Upload folder using huggingface_hub
Browse files- checkpoint-107/README.md +202 -0
- checkpoint-107/adapter_config.json +34 -0
- checkpoint-107/adapter_model.safetensors +3 -0
- checkpoint-107/added_tokens.json +6 -0
- checkpoint-107/optimizer.pt +3 -0
- checkpoint-107/rng_state.pth +3 -0
- checkpoint-107/scheduler.pt +3 -0
- checkpoint-107/special_tokens_map.json +35 -0
- checkpoint-107/tokenizer.json +0 -0
- checkpoint-107/tokenizer.model +3 -0
- checkpoint-107/tokenizer_config.json +81 -0
- checkpoint-107/trainer_state.json +770 -0
- checkpoint-107/training_args.bin +3 -0
- checkpoint-159/README.md +202 -0
- checkpoint-159/adapter_config.json +34 -0
- checkpoint-159/adapter_model.safetensors +3 -0
- checkpoint-159/added_tokens.json +6 -0
- checkpoint-159/optimizer.pt +3 -0
- checkpoint-159/rng_state.pth +3 -0
- checkpoint-159/scheduler.pt +3 -0
- checkpoint-159/special_tokens_map.json +35 -0
- checkpoint-159/tokenizer.json +0 -0
- checkpoint-159/tokenizer.model +3 -0
- checkpoint-159/tokenizer_config.json +81 -0
- checkpoint-159/trainer_state.json +1134 -0
- checkpoint-159/training_args.bin +3 -0
- checkpoint-53/README.md +202 -0
- checkpoint-53/adapter_config.json +34 -0
- checkpoint-53/adapter_model.safetensors +3 -0
- checkpoint-53/added_tokens.json +6 -0
- checkpoint-53/optimizer.pt +3 -0
- checkpoint-53/rng_state.pth +3 -0
- checkpoint-53/scheduler.pt +3 -0
- checkpoint-53/special_tokens_map.json +35 -0
- checkpoint-53/tokenizer.json +0 -0
- checkpoint-53/tokenizer.model +3 -0
- checkpoint-53/tokenizer_config.json +81 -0
- checkpoint-53/trainer_state.json +392 -0
- checkpoint-53/training_args.bin +3 -0
- runs/Apr05_12-01-19_83bf7c2258aa/events.out.tfevents.1712318488.83bf7c2258aa.34.0 +2 -2
checkpoint-107/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: Viet-Mistral/Vistral-7B-Chat
|
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-107/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Viet-Mistral/Vistral-7B-Chat",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 128,
|
14 |
+
"lora_dropout": 0,
|
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": "unsloth",
|
22 |
+
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"gate_proj",
|
25 |
+
"down_proj",
|
26 |
+
"o_proj",
|
27 |
+
"k_proj",
|
28 |
+
"q_proj",
|
29 |
+
"up_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-107/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3ed8c76fa6a8a73ec2291f08967181279eba329106ffae6ec2c1c1aa4aad32d
|
3 |
+
size 671149168
|
checkpoint-107/added_tokens.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<</SYS>>": 38366,
|
3 |
+
"<<SYS>>": 38365,
|
4 |
+
"[/INST]": 38368,
|
5 |
+
"[INST]": 38367
|
6 |
+
}
|
checkpoint-107/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74b32112f09d664d30fc491f2e07bbc5e07e14208d2885998305dbc0182e47b0
|
3 |
+
size 1342555602
|
checkpoint-107/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:567dd2aae9090c19b7559c7a01e5bcefd79cbdaf1923994bfb5bbd24f21f482e
|
3 |
+
size 14244
|
checkpoint-107/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5d765f2f4b14809c563b2740dd2156b381ea075ebfeb154359462d08210d479
|
3 |
+
size 1064
|
checkpoint-107/special_tokens_map.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"eos_token": {
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"pad_token": {
|
22 |
+
"content": "<unk>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"unk_token": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
checkpoint-107/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-107/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e792a804bbfc19a96b61b87109b8f2b0b7c92830025f285b402ba27c0c309c6f
|
3 |
+
size 596883
|
checkpoint-107/tokenizer_config.json
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"38365": {
|
30 |
+
"content": "<<SYS>>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": false
|
36 |
+
},
|
37 |
+
"38366": {
|
38 |
+
"content": "<</SYS>>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": false
|
44 |
+
},
|
45 |
+
"38367": {
|
46 |
+
"content": "[INST]",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": false
|
52 |
+
},
|
53 |
+
"38368": {
|
54 |
+
"content": "[/INST]",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": false
|
60 |
+
}
|
61 |
+
},
|
62 |
+
"additional_special_tokens": [
|
63 |
+
"<unk>",
|
64 |
+
"<s>",
|
65 |
+
"</s>"
|
66 |
+
],
|
67 |
+
"bos_token": "<s>",
|
68 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
69 |
+
"clean_up_tokenization_spaces": false,
|
70 |
+
"eos_token": "</s>",
|
71 |
+
"legacy": true,
|
72 |
+
"model_max_length": 32768,
|
73 |
+
"pad_token": "<unk>",
|
74 |
+
"padding_side": "right",
|
75 |
+
"sp_model_kwargs": {},
|
76 |
+
"spaces_between_special_tokens": false,
|
77 |
+
"tokenizer_class": "LlamaTokenizer",
|
78 |
+
"unk_token": "<unk>",
|
79 |
+
"use_default_system_prompt": false,
|
80 |
+
"use_fast": true
|
81 |
+
}
|
checkpoint-107/trainer_state.json
ADDED
@@ -0,0 +1,770 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.986078886310905,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 107,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02,
|
13 |
+
"grad_norm": 28.83467674255371,
|
14 |
+
"learning_rate": 2e-05,
|
15 |
+
"loss": 2.7878,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.04,
|
20 |
+
"grad_norm": 28.955718994140625,
|
21 |
+
"learning_rate": 4e-05,
|
22 |
+
"loss": 2.7826,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.06,
|
27 |
+
"grad_norm": 17.856950759887695,
|
28 |
+
"learning_rate": 6e-05,
|
29 |
+
"loss": 2.2388,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.07,
|
34 |
+
"grad_norm": 16.615158081054688,
|
35 |
+
"learning_rate": 8e-05,
|
36 |
+
"loss": 1.7809,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.09,
|
41 |
+
"grad_norm": 34.79571533203125,
|
42 |
+
"learning_rate": 0.0001,
|
43 |
+
"loss": 1.9714,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.11,
|
48 |
+
"grad_norm": 6.3113694190979,
|
49 |
+
"learning_rate": 9.935064935064936e-05,
|
50 |
+
"loss": 1.4032,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.13,
|
55 |
+
"grad_norm": 8.230330467224121,
|
56 |
+
"learning_rate": 9.870129870129871e-05,
|
57 |
+
"loss": 1.241,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.15,
|
62 |
+
"grad_norm": 17.19231605529785,
|
63 |
+
"learning_rate": 9.805194805194806e-05,
|
64 |
+
"loss": 1.2388,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.17,
|
69 |
+
"grad_norm": 6.900284767150879,
|
70 |
+
"learning_rate": 9.74025974025974e-05,
|
71 |
+
"loss": 1.0881,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.19,
|
76 |
+
"grad_norm": 2.7498185634613037,
|
77 |
+
"learning_rate": 9.675324675324677e-05,
|
78 |
+
"loss": 1.0071,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.2,
|
83 |
+
"grad_norm": 4.016067028045654,
|
84 |
+
"learning_rate": 9.610389610389611e-05,
|
85 |
+
"loss": 0.9962,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.22,
|
90 |
+
"grad_norm": 2.365187883377075,
|
91 |
+
"learning_rate": 9.545454545454546e-05,
|
92 |
+
"loss": 0.9928,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.24,
|
97 |
+
"grad_norm": 1.4348371028900146,
|
98 |
+
"learning_rate": 9.480519480519481e-05,
|
99 |
+
"loss": 0.9107,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.26,
|
104 |
+
"grad_norm": 1.8148932456970215,
|
105 |
+
"learning_rate": 9.415584415584417e-05,
|
106 |
+
"loss": 0.853,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.28,
|
111 |
+
"grad_norm": 1.9855575561523438,
|
112 |
+
"learning_rate": 9.35064935064935e-05,
|
113 |
+
"loss": 0.8598,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.3,
|
118 |
+
"grad_norm": 1.9960970878601074,
|
119 |
+
"learning_rate": 9.285714285714286e-05,
|
120 |
+
"loss": 0.8384,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.32,
|
125 |
+
"grad_norm": 1.4565762281417847,
|
126 |
+
"learning_rate": 9.220779220779221e-05,
|
127 |
+
"loss": 0.7895,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.33,
|
132 |
+
"grad_norm": 1.419858694076538,
|
133 |
+
"learning_rate": 9.155844155844156e-05,
|
134 |
+
"loss": 0.8162,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.35,
|
139 |
+
"grad_norm": 1.3651608228683472,
|
140 |
+
"learning_rate": 9.090909090909092e-05,
|
141 |
+
"loss": 0.7924,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.37,
|
146 |
+
"grad_norm": 1.1524626016616821,
|
147 |
+
"learning_rate": 9.025974025974027e-05,
|
148 |
+
"loss": 0.7484,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.39,
|
153 |
+
"grad_norm": 0.9174069166183472,
|
154 |
+
"learning_rate": 8.961038961038961e-05,
|
155 |
+
"loss": 0.7276,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.41,
|
160 |
+
"grad_norm": 1.1832919120788574,
|
161 |
+
"learning_rate": 8.896103896103896e-05,
|
162 |
+
"loss": 0.6658,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.43,
|
167 |
+
"grad_norm": 1.3024309873580933,
|
168 |
+
"learning_rate": 8.831168831168831e-05,
|
169 |
+
"loss": 0.7379,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.45,
|
174 |
+
"grad_norm": 1.1416062116622925,
|
175 |
+
"learning_rate": 8.766233766233767e-05,
|
176 |
+
"loss": 0.7202,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.46,
|
181 |
+
"grad_norm": 1.2058277130126953,
|
182 |
+
"learning_rate": 8.701298701298701e-05,
|
183 |
+
"loss": 0.6777,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.48,
|
188 |
+
"grad_norm": 1.0915583372116089,
|
189 |
+
"learning_rate": 8.636363636363637e-05,
|
190 |
+
"loss": 0.7063,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.5,
|
195 |
+
"grad_norm": 1.0384303331375122,
|
196 |
+
"learning_rate": 8.571428571428571e-05,
|
197 |
+
"loss": 0.6447,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.52,
|
202 |
+
"grad_norm": 1.131259560585022,
|
203 |
+
"learning_rate": 8.506493506493507e-05,
|
204 |
+
"loss": 0.6911,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.54,
|
209 |
+
"grad_norm": 1.1505099534988403,
|
210 |
+
"learning_rate": 8.441558441558442e-05,
|
211 |
+
"loss": 0.6142,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.56,
|
216 |
+
"grad_norm": 2.6675026416778564,
|
217 |
+
"learning_rate": 8.376623376623377e-05,
|
218 |
+
"loss": 0.6181,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.58,
|
223 |
+
"grad_norm": 1.2021816968917847,
|
224 |
+
"learning_rate": 8.311688311688312e-05,
|
225 |
+
"loss": 0.6542,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.59,
|
230 |
+
"grad_norm": 3.363269090652466,
|
231 |
+
"learning_rate": 8.246753246753248e-05,
|
232 |
+
"loss": 0.5968,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.61,
|
237 |
+
"grad_norm": 3.8007972240448,
|
238 |
+
"learning_rate": 8.181818181818183e-05,
|
239 |
+
"loss": 0.5983,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.63,
|
244 |
+
"grad_norm": 3.570556163787842,
|
245 |
+
"learning_rate": 8.116883116883117e-05,
|
246 |
+
"loss": 0.6375,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.65,
|
251 |
+
"grad_norm": 4.428549766540527,
|
252 |
+
"learning_rate": 8.051948051948052e-05,
|
253 |
+
"loss": 0.6519,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.67,
|
258 |
+
"grad_norm": 3.7240254878997803,
|
259 |
+
"learning_rate": 7.987012987012987e-05,
|
260 |
+
"loss": 0.5935,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.69,
|
265 |
+
"grad_norm": 2.453350782394409,
|
266 |
+
"learning_rate": 7.922077922077923e-05,
|
267 |
+
"loss": 0.604,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.71,
|
272 |
+
"grad_norm": 3.341071844100952,
|
273 |
+
"learning_rate": 7.857142857142858e-05,
|
274 |
+
"loss": 0.5994,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.72,
|
279 |
+
"grad_norm": 3.4222161769866943,
|
280 |
+
"learning_rate": 7.792207792207793e-05,
|
281 |
+
"loss": 0.5731,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.74,
|
286 |
+
"grad_norm": 2.9063804149627686,
|
287 |
+
"learning_rate": 7.727272727272727e-05,
|
288 |
+
"loss": 0.5566,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.76,
|
293 |
+
"grad_norm": 3.170330762863159,
|
294 |
+
"learning_rate": 7.662337662337662e-05,
|
295 |
+
"loss": 0.5684,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.78,
|
300 |
+
"grad_norm": 2.8363170623779297,
|
301 |
+
"learning_rate": 7.597402597402598e-05,
|
302 |
+
"loss": 0.5936,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.8,
|
307 |
+
"grad_norm": 2.3944592475891113,
|
308 |
+
"learning_rate": 7.532467532467533e-05,
|
309 |
+
"loss": 0.5571,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.82,
|
314 |
+
"grad_norm": 2.816237688064575,
|
315 |
+
"learning_rate": 7.467532467532467e-05,
|
316 |
+
"loss": 0.5598,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.84,
|
321 |
+
"grad_norm": 2.57438325881958,
|
322 |
+
"learning_rate": 7.402597402597404e-05,
|
323 |
+
"loss": 0.5615,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.85,
|
328 |
+
"grad_norm": 2.3164243698120117,
|
329 |
+
"learning_rate": 7.337662337662338e-05,
|
330 |
+
"loss": 0.5381,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.87,
|
335 |
+
"grad_norm": 2.4226622581481934,
|
336 |
+
"learning_rate": 7.272727272727273e-05,
|
337 |
+
"loss": 0.5592,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.89,
|
342 |
+
"grad_norm": 1.5568475723266602,
|
343 |
+
"learning_rate": 7.207792207792208e-05,
|
344 |
+
"loss": 0.5729,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.91,
|
349 |
+
"grad_norm": 1.1320440769195557,
|
350 |
+
"learning_rate": 7.142857142857143e-05,
|
351 |
+
"loss": 0.5546,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.93,
|
356 |
+
"grad_norm": 2.220273733139038,
|
357 |
+
"learning_rate": 7.077922077922077e-05,
|
358 |
+
"loss": 0.5587,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.95,
|
363 |
+
"grad_norm": 1.8099664449691772,
|
364 |
+
"learning_rate": 7.012987012987014e-05,
|
365 |
+
"loss": 0.5403,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.97,
|
370 |
+
"grad_norm": 1.7992054224014282,
|
371 |
+
"learning_rate": 6.948051948051948e-05,
|
372 |
+
"loss": 0.5374,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.98,
|
377 |
+
"grad_norm": 1.5891600847244263,
|
378 |
+
"learning_rate": 6.883116883116883e-05,
|
379 |
+
"loss": 0.5188,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 1.0,
|
384 |
+
"grad_norm": 1.713174819946289,
|
385 |
+
"learning_rate": 6.818181818181818e-05,
|
386 |
+
"loss": 0.5632,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 1.02,
|
391 |
+
"grad_norm": 1.529587984085083,
|
392 |
+
"learning_rate": 6.753246753246754e-05,
|
393 |
+
"loss": 0.4607,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 1.04,
|
398 |
+
"grad_norm": 1.243905782699585,
|
399 |
+
"learning_rate": 6.688311688311688e-05,
|
400 |
+
"loss": 0.4807,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 1.06,
|
405 |
+
"grad_norm": 0.92779141664505,
|
406 |
+
"learning_rate": 6.623376623376624e-05,
|
407 |
+
"loss": 0.4515,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 1.08,
|
412 |
+
"grad_norm": 1.8945612907409668,
|
413 |
+
"learning_rate": 6.55844155844156e-05,
|
414 |
+
"loss": 0.4788,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 1.1,
|
419 |
+
"grad_norm": 1.6997075080871582,
|
420 |
+
"learning_rate": 6.493506493506494e-05,
|
421 |
+
"loss": 0.4411,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 1.11,
|
426 |
+
"grad_norm": 1.4320181608200073,
|
427 |
+
"learning_rate": 6.428571428571429e-05,
|
428 |
+
"loss": 0.4474,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 1.13,
|
433 |
+
"grad_norm": 1.5225821733474731,
|
434 |
+
"learning_rate": 6.363636363636364e-05,
|
435 |
+
"loss": 0.4578,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 1.15,
|
440 |
+
"grad_norm": 1.4867883920669556,
|
441 |
+
"learning_rate": 6.2987012987013e-05,
|
442 |
+
"loss": 0.4838,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 1.17,
|
447 |
+
"grad_norm": 1.3935158252716064,
|
448 |
+
"learning_rate": 6.233766233766233e-05,
|
449 |
+
"loss": 0.4383,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 1.19,
|
454 |
+
"grad_norm": 1.3193836212158203,
|
455 |
+
"learning_rate": 6.16883116883117e-05,
|
456 |
+
"loss": 0.4369,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 1.21,
|
461 |
+
"grad_norm": 1.0565460920333862,
|
462 |
+
"learning_rate": 6.103896103896104e-05,
|
463 |
+
"loss": 0.4618,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 1.23,
|
468 |
+
"grad_norm": 1.9069595336914062,
|
469 |
+
"learning_rate": 6.03896103896104e-05,
|
470 |
+
"loss": 0.4636,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 1.24,
|
475 |
+
"grad_norm": 1.592588186264038,
|
476 |
+
"learning_rate": 5.9740259740259744e-05,
|
477 |
+
"loss": 0.4363,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 1.26,
|
482 |
+
"grad_norm": 1.392088770866394,
|
483 |
+
"learning_rate": 5.90909090909091e-05,
|
484 |
+
"loss": 0.4573,
|
485 |
+
"step": 68
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 1.28,
|
489 |
+
"grad_norm": 1.4312165975570679,
|
490 |
+
"learning_rate": 5.844155844155844e-05,
|
491 |
+
"loss": 0.4404,
|
492 |
+
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 1.3,
|
496 |
+
"grad_norm": 1.4288945198059082,
|
497 |
+
"learning_rate": 5.7792207792207796e-05,
|
498 |
+
"loss": 0.4517,
|
499 |
+
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 1.32,
|
503 |
+
"grad_norm": 1.247237205505371,
|
504 |
+
"learning_rate": 5.714285714285714e-05,
|
505 |
+
"loss": 0.4731,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 1.34,
|
510 |
+
"grad_norm": 1.4292420148849487,
|
511 |
+
"learning_rate": 5.64935064935065e-05,
|
512 |
+
"loss": 0.4561,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 1.35,
|
517 |
+
"grad_norm": 1.1647123098373413,
|
518 |
+
"learning_rate": 5.584415584415584e-05,
|
519 |
+
"loss": 0.4702,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 1.37,
|
524 |
+
"grad_norm": 1.6123448610305786,
|
525 |
+
"learning_rate": 5.51948051948052e-05,
|
526 |
+
"loss": 0.4681,
|
527 |
+
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 1.39,
|
531 |
+
"grad_norm": 1.3807860612869263,
|
532 |
+
"learning_rate": 5.4545454545454546e-05,
|
533 |
+
"loss": 0.4217,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 1.41,
|
538 |
+
"grad_norm": 1.4928926229476929,
|
539 |
+
"learning_rate": 5.38961038961039e-05,
|
540 |
+
"loss": 0.4344,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 1.43,
|
545 |
+
"grad_norm": 1.3118643760681152,
|
546 |
+
"learning_rate": 5.3246753246753245e-05,
|
547 |
+
"loss": 0.4509,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 1.45,
|
552 |
+
"grad_norm": 1.1260207891464233,
|
553 |
+
"learning_rate": 5.25974025974026e-05,
|
554 |
+
"loss": 0.4423,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 1.47,
|
559 |
+
"grad_norm": 1.1223907470703125,
|
560 |
+
"learning_rate": 5.1948051948051944e-05,
|
561 |
+
"loss": 0.4238,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 1.48,
|
566 |
+
"grad_norm": 1.123289704322815,
|
567 |
+
"learning_rate": 5.1298701298701304e-05,
|
568 |
+
"loss": 0.4415,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 1.5,
|
573 |
+
"grad_norm": 0.8493527770042419,
|
574 |
+
"learning_rate": 5.064935064935065e-05,
|
575 |
+
"loss": 0.4278,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 1.52,
|
580 |
+
"grad_norm": 1.3558621406555176,
|
581 |
+
"learning_rate": 5e-05,
|
582 |
+
"loss": 0.4326,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 1.54,
|
587 |
+
"grad_norm": 1.198364496231079,
|
588 |
+
"learning_rate": 4.9350649350649355e-05,
|
589 |
+
"loss": 0.4504,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 1.56,
|
594 |
+
"grad_norm": 1.318117380142212,
|
595 |
+
"learning_rate": 4.87012987012987e-05,
|
596 |
+
"loss": 0.4389,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 1.58,
|
601 |
+
"grad_norm": 1.323292851448059,
|
602 |
+
"learning_rate": 4.8051948051948054e-05,
|
603 |
+
"loss": 0.4559,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 1.6,
|
608 |
+
"grad_norm": 1.0558339357376099,
|
609 |
+
"learning_rate": 4.740259740259741e-05,
|
610 |
+
"loss": 0.4613,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 1.61,
|
615 |
+
"grad_norm": 1.0301963090896606,
|
616 |
+
"learning_rate": 4.675324675324675e-05,
|
617 |
+
"loss": 0.4194,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 1.63,
|
622 |
+
"grad_norm": 0.9772946834564209,
|
623 |
+
"learning_rate": 4.6103896103896106e-05,
|
624 |
+
"loss": 0.4278,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 1.65,
|
629 |
+
"grad_norm": 0.93486487865448,
|
630 |
+
"learning_rate": 4.545454545454546e-05,
|
631 |
+
"loss": 0.454,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 1.67,
|
636 |
+
"grad_norm": 1.1458832025527954,
|
637 |
+
"learning_rate": 4.4805194805194805e-05,
|
638 |
+
"loss": 0.4363,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 1.69,
|
643 |
+
"grad_norm": 0.9339586496353149,
|
644 |
+
"learning_rate": 4.415584415584416e-05,
|
645 |
+
"loss": 0.434,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 1.71,
|
650 |
+
"grad_norm": 1.3206239938735962,
|
651 |
+
"learning_rate": 4.3506493506493503e-05,
|
652 |
+
"loss": 0.4431,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 1.73,
|
657 |
+
"grad_norm": 1.1199604272842407,
|
658 |
+
"learning_rate": 4.2857142857142856e-05,
|
659 |
+
"loss": 0.4472,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 1.74,
|
664 |
+
"grad_norm": 1.0672180652618408,
|
665 |
+
"learning_rate": 4.220779220779221e-05,
|
666 |
+
"loss": 0.4091,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 1.76,
|
671 |
+
"grad_norm": 1.0920594930648804,
|
672 |
+
"learning_rate": 4.155844155844156e-05,
|
673 |
+
"loss": 0.417,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 1.78,
|
678 |
+
"grad_norm": 0.9002637267112732,
|
679 |
+
"learning_rate": 4.0909090909090915e-05,
|
680 |
+
"loss": 0.4103,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 1.8,
|
685 |
+
"grad_norm": 0.8468071222305298,
|
686 |
+
"learning_rate": 4.025974025974026e-05,
|
687 |
+
"loss": 0.4167,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 1.82,
|
692 |
+
"grad_norm": 0.9398940205574036,
|
693 |
+
"learning_rate": 3.9610389610389614e-05,
|
694 |
+
"loss": 0.4201,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 1.84,
|
699 |
+
"grad_norm": 0.7842636108398438,
|
700 |
+
"learning_rate": 3.8961038961038966e-05,
|
701 |
+
"loss": 0.4064,
|
702 |
+
"step": 99
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 1.86,
|
706 |
+
"grad_norm": 1.0805550813674927,
|
707 |
+
"learning_rate": 3.831168831168831e-05,
|
708 |
+
"loss": 0.4271,
|
709 |
+
"step": 100
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 1.87,
|
713 |
+
"grad_norm": 0.8424351215362549,
|
714 |
+
"learning_rate": 3.7662337662337665e-05,
|
715 |
+
"loss": 0.4087,
|
716 |
+
"step": 101
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 1.89,
|
720 |
+
"grad_norm": 1.0850481986999512,
|
721 |
+
"learning_rate": 3.701298701298702e-05,
|
722 |
+
"loss": 0.409,
|
723 |
+
"step": 102
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 1.91,
|
727 |
+
"grad_norm": 0.9894604086875916,
|
728 |
+
"learning_rate": 3.6363636363636364e-05,
|
729 |
+
"loss": 0.4139,
|
730 |
+
"step": 103
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 1.93,
|
734 |
+
"grad_norm": 0.97883540391922,
|
735 |
+
"learning_rate": 3.571428571428572e-05,
|
736 |
+
"loss": 0.4281,
|
737 |
+
"step": 104
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 1.95,
|
741 |
+
"grad_norm": 0.9291779398918152,
|
742 |
+
"learning_rate": 3.506493506493507e-05,
|
743 |
+
"loss": 0.4376,
|
744 |
+
"step": 105
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 1.97,
|
748 |
+
"grad_norm": 0.8272209167480469,
|
749 |
+
"learning_rate": 3.4415584415584416e-05,
|
750 |
+
"loss": 0.42,
|
751 |
+
"step": 106
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 1.99,
|
755 |
+
"grad_norm": 0.8428053855895996,
|
756 |
+
"learning_rate": 3.376623376623377e-05,
|
757 |
+
"loss": 0.4131,
|
758 |
+
"step": 107
|
759 |
+
}
|
760 |
+
],
|
761 |
+
"logging_steps": 1,
|
762 |
+
"max_steps": 159,
|
763 |
+
"num_input_tokens_seen": 0,
|
764 |
+
"num_train_epochs": 3,
|
765 |
+
"save_steps": 5,
|
766 |
+
"total_flos": 1.6171847189151744e+17,
|
767 |
+
"train_batch_size": 16,
|
768 |
+
"trial_name": null,
|
769 |
+
"trial_params": null
|
770 |
+
}
|
checkpoint-107/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:565d81edba8fc76a54ee2e5498f231de6e2c153d87eaba407ea8f5ba343a36f6
|
3 |
+
size 5048
|
checkpoint-159/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: Viet-Mistral/Vistral-7B-Chat
|
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-159/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Viet-Mistral/Vistral-7B-Chat",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 128,
|
14 |
+
"lora_dropout": 0,
|
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": "unsloth",
|
22 |
+
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"gate_proj",
|
25 |
+
"down_proj",
|
26 |
+
"o_proj",
|
27 |
+
"k_proj",
|
28 |
+
"q_proj",
|
29 |
+
"up_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-159/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8fc3c322d26d415576e723584120ce6f1718748e983eb7e12d9e92446d1d8df
|
3 |
+
size 671149168
|
checkpoint-159/added_tokens.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<</SYS>>": 38366,
|
3 |
+
"<<SYS>>": 38365,
|
4 |
+
"[/INST]": 38368,
|
5 |
+
"[INST]": 38367
|
6 |
+
}
|
checkpoint-159/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d5cf7dee76a09f1660545a0ee7fe191d92b67f90bc30b484cefadb1413286a7
|
3 |
+
size 1342555602
|
checkpoint-159/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcb6992d1198d99091f3027f81c1fc9d7036f4c471bb4563d4d3cef2bee37b1a
|
3 |
+
size 14244
|
checkpoint-159/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d74c8b4fd9531453c178cc6e5864e88045081d9006c22d8b0fb2f2f98de3dab
|
3 |
+
size 1064
|
checkpoint-159/special_tokens_map.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"eos_token": {
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"pad_token": {
|
22 |
+
"content": "<unk>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"unk_token": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
checkpoint-159/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-159/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e792a804bbfc19a96b61b87109b8f2b0b7c92830025f285b402ba27c0c309c6f
|
3 |
+
size 596883
|
checkpoint-159/tokenizer_config.json
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"38365": {
|
30 |
+
"content": "<<SYS>>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": false
|
36 |
+
},
|
37 |
+
"38366": {
|
38 |
+
"content": "<</SYS>>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": false
|
44 |
+
},
|
45 |
+
"38367": {
|
46 |
+
"content": "[INST]",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": false
|
52 |
+
},
|
53 |
+
"38368": {
|
54 |
+
"content": "[/INST]",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": false
|
60 |
+
}
|
61 |
+
},
|
62 |
+
"additional_special_tokens": [
|
63 |
+
"<unk>",
|
64 |
+
"<s>",
|
65 |
+
"</s>"
|
66 |
+
],
|
67 |
+
"bos_token": "<s>",
|
68 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
69 |
+
"clean_up_tokenization_spaces": false,
|
70 |
+
"eos_token": "</s>",
|
71 |
+
"legacy": true,
|
72 |
+
"model_max_length": 32768,
|
73 |
+
"pad_token": "<unk>",
|
74 |
+
"padding_side": "right",
|
75 |
+
"sp_model_kwargs": {},
|
76 |
+
"spaces_between_special_tokens": false,
|
77 |
+
"tokenizer_class": "LlamaTokenizer",
|
78 |
+
"unk_token": "<unk>",
|
79 |
+
"use_default_system_prompt": false,
|
80 |
+
"use_fast": true
|
81 |
+
}
|
checkpoint-159/trainer_state.json
ADDED
@@ -0,0 +1,1134 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.9512761020881673,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 159,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02,
|
13 |
+
"grad_norm": 28.83467674255371,
|
14 |
+
"learning_rate": 2e-05,
|
15 |
+
"loss": 2.7878,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.04,
|
20 |
+
"grad_norm": 28.955718994140625,
|
21 |
+
"learning_rate": 4e-05,
|
22 |
+
"loss": 2.7826,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.06,
|
27 |
+
"grad_norm": 17.856950759887695,
|
28 |
+
"learning_rate": 6e-05,
|
29 |
+
"loss": 2.2388,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.07,
|
34 |
+
"grad_norm": 16.615158081054688,
|
35 |
+
"learning_rate": 8e-05,
|
36 |
+
"loss": 1.7809,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.09,
|
41 |
+
"grad_norm": 34.79571533203125,
|
42 |
+
"learning_rate": 0.0001,
|
43 |
+
"loss": 1.9714,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.11,
|
48 |
+
"grad_norm": 6.3113694190979,
|
49 |
+
"learning_rate": 9.935064935064936e-05,
|
50 |
+
"loss": 1.4032,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.13,
|
55 |
+
"grad_norm": 8.230330467224121,
|
56 |
+
"learning_rate": 9.870129870129871e-05,
|
57 |
+
"loss": 1.241,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.15,
|
62 |
+
"grad_norm": 17.19231605529785,
|
63 |
+
"learning_rate": 9.805194805194806e-05,
|
64 |
+
"loss": 1.2388,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.17,
|
69 |
+
"grad_norm": 6.900284767150879,
|
70 |
+
"learning_rate": 9.74025974025974e-05,
|
71 |
+
"loss": 1.0881,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.19,
|
76 |
+
"grad_norm": 2.7498185634613037,
|
77 |
+
"learning_rate": 9.675324675324677e-05,
|
78 |
+
"loss": 1.0071,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.2,
|
83 |
+
"grad_norm": 4.016067028045654,
|
84 |
+
"learning_rate": 9.610389610389611e-05,
|
85 |
+
"loss": 0.9962,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.22,
|
90 |
+
"grad_norm": 2.365187883377075,
|
91 |
+
"learning_rate": 9.545454545454546e-05,
|
92 |
+
"loss": 0.9928,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.24,
|
97 |
+
"grad_norm": 1.4348371028900146,
|
98 |
+
"learning_rate": 9.480519480519481e-05,
|
99 |
+
"loss": 0.9107,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.26,
|
104 |
+
"grad_norm": 1.8148932456970215,
|
105 |
+
"learning_rate": 9.415584415584417e-05,
|
106 |
+
"loss": 0.853,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.28,
|
111 |
+
"grad_norm": 1.9855575561523438,
|
112 |
+
"learning_rate": 9.35064935064935e-05,
|
113 |
+
"loss": 0.8598,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.3,
|
118 |
+
"grad_norm": 1.9960970878601074,
|
119 |
+
"learning_rate": 9.285714285714286e-05,
|
120 |
+
"loss": 0.8384,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.32,
|
125 |
+
"grad_norm": 1.4565762281417847,
|
126 |
+
"learning_rate": 9.220779220779221e-05,
|
127 |
+
"loss": 0.7895,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.33,
|
132 |
+
"grad_norm": 1.419858694076538,
|
133 |
+
"learning_rate": 9.155844155844156e-05,
|
134 |
+
"loss": 0.8162,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.35,
|
139 |
+
"grad_norm": 1.3651608228683472,
|
140 |
+
"learning_rate": 9.090909090909092e-05,
|
141 |
+
"loss": 0.7924,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.37,
|
146 |
+
"grad_norm": 1.1524626016616821,
|
147 |
+
"learning_rate": 9.025974025974027e-05,
|
148 |
+
"loss": 0.7484,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.39,
|
153 |
+
"grad_norm": 0.9174069166183472,
|
154 |
+
"learning_rate": 8.961038961038961e-05,
|
155 |
+
"loss": 0.7276,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.41,
|
160 |
+
"grad_norm": 1.1832919120788574,
|
161 |
+
"learning_rate": 8.896103896103896e-05,
|
162 |
+
"loss": 0.6658,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.43,
|
167 |
+
"grad_norm": 1.3024309873580933,
|
168 |
+
"learning_rate": 8.831168831168831e-05,
|
169 |
+
"loss": 0.7379,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.45,
|
174 |
+
"grad_norm": 1.1416062116622925,
|
175 |
+
"learning_rate": 8.766233766233767e-05,
|
176 |
+
"loss": 0.7202,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.46,
|
181 |
+
"grad_norm": 1.2058277130126953,
|
182 |
+
"learning_rate": 8.701298701298701e-05,
|
183 |
+
"loss": 0.6777,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.48,
|
188 |
+
"grad_norm": 1.0915583372116089,
|
189 |
+
"learning_rate": 8.636363636363637e-05,
|
190 |
+
"loss": 0.7063,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.5,
|
195 |
+
"grad_norm": 1.0384303331375122,
|
196 |
+
"learning_rate": 8.571428571428571e-05,
|
197 |
+
"loss": 0.6447,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.52,
|
202 |
+
"grad_norm": 1.131259560585022,
|
203 |
+
"learning_rate": 8.506493506493507e-05,
|
204 |
+
"loss": 0.6911,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.54,
|
209 |
+
"grad_norm": 1.1505099534988403,
|
210 |
+
"learning_rate": 8.441558441558442e-05,
|
211 |
+
"loss": 0.6142,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.56,
|
216 |
+
"grad_norm": 2.6675026416778564,
|
217 |
+
"learning_rate": 8.376623376623377e-05,
|
218 |
+
"loss": 0.6181,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.58,
|
223 |
+
"grad_norm": 1.2021816968917847,
|
224 |
+
"learning_rate": 8.311688311688312e-05,
|
225 |
+
"loss": 0.6542,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.59,
|
230 |
+
"grad_norm": 3.363269090652466,
|
231 |
+
"learning_rate": 8.246753246753248e-05,
|
232 |
+
"loss": 0.5968,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.61,
|
237 |
+
"grad_norm": 3.8007972240448,
|
238 |
+
"learning_rate": 8.181818181818183e-05,
|
239 |
+
"loss": 0.5983,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.63,
|
244 |
+
"grad_norm": 3.570556163787842,
|
245 |
+
"learning_rate": 8.116883116883117e-05,
|
246 |
+
"loss": 0.6375,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.65,
|
251 |
+
"grad_norm": 4.428549766540527,
|
252 |
+
"learning_rate": 8.051948051948052e-05,
|
253 |
+
"loss": 0.6519,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.67,
|
258 |
+
"grad_norm": 3.7240254878997803,
|
259 |
+
"learning_rate": 7.987012987012987e-05,
|
260 |
+
"loss": 0.5935,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.69,
|
265 |
+
"grad_norm": 2.453350782394409,
|
266 |
+
"learning_rate": 7.922077922077923e-05,
|
267 |
+
"loss": 0.604,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.71,
|
272 |
+
"grad_norm": 3.341071844100952,
|
273 |
+
"learning_rate": 7.857142857142858e-05,
|
274 |
+
"loss": 0.5994,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.72,
|
279 |
+
"grad_norm": 3.4222161769866943,
|
280 |
+
"learning_rate": 7.792207792207793e-05,
|
281 |
+
"loss": 0.5731,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.74,
|
286 |
+
"grad_norm": 2.9063804149627686,
|
287 |
+
"learning_rate": 7.727272727272727e-05,
|
288 |
+
"loss": 0.5566,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.76,
|
293 |
+
"grad_norm": 3.170330762863159,
|
294 |
+
"learning_rate": 7.662337662337662e-05,
|
295 |
+
"loss": 0.5684,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.78,
|
300 |
+
"grad_norm": 2.8363170623779297,
|
301 |
+
"learning_rate": 7.597402597402598e-05,
|
302 |
+
"loss": 0.5936,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.8,
|
307 |
+
"grad_norm": 2.3944592475891113,
|
308 |
+
"learning_rate": 7.532467532467533e-05,
|
309 |
+
"loss": 0.5571,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.82,
|
314 |
+
"grad_norm": 2.816237688064575,
|
315 |
+
"learning_rate": 7.467532467532467e-05,
|
316 |
+
"loss": 0.5598,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.84,
|
321 |
+
"grad_norm": 2.57438325881958,
|
322 |
+
"learning_rate": 7.402597402597404e-05,
|
323 |
+
"loss": 0.5615,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.85,
|
328 |
+
"grad_norm": 2.3164243698120117,
|
329 |
+
"learning_rate": 7.337662337662338e-05,
|
330 |
+
"loss": 0.5381,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.87,
|
335 |
+
"grad_norm": 2.4226622581481934,
|
336 |
+
"learning_rate": 7.272727272727273e-05,
|
337 |
+
"loss": 0.5592,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.89,
|
342 |
+
"grad_norm": 1.5568475723266602,
|
343 |
+
"learning_rate": 7.207792207792208e-05,
|
344 |
+
"loss": 0.5729,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.91,
|
349 |
+
"grad_norm": 1.1320440769195557,
|
350 |
+
"learning_rate": 7.142857142857143e-05,
|
351 |
+
"loss": 0.5546,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.93,
|
356 |
+
"grad_norm": 2.220273733139038,
|
357 |
+
"learning_rate": 7.077922077922077e-05,
|
358 |
+
"loss": 0.5587,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.95,
|
363 |
+
"grad_norm": 1.8099664449691772,
|
364 |
+
"learning_rate": 7.012987012987014e-05,
|
365 |
+
"loss": 0.5403,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.97,
|
370 |
+
"grad_norm": 1.7992054224014282,
|
371 |
+
"learning_rate": 6.948051948051948e-05,
|
372 |
+
"loss": 0.5374,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.98,
|
377 |
+
"grad_norm": 1.5891600847244263,
|
378 |
+
"learning_rate": 6.883116883116883e-05,
|
379 |
+
"loss": 0.5188,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 1.0,
|
384 |
+
"grad_norm": 1.713174819946289,
|
385 |
+
"learning_rate": 6.818181818181818e-05,
|
386 |
+
"loss": 0.5632,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 1.02,
|
391 |
+
"grad_norm": 1.529587984085083,
|
392 |
+
"learning_rate": 6.753246753246754e-05,
|
393 |
+
"loss": 0.4607,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 1.04,
|
398 |
+
"grad_norm": 1.243905782699585,
|
399 |
+
"learning_rate": 6.688311688311688e-05,
|
400 |
+
"loss": 0.4807,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 1.06,
|
405 |
+
"grad_norm": 0.92779141664505,
|
406 |
+
"learning_rate": 6.623376623376624e-05,
|
407 |
+
"loss": 0.4515,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 1.08,
|
412 |
+
"grad_norm": 1.8945612907409668,
|
413 |
+
"learning_rate": 6.55844155844156e-05,
|
414 |
+
"loss": 0.4788,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 1.1,
|
419 |
+
"grad_norm": 1.6997075080871582,
|
420 |
+
"learning_rate": 6.493506493506494e-05,
|
421 |
+
"loss": 0.4411,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 1.11,
|
426 |
+
"grad_norm": 1.4320181608200073,
|
427 |
+
"learning_rate": 6.428571428571429e-05,
|
428 |
+
"loss": 0.4474,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 1.13,
|
433 |
+
"grad_norm": 1.5225821733474731,
|
434 |
+
"learning_rate": 6.363636363636364e-05,
|
435 |
+
"loss": 0.4578,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 1.15,
|
440 |
+
"grad_norm": 1.4867883920669556,
|
441 |
+
"learning_rate": 6.2987012987013e-05,
|
442 |
+
"loss": 0.4838,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 1.17,
|
447 |
+
"grad_norm": 1.3935158252716064,
|
448 |
+
"learning_rate": 6.233766233766233e-05,
|
449 |
+
"loss": 0.4383,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 1.19,
|
454 |
+
"grad_norm": 1.3193836212158203,
|
455 |
+
"learning_rate": 6.16883116883117e-05,
|
456 |
+
"loss": 0.4369,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 1.21,
|
461 |
+
"grad_norm": 1.0565460920333862,
|
462 |
+
"learning_rate": 6.103896103896104e-05,
|
463 |
+
"loss": 0.4618,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 1.23,
|
468 |
+
"grad_norm": 1.9069595336914062,
|
469 |
+
"learning_rate": 6.03896103896104e-05,
|
470 |
+
"loss": 0.4636,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 1.24,
|
475 |
+
"grad_norm": 1.592588186264038,
|
476 |
+
"learning_rate": 5.9740259740259744e-05,
|
477 |
+
"loss": 0.4363,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 1.26,
|
482 |
+
"grad_norm": 1.392088770866394,
|
483 |
+
"learning_rate": 5.90909090909091e-05,
|
484 |
+
"loss": 0.4573,
|
485 |
+
"step": 68
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 1.28,
|
489 |
+
"grad_norm": 1.4312165975570679,
|
490 |
+
"learning_rate": 5.844155844155844e-05,
|
491 |
+
"loss": 0.4404,
|
492 |
+
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 1.3,
|
496 |
+
"grad_norm": 1.4288945198059082,
|
497 |
+
"learning_rate": 5.7792207792207796e-05,
|
498 |
+
"loss": 0.4517,
|
499 |
+
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 1.32,
|
503 |
+
"grad_norm": 1.247237205505371,
|
504 |
+
"learning_rate": 5.714285714285714e-05,
|
505 |
+
"loss": 0.4731,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 1.34,
|
510 |
+
"grad_norm": 1.4292420148849487,
|
511 |
+
"learning_rate": 5.64935064935065e-05,
|
512 |
+
"loss": 0.4561,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 1.35,
|
517 |
+
"grad_norm": 1.1647123098373413,
|
518 |
+
"learning_rate": 5.584415584415584e-05,
|
519 |
+
"loss": 0.4702,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 1.37,
|
524 |
+
"grad_norm": 1.6123448610305786,
|
525 |
+
"learning_rate": 5.51948051948052e-05,
|
526 |
+
"loss": 0.4681,
|
527 |
+
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 1.39,
|
531 |
+
"grad_norm": 1.3807860612869263,
|
532 |
+
"learning_rate": 5.4545454545454546e-05,
|
533 |
+
"loss": 0.4217,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 1.41,
|
538 |
+
"grad_norm": 1.4928926229476929,
|
539 |
+
"learning_rate": 5.38961038961039e-05,
|
540 |
+
"loss": 0.4344,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 1.43,
|
545 |
+
"grad_norm": 1.3118643760681152,
|
546 |
+
"learning_rate": 5.3246753246753245e-05,
|
547 |
+
"loss": 0.4509,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 1.45,
|
552 |
+
"grad_norm": 1.1260207891464233,
|
553 |
+
"learning_rate": 5.25974025974026e-05,
|
554 |
+
"loss": 0.4423,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 1.47,
|
559 |
+
"grad_norm": 1.1223907470703125,
|
560 |
+
"learning_rate": 5.1948051948051944e-05,
|
561 |
+
"loss": 0.4238,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 1.48,
|
566 |
+
"grad_norm": 1.123289704322815,
|
567 |
+
"learning_rate": 5.1298701298701304e-05,
|
568 |
+
"loss": 0.4415,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 1.5,
|
573 |
+
"grad_norm": 0.8493527770042419,
|
574 |
+
"learning_rate": 5.064935064935065e-05,
|
575 |
+
"loss": 0.4278,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 1.52,
|
580 |
+
"grad_norm": 1.3558621406555176,
|
581 |
+
"learning_rate": 5e-05,
|
582 |
+
"loss": 0.4326,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 1.54,
|
587 |
+
"grad_norm": 1.198364496231079,
|
588 |
+
"learning_rate": 4.9350649350649355e-05,
|
589 |
+
"loss": 0.4504,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 1.56,
|
594 |
+
"grad_norm": 1.318117380142212,
|
595 |
+
"learning_rate": 4.87012987012987e-05,
|
596 |
+
"loss": 0.4389,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 1.58,
|
601 |
+
"grad_norm": 1.323292851448059,
|
602 |
+
"learning_rate": 4.8051948051948054e-05,
|
603 |
+
"loss": 0.4559,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 1.6,
|
608 |
+
"grad_norm": 1.0558339357376099,
|
609 |
+
"learning_rate": 4.740259740259741e-05,
|
610 |
+
"loss": 0.4613,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 1.61,
|
615 |
+
"grad_norm": 1.0301963090896606,
|
616 |
+
"learning_rate": 4.675324675324675e-05,
|
617 |
+
"loss": 0.4194,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 1.63,
|
622 |
+
"grad_norm": 0.9772946834564209,
|
623 |
+
"learning_rate": 4.6103896103896106e-05,
|
624 |
+
"loss": 0.4278,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 1.65,
|
629 |
+
"grad_norm": 0.93486487865448,
|
630 |
+
"learning_rate": 4.545454545454546e-05,
|
631 |
+
"loss": 0.454,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 1.67,
|
636 |
+
"grad_norm": 1.1458832025527954,
|
637 |
+
"learning_rate": 4.4805194805194805e-05,
|
638 |
+
"loss": 0.4363,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 1.69,
|
643 |
+
"grad_norm": 0.9339586496353149,
|
644 |
+
"learning_rate": 4.415584415584416e-05,
|
645 |
+
"loss": 0.434,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 1.71,
|
650 |
+
"grad_norm": 1.3206239938735962,
|
651 |
+
"learning_rate": 4.3506493506493503e-05,
|
652 |
+
"loss": 0.4431,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 1.73,
|
657 |
+
"grad_norm": 1.1199604272842407,
|
658 |
+
"learning_rate": 4.2857142857142856e-05,
|
659 |
+
"loss": 0.4472,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 1.74,
|
664 |
+
"grad_norm": 1.0672180652618408,
|
665 |
+
"learning_rate": 4.220779220779221e-05,
|
666 |
+
"loss": 0.4091,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 1.76,
|
671 |
+
"grad_norm": 1.0920594930648804,
|
672 |
+
"learning_rate": 4.155844155844156e-05,
|
673 |
+
"loss": 0.417,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 1.78,
|
678 |
+
"grad_norm": 0.9002637267112732,
|
679 |
+
"learning_rate": 4.0909090909090915e-05,
|
680 |
+
"loss": 0.4103,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 1.8,
|
685 |
+
"grad_norm": 0.8468071222305298,
|
686 |
+
"learning_rate": 4.025974025974026e-05,
|
687 |
+
"loss": 0.4167,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 1.82,
|
692 |
+
"grad_norm": 0.9398940205574036,
|
693 |
+
"learning_rate": 3.9610389610389614e-05,
|
694 |
+
"loss": 0.4201,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 1.84,
|
699 |
+
"grad_norm": 0.7842636108398438,
|
700 |
+
"learning_rate": 3.8961038961038966e-05,
|
701 |
+
"loss": 0.4064,
|
702 |
+
"step": 99
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 1.86,
|
706 |
+
"grad_norm": 1.0805550813674927,
|
707 |
+
"learning_rate": 3.831168831168831e-05,
|
708 |
+
"loss": 0.4271,
|
709 |
+
"step": 100
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 1.87,
|
713 |
+
"grad_norm": 0.8424351215362549,
|
714 |
+
"learning_rate": 3.7662337662337665e-05,
|
715 |
+
"loss": 0.4087,
|
716 |
+
"step": 101
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 1.89,
|
720 |
+
"grad_norm": 1.0850481986999512,
|
721 |
+
"learning_rate": 3.701298701298702e-05,
|
722 |
+
"loss": 0.409,
|
723 |
+
"step": 102
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 1.91,
|
727 |
+
"grad_norm": 0.9894604086875916,
|
728 |
+
"learning_rate": 3.6363636363636364e-05,
|
729 |
+
"loss": 0.4139,
|
730 |
+
"step": 103
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 1.93,
|
734 |
+
"grad_norm": 0.97883540391922,
|
735 |
+
"learning_rate": 3.571428571428572e-05,
|
736 |
+
"loss": 0.4281,
|
737 |
+
"step": 104
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 1.95,
|
741 |
+
"grad_norm": 0.9291779398918152,
|
742 |
+
"learning_rate": 3.506493506493507e-05,
|
743 |
+
"loss": 0.4376,
|
744 |
+
"step": 105
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 1.97,
|
748 |
+
"grad_norm": 0.8272209167480469,
|
749 |
+
"learning_rate": 3.4415584415584416e-05,
|
750 |
+
"loss": 0.42,
|
751 |
+
"step": 106
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 1.99,
|
755 |
+
"grad_norm": 0.8428053855895996,
|
756 |
+
"learning_rate": 3.376623376623377e-05,
|
757 |
+
"loss": 0.4131,
|
758 |
+
"step": 107
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 2.0,
|
762 |
+
"grad_norm": 1.3260736465454102,
|
763 |
+
"learning_rate": 3.311688311688312e-05,
|
764 |
+
"loss": 0.4329,
|
765 |
+
"step": 108
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 2.02,
|
769 |
+
"grad_norm": 1.0264040231704712,
|
770 |
+
"learning_rate": 3.246753246753247e-05,
|
771 |
+
"loss": 0.3687,
|
772 |
+
"step": 109
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 2.04,
|
776 |
+
"grad_norm": 0.7273842692375183,
|
777 |
+
"learning_rate": 3.181818181818182e-05,
|
778 |
+
"loss": 0.3292,
|
779 |
+
"step": 110
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 2.06,
|
783 |
+
"grad_norm": 0.9493059515953064,
|
784 |
+
"learning_rate": 3.1168831168831166e-05,
|
785 |
+
"loss": 0.3328,
|
786 |
+
"step": 111
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 2.08,
|
790 |
+
"grad_norm": 0.9515748023986816,
|
791 |
+
"learning_rate": 3.051948051948052e-05,
|
792 |
+
"loss": 0.3518,
|
793 |
+
"step": 112
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 2.1,
|
797 |
+
"grad_norm": 1.2278352975845337,
|
798 |
+
"learning_rate": 2.9870129870129872e-05,
|
799 |
+
"loss": 0.3383,
|
800 |
+
"step": 113
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 2.12,
|
804 |
+
"grad_norm": 1.132307767868042,
|
805 |
+
"learning_rate": 2.922077922077922e-05,
|
806 |
+
"loss": 0.3368,
|
807 |
+
"step": 114
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 2.13,
|
811 |
+
"grad_norm": 0.9746480584144592,
|
812 |
+
"learning_rate": 2.857142857142857e-05,
|
813 |
+
"loss": 0.3512,
|
814 |
+
"step": 115
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 2.15,
|
818 |
+
"grad_norm": 0.8400117754936218,
|
819 |
+
"learning_rate": 2.792207792207792e-05,
|
820 |
+
"loss": 0.307,
|
821 |
+
"step": 116
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 2.17,
|
825 |
+
"grad_norm": 0.7681165933609009,
|
826 |
+
"learning_rate": 2.7272727272727273e-05,
|
827 |
+
"loss": 0.3491,
|
828 |
+
"step": 117
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 2.19,
|
832 |
+
"grad_norm": 0.8219690918922424,
|
833 |
+
"learning_rate": 2.6623376623376623e-05,
|
834 |
+
"loss": 0.3324,
|
835 |
+
"step": 118
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 2.21,
|
839 |
+
"grad_norm": 0.7293068766593933,
|
840 |
+
"learning_rate": 2.5974025974025972e-05,
|
841 |
+
"loss": 0.3138,
|
842 |
+
"step": 119
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 2.23,
|
846 |
+
"grad_norm": 0.750535786151886,
|
847 |
+
"learning_rate": 2.5324675324675325e-05,
|
848 |
+
"loss": 0.3147,
|
849 |
+
"step": 120
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 2.25,
|
853 |
+
"grad_norm": 0.7550061345100403,
|
854 |
+
"learning_rate": 2.4675324675324678e-05,
|
855 |
+
"loss": 0.349,
|
856 |
+
"step": 121
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 2.26,
|
860 |
+
"grad_norm": 0.8848446607589722,
|
861 |
+
"learning_rate": 2.4025974025974027e-05,
|
862 |
+
"loss": 0.3118,
|
863 |
+
"step": 122
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 2.28,
|
867 |
+
"grad_norm": 0.8062836527824402,
|
868 |
+
"learning_rate": 2.3376623376623376e-05,
|
869 |
+
"loss": 0.3165,
|
870 |
+
"step": 123
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 2.3,
|
874 |
+
"grad_norm": 0.798675000667572,
|
875 |
+
"learning_rate": 2.272727272727273e-05,
|
876 |
+
"loss": 0.3037,
|
877 |
+
"step": 124
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 2.32,
|
881 |
+
"grad_norm": 0.8062317371368408,
|
882 |
+
"learning_rate": 2.207792207792208e-05,
|
883 |
+
"loss": 0.3247,
|
884 |
+
"step": 125
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 2.34,
|
888 |
+
"grad_norm": 0.8265979886054993,
|
889 |
+
"learning_rate": 2.1428571428571428e-05,
|
890 |
+
"loss": 0.326,
|
891 |
+
"step": 126
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 2.36,
|
895 |
+
"grad_norm": 0.7495214939117432,
|
896 |
+
"learning_rate": 2.077922077922078e-05,
|
897 |
+
"loss": 0.3199,
|
898 |
+
"step": 127
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 2.38,
|
902 |
+
"grad_norm": 0.7563657164573669,
|
903 |
+
"learning_rate": 2.012987012987013e-05,
|
904 |
+
"loss": 0.3343,
|
905 |
+
"step": 128
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 2.39,
|
909 |
+
"grad_norm": 0.7477392554283142,
|
910 |
+
"learning_rate": 1.9480519480519483e-05,
|
911 |
+
"loss": 0.3297,
|
912 |
+
"step": 129
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 2.41,
|
916 |
+
"grad_norm": 0.6956043243408203,
|
917 |
+
"learning_rate": 1.8831168831168833e-05,
|
918 |
+
"loss": 0.3225,
|
919 |
+
"step": 130
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 2.43,
|
923 |
+
"grad_norm": 0.7231197357177734,
|
924 |
+
"learning_rate": 1.8181818181818182e-05,
|
925 |
+
"loss": 0.3007,
|
926 |
+
"step": 131
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 2.45,
|
930 |
+
"grad_norm": 0.6901078224182129,
|
931 |
+
"learning_rate": 1.7532467532467535e-05,
|
932 |
+
"loss": 0.3152,
|
933 |
+
"step": 132
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 2.47,
|
937 |
+
"grad_norm": 0.6982807517051697,
|
938 |
+
"learning_rate": 1.6883116883116884e-05,
|
939 |
+
"loss": 0.3008,
|
940 |
+
"step": 133
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 2.49,
|
944 |
+
"grad_norm": 0.7720515727996826,
|
945 |
+
"learning_rate": 1.6233766233766234e-05,
|
946 |
+
"loss": 0.3385,
|
947 |
+
"step": 134
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 2.51,
|
951 |
+
"grad_norm": 0.7257162928581238,
|
952 |
+
"learning_rate": 1.5584415584415583e-05,
|
953 |
+
"loss": 0.3168,
|
954 |
+
"step": 135
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 2.52,
|
958 |
+
"grad_norm": 0.7416141629219055,
|
959 |
+
"learning_rate": 1.4935064935064936e-05,
|
960 |
+
"loss": 0.3053,
|
961 |
+
"step": 136
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 2.54,
|
965 |
+
"grad_norm": 0.7724016904830933,
|
966 |
+
"learning_rate": 1.4285714285714285e-05,
|
967 |
+
"loss": 0.3196,
|
968 |
+
"step": 137
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 2.56,
|
972 |
+
"grad_norm": 0.8549056649208069,
|
973 |
+
"learning_rate": 1.3636363636363637e-05,
|
974 |
+
"loss": 0.325,
|
975 |
+
"step": 138
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 2.58,
|
979 |
+
"grad_norm": 0.7366517782211304,
|
980 |
+
"learning_rate": 1.2987012987012986e-05,
|
981 |
+
"loss": 0.3129,
|
982 |
+
"step": 139
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 2.6,
|
986 |
+
"grad_norm": 0.7694143056869507,
|
987 |
+
"learning_rate": 1.2337662337662339e-05,
|
988 |
+
"loss": 0.2998,
|
989 |
+
"step": 140
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 2.62,
|
993 |
+
"grad_norm": 0.7590445876121521,
|
994 |
+
"learning_rate": 1.1688311688311688e-05,
|
995 |
+
"loss": 0.3046,
|
996 |
+
"step": 141
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 2.64,
|
1000 |
+
"grad_norm": 0.7564178109169006,
|
1001 |
+
"learning_rate": 1.103896103896104e-05,
|
1002 |
+
"loss": 0.2998,
|
1003 |
+
"step": 142
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 2.65,
|
1007 |
+
"grad_norm": 0.706037700176239,
|
1008 |
+
"learning_rate": 1.038961038961039e-05,
|
1009 |
+
"loss": 0.3016,
|
1010 |
+
"step": 143
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 2.67,
|
1014 |
+
"grad_norm": 0.79365074634552,
|
1015 |
+
"learning_rate": 9.740259740259742e-06,
|
1016 |
+
"loss": 0.3005,
|
1017 |
+
"step": 144
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 2.69,
|
1021 |
+
"grad_norm": 0.7816718816757202,
|
1022 |
+
"learning_rate": 9.090909090909091e-06,
|
1023 |
+
"loss": 0.3188,
|
1024 |
+
"step": 145
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 2.71,
|
1028 |
+
"grad_norm": 0.7753292918205261,
|
1029 |
+
"learning_rate": 8.441558441558442e-06,
|
1030 |
+
"loss": 0.3209,
|
1031 |
+
"step": 146
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 2.73,
|
1035 |
+
"grad_norm": 0.7564988136291504,
|
1036 |
+
"learning_rate": 7.792207792207792e-06,
|
1037 |
+
"loss": 0.3243,
|
1038 |
+
"step": 147
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 2.75,
|
1042 |
+
"grad_norm": 0.7076290249824524,
|
1043 |
+
"learning_rate": 7.142857142857143e-06,
|
1044 |
+
"loss": 0.3047,
|
1045 |
+
"step": 148
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 2.77,
|
1049 |
+
"grad_norm": 0.7081269025802612,
|
1050 |
+
"learning_rate": 6.493506493506493e-06,
|
1051 |
+
"loss": 0.3163,
|
1052 |
+
"step": 149
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 2.78,
|
1056 |
+
"grad_norm": 0.7407366037368774,
|
1057 |
+
"learning_rate": 5.844155844155844e-06,
|
1058 |
+
"loss": 0.3018,
|
1059 |
+
"step": 150
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 2.8,
|
1063 |
+
"grad_norm": 0.7546029686927795,
|
1064 |
+
"learning_rate": 5.194805194805195e-06,
|
1065 |
+
"loss": 0.2893,
|
1066 |
+
"step": 151
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 2.82,
|
1070 |
+
"grad_norm": 0.7611325979232788,
|
1071 |
+
"learning_rate": 4.5454545454545455e-06,
|
1072 |
+
"loss": 0.3045,
|
1073 |
+
"step": 152
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 2.84,
|
1077 |
+
"grad_norm": 0.7612661123275757,
|
1078 |
+
"learning_rate": 3.896103896103896e-06,
|
1079 |
+
"loss": 0.3131,
|
1080 |
+
"step": 153
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 2.86,
|
1084 |
+
"grad_norm": 0.7379683256149292,
|
1085 |
+
"learning_rate": 3.2467532467532465e-06,
|
1086 |
+
"loss": 0.3149,
|
1087 |
+
"step": 154
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 2.88,
|
1091 |
+
"grad_norm": 0.7501469850540161,
|
1092 |
+
"learning_rate": 2.5974025974025976e-06,
|
1093 |
+
"loss": 0.3127,
|
1094 |
+
"step": 155
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 2.9,
|
1098 |
+
"grad_norm": 0.7290940880775452,
|
1099 |
+
"learning_rate": 1.948051948051948e-06,
|
1100 |
+
"loss": 0.3183,
|
1101 |
+
"step": 156
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 2.91,
|
1105 |
+
"grad_norm": 0.7008856534957886,
|
1106 |
+
"learning_rate": 1.2987012987012988e-06,
|
1107 |
+
"loss": 0.2956,
|
1108 |
+
"step": 157
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 2.93,
|
1112 |
+
"grad_norm": 0.755764365196228,
|
1113 |
+
"learning_rate": 6.493506493506494e-07,
|
1114 |
+
"loss": 0.3082,
|
1115 |
+
"step": 158
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 2.95,
|
1119 |
+
"grad_norm": 0.7324373126029968,
|
1120 |
+
"learning_rate": 0.0,
|
1121 |
+
"loss": 0.3037,
|
1122 |
+
"step": 159
|
1123 |
+
}
|
1124 |
+
],
|
1125 |
+
"logging_steps": 1,
|
1126 |
+
"max_steps": 159,
|
1127 |
+
"num_input_tokens_seen": 0,
|
1128 |
+
"num_train_epochs": 3,
|
1129 |
+
"save_steps": 5,
|
1130 |
+
"total_flos": 2.3908841183133696e+17,
|
1131 |
+
"train_batch_size": 16,
|
1132 |
+
"trial_name": null,
|
1133 |
+
"trial_params": null
|
1134 |
+
}
|
checkpoint-159/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:565d81edba8fc76a54ee2e5498f231de6e2c153d87eaba407ea8f5ba343a36f6
|
3 |
+
size 5048
|
checkpoint-53/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: Viet-Mistral/Vistral-7B-Chat
|
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-53/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Viet-Mistral/Vistral-7B-Chat",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 128,
|
14 |
+
"lora_dropout": 0,
|
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": "unsloth",
|
22 |
+
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"gate_proj",
|
25 |
+
"down_proj",
|
26 |
+
"o_proj",
|
27 |
+
"k_proj",
|
28 |
+
"q_proj",
|
29 |
+
"up_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-53/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29b4a63413ec13ecfa6b19b633892e2f8e37bbae88f5d9f3acf0e87f784efd73
|
3 |
+
size 671149168
|
checkpoint-53/added_tokens.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<</SYS>>": 38366,
|
3 |
+
"<<SYS>>": 38365,
|
4 |
+
"[/INST]": 38368,
|
5 |
+
"[INST]": 38367
|
6 |
+
}
|
checkpoint-53/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c29637e549c2ee90ce9a827def1f01beb8422b4aedcd7fb53995b58e6c9f8ba
|
3 |
+
size 1342555602
|
checkpoint-53/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec995be8da3d39228d72b8931b8e5157f0339a5f6c8af5793ddbc486f90572ed
|
3 |
+
size 14244
|
checkpoint-53/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3eee9e5f977d7a005a09e3482d7caec1ee8ca3fa548fab1870797745596f8957
|
3 |
+
size 1064
|
checkpoint-53/special_tokens_map.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"eos_token": {
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"pad_token": {
|
22 |
+
"content": "<unk>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"unk_token": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
checkpoint-53/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-53/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e792a804bbfc19a96b61b87109b8f2b0b7c92830025f285b402ba27c0c309c6f
|
3 |
+
size 596883
|
checkpoint-53/tokenizer_config.json
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"38365": {
|
30 |
+
"content": "<<SYS>>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": false
|
36 |
+
},
|
37 |
+
"38366": {
|
38 |
+
"content": "<</SYS>>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": false
|
44 |
+
},
|
45 |
+
"38367": {
|
46 |
+
"content": "[INST]",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": false
|
52 |
+
},
|
53 |
+
"38368": {
|
54 |
+
"content": "[/INST]",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": false
|
60 |
+
}
|
61 |
+
},
|
62 |
+
"additional_special_tokens": [
|
63 |
+
"<unk>",
|
64 |
+
"<s>",
|
65 |
+
"</s>"
|
66 |
+
],
|
67 |
+
"bos_token": "<s>",
|
68 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
69 |
+
"clean_up_tokenization_spaces": false,
|
70 |
+
"eos_token": "</s>",
|
71 |
+
"legacy": true,
|
72 |
+
"model_max_length": 32768,
|
73 |
+
"pad_token": "<unk>",
|
74 |
+
"padding_side": "right",
|
75 |
+
"sp_model_kwargs": {},
|
76 |
+
"spaces_between_special_tokens": false,
|
77 |
+
"tokenizer_class": "LlamaTokenizer",
|
78 |
+
"unk_token": "<unk>",
|
79 |
+
"use_default_system_prompt": false,
|
80 |
+
"use_fast": true
|
81 |
+
}
|
checkpoint-53/trainer_state.json
ADDED
@@ -0,0 +1,392 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9837587006960556,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 53,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02,
|
13 |
+
"grad_norm": 28.83467674255371,
|
14 |
+
"learning_rate": 2e-05,
|
15 |
+
"loss": 2.7878,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.04,
|
20 |
+
"grad_norm": 28.955718994140625,
|
21 |
+
"learning_rate": 4e-05,
|
22 |
+
"loss": 2.7826,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.06,
|
27 |
+
"grad_norm": 17.856950759887695,
|
28 |
+
"learning_rate": 6e-05,
|
29 |
+
"loss": 2.2388,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.07,
|
34 |
+
"grad_norm": 16.615158081054688,
|
35 |
+
"learning_rate": 8e-05,
|
36 |
+
"loss": 1.7809,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.09,
|
41 |
+
"grad_norm": 34.79571533203125,
|
42 |
+
"learning_rate": 0.0001,
|
43 |
+
"loss": 1.9714,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.11,
|
48 |
+
"grad_norm": 6.3113694190979,
|
49 |
+
"learning_rate": 9.935064935064936e-05,
|
50 |
+
"loss": 1.4032,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.13,
|
55 |
+
"grad_norm": 8.230330467224121,
|
56 |
+
"learning_rate": 9.870129870129871e-05,
|
57 |
+
"loss": 1.241,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.15,
|
62 |
+
"grad_norm": 17.19231605529785,
|
63 |
+
"learning_rate": 9.805194805194806e-05,
|
64 |
+
"loss": 1.2388,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.17,
|
69 |
+
"grad_norm": 6.900284767150879,
|
70 |
+
"learning_rate": 9.74025974025974e-05,
|
71 |
+
"loss": 1.0881,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.19,
|
76 |
+
"grad_norm": 2.7498185634613037,
|
77 |
+
"learning_rate": 9.675324675324677e-05,
|
78 |
+
"loss": 1.0071,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.2,
|
83 |
+
"grad_norm": 4.016067028045654,
|
84 |
+
"learning_rate": 9.610389610389611e-05,
|
85 |
+
"loss": 0.9962,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.22,
|
90 |
+
"grad_norm": 2.365187883377075,
|
91 |
+
"learning_rate": 9.545454545454546e-05,
|
92 |
+
"loss": 0.9928,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.24,
|
97 |
+
"grad_norm": 1.4348371028900146,
|
98 |
+
"learning_rate": 9.480519480519481e-05,
|
99 |
+
"loss": 0.9107,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.26,
|
104 |
+
"grad_norm": 1.8148932456970215,
|
105 |
+
"learning_rate": 9.415584415584417e-05,
|
106 |
+
"loss": 0.853,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.28,
|
111 |
+
"grad_norm": 1.9855575561523438,
|
112 |
+
"learning_rate": 9.35064935064935e-05,
|
113 |
+
"loss": 0.8598,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.3,
|
118 |
+
"grad_norm": 1.9960970878601074,
|
119 |
+
"learning_rate": 9.285714285714286e-05,
|
120 |
+
"loss": 0.8384,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.32,
|
125 |
+
"grad_norm": 1.4565762281417847,
|
126 |
+
"learning_rate": 9.220779220779221e-05,
|
127 |
+
"loss": 0.7895,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.33,
|
132 |
+
"grad_norm": 1.419858694076538,
|
133 |
+
"learning_rate": 9.155844155844156e-05,
|
134 |
+
"loss": 0.8162,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.35,
|
139 |
+
"grad_norm": 1.3651608228683472,
|
140 |
+
"learning_rate": 9.090909090909092e-05,
|
141 |
+
"loss": 0.7924,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.37,
|
146 |
+
"grad_norm": 1.1524626016616821,
|
147 |
+
"learning_rate": 9.025974025974027e-05,
|
148 |
+
"loss": 0.7484,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.39,
|
153 |
+
"grad_norm": 0.9174069166183472,
|
154 |
+
"learning_rate": 8.961038961038961e-05,
|
155 |
+
"loss": 0.7276,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.41,
|
160 |
+
"grad_norm": 1.1832919120788574,
|
161 |
+
"learning_rate": 8.896103896103896e-05,
|
162 |
+
"loss": 0.6658,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.43,
|
167 |
+
"grad_norm": 1.3024309873580933,
|
168 |
+
"learning_rate": 8.831168831168831e-05,
|
169 |
+
"loss": 0.7379,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.45,
|
174 |
+
"grad_norm": 1.1416062116622925,
|
175 |
+
"learning_rate": 8.766233766233767e-05,
|
176 |
+
"loss": 0.7202,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.46,
|
181 |
+
"grad_norm": 1.2058277130126953,
|
182 |
+
"learning_rate": 8.701298701298701e-05,
|
183 |
+
"loss": 0.6777,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.48,
|
188 |
+
"grad_norm": 1.0915583372116089,
|
189 |
+
"learning_rate": 8.636363636363637e-05,
|
190 |
+
"loss": 0.7063,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.5,
|
195 |
+
"grad_norm": 1.0384303331375122,
|
196 |
+
"learning_rate": 8.571428571428571e-05,
|
197 |
+
"loss": 0.6447,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.52,
|
202 |
+
"grad_norm": 1.131259560585022,
|
203 |
+
"learning_rate": 8.506493506493507e-05,
|
204 |
+
"loss": 0.6911,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.54,
|
209 |
+
"grad_norm": 1.1505099534988403,
|
210 |
+
"learning_rate": 8.441558441558442e-05,
|
211 |
+
"loss": 0.6142,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.56,
|
216 |
+
"grad_norm": 2.6675026416778564,
|
217 |
+
"learning_rate": 8.376623376623377e-05,
|
218 |
+
"loss": 0.6181,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.58,
|
223 |
+
"grad_norm": 1.2021816968917847,
|
224 |
+
"learning_rate": 8.311688311688312e-05,
|
225 |
+
"loss": 0.6542,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.59,
|
230 |
+
"grad_norm": 3.363269090652466,
|
231 |
+
"learning_rate": 8.246753246753248e-05,
|
232 |
+
"loss": 0.5968,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.61,
|
237 |
+
"grad_norm": 3.8007972240448,
|
238 |
+
"learning_rate": 8.181818181818183e-05,
|
239 |
+
"loss": 0.5983,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.63,
|
244 |
+
"grad_norm": 3.570556163787842,
|
245 |
+
"learning_rate": 8.116883116883117e-05,
|
246 |
+
"loss": 0.6375,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.65,
|
251 |
+
"grad_norm": 4.428549766540527,
|
252 |
+
"learning_rate": 8.051948051948052e-05,
|
253 |
+
"loss": 0.6519,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.67,
|
258 |
+
"grad_norm": 3.7240254878997803,
|
259 |
+
"learning_rate": 7.987012987012987e-05,
|
260 |
+
"loss": 0.5935,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.69,
|
265 |
+
"grad_norm": 2.453350782394409,
|
266 |
+
"learning_rate": 7.922077922077923e-05,
|
267 |
+
"loss": 0.604,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.71,
|
272 |
+
"grad_norm": 3.341071844100952,
|
273 |
+
"learning_rate": 7.857142857142858e-05,
|
274 |
+
"loss": 0.5994,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.72,
|
279 |
+
"grad_norm": 3.4222161769866943,
|
280 |
+
"learning_rate": 7.792207792207793e-05,
|
281 |
+
"loss": 0.5731,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.74,
|
286 |
+
"grad_norm": 2.9063804149627686,
|
287 |
+
"learning_rate": 7.727272727272727e-05,
|
288 |
+
"loss": 0.5566,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.76,
|
293 |
+
"grad_norm": 3.170330762863159,
|
294 |
+
"learning_rate": 7.662337662337662e-05,
|
295 |
+
"loss": 0.5684,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.78,
|
300 |
+
"grad_norm": 2.8363170623779297,
|
301 |
+
"learning_rate": 7.597402597402598e-05,
|
302 |
+
"loss": 0.5936,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.8,
|
307 |
+
"grad_norm": 2.3944592475891113,
|
308 |
+
"learning_rate": 7.532467532467533e-05,
|
309 |
+
"loss": 0.5571,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.82,
|
314 |
+
"grad_norm": 2.816237688064575,
|
315 |
+
"learning_rate": 7.467532467532467e-05,
|
316 |
+
"loss": 0.5598,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.84,
|
321 |
+
"grad_norm": 2.57438325881958,
|
322 |
+
"learning_rate": 7.402597402597404e-05,
|
323 |
+
"loss": 0.5615,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.85,
|
328 |
+
"grad_norm": 2.3164243698120117,
|
329 |
+
"learning_rate": 7.337662337662338e-05,
|
330 |
+
"loss": 0.5381,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.87,
|
335 |
+
"grad_norm": 2.4226622581481934,
|
336 |
+
"learning_rate": 7.272727272727273e-05,
|
337 |
+
"loss": 0.5592,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.89,
|
342 |
+
"grad_norm": 1.5568475723266602,
|
343 |
+
"learning_rate": 7.207792207792208e-05,
|
344 |
+
"loss": 0.5729,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.91,
|
349 |
+
"grad_norm": 1.1320440769195557,
|
350 |
+
"learning_rate": 7.142857142857143e-05,
|
351 |
+
"loss": 0.5546,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.93,
|
356 |
+
"grad_norm": 2.220273733139038,
|
357 |
+
"learning_rate": 7.077922077922077e-05,
|
358 |
+
"loss": 0.5587,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.95,
|
363 |
+
"grad_norm": 1.8099664449691772,
|
364 |
+
"learning_rate": 7.012987012987014e-05,
|
365 |
+
"loss": 0.5403,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.97,
|
370 |
+
"grad_norm": 1.7992054224014282,
|
371 |
+
"learning_rate": 6.948051948051948e-05,
|
372 |
+
"loss": 0.5374,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.98,
|
377 |
+
"grad_norm": 1.5891600847244263,
|
378 |
+
"learning_rate": 6.883116883116883e-05,
|
379 |
+
"loss": 0.5188,
|
380 |
+
"step": 53
|
381 |
+
}
|
382 |
+
],
|
383 |
+
"logging_steps": 1,
|
384 |
+
"max_steps": 159,
|
385 |
+
"num_input_tokens_seen": 0,
|
386 |
+
"num_train_epochs": 3,
|
387 |
+
"save_steps": 5,
|
388 |
+
"total_flos": 8.106404006854656e+16,
|
389 |
+
"train_batch_size": 16,
|
390 |
+
"trial_name": null,
|
391 |
+
"trial_params": null
|
392 |
+
}
|
checkpoint-53/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:565d81edba8fc76a54ee2e5498f231de6e2c153d87eaba407ea8f5ba343a36f6
|
3 |
+
size 5048
|
runs/Apr05_12-01-19_83bf7c2258aa/events.out.tfevents.1712318488.83bf7c2258aa.34.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46aef8175affb59830279784bf05467095174c72aa964dbd95d4ffb30cb016de
|
3 |
+
size 38461
|