 1883 |
+
"grad_norm": 1.9650486707687378,
|
| 1884 |
+
"learning_rate": 1.5877840379480678e-06,
|
| 1885 |
+
"loss": 1.3017,
|
| 1886 |
+
"step": 21900
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.97,
|
| 1890 |
+
"grad_norm": 2.2148048877716064,
|
| 1891 |
+
"learning_rate": 1.5774419703123393e-06,
|
| 1892 |
+
"loss": 1.3118,
|
| 1893 |
+
"step": 22000
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.97,
|
| 1897 |
+
"eval_loss": 1.303900122642517,
|
| 1898 |
+
"eval_runtime": 1863.2857,
|
| 1899 |
+
"eval_samples_per_second": 5.145,
|
| 1900 |
+
"eval_steps_per_second": 0.643,
|
| 1901 |
+
"step": 22000
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 0.97,
|
| 1905 |
+
"grad_norm": 2.119337558746338,
|
| 1906 |
+
"learning_rate": 1.56709621011302e-06,
|
| 1907 |
+
"loss": 1.3038,
|
| 1908 |
+
"step": 22100
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 0.98,
|
| 1912 |
+
"grad_norm": 2.062990427017212,
|
| 1913 |
+
"learning_rate": 1.5567472506533827e-06,
|
| 1914 |
+
"loss": 1.2878,
|
| 1915 |
+
"step": 22200
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 0.98,
|
| 1919 |
+
"grad_norm": 2.1745545864105225,
|
| 1920 |
+
"learning_rate": 1.546395585389247e-06,
|
| 1921 |
+
"loss": 1.2964,
|
| 1922 |
+
"step": 22300
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 0.98,
|
| 1926 |
+
"grad_norm": 2.1263065338134766,
|
| 1927 |
+
"learning_rate": 1.5360417079054494e-06,
|
| 1928 |
+
"loss": 1.295,
|
| 1929 |
+
"step": 22400
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 0.99,
|
| 1933 |
+
"grad_norm": 2.044600248336792,
|
| 1934 |
+
"learning_rate": 1.5256861118923083e-06,
|
| 1935 |
+
"loss": 1.3049,
|
| 1936 |
+
"step": 22500
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 0.99,
|
| 1940 |
+
"eval_loss": 1.303480625152588,
|
| 1941 |
+
"eval_runtime": 1862.9597,
|
| 1942 |
+
"eval_samples_per_second": 5.146,
|
| 1943 |
+
"eval_steps_per_second": 0.644,
|
| 1944 |
+
"step": 22500
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 0.99,
|
| 1948 |
+
"grad_norm": 2.0431716442108154,
|
| 1949 |
+
"learning_rate": 1.5153292911220858e-06,
|
| 1950 |
+
"loss": 1.2992,
|
| 1951 |
+
"step": 22600
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 1.0,
|
| 1955 |
+
"grad_norm": 2.1952879428863525,
|
| 1956 |
+
"learning_rate": 1.5049717394254412e-06,
|
| 1957 |
+
"loss": 1.2952,
|
| 1958 |
+
"step": 22700
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 1.0,
|
| 1962 |
+
"grad_norm": 1.9967477321624756,
|
| 1963 |
+
"learning_rate": 1.4946139506678864e-06,
|
| 1964 |
+
"loss": 1.2967,
|
| 1965 |
+
"step": 22800
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 1.01,
|
| 1969 |
+
"grad_norm": 2.1949024200439453,
|
| 1970 |
+
"learning_rate": 1.4842564187262365e-06,
|
| 1971 |
+
"loss": 1.3107,
|
| 1972 |
+
"step": 22900
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 1.01,
|
| 1976 |
+
"grad_norm": 2.114365339279175,
|
| 1977 |
+
"learning_rate": 1.47389963746506e-06,
|
| 1978 |
+
"loss": 1.2946,
|
| 1979 |
+
"step": 23000
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 1.01,
|
| 1983 |
+
"eval_loss": 1.3029588460922241,
|
| 1984 |
+
"eval_runtime": 1862.6203,
|
| 1985 |
+
"eval_samples_per_second": 5.147,
|
| 1986 |
+
"eval_steps_per_second": 0.644,
|
| 1987 |
+
"step": 23000
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 1.02,
|
| 1991 |
+
"grad_norm": 2.3793764114379883,
|
| 1992 |
+
"learning_rate": 1.4635441007131343e-06,
|
| 1993 |
+
"loss": 1.3098,
|
| 1994 |
+
"step": 23100
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 1.02,
|
| 1998 |
+
"grad_norm": 2.0778090953826904,
|
| 1999 |
+
"learning_rate": 1.453190302239894e-06,
|
| 2000 |
+
"loss": 1.3051,
|
| 2001 |
+
"step": 23200
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 1.02,
|
| 2005 |
+
"grad_norm": 2.019946336746216,
|
| 2006 |
+
"learning_rate": 1.442838735731892e-06,
|
| 2007 |
+
"loss": 1.2966,
|
| 2008 |
+
"step": 23300
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 1.03,
|
| 2012 |
+
"grad_norm": 2.1698460578918457,
|
| 2013 |
+
"learning_rate": 1.432489894769254e-06,
|
| 2014 |
+
"loss": 1.3029,
|
| 2015 |
+
"step": 23400
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 1.03,
|
| 2019 |
+
"grad_norm": 2.034184217453003,
|
| 2020 |
+
"learning_rate": 1.4221442728021506e-06,
|
| 2021 |
+
"loss": 1.316,
|
| 2022 |
+
"step": 23500
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 1.03,
|
| 2026 |
+
"eval_loss": 1.3026907444000244,
|
| 2027 |
+
"eval_runtime": 1863.5533,
|
| 2028 |
+
"eval_samples_per_second": 5.144,
|
| 2029 |
+
"eval_steps_per_second": 0.643,
|
| 2030 |
+
"step": 23500
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 1.04,
|
| 2034 |
+
"grad_norm": 2.025113582611084,
|
| 2035 |
+
"learning_rate": 1.4118023631272633e-06,
|
| 2036 |
+
"loss": 1.2935,
|
| 2037 |
+
"step": 23600
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 1.04,
|
| 2041 |
+
"grad_norm": 2.073225259780884,
|
| 2042 |
+
"learning_rate": 1.4014646588642656e-06,
|
| 2043 |
+
"loss": 1.2967,
|
| 2044 |
+
"step": 23700
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 1.05,
|
| 2048 |
+
"grad_norm": 2.120889186859131,
|
| 2049 |
+
"learning_rate": 1.391131652932311e-06,
|
| 2050 |
+
"loss": 1.3013,
|
| 2051 |
+
"step": 23800
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 1.05,
|
| 2055 |
+
"grad_norm": 2.005122423171997,
|
| 2056 |
+
"learning_rate": 1.3808038380265258e-06,
|
| 2057 |
+
"loss": 1.2928,
|
| 2058 |
+
"step": 23900
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 1.06,
|
| 2062 |
+
"grad_norm": 2.147322654724121,
|
| 2063 |
+
"learning_rate": 1.3704817065945235e-06,
|
| 2064 |
+
"loss": 1.3059,
|
| 2065 |
+
"step": 24000
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 1.06,
|
| 2069 |
+
"eval_loss": 1.3021385669708252,
|
| 2070 |
+
"eval_runtime": 1865.741,
|
| 2071 |
+
"eval_samples_per_second": 5.138,
|
| 2072 |
+
"eval_steps_per_second": 0.643,
|
| 2073 |
+
"step": 24000
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 1.06,
|
| 2077 |
+
"grad_norm": 2.336851119995117,
|
| 2078 |
+
"learning_rate": 1.360165750812916e-06,
|
| 2079 |
+
"loss": 1.2986,
|
| 2080 |
+
"step": 24100
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 1.06,
|
| 2084 |
+
"grad_norm": 2.077028274536133,
|
| 2085 |
+
"learning_rate": 1.3498564625638525e-06,
|
| 2086 |
+
"loss": 1.3062,
|
| 2087 |
+
"step": 24200
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 1.07,
|
| 2091 |
+
"grad_norm": 2.137953519821167,
|
| 2092 |
+
"learning_rate": 1.3395543334115616e-06,
|
| 2093 |
+
"loss": 1.3071,
|
| 2094 |
+
"step": 24300
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 1.07,
|
| 2098 |
+
"grad_norm": 2.054823875427246,
|
| 2099 |
+
"learning_rate": 1.3292598545789157e-06,
|
| 2100 |
+
"loss": 1.2981,
|
| 2101 |
+
"step": 24400
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 1.08,
|
| 2105 |
+
"grad_norm": 2.045687198638916,
|
| 2106 |
+
"learning_rate": 1.3189735169240044e-06,
|
| 2107 |
+
"loss": 1.2971,
|
| 2108 |
+
"step": 24500
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 1.08,
|
| 2112 |
+
"eval_loss": 1.3017216920852661,
|
| 2113 |
+
"eval_runtime": 1863.3072,
|
| 2114 |
+
"eval_samples_per_second": 5.145,
|
| 2115 |
+
"eval_steps_per_second": 0.643,
|
| 2116 |
+
"step": 24500
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 1.08,
|
| 2120 |
+
"grad_norm": 2.2879574298858643,
|
| 2121 |
+
"learning_rate": 1.308695810916735e-06,
|
| 2122 |
+
"loss": 1.2943,
|
| 2123 |
+
"step": 24600
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 1.09,
|
| 2127 |
+
"grad_norm": 2.1517672538757324,
|
| 2128 |
+
"learning_rate": 1.2984272266154414e-06,
|
| 2129 |
+
"loss": 1.3083,
|
| 2130 |
+
"step": 24700
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 1.09,
|
| 2134 |
+
"grad_norm": 2.0498697757720947,
|
| 2135 |
+
"learning_rate": 1.288168253643521e-06,
|
| 2136 |
+
"loss": 1.2873,
|
| 2137 |
+
"step": 24800
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 1.09,
|
| 2141 |
+
"grad_norm": 2.1879069805145264,
|
| 2142 |
+
"learning_rate": 1.2779193811660837e-06,
|
| 2143 |
+
"loss": 1.2902,
|
| 2144 |
+
"step": 24900
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 1.1,
|
| 2148 |
+
"grad_norm": 2.2728075981140137,
|
| 2149 |
+
"learning_rate": 1.2676810978666353e-06,
|
| 2150 |
+
"loss": 1.3001,
|
| 2151 |
+
"step": 25000
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 1.1,
|
| 2155 |
+
"eval_loss": 1.3014191389083862,
|
| 2156 |
+
"eval_runtime": 1863.092,
|
| 2157 |
+
"eval_samples_per_second": 5.145,
|
| 2158 |
+
"eval_steps_per_second": 0.644,
|
| 2159 |
+
"step": 25000
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 1.1,
|
| 2163 |
+
"grad_norm": 2.2328622341156006,
|
| 2164 |
+
"learning_rate": 1.2574538919237673e-06,
|
| 2165 |
+
"loss": 1.3028,
|
| 2166 |
+
"step": 25100
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 1.11,
|
| 2170 |
+
"grad_norm": 2.2706058025360107,
|
| 2171 |
+
"learning_rate": 1.2472382509878873e-06,
|
| 2172 |
+
"loss": 1.2931,
|
| 2173 |
+
"step": 25200
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 1.11,
|
| 2177 |
+
"grad_norm": 2.234330892562866,
|
| 2178 |
+
"learning_rate": 1.2370346621579623e-06,
|
| 2179 |
+
"loss": 1.3025,
|
| 2180 |
+
"step": 25300
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 1.12,
|
| 2184 |
+
"grad_norm": 2.125455379486084,
|
| 2185 |
+
"learning_rate": 1.2268436119582958e-06,
|
| 2186 |
+
"loss": 1.3031,
|
| 2187 |
+
"step": 25400
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 1.12,
|
| 2191 |
+
"grad_norm": 2.0227627754211426,
|
| 2192 |
+
"learning_rate": 1.2166655863153263e-06,
|
| 2193 |
+
"loss": 1.2743,
|
| 2194 |
+
"step": 25500
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 1.12,
|
| 2198 |
+
"eval_loss": 1.3010908365249634,
|
| 2199 |
+
"eval_runtime": 1862.8931,
|
| 2200 |
+
"eval_samples_per_second": 5.146,
|
| 2201 |
+
"eval_steps_per_second": 0.644,
|
| 2202 |
+
"step": 25500
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 1.13,
|
| 2206 |
+
"grad_norm": 2.0580368041992188,
|
| 2207 |
+
"learning_rate": 1.2065010705344618e-06,
|
| 2208 |
+
"loss": 1.3054,
|
| 2209 |
+
"step": 25600
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 1.13,
|
| 2213 |
+
"grad_norm": 2.1647911071777344,
|
| 2214 |
+
"learning_rate": 1.1963505492769355e-06,
|
| 2215 |
+
"loss": 1.2916,
|
| 2216 |
+
"step": 25700
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 1.13,
|
| 2220 |
+
"grad_norm": 2.0057008266448975,
|
| 2221 |
+
"learning_rate": 1.1862145065366998e-06,
|
| 2222 |
+
"loss": 1.3016,
|
| 2223 |
+
"step": 25800
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 1.14,
|
| 2227 |
+
"grad_norm": 2.097618341445923,
|
| 2228 |
+
"learning_rate": 1.1760934256173447e-06,
|
| 2229 |
+
"loss": 1.2946,
|
| 2230 |
+
"step": 25900
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 1.14,
|
| 2234 |
+
"grad_norm": 2.1340222358703613,
|
| 2235 |
+
"learning_rate": 1.1659877891090587e-06,
|
| 2236 |
+
"loss": 1.2983,
|
| 2237 |
+
"step": 26000
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 1.14,
|
| 2241 |
+
"eval_loss": 1.300696849822998,
|
| 2242 |
+
"eval_runtime": 1862.6712,
|
| 2243 |
+
"eval_samples_per_second": 5.146,
|
| 2244 |
+
"eval_steps_per_second": 0.644,
|
| 2245 |
+
"step": 26000
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 1.15,
|
| 2249 |
+
"grad_norm": 2.054945468902588,
|
| 2250 |
+
"learning_rate": 1.155898078865611e-06,
|
| 2251 |
+
"loss": 1.3035,
|
| 2252 |
+
"step": 26100
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 1.15,
|
| 2256 |
+
"grad_norm": 2.0940968990325928,
|
| 2257 |
+
"learning_rate": 1.1458247759813828e-06,
|
| 2258 |
+
"loss": 1.2955,
|
| 2259 |
+
"step": 26200
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 1.16,
|
| 2263 |
+
"grad_norm": 2.199674129486084,
|
| 2264 |
+
"learning_rate": 1.135768360768423e-06,
|
| 2265 |
+
"loss": 1.3013,
|
| 2266 |
+
"step": 26300
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 1.16,
|
| 2270 |
+
"grad_norm": 2.2380006313323975,
|
| 2271 |
+
"learning_rate": 1.125729312733549e-06,
|
| 2272 |
+
"loss": 1.3017,
|
| 2273 |
+
"step": 26400
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 1.16,
|
| 2277 |
+
"grad_norm": 2.0469789505004883,
|
| 2278 |
+
"learning_rate": 1.1157081105554801e-06,
|
| 2279 |
+
"loss": 1.3048,
|
| 2280 |
+
"step": 26500
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 1.16,
|
| 2284 |
+
"eval_loss": 1.3003997802734375,
|
| 2285 |
+
"eval_runtime": 1862.5897,
|
| 2286 |
+
"eval_samples_per_second": 5.147,
|
| 2287 |
+
"eval_steps_per_second": 0.644,
|
| 2288 |
+
"step": 26500
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 1.17,
|
| 2292 |
+
"grad_norm": 2.136064052581787,
|
| 2293 |
+
"learning_rate": 1.1057052320620172e-06,
|
| 2294 |
+
"loss": 1.2849,
|
| 2295 |
+
"step": 26600
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 1.17,
|
| 2299 |
+
"grad_norm": 2.2330269813537598,
|
| 2300 |
+
"learning_rate": 1.0957211542072556e-06,
|
| 2301 |
+
"loss": 1.2946,
|
| 2302 |
+
"step": 26700
|
| 2303 |
+
},
|
| 2304 |
+
{
|
| 2305 |
+
"epoch": 1.18,
|
| 2306 |
+
"grad_norm": 2.45259690284729,
|
| 2307 |
+
"learning_rate": 1.085756353048846e-06,
|
| 2308 |
+
"loss": 1.2956,
|
| 2309 |
+
"step": 26800
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 1.18,
|
| 2313 |
+
"grad_norm": 2.133361339569092,
|
| 2314 |
+
"learning_rate": 1.0758113037252912e-06,
|
| 2315 |
+
"loss": 1.3041,
|
| 2316 |
+
"step": 26900
|
| 2317 |
+
},
|
| 2318 |
+
{
|
| 2319 |
+
"epoch": 1.19,
|
| 2320 |
+
"grad_norm": 2.1824896335601807,
|
| 2321 |
+
"learning_rate": 1.065886480433296e-06,
|
| 2322 |
+
"loss": 1.2945,
|
| 2323 |
+
"step": 27000
|
| 2324 |
+
},
|
| 2325 |
+
{
|
| 2326 |
+
"epoch": 1.19,
|
| 2327 |
+
"eval_loss": 1.2999972105026245,
|
| 2328 |
+
"eval_runtime": 1863.119,
|
| 2329 |
+
"eval_samples_per_second": 5.145,
|
| 2330 |
+
"eval_steps_per_second": 0.644,
|
| 2331 |
+
"step": 27000
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 1.19,
|
| 2335 |
+
"grad_norm": 2.218424081802368,
|
| 2336 |
+
"learning_rate": 1.0559823564051523e-06,
|
| 2337 |
+
"loss": 1.3011,
|
| 2338 |
+
"step": 27100
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 1.2,
|
| 2342 |
+
"grad_norm": 2.0408236980438232,
|
| 2343 |
+
"learning_rate": 1.0460994038861768e-06,
|
| 2344 |
+
"loss": 1.2935,
|
| 2345 |
+
"step": 27200
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 1.2,
|
| 2349 |
+
"grad_norm": 2.0885488986968994,
|
| 2350 |
+
"learning_rate": 1.0362380941121925e-06,
|
| 2351 |
+
"loss": 1.3001,
|
| 2352 |
+
"step": 27300
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 1.2,
|
| 2356 |
+
"grad_norm": 2.130805015563965,
|
| 2357 |
+
"learning_rate": 1.0263988972870613e-06,
|
| 2358 |
+
"loss": 1.3081,
|
| 2359 |
+
"step": 27400
|
| 2360 |
+
},
|
| 2361 |
+
{
|
| 2362 |
+
"epoch": 1.21,
|
| 2363 |
+
"grad_norm": 2.0574839115142822,
|
| 2364 |
+
"learning_rate": 1.0165822825602596e-06,
|
| 2365 |
+
"loss": 1.3071,
|
| 2366 |
+
"step": 27500
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 1.21,
|
| 2370 |
+
"eval_loss": 1.2996830940246582,
|
| 2371 |
+
"eval_runtime": 1863.286,
|
| 2372 |
+
"eval_samples_per_second": 5.145,
|
| 2373 |
+
"eval_steps_per_second": 0.643,
|
| 2374 |
+
"step": 27500
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 1.21,
|
| 2378 |
+
"grad_norm": 2.075486421585083,
|
| 2379 |
+
"learning_rate": 1.0067887180045145e-06,
|
| 2380 |
+
"loss": 1.296,
|
| 2381 |
+
"step": 27600
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 1.22,
|
| 2385 |
+
"grad_norm": 2.07733154296875,
|
| 2386 |
+
"learning_rate": 9.970186705934803e-07,
|
| 2387 |
+
"loss": 1.3015,
|
| 2388 |
+
"step": 27700
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 1.22,
|
| 2392 |
+
"grad_norm": 2.1551625728607178,
|
| 2393 |
+
"learning_rate": 9.872726061794744e-07,
|
| 2394 |
+
"loss": 1.2951,
|
| 2395 |
+
"step": 27800
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 1.23,
|
| 2399 |
+
"grad_norm": 2.174243927001953,
|
| 2400 |
+
"learning_rate": 9.775509894712656e-07,
|
| 2401 |
+
"loss": 1.3052,
|
| 2402 |
+
"step": 27900
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 1.23,
|
| 2406 |
+
"grad_norm": 2.11954665184021,
|
| 2407 |
+
"learning_rate": 9.678542840119123e-07,
|
| 2408 |
+
"loss": 1.294,
|
| 2409 |
+
"step": 28000
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 1.23,
|
| 2413 |
+
"eval_loss": 1.2994180917739868,
|
| 2414 |
+
"eval_runtime": 1864.2204,
|
| 2415 |
+
"eval_samples_per_second": 5.142,
|
| 2416 |
+
"eval_steps_per_second": 0.643,
|
| 2417 |
+
"step": 28000
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 1.24,
|
| 2421 |
+
"grad_norm": 2.0479559898376465,
|
| 2422 |
+
"learning_rate": 9.581829521566663e-07,
|
| 2423 |
+
"loss": 1.3078,
|
| 2424 |
+
"step": 28100
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 1.24,
|
| 2428 |
+
"grad_norm": 2.1119577884674072,
|
| 2429 |
+
"learning_rate": 9.485374550509197e-07,
|
| 2430 |
+
"loss": 1.2878,
|
| 2431 |
+
"step": 28200
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 1.24,
|
| 2435 |
+
"grad_norm": 2.1557509899139404,
|
| 2436 |
+
"learning_rate": 9.389182526082229e-07,
|
| 2437 |
+
"loss": 1.2866,
|
| 2438 |
+
"step": 28300
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 1.25,
|
| 2442 |
+
"grad_norm": 2.226323127746582,
|
| 2443 |
+
"learning_rate": 9.293258034883504e-07,
|
| 2444 |
+
"loss": 1.2977,
|
| 2445 |
+
"step": 28400
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 1.25,
|
| 2449 |
+
"grad_norm": 2.1167123317718506,
|
| 2450 |
+
"learning_rate": 9.197605650754353e-07,
|
| 2451 |
+
"loss": 1.2937,
|
| 2452 |
+
"step": 28500
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 1.25,
|
| 2456 |
+
"eval_loss": 1.2991981506347656,
|
| 2457 |
+
"eval_runtime": 1863.4013,
|
| 2458 |
+
"eval_samples_per_second": 5.144,
|
| 2459 |
+
"eval_steps_per_second": 0.643,
|
| 2460 |
+
"step": 28500
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 1.26,
|
| 2464 |
+
"grad_norm": 2.254310131072998,
|
| 2465 |
+
"learning_rate": 9.10222993456156e-07,
|
| 2466 |
+
"loss": 1.3016,
|
| 2467 |
+
"step": 28600
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 1.26,
|
| 2471 |
+
"grad_norm": 2.0988237857818604,
|
| 2472 |
+
"learning_rate": 9.007135433979935e-07,
|
| 2473 |
+
"loss": 1.3,
|
| 2474 |
+
"step": 28700
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 1.27,
|
| 2478 |
+
"grad_norm": 2.0965945720672607,
|
| 2479 |
+
"learning_rate": 8.912326683275442e-07,
|
| 2480 |
+
"loss": 1.2877,
|
| 2481 |
+
"step": 28800
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 1.27,
|
| 2485 |
+
"grad_norm": 2.037484884262085,
|
| 2486 |
+
"learning_rate": 8.817808203089022e-07,
|
| 2487 |
+
"loss": 1.3084,
|
| 2488 |
+
"step": 28900
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 1.27,
|
| 2492 |
+
"grad_norm": 2.0629284381866455,
|
| 2493 |
+
"learning_rate": 8.723584500221013e-07,
|
| 2494 |
+
"loss": 1.2857,
|
| 2495 |
+
"step": 29000
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 1.27,
|
| 2499 |
+
"eval_loss": 1.298945426940918,
|
| 2500 |
+
"eval_runtime": 1863.2462,
|
| 2501 |
+
"eval_samples_per_second": 5.145,
|
| 2502 |
+
"eval_steps_per_second": 0.644,
|
| 2503 |
+
"step": 29000
|
| 2504 |
+
},
|
| 2505 |
+
{
|
| 2506 |
+
"epoch": 1.28,
|
| 2507 |
+
"grad_norm": 2.1192641258239746,
|
| 2508 |
+
"learning_rate": 8.62966006741628e-07,
|
| 2509 |
+
"loss": 1.3011,
|
| 2510 |
+
"step": 29100
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 1.28,
|
| 2514 |
+
"grad_norm": 2.2492525577545166,
|
| 2515 |
+
"learning_rate": 8.536039383150001e-07,
|
| 2516 |
+
"loss": 1.2882,
|
| 2517 |
+
"step": 29200
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 1.29,
|
| 2521 |
+
"grad_norm": 2.1896586418151855,
|
| 2522 |
+
"learning_rate": 8.442726911414094e-07,
|
| 2523 |
+
"loss": 1.2933,
|
| 2524 |
+
"step": 29300
|
| 2525 |
+
},
|
| 2526 |
+
{
|
| 2527 |
+
"epoch": 1.29,
|
| 2528 |
+
"grad_norm": 2.073396921157837,
|
| 2529 |
+
"learning_rate": 8.349727101504388e-07,
|
| 2530 |
+
"loss": 1.3119,
|
| 2531 |
+
"step": 29400
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"epoch": 1.3,
|
| 2535 |
+
"grad_norm": 2.1311280727386475,
|
| 2536 |
+
"learning_rate": 8.257044387808482e-07,
|
| 2537 |
+
"loss": 1.2921,
|
| 2538 |
+
"step": 29500
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 1.3,
|
| 2542 |
+
"eval_loss": 1.2986724376678467,
|
| 2543 |
+
"eval_runtime": 1862.6142,
|
| 2544 |
+
"eval_samples_per_second": 5.147,
|
| 2545 |
+
"eval_steps_per_second": 0.644,
|
| 2546 |
+
"step": 29500
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 1.3,
|
| 2550 |
+
"grad_norm": 2.1984448432922363,
|
| 2551 |
+
"learning_rate": 8.164683189594269e-07,
|
| 2552 |
+
"loss": 1.2933,
|
| 2553 |
+
"step": 29600
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 1.31,
|
| 2557 |
+
"grad_norm": 2.1039230823516846,
|
| 2558 |
+
"learning_rate": 8.072647910799269e-07,
|
| 2559 |
+
"loss": 1.3129,
|
| 2560 |
+
"step": 29700
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 1.31,
|
| 2564 |
+
"grad_norm": 1.9746812582015991,
|
| 2565 |
+
"learning_rate": 7.980942939820596e-07,
|
| 2566 |
+
"loss": 1.305,
|
| 2567 |
+
"step": 29800
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 1.31,
|
| 2571 |
+
"grad_norm": 2.099011182785034,
|
| 2572 |
+
"learning_rate": 7.889572649305736e-07,
|
| 2573 |
+
"loss": 1.2956,
|
| 2574 |
+
"step": 29900
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 1.32,
|
| 2578 |
+
"grad_norm": 2.3024837970733643,
|
| 2579 |
+
"learning_rate": 7.798541395944053e-07,
|
| 2580 |
+
"loss": 1.2794,
|
| 2581 |
+
"step": 30000
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 1.32,
|
| 2585 |
+
"eval_loss": 1.2984648942947388,
|
| 2586 |
+
"eval_runtime": 1861.962,
|
| 2587 |
+
"eval_samples_per_second": 5.148,
|
| 2588 |
+
"eval_steps_per_second": 0.644,
|
| 2589 |
+
"step": 30000
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 1.32,
|
| 2593 |
+
"grad_norm": 2.1850967407226562,
|
| 2594 |
+
"learning_rate": 7.707853520259052e-07,
|
| 2595 |
+
"loss": 1.2854,
|
| 2596 |
+
"step": 30100
|
| 2597 |
+
},
|
| 2598 |
+
{
|
| 2599 |
+
"epoch": 1.33,
|
| 2600 |
+
"grad_norm": 2.239342212677002,
|
| 2601 |
+
"learning_rate": 7.617513346401388e-07,
|
| 2602 |
+
"loss": 1.2919,
|
| 2603 |
+
"step": 30200
|
| 2604 |
+
},
|
| 2605 |
+
{
|
| 2606 |
+
"epoch": 1.33,
|
| 2607 |
+
"grad_norm": 2.3949005603790283,
|
| 2608 |
+
"learning_rate": 7.527525181942738e-07,
|
| 2609 |
+
"loss": 1.3048,
|
| 2610 |
+
"step": 30300
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"epoch": 1.34,
|
| 2614 |
+
"grad_norm": 2.2545089721679688,
|
| 2615 |
+
"learning_rate": 7.437893317670351e-07,
|
| 2616 |
+
"loss": 1.2909,
|
| 2617 |
+
"step": 30400
|
| 2618 |
+
},
|
| 2619 |
+
{
|
| 2620 |
+
"epoch": 1.34,
|
| 2621 |
+
"grad_norm": 2.2839066982269287,
|
| 2622 |
+
"learning_rate": 7.348622027382499e-07,
|
| 2623 |
+
"loss": 1.299,
|
| 2624 |
+
"step": 30500
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 1.34,
|
| 2628 |
+
"eval_loss": 1.2982053756713867,
|
| 2629 |
+
"eval_runtime": 1862.6374,
|
| 2630 |
+
"eval_samples_per_second": 5.146,
|
| 2631 |
+
"eval_steps_per_second": 0.644,
|
| 2632 |
+
"step": 30500
|
| 2633 |
+
},
|
| 2634 |
+
{
|
| 2635 |
+
"epoch": 1.35,
|
| 2636 |
+
"grad_norm": 2.43034029006958,
|
| 2637 |
+
"learning_rate": 7.259715567684677e-07,
|
| 2638 |
+
"loss": 1.2973,
|
| 2639 |
+
"step": 30600
|
| 2640 |
+
},
|
| 2641 |
+
{
|
| 2642 |
+
"epoch": 1.35,
|
| 2643 |
+
"grad_norm": 2.251255989074707,
|
| 2644 |
+
"learning_rate": 7.171178177786646e-07,
|
| 2645 |
+
"loss": 1.2973,
|
| 2646 |
+
"step": 30700
|
| 2647 |
+
},
|
| 2648 |
+
{
|
| 2649 |
+
"epoch": 1.35,
|
| 2650 |
+
"grad_norm": 2.132671356201172,
|
| 2651 |
+
"learning_rate": 7.083014079300282e-07,
|
| 2652 |
+
"loss": 1.2931,
|
| 2653 |
+
"step": 30800
|
| 2654 |
+
},
|
| 2655 |
+
{
|
| 2656 |
+
"epoch": 1.36,
|
| 2657 |
+
"grad_norm": 2.243849277496338,
|
| 2658 |
+
"learning_rate": 6.995227476038316e-07,
|
| 2659 |
+
"loss": 1.2967,
|
| 2660 |
+
"step": 30900
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 1.36,
|
| 2664 |
+
"grad_norm": 2.284914016723633,
|
| 2665 |
+
"learning_rate": 6.907822553813857e-07,
|
| 2666 |
+
"loss": 1.2925,
|
| 2667 |
+
"step": 31000
|
| 2668 |
+
},
|
| 2669 |
+
{
|
| 2670 |
+
"epoch": 1.36,
|
| 2671 |
+
"eval_loss": 1.2980060577392578,
|
| 2672 |
+
"eval_runtime": 1862.987,
|
| 2673 |
+
"eval_samples_per_second": 5.146,
|
| 2674 |
+
"eval_steps_per_second": 0.644,
|
| 2675 |
+
"step": 31000
|
| 2676 |
+
},
|
| 2677 |
+
{
|
| 2678 |
+
"epoch": 1.37,
|
| 2679 |
+
"grad_norm": 2.1762306690216064,
|
| 2680 |
+
"learning_rate": 6.820803480240832e-07,
|
| 2681 |
+
"loss": 1.3035,
|
| 2682 |
+
"step": 31100
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 1.37,
|
| 2686 |
+
"grad_norm": 2.1974294185638428,
|
| 2687 |
+
"learning_rate": 6.734174404535233e-07,
|
| 2688 |
+
"loss": 1.2982,
|
| 2689 |
+
"step": 31200
|
| 2690 |
+
},
|
| 2691 |
+
{
|
| 2692 |
+
"epoch": 1.38,
|
| 2693 |
+
"grad_norm": 2.1154937744140625,
|
| 2694 |
+
"learning_rate": 6.647939457317332e-07,
|
| 2695 |
+
"loss": 1.2987,
|
| 2696 |
+
"step": 31300
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 1.38,
|
| 2700 |
+
"grad_norm": 2.2262349128723145,
|
| 2701 |
+
"learning_rate": 6.562102750414655e-07,
|
| 2702 |
+
"loss": 1.2894,
|
| 2703 |
+
"step": 31400
|
| 2704 |
+
},
|
| 2705 |
+
{
|
| 2706 |
+
"epoch": 1.38,
|
| 2707 |
+
"grad_norm": 2.2507781982421875,
|
| 2708 |
+
"learning_rate": 6.476668376665978e-07,
|
| 2709 |
+
"loss": 1.3024,
|
| 2710 |
+
"step": 31500
|
| 2711 |
+
},
|
| 2712 |
+
{
|
| 2713 |
+
"epoch": 1.38,
|
| 2714 |
+
"eval_loss": 1.2977538108825684,
|
| 2715 |
+
"eval_runtime": 1863.5376,
|
| 2716 |
+
"eval_samples_per_second": 5.144,
|
| 2717 |
+
"eval_steps_per_second": 0.643,
|
| 2718 |
+
"step": 31500
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 1.39,
|
| 2722 |
+
"grad_norm": 2.0441462993621826,
|
| 2723 |
+
"learning_rate": 6.391640409726157e-07,
|
| 2724 |
+
"loss": 1.2939,
|
| 2725 |
+
"step": 31600
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 1.39,
|
| 2729 |
+
"grad_norm": 2.172423839569092,
|
| 2730 |
+
"learning_rate": 6.307022903871869e-07,
|
| 2731 |
+
"loss": 1.3002,
|
| 2732 |
+
"step": 31700
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 1.4,
|
| 2736 |
+
"grad_norm": 1.932667851448059,
|
| 2737 |
+
"learning_rate": 6.222819893808335e-07,
|
| 2738 |
+
"loss": 1.292,
|
| 2739 |
+
"step": 31800
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 1.4,
|
| 2743 |
+
"grad_norm": 2.173680305480957,
|
| 2744 |
+
"learning_rate": 6.139035394476905e-07,
|
| 2745 |
+
"loss": 1.3025,
|
| 2746 |
+
"step": 31900
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 1.41,
|
| 2750 |
+
"grad_norm": 2.1886558532714844,
|
| 2751 |
+
"learning_rate": 6.055673400863636e-07,
|
| 2752 |
+
"loss": 1.3103,
|
| 2753 |
+
"step": 32000
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 1.41,
|
| 2757 |
+
"eval_loss": 1.2976477146148682,
|
| 2758 |
+
"eval_runtime": 1862.7508,
|
| 2759 |
+
"eval_samples_per_second": 5.146,
|
| 2760 |
+
"eval_steps_per_second": 0.644,
|
| 2761 |
+
"step": 32000
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 1.41,
|
| 2765 |
+
"grad_norm": 2.3404366970062256,
|
| 2766 |
+
"learning_rate": 5.972737887808805e-07,
|
| 2767 |
+
"loss": 1.2915,
|
| 2768 |
+
"step": 32100
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 1.42,
|
| 2772 |
+
"grad_norm": 2.2503886222839355,
|
| 2773 |
+
"learning_rate": 5.890232809817378e-07,
|
| 2774 |
+
"loss": 1.2887,
|
| 2775 |
+
"step": 32200
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 1.42,
|
| 2779 |
+
"grad_norm": 2.1247682571411133,
|
| 2780 |
+
"learning_rate": 5.808162100870441e-07,
|
| 2781 |
+
"loss": 1.297,
|
| 2782 |
+
"step": 32300
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 1.42,
|
| 2786 |
+
"grad_norm": 2.1436526775360107,
|
| 2787 |
+
"learning_rate": 5.72652967423765e-07,
|
| 2788 |
+
"loss": 1.3008,
|
| 2789 |
+
"step": 32400
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 1.43,
|
| 2793 |
+
"grad_norm": 2.1058590412139893,
|
| 2794 |
+
"learning_rate": 5.645339422290599e-07,
|
| 2795 |
+
"loss": 1.2956,
|
| 2796 |
+
"step": 32500
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 1.43,
|
| 2800 |
+
"eval_loss": 1.2974357604980469,
|
| 2801 |
+
"eval_runtime": 1866.987,
|
| 2802 |
+
"eval_samples_per_second": 5.134,
|
| 2803 |
+
"eval_steps_per_second": 0.642,
|
| 2804 |
+
"step": 32500
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 1.43,
|
| 2808 |
+
"grad_norm": 2.1536617279052734,
|
| 2809 |
+
"learning_rate": 5.564595216317266e-07,
|
| 2810 |
+
"loss": 1.299,
|
| 2811 |
+
"step": 32600
|
| 2812 |
+
},
|
| 2813 |
+
{
|
| 2814 |
+
"epoch": 1.44,
|
| 2815 |
+
"grad_norm": 2.031917095184326,
|
| 2816 |
+
"learning_rate": 5.484300906337403e-07,
|
| 2817 |
+
"loss": 1.2828,
|
| 2818 |
+
"step": 32700
|
| 2819 |
+
},
|
| 2820 |
+
{
|
| 2821 |
+
"epoch": 1.44,
|
| 2822 |
+
"grad_norm": 1.9297816753387451,
|
| 2823 |
+
"learning_rate": 5.404460320918966e-07,
|
| 2824 |
+
"loss": 1.2937,
|
| 2825 |
+
"step": 32800
|
| 2826 |
+
},
|
| 2827 |
+
{
|
| 2828 |
+
"epoch": 1.45,
|
| 2829 |
+
"grad_norm": 2.253413677215576,
|
| 2830 |
+
"learning_rate": 5.325077266995542e-07,
|
| 2831 |
+
"loss": 1.3078,
|
| 2832 |
+
"step": 32900
|
| 2833 |
+
},
|
| 2834 |
+
{
|
| 2835 |
+
"epoch": 1.45,
|
| 2836 |
+
"grad_norm": 2.250991106033325,
|
| 2837 |
+
"learning_rate": 5.24615552968487e-07,
|
| 2838 |
+
"loss": 1.2788,
|
| 2839 |
+
"step": 33000
|
| 2840 |
+
},
|
| 2841 |
+
{
|
| 2842 |
+
"epoch": 1.45,
|
| 2843 |
+
"eval_loss": 1.297324776649475,
|
| 2844 |
+
"eval_runtime": 1864.5246,
|
| 2845 |
+
"eval_samples_per_second": 5.141,
|
| 2846 |
+
"eval_steps_per_second": 0.643,
|
| 2847 |
+
"step": 33000
|
| 2848 |
+
},
|
| 2849 |
+
{
|
| 2850 |
+
"epoch": 1.46,
|
| 2851 |
+
"grad_norm": 2.186206579208374,
|
| 2852 |
+
"learning_rate": 5.167698872108312e-07,
|
| 2853 |
+
"loss": 1.3048,
|
| 2854 |
+
"step": 33100
|
| 2855 |
+
},
|
| 2856 |
+
{
|
| 2857 |
+
"epoch": 1.46,
|
| 2858 |
+
"grad_norm": 2.1334028244018555,
|
| 2859 |
+
"learning_rate": 5.089711035211465e-07,
|
| 2860 |
+
"loss": 1.279,
|
| 2861 |
+
"step": 33200
|
| 2862 |
+
},
|
| 2863 |
+
{
|
| 2864 |
+
"epoch": 1.46,
|
| 2865 |
+
"grad_norm": 2.334712266921997,
|
| 2866 |
+
"learning_rate": 5.012195737585756e-07,
|
| 2867 |
+
"loss": 1.2949,
|
| 2868 |
+
"step": 33300
|
| 2869 |
+
},
|
| 2870 |
+
{
|
| 2871 |
+
"epoch": 1.47,
|
| 2872 |
+
"grad_norm": 2.2277867794036865,
|
| 2873 |
+
"learning_rate": 4.935156675291152e-07,
|
| 2874 |
+
"loss": 1.2998,
|
| 2875 |
+
"step": 33400
|
| 2876 |
+
},
|
| 2877 |
+
{
|
| 2878 |
+
"epoch": 1.47,
|
| 2879 |
+
"grad_norm": 2.1463205814361572,
|
| 2880 |
+
"learning_rate": 4.858597521679899e-07,
|
| 2881 |
+
"loss": 1.2878,
|
| 2882 |
+
"step": 33500
|
| 2883 |
+
},
|
| 2884 |
+
{
|
| 2885 |
+
"epoch": 1.47,
|
| 2886 |
+
"eval_loss": 1.2971347570419312,
|
| 2887 |
+
"eval_runtime": 1865.0446,
|
| 2888 |
+
"eval_samples_per_second": 5.14,
|
| 2889 |
+
"eval_steps_per_second": 0.643,
|
| 2890 |
+
"step": 33500
|
| 2891 |
+
},
|
| 2892 |
+
{
|
| 2893 |
+
"epoch": 1.48,
|
| 2894 |
+
"grad_norm": 2.0899240970611572,
|
| 2895 |
+
"learning_rate": 4.782521927221414e-07,
|
| 2896 |
+
"loss": 1.2927,
|
| 2897 |
+
"step": 33600
|
| 2898 |
+
},
|
| 2899 |
+
{
|
| 2900 |
+
"epoch": 1.48,
|
| 2901 |
+
"grad_norm": 2.1801438331604004,
|
| 2902 |
+
"learning_rate": 4.70693351932817e-07,
|
| 2903 |
+
"loss": 1.2822,
|
| 2904 |
+
"step": 33700
|
| 2905 |
+
},
|
| 2906 |
+
{
|
| 2907 |
+
"epoch": 1.49,
|
| 2908 |
+
"grad_norm": 2.0565810203552246,
|
| 2909 |
+
"learning_rate": 4.631835902182795e-07,
|
| 2910 |
+
"loss": 1.2998,
|
| 2911 |
+
"step": 33800
|
| 2912 |
+
},
|
| 2913 |
+
{
|
| 2914 |
+
"epoch": 1.49,
|
| 2915 |
+
"grad_norm": 2.0865461826324463,
|
| 2916 |
+
"learning_rate": 4.55723265656616e-07,
|
| 2917 |
+
"loss": 1.2912,
|
| 2918 |
+
"step": 33900
|
| 2919 |
+
},
|
| 2920 |
+
{
|
| 2921 |
+
"epoch": 1.49,
|
| 2922 |
+
"grad_norm": 2.186192750930786,
|
| 2923 |
+
"learning_rate": 4.483127339686686e-07,
|
| 2924 |
+
"loss": 1.2893,
|
| 2925 |
+
"step": 34000
|
| 2926 |
+
},
|
| 2927 |
+
{
|
| 2928 |
+
"epoch": 1.49,
|
| 2929 |
+
"eval_loss": 1.297006368637085,
|
| 2930 |
+
"eval_runtime": 1864.1525,
|
| 2931 |
+
"eval_samples_per_second": 5.142,
|
| 2932 |
+
"eval_steps_per_second": 0.643,
|
| 2933 |
+
"step": 34000
|
| 2934 |
+
},
|
| 2935 |
+
{
|
| 2936 |
+
"epoch": 1.5,
|
| 2937 |
+
"grad_norm": 2.418661594390869,
|
| 2938 |
+
"learning_rate": 4.409523485010707e-07,
|
| 2939 |
+
"loss": 1.2823,
|
| 2940 |
+
"step": 34100
|
| 2941 |
+
},
|
| 2942 |
+
{
|
| 2943 |
+
"epoch": 1.5,
|
| 2944 |
+
"grad_norm": 2.213181972503662,
|
| 2945 |
+
"learning_rate": 4.3364246020940003e-07,
|
| 2946 |
+
"loss": 1.2921,
|
| 2947 |
+
"step": 34200
|
| 2948 |
+
},
|
| 2949 |
+
{
|
| 2950 |
+
"epoch": 1.51,
|
| 2951 |
+
"grad_norm": 2.1837573051452637,
|
| 2952 |
+
"learning_rate": 4.263834176414426e-07,
|
| 2953 |
+
"loss": 1.2834,
|
| 2954 |
+
"step": 34300
|
| 2955 |
+
},
|
| 2956 |
+
{
|
| 2957 |
+
"epoch": 1.51,
|
| 2958 |
+
"grad_norm": 2.2444188594818115,
|
| 2959 |
+
"learning_rate": 4.191755669205763e-07,
|
| 2960 |
+
"loss": 1.3072,
|
| 2961 |
+
"step": 34400
|
| 2962 |
+
},
|
| 2963 |
+
{
|
| 2964 |
+
"epoch": 1.52,
|
| 2965 |
+
"grad_norm": 2.1974008083343506,
|
| 2966 |
+
"learning_rate": 4.120192517292637e-07,
|
| 2967 |
+
"loss": 1.295,
|
| 2968 |
+
"step": 34500
|
| 2969 |
+
},
|
| 2970 |
+
{
|
| 2971 |
+
"epoch": 1.52,
|
| 2972 |
+
"eval_loss": 1.2968517541885376,
|
| 2973 |
+
"eval_runtime": 1863.4227,
|
| 2974 |
+
"eval_samples_per_second": 5.144,
|
| 2975 |
+
"eval_steps_per_second": 0.643,
|
| 2976 |
+
"step": 34500
|
| 2977 |
+
},
|
| 2978 |
+
{
|
| 2979 |
+
"epoch": 1.52,
|
| 2980 |
+
"grad_norm": 2.2060582637786865,
|
| 2981 |
+
"learning_rate": 4.0491481329266823e-07,
|
| 2982 |
+
"loss": 1.294,
|
| 2983 |
+
"step": 34600
|
| 2984 |
+
},
|
| 2985 |
+
{
|
| 2986 |
+
"epoch": 1.53,
|
| 2987 |
+
"grad_norm": 2.2055234909057617,
|
| 2988 |
+
"learning_rate": 3.978625903623813e-07,
|
| 2989 |
+
"loss": 1.301,
|
| 2990 |
+
"step": 34700
|
| 2991 |
+
},
|
| 2992 |
+
{
|
| 2993 |
+
"epoch": 1.53,
|
| 2994 |
+
"grad_norm": 2.3005611896514893,
|
| 2995 |
+
"learning_rate": 3.9086291920027183e-07,
|
| 2996 |
+
"loss": 1.2909,
|
| 2997 |
+
"step": 34800
|
| 2998 |
+
},
|
| 2999 |
+
{
|
| 3000 |
+
"epoch": 1.53,
|
| 3001 |
+
"grad_norm": 2.2892158031463623,
|
| 3002 |
+
"learning_rate": 3.839161335624504e-07,
|
| 3003 |
+
"loss": 1.2898,
|
| 3004 |
+
"step": 34900
|
| 3005 |
+
},
|
| 3006 |
+
{
|
| 3007 |
+
"epoch": 1.54,
|
| 3008 |
+
"grad_norm": 2.2120680809020996,
|
| 3009 |
+
"learning_rate": 3.7702256468335877e-07,
|
| 3010 |
+
"loss": 1.2937,
|
| 3011 |
+
"step": 35000
|
| 3012 |
+
},
|
| 3013 |
+
{
|
| 3014 |
+
"epoch": 1.54,
|
| 3015 |
+
"eval_loss": 1.2967385053634644,
|
| 3016 |
+
"eval_runtime": 1863.4438,
|
| 3017 |
+
"eval_samples_per_second": 5.144,
|
| 3018 |
+
"eval_steps_per_second": 0.643,
|
| 3019 |
+
"step": 35000
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 1.54,
|
| 3023 |
+
"grad_norm": 2.06485652923584,
|
| 3024 |
+
"learning_rate": 3.7018254125997167e-07,
|
| 3025 |
+
"loss": 1.3034,
|
| 3026 |
+
"step": 35100
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 1.55,
|
| 3030 |
+
"grad_norm": 2.2690818309783936,
|
| 3031 |
+
"learning_rate": 3.6339638943612876e-07,
|
| 3032 |
+
"loss": 1.2816,
|
| 3033 |
+
"step": 35200
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 1.55,
|
| 3037 |
+
"grad_norm": 2.1384482383728027,
|
| 3038 |
+
"learning_rate": 3.566644327869784e-07,
|
| 3039 |
+
"loss": 1.2958,
|
| 3040 |
+
"step": 35300
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 1.56,
|
| 3044 |
+
"grad_norm": 2.262807607650757,
|
| 3045 |
+
"learning_rate": 3.4998699230355445e-07,
|
| 3046 |
+
"loss": 1.2906,
|
| 3047 |
+
"step": 35400
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 1.56,
|
| 3051 |
+
"grad_norm": 2.1555404663085938,
|
| 3052 |
+
"learning_rate": 3.4336438637746716e-07,
|
| 3053 |
+
"loss": 1.2911,
|
| 3054 |
+
"step": 35500
|
| 3055 |
+
},
|
| 3056 |
+
{
|
| 3057 |
+
"epoch": 1.56,
|
| 3058 |
+
"eval_loss": 1.2966289520263672,
|
| 3059 |
+
"eval_runtime": 1863.3587,
|
| 3060 |
+
"eval_samples_per_second": 5.144,
|
| 3061 |
+
"eval_steps_per_second": 0.643,
|
| 3062 |
+
"step": 35500
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 1.56,
|
| 3066 |
+
"grad_norm": 2.088890552520752,
|
| 3067 |
+
"learning_rate": 3.3679693078572135e-07,
|
| 3068 |
+
"loss": 1.2905,
|
| 3069 |
+
"step": 35600
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 1.57,
|
| 3073 |
+
"grad_norm": 2.362851142883301,
|
| 3074 |
+
"learning_rate": 3.302849386756631e-07,
|
| 3075 |
+
"loss": 1.2877,
|
| 3076 |
+
"step": 35700
|
| 3077 |
+
},
|
| 3078 |
+
{
|
| 3079 |
+
"epoch": 1.57,
|
| 3080 |
+
"grad_norm": 2.3154048919677734,
|
| 3081 |
+
"learning_rate": 3.2382872055004437e-07,
|
| 3082 |
+
"loss": 1.288,
|
| 3083 |
+
"step": 35800
|
| 3084 |
+
},
|
| 3085 |
+
{
|
| 3086 |
+
"epoch": 1.58,
|
| 3087 |
+
"grad_norm": 2.204124927520752,
|
| 3088 |
+
"learning_rate": 3.1742858425222153e-07,
|
| 3089 |
+
"loss": 1.2888,
|
| 3090 |
+
"step": 35900
|
| 3091 |
+
},
|
| 3092 |
+
{
|
| 3093 |
+
"epoch": 1.58,
|
| 3094 |
+
"grad_norm": 2.0219850540161133,
|
| 3095 |
+
"learning_rate": 3.1108483495147276e-07,
|
| 3096 |
+
"loss": 1.2962,
|
| 3097 |
+
"step": 36000
|
| 3098 |
+
},
|
| 3099 |
+
{
|
| 3100 |
+
"epoch": 1.58,
|
| 3101 |
+
"eval_loss": 1.2965224981307983,
|
| 3102 |
+
"eval_runtime": 1863.8916,
|
| 3103 |
+
"eval_samples_per_second": 5.143,
|
| 3104 |
+
"eval_steps_per_second": 0.643,
|
| 3105 |
+
"step": 36000
|
| 3106 |
+
},
|
| 3107 |
+
{
|
| 3108 |
+
"epoch": 1.59,
|
| 3109 |
+
"grad_norm": 2.456171989440918,
|
| 3110 |
+
"learning_rate": 3.0479777512845107e-07,
|
| 3111 |
+
"loss": 1.291,
|
| 3112 |
+
"step": 36100
|
| 3113 |
+
},
|
| 3114 |
+
{
|
| 3115 |
+
"epoch": 1.59,
|
| 3116 |
+
"grad_norm": 2.043088674545288,
|
| 3117 |
+
"learning_rate": 2.9856770456075904e-07,
|
| 3118 |
+
"loss": 1.2926,
|
| 3119 |
+
"step": 36200
|
| 3120 |
+
},
|
| 3121 |
+
{
|
| 3122 |
+
"epoch": 1.6,
|
| 3123 |
+
"grad_norm": 2.3121893405914307,
|
| 3124 |
+
"learning_rate": 2.9239492030865573e-07,
|
| 3125 |
+
"loss": 1.2933,
|
| 3126 |
+
"step": 36300
|
| 3127 |
+
},
|
| 3128 |
+
{
|
| 3129 |
+
"epoch": 1.6,
|
| 3130 |
+
"grad_norm": 2.117414712905884,
|
| 3131 |
+
"learning_rate": 2.862797167008913e-07,
|
| 3132 |
+
"loss": 1.2842,
|
| 3133 |
+
"step": 36400
|
| 3134 |
+
},
|
| 3135 |
+
{
|
| 3136 |
+
"epoch": 1.6,
|
| 3137 |
+
"grad_norm": 2.2130415439605713,
|
| 3138 |
+
"learning_rate": 2.802223853206752e-07,
|
| 3139 |
+
"loss": 1.2952,
|
| 3140 |
+
"step": 36500
|
| 3141 |
+
},
|
| 3142 |
+
{
|
| 3143 |
+
"epoch": 1.6,
|
| 3144 |
+
"eval_loss": 1.2964164018630981,
|
| 3145 |
+
"eval_runtime": 1863.5413,
|
| 3146 |
+
"eval_samples_per_second": 5.144,
|
| 3147 |
+
"eval_steps_per_second": 0.643,
|
| 3148 |
+
"step": 36500
|
| 3149 |
+
},
|
| 3150 |
+
{
|
| 3151 |
+
"epoch": 1.61,
|
| 3152 |
+
"grad_norm": 2.1747307777404785,
|
| 3153 |
+
"learning_rate": 2.7422321499177006e-07,
|
| 3154 |
+
"loss": 1.2953,
|
| 3155 |
+
"step": 36600
|
| 3156 |
+
},
|
| 3157 |
+
{
|
| 3158 |
+
"epoch": 1.61,
|
| 3159 |
+
"grad_norm": 2.238208293914795,
|
| 3160 |
+
"learning_rate": 2.6828249176472284e-07,
|
| 3161 |
+
"loss": 1.2901,
|
| 3162 |
+
"step": 36700
|
| 3163 |
+
},
|
| 3164 |
+
{
|
| 3165 |
+
"epoch": 1.62,
|
| 3166 |
+
"grad_norm": 2.170766830444336,
|
| 3167 |
+
"learning_rate": 2.624004989032238e-07,
|
| 3168 |
+
"loss": 1.3061,
|
| 3169 |
+
"step": 36800
|
| 3170 |
+
},
|
| 3171 |
+
{
|
| 3172 |
+
"epoch": 1.62,
|
| 3173 |
+
"grad_norm": 2.2250659465789795,
|
| 3174 |
+
"learning_rate": 2.565775168706008e-07,
|
| 3175 |
+
"loss": 1.3015,
|
| 3176 |
+
"step": 36900
|
| 3177 |
+
},
|
| 3178 |
+
{
|
| 3179 |
+
"epoch": 1.63,
|
| 3180 |
+
"grad_norm": 2.16519832611084,
|
| 3181 |
+
"learning_rate": 2.5081382331644484e-07,
|
| 3182 |
+
"loss": 1.3065,
|
| 3183 |
+
"step": 37000
|
| 3184 |
+
},
|
| 3185 |
+
{
|
| 3186 |
+
"epoch": 1.63,
|
| 3187 |
+
"eval_loss": 1.2963379621505737,
|
| 3188 |
+
"eval_runtime": 1863.6216,
|
| 3189 |
+
"eval_samples_per_second": 5.144,
|
| 3190 |
+
"eval_steps_per_second": 0.643,
|
| 3191 |
+
"step": 37000
|
| 3192 |
+
},
|
| 3193 |
+
{
|
| 3194 |
+
"epoch": 1.63,
|
| 3195 |
+
"grad_norm": 2.3075404167175293,
|
| 3196 |
+
"learning_rate": 2.451096930633741e-07,
|
| 3197 |
+
"loss": 1.2933,
|
| 3198 |
+
"step": 37100
|
| 3199 |
+
},
|
| 3200 |
+
{
|
| 3201 |
+
"epoch": 1.64,
|
| 3202 |
+
"grad_norm": 2.204376459121704,
|
| 3203 |
+
"learning_rate": 2.3946539809392637e-07,
|
| 3204 |
+
"loss": 1.2938,
|
| 3205 |
+
"step": 37200
|
| 3206 |
+
},
|
| 3207 |
+
{
|
| 3208 |
+
"epoch": 1.64,
|
| 3209 |
+
"grad_norm": 2.1348817348480225,
|
| 3210 |
+
"learning_rate": 2.33881207537594e-07,
|
| 3211 |
+
"loss": 1.2975,
|
| 3212 |
+
"step": 37300
|
| 3213 |
+
},
|
| 3214 |
+
{
|
| 3215 |
+
"epoch": 1.64,
|
| 3216 |
+
"grad_norm": 2.2030017375946045,
|
| 3217 |
+
"learning_rate": 2.283573876579882e-07,
|
| 3218 |
+
"loss": 1.2873,
|
| 3219 |
+
"step": 37400
|
| 3220 |
+
},
|
| 3221 |
+
{
|
| 3222 |
+
"epoch": 1.65,
|
| 3223 |
+
"grad_norm": 2.280266523361206,
|
| 3224 |
+
"learning_rate": 2.2289420184014636e-07,
|
| 3225 |
+
"loss": 1.2862,
|
| 3226 |
+
"step": 37500
|
| 3227 |
+
},
|
| 3228 |
+
{
|
| 3229 |
+
"epoch": 1.65,
|
| 3230 |
+
"eval_loss": 1.2962608337402344,
|
| 3231 |
+
"eval_runtime": 1864.1974,
|
| 3232 |
+
"eval_samples_per_second": 5.142,
|
| 3233 |
+
"eval_steps_per_second": 0.643,
|
| 3234 |
+
"step": 37500
|
| 3235 |
+
},
|
| 3236 |
+
{
|
| 3237 |
+
"epoch": 1.65,
|
| 3238 |
+
"grad_norm": 2.2561440467834473,
|
| 3239 |
+
"learning_rate": 2.1749191057796996e-07,
|
| 3240 |
+
"loss": 1.2926,
|
| 3241 |
+
"step": 37600
|
| 3242 |
+
},
|
| 3243 |
+
{
|
| 3244 |
+
"epoch": 1.66,
|
| 3245 |
+
"grad_norm": 2.064223289489746,
|
| 3246 |
+
"learning_rate": 2.1215077146180688e-07,
|
| 3247 |
+
"loss": 1.2911,
|
| 3248 |
+
"step": 37700
|
| 3249 |
+
},
|
| 3250 |
+
{
|
| 3251 |
+
"epoch": 1.66,
|
| 3252 |
+
"grad_norm": 2.0723884105682373,
|
| 3253 |
+
"learning_rate": 2.0687103916616612e-07,
|
| 3254 |
+
"loss": 1.2927,
|
| 3255 |
+
"step": 37800
|
| 3256 |
+
},
|
| 3257 |
+
{
|
| 3258 |
+
"epoch": 1.67,
|
| 3259 |
+
"grad_norm": 2.1863532066345215,
|
| 3260 |
+
"learning_rate": 2.0165296543757777e-07,
|
| 3261 |
+
"loss": 1.2958,
|
| 3262 |
+
"step": 37900
|
| 3263 |
+
},
|
| 3264 |
+
{
|
| 3265 |
+
"epoch": 1.67,
|
| 3266 |
+
"grad_norm": 2.242121458053589,
|
| 3267 |
+
"learning_rate": 1.9649679908258606e-07,
|
| 3268 |
+
"loss": 1.2856,
|
| 3269 |
+
"step": 38000
|
| 3270 |
+
},
|
| 3271 |
+
{
|
| 3272 |
+
"epoch": 1.67,
|
| 3273 |
+
"eval_loss": 1.2961931228637695,
|
| 3274 |
+
"eval_runtime": 1863.7107,
|
| 3275 |
+
"eval_samples_per_second": 5.144,
|
| 3276 |
+
"eval_steps_per_second": 0.643,
|
| 3277 |
+
"step": 38000
|
| 3278 |
+
},
|
| 3279 |
+
{
|
| 3280 |
+
"epoch": 1.67,
|
| 3281 |
+
"grad_norm": 2.2258660793304443,
|
| 3282 |
+
"learning_rate": 1.914027859558884e-07,
|
| 3283 |
+
"loss": 1.2895,
|
| 3284 |
+
"step": 38100
|
| 3285 |
+
},
|
| 3286 |
+
{
|
| 3287 |
+
"epoch": 1.68,
|
| 3288 |
+
"grad_norm": 2.194655418395996,
|
| 3289 |
+
"learning_rate": 1.8637116894861117e-07,
|
| 3290 |
+
"loss": 1.299,
|
| 3291 |
+
"step": 38200
|
| 3292 |
+
},
|
| 3293 |
+
{
|
| 3294 |
+
"epoch": 1.68,
|
| 3295 |
+
"grad_norm": 2.083817958831787,
|
| 3296 |
+
"learning_rate": 1.8140218797672898e-07,
|
| 3297 |
+
"loss": 1.2868,
|
| 3298 |
+
"step": 38300
|
| 3299 |
+
},
|
| 3300 |
+
{
|
| 3301 |
+
"epoch": 1.69,
|
| 3302 |
+
"grad_norm": 2.1037402153015137,
|
| 3303 |
+
"learning_rate": 1.7649607996962425e-07,
|
| 3304 |
+
"loss": 1.2833,
|
| 3305 |
+
"step": 38400
|
| 3306 |
+
},
|
| 3307 |
+
{
|
| 3308 |
+
"epoch": 1.69,
|
| 3309 |
+
"grad_norm": 2.3146462440490723,
|
| 3310 |
+
"learning_rate": 1.71653078858791e-07,
|
| 3311 |
+
"loss": 1.295,
|
| 3312 |
+
"step": 38500
|
| 3313 |
+
},
|
| 3314 |
+
{
|
| 3315 |
+
"epoch": 1.69,
|
| 3316 |
+
"eval_loss": 1.2961418628692627,
|
| 3317 |
+
"eval_runtime": 1863.9344,
|
| 3318 |
+
"eval_samples_per_second": 5.143,
|
| 3319 |
+
"eval_steps_per_second": 0.643,
|
| 3320 |
+
"step": 38500
|
| 3321 |
+
},
|
| 3322 |
+
{
|
| 3323 |
+
"epoch": 1.7,
|
| 3324 |
+
"grad_norm": 2.178917646408081,
|
| 3325 |
+
"learning_rate": 1.6687341556667956e-07,
|
| 3326 |
+
"loss": 1.2967,
|
| 3327 |
+
"step": 38600
|
| 3328 |
+
},
|
| 3329 |
+
{
|
| 3330 |
+
"epoch": 1.7,
|
| 3331 |
+
"grad_norm": 2.230252742767334,
|
| 3332 |
+
"learning_rate": 1.6215731799568707e-07,
|
| 3333 |
+
"loss": 1.2912,
|
| 3334 |
+
"step": 38700
|
| 3335 |
+
},
|
| 3336 |
+
{
|
| 3337 |
+
"epoch": 1.71,
|
| 3338 |
+
"grad_norm": 2.027996301651001,
|
| 3339 |
+
"learning_rate": 1.575050110172896e-07,
|
| 3340 |
+
"loss": 1.2931,
|
| 3341 |
+
"step": 38800
|
| 3342 |
+
},
|
| 3343 |
+
{
|
| 3344 |
+
"epoch": 1.71,
|
| 3345 |
+
"grad_norm": 2.343449831008911,
|
| 3346 |
+
"learning_rate": 1.5291671646132082e-07,
|
| 3347 |
+
"loss": 1.2896,
|
| 3348 |
+
"step": 38900
|
| 3349 |
+
},
|
| 3350 |
+
{
|
| 3351 |
+
"epoch": 1.71,
|
| 3352 |
+
"grad_norm": 2.1190574169158936,
|
| 3353 |
+
"learning_rate": 1.483926531053933e-07,
|
| 3354 |
+
"loss": 1.2926,
|
| 3355 |
+
"step": 39000
|
| 3356 |
+
},
|
| 3357 |
+
{
|
| 3358 |
+
"epoch": 1.71,
|
| 3359 |
+
"eval_loss": 1.2960731983184814,
|
| 3360 |
+
"eval_runtime": 1864.8274,
|
| 3361 |
+
"eval_samples_per_second": 5.14,
|
| 3362 |
+
"eval_steps_per_second": 0.643,
|
| 3363 |
+
"step": 39000
|
| 3364 |
+
},
|
| 3365 |
+
{
|
| 3366 |
+
"epoch": 1.72,
|
| 3367 |
+
"grad_norm": 2.0614373683929443,
|
| 3368 |
+
"learning_rate": 1.4393303666446873e-07,
|
| 3369 |
+
"loss": 1.2939,
|
| 3370 |
+
"step": 39100
|
| 3371 |
+
},
|
| 3372 |
+
{
|
| 3373 |
+
"epoch": 1.72,
|
| 3374 |
+
"grad_norm": 2.185314178466797,
|
| 3375 |
+
"learning_rate": 1.395380797805706e-07,
|
| 3376 |
+
"loss": 1.293,
|
| 3377 |
+
"step": 39200
|
| 3378 |
+
},
|
| 3379 |
+
{
|
| 3380 |
+
"epoch": 1.73,
|
| 3381 |
+
"grad_norm": 2.1229093074798584,
|
| 3382 |
+
"learning_rate": 1.3520799201264644e-07,
|
| 3383 |
+
"loss": 1.3041,
|
| 3384 |
+
"step": 39300
|
| 3385 |
+
},
|
| 3386 |
+
{
|
| 3387 |
+
"epoch": 1.73,
|
| 3388 |
+
"grad_norm": 2.213289976119995,
|
| 3389 |
+
"learning_rate": 1.3094297982657484e-07,
|
| 3390 |
+
"loss": 1.2956,
|
| 3391 |
+
"step": 39400
|
| 3392 |
+
},
|
| 3393 |
+
{
|
| 3394 |
+
"epoch": 1.74,
|
| 3395 |
+
"grad_norm": 2.1949591636657715,
|
| 3396 |
+
"learning_rate": 1.267432465853209e-07,
|
| 3397 |
+
"loss": 1.2928,
|
| 3398 |
+
"step": 39500
|
| 3399 |
+
},
|
| 3400 |
+
{
|
| 3401 |
+
"epoch": 1.74,
|
| 3402 |
+
"eval_loss": 1.2960156202316284,
|
| 3403 |
+
"eval_runtime": 1862.2042,
|
| 3404 |
+
"eval_samples_per_second": 5.148,
|
| 3405 |
+
"eval_steps_per_second": 0.644,
|
| 3406 |
+
"step": 39500
|
| 3407 |
+
},
|
| 3408 |
+
{
|
| 3409 |
+
"epoch": 1.74,
|
| 3410 |
+
"grad_norm": 2.0892333984375,
|
| 3411 |
+
"learning_rate": 1.2260899253924008e-07,
|
| 3412 |
+
"loss": 1.2991,
|
| 3413 |
+
"step": 39600
|
| 3414 |
+
},
|
| 3415 |
+
{
|
| 3416 |
+
"epoch": 1.75,
|
| 3417 |
+
"grad_norm": 2.1460952758789062,
|
| 3418 |
+
"learning_rate": 1.1854041481652849e-07,
|
| 3419 |
+
"loss": 1.2949,
|
| 3420 |
+
"step": 39700
|
| 3421 |
+
},
|
| 3422 |
+
{
|
| 3423 |
+
"epoch": 1.75,
|
| 3424 |
+
"grad_norm": 2.241546630859375,
|
| 3425 |
+
"learning_rate": 1.1453770741382607e-07,
|
| 3426 |
+
"loss": 1.2836,
|
| 3427 |
+
"step": 39800
|
| 3428 |
+
},
|
| 3429 |
+
{
|
| 3430 |
+
"epoch": 1.75,
|
| 3431 |
+
"grad_norm": 2.225529670715332,
|
| 3432 |
+
"learning_rate": 1.1060106118696345e-07,
|
| 3433 |
+
"loss": 1.2923,
|
| 3434 |
+
"step": 39900
|
| 3435 |
+
},
|
| 3436 |
+
{
|
| 3437 |
+
"epoch": 1.76,
|
| 3438 |
+
"grad_norm": 2.106523036956787,
|
| 3439 |
+
"learning_rate": 1.0673066384186425e-07,
|
| 3440 |
+
"loss": 1.2966,
|
| 3441 |
+
"step": 40000
|
| 3442 |
+
},
|
| 3443 |
+
{
|
| 3444 |
+
"epoch": 1.76,
|
| 3445 |
+
"eval_loss": 1.295967698097229,
|
| 3446 |
+
"eval_runtime": 1866.8915,
|
| 3447 |
+
"eval_samples_per_second": 5.135,
|
| 3448 |
+
"eval_steps_per_second": 0.642,
|
| 3449 |
+
"step": 40000
|
| 3450 |
+
}
|
| 3451 |
+
],
|
| 3452 |
+
"logging_steps": 100,
|
| 3453 |
+
"max_steps": 45496,
|
| 3454 |
+
"num_input_tokens_seen": 0,
|
| 3455 |
+
"num_train_epochs": 2,
|
| 3456 |
+
"save_steps": 1000,
|
| 3457 |
+
"total_flos": 1.403599875735552e+19,
|
| 3458 |
+
"train_batch_size": 2,
|
| 3459 |
+
"trial_name": null,
|
| 3460 |
+
"trial_params": null
|
| 3461 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e372df1cca975d4e04ae7e30b8da301558a716d1cf7bbee79ab642cb2449300
|
| 3 |
+
size 4856
|