Training in progress, step 500
Browse files- README.md +202 -0
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- all_results.json +13 -0
- eval_results.json +8 -0
- merges.txt +0 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +20 -0
- train_results.json +8 -0
- trainer_state.json +645 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: openai-community/gpt2-xl
|
3 |
+
library_name: peft
|
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 0.13.0
|
adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "openai-community/gpt2-xl",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": true,
|
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": 0.1,
|
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 |
+
"c_attn",
|
24 |
+
"c_proj"
|
25 |
+
],
|
26 |
+
"task_type": "CAUSAL_LM",
|
27 |
+
"use_dora": false,
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1095a14f496f4851e8dc82666ba39ed2d0aa18e81b9b668f9bcb290a689ff757
|
3 |
+
size 27070688
|
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_loss": 1.9266319274902344,
|
4 |
+
"eval_runtime": 63.6699,
|
5 |
+
"eval_samples_per_second": 15.549,
|
6 |
+
"eval_steps_per_second": 1.948,
|
7 |
+
"perplexity": 6.866344904696836,
|
8 |
+
"total_flos": 1.5640093507584e+17,
|
9 |
+
"train_loss": 2.1807824082961527,
|
10 |
+
"train_runtime": 2484.8584,
|
11 |
+
"train_samples_per_second": 6.911,
|
12 |
+
"train_steps_per_second": 3.456
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_loss": 1.9266319274902344,
|
4 |
+
"eval_runtime": 63.6699,
|
5 |
+
"eval_samples_per_second": 15.549,
|
6 |
+
"eval_steps_per_second": 1.948,
|
7 |
+
"perplexity": 6.866344904696836
|
8 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"clean_up_tokenization_spaces": false,
|
15 |
+
"eos_token": "<|endoftext|>",
|
16 |
+
"model_max_length": 1024,
|
17 |
+
"pad_token": "<|endoftext|>",
|
18 |
+
"tokenizer_class": "GPT2Tokenizer",
|
19 |
+
"unk_token": "<|endoftext|>"
|
20 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"total_flos": 1.5640093507584e+17,
|
4 |
+
"train_loss": 2.1807824082961527,
|
5 |
+
"train_runtime": 2484.8584,
|
6 |
+
"train_samples_per_second": 6.911,
|
7 |
+
"train_steps_per_second": 3.456
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,645 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 8587,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01164551065564225,
|
13 |
+
"grad_norm": 0.14791734516620636,
|
14 |
+
"learning_rate": 2.331002331002331e-06,
|
15 |
+
"loss": 2.4953,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0232910213112845,
|
20 |
+
"grad_norm": 0.2441452145576477,
|
21 |
+
"learning_rate": 4.662004662004662e-06,
|
22 |
+
"loss": 2.4575,
|
23 |
+
"step": 200
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.03493653196692675,
|
27 |
+
"grad_norm": 0.22649115324020386,
|
28 |
+
"learning_rate": 6.993006993006993e-06,
|
29 |
+
"loss": 2.4409,
|
30 |
+
"step": 300
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.046582042622569,
|
34 |
+
"grad_norm": 0.3321034610271454,
|
35 |
+
"learning_rate": 9.324009324009324e-06,
|
36 |
+
"loss": 2.4497,
|
37 |
+
"step": 400
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.05822755327821125,
|
41 |
+
"grad_norm": 0.36618897318840027,
|
42 |
+
"learning_rate": 1.1655011655011657e-05,
|
43 |
+
"loss": 2.3973,
|
44 |
+
"step": 500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.0698730639338535,
|
48 |
+
"grad_norm": 0.42568501830101013,
|
49 |
+
"learning_rate": 1.3986013986013986e-05,
|
50 |
+
"loss": 2.356,
|
51 |
+
"step": 600
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.08151857458949575,
|
55 |
+
"grad_norm": 0.4560384452342987,
|
56 |
+
"learning_rate": 1.6317016317016318e-05,
|
57 |
+
"loss": 2.317,
|
58 |
+
"step": 700
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.093164085245138,
|
62 |
+
"grad_norm": 0.5321765542030334,
|
63 |
+
"learning_rate": 1.8648018648018647e-05,
|
64 |
+
"loss": 2.3544,
|
65 |
+
"step": 800
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.10480959590078025,
|
69 |
+
"grad_norm": 0.5255011916160583,
|
70 |
+
"learning_rate": 1.999854282682324e-05,
|
71 |
+
"loss": 2.3049,
|
72 |
+
"step": 900
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.1164551065564225,
|
76 |
+
"grad_norm": 0.563510537147522,
|
77 |
+
"learning_rate": 1.9983347507285766e-05,
|
78 |
+
"loss": 2.2863,
|
79 |
+
"step": 1000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.12810061721206475,
|
83 |
+
"grad_norm": 0.5928713083267212,
|
84 |
+
"learning_rate": 1.9951660332101616e-05,
|
85 |
+
"loss": 2.2718,
|
86 |
+
"step": 1100
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.139746127867707,
|
90 |
+
"grad_norm": 0.7078022956848145,
|
91 |
+
"learning_rate": 1.9903533646470504e-05,
|
92 |
+
"loss": 2.2645,
|
93 |
+
"step": 1200
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.15139163852334925,
|
97 |
+
"grad_norm": 0.612659752368927,
|
98 |
+
"learning_rate": 1.9839046952618667e-05,
|
99 |
+
"loss": 2.2507,
|
100 |
+
"step": 1300
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.1630371491789915,
|
104 |
+
"grad_norm": 0.6351534724235535,
|
105 |
+
"learning_rate": 1.9758306778466264e-05,
|
106 |
+
"loss": 2.2474,
|
107 |
+
"step": 1400
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.17468265983463374,
|
111 |
+
"grad_norm": 0.616267740726471,
|
112 |
+
"learning_rate": 1.966144650165e-05,
|
113 |
+
"loss": 2.2574,
|
114 |
+
"step": 1500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.186328170490276,
|
118 |
+
"grad_norm": 0.6416229009628296,
|
119 |
+
"learning_rate": 1.9548626129191778e-05,
|
120 |
+
"loss": 2.249,
|
121 |
+
"step": 1600
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.19797368114591826,
|
125 |
+
"grad_norm": 0.6149903535842896,
|
126 |
+
"learning_rate": 1.9420032033177225e-05,
|
127 |
+
"loss": 2.2497,
|
128 |
+
"step": 1700
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.2096191918015605,
|
132 |
+
"grad_norm": 0.9221161007881165,
|
133 |
+
"learning_rate": 1.927587664288089e-05,
|
134 |
+
"loss": 2.223,
|
135 |
+
"step": 1800
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.22126470245720276,
|
139 |
+
"grad_norm": 0.6987215876579285,
|
140 |
+
"learning_rate": 1.911639809384656e-05,
|
141 |
+
"loss": 2.1861,
|
142 |
+
"step": 1900
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.232910213112845,
|
146 |
+
"grad_norm": 1.0042574405670166,
|
147 |
+
"learning_rate": 1.8941859834502484e-05,
|
148 |
+
"loss": 2.1883,
|
149 |
+
"step": 2000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.24455572376848725,
|
153 |
+
"grad_norm": 0.975431501865387,
|
154 |
+
"learning_rate": 1.8752550190961288e-05,
|
155 |
+
"loss": 2.2078,
|
156 |
+
"step": 2100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.2562012344241295,
|
160 |
+
"grad_norm": 0.8907233476638794,
|
161 |
+
"learning_rate": 1.8548781890723614e-05,
|
162 |
+
"loss": 2.2046,
|
163 |
+
"step": 2200
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.26784674507977174,
|
167 |
+
"grad_norm": 0.9513066411018372,
|
168 |
+
"learning_rate": 1.8330891546072095e-05,
|
169 |
+
"loss": 2.2023,
|
170 |
+
"step": 2300
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.279492255735414,
|
174 |
+
"grad_norm": 0.6928815841674805,
|
175 |
+
"learning_rate": 1.809923909800931e-05,
|
176 |
+
"loss": 2.1932,
|
177 |
+
"step": 2400
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.29113776639105626,
|
181 |
+
"grad_norm": 0.7470653057098389,
|
182 |
+
"learning_rate": 1.7854207221658092e-05,
|
183 |
+
"loss": 2.2031,
|
184 |
+
"step": 2500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.3027832770466985,
|
188 |
+
"grad_norm": 0.7841106653213501,
|
189 |
+
"learning_rate": 1.7596200694106552e-05,
|
190 |
+
"loss": 2.1867,
|
191 |
+
"step": 2600
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.31442878770234073,
|
195 |
+
"grad_norm": 0.9168167114257812,
|
196 |
+
"learning_rate": 1.7325645725742056e-05,
|
197 |
+
"loss": 2.1939,
|
198 |
+
"step": 2700
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.326074298357983,
|
202 |
+
"grad_norm": 0.9133324027061462,
|
203 |
+
"learning_rate": 1.7042989256178744e-05,
|
204 |
+
"loss": 2.1522,
|
205 |
+
"step": 2800
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.33771980901362525,
|
209 |
+
"grad_norm": 0.985498309135437,
|
210 |
+
"learning_rate": 1.6748698215941704e-05,
|
211 |
+
"loss": 2.1735,
|
212 |
+
"step": 2900
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.3493653196692675,
|
216 |
+
"grad_norm": 0.7974863052368164,
|
217 |
+
"learning_rate": 1.6443258755127393e-05,
|
218 |
+
"loss": 2.1939,
|
219 |
+
"step": 3000
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.36101083032490977,
|
223 |
+
"grad_norm": 0.6346118450164795,
|
224 |
+
"learning_rate": 1.6127175440314596e-05,
|
225 |
+
"loss": 2.1204,
|
226 |
+
"step": 3100
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.372656340980552,
|
230 |
+
"grad_norm": 0.8495335578918457,
|
231 |
+
"learning_rate": 1.5800970421052487e-05,
|
232 |
+
"loss": 2.1964,
|
233 |
+
"step": 3200
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.38430185163619424,
|
237 |
+
"grad_norm": 1.029366135597229,
|
238 |
+
"learning_rate": 1.546518256730277e-05,
|
239 |
+
"loss": 2.1838,
|
240 |
+
"step": 3300
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.3959473622918365,
|
244 |
+
"grad_norm": 1.0092447996139526,
|
245 |
+
"learning_rate": 1.5120366579260734e-05,
|
246 |
+
"loss": 2.1607,
|
247 |
+
"step": 3400
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.40759287294747876,
|
251 |
+
"grad_norm": 0.8872857689857483,
|
252 |
+
"learning_rate": 1.4767092071025792e-05,
|
253 |
+
"loss": 2.1836,
|
254 |
+
"step": 3500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.419238383603121,
|
258 |
+
"grad_norm": 0.8824167251586914,
|
259 |
+
"learning_rate": 1.4405942629635174e-05,
|
260 |
+
"loss": 2.1207,
|
261 |
+
"step": 3600
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.4308838942587632,
|
265 |
+
"grad_norm": 0.7451480627059937,
|
266 |
+
"learning_rate": 1.4037514851015241e-05,
|
267 |
+
"loss": 2.215,
|
268 |
+
"step": 3700
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.4425294049144055,
|
272 |
+
"grad_norm": 0.9333692193031311,
|
273 |
+
"learning_rate": 1.3662417354442924e-05,
|
274 |
+
"loss": 2.1836,
|
275 |
+
"step": 3800
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.45417491557004774,
|
279 |
+
"grad_norm": 0.9870197176933289,
|
280 |
+
"learning_rate": 1.3281269777145354e-05,
|
281 |
+
"loss": 2.1935,
|
282 |
+
"step": 3900
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.46582042622569,
|
286 |
+
"grad_norm": 1.1925898790359497,
|
287 |
+
"learning_rate": 1.2894701750698541e-05,
|
288 |
+
"loss": 2.1383,
|
289 |
+
"step": 4000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.47746593688133226,
|
293 |
+
"grad_norm": 0.8721115589141846,
|
294 |
+
"learning_rate": 1.2503351860916024e-05,
|
295 |
+
"loss": 2.1506,
|
296 |
+
"step": 4100
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.4891114475369745,
|
300 |
+
"grad_norm": 1.3675851821899414,
|
301 |
+
"learning_rate": 1.2107866592945686e-05,
|
302 |
+
"loss": 2.1562,
|
303 |
+
"step": 4200
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.5007569581926168,
|
307 |
+
"grad_norm": 0.9814177751541138,
|
308 |
+
"learning_rate": 1.1708899263317381e-05,
|
309 |
+
"loss": 2.1394,
|
310 |
+
"step": 4300
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.512402468848259,
|
314 |
+
"grad_norm": 0.8111391067504883,
|
315 |
+
"learning_rate": 1.1307108940705536e-05,
|
316 |
+
"loss": 2.1605,
|
317 |
+
"step": 4400
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.5240479795039013,
|
321 |
+
"grad_norm": 0.9435734152793884,
|
322 |
+
"learning_rate": 1.090315935718958e-05,
|
323 |
+
"loss": 2.1108,
|
324 |
+
"step": 4500
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.5356934901595435,
|
328 |
+
"grad_norm": 0.8855921626091003,
|
329 |
+
"learning_rate": 1.0497717811810748e-05,
|
330 |
+
"loss": 2.1364,
|
331 |
+
"step": 4600
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.5473390008151857,
|
335 |
+
"grad_norm": 0.7305698990821838,
|
336 |
+
"learning_rate": 1.0091454068236455e-05,
|
337 |
+
"loss": 2.1498,
|
338 |
+
"step": 4700
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.558984511470828,
|
342 |
+
"grad_norm": 1.123586654663086,
|
343 |
+
"learning_rate": 9.685039248353284e-06,
|
344 |
+
"loss": 2.1634,
|
345 |
+
"step": 4800
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.5706300221264703,
|
349 |
+
"grad_norm": 0.857729434967041,
|
350 |
+
"learning_rate": 9.279144723616279e-06,
|
351 |
+
"loss": 2.0721,
|
352 |
+
"step": 4900
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.5822755327821125,
|
356 |
+
"grad_norm": 0.7783474326133728,
|
357 |
+
"learning_rate": 8.874441005985965e-06,
|
358 |
+
"loss": 2.1569,
|
359 |
+
"step": 5000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.5939210434377548,
|
363 |
+
"grad_norm": 1.0050169229507446,
|
364 |
+
"learning_rate": 8.47159664028521e-06,
|
365 |
+
"loss": 2.1631,
|
366 |
+
"step": 5100
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.605566554093397,
|
370 |
+
"grad_norm": 0.7871978282928467,
|
371 |
+
"learning_rate": 8.07127709980564e-06,
|
372 |
+
"loss": 2.1207,
|
373 |
+
"step": 5200
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.6172120647490392,
|
377 |
+
"grad_norm": 1.3452588319778442,
|
378 |
+
"learning_rate": 7.674143686988085e-06,
|
379 |
+
"loss": 2.0871,
|
380 |
+
"step": 5300
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.6288575754046815,
|
384 |
+
"grad_norm": 0.7304858565330505,
|
385 |
+
"learning_rate": 7.280852440992941e-06,
|
386 |
+
"loss": 2.1289,
|
387 |
+
"step": 5400
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.6405030860603237,
|
391 |
+
"grad_norm": 0.9213933944702148,
|
392 |
+
"learning_rate": 6.89205305396518e-06,
|
393 |
+
"loss": 2.1067,
|
394 |
+
"step": 5500
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.652148596715966,
|
398 |
+
"grad_norm": 0.9295869469642639,
|
399 |
+
"learning_rate": 6.508387797784227e-06,
|
400 |
+
"loss": 2.0959,
|
401 |
+
"step": 5600
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.6637941073716083,
|
405 |
+
"grad_norm": 0.9920222759246826,
|
406 |
+
"learning_rate": 6.130490463071604e-06,
|
407 |
+
"loss": 2.0919,
|
408 |
+
"step": 5700
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.6754396180272505,
|
412 |
+
"grad_norm": 0.8308998942375183,
|
413 |
+
"learning_rate": 5.758985312209124e-06,
|
414 |
+
"loss": 2.1206,
|
415 |
+
"step": 5800
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.6870851286828927,
|
419 |
+
"grad_norm": 1.1122294664382935,
|
420 |
+
"learning_rate": 5.394486048097099e-06,
|
421 |
+
"loss": 2.116,
|
422 |
+
"step": 5900
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.698730639338535,
|
426 |
+
"grad_norm": 0.7995828986167908,
|
427 |
+
"learning_rate": 5.037594800356142e-06,
|
428 |
+
"loss": 2.1159,
|
429 |
+
"step": 6000
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.7103761499941772,
|
433 |
+
"grad_norm": 1.1691644191741943,
|
434 |
+
"learning_rate": 4.688901130647314e-06,
|
435 |
+
"loss": 2.1396,
|
436 |
+
"step": 6100
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.7220216606498195,
|
440 |
+
"grad_norm": 0.8228808045387268,
|
441 |
+
"learning_rate": 4.348981058753708e-06,
|
442 |
+
"loss": 2.0819,
|
443 |
+
"step": 6200
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.7336671713054618,
|
447 |
+
"grad_norm": 1.0278650522232056,
|
448 |
+
"learning_rate": 4.018396111032394e-06,
|
449 |
+
"loss": 2.1227,
|
450 |
+
"step": 6300
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.745312681961104,
|
454 |
+
"grad_norm": 0.9175333976745605,
|
455 |
+
"learning_rate": 3.697692392808545e-06,
|
456 |
+
"loss": 2.1037,
|
457 |
+
"step": 6400
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.7569581926167462,
|
461 |
+
"grad_norm": 0.7555139064788818,
|
462 |
+
"learning_rate": 3.387399686244144e-06,
|
463 |
+
"loss": 2.0953,
|
464 |
+
"step": 6500
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.7686037032723885,
|
468 |
+
"grad_norm": 0.8671744465827942,
|
469 |
+
"learning_rate": 3.0880305751715402e-06,
|
470 |
+
"loss": 2.1201,
|
471 |
+
"step": 6600
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.7802492139280307,
|
475 |
+
"grad_norm": 0.8459142446517944,
|
476 |
+
"learning_rate": 2.800079598337505e-06,
|
477 |
+
"loss": 2.1136,
|
478 |
+
"step": 6700
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.791894724583673,
|
482 |
+
"grad_norm": 0.763583242893219,
|
483 |
+
"learning_rate": 2.524022432456664e-06,
|
484 |
+
"loss": 2.1386,
|
485 |
+
"step": 6800
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.8035402352393153,
|
489 |
+
"grad_norm": 0.8807295560836792,
|
490 |
+
"learning_rate": 2.260315106423807e-06,
|
491 |
+
"loss": 2.0779,
|
492 |
+
"step": 6900
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.8151857458949575,
|
496 |
+
"grad_norm": 0.8740783333778381,
|
497 |
+
"learning_rate": 2.0093932479830935e-06,
|
498 |
+
"loss": 2.1367,
|
499 |
+
"step": 7000
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.8268312565505997,
|
503 |
+
"grad_norm": 1.039287805557251,
|
504 |
+
"learning_rate": 1.7716713640987526e-06,
|
505 |
+
"loss": 2.1166,
|
506 |
+
"step": 7100
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.838476767206242,
|
510 |
+
"grad_norm": 0.8560532331466675,
|
511 |
+
"learning_rate": 1.5475421562158854e-06,
|
512 |
+
"loss": 2.1459,
|
513 |
+
"step": 7200
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.8501222778618842,
|
517 |
+
"grad_norm": 0.9102568030357361,
|
518 |
+
"learning_rate": 1.3373758715426444e-06,
|
519 |
+
"loss": 2.1095,
|
520 |
+
"step": 7300
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.8617677885175264,
|
524 |
+
"grad_norm": 0.8189859390258789,
|
525 |
+
"learning_rate": 1.141519691425379e-06,
|
526 |
+
"loss": 2.0852,
|
527 |
+
"step": 7400
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.8734132991731688,
|
531 |
+
"grad_norm": 0.9001794457435608,
|
532 |
+
"learning_rate": 9.60297157827106e-07,
|
533 |
+
"loss": 2.1364,
|
534 |
+
"step": 7500
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.885058809828811,
|
538 |
+
"grad_norm": 0.8623350262641907,
|
539 |
+
"learning_rate": 7.94007638856753e-07,
|
540 |
+
"loss": 2.1407,
|
541 |
+
"step": 7600
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.8967043204844533,
|
545 |
+
"grad_norm": 0.8134225010871887,
|
546 |
+
"learning_rate": 6.429258342320677e-07,
|
547 |
+
"loss": 2.1512,
|
548 |
+
"step": 7700
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.9083498311400955,
|
552 |
+
"grad_norm": 0.8605279326438904,
|
553 |
+
"learning_rate": 5.073013214931377e-07,
|
554 |
+
"loss": 2.1837,
|
555 |
+
"step": 7800
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.9199953417957377,
|
559 |
+
"grad_norm": 0.8916401267051697,
|
560 |
+
"learning_rate": 3.8735814371615554e-07,
|
561 |
+
"loss": 2.1317,
|
562 |
+
"step": 7900
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.93164085245138,
|
566 |
+
"grad_norm": 0.8076800107955933,
|
567 |
+
"learning_rate": 2.8329443940849577e-07,
|
568 |
+
"loss": 2.1349,
|
569 |
+
"step": 8000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.9432863631070223,
|
573 |
+
"grad_norm": 0.7975759506225586,
|
574 |
+
"learning_rate": 1.9528211519649341e-07,
|
575 |
+
"loss": 2.094,
|
576 |
+
"step": 8100
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.9549318737626645,
|
580 |
+
"grad_norm": 1.0410187244415283,
|
581 |
+
"learning_rate": 1.234665618466202e-07,
|
582 |
+
"loss": 2.1501,
|
583 |
+
"step": 8200
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.9665773844183068,
|
587 |
+
"grad_norm": 0.8723394274711609,
|
588 |
+
"learning_rate": 6.796641408917671e-08,
|
589 |
+
"loss": 2.0692,
|
590 |
+
"step": 8300
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.978222895073949,
|
594 |
+
"grad_norm": 0.7656298279762268,
|
595 |
+
"learning_rate": 2.8873354641258955e-08,
|
596 |
+
"loss": 2.0986,
|
597 |
+
"step": 8400
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.9898684057295912,
|
601 |
+
"grad_norm": 1.4604876041412354,
|
602 |
+
"learning_rate": 6.396496618182868e-09,
|
603 |
+
"loss": 2.1445,
|
604 |
+
"step": 8500
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 1.0,
|
608 |
+
"eval_loss": 1.9266319274902344,
|
609 |
+
"eval_runtime": 63.649,
|
610 |
+
"eval_samples_per_second": 15.554,
|
611 |
+
"eval_steps_per_second": 1.948,
|
612 |
+
"step": 8587
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 1.0,
|
616 |
+
"step": 8587,
|
617 |
+
"total_flos": 1.5640093507584e+17,
|
618 |
+
"train_loss": 2.1807824082961527,
|
619 |
+
"train_runtime": 2484.8584,
|
620 |
+
"train_samples_per_second": 6.911,
|
621 |
+
"train_steps_per_second": 3.456
|
622 |
+
}
|
623 |
+
],
|
624 |
+
"logging_steps": 100,
|
625 |
+
"max_steps": 8587,
|
626 |
+
"num_input_tokens_seen": 0,
|
627 |
+
"num_train_epochs": 1,
|
628 |
+
"save_steps": 500,
|
629 |
+
"stateful_callbacks": {
|
630 |
+
"TrainerControl": {
|
631 |
+
"args": {
|
632 |
+
"should_epoch_stop": false,
|
633 |
+
"should_evaluate": false,
|
634 |
+
"should_log": false,
|
635 |
+
"should_save": true,
|
636 |
+
"should_training_stop": true
|
637 |
+
},
|
638 |
+
"attributes": {}
|
639 |
+
}
|
640 |
+
},
|
641 |
+
"total_flos": 1.5640093507584e+17,
|
642 |
+
"train_batch_size": 2,
|
643 |
+
"trial_name": null,
|
644 |
+
"trial_params": null
|
645 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0336db35530bc19737741564cfe17af26e088697af3ecb56d0c6d50e011662a4
|
3 |
+
size 5304
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|