Upload folder using huggingface_hub
Browse files- adapter_config.json +34 -0
- checkpoint-76/README.md +202 -0
- checkpoint-76/adapter_config.json +34 -0
- checkpoint-76/adapter_model.safetensors +3 -0
- checkpoint-76/optimizer.pt +3 -0
- checkpoint-76/rng_state_0.pth +3 -0
- checkpoint-76/rng_state_1.pth +3 -0
- checkpoint-76/scheduler.pt +3 -0
- checkpoint-76/special_tokens_map.json +24 -0
- checkpoint-76/tokenizer.model +3 -0
- checkpoint-76/tokenizer_config.json +0 -0
- checkpoint-76/trainer_state.json +593 -0
- checkpoint-76/training_args.bin +3 -0
- config.json +41 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.3",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": false,
|
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": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 32,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"gate_proj",
|
24 |
+
"o_proj",
|
25 |
+
"down_proj",
|
26 |
+
"k_proj",
|
27 |
+
"v_proj",
|
28 |
+
"up_proj",
|
29 |
+
"q_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-76/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: mistralai/Mistral-7B-v0.3
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.10.0
|
checkpoint-76/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.3",
|
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": 16,
|
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": 32,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"up_proj",
|
24 |
+
"o_proj",
|
25 |
+
"q_proj",
|
26 |
+
"k_proj",
|
27 |
+
"gate_proj",
|
28 |
+
"v_proj",
|
29 |
+
"down_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-76/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb9060a90f9d59c89f89ef7788ec114ab0161074731cf8bf273a83718431afd5
|
3 |
+
size 335604696
|
checkpoint-76/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb30f4496893edaf1811b1f60ef50944169b674417f744383f0e0a0311292892
|
3 |
+
size 671364090
|
checkpoint-76/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48da1126c653afed0e044f186d0b49f1e65c77952d648ee33d6c6c4855796131
|
3 |
+
size 14512
|
checkpoint-76/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9578ee48d006eead2fecbbe47daf1daedbf65e31ed3b6e12601b72af605797ab
|
3 |
+
size 14512
|
checkpoint-76/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:869be1b688bd945109320a2a0a85a6a4361d496077d7dfbf1f735bc3bd3fb012
|
3 |
+
size 1064
|
checkpoint-76/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
checkpoint-76/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
|
3 |
+
size 587404
|
checkpoint-76/tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-76/trainer_state.json
ADDED
@@ -0,0 +1,593 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9934640522875817,
|
5 |
+
"eval_steps": 19,
|
6 |
+
"global_step": 76,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01,
|
13 |
+
"grad_norm": 0.5949503183364868,
|
14 |
+
"learning_rate": 2e-05,
|
15 |
+
"loss": 0.6013,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.01,
|
20 |
+
"eval_loss": 0.6381258368492126,
|
21 |
+
"eval_runtime": 227.2126,
|
22 |
+
"eval_samples_per_second": 0.99,
|
23 |
+
"eval_steps_per_second": 0.251,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.03,
|
28 |
+
"grad_norm": 0.64601069688797,
|
29 |
+
"learning_rate": 4e-05,
|
30 |
+
"loss": 0.576,
|
31 |
+
"step": 2
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.04,
|
35 |
+
"grad_norm": 0.6663902997970581,
|
36 |
+
"learning_rate": 6e-05,
|
37 |
+
"loss": 0.6185,
|
38 |
+
"step": 3
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.05,
|
42 |
+
"grad_norm": 0.5505500435829163,
|
43 |
+
"learning_rate": 8e-05,
|
44 |
+
"loss": 0.6262,
|
45 |
+
"step": 4
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.07,
|
49 |
+
"grad_norm": 0.48474058508872986,
|
50 |
+
"learning_rate": 0.0001,
|
51 |
+
"loss": 0.4706,
|
52 |
+
"step": 5
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.08,
|
56 |
+
"grad_norm": 0.38366734981536865,
|
57 |
+
"learning_rate": 0.00012,
|
58 |
+
"loss": 0.4193,
|
59 |
+
"step": 6
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.09,
|
63 |
+
"grad_norm": 0.4141893982887268,
|
64 |
+
"learning_rate": 0.00014,
|
65 |
+
"loss": 0.4098,
|
66 |
+
"step": 7
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.1,
|
70 |
+
"grad_norm": 0.34236717224121094,
|
71 |
+
"learning_rate": 0.00016,
|
72 |
+
"loss": 0.3945,
|
73 |
+
"step": 8
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.12,
|
77 |
+
"grad_norm": 0.39320266246795654,
|
78 |
+
"learning_rate": 0.00018,
|
79 |
+
"loss": 0.275,
|
80 |
+
"step": 9
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.13,
|
84 |
+
"grad_norm": 0.2930893898010254,
|
85 |
+
"learning_rate": 0.0002,
|
86 |
+
"loss": 0.2816,
|
87 |
+
"step": 10
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.14,
|
91 |
+
"grad_norm": 0.3190990388393402,
|
92 |
+
"learning_rate": 0.00019997552766852432,
|
93 |
+
"loss": 0.3329,
|
94 |
+
"step": 11
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.16,
|
98 |
+
"grad_norm": 0.2727949917316437,
|
99 |
+
"learning_rate": 0.00019990212265199738,
|
100 |
+
"loss": 0.2907,
|
101 |
+
"step": 12
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.17,
|
105 |
+
"grad_norm": 0.26549383997917175,
|
106 |
+
"learning_rate": 0.00019977982087825713,
|
107 |
+
"loss": 0.2683,
|
108 |
+
"step": 13
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.18,
|
112 |
+
"grad_norm": 0.25718459486961365,
|
113 |
+
"learning_rate": 0.00019960868220749448,
|
114 |
+
"loss": 0.3263,
|
115 |
+
"step": 14
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.2,
|
119 |
+
"grad_norm": 0.21319492161273956,
|
120 |
+
"learning_rate": 0.00019938879040295508,
|
121 |
+
"loss": 0.2356,
|
122 |
+
"step": 15
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.21,
|
126 |
+
"grad_norm": 0.21261896193027496,
|
127 |
+
"learning_rate": 0.00019912025308994148,
|
128 |
+
"loss": 0.2944,
|
129 |
+
"step": 16
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.22,
|
133 |
+
"grad_norm": 0.17002587020397186,
|
134 |
+
"learning_rate": 0.0001988032017031364,
|
135 |
+
"loss": 0.2497,
|
136 |
+
"step": 17
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.24,
|
140 |
+
"grad_norm": 0.2019287794828415,
|
141 |
+
"learning_rate": 0.00019843779142227256,
|
142 |
+
"loss": 0.2193,
|
143 |
+
"step": 18
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.25,
|
147 |
+
"grad_norm": 0.17646998167037964,
|
148 |
+
"learning_rate": 0.0001980242010961803,
|
149 |
+
"loss": 0.3043,
|
150 |
+
"step": 19
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.25,
|
154 |
+
"eval_loss": 0.23305918276309967,
|
155 |
+
"eval_runtime": 228.0462,
|
156 |
+
"eval_samples_per_second": 0.987,
|
157 |
+
"eval_steps_per_second": 0.25,
|
158 |
+
"step": 19
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.26,
|
162 |
+
"grad_norm": 0.19342155754566193,
|
163 |
+
"learning_rate": 0.0001975626331552507,
|
164 |
+
"loss": 0.2639,
|
165 |
+
"step": 20
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.27,
|
169 |
+
"grad_norm": 0.2633172273635864,
|
170 |
+
"learning_rate": 0.00019705331351235674,
|
171 |
+
"loss": 0.2531,
|
172 |
+
"step": 21
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 0.29,
|
176 |
+
"grad_norm": 0.20328564941883087,
|
177 |
+
"learning_rate": 0.00019649649145228102,
|
178 |
+
"loss": 0.2239,
|
179 |
+
"step": 22
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.3,
|
183 |
+
"grad_norm": 0.21121543645858765,
|
184 |
+
"learning_rate": 0.00019589243950970402,
|
185 |
+
"loss": 0.2192,
|
186 |
+
"step": 23
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 0.31,
|
190 |
+
"grad_norm": 0.20558255910873413,
|
191 |
+
"learning_rate": 0.00019524145333581317,
|
192 |
+
"loss": 0.2398,
|
193 |
+
"step": 24
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.33,
|
197 |
+
"grad_norm": 0.1567656546831131,
|
198 |
+
"learning_rate": 0.00019454385155359702,
|
199 |
+
"loss": 0.2308,
|
200 |
+
"step": 25
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.34,
|
204 |
+
"grad_norm": 0.1913561373949051,
|
205 |
+
"learning_rate": 0.00019379997560189675,
|
206 |
+
"loss": 0.2772,
|
207 |
+
"step": 26
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.35,
|
211 |
+
"grad_norm": 0.17273519933223724,
|
212 |
+
"learning_rate": 0.00019301018956828964,
|
213 |
+
"loss": 0.2506,
|
214 |
+
"step": 27
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.37,
|
218 |
+
"grad_norm": 0.17341050505638123,
|
219 |
+
"learning_rate": 0.00019217488001088784,
|
220 |
+
"loss": 0.3025,
|
221 |
+
"step": 28
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.38,
|
225 |
+
"grad_norm": 0.16498418152332306,
|
226 |
+
"learning_rate": 0.00019129445576913888,
|
227 |
+
"loss": 0.2379,
|
228 |
+
"step": 29
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 0.39,
|
232 |
+
"grad_norm": 0.18727342784404755,
|
233 |
+
"learning_rate": 0.0001903693477637204,
|
234 |
+
"loss": 0.1984,
|
235 |
+
"step": 30
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 0.41,
|
239 |
+
"grad_norm": 0.16094434261322021,
|
240 |
+
"learning_rate": 0.00018940000878562758,
|
241 |
+
"loss": 0.274,
|
242 |
+
"step": 31
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.42,
|
246 |
+
"grad_norm": 0.19264625012874603,
|
247 |
+
"learning_rate": 0.0001883869132745561,
|
248 |
+
"loss": 0.166,
|
249 |
+
"step": 32
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.43,
|
253 |
+
"grad_norm": 0.20498374104499817,
|
254 |
+
"learning_rate": 0.00018733055708668926,
|
255 |
+
"loss": 0.2288,
|
256 |
+
"step": 33
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.44,
|
260 |
+
"grad_norm": 0.2155662328004837,
|
261 |
+
"learning_rate": 0.00018623145725200278,
|
262 |
+
"loss": 0.2285,
|
263 |
+
"step": 34
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.46,
|
267 |
+
"grad_norm": 0.15915091335773468,
|
268 |
+
"learning_rate": 0.00018509015172120621,
|
269 |
+
"loss": 0.1889,
|
270 |
+
"step": 35
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 0.47,
|
274 |
+
"grad_norm": 0.307817280292511,
|
275 |
+
"learning_rate": 0.00018390719910244487,
|
276 |
+
"loss": 0.2761,
|
277 |
+
"step": 36
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 0.48,
|
281 |
+
"grad_norm": 0.16877825558185577,
|
282 |
+
"learning_rate": 0.00018268317838789088,
|
283 |
+
"loss": 0.1846,
|
284 |
+
"step": 37
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.5,
|
288 |
+
"grad_norm": 0.1811710000038147,
|
289 |
+
"learning_rate": 0.00018141868867035745,
|
290 |
+
"loss": 0.2089,
|
291 |
+
"step": 38
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.5,
|
295 |
+
"eval_loss": 0.21359780430793762,
|
296 |
+
"eval_runtime": 230.1518,
|
297 |
+
"eval_samples_per_second": 0.978,
|
298 |
+
"eval_steps_per_second": 0.248,
|
299 |
+
"step": 38
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 0.51,
|
303 |
+
"grad_norm": 0.1842685490846634,
|
304 |
+
"learning_rate": 0.00018011434885007482,
|
305 |
+
"loss": 0.2266,
|
306 |
+
"step": 39
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 0.52,
|
310 |
+
"grad_norm": 0.14146481454372406,
|
311 |
+
"learning_rate": 0.00017877079733177184,
|
312 |
+
"loss": 0.2139,
|
313 |
+
"step": 40
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 0.54,
|
317 |
+
"grad_norm": 0.1733115017414093,
|
318 |
+
"learning_rate": 0.00017738869171221068,
|
319 |
+
"loss": 0.1732,
|
320 |
+
"step": 41
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 0.55,
|
324 |
+
"grad_norm": 0.15819582343101501,
|
325 |
+
"learning_rate": 0.0001759687084583285,
|
326 |
+
"loss": 0.2481,
|
327 |
+
"step": 42
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.56,
|
331 |
+
"grad_norm": 0.1295730471611023,
|
332 |
+
"learning_rate": 0.00017451154257614287,
|
333 |
+
"loss": 0.17,
|
334 |
+
"step": 43
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 0.58,
|
338 |
+
"grad_norm": 0.146436408162117,
|
339 |
+
"learning_rate": 0.00017301790727058345,
|
340 |
+
"loss": 0.175,
|
341 |
+
"step": 44
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 0.59,
|
345 |
+
"grad_norm": 0.16391891241073608,
|
346 |
+
"learning_rate": 0.00017148853359641626,
|
347 |
+
"loss": 0.2264,
|
348 |
+
"step": 45
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 0.6,
|
352 |
+
"grad_norm": 0.1425042748451233,
|
353 |
+
"learning_rate": 0.00016992417010043142,
|
354 |
+
"loss": 0.2043,
|
355 |
+
"step": 46
|
356 |
+
},
|
357 |
+
{
|
358 |
+
"epoch": 0.61,
|
359 |
+
"grad_norm": 0.13763852417469025,
|
360 |
+
"learning_rate": 0.00016832558245506935,
|
361 |
+
"loss": 0.2073,
|
362 |
+
"step": 47
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 0.63,
|
366 |
+
"grad_norm": 0.15860064327716827,
|
367 |
+
"learning_rate": 0.0001666935530836651,
|
368 |
+
"loss": 0.252,
|
369 |
+
"step": 48
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.64,
|
373 |
+
"grad_norm": 0.135626882314682,
|
374 |
+
"learning_rate": 0.0001650288807774937,
|
375 |
+
"loss": 0.2388,
|
376 |
+
"step": 49
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 0.65,
|
380 |
+
"grad_norm": 0.168660506606102,
|
381 |
+
"learning_rate": 0.0001633323803048047,
|
382 |
+
"loss": 0.2523,
|
383 |
+
"step": 50
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 0.67,
|
387 |
+
"grad_norm": 0.16346889734268188,
|
388 |
+
"learning_rate": 0.00016160488201203644,
|
389 |
+
"loss": 0.2764,
|
390 |
+
"step": 51
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 0.68,
|
394 |
+
"grad_norm": 0.1559883952140808,
|
395 |
+
"learning_rate": 0.00015984723141740576,
|
396 |
+
"loss": 0.2011,
|
397 |
+
"step": 52
|
398 |
+
},
|
399 |
+
{
|
400 |
+
"epoch": 0.69,
|
401 |
+
"grad_norm": 0.16393092274665833,
|
402 |
+
"learning_rate": 0.0001580602887970721,
|
403 |
+
"loss": 0.2131,
|
404 |
+
"step": 53
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.71,
|
408 |
+
"grad_norm": 0.16602680087089539,
|
409 |
+
"learning_rate": 0.0001562449287640781,
|
410 |
+
"loss": 0.2719,
|
411 |
+
"step": 54
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.72,
|
415 |
+
"grad_norm": 0.14725206792354584,
|
416 |
+
"learning_rate": 0.00015440203984027324,
|
417 |
+
"loss": 0.1635,
|
418 |
+
"step": 55
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"epoch": 0.73,
|
422 |
+
"grad_norm": 0.16429893672466278,
|
423 |
+
"learning_rate": 0.00015253252402142988,
|
424 |
+
"loss": 0.2428,
|
425 |
+
"step": 56
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 0.75,
|
429 |
+
"grad_norm": 0.1661713421344757,
|
430 |
+
"learning_rate": 0.0001506372963357644,
|
431 |
+
"loss": 0.1932,
|
432 |
+
"step": 57
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 0.75,
|
436 |
+
"eval_loss": 0.20187948644161224,
|
437 |
+
"eval_runtime": 229.6445,
|
438 |
+
"eval_samples_per_second": 0.98,
|
439 |
+
"eval_steps_per_second": 0.248,
|
440 |
+
"step": 57
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 0.76,
|
444 |
+
"grad_norm": 0.15299098193645477,
|
445 |
+
"learning_rate": 0.00014871728439607966,
|
446 |
+
"loss": 0.2265,
|
447 |
+
"step": 58
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.77,
|
451 |
+
"grad_norm": 0.18591280281543732,
|
452 |
+
"learning_rate": 0.00014677342794574817,
|
453 |
+
"loss": 0.1976,
|
454 |
+
"step": 59
|
455 |
+
},
|
456 |
+
{
|
457 |
+
"epoch": 0.78,
|
458 |
+
"grad_norm": 0.16052399575710297,
|
459 |
+
"learning_rate": 0.00014480667839875786,
|
460 |
+
"loss": 0.1962,
|
461 |
+
"step": 60
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 0.8,
|
465 |
+
"grad_norm": 0.14768967032432556,
|
466 |
+
"learning_rate": 0.00014281799837404552,
|
467 |
+
"loss": 0.2543,
|
468 |
+
"step": 61
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 0.81,
|
472 |
+
"grad_norm": 0.17109468579292297,
|
473 |
+
"learning_rate": 0.0001408083612243465,
|
474 |
+
"loss": 0.1847,
|
475 |
+
"step": 62
|
476 |
+
},
|
477 |
+
{
|
478 |
+
"epoch": 0.82,
|
479 |
+
"grad_norm": 0.14455659687519073,
|
480 |
+
"learning_rate": 0.00013877875055979023,
|
481 |
+
"loss": 0.2847,
|
482 |
+
"step": 63
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 0.84,
|
486 |
+
"grad_norm": 0.15863843262195587,
|
487 |
+
"learning_rate": 0.00013673015976647568,
|
488 |
+
"loss": 0.2151,
|
489 |
+
"step": 64
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.85,
|
493 |
+
"grad_norm": 0.12969669699668884,
|
494 |
+
"learning_rate": 0.00013466359152026195,
|
495 |
+
"loss": 0.1925,
|
496 |
+
"step": 65
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 0.86,
|
500 |
+
"grad_norm": 0.13628815114498138,
|
501 |
+
"learning_rate": 0.00013258005729601177,
|
502 |
+
"loss": 0.255,
|
503 |
+
"step": 66
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 0.88,
|
507 |
+
"grad_norm": 0.12767894566059113,
|
508 |
+
"learning_rate": 0.00013048057687252865,
|
509 |
+
"loss": 0.2161,
|
510 |
+
"step": 67
|
511 |
+
},
|
512 |
+
{
|
513 |
+
"epoch": 0.89,
|
514 |
+
"grad_norm": 0.17236588895320892,
|
515 |
+
"learning_rate": 0.0001283661778334297,
|
516 |
+
"loss": 0.1951,
|
517 |
+
"step": 68
|
518 |
+
},
|
519 |
+
{
|
520 |
+
"epoch": 0.9,
|
521 |
+
"grad_norm": 0.1588594615459442,
|
522 |
+
"learning_rate": 0.0001262378950641979,
|
523 |
+
"loss": 0.2506,
|
524 |
+
"step": 69
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 0.92,
|
528 |
+
"grad_norm": 0.13196192681789398,
|
529 |
+
"learning_rate": 0.00012409677024566144,
|
530 |
+
"loss": 0.1636,
|
531 |
+
"step": 70
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.93,
|
535 |
+
"grad_norm": 0.127383291721344,
|
536 |
+
"learning_rate": 0.00012194385134414608,
|
537 |
+
"loss": 0.2257,
|
538 |
+
"step": 71
|
539 |
+
},
|
540 |
+
{
|
541 |
+
"epoch": 0.94,
|
542 |
+
"grad_norm": 0.1441836953163147,
|
543 |
+
"learning_rate": 0.00011978019209855174,
|
544 |
+
"loss": 0.2278,
|
545 |
+
"step": 72
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 0.95,
|
549 |
+
"grad_norm": 0.15123869478702545,
|
550 |
+
"learning_rate": 0.00011760685150460362,
|
551 |
+
"loss": 0.2141,
|
552 |
+
"step": 73
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"epoch": 0.97,
|
556 |
+
"grad_norm": 0.1521189659833908,
|
557 |
+
"learning_rate": 0.00011542489329653024,
|
558 |
+
"loss": 0.1782,
|
559 |
+
"step": 74
|
560 |
+
},
|
561 |
+
{
|
562 |
+
"epoch": 0.98,
|
563 |
+
"grad_norm": 0.20674781501293182,
|
564 |
+
"learning_rate": 0.00011323538542642227,
|
565 |
+
"loss": 0.1973,
|
566 |
+
"step": 75
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.99,
|
570 |
+
"grad_norm": 0.1552877575159073,
|
571 |
+
"learning_rate": 0.000111039399541527,
|
572 |
+
"loss": 0.2315,
|
573 |
+
"step": 76
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.99,
|
577 |
+
"eval_loss": 0.19675016403198242,
|
578 |
+
"eval_runtime": 229.2135,
|
579 |
+
"eval_samples_per_second": 0.982,
|
580 |
+
"eval_steps_per_second": 0.249,
|
581 |
+
"step": 76
|
582 |
+
}
|
583 |
+
],
|
584 |
+
"logging_steps": 1,
|
585 |
+
"max_steps": 152,
|
586 |
+
"num_input_tokens_seen": 0,
|
587 |
+
"num_train_epochs": 2,
|
588 |
+
"save_steps": 76,
|
589 |
+
"total_flos": 1.0754940954948403e+17,
|
590 |
+
"train_batch_size": 2,
|
591 |
+
"trial_name": null,
|
592 |
+
"trial_params": null
|
593 |
+
}
|
checkpoint-76/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1b2dcab169e2e00ba6ec3514abd0d723f2af79cba950a2f09041beca2670615
|
3 |
+
size 5816
|
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mistralai/Mistral-7B-v0.3",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"quantization_config": {
|
19 |
+
"_load_in_4bit": false,
|
20 |
+
"_load_in_8bit": true,
|
21 |
+
"bnb_4bit_compute_dtype": "float32",
|
22 |
+
"bnb_4bit_quant_storage": "uint8",
|
23 |
+
"bnb_4bit_quant_type": "fp4",
|
24 |
+
"bnb_4bit_use_double_quant": false,
|
25 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
26 |
+
"llm_int8_has_fp16_weight": false,
|
27 |
+
"llm_int8_skip_modules": null,
|
28 |
+
"llm_int8_threshold": 6.0,
|
29 |
+
"load_in_4bit": false,
|
30 |
+
"load_in_8bit": true,
|
31 |
+
"quant_method": "bitsandbytes"
|
32 |
+
},
|
33 |
+
"rms_norm_eps": 1e-05,
|
34 |
+
"rope_theta": 1000000.0,
|
35 |
+
"sliding_window": null,
|
36 |
+
"tie_word_embeddings": false,
|
37 |
+
"torch_dtype": "bfloat16",
|
38 |
+
"transformers_version": "4.40.0.dev0",
|
39 |
+
"use_cache": false,
|
40 |
+
"vocab_size": 32768
|
41 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
|
3 |
+
size 587404
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|