Jamesb1974
commited on
Commit
•
d334e67
1
Parent(s):
2056e2b
Upload folder using huggingface_hub
Browse files- README.md +45 -0
- adapter_config.json +30 -0
- adapter_model.safetensors +3 -0
- checkpoint-6366/README.md +202 -0
- checkpoint-6366/adapter_config.json +30 -0
- checkpoint-6366/adapter_model.safetensors +3 -0
- checkpoint-6366/merges.txt +0 -0
- checkpoint-6366/optimizer.pt +3 -0
- checkpoint-6366/pytorch_model.bin +3 -0
- checkpoint-6366/rng_state.pth +3 -0
- checkpoint-6366/scheduler.pt +3 -0
- checkpoint-6366/special_tokens_map.json +6 -0
- checkpoint-6366/tokenizer.json +0 -0
- checkpoint-6366/tokenizer_config.json +21 -0
- checkpoint-6366/trainer_state.json +1799 -0
- checkpoint-6366/training_args.bin +3 -0
- checkpoint-6366/vocab.json +0 -0
- merges.txt +0 -0
- runs/Mar26_19-46-04_r-jamesb1974-gpu01-wtyrob2c-89c4d-ngnc1/events.out.tfevents.1711482377.r-jamesb1974-gpu01-wtyrob2c-89c4d-ngnc1.59.0 +2 -2
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +21 -0
- training_args.bin +3 -0
- training_params.json +47 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- autotrain
|
4 |
+
- text-generation-inference
|
5 |
+
- text-generation
|
6 |
+
- peft
|
7 |
+
library_name: transformers
|
8 |
+
widget:
|
9 |
+
- messages:
|
10 |
+
- role: user
|
11 |
+
content: What is your favorite condiment?
|
12 |
+
license: other
|
13 |
+
---
|
14 |
+
|
15 |
+
# Model Trained Using AutoTrain
|
16 |
+
|
17 |
+
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
|
18 |
+
|
19 |
+
# Usage
|
20 |
+
|
21 |
+
```python
|
22 |
+
|
23 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
24 |
+
|
25 |
+
model_path = "PATH_TO_THIS_REPO"
|
26 |
+
|
27 |
+
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
28 |
+
model = AutoModelForCausalLM.from_pretrained(
|
29 |
+
model_path,
|
30 |
+
device_map="auto",
|
31 |
+
torch_dtype='auto'
|
32 |
+
).eval()
|
33 |
+
|
34 |
+
# Prompt content: "hi"
|
35 |
+
messages = [
|
36 |
+
{"role": "user", "content": "hi"}
|
37 |
+
]
|
38 |
+
|
39 |
+
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
|
40 |
+
output_ids = model.generate(input_ids.to('cuda'))
|
41 |
+
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
|
42 |
+
|
43 |
+
# Model response: "Hello! How can I assist you today?"
|
44 |
+
print(response)
|
45 |
+
```
|
adapter_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "openai-community/gpt2",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"c_fc",
|
24 |
+
"c_attn",
|
25 |
+
"c_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM",
|
28 |
+
"use_dora": false,
|
29 |
+
"use_rslora": false
|
30 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9ff5e1c3f8a1ad91cdccc081a6c163c6477e3a5ebc7962db2f6c679b32d7493
|
3 |
+
size 9449344
|
checkpoint-6366/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: openai-community/gpt2
|
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 0.10.0
|
checkpoint-6366/adapter_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "openai-community/gpt2",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"c_fc",
|
24 |
+
"c_attn",
|
25 |
+
"c_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM",
|
28 |
+
"use_dora": false,
|
29 |
+
"use_rslora": false
|
30 |
+
}
|
checkpoint-6366/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9ff5e1c3f8a1ad91cdccc081a6c163c6477e3a5ebc7962db2f6c679b32d7493
|
3 |
+
size 9449344
|
checkpoint-6366/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-6366/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9d30031b9ee39eca8403fa753c7495804d32c38376fd89ab9284aa1c813ca2d
|
3 |
+
size 18955258
|
checkpoint-6366/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
|
3 |
+
size 888
|
checkpoint-6366/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:087add2a618d3fc14510cd2ca22f1aefb1c83125c7d42f5389e6f90436f5363c
|
3 |
+
size 14244
|
checkpoint-6366/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3a8eea645e5d8b4dd952697b6ba6565c956e27b3327524d93be41a93401c0b3
|
3 |
+
size 1064
|
checkpoint-6366/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
checkpoint-6366/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-6366/tokenizer_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
}
|
12 |
+
},
|
13 |
+
"bos_token": "<|endoftext|>",
|
14 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
15 |
+
"clean_up_tokenization_spaces": true,
|
16 |
+
"eos_token": "<|endoftext|>",
|
17 |
+
"model_max_length": 1024,
|
18 |
+
"pad_token": "<|endoftext|>",
|
19 |
+
"tokenizer_class": "GPT2Tokenizer",
|
20 |
+
"unk_token": "<|endoftext|>"
|
21 |
+
}
|
checkpoint-6366/trainer_state.json
ADDED
@@ -0,0 +1,1799 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 6.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 6366,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02,
|
13 |
+
"grad_norm": 1.4550137519836426,
|
14 |
+
"learning_rate": 1.1773940345368917e-06,
|
15 |
+
"loss": 2.7174,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.05,
|
20 |
+
"grad_norm": 1.3239152431488037,
|
21 |
+
"learning_rate": 2.3547880690737835e-06,
|
22 |
+
"loss": 2.7301,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.07,
|
27 |
+
"grad_norm": 1.2503877878189087,
|
28 |
+
"learning_rate": 3.532182103610675e-06,
|
29 |
+
"loss": 2.7177,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.09,
|
34 |
+
"grad_norm": 1.4258066415786743,
|
35 |
+
"learning_rate": 4.709576138147567e-06,
|
36 |
+
"loss": 2.6627,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.12,
|
41 |
+
"grad_norm": 1.5414007902145386,
|
42 |
+
"learning_rate": 5.886970172684459e-06,
|
43 |
+
"loss": 2.5528,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.14,
|
48 |
+
"grad_norm": 1.1376500129699707,
|
49 |
+
"learning_rate": 7.06436420722135e-06,
|
50 |
+
"loss": 2.4215,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.16,
|
55 |
+
"grad_norm": 0.903887152671814,
|
56 |
+
"learning_rate": 8.241758241758243e-06,
|
57 |
+
"loss": 2.2661,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.19,
|
62 |
+
"grad_norm": 0.7810421586036682,
|
63 |
+
"learning_rate": 9.419152276295134e-06,
|
64 |
+
"loss": 2.1661,
|
65 |
+
"step": 200
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.21,
|
69 |
+
"grad_norm": 0.806953489780426,
|
70 |
+
"learning_rate": 1.054945054945055e-05,
|
71 |
+
"loss": 2.0261,
|
72 |
+
"step": 225
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.24,
|
76 |
+
"grad_norm": 0.6058614253997803,
|
77 |
+
"learning_rate": 1.1726844583987441e-05,
|
78 |
+
"loss": 1.9551,
|
79 |
+
"step": 250
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.26,
|
83 |
+
"grad_norm": 0.528014063835144,
|
84 |
+
"learning_rate": 1.2904238618524332e-05,
|
85 |
+
"loss": 1.8942,
|
86 |
+
"step": 275
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.28,
|
90 |
+
"grad_norm": 0.47531402111053467,
|
91 |
+
"learning_rate": 1.4081632653061225e-05,
|
92 |
+
"loss": 1.7891,
|
93 |
+
"step": 300
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.31,
|
97 |
+
"grad_norm": 0.47076013684272766,
|
98 |
+
"learning_rate": 1.5259026687598116e-05,
|
99 |
+
"loss": 1.7725,
|
100 |
+
"step": 325
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.33,
|
104 |
+
"grad_norm": 0.5390304327011108,
|
105 |
+
"learning_rate": 1.643642072213501e-05,
|
106 |
+
"loss": 1.7132,
|
107 |
+
"step": 350
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.35,
|
111 |
+
"grad_norm": 0.6033918857574463,
|
112 |
+
"learning_rate": 1.7613814756671898e-05,
|
113 |
+
"loss": 1.7432,
|
114 |
+
"step": 375
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.38,
|
118 |
+
"grad_norm": 0.6497958302497864,
|
119 |
+
"learning_rate": 1.8791208791208793e-05,
|
120 |
+
"loss": 1.7009,
|
121 |
+
"step": 400
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.4,
|
125 |
+
"grad_norm": 0.3979990780353546,
|
126 |
+
"learning_rate": 1.9968602825745684e-05,
|
127 |
+
"loss": 1.6574,
|
128 |
+
"step": 425
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.42,
|
132 |
+
"grad_norm": 0.39559292793273926,
|
133 |
+
"learning_rate": 2.1145996860282575e-05,
|
134 |
+
"loss": 1.596,
|
135 |
+
"step": 450
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.45,
|
139 |
+
"grad_norm": 0.4321981370449066,
|
140 |
+
"learning_rate": 2.2323390894819466e-05,
|
141 |
+
"loss": 1.5367,
|
142 |
+
"step": 475
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.47,
|
146 |
+
"grad_norm": 0.4313070476055145,
|
147 |
+
"learning_rate": 2.350078492935636e-05,
|
148 |
+
"loss": 1.5457,
|
149 |
+
"step": 500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.49,
|
153 |
+
"grad_norm": 0.4958736002445221,
|
154 |
+
"learning_rate": 2.4678178963893248e-05,
|
155 |
+
"loss": 1.5258,
|
156 |
+
"step": 525
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.52,
|
160 |
+
"grad_norm": 0.5069326758384705,
|
161 |
+
"learning_rate": 2.5855572998430143e-05,
|
162 |
+
"loss": 1.5096,
|
163 |
+
"step": 550
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.54,
|
167 |
+
"grad_norm": 0.5262688994407654,
|
168 |
+
"learning_rate": 2.7032967032967034e-05,
|
169 |
+
"loss": 1.4645,
|
170 |
+
"step": 575
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.57,
|
174 |
+
"grad_norm": 0.6320958137512207,
|
175 |
+
"learning_rate": 2.821036106750393e-05,
|
176 |
+
"loss": 1.4081,
|
177 |
+
"step": 600
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.59,
|
181 |
+
"grad_norm": 0.44404885172843933,
|
182 |
+
"learning_rate": 2.9387755102040816e-05,
|
183 |
+
"loss": 1.4278,
|
184 |
+
"step": 625
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.61,
|
188 |
+
"grad_norm": 0.5611394047737122,
|
189 |
+
"learning_rate": 2.9937161808343517e-05,
|
190 |
+
"loss": 1.359,
|
191 |
+
"step": 650
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.64,
|
195 |
+
"grad_norm": 0.50496906042099,
|
196 |
+
"learning_rate": 2.980624890905917e-05,
|
197 |
+
"loss": 1.3366,
|
198 |
+
"step": 675
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.66,
|
202 |
+
"grad_norm": 0.49874988198280334,
|
203 |
+
"learning_rate": 2.967533600977483e-05,
|
204 |
+
"loss": 1.3175,
|
205 |
+
"step": 700
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.68,
|
209 |
+
"grad_norm": 0.4491003453731537,
|
210 |
+
"learning_rate": 2.954442311049049e-05,
|
211 |
+
"loss": 1.351,
|
212 |
+
"step": 725
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.71,
|
216 |
+
"grad_norm": 0.6342208981513977,
|
217 |
+
"learning_rate": 2.9413510211206147e-05,
|
218 |
+
"loss": 1.353,
|
219 |
+
"step": 750
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.73,
|
223 |
+
"grad_norm": 0.4711619019508362,
|
224 |
+
"learning_rate": 2.9282597311921802e-05,
|
225 |
+
"loss": 1.2784,
|
226 |
+
"step": 775
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.75,
|
230 |
+
"grad_norm": 0.533415675163269,
|
231 |
+
"learning_rate": 2.9151684412637457e-05,
|
232 |
+
"loss": 1.2759,
|
233 |
+
"step": 800
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.78,
|
237 |
+
"grad_norm": 0.6422008872032166,
|
238 |
+
"learning_rate": 2.9020771513353116e-05,
|
239 |
+
"loss": 1.2829,
|
240 |
+
"step": 825
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.8,
|
244 |
+
"grad_norm": 0.5320819616317749,
|
245 |
+
"learning_rate": 2.8889858614068774e-05,
|
246 |
+
"loss": 1.294,
|
247 |
+
"step": 850
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.82,
|
251 |
+
"grad_norm": 0.6057177782058716,
|
252 |
+
"learning_rate": 2.8758945714784433e-05,
|
253 |
+
"loss": 1.2728,
|
254 |
+
"step": 875
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.85,
|
258 |
+
"grad_norm": 0.47568175196647644,
|
259 |
+
"learning_rate": 2.8628032815500088e-05,
|
260 |
+
"loss": 1.2308,
|
261 |
+
"step": 900
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.87,
|
265 |
+
"grad_norm": 0.5981771349906921,
|
266 |
+
"learning_rate": 2.8497119916215743e-05,
|
267 |
+
"loss": 1.2759,
|
268 |
+
"step": 925
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.9,
|
272 |
+
"grad_norm": 0.5540325045585632,
|
273 |
+
"learning_rate": 2.83662070169314e-05,
|
274 |
+
"loss": 1.2731,
|
275 |
+
"step": 950
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.92,
|
279 |
+
"grad_norm": 0.4720264673233032,
|
280 |
+
"learning_rate": 2.823529411764706e-05,
|
281 |
+
"loss": 1.1777,
|
282 |
+
"step": 975
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.94,
|
286 |
+
"grad_norm": 0.5205626487731934,
|
287 |
+
"learning_rate": 2.8104381218362718e-05,
|
288 |
+
"loss": 1.2607,
|
289 |
+
"step": 1000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.97,
|
293 |
+
"grad_norm": 0.6065472960472107,
|
294 |
+
"learning_rate": 2.7973468319078373e-05,
|
295 |
+
"loss": 1.2371,
|
296 |
+
"step": 1025
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.99,
|
300 |
+
"grad_norm": 0.5618084669113159,
|
301 |
+
"learning_rate": 2.7842555419794032e-05,
|
302 |
+
"loss": 1.2351,
|
303 |
+
"step": 1050
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 1.01,
|
307 |
+
"grad_norm": 0.49749478697776794,
|
308 |
+
"learning_rate": 2.7711642520509687e-05,
|
309 |
+
"loss": 1.229,
|
310 |
+
"step": 1075
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 1.04,
|
314 |
+
"grad_norm": 0.5713375210762024,
|
315 |
+
"learning_rate": 2.7580729621225345e-05,
|
316 |
+
"loss": 1.2189,
|
317 |
+
"step": 1100
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 1.06,
|
321 |
+
"grad_norm": 0.5449201464653015,
|
322 |
+
"learning_rate": 2.7449816721941004e-05,
|
323 |
+
"loss": 1.2217,
|
324 |
+
"step": 1125
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 1.08,
|
328 |
+
"grad_norm": 0.5718939304351807,
|
329 |
+
"learning_rate": 2.731890382265666e-05,
|
330 |
+
"loss": 1.2169,
|
331 |
+
"step": 1150
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 1.11,
|
335 |
+
"grad_norm": 0.5724524259567261,
|
336 |
+
"learning_rate": 2.7187990923372317e-05,
|
337 |
+
"loss": 1.1946,
|
338 |
+
"step": 1175
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.13,
|
342 |
+
"grad_norm": 0.4745756685733795,
|
343 |
+
"learning_rate": 2.7057078024087976e-05,
|
344 |
+
"loss": 1.1995,
|
345 |
+
"step": 1200
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 1.15,
|
349 |
+
"grad_norm": 0.679215669631958,
|
350 |
+
"learning_rate": 2.692616512480363e-05,
|
351 |
+
"loss": 1.1511,
|
352 |
+
"step": 1225
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 1.18,
|
356 |
+
"grad_norm": 0.5852200388908386,
|
357 |
+
"learning_rate": 2.679525222551929e-05,
|
358 |
+
"loss": 1.1293,
|
359 |
+
"step": 1250
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 1.2,
|
363 |
+
"grad_norm": 0.5490656495094299,
|
364 |
+
"learning_rate": 2.6664339326234944e-05,
|
365 |
+
"loss": 1.192,
|
366 |
+
"step": 1275
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 1.23,
|
370 |
+
"grad_norm": 0.7541109919548035,
|
371 |
+
"learning_rate": 2.6533426426950603e-05,
|
372 |
+
"loss": 1.2221,
|
373 |
+
"step": 1300
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 1.25,
|
377 |
+
"grad_norm": 0.7117947340011597,
|
378 |
+
"learning_rate": 2.640251352766626e-05,
|
379 |
+
"loss": 1.1575,
|
380 |
+
"step": 1325
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 1.27,
|
384 |
+
"grad_norm": 0.5711504817008972,
|
385 |
+
"learning_rate": 2.627160062838192e-05,
|
386 |
+
"loss": 1.1758,
|
387 |
+
"step": 1350
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 1.3,
|
391 |
+
"grad_norm": 0.6238616108894348,
|
392 |
+
"learning_rate": 2.614068772909757e-05,
|
393 |
+
"loss": 1.1511,
|
394 |
+
"step": 1375
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 1.32,
|
398 |
+
"grad_norm": 0.5755292773246765,
|
399 |
+
"learning_rate": 2.600977482981323e-05,
|
400 |
+
"loss": 1.1309,
|
401 |
+
"step": 1400
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 1.34,
|
405 |
+
"grad_norm": 0.5652589797973633,
|
406 |
+
"learning_rate": 2.587886193052889e-05,
|
407 |
+
"loss": 1.1294,
|
408 |
+
"step": 1425
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 1.37,
|
412 |
+
"grad_norm": 0.5230275988578796,
|
413 |
+
"learning_rate": 2.5747949031244547e-05,
|
414 |
+
"loss": 1.1318,
|
415 |
+
"step": 1450
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 1.39,
|
419 |
+
"grad_norm": 0.6454095840454102,
|
420 |
+
"learning_rate": 2.5617036131960205e-05,
|
421 |
+
"loss": 1.1668,
|
422 |
+
"step": 1475
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 1.41,
|
426 |
+
"grad_norm": 0.7409027218818665,
|
427 |
+
"learning_rate": 2.5486123232675857e-05,
|
428 |
+
"loss": 1.1187,
|
429 |
+
"step": 1500
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 1.44,
|
433 |
+
"grad_norm": 0.5434130430221558,
|
434 |
+
"learning_rate": 2.5355210333391516e-05,
|
435 |
+
"loss": 1.186,
|
436 |
+
"step": 1525
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 1.46,
|
440 |
+
"grad_norm": 0.5816170573234558,
|
441 |
+
"learning_rate": 2.5224297434107174e-05,
|
442 |
+
"loss": 1.126,
|
443 |
+
"step": 1550
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 1.48,
|
447 |
+
"grad_norm": 0.5217471122741699,
|
448 |
+
"learning_rate": 2.5093384534822833e-05,
|
449 |
+
"loss": 1.1651,
|
450 |
+
"step": 1575
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 1.51,
|
454 |
+
"grad_norm": 0.6262175440788269,
|
455 |
+
"learning_rate": 2.496247163553849e-05,
|
456 |
+
"loss": 1.1083,
|
457 |
+
"step": 1600
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 1.53,
|
461 |
+
"grad_norm": 0.7060381174087524,
|
462 |
+
"learning_rate": 2.4831558736254146e-05,
|
463 |
+
"loss": 1.1523,
|
464 |
+
"step": 1625
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 1.56,
|
468 |
+
"grad_norm": 0.627524197101593,
|
469 |
+
"learning_rate": 2.47006458369698e-05,
|
470 |
+
"loss": 1.1575,
|
471 |
+
"step": 1650
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 1.58,
|
475 |
+
"grad_norm": 0.6749070286750793,
|
476 |
+
"learning_rate": 2.456973293768546e-05,
|
477 |
+
"loss": 1.1535,
|
478 |
+
"step": 1675
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 1.6,
|
482 |
+
"grad_norm": 0.6341940760612488,
|
483 |
+
"learning_rate": 2.4438820038401118e-05,
|
484 |
+
"loss": 1.1009,
|
485 |
+
"step": 1700
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 1.63,
|
489 |
+
"grad_norm": 0.5389090776443481,
|
490 |
+
"learning_rate": 2.4307907139116777e-05,
|
491 |
+
"loss": 1.1221,
|
492 |
+
"step": 1725
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 1.65,
|
496 |
+
"grad_norm": 0.6468391418457031,
|
497 |
+
"learning_rate": 2.417699423983243e-05,
|
498 |
+
"loss": 1.1398,
|
499 |
+
"step": 1750
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 1.67,
|
503 |
+
"grad_norm": 0.5632995367050171,
|
504 |
+
"learning_rate": 2.404608134054809e-05,
|
505 |
+
"loss": 1.098,
|
506 |
+
"step": 1775
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 1.7,
|
510 |
+
"grad_norm": 0.5900394320487976,
|
511 |
+
"learning_rate": 2.3915168441263745e-05,
|
512 |
+
"loss": 1.1081,
|
513 |
+
"step": 1800
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 1.72,
|
517 |
+
"grad_norm": 0.5528013110160828,
|
518 |
+
"learning_rate": 2.3784255541979404e-05,
|
519 |
+
"loss": 1.1314,
|
520 |
+
"step": 1825
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 1.74,
|
524 |
+
"grad_norm": 0.5529065132141113,
|
525 |
+
"learning_rate": 2.3653342642695062e-05,
|
526 |
+
"loss": 1.151,
|
527 |
+
"step": 1850
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 1.77,
|
531 |
+
"grad_norm": 0.6382936835289001,
|
532 |
+
"learning_rate": 2.3522429743410717e-05,
|
533 |
+
"loss": 1.0977,
|
534 |
+
"step": 1875
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 1.79,
|
538 |
+
"grad_norm": 0.6123020648956299,
|
539 |
+
"learning_rate": 2.3391516844126376e-05,
|
540 |
+
"loss": 1.1206,
|
541 |
+
"step": 1900
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 1.81,
|
545 |
+
"grad_norm": 0.5873188376426697,
|
546 |
+
"learning_rate": 2.3260603944842034e-05,
|
547 |
+
"loss": 1.1202,
|
548 |
+
"step": 1925
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 1.84,
|
552 |
+
"grad_norm": 0.6366047859191895,
|
553 |
+
"learning_rate": 2.312969104555769e-05,
|
554 |
+
"loss": 1.1159,
|
555 |
+
"step": 1950
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 1.86,
|
559 |
+
"grad_norm": 0.6183773875236511,
|
560 |
+
"learning_rate": 2.2998778146273344e-05,
|
561 |
+
"loss": 1.1617,
|
562 |
+
"step": 1975
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 1.89,
|
566 |
+
"grad_norm": 0.6744990944862366,
|
567 |
+
"learning_rate": 2.2867865246989003e-05,
|
568 |
+
"loss": 1.1109,
|
569 |
+
"step": 2000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 1.91,
|
573 |
+
"grad_norm": 0.6510053277015686,
|
574 |
+
"learning_rate": 2.273695234770466e-05,
|
575 |
+
"loss": 1.0807,
|
576 |
+
"step": 2025
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 1.93,
|
580 |
+
"grad_norm": 0.637360692024231,
|
581 |
+
"learning_rate": 2.260603944842032e-05,
|
582 |
+
"loss": 1.122,
|
583 |
+
"step": 2050
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 1.96,
|
587 |
+
"grad_norm": 0.65646892786026,
|
588 |
+
"learning_rate": 2.2475126549135978e-05,
|
589 |
+
"loss": 1.1264,
|
590 |
+
"step": 2075
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 1.98,
|
594 |
+
"grad_norm": 0.5863879919052124,
|
595 |
+
"learning_rate": 2.234421364985163e-05,
|
596 |
+
"loss": 1.0748,
|
597 |
+
"step": 2100
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 2.0,
|
601 |
+
"grad_norm": 0.6076034903526306,
|
602 |
+
"learning_rate": 2.221330075056729e-05,
|
603 |
+
"loss": 1.0891,
|
604 |
+
"step": 2125
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 2.03,
|
608 |
+
"grad_norm": 0.6606038808822632,
|
609 |
+
"learning_rate": 2.2082387851282947e-05,
|
610 |
+
"loss": 1.1157,
|
611 |
+
"step": 2150
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 2.05,
|
615 |
+
"grad_norm": 0.7062047719955444,
|
616 |
+
"learning_rate": 2.1951474951998605e-05,
|
617 |
+
"loss": 1.0886,
|
618 |
+
"step": 2175
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 2.07,
|
622 |
+
"grad_norm": 0.5990228056907654,
|
623 |
+
"learning_rate": 2.1820562052714264e-05,
|
624 |
+
"loss": 1.1008,
|
625 |
+
"step": 2200
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 2.1,
|
629 |
+
"grad_norm": 0.6606985926628113,
|
630 |
+
"learning_rate": 2.168964915342992e-05,
|
631 |
+
"loss": 1.0696,
|
632 |
+
"step": 2225
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 2.12,
|
636 |
+
"grad_norm": 0.6489419937133789,
|
637 |
+
"learning_rate": 2.1558736254145574e-05,
|
638 |
+
"loss": 1.1455,
|
639 |
+
"step": 2250
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 2.14,
|
643 |
+
"grad_norm": 0.6855771541595459,
|
644 |
+
"learning_rate": 2.1427823354861232e-05,
|
645 |
+
"loss": 1.099,
|
646 |
+
"step": 2275
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 2.17,
|
650 |
+
"grad_norm": 0.620990514755249,
|
651 |
+
"learning_rate": 2.129691045557689e-05,
|
652 |
+
"loss": 1.0636,
|
653 |
+
"step": 2300
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 2.19,
|
657 |
+
"grad_norm": 0.6790271401405334,
|
658 |
+
"learning_rate": 2.116599755629255e-05,
|
659 |
+
"loss": 1.1138,
|
660 |
+
"step": 2325
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 2.21,
|
664 |
+
"grad_norm": 0.7244608998298645,
|
665 |
+
"learning_rate": 2.1035084657008204e-05,
|
666 |
+
"loss": 1.1204,
|
667 |
+
"step": 2350
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 2.24,
|
671 |
+
"grad_norm": 0.627005934715271,
|
672 |
+
"learning_rate": 2.090417175772386e-05,
|
673 |
+
"loss": 1.0882,
|
674 |
+
"step": 2375
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 2.26,
|
678 |
+
"grad_norm": 0.6555240750312805,
|
679 |
+
"learning_rate": 2.0773258858439518e-05,
|
680 |
+
"loss": 1.1137,
|
681 |
+
"step": 2400
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 2.29,
|
685 |
+
"grad_norm": 0.5681769847869873,
|
686 |
+
"learning_rate": 2.0642345959155177e-05,
|
687 |
+
"loss": 1.0877,
|
688 |
+
"step": 2425
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 2.31,
|
692 |
+
"grad_norm": 0.7020453810691833,
|
693 |
+
"learning_rate": 2.051143305987083e-05,
|
694 |
+
"loss": 1.0683,
|
695 |
+
"step": 2450
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 2.33,
|
699 |
+
"grad_norm": 0.569598376750946,
|
700 |
+
"learning_rate": 2.038052016058649e-05,
|
701 |
+
"loss": 1.0832,
|
702 |
+
"step": 2475
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 2.36,
|
706 |
+
"grad_norm": 0.6652840971946716,
|
707 |
+
"learning_rate": 2.024960726130215e-05,
|
708 |
+
"loss": 1.0934,
|
709 |
+
"step": 2500
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 2.38,
|
713 |
+
"grad_norm": 0.5610460042953491,
|
714 |
+
"learning_rate": 2.0118694362017804e-05,
|
715 |
+
"loss": 1.0266,
|
716 |
+
"step": 2525
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 2.4,
|
720 |
+
"grad_norm": 0.8069761395454407,
|
721 |
+
"learning_rate": 1.9987781462733462e-05,
|
722 |
+
"loss": 1.1016,
|
723 |
+
"step": 2550
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 2.43,
|
727 |
+
"grad_norm": 0.5885408520698547,
|
728 |
+
"learning_rate": 1.9856868563449117e-05,
|
729 |
+
"loss": 1.0981,
|
730 |
+
"step": 2575
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 2.45,
|
734 |
+
"grad_norm": 0.7160201072692871,
|
735 |
+
"learning_rate": 1.9725955664164776e-05,
|
736 |
+
"loss": 1.064,
|
737 |
+
"step": 2600
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 2.47,
|
741 |
+
"grad_norm": 0.6466575264930725,
|
742 |
+
"learning_rate": 1.9595042764880434e-05,
|
743 |
+
"loss": 1.103,
|
744 |
+
"step": 2625
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 2.5,
|
748 |
+
"grad_norm": 0.826030969619751,
|
749 |
+
"learning_rate": 1.9464129865596093e-05,
|
750 |
+
"loss": 1.1049,
|
751 |
+
"step": 2650
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 2.52,
|
755 |
+
"grad_norm": 0.6309208273887634,
|
756 |
+
"learning_rate": 1.9333216966311748e-05,
|
757 |
+
"loss": 1.1226,
|
758 |
+
"step": 2675
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 2.54,
|
762 |
+
"grad_norm": 0.7945444583892822,
|
763 |
+
"learning_rate": 1.9202304067027403e-05,
|
764 |
+
"loss": 1.0658,
|
765 |
+
"step": 2700
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 2.57,
|
769 |
+
"grad_norm": 0.5897024869918823,
|
770 |
+
"learning_rate": 1.907139116774306e-05,
|
771 |
+
"loss": 1.1115,
|
772 |
+
"step": 2725
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 2.59,
|
776 |
+
"grad_norm": 0.6963732242584229,
|
777 |
+
"learning_rate": 1.894047826845872e-05,
|
778 |
+
"loss": 1.0736,
|
779 |
+
"step": 2750
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 2.62,
|
783 |
+
"grad_norm": 0.6119255423545837,
|
784 |
+
"learning_rate": 1.8809565369174378e-05,
|
785 |
+
"loss": 1.0645,
|
786 |
+
"step": 2775
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 2.64,
|
790 |
+
"grad_norm": 0.674546480178833,
|
791 |
+
"learning_rate": 1.8678652469890037e-05,
|
792 |
+
"loss": 1.087,
|
793 |
+
"step": 2800
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 2.66,
|
797 |
+
"grad_norm": 0.6722444891929626,
|
798 |
+
"learning_rate": 1.854773957060569e-05,
|
799 |
+
"loss": 1.0613,
|
800 |
+
"step": 2825
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 2.69,
|
804 |
+
"grad_norm": 0.6713480949401855,
|
805 |
+
"learning_rate": 1.8416826671321347e-05,
|
806 |
+
"loss": 1.0695,
|
807 |
+
"step": 2850
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 2.71,
|
811 |
+
"grad_norm": 0.7733056545257568,
|
812 |
+
"learning_rate": 1.8285913772037005e-05,
|
813 |
+
"loss": 1.0502,
|
814 |
+
"step": 2875
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 2.73,
|
818 |
+
"grad_norm": 0.6311067938804626,
|
819 |
+
"learning_rate": 1.8155000872752664e-05,
|
820 |
+
"loss": 1.056,
|
821 |
+
"step": 2900
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 2.76,
|
825 |
+
"grad_norm": 0.6068445444107056,
|
826 |
+
"learning_rate": 1.8024087973468322e-05,
|
827 |
+
"loss": 1.0751,
|
828 |
+
"step": 2925
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 2.78,
|
832 |
+
"grad_norm": 0.6926267743110657,
|
833 |
+
"learning_rate": 1.7893175074183977e-05,
|
834 |
+
"loss": 1.0392,
|
835 |
+
"step": 2950
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 2.8,
|
839 |
+
"grad_norm": 0.6936379075050354,
|
840 |
+
"learning_rate": 1.7762262174899632e-05,
|
841 |
+
"loss": 1.0896,
|
842 |
+
"step": 2975
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 2.83,
|
846 |
+
"grad_norm": 0.6111378073692322,
|
847 |
+
"learning_rate": 1.763134927561529e-05,
|
848 |
+
"loss": 1.068,
|
849 |
+
"step": 3000
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 2.85,
|
853 |
+
"grad_norm": 0.5566198229789734,
|
854 |
+
"learning_rate": 1.750043637633095e-05,
|
855 |
+
"loss": 1.094,
|
856 |
+
"step": 3025
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 2.87,
|
860 |
+
"grad_norm": 0.6551353335380554,
|
861 |
+
"learning_rate": 1.7369523477046604e-05,
|
862 |
+
"loss": 1.0362,
|
863 |
+
"step": 3050
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 2.9,
|
867 |
+
"grad_norm": 0.702276349067688,
|
868 |
+
"learning_rate": 1.7238610577762263e-05,
|
869 |
+
"loss": 1.0609,
|
870 |
+
"step": 3075
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 2.92,
|
874 |
+
"grad_norm": 0.5946235060691833,
|
875 |
+
"learning_rate": 1.7107697678477918e-05,
|
876 |
+
"loss": 1.0816,
|
877 |
+
"step": 3100
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 2.95,
|
881 |
+
"grad_norm": 0.5896125435829163,
|
882 |
+
"learning_rate": 1.6976784779193576e-05,
|
883 |
+
"loss": 1.0511,
|
884 |
+
"step": 3125
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 2.97,
|
888 |
+
"grad_norm": 0.7790045738220215,
|
889 |
+
"learning_rate": 1.6845871879909235e-05,
|
890 |
+
"loss": 1.0315,
|
891 |
+
"step": 3150
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 2.99,
|
895 |
+
"grad_norm": 0.6814244985580444,
|
896 |
+
"learning_rate": 1.671495898062489e-05,
|
897 |
+
"loss": 1.0399,
|
898 |
+
"step": 3175
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 3.02,
|
902 |
+
"grad_norm": 0.6677020788192749,
|
903 |
+
"learning_rate": 1.658404608134055e-05,
|
904 |
+
"loss": 1.0403,
|
905 |
+
"step": 3200
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 3.04,
|
909 |
+
"grad_norm": 0.5795513987541199,
|
910 |
+
"learning_rate": 1.6453133182056207e-05,
|
911 |
+
"loss": 1.076,
|
912 |
+
"step": 3225
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 3.06,
|
916 |
+
"grad_norm": 0.8617599606513977,
|
917 |
+
"learning_rate": 1.6322220282771862e-05,
|
918 |
+
"loss": 1.0515,
|
919 |
+
"step": 3250
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 3.09,
|
923 |
+
"grad_norm": 0.6513819098472595,
|
924 |
+
"learning_rate": 1.619130738348752e-05,
|
925 |
+
"loss": 1.0493,
|
926 |
+
"step": 3275
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 3.11,
|
930 |
+
"grad_norm": 0.7479323148727417,
|
931 |
+
"learning_rate": 1.6060394484203176e-05,
|
932 |
+
"loss": 1.0876,
|
933 |
+
"step": 3300
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 3.13,
|
937 |
+
"grad_norm": 0.718534529209137,
|
938 |
+
"learning_rate": 1.5929481584918834e-05,
|
939 |
+
"loss": 1.029,
|
940 |
+
"step": 3325
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 3.16,
|
944 |
+
"grad_norm": 0.6990604400634766,
|
945 |
+
"learning_rate": 1.5798568685634493e-05,
|
946 |
+
"loss": 1.015,
|
947 |
+
"step": 3350
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 3.18,
|
951 |
+
"grad_norm": 0.6723743677139282,
|
952 |
+
"learning_rate": 1.566765578635015e-05,
|
953 |
+
"loss": 1.0693,
|
954 |
+
"step": 3375
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 3.2,
|
958 |
+
"grad_norm": 0.7294295430183411,
|
959 |
+
"learning_rate": 1.5536742887065806e-05,
|
960 |
+
"loss": 1.0229,
|
961 |
+
"step": 3400
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 3.23,
|
965 |
+
"grad_norm": 0.7458708882331848,
|
966 |
+
"learning_rate": 1.540582998778146e-05,
|
967 |
+
"loss": 1.0861,
|
968 |
+
"step": 3425
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 3.25,
|
972 |
+
"grad_norm": 0.702514111995697,
|
973 |
+
"learning_rate": 1.527491708849712e-05,
|
974 |
+
"loss": 1.0729,
|
975 |
+
"step": 3450
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 3.28,
|
979 |
+
"grad_norm": 0.6749513745307922,
|
980 |
+
"learning_rate": 1.5144004189212778e-05,
|
981 |
+
"loss": 1.0461,
|
982 |
+
"step": 3475
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 3.3,
|
986 |
+
"grad_norm": 0.6903010010719299,
|
987 |
+
"learning_rate": 1.5013091289928435e-05,
|
988 |
+
"loss": 1.0243,
|
989 |
+
"step": 3500
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 3.32,
|
993 |
+
"grad_norm": 0.6058205366134644,
|
994 |
+
"learning_rate": 1.4882178390644092e-05,
|
995 |
+
"loss": 1.058,
|
996 |
+
"step": 3525
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 3.35,
|
1000 |
+
"grad_norm": 0.7527756690979004,
|
1001 |
+
"learning_rate": 1.475126549135975e-05,
|
1002 |
+
"loss": 1.0847,
|
1003 |
+
"step": 3550
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 3.37,
|
1007 |
+
"grad_norm": 0.7360561490058899,
|
1008 |
+
"learning_rate": 1.4620352592075405e-05,
|
1009 |
+
"loss": 1.05,
|
1010 |
+
"step": 3575
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 3.39,
|
1014 |
+
"grad_norm": 0.616054356098175,
|
1015 |
+
"learning_rate": 1.4489439692791064e-05,
|
1016 |
+
"loss": 1.0508,
|
1017 |
+
"step": 3600
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 3.42,
|
1021 |
+
"grad_norm": 0.6187878847122192,
|
1022 |
+
"learning_rate": 1.435852679350672e-05,
|
1023 |
+
"loss": 1.0636,
|
1024 |
+
"step": 3625
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 3.44,
|
1028 |
+
"grad_norm": 0.7025036215782166,
|
1029 |
+
"learning_rate": 1.4227613894222377e-05,
|
1030 |
+
"loss": 1.061,
|
1031 |
+
"step": 3650
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 3.46,
|
1035 |
+
"grad_norm": 0.6583489179611206,
|
1036 |
+
"learning_rate": 1.4096700994938036e-05,
|
1037 |
+
"loss": 1.0788,
|
1038 |
+
"step": 3675
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 3.49,
|
1042 |
+
"grad_norm": 0.6254659295082092,
|
1043 |
+
"learning_rate": 1.3965788095653692e-05,
|
1044 |
+
"loss": 1.0755,
|
1045 |
+
"step": 3700
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 3.51,
|
1049 |
+
"grad_norm": 0.6398507356643677,
|
1050 |
+
"learning_rate": 1.383487519636935e-05,
|
1051 |
+
"loss": 1.0371,
|
1052 |
+
"step": 3725
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 3.53,
|
1056 |
+
"grad_norm": 0.684704065322876,
|
1057 |
+
"learning_rate": 1.3703962297085006e-05,
|
1058 |
+
"loss": 1.0261,
|
1059 |
+
"step": 3750
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 3.56,
|
1063 |
+
"grad_norm": 0.6592278480529785,
|
1064 |
+
"learning_rate": 1.3573049397800665e-05,
|
1065 |
+
"loss": 1.0256,
|
1066 |
+
"step": 3775
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 3.58,
|
1070 |
+
"grad_norm": 0.7980201244354248,
|
1071 |
+
"learning_rate": 1.344213649851632e-05,
|
1072 |
+
"loss": 1.0478,
|
1073 |
+
"step": 3800
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 3.61,
|
1077 |
+
"grad_norm": 0.6509789228439331,
|
1078 |
+
"learning_rate": 1.3311223599231978e-05,
|
1079 |
+
"loss": 1.0565,
|
1080 |
+
"step": 3825
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 3.63,
|
1084 |
+
"grad_norm": 0.6620888113975525,
|
1085 |
+
"learning_rate": 1.3180310699947637e-05,
|
1086 |
+
"loss": 1.0396,
|
1087 |
+
"step": 3850
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 3.65,
|
1091 |
+
"grad_norm": 0.9185547828674316,
|
1092 |
+
"learning_rate": 1.3049397800663292e-05,
|
1093 |
+
"loss": 1.0543,
|
1094 |
+
"step": 3875
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 3.68,
|
1098 |
+
"grad_norm": 0.6710821986198425,
|
1099 |
+
"learning_rate": 1.291848490137895e-05,
|
1100 |
+
"loss": 1.0762,
|
1101 |
+
"step": 3900
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 3.7,
|
1105 |
+
"grad_norm": 0.7180879712104797,
|
1106 |
+
"learning_rate": 1.2787572002094607e-05,
|
1107 |
+
"loss": 1.0178,
|
1108 |
+
"step": 3925
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 3.72,
|
1112 |
+
"grad_norm": 0.7070004343986511,
|
1113 |
+
"learning_rate": 1.2656659102810264e-05,
|
1114 |
+
"loss": 1.111,
|
1115 |
+
"step": 3950
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 3.75,
|
1119 |
+
"grad_norm": 0.6417202353477478,
|
1120 |
+
"learning_rate": 1.2525746203525922e-05,
|
1121 |
+
"loss": 1.0187,
|
1122 |
+
"step": 3975
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 3.77,
|
1126 |
+
"grad_norm": 0.6464525461196899,
|
1127 |
+
"learning_rate": 1.2394833304241579e-05,
|
1128 |
+
"loss": 1.0538,
|
1129 |
+
"step": 4000
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 3.79,
|
1133 |
+
"grad_norm": 0.7412322759628296,
|
1134 |
+
"learning_rate": 1.2263920404957236e-05,
|
1135 |
+
"loss": 0.9896,
|
1136 |
+
"step": 4025
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 3.82,
|
1140 |
+
"grad_norm": 0.6961266398429871,
|
1141 |
+
"learning_rate": 1.2133007505672892e-05,
|
1142 |
+
"loss": 1.038,
|
1143 |
+
"step": 4050
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 3.84,
|
1147 |
+
"grad_norm": 0.6745458245277405,
|
1148 |
+
"learning_rate": 1.2002094606388551e-05,
|
1149 |
+
"loss": 1.0348,
|
1150 |
+
"step": 4075
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 3.86,
|
1154 |
+
"grad_norm": 0.7007986307144165,
|
1155 |
+
"learning_rate": 1.1871181707104206e-05,
|
1156 |
+
"loss": 1.056,
|
1157 |
+
"step": 4100
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 3.89,
|
1161 |
+
"grad_norm": 0.6684093475341797,
|
1162 |
+
"learning_rate": 1.1740268807819864e-05,
|
1163 |
+
"loss": 1.0506,
|
1164 |
+
"step": 4125
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 3.91,
|
1168 |
+
"grad_norm": 0.6373914480209351,
|
1169 |
+
"learning_rate": 1.1609355908535521e-05,
|
1170 |
+
"loss": 1.0317,
|
1171 |
+
"step": 4150
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 3.93,
|
1175 |
+
"grad_norm": 0.6588457822799683,
|
1176 |
+
"learning_rate": 1.1478443009251178e-05,
|
1177 |
+
"loss": 1.0408,
|
1178 |
+
"step": 4175
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 3.96,
|
1182 |
+
"grad_norm": 0.6651216745376587,
|
1183 |
+
"learning_rate": 1.1347530109966836e-05,
|
1184 |
+
"loss": 1.0409,
|
1185 |
+
"step": 4200
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 3.98,
|
1189 |
+
"grad_norm": 0.6777089834213257,
|
1190 |
+
"learning_rate": 1.1216617210682492e-05,
|
1191 |
+
"loss": 1.0415,
|
1192 |
+
"step": 4225
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 4.01,
|
1196 |
+
"grad_norm": 0.5962642431259155,
|
1197 |
+
"learning_rate": 1.108570431139815e-05,
|
1198 |
+
"loss": 1.0276,
|
1199 |
+
"step": 4250
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 4.03,
|
1203 |
+
"grad_norm": 0.7103810906410217,
|
1204 |
+
"learning_rate": 1.0954791412113807e-05,
|
1205 |
+
"loss": 1.0398,
|
1206 |
+
"step": 4275
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 4.05,
|
1210 |
+
"grad_norm": 0.6657726764678955,
|
1211 |
+
"learning_rate": 1.0823878512829464e-05,
|
1212 |
+
"loss": 1.0295,
|
1213 |
+
"step": 4300
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 4.08,
|
1217 |
+
"grad_norm": 0.6180024147033691,
|
1218 |
+
"learning_rate": 1.0692965613545122e-05,
|
1219 |
+
"loss": 1.0673,
|
1220 |
+
"step": 4325
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 4.1,
|
1224 |
+
"grad_norm": 0.6927649974822998,
|
1225 |
+
"learning_rate": 1.0562052714260779e-05,
|
1226 |
+
"loss": 1.006,
|
1227 |
+
"step": 4350
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 4.12,
|
1231 |
+
"grad_norm": 0.6404564380645752,
|
1232 |
+
"learning_rate": 1.0431139814976436e-05,
|
1233 |
+
"loss": 1.0415,
|
1234 |
+
"step": 4375
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 4.15,
|
1238 |
+
"grad_norm": 0.7053262591362,
|
1239 |
+
"learning_rate": 1.0300226915692092e-05,
|
1240 |
+
"loss": 0.9987,
|
1241 |
+
"step": 4400
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 4.17,
|
1245 |
+
"grad_norm": 0.6685893535614014,
|
1246 |
+
"learning_rate": 1.0169314016407751e-05,
|
1247 |
+
"loss": 1.0407,
|
1248 |
+
"step": 4425
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 4.19,
|
1252 |
+
"grad_norm": 0.7120438814163208,
|
1253 |
+
"learning_rate": 1.0038401117123408e-05,
|
1254 |
+
"loss": 1.1023,
|
1255 |
+
"step": 4450
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 4.22,
|
1259 |
+
"grad_norm": 0.765691876411438,
|
1260 |
+
"learning_rate": 9.907488217839064e-06,
|
1261 |
+
"loss": 1.061,
|
1262 |
+
"step": 4475
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 4.24,
|
1266 |
+
"grad_norm": 0.7191650867462158,
|
1267 |
+
"learning_rate": 9.776575318554723e-06,
|
1268 |
+
"loss": 1.0052,
|
1269 |
+
"step": 4500
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 4.26,
|
1273 |
+
"grad_norm": 0.6924612522125244,
|
1274 |
+
"learning_rate": 9.645662419270378e-06,
|
1275 |
+
"loss": 1.028,
|
1276 |
+
"step": 4525
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 4.29,
|
1280 |
+
"grad_norm": 0.7597302198410034,
|
1281 |
+
"learning_rate": 9.514749519986036e-06,
|
1282 |
+
"loss": 1.0309,
|
1283 |
+
"step": 4550
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 4.31,
|
1287 |
+
"grad_norm": 0.7024239301681519,
|
1288 |
+
"learning_rate": 9.383836620701693e-06,
|
1289 |
+
"loss": 1.0261,
|
1290 |
+
"step": 4575
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 4.34,
|
1294 |
+
"grad_norm": 0.7462353706359863,
|
1295 |
+
"learning_rate": 9.25292372141735e-06,
|
1296 |
+
"loss": 1.0323,
|
1297 |
+
"step": 4600
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 4.36,
|
1301 |
+
"grad_norm": 0.6952032446861267,
|
1302 |
+
"learning_rate": 9.122010822133008e-06,
|
1303 |
+
"loss": 1.044,
|
1304 |
+
"step": 4625
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 4.38,
|
1308 |
+
"grad_norm": 0.7031837701797485,
|
1309 |
+
"learning_rate": 8.991097922848665e-06,
|
1310 |
+
"loss": 0.9975,
|
1311 |
+
"step": 4650
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 4.41,
|
1315 |
+
"grad_norm": 0.6907106041908264,
|
1316 |
+
"learning_rate": 8.860185023564322e-06,
|
1317 |
+
"loss": 1.0763,
|
1318 |
+
"step": 4675
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 4.43,
|
1322 |
+
"grad_norm": 0.6010780334472656,
|
1323 |
+
"learning_rate": 8.729272124279979e-06,
|
1324 |
+
"loss": 0.9934,
|
1325 |
+
"step": 4700
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 4.45,
|
1329 |
+
"grad_norm": 0.6455862522125244,
|
1330 |
+
"learning_rate": 8.598359224995637e-06,
|
1331 |
+
"loss": 1.051,
|
1332 |
+
"step": 4725
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 4.48,
|
1336 |
+
"grad_norm": 0.6011804342269897,
|
1337 |
+
"learning_rate": 8.467446325711294e-06,
|
1338 |
+
"loss": 1.0386,
|
1339 |
+
"step": 4750
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 4.5,
|
1343 |
+
"grad_norm": 0.7045350074768066,
|
1344 |
+
"learning_rate": 8.33653342642695e-06,
|
1345 |
+
"loss": 1.051,
|
1346 |
+
"step": 4775
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 4.52,
|
1350 |
+
"grad_norm": 0.6799806356430054,
|
1351 |
+
"learning_rate": 8.20562052714261e-06,
|
1352 |
+
"loss": 1.0509,
|
1353 |
+
"step": 4800
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 4.55,
|
1357 |
+
"grad_norm": 0.6759226322174072,
|
1358 |
+
"learning_rate": 8.074707627858264e-06,
|
1359 |
+
"loss": 0.983,
|
1360 |
+
"step": 4825
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 4.57,
|
1364 |
+
"grad_norm": 0.6579796671867371,
|
1365 |
+
"learning_rate": 7.943794728573923e-06,
|
1366 |
+
"loss": 1.0901,
|
1367 |
+
"step": 4850
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 4.59,
|
1371 |
+
"grad_norm": 0.6630005240440369,
|
1372 |
+
"learning_rate": 7.812881829289578e-06,
|
1373 |
+
"loss": 1.0501,
|
1374 |
+
"step": 4875
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 4.62,
|
1378 |
+
"grad_norm": 0.693554699420929,
|
1379 |
+
"learning_rate": 7.681968930005236e-06,
|
1380 |
+
"loss": 1.0399,
|
1381 |
+
"step": 4900
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 4.64,
|
1385 |
+
"grad_norm": 0.6797517538070679,
|
1386 |
+
"learning_rate": 7.551056030720894e-06,
|
1387 |
+
"loss": 1.062,
|
1388 |
+
"step": 4925
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 4.67,
|
1392 |
+
"grad_norm": 0.671291172504425,
|
1393 |
+
"learning_rate": 7.420143131436551e-06,
|
1394 |
+
"loss": 1.0045,
|
1395 |
+
"step": 4950
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 4.69,
|
1399 |
+
"grad_norm": 0.7400732040405273,
|
1400 |
+
"learning_rate": 7.2892302321522084e-06,
|
1401 |
+
"loss": 1.041,
|
1402 |
+
"step": 4975
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 4.71,
|
1406 |
+
"grad_norm": 0.5939465165138245,
|
1407 |
+
"learning_rate": 7.158317332867866e-06,
|
1408 |
+
"loss": 1.0551,
|
1409 |
+
"step": 5000
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 4.74,
|
1413 |
+
"grad_norm": 0.6042287349700928,
|
1414 |
+
"learning_rate": 7.027404433583523e-06,
|
1415 |
+
"loss": 1.0298,
|
1416 |
+
"step": 5025
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 4.76,
|
1420 |
+
"grad_norm": 0.6053622961044312,
|
1421 |
+
"learning_rate": 6.89649153429918e-06,
|
1422 |
+
"loss": 1.0218,
|
1423 |
+
"step": 5050
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 4.78,
|
1427 |
+
"grad_norm": 0.6911068558692932,
|
1428 |
+
"learning_rate": 6.77081515098621e-06,
|
1429 |
+
"loss": 1.0442,
|
1430 |
+
"step": 5075
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 4.81,
|
1434 |
+
"grad_norm": 0.6786155104637146,
|
1435 |
+
"learning_rate": 6.639902251701868e-06,
|
1436 |
+
"loss": 1.0321,
|
1437 |
+
"step": 5100
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 4.83,
|
1441 |
+
"grad_norm": 0.6624850034713745,
|
1442 |
+
"learning_rate": 6.508989352417526e-06,
|
1443 |
+
"loss": 1.0696,
|
1444 |
+
"step": 5125
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 4.85,
|
1448 |
+
"grad_norm": 0.850053071975708,
|
1449 |
+
"learning_rate": 6.378076453133182e-06,
|
1450 |
+
"loss": 0.9769,
|
1451 |
+
"step": 5150
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 4.88,
|
1455 |
+
"grad_norm": 0.8631001710891724,
|
1456 |
+
"learning_rate": 6.247163553848839e-06,
|
1457 |
+
"loss": 0.9791,
|
1458 |
+
"step": 5175
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 4.9,
|
1462 |
+
"grad_norm": 0.6453446745872498,
|
1463 |
+
"learning_rate": 6.116250654564497e-06,
|
1464 |
+
"loss": 1.035,
|
1465 |
+
"step": 5200
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 4.92,
|
1469 |
+
"grad_norm": 0.6186447739601135,
|
1470 |
+
"learning_rate": 5.9853377552801536e-06,
|
1471 |
+
"loss": 1.0209,
|
1472 |
+
"step": 5225
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 4.95,
|
1476 |
+
"grad_norm": 0.6838425397872925,
|
1477 |
+
"learning_rate": 5.854424855995811e-06,
|
1478 |
+
"loss": 0.9938,
|
1479 |
+
"step": 5250
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 4.97,
|
1483 |
+
"grad_norm": 0.6573156118392944,
|
1484 |
+
"learning_rate": 5.723511956711468e-06,
|
1485 |
+
"loss": 1.0532,
|
1486 |
+
"step": 5275
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 5.0,
|
1490 |
+
"grad_norm": 0.6593102216720581,
|
1491 |
+
"learning_rate": 5.592599057427126e-06,
|
1492 |
+
"loss": 0.9892,
|
1493 |
+
"step": 5300
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 5.02,
|
1497 |
+
"grad_norm": 0.6164034605026245,
|
1498 |
+
"learning_rate": 5.461686158142782e-06,
|
1499 |
+
"loss": 1.0142,
|
1500 |
+
"step": 5325
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 5.04,
|
1504 |
+
"grad_norm": 0.5685546398162842,
|
1505 |
+
"learning_rate": 5.330773258858439e-06,
|
1506 |
+
"loss": 1.0124,
|
1507 |
+
"step": 5350
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 5.07,
|
1511 |
+
"grad_norm": 0.718358039855957,
|
1512 |
+
"learning_rate": 5.199860359574097e-06,
|
1513 |
+
"loss": 1.036,
|
1514 |
+
"step": 5375
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 5.09,
|
1518 |
+
"grad_norm": 0.7039633989334106,
|
1519 |
+
"learning_rate": 5.068947460289754e-06,
|
1520 |
+
"loss": 0.9901,
|
1521 |
+
"step": 5400
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 5.11,
|
1525 |
+
"grad_norm": 0.7492026090621948,
|
1526 |
+
"learning_rate": 4.938034561005411e-06,
|
1527 |
+
"loss": 1.0949,
|
1528 |
+
"step": 5425
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 5.14,
|
1532 |
+
"grad_norm": 0.7225030064582825,
|
1533 |
+
"learning_rate": 4.807121661721069e-06,
|
1534 |
+
"loss": 0.9975,
|
1535 |
+
"step": 5450
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 5.16,
|
1539 |
+
"grad_norm": 0.7279338240623474,
|
1540 |
+
"learning_rate": 4.6762087624367256e-06,
|
1541 |
+
"loss": 1.0505,
|
1542 |
+
"step": 5475
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 5.18,
|
1546 |
+
"grad_norm": 0.5847637057304382,
|
1547 |
+
"learning_rate": 4.545295863152382e-06,
|
1548 |
+
"loss": 1.0111,
|
1549 |
+
"step": 5500
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"epoch": 5.21,
|
1553 |
+
"grad_norm": 0.647482693195343,
|
1554 |
+
"learning_rate": 4.41438296386804e-06,
|
1555 |
+
"loss": 1.0477,
|
1556 |
+
"step": 5525
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 5.23,
|
1560 |
+
"grad_norm": 0.6671623587608337,
|
1561 |
+
"learning_rate": 4.283470064583698e-06,
|
1562 |
+
"loss": 1.0096,
|
1563 |
+
"step": 5550
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 5.25,
|
1567 |
+
"grad_norm": 0.7235545516014099,
|
1568 |
+
"learning_rate": 4.152557165299354e-06,
|
1569 |
+
"loss": 1.0466,
|
1570 |
+
"step": 5575
|
1571 |
+
},
|
1572 |
+
{
|
1573 |
+
"epoch": 5.28,
|
1574 |
+
"grad_norm": 0.7705885767936707,
|
1575 |
+
"learning_rate": 4.021644266015012e-06,
|
1576 |
+
"loss": 1.005,
|
1577 |
+
"step": 5600
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 5.3,
|
1581 |
+
"grad_norm": 0.6789776682853699,
|
1582 |
+
"learning_rate": 3.890731366730669e-06,
|
1583 |
+
"loss": 1.0132,
|
1584 |
+
"step": 5625
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 5.33,
|
1588 |
+
"grad_norm": 0.6266222596168518,
|
1589 |
+
"learning_rate": 3.7598184674463255e-06,
|
1590 |
+
"loss": 1.053,
|
1591 |
+
"step": 5650
|
1592 |
+
},
|
1593 |
+
{
|
1594 |
+
"epoch": 5.35,
|
1595 |
+
"grad_norm": 0.6509959697723389,
|
1596 |
+
"learning_rate": 3.628905568161983e-06,
|
1597 |
+
"loss": 1.0416,
|
1598 |
+
"step": 5675
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 5.37,
|
1602 |
+
"grad_norm": 0.6754451394081116,
|
1603 |
+
"learning_rate": 3.4979926688776404e-06,
|
1604 |
+
"loss": 1.0234,
|
1605 |
+
"step": 5700
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 5.4,
|
1609 |
+
"grad_norm": 0.6019960045814514,
|
1610 |
+
"learning_rate": 3.367079769593297e-06,
|
1611 |
+
"loss": 1.024,
|
1612 |
+
"step": 5725
|
1613 |
+
},
|
1614 |
+
{
|
1615 |
+
"epoch": 5.42,
|
1616 |
+
"grad_norm": 0.6941302418708801,
|
1617 |
+
"learning_rate": 3.2361668703089548e-06,
|
1618 |
+
"loss": 1.0429,
|
1619 |
+
"step": 5750
|
1620 |
+
},
|
1621 |
+
{
|
1622 |
+
"epoch": 5.44,
|
1623 |
+
"grad_norm": 0.7364933490753174,
|
1624 |
+
"learning_rate": 3.1052539710246115e-06,
|
1625 |
+
"loss": 0.9956,
|
1626 |
+
"step": 5775
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 5.47,
|
1630 |
+
"grad_norm": 0.7257634401321411,
|
1631 |
+
"learning_rate": 2.9743410717402687e-06,
|
1632 |
+
"loss": 1.0185,
|
1633 |
+
"step": 5800
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 5.49,
|
1637 |
+
"grad_norm": 0.7992274761199951,
|
1638 |
+
"learning_rate": 2.8434281724559264e-06,
|
1639 |
+
"loss": 1.0608,
|
1640 |
+
"step": 5825
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 5.51,
|
1644 |
+
"grad_norm": 0.6821667551994324,
|
1645 |
+
"learning_rate": 2.7177517891429567e-06,
|
1646 |
+
"loss": 0.98,
|
1647 |
+
"step": 5850
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 5.54,
|
1651 |
+
"grad_norm": 0.8012374043464661,
|
1652 |
+
"learning_rate": 2.5868388898586143e-06,
|
1653 |
+
"loss": 1.0294,
|
1654 |
+
"step": 5875
|
1655 |
+
},
|
1656 |
+
{
|
1657 |
+
"epoch": 5.56,
|
1658 |
+
"grad_norm": 0.6576132774353027,
|
1659 |
+
"learning_rate": 2.4559259905742715e-06,
|
1660 |
+
"loss": 1.0476,
|
1661 |
+
"step": 5900
|
1662 |
+
},
|
1663 |
+
{
|
1664 |
+
"epoch": 5.58,
|
1665 |
+
"grad_norm": 0.6078372597694397,
|
1666 |
+
"learning_rate": 2.3250130912899283e-06,
|
1667 |
+
"loss": 1.0589,
|
1668 |
+
"step": 5925
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 5.61,
|
1672 |
+
"grad_norm": 0.7334024906158447,
|
1673 |
+
"learning_rate": 2.194100192005586e-06,
|
1674 |
+
"loss": 1.0186,
|
1675 |
+
"step": 5950
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 5.63,
|
1679 |
+
"grad_norm": 0.6493911743164062,
|
1680 |
+
"learning_rate": 2.0631872927212427e-06,
|
1681 |
+
"loss": 1.0143,
|
1682 |
+
"step": 5975
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 5.66,
|
1686 |
+
"grad_norm": 0.8003960251808167,
|
1687 |
+
"learning_rate": 1.9322743934369e-06,
|
1688 |
+
"loss": 1.0243,
|
1689 |
+
"step": 6000
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 5.68,
|
1693 |
+
"grad_norm": 0.7148457169532776,
|
1694 |
+
"learning_rate": 1.801361494152557e-06,
|
1695 |
+
"loss": 1.0195,
|
1696 |
+
"step": 6025
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 5.7,
|
1700 |
+
"grad_norm": 0.6924374103546143,
|
1701 |
+
"learning_rate": 1.6704485948682145e-06,
|
1702 |
+
"loss": 1.0034,
|
1703 |
+
"step": 6050
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 5.73,
|
1707 |
+
"grad_norm": 0.7333653569221497,
|
1708 |
+
"learning_rate": 1.5395356955838715e-06,
|
1709 |
+
"loss": 1.0448,
|
1710 |
+
"step": 6075
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 5.75,
|
1714 |
+
"grad_norm": 0.7860874533653259,
|
1715 |
+
"learning_rate": 1.4086227962995287e-06,
|
1716 |
+
"loss": 1.0205,
|
1717 |
+
"step": 6100
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 5.77,
|
1721 |
+
"grad_norm": 0.6410927176475525,
|
1722 |
+
"learning_rate": 1.2777098970151859e-06,
|
1723 |
+
"loss": 0.9727,
|
1724 |
+
"step": 6125
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 5.8,
|
1728 |
+
"grad_norm": 0.6415342688560486,
|
1729 |
+
"learning_rate": 1.146796997730843e-06,
|
1730 |
+
"loss": 1.0137,
|
1731 |
+
"step": 6150
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 5.82,
|
1735 |
+
"grad_norm": 0.6379125118255615,
|
1736 |
+
"learning_rate": 1.0158840984465003e-06,
|
1737 |
+
"loss": 1.0076,
|
1738 |
+
"step": 6175
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 5.84,
|
1742 |
+
"grad_norm": 0.6775155663490295,
|
1743 |
+
"learning_rate": 8.849711991621574e-07,
|
1744 |
+
"loss": 1.0328,
|
1745 |
+
"step": 6200
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 5.87,
|
1749 |
+
"grad_norm": 0.614631712436676,
|
1750 |
+
"learning_rate": 7.540582998778147e-07,
|
1751 |
+
"loss": 0.9982,
|
1752 |
+
"step": 6225
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 5.89,
|
1756 |
+
"grad_norm": 0.7537350058555603,
|
1757 |
+
"learning_rate": 6.231454005934718e-07,
|
1758 |
+
"loss": 1.0465,
|
1759 |
+
"step": 6250
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"epoch": 5.91,
|
1763 |
+
"grad_norm": 0.6336871385574341,
|
1764 |
+
"learning_rate": 4.92232501309129e-07,
|
1765 |
+
"loss": 1.0098,
|
1766 |
+
"step": 6275
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 5.94,
|
1770 |
+
"grad_norm": 0.7179773449897766,
|
1771 |
+
"learning_rate": 3.613196020247862e-07,
|
1772 |
+
"loss": 1.0218,
|
1773 |
+
"step": 6300
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 5.96,
|
1777 |
+
"grad_norm": 0.6881077289581299,
|
1778 |
+
"learning_rate": 2.3040670274044336e-07,
|
1779 |
+
"loss": 1.0088,
|
1780 |
+
"step": 6325
|
1781 |
+
},
|
1782 |
+
{
|
1783 |
+
"epoch": 5.98,
|
1784 |
+
"grad_norm": 0.6044571399688721,
|
1785 |
+
"learning_rate": 9.949380345610055e-08,
|
1786 |
+
"loss": 1.0526,
|
1787 |
+
"step": 6350
|
1788 |
+
}
|
1789 |
+
],
|
1790 |
+
"logging_steps": 25,
|
1791 |
+
"max_steps": 6366,
|
1792 |
+
"num_input_tokens_seen": 0,
|
1793 |
+
"num_train_epochs": 6,
|
1794 |
+
"save_steps": 500,
|
1795 |
+
"total_flos": 1.3676194390081536e+16,
|
1796 |
+
"train_batch_size": 1,
|
1797 |
+
"trial_name": null,
|
1798 |
+
"trial_params": null
|
1799 |
+
}
|
checkpoint-6366/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef4c22b78d71f5b49da24429145951afb9dfa28993888fc6029bab482e08dde7
|
3 |
+
size 5048
|
checkpoint-6366/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Mar26_19-46-04_r-jamesb1974-gpu01-wtyrob2c-89c4d-ngnc1/events.out.tfevents.1711482377.r-jamesb1974-gpu01-wtyrob2c-89c4d-ngnc1.59.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5cbd21cf48bf92934847ca824792e038ca23fd8a2bb272a7948934f48c2feca
|
3 |
+
size 59358
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
}
|
12 |
+
},
|
13 |
+
"bos_token": "<|endoftext|>",
|
14 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
15 |
+
"clean_up_tokenization_spaces": true,
|
16 |
+
"eos_token": "<|endoftext|>",
|
17 |
+
"model_max_length": 1024,
|
18 |
+
"pad_token": "<|endoftext|>",
|
19 |
+
"tokenizer_class": "GPT2Tokenizer",
|
20 |
+
"unk_token": "<|endoftext|>"
|
21 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef4c22b78d71f5b49da24429145951afb9dfa28993888fc6029bab482e08dde7
|
3 |
+
size 5048
|
training_params.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model": "openai-community/gpt2",
|
3 |
+
"project_name": "autotraincom-gtp2-ep2-bs2-sft-600T",
|
4 |
+
"data_path": "autotraincom-gtp2-ep2-bs2-sft-600T/autotrain-data",
|
5 |
+
"train_split": "train",
|
6 |
+
"valid_split": null,
|
7 |
+
"add_eos_token": true,
|
8 |
+
"block_size": 1024,
|
9 |
+
"model_max_length": 2048,
|
10 |
+
"padding": "right",
|
11 |
+
"trainer": "sft",
|
12 |
+
"use_flash_attention_2": false,
|
13 |
+
"log": "tensorboard",
|
14 |
+
"disable_gradient_checkpointing": false,
|
15 |
+
"logging_steps": -1,
|
16 |
+
"evaluation_strategy": "epoch",
|
17 |
+
"save_total_limit": 1,
|
18 |
+
"save_strategy": "epoch",
|
19 |
+
"auto_find_batch_size": false,
|
20 |
+
"mixed_precision": "fp16",
|
21 |
+
"lr": 3e-05,
|
22 |
+
"epochs": 6,
|
23 |
+
"batch_size": 1,
|
24 |
+
"warmup_ratio": 0.1,
|
25 |
+
"gradient_accumulation": 4,
|
26 |
+
"optimizer": "adamw_torch",
|
27 |
+
"scheduler": "linear",
|
28 |
+
"weight_decay": 0.0,
|
29 |
+
"max_grad_norm": 1.0,
|
30 |
+
"seed": 42,
|
31 |
+
"chat_template": "none",
|
32 |
+
"quantization": "int4",
|
33 |
+
"target_modules": "all-linear",
|
34 |
+
"merge_adapter": false,
|
35 |
+
"peft": true,
|
36 |
+
"lora_r": 16,
|
37 |
+
"lora_alpha": 32,
|
38 |
+
"lora_dropout": 0.05,
|
39 |
+
"model_ref": null,
|
40 |
+
"dpo_beta": 0.1,
|
41 |
+
"prompt_text_column": "autotrain_prompt",
|
42 |
+
"text_column": "autotrain_text",
|
43 |
+
"rejected_text_column": "autotrain_rejected_text",
|
44 |
+
"push_to_hub": true,
|
45 |
+
"repo_id": "Jamesb1974/autotraincom-gtp2-ep2-bs2-sft-600T",
|
46 |
+
"username": "Jamesb1974"
|
47 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|