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 +428 -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_proj",
|
24 |
+
"c_attn"
|
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:d2d7a002444aeda64444cae48fae98b31cce7cea7f8eae898b5e8f79bdd199ef
|
3 |
+
size 27070688
|
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_loss": 1.9224168062210083,
|
4 |
+
"eval_runtime": 63.692,
|
5 |
+
"eval_samples_per_second": 15.591,
|
6 |
+
"eval_steps_per_second": 1.963,
|
7 |
+
"perplexity": 6.837463340656789,
|
8 |
+
"total_flos": 1.0003539689472e+17,
|
9 |
+
"train_loss": 2.061040549059463,
|
10 |
+
"train_runtime": 1615.6801,
|
11 |
+
"train_samples_per_second": 6.798,
|
12 |
+
"train_steps_per_second": 3.399
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_loss": 1.9224168062210083,
|
4 |
+
"eval_runtime": 63.692,
|
5 |
+
"eval_samples_per_second": 15.591,
|
6 |
+
"eval_steps_per_second": 1.963,
|
7 |
+
"perplexity": 6.837463340656789
|
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": 1.0003539689472e+17,
|
4 |
+
"train_loss": 2.061040549059463,
|
5 |
+
"train_runtime": 1615.6801,
|
6 |
+
"train_samples_per_second": 6.798,
|
7 |
+
"train_steps_per_second": 3.399
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,428 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 5492,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01820830298616169,
|
13 |
+
"grad_norm": 0.22019147872924805,
|
14 |
+
"learning_rate": 3.642987249544627e-06,
|
15 |
+
"loss": 2.4398,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.03641660597232338,
|
20 |
+
"grad_norm": 0.1777569204568863,
|
21 |
+
"learning_rate": 7.285974499089254e-06,
|
22 |
+
"loss": 2.4058,
|
23 |
+
"step": 200
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.05462490895848507,
|
27 |
+
"grad_norm": 0.2692304253578186,
|
28 |
+
"learning_rate": 1.0928961748633882e-05,
|
29 |
+
"loss": 2.3914,
|
30 |
+
"step": 300
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.07283321194464676,
|
34 |
+
"grad_norm": 0.36335742473602295,
|
35 |
+
"learning_rate": 1.4571948998178507e-05,
|
36 |
+
"loss": 2.3211,
|
37 |
+
"step": 400
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.09104151493080845,
|
41 |
+
"grad_norm": 0.5098339319229126,
|
42 |
+
"learning_rate": 1.8214936247723133e-05,
|
43 |
+
"loss": 2.2797,
|
44 |
+
"step": 500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.10924981791697014,
|
48 |
+
"grad_norm": 0.5050227642059326,
|
49 |
+
"learning_rate": 1.999474720010985e-05,
|
50 |
+
"loss": 2.2523,
|
51 |
+
"step": 600
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.12745812090313183,
|
55 |
+
"grad_norm": 0.6238083839416504,
|
56 |
+
"learning_rate": 1.9953983978532914e-05,
|
57 |
+
"loss": 2.2214,
|
58 |
+
"step": 700
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.14566642388929352,
|
62 |
+
"grad_norm": 0.6451362371444702,
|
63 |
+
"learning_rate": 1.987302601308333e-05,
|
64 |
+
"loss": 2.1591,
|
65 |
+
"step": 800
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.1638747268754552,
|
69 |
+
"grad_norm": 0.6711136102676392,
|
70 |
+
"learning_rate": 1.9752200216552278e-05,
|
71 |
+
"loss": 2.1624,
|
72 |
+
"step": 900
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.1820830298616169,
|
76 |
+
"grad_norm": 0.7889479994773865,
|
77 |
+
"learning_rate": 1.9591994490261997e-05,
|
78 |
+
"loss": 2.0842,
|
79 |
+
"step": 1000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.20029133284777859,
|
83 |
+
"grad_norm": 0.8510493040084839,
|
84 |
+
"learning_rate": 1.9393055753893e-05,
|
85 |
+
"loss": 2.1171,
|
86 |
+
"step": 1100
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.21849963583394028,
|
90 |
+
"grad_norm": 0.741717517375946,
|
91 |
+
"learning_rate": 1.915618733318621e-05,
|
92 |
+
"loss": 2.1071,
|
93 |
+
"step": 1200
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.23670793882010197,
|
97 |
+
"grad_norm": 0.7924832701683044,
|
98 |
+
"learning_rate": 1.8882345716068708e-05,
|
99 |
+
"loss": 2.0552,
|
100 |
+
"step": 1300
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.25491624180626365,
|
104 |
+
"grad_norm": 0.8211630582809448,
|
105 |
+
"learning_rate": 1.8572636690301997e-05,
|
106 |
+
"loss": 2.0649,
|
107 |
+
"step": 1400
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.27312454479242537,
|
111 |
+
"grad_norm": 0.7808334231376648,
|
112 |
+
"learning_rate": 1.8228310878249212e-05,
|
113 |
+
"loss": 2.0604,
|
114 |
+
"step": 1500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.29133284777858703,
|
118 |
+
"grad_norm": 1.0906625986099243,
|
119 |
+
"learning_rate": 1.7850758686792054e-05,
|
120 |
+
"loss": 2.08,
|
121 |
+
"step": 1600
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.30954115076474875,
|
125 |
+
"grad_norm": 0.7606624960899353,
|
126 |
+
"learning_rate": 1.7441504692790104e-05,
|
127 |
+
"loss": 2.0447,
|
128 |
+
"step": 1700
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.3277494537509104,
|
132 |
+
"grad_norm": 0.8482190370559692,
|
133 |
+
"learning_rate": 1.700220148675417e-05,
|
134 |
+
"loss": 2.0584,
|
135 |
+
"step": 1800
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.34595775673707213,
|
139 |
+
"grad_norm": 0.8170859813690186,
|
140 |
+
"learning_rate": 1.6534622999593437e-05,
|
141 |
+
"loss": 2.0788,
|
142 |
+
"step": 1900
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.3641660597232338,
|
146 |
+
"grad_norm": 0.9151561260223389,
|
147 |
+
"learning_rate": 1.6040657339383255e-05,
|
148 |
+
"loss": 2.0458,
|
149 |
+
"step": 2000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.3823743627093955,
|
153 |
+
"grad_norm": 0.7852152585983276,
|
154 |
+
"learning_rate": 1.5522299167079173e-05,
|
155 |
+
"loss": 2.0271,
|
156 |
+
"step": 2100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.40058266569555717,
|
160 |
+
"grad_norm": 1.1423839330673218,
|
161 |
+
"learning_rate": 1.4981641641964437e-05,
|
162 |
+
"loss": 2.0153,
|
163 |
+
"step": 2200
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.4187909686817189,
|
167 |
+
"grad_norm": 0.9260895252227783,
|
168 |
+
"learning_rate": 1.44208679693558e-05,
|
169 |
+
"loss": 2.038,
|
170 |
+
"step": 2300
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.43699927166788055,
|
174 |
+
"grad_norm": 0.8138246536254883,
|
175 |
+
"learning_rate": 1.384224258469838e-05,
|
176 |
+
"loss": 2.0325,
|
177 |
+
"step": 2400
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.45520757465404227,
|
181 |
+
"grad_norm": 0.8293213844299316,
|
182 |
+
"learning_rate": 1.3248102009648686e-05,
|
183 |
+
"loss": 1.9852,
|
184 |
+
"step": 2500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.47341587764020393,
|
188 |
+
"grad_norm": 1.0487293004989624,
|
189 |
+
"learning_rate": 1.2640845417069571e-05,
|
190 |
+
"loss": 2.0304,
|
191 |
+
"step": 2600
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.49162418062636565,
|
195 |
+
"grad_norm": 1.4424030780792236,
|
196 |
+
"learning_rate": 1.2022924943036024e-05,
|
197 |
+
"loss": 2.0349,
|
198 |
+
"step": 2700
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.5098324836125273,
|
202 |
+
"grad_norm": 0.930513322353363,
|
203 |
+
"learning_rate": 1.139683578497262e-05,
|
204 |
+
"loss": 2.0298,
|
205 |
+
"step": 2800
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.528040786598689,
|
209 |
+
"grad_norm": 1.3939330577850342,
|
210 |
+
"learning_rate": 1.0765106125906782e-05,
|
211 |
+
"loss": 2.0071,
|
212 |
+
"step": 2900
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.5462490895848507,
|
216 |
+
"grad_norm": 1.0249812602996826,
|
217 |
+
"learning_rate": 1.0130286925524367e-05,
|
218 |
+
"loss": 1.9692,
|
219 |
+
"step": 3000
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.5644573925710124,
|
223 |
+
"grad_norm": 0.9683905243873596,
|
224 |
+
"learning_rate": 9.494941619251817e-06,
|
225 |
+
"loss": 2.0243,
|
226 |
+
"step": 3100
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.5826656955571741,
|
230 |
+
"grad_norm": 1.1064997911453247,
|
231 |
+
"learning_rate": 8.861635766960579e-06,
|
232 |
+
"loss": 1.9983,
|
233 |
+
"step": 3200
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.6008739985433358,
|
237 |
+
"grad_norm": 0.9611035585403442,
|
238 |
+
"learning_rate": 8.232926693092881e-06,
|
239 |
+
"loss": 1.9898,
|
240 |
+
"step": 3300
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.6190823015294975,
|
244 |
+
"grad_norm": 1.2558187246322632,
|
245 |
+
"learning_rate": 7.611353160042658e-06,
|
246 |
+
"loss": 1.9698,
|
247 |
+
"step": 3400
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.6372906045156591,
|
251 |
+
"grad_norm": 1.1066709756851196,
|
252 |
+
"learning_rate": 6.99942511649105e-06,
|
253 |
+
"loss": 2.0468,
|
254 |
+
"step": 3500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.6554989075018208,
|
258 |
+
"grad_norm": 1.0138076543807983,
|
259 |
+
"learning_rate": 6.399613562093272e-06,
|
260 |
+
"loss": 2.0535,
|
261 |
+
"step": 3600
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.6737072104879825,
|
265 |
+
"grad_norm": 1.125917673110962,
|
266 |
+
"learning_rate": 5.814340569443867e-06,
|
267 |
+
"loss": 2.009,
|
268 |
+
"step": 3700
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.6919155134741443,
|
272 |
+
"grad_norm": 0.7838294506072998,
|
273 |
+
"learning_rate": 5.245969503612125e-06,
|
274 |
+
"loss": 1.9229,
|
275 |
+
"step": 3800
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.7101238164603059,
|
279 |
+
"grad_norm": 1.051643967628479,
|
280 |
+
"learning_rate": 4.696795478741786e-06,
|
281 |
+
"loss": 1.9857,
|
282 |
+
"step": 3900
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.7283321194464676,
|
286 |
+
"grad_norm": 0.9563839435577393,
|
287 |
+
"learning_rate": 4.169036090251809e-06,
|
288 |
+
"loss": 2.0503,
|
289 |
+
"step": 4000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.7465404224326293,
|
293 |
+
"grad_norm": 0.8592619299888611,
|
294 |
+
"learning_rate": 3.6648224600620653e-06,
|
295 |
+
"loss": 2.0066,
|
296 |
+
"step": 4100
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.764748725418791,
|
300 |
+
"grad_norm": 0.9203991293907166,
|
301 |
+
"learning_rate": 3.1861906310038825e-06,
|
302 |
+
"loss": 1.9719,
|
303 |
+
"step": 4200
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.7829570284049526,
|
307 |
+
"grad_norm": 0.9755929112434387,
|
308 |
+
"learning_rate": 2.735073345165228e-06,
|
309 |
+
"loss": 1.9785,
|
310 |
+
"step": 4300
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.8011653313911143,
|
314 |
+
"grad_norm": 1.030912160873413,
|
315 |
+
"learning_rate": 2.313292239370102e-06,
|
316 |
+
"loss": 2.0122,
|
317 |
+
"step": 4400
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.8193736343772761,
|
321 |
+
"grad_norm": 1.2122974395751953,
|
322 |
+
"learning_rate": 1.9225504893071823e-06,
|
323 |
+
"loss": 1.9747,
|
324 |
+
"step": 4500
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.8375819373634378,
|
328 |
+
"grad_norm": 1.0663396120071411,
|
329 |
+
"learning_rate": 1.5644259320111733e-06,
|
330 |
+
"loss": 1.9379,
|
331 |
+
"step": 4600
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.8557902403495994,
|
335 |
+
"grad_norm": 0.9615539908409119,
|
336 |
+
"learning_rate": 1.2403646944686198e-06,
|
337 |
+
"loss": 1.9893,
|
338 |
+
"step": 4700
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.8739985433357611,
|
342 |
+
"grad_norm": 1.184589147567749,
|
343 |
+
"learning_rate": 9.516753540762868e-07,
|
344 |
+
"loss": 1.9812,
|
345 |
+
"step": 4800
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.8922068463219228,
|
349 |
+
"grad_norm": 1.2580232620239258,
|
350 |
+
"learning_rate": 6.995236545324624e-07,
|
351 |
+
"loss": 1.948,
|
352 |
+
"step": 4900
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.9104151493080845,
|
356 |
+
"grad_norm": 0.958463728427887,
|
357 |
+
"learning_rate": 4.849277984987221e-07,
|
358 |
+
"loss": 1.9752,
|
359 |
+
"step": 5000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.9286234522942461,
|
363 |
+
"grad_norm": 1.0817508697509766,
|
364 |
+
"learning_rate": 3.0875433604064976e-07,
|
365 |
+
"loss": 2.0005,
|
366 |
+
"step": 5100
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.9468317552804079,
|
370 |
+
"grad_norm": 1.1332553625106812,
|
371 |
+
"learning_rate": 1.7171466545021665e-07,
|
372 |
+
"loss": 1.9255,
|
373 |
+
"step": 5200
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.9650400582665696,
|
377 |
+
"grad_norm": 0.9218988418579102,
|
378 |
+
"learning_rate": 7.436216057970735e-08,
|
379 |
+
"loss": 2.0052,
|
380 |
+
"step": 5300
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.9832483612527313,
|
384 |
+
"grad_norm": 1.2976170778274536,
|
385 |
+
"learning_rate": 1.708993628716016e-08,
|
386 |
+
"loss": 2.0214,
|
387 |
+
"step": 5400
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 1.0,
|
391 |
+
"eval_loss": 1.9224168062210083,
|
392 |
+
"eval_runtime": 63.6773,
|
393 |
+
"eval_samples_per_second": 15.594,
|
394 |
+
"eval_steps_per_second": 1.963,
|
395 |
+
"step": 5492
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 1.0,
|
399 |
+
"step": 5492,
|
400 |
+
"total_flos": 1.0003539689472e+17,
|
401 |
+
"train_loss": 2.061040549059463,
|
402 |
+
"train_runtime": 1615.6801,
|
403 |
+
"train_samples_per_second": 6.798,
|
404 |
+
"train_steps_per_second": 3.399
|
405 |
+
}
|
406 |
+
],
|
407 |
+
"logging_steps": 100,
|
408 |
+
"max_steps": 5492,
|
409 |
+
"num_input_tokens_seen": 0,
|
410 |
+
"num_train_epochs": 1,
|
411 |
+
"save_steps": 500,
|
412 |
+
"stateful_callbacks": {
|
413 |
+
"TrainerControl": {
|
414 |
+
"args": {
|
415 |
+
"should_epoch_stop": false,
|
416 |
+
"should_evaluate": false,
|
417 |
+
"should_log": false,
|
418 |
+
"should_save": true,
|
419 |
+
"should_training_stop": true
|
420 |
+
},
|
421 |
+
"attributes": {}
|
422 |
+
}
|
423 |
+
},
|
424 |
+
"total_flos": 1.0003539689472e+17,
|
425 |
+
"train_batch_size": 2,
|
426 |
+
"trial_name": null,
|
427 |
+
"trial_params": null
|
428 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:562b76a7ab07d8605ae9ca4d2dd69562d1da363f04720fe69c7f093b76ce281c
|
3 |
+
size 5304
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|