Training in progress, step 50, checkpoint
Browse files- last-checkpoint/README.md +202 -0
- last-checkpoint/adapter_config.json +34 -0
- last-checkpoint/adapter_model.safetensors +3 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/special_tokens_map.json +30 -0
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer.model +3 -0
- last-checkpoint/tokenizer_config.json +44 -0
- last-checkpoint/trainer_state.json +408 -0
- last-checkpoint/training_args.bin +3 -0
last-checkpoint/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: lmsys/vicuna-7b-v1.5
|
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 0.13.2
|
last-checkpoint/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "lmsys/vicuna-7b-v1.5",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
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": 128,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 64,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"down_proj",
|
25 |
+
"o_proj",
|
26 |
+
"k_proj",
|
27 |
+
"up_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"v_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
last-checkpoint/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4506e43162c12da46c1fbb645857eafb715ac4448247ce22a0c60cb79e767d1d
|
3 |
+
size 639691872
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d491505e128f186b84f784836ae63b23651c8b235ae7d9f466a3c68b531d01e9
|
3 |
+
size 325339796
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81c6b7932641a54e7d5e2a3b3eaa2a6bbc29fc1c6513c981e348db0724a10bb4
|
3 |
+
size 14244
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e84fc6153e3310b0eb429aac0cac822e6f8efb0a9919ee22745eaa72fdb66b39
|
3 |
+
size 1064
|
last-checkpoint/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
last-checkpoint/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
last-checkpoint/tokenizer_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": false,
|
36 |
+
"model_max_length": 4096,
|
37 |
+
"pad_token": "<unk>",
|
38 |
+
"padding_side": "right",
|
39 |
+
"sp_model_kwargs": {},
|
40 |
+
"spaces_between_special_tokens": false,
|
41 |
+
"tokenizer_class": "LlamaTokenizer",
|
42 |
+
"unk_token": "<unk>",
|
43 |
+
"use_default_system_prompt": false
|
44 |
+
}
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,408 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.201499104499817,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
4 |
+
"epoch": 0.2364066193853428,
|
5 |
+
"eval_steps": 50,
|
6 |
+
"global_step": 50,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.004728132387706856,
|
13 |
+
"grad_norm": 0.9486807584762573,
|
14 |
+
"learning_rate": 1e-05,
|
15 |
+
"loss": 1.8408,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.004728132387706856,
|
20 |
+
"eval_loss": 1.963819146156311,
|
21 |
+
"eval_runtime": 38.0049,
|
22 |
+
"eval_samples_per_second": 9.394,
|
23 |
+
"eval_steps_per_second": 2.368,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.009456264775413711,
|
28 |
+
"grad_norm": 0.9640880227088928,
|
29 |
+
"learning_rate": 2e-05,
|
30 |
+
"loss": 1.8428,
|
31 |
+
"step": 2
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.014184397163120567,
|
35 |
+
"grad_norm": 0.9609369039535522,
|
36 |
+
"learning_rate": 3e-05,
|
37 |
+
"loss": 1.9502,
|
38 |
+
"step": 3
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.018912529550827423,
|
42 |
+
"grad_norm": 0.9109072685241699,
|
43 |
+
"learning_rate": 4e-05,
|
44 |
+
"loss": 1.9277,
|
45 |
+
"step": 4
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.02364066193853428,
|
49 |
+
"grad_norm": 0.9222002625465393,
|
50 |
+
"learning_rate": 5e-05,
|
51 |
+
"loss": 1.8179,
|
52 |
+
"step": 5
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.028368794326241134,
|
56 |
+
"grad_norm": 0.7830185890197754,
|
57 |
+
"learning_rate": 6e-05,
|
58 |
+
"loss": 1.7072,
|
59 |
+
"step": 6
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.03309692671394799,
|
63 |
+
"grad_norm": 0.6503215432167053,
|
64 |
+
"learning_rate": 7e-05,
|
65 |
+
"loss": 1.6178,
|
66 |
+
"step": 7
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.037825059101654845,
|
70 |
+
"grad_norm": 0.5257905125617981,
|
71 |
+
"learning_rate": 8e-05,
|
72 |
+
"loss": 1.5769,
|
73 |
+
"step": 8
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.0425531914893617,
|
77 |
+
"grad_norm": 0.5728737711906433,
|
78 |
+
"learning_rate": 9e-05,
|
79 |
+
"loss": 1.5687,
|
80 |
+
"step": 9
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.04728132387706856,
|
84 |
+
"grad_norm": 0.7015601396560669,
|
85 |
+
"learning_rate": 0.0001,
|
86 |
+
"loss": 1.6133,
|
87 |
+
"step": 10
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.05200945626477541,
|
91 |
+
"grad_norm": 0.797338604927063,
|
92 |
+
"learning_rate": 9.999395316300748e-05,
|
93 |
+
"loss": 1.5002,
|
94 |
+
"step": 11
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.05673758865248227,
|
98 |
+
"grad_norm": 0.6119827628135681,
|
99 |
+
"learning_rate": 9.997581411459941e-05,
|
100 |
+
"loss": 1.5473,
|
101 |
+
"step": 12
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.061465721040189124,
|
105 |
+
"grad_norm": 0.49313884973526,
|
106 |
+
"learning_rate": 9.994558724213054e-05,
|
107 |
+
"loss": 1.4589,
|
108 |
+
"step": 13
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.06619385342789598,
|
112 |
+
"grad_norm": 0.4498696029186249,
|
113 |
+
"learning_rate": 9.990327985667972e-05,
|
114 |
+
"loss": 1.4562,
|
115 |
+
"step": 14
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.07092198581560284,
|
119 |
+
"grad_norm": 0.38253799080848694,
|
120 |
+
"learning_rate": 9.984890219128146e-05,
|
121 |
+
"loss": 1.3475,
|
122 |
+
"step": 15
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.07565011820330969,
|
126 |
+
"grad_norm": 0.40526261925697327,
|
127 |
+
"learning_rate": 9.978246739845094e-05,
|
128 |
+
"loss": 1.3564,
|
129 |
+
"step": 16
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.08037825059101655,
|
133 |
+
"grad_norm": 0.4410207271575928,
|
134 |
+
"learning_rate": 9.970399154700263e-05,
|
135 |
+
"loss": 1.3799,
|
136 |
+
"step": 17
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.0851063829787234,
|
140 |
+
"grad_norm": 0.4076521098613739,
|
141 |
+
"learning_rate": 9.961349361816384e-05,
|
142 |
+
"loss": 1.4092,
|
143 |
+
"step": 18
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.08983451536643026,
|
147 |
+
"grad_norm": 0.4196551442146301,
|
148 |
+
"learning_rate": 9.951099550098349e-05,
|
149 |
+
"loss": 1.3264,
|
150 |
+
"step": 19
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.09456264775413711,
|
154 |
+
"grad_norm": 0.3697325885295868,
|
155 |
+
"learning_rate": 9.939652198703784e-05,
|
156 |
+
"loss": 1.3886,
|
157 |
+
"step": 20
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.09929078014184398,
|
161 |
+
"grad_norm": 0.346131294965744,
|
162 |
+
"learning_rate": 9.927010076443407e-05,
|
163 |
+
"loss": 1.2821,
|
164 |
+
"step": 21
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.10401891252955082,
|
168 |
+
"grad_norm": 0.3620453476905823,
|
169 |
+
"learning_rate": 9.913176241111319e-05,
|
170 |
+
"loss": 1.3636,
|
171 |
+
"step": 22
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.10874704491725769,
|
175 |
+
"grad_norm": 0.37463706731796265,
|
176 |
+
"learning_rate": 9.898154038745408e-05,
|
177 |
+
"loss": 1.275,
|
178 |
+
"step": 23
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.11347517730496454,
|
182 |
+
"grad_norm": 0.3912721574306488,
|
183 |
+
"learning_rate": 9.881947102818036e-05,
|
184 |
+
"loss": 1.2499,
|
185 |
+
"step": 24
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.1182033096926714,
|
189 |
+
"grad_norm": 0.3786635100841522,
|
190 |
+
"learning_rate": 9.864559353357187e-05,
|
191 |
+
"loss": 1.3173,
|
192 |
+
"step": 25
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.12293144208037825,
|
196 |
+
"grad_norm": 0.3728365898132324,
|
197 |
+
"learning_rate": 9.845994995998332e-05,
|
198 |
+
"loss": 1.2287,
|
199 |
+
"step": 26
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.1276595744680851,
|
203 |
+
"grad_norm": 0.40303531289100647,
|
204 |
+
"learning_rate": 9.826258520967178e-05,
|
205 |
+
"loss": 1.2327,
|
206 |
+
"step": 27
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.13238770685579196,
|
210 |
+
"grad_norm": 0.3770873546600342,
|
211 |
+
"learning_rate": 9.805354701993623e-05,
|
212 |
+
"loss": 1.2309,
|
213 |
+
"step": 28
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.13711583924349882,
|
217 |
+
"grad_norm": 0.41253548860549927,
|
218 |
+
"learning_rate": 9.783288595157098e-05,
|
219 |
+
"loss": 1.3503,
|
220 |
+
"step": 29
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.14184397163120568,
|
224 |
+
"grad_norm": 0.3858996033668518,
|
225 |
+
"learning_rate": 9.760065537663649e-05,
|
226 |
+
"loss": 1.2443,
|
227 |
+
"step": 30
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.14657210401891252,
|
231 |
+
"grad_norm": 0.40391531586647034,
|
232 |
+
"learning_rate": 9.735691146555002e-05,
|
233 |
+
"loss": 1.1587,
|
234 |
+
"step": 31
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.15130023640661938,
|
238 |
+
"grad_norm": 0.40914273262023926,
|
239 |
+
"learning_rate": 9.710171317349945e-05,
|
240 |
+
"loss": 1.2247,
|
241 |
+
"step": 32
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.15602836879432624,
|
245 |
+
"grad_norm": 0.41252586245536804,
|
246 |
+
"learning_rate": 9.683512222618377e-05,
|
247 |
+
"loss": 1.1826,
|
248 |
+
"step": 33
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.1607565011820331,
|
252 |
+
"grad_norm": 0.42859312891960144,
|
253 |
+
"learning_rate": 9.655720310488299e-05,
|
254 |
+
"loss": 1.1764,
|
255 |
+
"step": 34
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.16548463356973994,
|
259 |
+
"grad_norm": 0.4406868815422058,
|
260 |
+
"learning_rate": 9.626802303086208e-05,
|
261 |
+
"loss": 1.1773,
|
262 |
+
"step": 35
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.1702127659574468,
|
266 |
+
"grad_norm": 0.46166718006134033,
|
267 |
+
"learning_rate": 9.596765194911181e-05,
|
268 |
+
"loss": 1.3088,
|
269 |
+
"step": 36
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.17494089834515367,
|
273 |
+
"grad_norm": 0.4437083303928375,
|
274 |
+
"learning_rate": 9.565616251143094e-05,
|
275 |
+
"loss": 1.2081,
|
276 |
+
"step": 37
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.17966903073286053,
|
280 |
+
"grad_norm": 0.41885045170783997,
|
281 |
+
"learning_rate": 9.533363005885363e-05,
|
282 |
+
"loss": 1.2329,
|
283 |
+
"step": 38
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.18439716312056736,
|
287 |
+
"grad_norm": 0.40488675236701965,
|
288 |
+
"learning_rate": 9.500013260342651e-05,
|
289 |
+
"loss": 1.1143,
|
290 |
+
"step": 39
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.18912529550827423,
|
294 |
+
"grad_norm": 0.4128928780555725,
|
295 |
+
"learning_rate": 9.465575080933958e-05,
|
296 |
+
"loss": 1.1915,
|
297 |
+
"step": 40
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.1938534278959811,
|
301 |
+
"grad_norm": 0.4129532277584076,
|
302 |
+
"learning_rate": 9.430056797341574e-05,
|
303 |
+
"loss": 1.1523,
|
304 |
+
"step": 41
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.19858156028368795,
|
308 |
+
"grad_norm": 0.4176290035247803,
|
309 |
+
"learning_rate": 9.393467000496344e-05,
|
310 |
+
"loss": 1.1828,
|
311 |
+
"step": 42
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.2033096926713948,
|
315 |
+
"grad_norm": 0.40814054012298584,
|
316 |
+
"learning_rate": 9.355814540499752e-05,
|
317 |
+
"loss": 1.1198,
|
318 |
+
"step": 43
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.20803782505910165,
|
322 |
+
"grad_norm": 0.44160643219947815,
|
323 |
+
"learning_rate": 9.317108524483318e-05,
|
324 |
+
"loss": 1.1523,
|
325 |
+
"step": 44
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.2127659574468085,
|
329 |
+
"grad_norm": 0.449492484331131,
|
330 |
+
"learning_rate": 9.27735831440582e-05,
|
331 |
+
"loss": 1.1841,
|
332 |
+
"step": 45
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.21749408983451538,
|
336 |
+
"grad_norm": 0.4739810526371002,
|
337 |
+
"learning_rate": 9.236573524788887e-05,
|
338 |
+
"loss": 1.2485,
|
339 |
+
"step": 46
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.2222222222222222,
|
343 |
+
"grad_norm": 0.4747321605682373,
|
344 |
+
"learning_rate": 9.194764020391506e-05,
|
345 |
+
"loss": 1.1819,
|
346 |
+
"step": 47
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.22695035460992907,
|
350 |
+
"grad_norm": 0.5036101937294006,
|
351 |
+
"learning_rate": 9.151939913823988e-05,
|
352 |
+
"loss": 1.2246,
|
353 |
+
"step": 48
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.23167848699763594,
|
357 |
+
"grad_norm": 0.4752824008464813,
|
358 |
+
"learning_rate": 9.108111563102004e-05,
|
359 |
+
"loss": 1.1525,
|
360 |
+
"step": 49
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.2364066193853428,
|
364 |
+
"grad_norm": 0.6015028953552246,
|
365 |
+
"learning_rate": 9.063289569141251e-05,
|
366 |
+
"loss": 1.202,
|
367 |
+
"step": 50
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.2364066193853428,
|
371 |
+
"eval_loss": 1.201499104499817,
|
372 |
+
"eval_runtime": 38.7229,
|
373 |
+
"eval_samples_per_second": 9.219,
|
374 |
+
"eval_steps_per_second": 2.324,
|
375 |
+
"step": 50
|
376 |
+
}
|
377 |
+
],
|
378 |
+
"logging_steps": 1,
|
379 |
+
"max_steps": 212,
|
380 |
+
"num_input_tokens_seen": 0,
|
381 |
+
"num_train_epochs": 2,
|
382 |
+
"save_steps": 50,
|
383 |
+
"stateful_callbacks": {
|
384 |
+
"EarlyStoppingCallback": {
|
385 |
+
"args": {
|
386 |
+
"early_stopping_patience": 5,
|
387 |
+
"early_stopping_threshold": 0.0
|
388 |
+
},
|
389 |
+
"attributes": {
|
390 |
+
"early_stopping_patience_counter": 0
|
391 |
+
}
|
392 |
+
},
|
393 |
+
"TrainerControl": {
|
394 |
+
"args": {
|
395 |
+
"should_epoch_stop": false,
|
396 |
+
"should_evaluate": false,
|
397 |
+
"should_log": false,
|
398 |
+
"should_save": true,
|
399 |
+
"should_training_stop": false
|
400 |
+
},
|
401 |
+
"attributes": {}
|
402 |
+
}
|
403 |
+
},
|
404 |
+
"total_flos": 6.685741265662771e+16,
|
405 |
+
"train_batch_size": 8,
|
406 |
+
"trial_name": null,
|
407 |
+
"trial_params": null
|
408 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:197098785ebad943711e80cad3660d50255f76b1a856882ff79045a77f5effb2
|
3 |
+
size 6840
|