Upload 16 files
Browse files- .gitattributes +1 -0
- added_tokens.json +24 -0
- config.json +30 -0
- generation_config.json +6 -0
- main.py +24 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +208 -0
- trainer_state.json +565 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Qwen/Qwen2.5-0.5B",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151643,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 896,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 4864,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"max_window_layers": 24,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"num_attention_heads": 14,
|
17 |
+
"num_hidden_layers": 24,
|
18 |
+
"num_key_value_heads": 2,
|
19 |
+
"rms_norm_eps": 1e-06,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"rope_theta": 1000000.0,
|
22 |
+
"sliding_window": 32768,
|
23 |
+
"tie_word_embeddings": true,
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.49.0",
|
26 |
+
"use_cache": true,
|
27 |
+
"use_mrope": false,
|
28 |
+
"use_sliding_window": false,
|
29 |
+
"vocab_size": 151936
|
30 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"eos_token_id": 151643,
|
4 |
+
"max_new_tokens": 2048,
|
5 |
+
"transformers_version": "4.49.0"
|
6 |
+
}
|
main.py
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import torch
|
2 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
3 |
+
|
4 |
+
model_path = "./Path-to-llm-folder"
|
5 |
+
|
6 |
+
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
7 |
+
model = AutoModelForCausalLM.from_pretrained(model_path)
|
8 |
+
|
9 |
+
device = "cuda" if torch.cuda.is_available() else "cpu"
|
10 |
+
model.to(device)
|
11 |
+
|
12 |
+
def generate_text(prompt, max_length=2000):
|
13 |
+
inputs = tokenizer(prompt, return_tensors="pt").to(device)
|
14 |
+
output = model.generate(
|
15 |
+
**inputs,
|
16 |
+
do_sample=True,
|
17 |
+
temperature=0.7
|
18 |
+
)
|
19 |
+
return tokenizer.decode(output[0], skip_special_tokens=True)
|
20 |
+
|
21 |
+
prompt = "Write a code in react for calling api to server at https://example.com/test"
|
22 |
+
generated_text = generate_text(prompt)
|
23 |
+
|
24 |
+
print(generated_text)
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac65ca279281cf744fb4668c6c824ee5aa85a4c0f5e102fb03eb9ae801ccd727
|
3 |
+
size 1976163472
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce3891f5630d76ca40928cc31f3aecab9dfb868b998f2acda96f7bff9078cf30
|
3 |
+
size 3952505274
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95b6047bd8cc6f4cdf7c46dea47edb8e542435510070c6cd1e0a7d9ccf5fd7da
|
3 |
+
size 14244
|
scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9710f568b59aba2846ca4ef568d997abfab62e884f5f4524a6561eb514a981e
|
3 |
+
size 988
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61effe5a5a556d42bd8f2f6a98f8f6bc989ee943d8307697de4a78bae8f1175e
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<|endoftext|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
3 |
+
size 11421896
|
tokenizer_config.json
ADDED
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"additional_special_tokens": [
|
183 |
+
"<|im_start|>",
|
184 |
+
"<|im_end|>",
|
185 |
+
"<|object_ref_start|>",
|
186 |
+
"<|object_ref_end|>",
|
187 |
+
"<|box_start|>",
|
188 |
+
"<|box_end|>",
|
189 |
+
"<|quad_start|>",
|
190 |
+
"<|quad_end|>",
|
191 |
+
"<|vision_start|>",
|
192 |
+
"<|vision_end|>",
|
193 |
+
"<|vision_pad|>",
|
194 |
+
"<|image_pad|>",
|
195 |
+
"<|video_pad|>"
|
196 |
+
],
|
197 |
+
"bos_token": null,
|
198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
199 |
+
"clean_up_tokenization_spaces": false,
|
200 |
+
"eos_token": "<|endoftext|>",
|
201 |
+
"errors": "replace",
|
202 |
+
"extra_special_tokens": {},
|
203 |
+
"model_max_length": 131072,
|
204 |
+
"pad_token": "<|endoftext|>",
|
205 |
+
"split_special_tokens": false,
|
206 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
207 |
+
"unk_token": null
|
208 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,565 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 6.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 7662,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.07830853563038372,
|
13 |
+
"grad_norm": 9.886259078979492,
|
14 |
+
"learning_rate": 9.874706342991386e-05,
|
15 |
+
"loss": 2.2961,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.15661707126076743,
|
20 |
+
"grad_norm": 9.754347801208496,
|
21 |
+
"learning_rate": 9.744192116940747e-05,
|
22 |
+
"loss": 2.1652,
|
23 |
+
"step": 200
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.23492560689115113,
|
27 |
+
"grad_norm": 10.011685371398926,
|
28 |
+
"learning_rate": 9.613677890890107e-05,
|
29 |
+
"loss": 2.2701,
|
30 |
+
"step": 300
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.31323414252153486,
|
34 |
+
"grad_norm": 10.389019966125488,
|
35 |
+
"learning_rate": 9.483163664839469e-05,
|
36 |
+
"loss": 2.1357,
|
37 |
+
"step": 400
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.39154267815191857,
|
41 |
+
"grad_norm": 8.717257499694824,
|
42 |
+
"learning_rate": 9.352649438788829e-05,
|
43 |
+
"loss": 2.0979,
|
44 |
+
"step": 500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.46985121378230227,
|
48 |
+
"grad_norm": 10.2243070602417,
|
49 |
+
"learning_rate": 9.222135212738188e-05,
|
50 |
+
"loss": 2.0926,
|
51 |
+
"step": 600
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.548159749412686,
|
55 |
+
"grad_norm": 9.24715518951416,
|
56 |
+
"learning_rate": 9.091620986687549e-05,
|
57 |
+
"loss": 2.0199,
|
58 |
+
"step": 700
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.6264682850430697,
|
62 |
+
"grad_norm": 8.67659854888916,
|
63 |
+
"learning_rate": 8.96110676063691e-05,
|
64 |
+
"loss": 2.071,
|
65 |
+
"step": 800
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.7047768206734534,
|
69 |
+
"grad_norm": 6.2473015785217285,
|
70 |
+
"learning_rate": 8.830592534586271e-05,
|
71 |
+
"loss": 2.0342,
|
72 |
+
"step": 900
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.7830853563038371,
|
76 |
+
"grad_norm": 9.428214073181152,
|
77 |
+
"learning_rate": 8.700078308535631e-05,
|
78 |
+
"loss": 1.9497,
|
79 |
+
"step": 1000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.8613938919342208,
|
83 |
+
"grad_norm": 7.909013271331787,
|
84 |
+
"learning_rate": 8.569564082484992e-05,
|
85 |
+
"loss": 2.006,
|
86 |
+
"step": 1100
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.9397024275646045,
|
90 |
+
"grad_norm": 7.305349826812744,
|
91 |
+
"learning_rate": 8.43904985643435e-05,
|
92 |
+
"loss": 1.9751,
|
93 |
+
"step": 1200
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.0180109631949883,
|
97 |
+
"grad_norm": 6.404293060302734,
|
98 |
+
"learning_rate": 8.308535630383712e-05,
|
99 |
+
"loss": 1.7841,
|
100 |
+
"step": 1300
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.096319498825372,
|
104 |
+
"grad_norm": 6.121842384338379,
|
105 |
+
"learning_rate": 8.178021404333073e-05,
|
106 |
+
"loss": 1.2646,
|
107 |
+
"step": 1400
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.1746280344557556,
|
111 |
+
"grad_norm": 5.871735572814941,
|
112 |
+
"learning_rate": 8.047507178282433e-05,
|
113 |
+
"loss": 1.2666,
|
114 |
+
"step": 1500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.2529365700861395,
|
118 |
+
"grad_norm": 6.930913925170898,
|
119 |
+
"learning_rate": 7.916992952231794e-05,
|
120 |
+
"loss": 1.295,
|
121 |
+
"step": 1600
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.331245105716523,
|
125 |
+
"grad_norm": 5.334323406219482,
|
126 |
+
"learning_rate": 7.786478726181154e-05,
|
127 |
+
"loss": 1.3333,
|
128 |
+
"step": 1700
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.4095536413469067,
|
132 |
+
"grad_norm": 7.161041259765625,
|
133 |
+
"learning_rate": 7.655964500130514e-05,
|
134 |
+
"loss": 1.3355,
|
135 |
+
"step": 1800
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.4878621769772904,
|
139 |
+
"grad_norm": 7.43231725692749,
|
140 |
+
"learning_rate": 7.525450274079875e-05,
|
141 |
+
"loss": 1.284,
|
142 |
+
"step": 1900
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.5661707126076743,
|
146 |
+
"grad_norm": 6.2656354904174805,
|
147 |
+
"learning_rate": 7.394936048029235e-05,
|
148 |
+
"loss": 1.287,
|
149 |
+
"step": 2000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.644479248238058,
|
153 |
+
"grad_norm": 5.97381067276001,
|
154 |
+
"learning_rate": 7.264421821978597e-05,
|
155 |
+
"loss": 1.3196,
|
156 |
+
"step": 2100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.7227877838684416,
|
160 |
+
"grad_norm": 7.828345775604248,
|
161 |
+
"learning_rate": 7.133907595927957e-05,
|
162 |
+
"loss": 1.2884,
|
163 |
+
"step": 2200
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 1.8010963194988254,
|
167 |
+
"grad_norm": 7.866464614868164,
|
168 |
+
"learning_rate": 7.003393369877316e-05,
|
169 |
+
"loss": 1.3136,
|
170 |
+
"step": 2300
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.879404855129209,
|
174 |
+
"grad_norm": 5.8095598220825195,
|
175 |
+
"learning_rate": 6.872879143826677e-05,
|
176 |
+
"loss": 1.2181,
|
177 |
+
"step": 2400
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.9577133907595927,
|
181 |
+
"grad_norm": 6.666238784790039,
|
182 |
+
"learning_rate": 6.742364917776038e-05,
|
183 |
+
"loss": 1.2461,
|
184 |
+
"step": 2500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 2.0360219263899766,
|
188 |
+
"grad_norm": 7.129757881164551,
|
189 |
+
"learning_rate": 6.611850691725399e-05,
|
190 |
+
"loss": 0.9798,
|
191 |
+
"step": 2600
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 2.11433046202036,
|
195 |
+
"grad_norm": 6.111073017120361,
|
196 |
+
"learning_rate": 6.481336465674759e-05,
|
197 |
+
"loss": 0.6804,
|
198 |
+
"step": 2700
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 2.192638997650744,
|
202 |
+
"grad_norm": 5.344665050506592,
|
203 |
+
"learning_rate": 6.35082223962412e-05,
|
204 |
+
"loss": 0.6946,
|
205 |
+
"step": 2800
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 2.2709475332811278,
|
209 |
+
"grad_norm": 5.611790657043457,
|
210 |
+
"learning_rate": 6.220308013573479e-05,
|
211 |
+
"loss": 0.6516,
|
212 |
+
"step": 2900
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.349256068911511,
|
216 |
+
"grad_norm": 7.892216682434082,
|
217 |
+
"learning_rate": 6.0897937875228404e-05,
|
218 |
+
"loss": 0.6718,
|
219 |
+
"step": 3000
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 2.427564604541895,
|
223 |
+
"grad_norm": 8.479430198669434,
|
224 |
+
"learning_rate": 5.959279561472201e-05,
|
225 |
+
"loss": 0.6601,
|
226 |
+
"step": 3100
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 2.505873140172279,
|
230 |
+
"grad_norm": 6.140246391296387,
|
231 |
+
"learning_rate": 5.828765335421561e-05,
|
232 |
+
"loss": 0.6619,
|
233 |
+
"step": 3200
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 2.5841816758026623,
|
237 |
+
"grad_norm": 6.076893329620361,
|
238 |
+
"learning_rate": 5.6982511093709215e-05,
|
239 |
+
"loss": 0.69,
|
240 |
+
"step": 3300
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 2.662490211433046,
|
244 |
+
"grad_norm": 6.6155900955200195,
|
245 |
+
"learning_rate": 5.5677368833202826e-05,
|
246 |
+
"loss": 0.6866,
|
247 |
+
"step": 3400
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 2.74079874706343,
|
251 |
+
"grad_norm": 6.685502052307129,
|
252 |
+
"learning_rate": 5.437222657269643e-05,
|
253 |
+
"loss": 0.6615,
|
254 |
+
"step": 3500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 2.8191072826938135,
|
258 |
+
"grad_norm": 8.586551666259766,
|
259 |
+
"learning_rate": 5.306708431219003e-05,
|
260 |
+
"loss": 0.7118,
|
261 |
+
"step": 3600
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 2.8974158183241974,
|
265 |
+
"grad_norm": 5.001748085021973,
|
266 |
+
"learning_rate": 5.176194205168363e-05,
|
267 |
+
"loss": 0.7117,
|
268 |
+
"step": 3700
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 2.975724353954581,
|
272 |
+
"grad_norm": 5.666826248168945,
|
273 |
+
"learning_rate": 5.045679979117724e-05,
|
274 |
+
"loss": 0.6868,
|
275 |
+
"step": 3800
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 3.0540328895849647,
|
279 |
+
"grad_norm": 5.463041305541992,
|
280 |
+
"learning_rate": 4.9151657530670846e-05,
|
281 |
+
"loss": 0.4208,
|
282 |
+
"step": 3900
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 3.1323414252153485,
|
286 |
+
"grad_norm": 6.563859939575195,
|
287 |
+
"learning_rate": 4.784651527016445e-05,
|
288 |
+
"loss": 0.2744,
|
289 |
+
"step": 4000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 3.210649960845732,
|
293 |
+
"grad_norm": 5.918147087097168,
|
294 |
+
"learning_rate": 4.654137300965806e-05,
|
295 |
+
"loss": 0.309,
|
296 |
+
"step": 4100
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 3.288958496476116,
|
300 |
+
"grad_norm": 4.2588958740234375,
|
301 |
+
"learning_rate": 4.523623074915166e-05,
|
302 |
+
"loss": 0.3063,
|
303 |
+
"step": 4200
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 3.3672670321064997,
|
307 |
+
"grad_norm": 5.194436073303223,
|
308 |
+
"learning_rate": 4.393108848864527e-05,
|
309 |
+
"loss": 0.3002,
|
310 |
+
"step": 4300
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 3.445575567736883,
|
314 |
+
"grad_norm": 4.340348720550537,
|
315 |
+
"learning_rate": 4.262594622813887e-05,
|
316 |
+
"loss": 0.2957,
|
317 |
+
"step": 4400
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 3.523884103367267,
|
321 |
+
"grad_norm": 3.6878747940063477,
|
322 |
+
"learning_rate": 4.1320803967632476e-05,
|
323 |
+
"loss": 0.2968,
|
324 |
+
"step": 4500
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 3.602192638997651,
|
328 |
+
"grad_norm": 4.565743923187256,
|
329 |
+
"learning_rate": 4.001566170712608e-05,
|
330 |
+
"loss": 0.2921,
|
331 |
+
"step": 4600
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 3.6805011746280343,
|
335 |
+
"grad_norm": 4.834578514099121,
|
336 |
+
"learning_rate": 3.8710519446619684e-05,
|
337 |
+
"loss": 0.2937,
|
338 |
+
"step": 4700
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 3.758809710258418,
|
342 |
+
"grad_norm": 4.321404933929443,
|
343 |
+
"learning_rate": 3.740537718611329e-05,
|
344 |
+
"loss": 0.2927,
|
345 |
+
"step": 4800
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 3.837118245888802,
|
349 |
+
"grad_norm": 5.987460136413574,
|
350 |
+
"learning_rate": 3.610023492560689e-05,
|
351 |
+
"loss": 0.2813,
|
352 |
+
"step": 4900
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 3.9154267815191854,
|
356 |
+
"grad_norm": 4.690079689025879,
|
357 |
+
"learning_rate": 3.4795092665100495e-05,
|
358 |
+
"loss": 0.2848,
|
359 |
+
"step": 5000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 3.9937353171495693,
|
363 |
+
"grad_norm": 4.9851298332214355,
|
364 |
+
"learning_rate": 3.34899504045941e-05,
|
365 |
+
"loss": 0.2776,
|
366 |
+
"step": 5100
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 4.072043852779953,
|
370 |
+
"grad_norm": 4.890774726867676,
|
371 |
+
"learning_rate": 3.218480814408771e-05,
|
372 |
+
"loss": 0.1309,
|
373 |
+
"step": 5200
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 4.150352388410337,
|
377 |
+
"grad_norm": 3.3844189643859863,
|
378 |
+
"learning_rate": 3.087966588358131e-05,
|
379 |
+
"loss": 0.1197,
|
380 |
+
"step": 5300
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 4.22866092404072,
|
384 |
+
"grad_norm": 3.3200528621673584,
|
385 |
+
"learning_rate": 2.9574523623074918e-05,
|
386 |
+
"loss": 0.1252,
|
387 |
+
"step": 5400
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 4.306969459671104,
|
391 |
+
"grad_norm": 2.3074514865875244,
|
392 |
+
"learning_rate": 2.826938136256852e-05,
|
393 |
+
"loss": 0.1181,
|
394 |
+
"step": 5500
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 4.385277995301488,
|
398 |
+
"grad_norm": 4.1699724197387695,
|
399 |
+
"learning_rate": 2.696423910206213e-05,
|
400 |
+
"loss": 0.1234,
|
401 |
+
"step": 5600
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 4.463586530931871,
|
405 |
+
"grad_norm": 3.833683729171753,
|
406 |
+
"learning_rate": 2.565909684155573e-05,
|
407 |
+
"loss": 0.1161,
|
408 |
+
"step": 5700
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 4.5418950665622555,
|
412 |
+
"grad_norm": 2.7541275024414062,
|
413 |
+
"learning_rate": 2.4353954581049333e-05,
|
414 |
+
"loss": 0.1101,
|
415 |
+
"step": 5800
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 4.620203602192639,
|
419 |
+
"grad_norm": 4.193445205688477,
|
420 |
+
"learning_rate": 2.304881232054294e-05,
|
421 |
+
"loss": 0.1118,
|
422 |
+
"step": 5900
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 4.698512137823022,
|
426 |
+
"grad_norm": 3.851712465286255,
|
427 |
+
"learning_rate": 2.1743670060036544e-05,
|
428 |
+
"loss": 0.1144,
|
429 |
+
"step": 6000
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 4.776820673453407,
|
433 |
+
"grad_norm": 3.333712100982666,
|
434 |
+
"learning_rate": 2.043852779953015e-05,
|
435 |
+
"loss": 0.1117,
|
436 |
+
"step": 6100
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 4.85512920908379,
|
440 |
+
"grad_norm": 3.7569446563720703,
|
441 |
+
"learning_rate": 1.9133385539023756e-05,
|
442 |
+
"loss": 0.1049,
|
443 |
+
"step": 6200
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 4.9334377447141735,
|
447 |
+
"grad_norm": 3.2152910232543945,
|
448 |
+
"learning_rate": 1.782824327851736e-05,
|
449 |
+
"loss": 0.1064,
|
450 |
+
"step": 6300
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 5.011746280344558,
|
454 |
+
"grad_norm": 1.593434453010559,
|
455 |
+
"learning_rate": 1.6523101018010963e-05,
|
456 |
+
"loss": 0.0936,
|
457 |
+
"step": 6400
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 5.090054815974941,
|
461 |
+
"grad_norm": 1.8612021207809448,
|
462 |
+
"learning_rate": 1.5217958757504569e-05,
|
463 |
+
"loss": 0.047,
|
464 |
+
"step": 6500
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 5.168363351605325,
|
468 |
+
"grad_norm": 2.482856035232544,
|
469 |
+
"learning_rate": 1.3912816496998175e-05,
|
470 |
+
"loss": 0.0448,
|
471 |
+
"step": 6600
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 5.246671887235709,
|
475 |
+
"grad_norm": 1.4229090213775635,
|
476 |
+
"learning_rate": 1.2607674236491779e-05,
|
477 |
+
"loss": 0.044,
|
478 |
+
"step": 6700
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 5.324980422866092,
|
482 |
+
"grad_norm": 1.7034039497375488,
|
483 |
+
"learning_rate": 1.1302531975985382e-05,
|
484 |
+
"loss": 0.0459,
|
485 |
+
"step": 6800
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 5.403288958496476,
|
489 |
+
"grad_norm": 2.2560577392578125,
|
490 |
+
"learning_rate": 9.997389715478986e-06,
|
491 |
+
"loss": 0.0453,
|
492 |
+
"step": 6900
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 5.48159749412686,
|
496 |
+
"grad_norm": 2.826206922531128,
|
497 |
+
"learning_rate": 8.692247454972592e-06,
|
498 |
+
"loss": 0.0439,
|
499 |
+
"step": 7000
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 5.559906029757244,
|
503 |
+
"grad_norm": 1.7038235664367676,
|
504 |
+
"learning_rate": 7.387105194466197e-06,
|
505 |
+
"loss": 0.0421,
|
506 |
+
"step": 7100
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 5.638214565387627,
|
510 |
+
"grad_norm": 2.713496685028076,
|
511 |
+
"learning_rate": 6.081962933959802e-06,
|
512 |
+
"loss": 0.0417,
|
513 |
+
"step": 7200
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 5.716523101018011,
|
517 |
+
"grad_norm": 0.9614657163619995,
|
518 |
+
"learning_rate": 4.776820673453407e-06,
|
519 |
+
"loss": 0.0403,
|
520 |
+
"step": 7300
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 5.794831636648395,
|
524 |
+
"grad_norm": 1.6873942613601685,
|
525 |
+
"learning_rate": 3.471678412947011e-06,
|
526 |
+
"loss": 0.0407,
|
527 |
+
"step": 7400
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 5.873140172278778,
|
531 |
+
"grad_norm": 2.548095464706421,
|
532 |
+
"learning_rate": 2.166536152440616e-06,
|
533 |
+
"loss": 0.0397,
|
534 |
+
"step": 7500
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 5.9514487079091625,
|
538 |
+
"grad_norm": 1.1459206342697144,
|
539 |
+
"learning_rate": 8.613938919342209e-07,
|
540 |
+
"loss": 0.0366,
|
541 |
+
"step": 7600
|
542 |
+
}
|
543 |
+
],
|
544 |
+
"logging_steps": 100,
|
545 |
+
"max_steps": 7662,
|
546 |
+
"num_input_tokens_seen": 0,
|
547 |
+
"num_train_epochs": 6,
|
548 |
+
"save_steps": 500,
|
549 |
+
"stateful_callbacks": {
|
550 |
+
"TrainerControl": {
|
551 |
+
"args": {
|
552 |
+
"should_epoch_stop": false,
|
553 |
+
"should_evaluate": false,
|
554 |
+
"should_log": false,
|
555 |
+
"should_save": true,
|
556 |
+
"should_training_stop": true
|
557 |
+
},
|
558 |
+
"attributes": {}
|
559 |
+
}
|
560 |
+
},
|
561 |
+
"total_flos": 8424085506490368.0,
|
562 |
+
"train_batch_size": 1,
|
563 |
+
"trial_name": null,
|
564 |
+
"trial_params": null
|
565 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4664b8c7a0f79707f74e0aadf4dd8746c525027955e7321ade9815f3f41f1407
|
3 |
+
size 5304
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|