Upload 15 files
Browse files- README.md +202 -3
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +5 -0
- all_results.json +8 -0
- merges.txt +0 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +44 -0
- train_results.json +8 -0
- trainer_log.jsonl +71 -0
- trainer_state.json +532 -0
- training_args.bin +3 -0
- training_loss.png +0 -0
- vocab.json +0 -0
README.md
CHANGED
@@ -1,3 +1,202 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: Qwen2/Qwen2-7B-Instruct
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.11.1
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "/root/LLM_Data_Engineer/LLaMA-Factory/models/Qwen2-7B-Instruct-lora-06072000",
|
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": 16,
|
14 |
+
"lora_dropout": 0.0,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"o_proj",
|
24 |
+
"up_proj",
|
25 |
+
"down_proj",
|
26 |
+
"k_proj",
|
27 |
+
"gate_proj",
|
28 |
+
"v_proj",
|
29 |
+
"q_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4b55800b868058f3ead65a3d587b3da3dc74f88cabe633a7e67341879cb3e15
|
3 |
+
size 80792096
|
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.9528795811518327,
|
3 |
+
"total_flos": 5.744674604829082e+16,
|
4 |
+
"train_loss": 0.7884446775659602,
|
5 |
+
"train_runtime": 510.788,
|
6 |
+
"train_samples_per_second": 8.957,
|
7 |
+
"train_steps_per_second": 0.276
|
8 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"eos_token": {
|
7 |
+
"content": "<|im_end|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"pad_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
}
|
20 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"additional_special_tokens": [
|
30 |
+
"<|im_start|>",
|
31 |
+
"<|im_end|>"
|
32 |
+
],
|
33 |
+
"bos_token": null,
|
34 |
+
"chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
|
35 |
+
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "<|im_end|>",
|
37 |
+
"errors": "replace",
|
38 |
+
"model_max_length": 131072,
|
39 |
+
"pad_token": "<|endoftext|>",
|
40 |
+
"padding_side": "right",
|
41 |
+
"split_special_tokens": false,
|
42 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
43 |
+
"unk_token": null
|
44 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.9528795811518327,
|
3 |
+
"total_flos": 5.744674604829082e+16,
|
4 |
+
"train_loss": 0.7884446775659602,
|
5 |
+
"train_runtime": 510.788,
|
6 |
+
"train_samples_per_second": 8.957,
|
7 |
+
"train_steps_per_second": 0.276
|
8 |
+
}
|
trainer_log.jsonl
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"current_steps": 2, "total_steps": 141, "loss": 1.0015, "learning_rate": 1.3333333333333333e-05, "epoch": 0.041884816753926704, "percentage": 1.42, "elapsed_time": "0:00:07", "remaining_time": "0:08:23", "throughput": "0.00", "total_tokens": 0}
|
2 |
+
{"current_steps": 4, "total_steps": 141, "loss": 0.9283, "learning_rate": 2.6666666666666667e-05, "epoch": 0.08376963350785341, "percentage": 2.84, "elapsed_time": "0:00:15", "remaining_time": "0:08:48", "throughput": "0.00", "total_tokens": 0}
|
3 |
+
{"current_steps": 6, "total_steps": 141, "loss": 0.8643, "learning_rate": 4e-05, "epoch": 0.1256544502617801, "percentage": 4.26, "elapsed_time": "0:00:23", "remaining_time": "0:08:42", "throughput": "0.00", "total_tokens": 0}
|
4 |
+
{"current_steps": 8, "total_steps": 141, "loss": 1.0013, "learning_rate": 5.333333333333333e-05, "epoch": 0.16753926701570682, "percentage": 5.67, "elapsed_time": "0:00:30", "remaining_time": "0:08:24", "throughput": "0.00", "total_tokens": 0}
|
5 |
+
{"current_steps": 10, "total_steps": 141, "loss": 0.9341, "learning_rate": 6.666666666666667e-05, "epoch": 0.2094240837696335, "percentage": 7.09, "elapsed_time": "0:00:38", "remaining_time": "0:08:24", "throughput": "0.00", "total_tokens": 0}
|
6 |
+
{"current_steps": 12, "total_steps": 141, "loss": 0.9068, "learning_rate": 8e-05, "epoch": 0.2513089005235602, "percentage": 8.51, "elapsed_time": "0:00:45", "remaining_time": "0:08:13", "throughput": "0.00", "total_tokens": 0}
|
7 |
+
{"current_steps": 14, "total_steps": 141, "loss": 0.8083, "learning_rate": 9.333333333333334e-05, "epoch": 0.2931937172774869, "percentage": 9.93, "elapsed_time": "0:00:53", "remaining_time": "0:08:08", "throughput": "0.00", "total_tokens": 0}
|
8 |
+
{"current_steps": 16, "total_steps": 141, "loss": 0.8985, "learning_rate": 9.998445910004082e-05, "epoch": 0.33507853403141363, "percentage": 11.35, "elapsed_time": "0:01:00", "remaining_time": "0:07:54", "throughput": "0.00", "total_tokens": 0}
|
9 |
+
{"current_steps": 18, "total_steps": 141, "loss": 0.9362, "learning_rate": 9.986018985905901e-05, "epoch": 0.3769633507853403, "percentage": 12.77, "elapsed_time": "0:01:07", "remaining_time": "0:07:41", "throughput": "0.00", "total_tokens": 0}
|
10 |
+
{"current_steps": 20, "total_steps": 141, "loss": 0.9174, "learning_rate": 9.961196033000861e-05, "epoch": 0.418848167539267, "percentage": 14.18, "elapsed_time": "0:01:14", "remaining_time": "0:07:30", "throughput": "0.00", "total_tokens": 0}
|
11 |
+
{"current_steps": 22, "total_steps": 141, "loss": 0.8732, "learning_rate": 9.924038765061042e-05, "epoch": 0.4607329842931937, "percentage": 15.6, "elapsed_time": "0:01:22", "remaining_time": "0:07:23", "throughput": "0.00", "total_tokens": 0}
|
12 |
+
{"current_steps": 24, "total_steps": 141, "loss": 0.8653, "learning_rate": 9.874639560909117e-05, "epoch": 0.5026178010471204, "percentage": 17.02, "elapsed_time": "0:01:30", "remaining_time": "0:07:20", "throughput": "0.00", "total_tokens": 0}
|
13 |
+
{"current_steps": 26, "total_steps": 141, "loss": 0.8592, "learning_rate": 9.81312123475006e-05, "epoch": 0.5445026178010471, "percentage": 18.44, "elapsed_time": "0:01:36", "remaining_time": "0:07:08", "throughput": "0.00", "total_tokens": 0}
|
14 |
+
{"current_steps": 28, "total_steps": 141, "loss": 0.805, "learning_rate": 9.73963673083566e-05, "epoch": 0.5863874345549738, "percentage": 19.86, "elapsed_time": "0:01:45", "remaining_time": "0:07:04", "throughput": "0.00", "total_tokens": 0}
|
15 |
+
{"current_steps": 30, "total_steps": 141, "loss": 0.7464, "learning_rate": 9.654368743221022e-05, "epoch": 0.6282722513089005, "percentage": 21.28, "elapsed_time": "0:01:53", "remaining_time": "0:07:00", "throughput": "0.00", "total_tokens": 0}
|
16 |
+
{"current_steps": 32, "total_steps": 141, "loss": 0.7796, "learning_rate": 9.557529261558367e-05, "epoch": 0.6701570680628273, "percentage": 22.7, "elapsed_time": "0:02:00", "remaining_time": "0:06:51", "throughput": "0.00", "total_tokens": 0}
|
17 |
+
{"current_steps": 34, "total_steps": 141, "loss": 0.7768, "learning_rate": 9.449359044057345e-05, "epoch": 0.7120418848167539, "percentage": 24.11, "elapsed_time": "0:02:08", "remaining_time": "0:06:44", "throughput": "0.00", "total_tokens": 0}
|
18 |
+
{"current_steps": 36, "total_steps": 141, "loss": 0.8751, "learning_rate": 9.330127018922194e-05, "epoch": 0.7539267015706806, "percentage": 25.53, "elapsed_time": "0:02:15", "remaining_time": "0:06:35", "throughput": "0.00", "total_tokens": 0}
|
19 |
+
{"current_steps": 38, "total_steps": 141, "loss": 0.7966, "learning_rate": 9.200129615753859e-05, "epoch": 0.7958115183246073, "percentage": 26.95, "elapsed_time": "0:02:22", "remaining_time": "0:06:26", "throughput": "0.00", "total_tokens": 0}
|
20 |
+
{"current_steps": 40, "total_steps": 141, "loss": 0.7963, "learning_rate": 9.059690028579284e-05, "epoch": 0.837696335078534, "percentage": 28.37, "elapsed_time": "0:02:29", "remaining_time": "0:06:17", "throughput": "0.00", "total_tokens": 0}
|
21 |
+
{"current_steps": 42, "total_steps": 141, "loss": 0.8332, "learning_rate": 8.90915741234015e-05, "epoch": 0.8795811518324608, "percentage": 29.79, "elapsed_time": "0:02:35", "remaining_time": "0:06:07", "throughput": "0.00", "total_tokens": 0}
|
22 |
+
{"current_steps": 44, "total_steps": 141, "loss": 0.7869, "learning_rate": 8.748906014838672e-05, "epoch": 0.9214659685863874, "percentage": 31.21, "elapsed_time": "0:02:42", "remaining_time": "0:05:59", "throughput": "0.00", "total_tokens": 0}
|
23 |
+
{"current_steps": 46, "total_steps": 141, "loss": 0.8517, "learning_rate": 8.579334246298593e-05, "epoch": 0.9633507853403142, "percentage": 32.62, "elapsed_time": "0:02:48", "remaining_time": "0:05:48", "throughput": "0.00", "total_tokens": 0}
|
24 |
+
{"current_steps": 48, "total_steps": 141, "loss": 0.8694, "learning_rate": 8.400863688854597e-05, "epoch": 1.0052356020942408, "percentage": 34.04, "elapsed_time": "0:02:55", "remaining_time": "0:05:39", "throughput": "0.00", "total_tokens": 0}
|
25 |
+
{"current_steps": 50, "total_steps": 141, "loss": 0.8002, "learning_rate": 8.213938048432697e-05, "epoch": 1.0471204188481675, "percentage": 35.46, "elapsed_time": "0:03:02", "remaining_time": "0:05:31", "throughput": "0.00", "total_tokens": 0}
|
26 |
+
{"current_steps": 52, "total_steps": 141, "loss": 0.7798, "learning_rate": 8.019022051627388e-05, "epoch": 1.0890052356020943, "percentage": 36.88, "elapsed_time": "0:03:09", "remaining_time": "0:05:23", "throughput": "0.00", "total_tokens": 0}
|
27 |
+
{"current_steps": 54, "total_steps": 141, "loss": 0.8114, "learning_rate": 7.81660029031811e-05, "epoch": 1.130890052356021, "percentage": 38.3, "elapsed_time": "0:03:16", "remaining_time": "0:05:16", "throughput": "0.00", "total_tokens": 0}
|
28 |
+
{"current_steps": 56, "total_steps": 141, "loss": 0.8206, "learning_rate": 7.60717601689749e-05, "epoch": 1.1727748691099475, "percentage": 39.72, "elapsed_time": "0:03:24", "remaining_time": "0:05:09", "throughput": "0.00", "total_tokens": 0}
|
29 |
+
{"current_steps": 58, "total_steps": 141, "loss": 0.8477, "learning_rate": 7.391269893106592e-05, "epoch": 1.2146596858638743, "percentage": 41.13, "elapsed_time": "0:03:30", "remaining_time": "0:05:01", "throughput": "0.00", "total_tokens": 0}
|
30 |
+
{"current_steps": 60, "total_steps": 141, "loss": 0.8213, "learning_rate": 7.169418695587791e-05, "epoch": 1.256544502617801, "percentage": 42.55, "elapsed_time": "0:03:37", "remaining_time": "0:04:53", "throughput": "0.00", "total_tokens": 0}
|
31 |
+
{"current_steps": 62, "total_steps": 141, "loss": 0.8287, "learning_rate": 6.942173981373474e-05, "epoch": 1.2984293193717278, "percentage": 43.97, "elapsed_time": "0:03:43", "remaining_time": "0:04:45", "throughput": "0.00", "total_tokens": 0}
|
32 |
+
{"current_steps": 64, "total_steps": 141, "loss": 0.7643, "learning_rate": 6.710100716628344e-05, "epoch": 1.3403141361256545, "percentage": 45.39, "elapsed_time": "0:03:51", "remaining_time": "0:04:39", "throughput": "0.00", "total_tokens": 0}
|
33 |
+
{"current_steps": 66, "total_steps": 141, "loss": 0.7315, "learning_rate": 6.473775872054521e-05, "epoch": 1.3821989528795813, "percentage": 46.81, "elapsed_time": "0:03:59", "remaining_time": "0:04:31", "throughput": "0.00", "total_tokens": 0}
|
34 |
+
{"current_steps": 68, "total_steps": 141, "loss": 0.7811, "learning_rate": 6.233786988451468e-05, "epoch": 1.4240837696335078, "percentage": 48.23, "elapsed_time": "0:04:07", "remaining_time": "0:04:25", "throughput": "0.00", "total_tokens": 0}
|
35 |
+
{"current_steps": 70, "total_steps": 141, "loss": 0.754, "learning_rate": 5.9907307159969884e-05, "epoch": 1.4659685863874345, "percentage": 49.65, "elapsed_time": "0:04:15", "remaining_time": "0:04:18", "throughput": "0.00", "total_tokens": 0}
|
36 |
+
{"current_steps": 72, "total_steps": 141, "loss": 0.7809, "learning_rate": 5.745211330880872e-05, "epoch": 1.5078534031413613, "percentage": 51.06, "elapsed_time": "0:04:22", "remaining_time": "0:04:11", "throughput": "0.00", "total_tokens": 0}
|
37 |
+
{"current_steps": 74, "total_steps": 141, "loss": 0.8319, "learning_rate": 5.497839232979084e-05, "epoch": 1.5497382198952878, "percentage": 52.48, "elapsed_time": "0:04:30", "remaining_time": "0:04:04", "throughput": "0.00", "total_tokens": 0}
|
38 |
+
{"current_steps": 76, "total_steps": 141, "loss": 0.7745, "learning_rate": 5.249229428303486e-05, "epoch": 1.5916230366492146, "percentage": 53.9, "elapsed_time": "0:04:37", "remaining_time": "0:03:57", "throughput": "0.00", "total_tokens": 0}
|
39 |
+
{"current_steps": 78, "total_steps": 141, "loss": 0.8002, "learning_rate": 5e-05, "epoch": 1.6335078534031413, "percentage": 55.32, "elapsed_time": "0:04:44", "remaining_time": "0:03:50", "throughput": "0.00", "total_tokens": 0}
|
40 |
+
{"current_steps": 80, "total_steps": 141, "loss": 0.7718, "learning_rate": 4.750770571696514e-05, "epoch": 1.675392670157068, "percentage": 56.74, "elapsed_time": "0:04:51", "remaining_time": "0:03:42", "throughput": "0.00", "total_tokens": 0}
|
41 |
+
{"current_steps": 82, "total_steps": 141, "loss": 0.742, "learning_rate": 4.502160767020918e-05, "epoch": 1.7172774869109948, "percentage": 58.16, "elapsed_time": "0:04:58", "remaining_time": "0:03:34", "throughput": "0.00", "total_tokens": 0}
|
42 |
+
{"current_steps": 84, "total_steps": 141, "loss": 0.7687, "learning_rate": 4.254788669119127e-05, "epoch": 1.7591623036649215, "percentage": 59.57, "elapsed_time": "0:05:05", "remaining_time": "0:03:27", "throughput": "0.00", "total_tokens": 0}
|
43 |
+
{"current_steps": 86, "total_steps": 141, "loss": 0.7066, "learning_rate": 4.0092692840030134e-05, "epoch": 1.8010471204188483, "percentage": 60.99, "elapsed_time": "0:05:12", "remaining_time": "0:03:19", "throughput": "0.00", "total_tokens": 0}
|
44 |
+
{"current_steps": 88, "total_steps": 141, "loss": 0.7098, "learning_rate": 3.7662130115485314e-05, "epoch": 1.8429319371727748, "percentage": 62.41, "elapsed_time": "0:05:20", "remaining_time": "0:03:12", "throughput": "0.00", "total_tokens": 0}
|
45 |
+
{"current_steps": 90, "total_steps": 141, "loss": 0.6961, "learning_rate": 3.5262241279454785e-05, "epoch": 1.8848167539267016, "percentage": 63.83, "elapsed_time": "0:05:28", "remaining_time": "0:03:06", "throughput": "0.00", "total_tokens": 0}
|
46 |
+
{"current_steps": 92, "total_steps": 141, "loss": 0.7948, "learning_rate": 3.289899283371657e-05, "epoch": 1.9267015706806283, "percentage": 65.25, "elapsed_time": "0:05:34", "remaining_time": "0:02:58", "throughput": "0.00", "total_tokens": 0}
|
47 |
+
{"current_steps": 94, "total_steps": 141, "loss": 0.7264, "learning_rate": 3.0578260186265265e-05, "epoch": 1.9685863874345548, "percentage": 66.67, "elapsed_time": "0:05:41", "remaining_time": "0:02:50", "throughput": "0.00", "total_tokens": 0}
|
48 |
+
{"current_steps": 96, "total_steps": 141, "loss": 0.6696, "learning_rate": 2.8305813044122097e-05, "epoch": 2.0104712041884816, "percentage": 68.09, "elapsed_time": "0:05:49", "remaining_time": "0:02:43", "throughput": "0.00", "total_tokens": 0}
|
49 |
+
{"current_steps": 98, "total_steps": 141, "loss": 0.7135, "learning_rate": 2.6087301068934106e-05, "epoch": 2.0523560209424083, "percentage": 69.5, "elapsed_time": "0:05:56", "remaining_time": "0:02:36", "throughput": "0.00", "total_tokens": 0}
|
50 |
+
{"current_steps": 100, "total_steps": 141, "loss": 0.7865, "learning_rate": 2.39282398310251e-05, "epoch": 2.094240837696335, "percentage": 70.92, "elapsed_time": "0:06:03", "remaining_time": "0:02:28", "throughput": "0.00", "total_tokens": 0}
|
51 |
+
{"current_steps": 102, "total_steps": 141, "loss": 0.7411, "learning_rate": 2.1833997096818898e-05, "epoch": 2.136125654450262, "percentage": 72.34, "elapsed_time": "0:06:11", "remaining_time": "0:02:21", "throughput": "0.00", "total_tokens": 0}
|
52 |
+
{"current_steps": 104, "total_steps": 141, "loss": 0.772, "learning_rate": 1.980977948372612e-05, "epoch": 2.1780104712041886, "percentage": 73.76, "elapsed_time": "0:06:17", "remaining_time": "0:02:14", "throughput": "0.00", "total_tokens": 0}
|
53 |
+
{"current_steps": 106, "total_steps": 141, "loss": 0.7096, "learning_rate": 1.7860619515673033e-05, "epoch": 2.2198952879581153, "percentage": 75.18, "elapsed_time": "0:06:25", "remaining_time": "0:02:07", "throughput": "0.00", "total_tokens": 0}
|
54 |
+
{"current_steps": 108, "total_steps": 141, "loss": 0.7378, "learning_rate": 1.599136311145402e-05, "epoch": 2.261780104712042, "percentage": 76.6, "elapsed_time": "0:06:32", "remaining_time": "0:01:59", "throughput": "0.00", "total_tokens": 0}
|
55 |
+
{"current_steps": 110, "total_steps": 141, "loss": 0.6471, "learning_rate": 1.4206657537014079e-05, "epoch": 2.303664921465969, "percentage": 78.01, "elapsed_time": "0:06:39", "remaining_time": "0:01:52", "throughput": "0.00", "total_tokens": 0}
|
56 |
+
{"current_steps": 112, "total_steps": 141, "loss": 0.7359, "learning_rate": 1.2510939851613285e-05, "epoch": 2.345549738219895, "percentage": 79.43, "elapsed_time": "0:06:47", "remaining_time": "0:01:45", "throughput": "0.00", "total_tokens": 0}
|
57 |
+
{"current_steps": 114, "total_steps": 141, "loss": 0.7572, "learning_rate": 1.090842587659851e-05, "epoch": 2.387434554973822, "percentage": 80.85, "elapsed_time": "0:06:54", "remaining_time": "0:01:38", "throughput": "0.00", "total_tokens": 0}
|
58 |
+
{"current_steps": 116, "total_steps": 141, "loss": 0.7411, "learning_rate": 9.403099714207175e-06, "epoch": 2.4293193717277486, "percentage": 82.27, "elapsed_time": "0:07:01", "remaining_time": "0:01:30", "throughput": "0.00", "total_tokens": 0}
|
59 |
+
{"current_steps": 118, "total_steps": 141, "loss": 0.6692, "learning_rate": 7.998703842461431e-06, "epoch": 2.4712041884816753, "percentage": 83.69, "elapsed_time": "0:07:08", "remaining_time": "0:01:23", "throughput": "0.00", "total_tokens": 0}
|
60 |
+
{"current_steps": 120, "total_steps": 141, "loss": 0.7619, "learning_rate": 6.698729810778065e-06, "epoch": 2.513089005235602, "percentage": 85.11, "elapsed_time": "0:07:15", "remaining_time": "0:01:16", "throughput": "0.00", "total_tokens": 0}
|
61 |
+
{"current_steps": 122, "total_steps": 141, "loss": 0.708, "learning_rate": 5.506409559426573e-06, "epoch": 2.554973821989529, "percentage": 86.52, "elapsed_time": "0:07:22", "remaining_time": "0:01:08", "throughput": "0.00", "total_tokens": 0}
|
62 |
+
{"current_steps": 124, "total_steps": 141, "loss": 0.7279, "learning_rate": 4.424707384416344e-06, "epoch": 2.5968586387434556, "percentage": 87.94, "elapsed_time": "0:07:30", "remaining_time": "0:01:01", "throughput": "0.00", "total_tokens": 0}
|
63 |
+
{"current_steps": 126, "total_steps": 141, "loss": 0.7629, "learning_rate": 3.4563125677897932e-06, "epoch": 2.6387434554973823, "percentage": 89.36, "elapsed_time": "0:07:37", "remaining_time": "0:00:54", "throughput": "0.00", "total_tokens": 0}
|
64 |
+
{"current_steps": 128, "total_steps": 141, "loss": 0.7334, "learning_rate": 2.603632691643415e-06, "epoch": 2.680628272251309, "percentage": 90.78, "elapsed_time": "0:07:44", "remaining_time": "0:00:47", "throughput": "0.00", "total_tokens": 0}
|
65 |
+
{"current_steps": 130, "total_steps": 141, "loss": 0.6643, "learning_rate": 1.8687876524993987e-06, "epoch": 2.7225130890052354, "percentage": 92.2, "elapsed_time": "0:07:52", "remaining_time": "0:00:39", "throughput": "0.00", "total_tokens": 0}
|
66 |
+
{"current_steps": 132, "total_steps": 141, "loss": 0.7363, "learning_rate": 1.2536043909088191e-06, "epoch": 2.7643979057591626, "percentage": 93.62, "elapsed_time": "0:07:58", "remaining_time": "0:00:32", "throughput": "0.00", "total_tokens": 0}
|
67 |
+
{"current_steps": 134, "total_steps": 141, "loss": 0.7018, "learning_rate": 7.596123493895991e-07, "epoch": 2.806282722513089, "percentage": 95.04, "elapsed_time": "0:08:06", "remaining_time": "0:00:25", "throughput": "0.00", "total_tokens": 0}
|
68 |
+
{"current_steps": 136, "total_steps": 141, "loss": 0.8282, "learning_rate": 3.8803966999139684e-07, "epoch": 2.8481675392670156, "percentage": 96.45, "elapsed_time": "0:08:14", "remaining_time": "0:00:18", "throughput": "0.00", "total_tokens": 0}
|
69 |
+
{"current_steps": 138, "total_steps": 141, "loss": 0.6387, "learning_rate": 1.3981014094099353e-07, "epoch": 2.8900523560209423, "percentage": 97.87, "elapsed_time": "0:08:21", "remaining_time": "0:00:10", "throughput": "0.00", "total_tokens": 0}
|
70 |
+
{"current_steps": 140, "total_steps": 141, "loss": 0.7076, "learning_rate": 1.5540899959187727e-08, "epoch": 2.931937172774869, "percentage": 99.29, "elapsed_time": "0:08:27", "remaining_time": "0:00:03", "throughput": "0.00", "total_tokens": 0}
|
71 |
+
{"current_steps": 141, "total_steps": 141, "epoch": 2.9528795811518327, "percentage": 100.0, "elapsed_time": "0:08:30", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
|
trainer_state.json
ADDED
@@ -0,0 +1,532 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.9528795811518327,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 141,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.041884816753926704,
|
13 |
+
"grad_norm": 0.21733999252319336,
|
14 |
+
"learning_rate": 1.3333333333333333e-05,
|
15 |
+
"loss": 1.0015,
|
16 |
+
"step": 2
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.08376963350785341,
|
20 |
+
"grad_norm": 0.21422453224658966,
|
21 |
+
"learning_rate": 2.6666666666666667e-05,
|
22 |
+
"loss": 0.9283,
|
23 |
+
"step": 4
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.1256544502617801,
|
27 |
+
"grad_norm": 0.18293505907058716,
|
28 |
+
"learning_rate": 4e-05,
|
29 |
+
"loss": 0.8643,
|
30 |
+
"step": 6
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.16753926701570682,
|
34 |
+
"grad_norm": 0.2287076711654663,
|
35 |
+
"learning_rate": 5.333333333333333e-05,
|
36 |
+
"loss": 1.0013,
|
37 |
+
"step": 8
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.2094240837696335,
|
41 |
+
"grad_norm": 0.2509159445762634,
|
42 |
+
"learning_rate": 6.666666666666667e-05,
|
43 |
+
"loss": 0.9341,
|
44 |
+
"step": 10
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.2513089005235602,
|
48 |
+
"grad_norm": 0.21400025486946106,
|
49 |
+
"learning_rate": 8e-05,
|
50 |
+
"loss": 0.9068,
|
51 |
+
"step": 12
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.2931937172774869,
|
55 |
+
"grad_norm": 0.20343424379825592,
|
56 |
+
"learning_rate": 9.333333333333334e-05,
|
57 |
+
"loss": 0.8083,
|
58 |
+
"step": 14
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.33507853403141363,
|
62 |
+
"grad_norm": 0.25129085779190063,
|
63 |
+
"learning_rate": 9.998445910004082e-05,
|
64 |
+
"loss": 0.8985,
|
65 |
+
"step": 16
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.3769633507853403,
|
69 |
+
"grad_norm": 0.28799620270729065,
|
70 |
+
"learning_rate": 9.986018985905901e-05,
|
71 |
+
"loss": 0.9362,
|
72 |
+
"step": 18
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.418848167539267,
|
76 |
+
"grad_norm": 0.29551103711128235,
|
77 |
+
"learning_rate": 9.961196033000861e-05,
|
78 |
+
"loss": 0.9174,
|
79 |
+
"step": 20
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.4607329842931937,
|
83 |
+
"grad_norm": 0.31457847356796265,
|
84 |
+
"learning_rate": 9.924038765061042e-05,
|
85 |
+
"loss": 0.8732,
|
86 |
+
"step": 22
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.5026178010471204,
|
90 |
+
"grad_norm": 0.2715758979320526,
|
91 |
+
"learning_rate": 9.874639560909117e-05,
|
92 |
+
"loss": 0.8653,
|
93 |
+
"step": 24
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.5445026178010471,
|
97 |
+
"grad_norm": 0.25824904441833496,
|
98 |
+
"learning_rate": 9.81312123475006e-05,
|
99 |
+
"loss": 0.8592,
|
100 |
+
"step": 26
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.5863874345549738,
|
104 |
+
"grad_norm": 0.22251802682876587,
|
105 |
+
"learning_rate": 9.73963673083566e-05,
|
106 |
+
"loss": 0.805,
|
107 |
+
"step": 28
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.6282722513089005,
|
111 |
+
"grad_norm": 0.22290602326393127,
|
112 |
+
"learning_rate": 9.654368743221022e-05,
|
113 |
+
"loss": 0.7464,
|
114 |
+
"step": 30
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.6701570680628273,
|
118 |
+
"grad_norm": 0.2132934331893921,
|
119 |
+
"learning_rate": 9.557529261558367e-05,
|
120 |
+
"loss": 0.7796,
|
121 |
+
"step": 32
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.7120418848167539,
|
125 |
+
"grad_norm": 0.19897978007793427,
|
126 |
+
"learning_rate": 9.449359044057345e-05,
|
127 |
+
"loss": 0.7768,
|
128 |
+
"step": 34
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.7539267015706806,
|
132 |
+
"grad_norm": 0.21434754133224487,
|
133 |
+
"learning_rate": 9.330127018922194e-05,
|
134 |
+
"loss": 0.8751,
|
135 |
+
"step": 36
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.7958115183246073,
|
139 |
+
"grad_norm": 0.2214685082435608,
|
140 |
+
"learning_rate": 9.200129615753859e-05,
|
141 |
+
"loss": 0.7966,
|
142 |
+
"step": 38
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.837696335078534,
|
146 |
+
"grad_norm": 0.20432740449905396,
|
147 |
+
"learning_rate": 9.059690028579284e-05,
|
148 |
+
"loss": 0.7963,
|
149 |
+
"step": 40
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.8795811518324608,
|
153 |
+
"grad_norm": 0.23610389232635498,
|
154 |
+
"learning_rate": 8.90915741234015e-05,
|
155 |
+
"loss": 0.8332,
|
156 |
+
"step": 42
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.9214659685863874,
|
160 |
+
"grad_norm": 0.23847244679927826,
|
161 |
+
"learning_rate": 8.748906014838672e-05,
|
162 |
+
"loss": 0.7869,
|
163 |
+
"step": 44
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.9633507853403142,
|
167 |
+
"grad_norm": 0.23536360263824463,
|
168 |
+
"learning_rate": 8.579334246298593e-05,
|
169 |
+
"loss": 0.8517,
|
170 |
+
"step": 46
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.0052356020942408,
|
174 |
+
"grad_norm": 0.24705368280410767,
|
175 |
+
"learning_rate": 8.400863688854597e-05,
|
176 |
+
"loss": 0.8694,
|
177 |
+
"step": 48
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.0471204188481675,
|
181 |
+
"grad_norm": 0.22067400813102722,
|
182 |
+
"learning_rate": 8.213938048432697e-05,
|
183 |
+
"loss": 0.8002,
|
184 |
+
"step": 50
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 1.0890052356020943,
|
188 |
+
"grad_norm": 0.21238695085048676,
|
189 |
+
"learning_rate": 8.019022051627388e-05,
|
190 |
+
"loss": 0.7798,
|
191 |
+
"step": 52
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.130890052356021,
|
195 |
+
"grad_norm": 0.2280968427658081,
|
196 |
+
"learning_rate": 7.81660029031811e-05,
|
197 |
+
"loss": 0.8114,
|
198 |
+
"step": 54
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 1.1727748691099475,
|
202 |
+
"grad_norm": 0.2327934205532074,
|
203 |
+
"learning_rate": 7.60717601689749e-05,
|
204 |
+
"loss": 0.8206,
|
205 |
+
"step": 56
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 1.2146596858638743,
|
209 |
+
"grad_norm": 0.2437446266412735,
|
210 |
+
"learning_rate": 7.391269893106592e-05,
|
211 |
+
"loss": 0.8477,
|
212 |
+
"step": 58
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.256544502617801,
|
216 |
+
"grad_norm": 0.2429206371307373,
|
217 |
+
"learning_rate": 7.169418695587791e-05,
|
218 |
+
"loss": 0.8213,
|
219 |
+
"step": 60
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 1.2984293193717278,
|
223 |
+
"grad_norm": 0.23616257309913635,
|
224 |
+
"learning_rate": 6.942173981373474e-05,
|
225 |
+
"loss": 0.8287,
|
226 |
+
"step": 62
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 1.3403141361256545,
|
230 |
+
"grad_norm": 0.2597900629043579,
|
231 |
+
"learning_rate": 6.710100716628344e-05,
|
232 |
+
"loss": 0.7643,
|
233 |
+
"step": 64
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.3821989528795813,
|
237 |
+
"grad_norm": 0.2668094038963318,
|
238 |
+
"learning_rate": 6.473775872054521e-05,
|
239 |
+
"loss": 0.7315,
|
240 |
+
"step": 66
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 1.4240837696335078,
|
244 |
+
"grad_norm": 0.2583785355091095,
|
245 |
+
"learning_rate": 6.233786988451468e-05,
|
246 |
+
"loss": 0.7811,
|
247 |
+
"step": 68
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 1.4659685863874345,
|
251 |
+
"grad_norm": 0.2756960391998291,
|
252 |
+
"learning_rate": 5.9907307159969884e-05,
|
253 |
+
"loss": 0.754,
|
254 |
+
"step": 70
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.5078534031413613,
|
258 |
+
"grad_norm": 0.28554120659828186,
|
259 |
+
"learning_rate": 5.745211330880872e-05,
|
260 |
+
"loss": 0.7809,
|
261 |
+
"step": 72
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 1.5497382198952878,
|
265 |
+
"grad_norm": 0.3146248459815979,
|
266 |
+
"learning_rate": 5.497839232979084e-05,
|
267 |
+
"loss": 0.8319,
|
268 |
+
"step": 74
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 1.5916230366492146,
|
272 |
+
"grad_norm": 0.2715282142162323,
|
273 |
+
"learning_rate": 5.249229428303486e-05,
|
274 |
+
"loss": 0.7745,
|
275 |
+
"step": 76
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 1.6335078534031413,
|
279 |
+
"grad_norm": 0.28730642795562744,
|
280 |
+
"learning_rate": 5e-05,
|
281 |
+
"loss": 0.8002,
|
282 |
+
"step": 78
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 1.675392670157068,
|
286 |
+
"grad_norm": 0.3208574652671814,
|
287 |
+
"learning_rate": 4.750770571696514e-05,
|
288 |
+
"loss": 0.7718,
|
289 |
+
"step": 80
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 1.7172774869109948,
|
293 |
+
"grad_norm": 0.307959645986557,
|
294 |
+
"learning_rate": 4.502160767020918e-05,
|
295 |
+
"loss": 0.742,
|
296 |
+
"step": 82
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.7591623036649215,
|
300 |
+
"grad_norm": 0.34215685725212097,
|
301 |
+
"learning_rate": 4.254788669119127e-05,
|
302 |
+
"loss": 0.7687,
|
303 |
+
"step": 84
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 1.8010471204188483,
|
307 |
+
"grad_norm": 0.28537240624427795,
|
308 |
+
"learning_rate": 4.0092692840030134e-05,
|
309 |
+
"loss": 0.7066,
|
310 |
+
"step": 86
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 1.8429319371727748,
|
314 |
+
"grad_norm": 0.31295880675315857,
|
315 |
+
"learning_rate": 3.7662130115485314e-05,
|
316 |
+
"loss": 0.7098,
|
317 |
+
"step": 88
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 1.8848167539267016,
|
321 |
+
"grad_norm": 0.2994559705257416,
|
322 |
+
"learning_rate": 3.5262241279454785e-05,
|
323 |
+
"loss": 0.6961,
|
324 |
+
"step": 90
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 1.9267015706806283,
|
328 |
+
"grad_norm": 0.3853859603404999,
|
329 |
+
"learning_rate": 3.289899283371657e-05,
|
330 |
+
"loss": 0.7948,
|
331 |
+
"step": 92
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 1.9685863874345548,
|
335 |
+
"grad_norm": 0.3592422306537628,
|
336 |
+
"learning_rate": 3.0578260186265265e-05,
|
337 |
+
"loss": 0.7264,
|
338 |
+
"step": 94
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 2.0104712041884816,
|
342 |
+
"grad_norm": 0.42988094687461853,
|
343 |
+
"learning_rate": 2.8305813044122097e-05,
|
344 |
+
"loss": 0.6696,
|
345 |
+
"step": 96
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 2.0523560209424083,
|
349 |
+
"grad_norm": 0.3221912086009979,
|
350 |
+
"learning_rate": 2.6087301068934106e-05,
|
351 |
+
"loss": 0.7135,
|
352 |
+
"step": 98
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 2.094240837696335,
|
356 |
+
"grad_norm": 0.3392656743526459,
|
357 |
+
"learning_rate": 2.39282398310251e-05,
|
358 |
+
"loss": 0.7865,
|
359 |
+
"step": 100
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 2.136125654450262,
|
363 |
+
"grad_norm": 0.32586315274238586,
|
364 |
+
"learning_rate": 2.1833997096818898e-05,
|
365 |
+
"loss": 0.7411,
|
366 |
+
"step": 102
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 2.1780104712041886,
|
370 |
+
"grad_norm": 0.36464083194732666,
|
371 |
+
"learning_rate": 1.980977948372612e-05,
|
372 |
+
"loss": 0.772,
|
373 |
+
"step": 104
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 2.2198952879581153,
|
377 |
+
"grad_norm": 0.3270440697669983,
|
378 |
+
"learning_rate": 1.7860619515673033e-05,
|
379 |
+
"loss": 0.7096,
|
380 |
+
"step": 106
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 2.261780104712042,
|
384 |
+
"grad_norm": 0.3391498923301697,
|
385 |
+
"learning_rate": 1.599136311145402e-05,
|
386 |
+
"loss": 0.7378,
|
387 |
+
"step": 108
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 2.303664921465969,
|
391 |
+
"grad_norm": 0.3948444128036499,
|
392 |
+
"learning_rate": 1.4206657537014079e-05,
|
393 |
+
"loss": 0.6471,
|
394 |
+
"step": 110
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 2.345549738219895,
|
398 |
+
"grad_norm": 0.38464757800102234,
|
399 |
+
"learning_rate": 1.2510939851613285e-05,
|
400 |
+
"loss": 0.7359,
|
401 |
+
"step": 112
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 2.387434554973822,
|
405 |
+
"grad_norm": 0.38830411434173584,
|
406 |
+
"learning_rate": 1.090842587659851e-05,
|
407 |
+
"loss": 0.7572,
|
408 |
+
"step": 114
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 2.4293193717277486,
|
412 |
+
"grad_norm": 0.37749606370925903,
|
413 |
+
"learning_rate": 9.403099714207175e-06,
|
414 |
+
"loss": 0.7411,
|
415 |
+
"step": 116
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 2.4712041884816753,
|
419 |
+
"grad_norm": 0.3769814968109131,
|
420 |
+
"learning_rate": 7.998703842461431e-06,
|
421 |
+
"loss": 0.6692,
|
422 |
+
"step": 118
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 2.513089005235602,
|
426 |
+
"grad_norm": 0.4309244453907013,
|
427 |
+
"learning_rate": 6.698729810778065e-06,
|
428 |
+
"loss": 0.7619,
|
429 |
+
"step": 120
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 2.554973821989529,
|
433 |
+
"grad_norm": 0.37709513306617737,
|
434 |
+
"learning_rate": 5.506409559426573e-06,
|
435 |
+
"loss": 0.708,
|
436 |
+
"step": 122
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 2.5968586387434556,
|
440 |
+
"grad_norm": 0.40647101402282715,
|
441 |
+
"learning_rate": 4.424707384416344e-06,
|
442 |
+
"loss": 0.7279,
|
443 |
+
"step": 124
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 2.6387434554973823,
|
447 |
+
"grad_norm": 0.3731394112110138,
|
448 |
+
"learning_rate": 3.4563125677897932e-06,
|
449 |
+
"loss": 0.7629,
|
450 |
+
"step": 126
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 2.680628272251309,
|
454 |
+
"grad_norm": 0.40869101881980896,
|
455 |
+
"learning_rate": 2.603632691643415e-06,
|
456 |
+
"loss": 0.7334,
|
457 |
+
"step": 128
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 2.7225130890052354,
|
461 |
+
"grad_norm": 0.33611902594566345,
|
462 |
+
"learning_rate": 1.8687876524993987e-06,
|
463 |
+
"loss": 0.6643,
|
464 |
+
"step": 130
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 2.7643979057591626,
|
468 |
+
"grad_norm": 0.38377344608306885,
|
469 |
+
"learning_rate": 1.2536043909088191e-06,
|
470 |
+
"loss": 0.7363,
|
471 |
+
"step": 132
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 2.806282722513089,
|
475 |
+
"grad_norm": 0.38260236382484436,
|
476 |
+
"learning_rate": 7.596123493895991e-07,
|
477 |
+
"loss": 0.7018,
|
478 |
+
"step": 134
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 2.8481675392670156,
|
482 |
+
"grad_norm": 0.3747893273830414,
|
483 |
+
"learning_rate": 3.8803966999139684e-07,
|
484 |
+
"loss": 0.8282,
|
485 |
+
"step": 136
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 2.8900523560209423,
|
489 |
+
"grad_norm": 0.40073326230049133,
|
490 |
+
"learning_rate": 1.3981014094099353e-07,
|
491 |
+
"loss": 0.6387,
|
492 |
+
"step": 138
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 2.931937172774869,
|
496 |
+
"grad_norm": 0.4021676480770111,
|
497 |
+
"learning_rate": 1.5540899959187727e-08,
|
498 |
+
"loss": 0.7076,
|
499 |
+
"step": 140
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 2.9528795811518327,
|
503 |
+
"step": 141,
|
504 |
+
"total_flos": 5.744674604829082e+16,
|
505 |
+
"train_loss": 0.7884446775659602,
|
506 |
+
"train_runtime": 510.788,
|
507 |
+
"train_samples_per_second": 8.957,
|
508 |
+
"train_steps_per_second": 0.276
|
509 |
+
}
|
510 |
+
],
|
511 |
+
"logging_steps": 2,
|
512 |
+
"max_steps": 141,
|
513 |
+
"num_input_tokens_seen": 0,
|
514 |
+
"num_train_epochs": 3,
|
515 |
+
"save_steps": 500,
|
516 |
+
"stateful_callbacks": {
|
517 |
+
"TrainerControl": {
|
518 |
+
"args": {
|
519 |
+
"should_epoch_stop": false,
|
520 |
+
"should_evaluate": false,
|
521 |
+
"should_log": false,
|
522 |
+
"should_save": false,
|
523 |
+
"should_training_stop": false
|
524 |
+
},
|
525 |
+
"attributes": {}
|
526 |
+
}
|
527 |
+
},
|
528 |
+
"total_flos": 5.744674604829082e+16,
|
529 |
+
"train_batch_size": 4,
|
530 |
+
"trial_name": null,
|
531 |
+
"trial_params": null
|
532 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43983893470f521a5d365e448af8448f4819056d6c2d89ad6ca9fb6d006dea24
|
3 |
+
size 5304
|
training_loss.png
ADDED
![]() |
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|