Hugging Face's logo

Chaeseung
/
lslm_lst_patch_align_ft

TensorBoard
Safetensors
qwen2
Model card Files
xet
 Metrics Community
Chaeseung commited on
Commit
6be21bf
·
verified ·
1 Parent(s): b9bdbf3

Upload folder using huggingface_hub

Browse files
Files changed (32) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +24 -0
  3. chat_template.jinja +54 -0
  4. checkpoint-4500/optimizer.pt +3 -0
  5. checkpoint-4500/pytorch_model.bin +3 -0
  6. checkpoint-4500/rng_state.pth +3 -0
  7. checkpoint-4500/scheduler.pt +3 -0
  8. checkpoint-4500/trainer_state.json +1609 -0
  9. checkpoint-4500/training_args.bin +3 -0
  10. checkpoint-5000/optimizer.pt +3 -0
  11. checkpoint-5000/pytorch_model.bin +3 -0
  12. checkpoint-5000/rng_state.pth +3 -0
  13. checkpoint-5000/scheduler.pt +3 -0
  14. checkpoint-5000/trainer_state.json +1784 -0
  15. checkpoint-5000/training_args.bin +3 -0
  16. checkpoint-5319/optimizer.pt +3 -0
  17. checkpoint-5319/pytorch_model.bin +3 -0
  18. checkpoint-5319/rng_state.pth +3 -0
  19. checkpoint-5319/scheduler.pt +3 -0
  20. checkpoint-5319/trainer_state.json +1889 -0
  21. checkpoint-5319/training_args.bin +3 -0
  22. config.json +59 -0
  23. generation_config.json +6 -0
  24. logs/events.out.tfevents.1778526155.2183d5a8cefc.13908.0 +3 -0
  25. merges.txt +0 -0
  26. model.safetensors +3 -0
  27. special_tokens_map.json +31 -0
  28. speech_patch_encoder.pt +3 -0
  29. speech_token_meta.json +21 -0
  30. tokenizer.json +3 -0
  31. tokenizer_config.json +207 -0
  32. 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
+ }
chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\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>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\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" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
checkpoint-4500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af67f8b27cea7eb972f5d955b4253ec6254de65e40bef0d6835fc005cfe55729
3
+ size 1483239819
checkpoint-4500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1942ad0b32196975ee063e46f74b27aa3523b3bf976a4f9a3aeb424ce91aa9e
3
+ size 1014303003
checkpoint-4500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
3
+ size 14645
checkpoint-4500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bc7e75ce47eb9372d98730127e5f37ae1c6534e172d8615f2be31f2fe4f549c
3
+ size 1465
checkpoint-4500/trainer_state.json ADDED
@@ -0,0 +1,1609 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.53818489528242,
6
+ "eval_steps": 500,
7
+ "global_step": 4500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.01128270220717862,
14
+ "grad_norm": 684.0,
15
+ "learning_rate": 1.1875e-06,
16
+ "loss": 42.923,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 0.02256540441435724,
21
+ "grad_norm": 378.0,
22
+ "learning_rate": 2.4375e-06,
23
+ "loss": 41.9073,
24
+ "step": 40
25
+ },
26
+ {
27
+ "epoch": 0.03384810662153586,
28
+ "grad_norm": 322.0,
29
+ "learning_rate": 3.6875000000000007e-06,
30
+ "loss": 39.9877,
31
+ "step": 60
32
+ },
33
+ {
34
+ "epoch": 0.04513080882871448,
35
+ "grad_norm": 280.0,
36
+ "learning_rate": 4.937500000000001e-06,
37
+ "loss": 38.0747,
38
+ "step": 80
39
+ },
40
+ {
41
+ "epoch": 0.056413511035893094,
42
+ "grad_norm": 1328.0,
43
+ "learning_rate": 6.1875000000000005e-06,
44
+ "loss": 36.2999,
45
+ "step": 100
46
+ },
47
+ {
48
+ "epoch": 0.06769621324307172,
49
+ "grad_norm": 212.0,
50
+ "learning_rate": 7.437500000000001e-06,
51
+ "loss": 35.0646,
52
+ "step": 120
53
+ },
54
+ {
55
+ "epoch": 0.07897891545025033,
56
+ "grad_norm": 208.0,
57
+ "learning_rate": 8.687500000000001e-06,
58
+ "loss": 34.4917,
59
+ "step": 140
60
+ },
61
+ {
62
+ "epoch": 0.09026161765742896,
63
+ "grad_norm": 180.0,
64
+ "learning_rate": 9.937500000000001e-06,
65
+ "loss": 34.5205,
66
+ "step": 160
67
+ },
68
+ {
69
+ "epoch": 0.10154431986460757,
70
+ "grad_norm": 213.0,
71
+ "learning_rate": 9.96317115720101e-06,
72
+ "loss": 33.3244,
73
+ "step": 180
74
+ },
75
+ {
76
+ "epoch": 0.11282702207178619,
77
+ "grad_norm": 174.0,
78
+ "learning_rate": 9.9244039542547e-06,
79
+ "loss": 33.6509,
80
+ "step": 200
81
+ },
82
+ {
83
+ "epoch": 0.12410972427896481,
84
+ "grad_norm": 234.0,
85
+ "learning_rate": 9.885636751308394e-06,
86
+ "loss": 34.1064,
87
+ "step": 220
88
+ },
89
+ {
90
+ "epoch": 0.13539242648614344,
91
+ "grad_norm": 176.0,
92
+ "learning_rate": 9.846869548362087e-06,
93
+ "loss": 34.0945,
94
+ "step": 240
95
+ },
96
+ {
97
+ "epoch": 0.14667512869332205,
98
+ "grad_norm": 222.0,
99
+ "learning_rate": 9.80810234541578e-06,
100
+ "loss": 33.8671,
101
+ "step": 260
102
+ },
103
+ {
104
+ "epoch": 0.15795783090050067,
105
+ "grad_norm": 164.0,
106
+ "learning_rate": 9.769335142469472e-06,
107
+ "loss": 33.4257,
108
+ "step": 280
109
+ },
110
+ {
111
+ "epoch": 0.16924053310767928,
112
+ "grad_norm": 185.0,
113
+ "learning_rate": 9.730567939523164e-06,
114
+ "loss": 33.4832,
115
+ "step": 300
116
+ },
117
+ {
118
+ "epoch": 0.18052323531485792,
119
+ "grad_norm": 188.0,
120
+ "learning_rate": 9.691800736576857e-06,
121
+ "loss": 33.4079,
122
+ "step": 320
123
+ },
124
+ {
125
+ "epoch": 0.19180593752203653,
126
+ "grad_norm": 195.0,
127
+ "learning_rate": 9.65303353363055e-06,
128
+ "loss": 34.1975,
129
+ "step": 340
130
+ },
131
+ {
132
+ "epoch": 0.20308863972921515,
133
+ "grad_norm": 186.0,
134
+ "learning_rate": 9.614266330684242e-06,
135
+ "loss": 33.3613,
136
+ "step": 360
137
+ },
138
+ {
139
+ "epoch": 0.21437134193639376,
140
+ "grad_norm": 172.0,
141
+ "learning_rate": 9.575499127737934e-06,
142
+ "loss": 32.6162,
143
+ "step": 380
144
+ },
145
+ {
146
+ "epoch": 0.22565404414357237,
147
+ "grad_norm": 170.0,
148
+ "learning_rate": 9.536731924791627e-06,
149
+ "loss": 33.3925,
150
+ "step": 400
151
+ },
152
+ {
153
+ "epoch": 0.23693674635075102,
154
+ "grad_norm": 168.0,
155
+ "learning_rate": 9.49796472184532e-06,
156
+ "loss": 33.4435,
157
+ "step": 420
158
+ },
159
+ {
160
+ "epoch": 0.24821944855792963,
161
+ "grad_norm": 197.0,
162
+ "learning_rate": 9.459197518899013e-06,
163
+ "loss": 32.9941,
164
+ "step": 440
165
+ },
166
+ {
167
+ "epoch": 0.25950215076510824,
168
+ "grad_norm": 190.0,
169
+ "learning_rate": 9.420430315952704e-06,
170
+ "loss": 33.2245,
171
+ "step": 460
172
+ },
173
+ {
174
+ "epoch": 0.2707848529722869,
175
+ "grad_norm": 185.0,
176
+ "learning_rate": 9.381663113006397e-06,
177
+ "loss": 33.2802,
178
+ "step": 480
179
+ },
180
+ {
181
+ "epoch": 0.28206755517946547,
182
+ "grad_norm": 201.0,
183
+ "learning_rate": 9.34289591006009e-06,
184
+ "loss": 33.3563,
185
+ "step": 500
186
+ },
187
+ {
188
+ "epoch": 0.2933502573866441,
189
+ "grad_norm": 160.0,
190
+ "learning_rate": 9.304128707113782e-06,
191
+ "loss": 32.8094,
192
+ "step": 520
193
+ },
194
+ {
195
+ "epoch": 0.3046329595938227,
196
+ "grad_norm": 171.0,
197
+ "learning_rate": 9.265361504167476e-06,
198
+ "loss": 33.967,
199
+ "step": 540
200
+ },
201
+ {
202
+ "epoch": 0.31591566180100134,
203
+ "grad_norm": 185.0,
204
+ "learning_rate": 9.226594301221168e-06,
205
+ "loss": 33.9071,
206
+ "step": 560
207
+ },
208
+ {
209
+ "epoch": 0.32719836400818,
210
+ "grad_norm": 168.0,
211
+ "learning_rate": 9.18782709827486e-06,
212
+ "loss": 33.5103,
213
+ "step": 580
214
+ },
215
+ {
216
+ "epoch": 0.33848106621535856,
217
+ "grad_norm": 185.0,
218
+ "learning_rate": 9.149059895328553e-06,
219
+ "loss": 33.2943,
220
+ "step": 600
221
+ },
222
+ {
223
+ "epoch": 0.3497637684225372,
224
+ "grad_norm": 235.0,
225
+ "learning_rate": 9.110292692382246e-06,
226
+ "loss": 33.8674,
227
+ "step": 620
228
+ },
229
+ {
230
+ "epoch": 0.36104647062971584,
231
+ "grad_norm": 171.0,
232
+ "learning_rate": 9.071525489435938e-06,
233
+ "loss": 34.1437,
234
+ "step": 640
235
+ },
236
+ {
237
+ "epoch": 0.37232917283689443,
238
+ "grad_norm": 176.0,
239
+ "learning_rate": 9.03275828648963e-06,
240
+ "loss": 32.9577,
241
+ "step": 660
242
+ },
243
+ {
244
+ "epoch": 0.38361187504407307,
245
+ "grad_norm": 179.0,
246
+ "learning_rate": 8.993991083543323e-06,
247
+ "loss": 33.5755,
248
+ "step": 680
249
+ },
250
+ {
251
+ "epoch": 0.39489457725125165,
252
+ "grad_norm": 187.0,
253
+ "learning_rate": 8.955223880597016e-06,
254
+ "loss": 34.03,
255
+ "step": 700
256
+ },
257
+ {
258
+ "epoch": 0.4061772794584303,
259
+ "grad_norm": 175.0,
260
+ "learning_rate": 8.916456677650708e-06,
261
+ "loss": 34.0341,
262
+ "step": 720
263
+ },
264
+ {
265
+ "epoch": 0.41745998166560894,
266
+ "grad_norm": 184.0,
267
+ "learning_rate": 8.8776894747044e-06,
268
+ "loss": 34.1199,
269
+ "step": 740
270
+ },
271
+ {
272
+ "epoch": 0.4287426838727875,
273
+ "grad_norm": 214.0,
274
+ "learning_rate": 8.838922271758093e-06,
275
+ "loss": 34.5299,
276
+ "step": 760
277
+ },
278
+ {
279
+ "epoch": 0.44002538607996616,
280
+ "grad_norm": 187.0,
281
+ "learning_rate": 8.800155068811787e-06,
282
+ "loss": 33.6687,
283
+ "step": 780
284
+ },
285
+ {
286
+ "epoch": 0.45130808828714475,
287
+ "grad_norm": 207.0,
288
+ "learning_rate": 8.761387865865478e-06,
289
+ "loss": 33.4913,
290
+ "step": 800
291
+ },
292
+ {
293
+ "epoch": 0.4625907904943234,
294
+ "grad_norm": 199.0,
295
+ "learning_rate": 8.72262066291917e-06,
296
+ "loss": 34.6043,
297
+ "step": 820
298
+ },
299
+ {
300
+ "epoch": 0.47387349270150203,
301
+ "grad_norm": 308.0,
302
+ "learning_rate": 8.683853459972865e-06,
303
+ "loss": 34.1107,
304
+ "step": 840
305
+ },
306
+ {
307
+ "epoch": 0.4851561949086806,
308
+ "grad_norm": 219.0,
309
+ "learning_rate": 8.645086257026555e-06,
310
+ "loss": 33.5659,
311
+ "step": 860
312
+ },
313
+ {
314
+ "epoch": 0.49643889711585926,
315
+ "grad_norm": 184.0,
316
+ "learning_rate": 8.60631905408025e-06,
317
+ "loss": 34.6702,
318
+ "step": 880
319
+ },
320
+ {
321
+ "epoch": 0.5077215993230378,
322
+ "grad_norm": 188.0,
323
+ "learning_rate": 8.567551851133942e-06,
324
+ "loss": 33.9021,
325
+ "step": 900
326
+ },
327
+ {
328
+ "epoch": 0.5190043015302165,
329
+ "grad_norm": 189.0,
330
+ "learning_rate": 8.528784648187633e-06,
331
+ "loss": 33.8139,
332
+ "step": 920
333
+ },
334
+ {
335
+ "epoch": 0.5302870037373951,
336
+ "grad_norm": 202.0,
337
+ "learning_rate": 8.490017445241327e-06,
338
+ "loss": 33.9562,
339
+ "step": 940
340
+ },
341
+ {
342
+ "epoch": 0.5415697059445738,
343
+ "grad_norm": 184.0,
344
+ "learning_rate": 8.45125024229502e-06,
345
+ "loss": 34.1304,
346
+ "step": 960
347
+ },
348
+ {
349
+ "epoch": 0.5528524081517523,
350
+ "grad_norm": 210.0,
351
+ "learning_rate": 8.412483039348712e-06,
352
+ "loss": 34.3385,
353
+ "step": 980
354
+ },
355
+ {
356
+ "epoch": 0.5641351103589309,
357
+ "grad_norm": 167.0,
358
+ "learning_rate": 8.373715836402404e-06,
359
+ "loss": 34.2957,
360
+ "step": 1000
361
+ },
362
+ {
363
+ "epoch": 0.5754178125661096,
364
+ "grad_norm": 197.0,
365
+ "learning_rate": 8.334948633456097e-06,
366
+ "loss": 34.701,
367
+ "step": 1020
368
+ },
369
+ {
370
+ "epoch": 0.5867005147732882,
371
+ "grad_norm": 220.0,
372
+ "learning_rate": 8.29618143050979e-06,
373
+ "loss": 34.1251,
374
+ "step": 1040
375
+ },
376
+ {
377
+ "epoch": 0.5979832169804669,
378
+ "grad_norm": 199.0,
379
+ "learning_rate": 8.257414227563482e-06,
380
+ "loss": 34.2395,
381
+ "step": 1060
382
+ },
383
+ {
384
+ "epoch": 0.6092659191876454,
385
+ "grad_norm": 210.0,
386
+ "learning_rate": 8.218647024617174e-06,
387
+ "loss": 33.7562,
388
+ "step": 1080
389
+ },
390
+ {
391
+ "epoch": 0.620548621394824,
392
+ "grad_norm": 213.0,
393
+ "learning_rate": 8.179879821670867e-06,
394
+ "loss": 35.2014,
395
+ "step": 1100
396
+ },
397
+ {
398
+ "epoch": 0.6318313236020027,
399
+ "grad_norm": 214.0,
400
+ "learning_rate": 8.14111261872456e-06,
401
+ "loss": 33.6772,
402
+ "step": 1120
403
+ },
404
+ {
405
+ "epoch": 0.6431140258091813,
406
+ "grad_norm": 220.0,
407
+ "learning_rate": 8.102345415778252e-06,
408
+ "loss": 34.0573,
409
+ "step": 1140
410
+ },
411
+ {
412
+ "epoch": 0.65439672801636,
413
+ "grad_norm": 162.0,
414
+ "learning_rate": 8.063578212831944e-06,
415
+ "loss": 34.1778,
416
+ "step": 1160
417
+ },
418
+ {
419
+ "epoch": 0.6656794302235386,
420
+ "grad_norm": 171.0,
421
+ "learning_rate": 8.024811009885637e-06,
422
+ "loss": 34.7704,
423
+ "step": 1180
424
+ },
425
+ {
426
+ "epoch": 0.6769621324307171,
427
+ "grad_norm": 192.0,
428
+ "learning_rate": 7.98604380693933e-06,
429
+ "loss": 34.5073,
430
+ "step": 1200
431
+ },
432
+ {
433
+ "epoch": 0.6882448346378958,
434
+ "grad_norm": 199.0,
435
+ "learning_rate": 7.947276603993023e-06,
436
+ "loss": 35.1462,
437
+ "step": 1220
438
+ },
439
+ {
440
+ "epoch": 0.6995275368450744,
441
+ "grad_norm": 194.0,
442
+ "learning_rate": 7.908509401046716e-06,
443
+ "loss": 35.0324,
444
+ "step": 1240
445
+ },
446
+ {
447
+ "epoch": 0.710810239052253,
448
+ "grad_norm": 180.0,
449
+ "learning_rate": 7.869742198100407e-06,
450
+ "loss": 34.4355,
451
+ "step": 1260
452
+ },
453
+ {
454
+ "epoch": 0.7220929412594317,
455
+ "grad_norm": 171.0,
456
+ "learning_rate": 7.8309749951541e-06,
457
+ "loss": 34.3484,
458
+ "step": 1280
459
+ },
460
+ {
461
+ "epoch": 0.7333756434666102,
462
+ "grad_norm": 234.0,
463
+ "learning_rate": 7.792207792207793e-06,
464
+ "loss": 34.3537,
465
+ "step": 1300
466
+ },
467
+ {
468
+ "epoch": 0.7446583456737889,
469
+ "grad_norm": 217.0,
470
+ "learning_rate": 7.753440589261486e-06,
471
+ "loss": 34.4467,
472
+ "step": 1320
473
+ },
474
+ {
475
+ "epoch": 0.7559410478809675,
476
+ "grad_norm": 183.0,
477
+ "learning_rate": 7.714673386315178e-06,
478
+ "loss": 34.5935,
479
+ "step": 1340
480
+ },
481
+ {
482
+ "epoch": 0.7672237500881461,
483
+ "grad_norm": 167.0,
484
+ "learning_rate": 7.67590618336887e-06,
485
+ "loss": 34.1833,
486
+ "step": 1360
487
+ },
488
+ {
489
+ "epoch": 0.7785064522953248,
490
+ "grad_norm": 182.0,
491
+ "learning_rate": 7.637138980422563e-06,
492
+ "loss": 34.5052,
493
+ "step": 1380
494
+ },
495
+ {
496
+ "epoch": 0.7897891545025033,
497
+ "grad_norm": 170.0,
498
+ "learning_rate": 7.598371777476256e-06,
499
+ "loss": 34.5334,
500
+ "step": 1400
501
+ },
502
+ {
503
+ "epoch": 0.801071856709682,
504
+ "grad_norm": 181.0,
505
+ "learning_rate": 7.559604574529948e-06,
506
+ "loss": 34.1411,
507
+ "step": 1420
508
+ },
509
+ {
510
+ "epoch": 0.8123545589168606,
511
+ "grad_norm": 163.0,
512
+ "learning_rate": 7.5208373715836415e-06,
513
+ "loss": 34.7683,
514
+ "step": 1440
515
+ },
516
+ {
517
+ "epoch": 0.8236372611240392,
518
+ "grad_norm": 176.0,
519
+ "learning_rate": 7.482070168637333e-06,
520
+ "loss": 34.7674,
521
+ "step": 1460
522
+ },
523
+ {
524
+ "epoch": 0.8349199633312179,
525
+ "grad_norm": 165.0,
526
+ "learning_rate": 7.4433029656910264e-06,
527
+ "loss": 34.7617,
528
+ "step": 1480
529
+ },
530
+ {
531
+ "epoch": 0.8462026655383964,
532
+ "grad_norm": 194.0,
533
+ "learning_rate": 7.404535762744719e-06,
534
+ "loss": 34.7591,
535
+ "step": 1500
536
+ },
537
+ {
538
+ "epoch": 0.857485367745575,
539
+ "grad_norm": 175.0,
540
+ "learning_rate": 7.3657685597984105e-06,
541
+ "loss": 34.0827,
542
+ "step": 1520
543
+ },
544
+ {
545
+ "epoch": 0.8687680699527537,
546
+ "grad_norm": 179.0,
547
+ "learning_rate": 7.327001356852104e-06,
548
+ "loss": 34.5944,
549
+ "step": 1540
550
+ },
551
+ {
552
+ "epoch": 0.8800507721599323,
553
+ "grad_norm": 198.0,
554
+ "learning_rate": 7.288234153905796e-06,
555
+ "loss": 35.1967,
556
+ "step": 1560
557
+ },
558
+ {
559
+ "epoch": 0.891333474367111,
560
+ "grad_norm": 192.0,
561
+ "learning_rate": 7.249466950959488e-06,
562
+ "loss": 35.0658,
563
+ "step": 1580
564
+ },
565
+ {
566
+ "epoch": 0.9026161765742895,
567
+ "grad_norm": 207.0,
568
+ "learning_rate": 7.210699748013181e-06,
569
+ "loss": 34.9624,
570
+ "step": 1600
571
+ },
572
+ {
573
+ "epoch": 0.9138988787814681,
574
+ "grad_norm": 195.0,
575
+ "learning_rate": 7.171932545066874e-06,
576
+ "loss": 34.5503,
577
+ "step": 1620
578
+ },
579
+ {
580
+ "epoch": 0.9251815809886468,
581
+ "grad_norm": 187.0,
582
+ "learning_rate": 7.133165342120567e-06,
583
+ "loss": 34.6947,
584
+ "step": 1640
585
+ },
586
+ {
587
+ "epoch": 0.9364642831958254,
588
+ "grad_norm": 178.0,
589
+ "learning_rate": 7.094398139174259e-06,
590
+ "loss": 34.7273,
591
+ "step": 1660
592
+ },
593
+ {
594
+ "epoch": 0.9477469854030041,
595
+ "grad_norm": 195.0,
596
+ "learning_rate": 7.055630936227952e-06,
597
+ "loss": 35.1698,
598
+ "step": 1680
599
+ },
600
+ {
601
+ "epoch": 0.9590296876101826,
602
+ "grad_norm": 194.0,
603
+ "learning_rate": 7.0168637332816445e-06,
604
+ "loss": 34.8608,
605
+ "step": 1700
606
+ },
607
+ {
608
+ "epoch": 0.9703123898173612,
609
+ "grad_norm": 209.0,
610
+ "learning_rate": 6.978096530335336e-06,
611
+ "loss": 34.3997,
612
+ "step": 1720
613
+ },
614
+ {
615
+ "epoch": 0.9815950920245399,
616
+ "grad_norm": 142.0,
617
+ "learning_rate": 6.9393293273890295e-06,
618
+ "loss": 34.856,
619
+ "step": 1740
620
+ },
621
+ {
622
+ "epoch": 0.9928777942317185,
623
+ "grad_norm": 186.0,
624
+ "learning_rate": 6.900562124442722e-06,
625
+ "loss": 34.3359,
626
+ "step": 1760
627
+ },
628
+ {
629
+ "epoch": 1.0039489457725126,
630
+ "grad_norm": 169.0,
631
+ "learning_rate": 6.8617949214964145e-06,
632
+ "loss": 33.62,
633
+ "step": 1780
634
+ },
635
+ {
636
+ "epoch": 1.0152316479796912,
637
+ "grad_norm": 189.0,
638
+ "learning_rate": 6.823027718550107e-06,
639
+ "loss": 33.4374,
640
+ "step": 1800
641
+ },
642
+ {
643
+ "epoch": 1.0265143501868697,
644
+ "grad_norm": 191.0,
645
+ "learning_rate": 6.7842605156038e-06,
646
+ "loss": 32.8082,
647
+ "step": 1820
648
+ },
649
+ {
650
+ "epoch": 1.0377970523940483,
651
+ "grad_norm": 151.0,
652
+ "learning_rate": 6.745493312657493e-06,
653
+ "loss": 33.2524,
654
+ "step": 1840
655
+ },
656
+ {
657
+ "epoch": 1.049079754601227,
658
+ "grad_norm": 153.0,
659
+ "learning_rate": 6.706726109711184e-06,
660
+ "loss": 32.7946,
661
+ "step": 1860
662
+ },
663
+ {
664
+ "epoch": 1.0603624568084056,
665
+ "grad_norm": 190.0,
666
+ "learning_rate": 6.667958906764878e-06,
667
+ "loss": 34.0579,
668
+ "step": 1880
669
+ },
670
+ {
671
+ "epoch": 1.0716451590155842,
672
+ "grad_norm": 169.0,
673
+ "learning_rate": 6.62919170381857e-06,
674
+ "loss": 33.6604,
675
+ "step": 1900
676
+ },
677
+ {
678
+ "epoch": 1.0829278612227629,
679
+ "grad_norm": 203.0,
680
+ "learning_rate": 6.590424500872263e-06,
681
+ "loss": 33.566,
682
+ "step": 1920
683
+ },
684
+ {
685
+ "epoch": 1.0942105634299415,
686
+ "grad_norm": 166.0,
687
+ "learning_rate": 6.551657297925955e-06,
688
+ "loss": 32.8621,
689
+ "step": 1940
690
+ },
691
+ {
692
+ "epoch": 1.1054932656371201,
693
+ "grad_norm": 190.0,
694
+ "learning_rate": 6.5128900949796484e-06,
695
+ "loss": 32.7915,
696
+ "step": 1960
697
+ },
698
+ {
699
+ "epoch": 1.1167759678442988,
700
+ "grad_norm": 159.0,
701
+ "learning_rate": 6.47412289203334e-06,
702
+ "loss": 32.8263,
703
+ "step": 1980
704
+ },
705
+ {
706
+ "epoch": 1.1280586700514774,
707
+ "grad_norm": 213.0,
708
+ "learning_rate": 6.4353556890870326e-06,
709
+ "loss": 33.4649,
710
+ "step": 2000
711
+ },
712
+ {
713
+ "epoch": 1.1393413722586558,
714
+ "grad_norm": 170.0,
715
+ "learning_rate": 6.396588486140726e-06,
716
+ "loss": 33.0993,
717
+ "step": 2020
718
+ },
719
+ {
720
+ "epoch": 1.1506240744658345,
721
+ "grad_norm": 178.0,
722
+ "learning_rate": 6.3578212831944175e-06,
723
+ "loss": 32.8403,
724
+ "step": 2040
725
+ },
726
+ {
727
+ "epoch": 1.1619067766730131,
728
+ "grad_norm": 192.0,
729
+ "learning_rate": 6.31905408024811e-06,
730
+ "loss": 33.212,
731
+ "step": 2060
732
+ },
733
+ {
734
+ "epoch": 1.1731894788801918,
735
+ "grad_norm": 177.0,
736
+ "learning_rate": 6.280286877301803e-06,
737
+ "loss": 32.9688,
738
+ "step": 2080
739
+ },
740
+ {
741
+ "epoch": 1.1844721810873704,
742
+ "grad_norm": 176.0,
743
+ "learning_rate": 6.241519674355496e-06,
744
+ "loss": 33.0461,
745
+ "step": 2100
746
+ },
747
+ {
748
+ "epoch": 1.195754883294549,
749
+ "grad_norm": 191.0,
750
+ "learning_rate": 6.202752471409188e-06,
751
+ "loss": 33.4505,
752
+ "step": 2120
753
+ },
754
+ {
755
+ "epoch": 1.2070375855017277,
756
+ "grad_norm": 165.0,
757
+ "learning_rate": 6.163985268462881e-06,
758
+ "loss": 33.6436,
759
+ "step": 2140
760
+ },
761
+ {
762
+ "epoch": 1.2183202877089063,
763
+ "grad_norm": 177.0,
764
+ "learning_rate": 6.125218065516574e-06,
765
+ "loss": 32.9951,
766
+ "step": 2160
767
+ },
768
+ {
769
+ "epoch": 1.229602989916085,
770
+ "grad_norm": 181.0,
771
+ "learning_rate": 6.086450862570266e-06,
772
+ "loss": 34.0142,
773
+ "step": 2180
774
+ },
775
+ {
776
+ "epoch": 1.2408856921232636,
777
+ "grad_norm": 174.0,
778
+ "learning_rate": 6.047683659623958e-06,
779
+ "loss": 33.6973,
780
+ "step": 2200
781
+ },
782
+ {
783
+ "epoch": 1.2521683943304422,
784
+ "grad_norm": 160.0,
785
+ "learning_rate": 6.0089164566776515e-06,
786
+ "loss": 32.4556,
787
+ "step": 2220
788
+ },
789
+ {
790
+ "epoch": 1.2634510965376209,
791
+ "grad_norm": 165.0,
792
+ "learning_rate": 5.970149253731343e-06,
793
+ "loss": 33.3473,
794
+ "step": 2240
795
+ },
796
+ {
797
+ "epoch": 1.2747337987447993,
798
+ "grad_norm": 192.0,
799
+ "learning_rate": 5.9313820507850365e-06,
800
+ "loss": 32.9415,
801
+ "step": 2260
802
+ },
803
+ {
804
+ "epoch": 1.286016500951978,
805
+ "grad_norm": 169.0,
806
+ "learning_rate": 5.892614847838729e-06,
807
+ "loss": 33.7312,
808
+ "step": 2280
809
+ },
810
+ {
811
+ "epoch": 1.2972992031591566,
812
+ "grad_norm": 172.0,
813
+ "learning_rate": 5.853847644892422e-06,
814
+ "loss": 33.2523,
815
+ "step": 2300
816
+ },
817
+ {
818
+ "epoch": 1.3085819053663352,
819
+ "grad_norm": 166.0,
820
+ "learning_rate": 5.815080441946114e-06,
821
+ "loss": 33.4629,
822
+ "step": 2320
823
+ },
824
+ {
825
+ "epoch": 1.3198646075735139,
826
+ "grad_norm": 220.0,
827
+ "learning_rate": 5.776313238999806e-06,
828
+ "loss": 33.6943,
829
+ "step": 2340
830
+ },
831
+ {
832
+ "epoch": 1.3311473097806925,
833
+ "grad_norm": 163.0,
834
+ "learning_rate": 5.7375460360535e-06,
835
+ "loss": 33.2026,
836
+ "step": 2360
837
+ },
838
+ {
839
+ "epoch": 1.3424300119878712,
840
+ "grad_norm": 227.0,
841
+ "learning_rate": 5.698778833107191e-06,
842
+ "loss": 33.3166,
843
+ "step": 2380
844
+ },
845
+ {
846
+ "epoch": 1.3537127141950498,
847
+ "grad_norm": 198.0,
848
+ "learning_rate": 5.660011630160885e-06,
849
+ "loss": 33.5236,
850
+ "step": 2400
851
+ },
852
+ {
853
+ "epoch": 1.3649954164022282,
854
+ "grad_norm": 178.0,
855
+ "learning_rate": 5.621244427214577e-06,
856
+ "loss": 33.3746,
857
+ "step": 2420
858
+ },
859
+ {
860
+ "epoch": 1.3762781186094069,
861
+ "grad_norm": 182.0,
862
+ "learning_rate": 5.582477224268269e-06,
863
+ "loss": 33.2293,
864
+ "step": 2440
865
+ },
866
+ {
867
+ "epoch": 1.3875608208165855,
868
+ "grad_norm": 232.0,
869
+ "learning_rate": 5.543710021321962e-06,
870
+ "loss": 34.0862,
871
+ "step": 2460
872
+ },
873
+ {
874
+ "epoch": 1.3988435230237641,
875
+ "grad_norm": 175.0,
876
+ "learning_rate": 5.5049428183756546e-06,
877
+ "loss": 33.4116,
878
+ "step": 2480
879
+ },
880
+ {
881
+ "epoch": 1.4101262252309428,
882
+ "grad_norm": 198.0,
883
+ "learning_rate": 5.466175615429348e-06,
884
+ "loss": 32.8442,
885
+ "step": 2500
886
+ },
887
+ {
888
+ "epoch": 1.4214089274381214,
889
+ "grad_norm": 162.0,
890
+ "learning_rate": 5.4274084124830395e-06,
891
+ "loss": 33.7111,
892
+ "step": 2520
893
+ },
894
+ {
895
+ "epoch": 1.4326916296453,
896
+ "grad_norm": 208.0,
897
+ "learning_rate": 5.388641209536732e-06,
898
+ "loss": 33.0033,
899
+ "step": 2540
900
+ },
901
+ {
902
+ "epoch": 1.4439743318524787,
903
+ "grad_norm": 192.0,
904
+ "learning_rate": 5.349874006590425e-06,
905
+ "loss": 33.8201,
906
+ "step": 2560
907
+ },
908
+ {
909
+ "epoch": 1.4552570340596573,
910
+ "grad_norm": 169.0,
911
+ "learning_rate": 5.311106803644117e-06,
912
+ "loss": 32.9213,
913
+ "step": 2580
914
+ },
915
+ {
916
+ "epoch": 1.466539736266836,
917
+ "grad_norm": 181.0,
918
+ "learning_rate": 5.27233960069781e-06,
919
+ "loss": 33.9638,
920
+ "step": 2600
921
+ },
922
+ {
923
+ "epoch": 1.4778224384740146,
924
+ "grad_norm": 173.0,
925
+ "learning_rate": 5.233572397751503e-06,
926
+ "loss": 33.5811,
927
+ "step": 2620
928
+ },
929
+ {
930
+ "epoch": 1.4891051406811933,
931
+ "grad_norm": 190.0,
932
+ "learning_rate": 5.194805194805194e-06,
933
+ "loss": 33.8197,
934
+ "step": 2640
935
+ },
936
+ {
937
+ "epoch": 1.500387842888372,
938
+ "grad_norm": 197.0,
939
+ "learning_rate": 5.156037991858888e-06,
940
+ "loss": 33.6394,
941
+ "step": 2660
942
+ },
943
+ {
944
+ "epoch": 1.5116705450955505,
945
+ "grad_norm": 290.0,
946
+ "learning_rate": 5.11727078891258e-06,
947
+ "loss": 33.2235,
948
+ "step": 2680
949
+ },
950
+ {
951
+ "epoch": 1.522953247302729,
952
+ "grad_norm": 148.0,
953
+ "learning_rate": 5.0785035859662735e-06,
954
+ "loss": 33.6943,
955
+ "step": 2700
956
+ },
957
+ {
958
+ "epoch": 1.5342359495099076,
959
+ "grad_norm": 183.0,
960
+ "learning_rate": 5.039736383019965e-06,
961
+ "loss": 33.5758,
962
+ "step": 2720
963
+ },
964
+ {
965
+ "epoch": 1.5455186517170862,
966
+ "grad_norm": 175.0,
967
+ "learning_rate": 5.0009691800736585e-06,
968
+ "loss": 34.077,
969
+ "step": 2740
970
+ },
971
+ {
972
+ "epoch": 1.5568013539242649,
973
+ "grad_norm": 178.0,
974
+ "learning_rate": 4.96220197712735e-06,
975
+ "loss": 33.2421,
976
+ "step": 2760
977
+ },
978
+ {
979
+ "epoch": 1.5680840561314435,
980
+ "grad_norm": 169.0,
981
+ "learning_rate": 4.9234347741810434e-06,
982
+ "loss": 34.0267,
983
+ "step": 2780
984
+ },
985
+ {
986
+ "epoch": 1.579366758338622,
987
+ "grad_norm": 171.0,
988
+ "learning_rate": 4.884667571234736e-06,
989
+ "loss": 33.5599,
990
+ "step": 2800
991
+ },
992
+ {
993
+ "epoch": 1.5906494605458006,
994
+ "grad_norm": 206.0,
995
+ "learning_rate": 4.845900368288428e-06,
996
+ "loss": 33.7535,
997
+ "step": 2820
998
+ },
999
+ {
1000
+ "epoch": 1.6019321627529792,
1001
+ "grad_norm": 168.0,
1002
+ "learning_rate": 4.807133165342121e-06,
1003
+ "loss": 33.4231,
1004
+ "step": 2840
1005
+ },
1006
+ {
1007
+ "epoch": 1.6132148649601579,
1008
+ "grad_norm": 208.0,
1009
+ "learning_rate": 4.768365962395813e-06,
1010
+ "loss": 33.1695,
1011
+ "step": 2860
1012
+ },
1013
+ {
1014
+ "epoch": 1.6244975671673365,
1015
+ "grad_norm": 213.0,
1016
+ "learning_rate": 4.729598759449507e-06,
1017
+ "loss": 33.2739,
1018
+ "step": 2880
1019
+ },
1020
+ {
1021
+ "epoch": 1.6357802693745152,
1022
+ "grad_norm": 177.0,
1023
+ "learning_rate": 4.690831556503198e-06,
1024
+ "loss": 33.3967,
1025
+ "step": 2900
1026
+ },
1027
+ {
1028
+ "epoch": 1.6470629715816938,
1029
+ "grad_norm": 234.0,
1030
+ "learning_rate": 4.652064353556891e-06,
1031
+ "loss": 34.2787,
1032
+ "step": 2920
1033
+ },
1034
+ {
1035
+ "epoch": 1.6583456737888724,
1036
+ "grad_norm": 163.0,
1037
+ "learning_rate": 4.613297150610584e-06,
1038
+ "loss": 34.1793,
1039
+ "step": 2940
1040
+ },
1041
+ {
1042
+ "epoch": 1.669628375996051,
1043
+ "grad_norm": 192.0,
1044
+ "learning_rate": 4.574529947664277e-06,
1045
+ "loss": 33.67,
1046
+ "step": 2960
1047
+ },
1048
+ {
1049
+ "epoch": 1.6809110782032297,
1050
+ "grad_norm": 188.0,
1051
+ "learning_rate": 4.535762744717969e-06,
1052
+ "loss": 34.1299,
1053
+ "step": 2980
1054
+ },
1055
+ {
1056
+ "epoch": 1.6921937804104084,
1057
+ "grad_norm": 210.0,
1058
+ "learning_rate": 4.4969955417716615e-06,
1059
+ "loss": 33.6063,
1060
+ "step": 3000
1061
+ },
1062
+ {
1063
+ "epoch": 1.703476482617587,
1064
+ "grad_norm": 222.0,
1065
+ "learning_rate": 4.458228338825354e-06,
1066
+ "loss": 33.864,
1067
+ "step": 3020
1068
+ },
1069
+ {
1070
+ "epoch": 1.7147591848247656,
1071
+ "grad_norm": 167.0,
1072
+ "learning_rate": 4.4194611358790465e-06,
1073
+ "loss": 33.9385,
1074
+ "step": 3040
1075
+ },
1076
+ {
1077
+ "epoch": 1.7260418870319443,
1078
+ "grad_norm": 201.0,
1079
+ "learning_rate": 4.380693932932739e-06,
1080
+ "loss": 33.4324,
1081
+ "step": 3060
1082
+ },
1083
+ {
1084
+ "epoch": 1.737324589239123,
1085
+ "grad_norm": 171.0,
1086
+ "learning_rate": 4.341926729986432e-06,
1087
+ "loss": 33.6625,
1088
+ "step": 3080
1089
+ },
1090
+ {
1091
+ "epoch": 1.7486072914463013,
1092
+ "grad_norm": 166.0,
1093
+ "learning_rate": 4.303159527040125e-06,
1094
+ "loss": 33.1414,
1095
+ "step": 3100
1096
+ },
1097
+ {
1098
+ "epoch": 1.75988999365348,
1099
+ "grad_norm": 151.0,
1100
+ "learning_rate": 4.264392324093816e-06,
1101
+ "loss": 34.045,
1102
+ "step": 3120
1103
+ },
1104
+ {
1105
+ "epoch": 1.7711726958606586,
1106
+ "grad_norm": 179.0,
1107
+ "learning_rate": 4.22562512114751e-06,
1108
+ "loss": 33.642,
1109
+ "step": 3140
1110
+ },
1111
+ {
1112
+ "epoch": 1.7824553980678373,
1113
+ "grad_norm": 204.0,
1114
+ "learning_rate": 4.186857918201202e-06,
1115
+ "loss": 33.6747,
1116
+ "step": 3160
1117
+ },
1118
+ {
1119
+ "epoch": 1.793738100275016,
1120
+ "grad_norm": 156.0,
1121
+ "learning_rate": 4.148090715254895e-06,
1122
+ "loss": 33.6803,
1123
+ "step": 3180
1124
+ },
1125
+ {
1126
+ "epoch": 1.8050208024821943,
1127
+ "grad_norm": 181.0,
1128
+ "learning_rate": 4.109323512308587e-06,
1129
+ "loss": 33.9288,
1130
+ "step": 3200
1131
+ },
1132
+ {
1133
+ "epoch": 1.816303504689373,
1134
+ "grad_norm": 167.0,
1135
+ "learning_rate": 4.07055630936228e-06,
1136
+ "loss": 33.6484,
1137
+ "step": 3220
1138
+ },
1139
+ {
1140
+ "epoch": 1.8275862068965516,
1141
+ "grad_norm": 179.0,
1142
+ "learning_rate": 4.031789106415972e-06,
1143
+ "loss": 33.5411,
1144
+ "step": 3240
1145
+ },
1146
+ {
1147
+ "epoch": 1.8388689091037302,
1148
+ "grad_norm": 202.0,
1149
+ "learning_rate": 3.993021903469665e-06,
1150
+ "loss": 33.7925,
1151
+ "step": 3260
1152
+ },
1153
+ {
1154
+ "epoch": 1.8501516113109089,
1155
+ "grad_norm": 211.0,
1156
+ "learning_rate": 3.954254700523358e-06,
1157
+ "loss": 34.3101,
1158
+ "step": 3280
1159
+ },
1160
+ {
1161
+ "epoch": 1.8614343135180875,
1162
+ "grad_norm": 187.0,
1163
+ "learning_rate": 3.91548749757705e-06,
1164
+ "loss": 33.674,
1165
+ "step": 3300
1166
+ },
1167
+ {
1168
+ "epoch": 1.8727170157252662,
1169
+ "grad_norm": 186.0,
1170
+ "learning_rate": 3.876720294630743e-06,
1171
+ "loss": 34.4049,
1172
+ "step": 3320
1173
+ },
1174
+ {
1175
+ "epoch": 1.8839997179324448,
1176
+ "grad_norm": 170.0,
1177
+ "learning_rate": 3.837953091684435e-06,
1178
+ "loss": 33.3274,
1179
+ "step": 3340
1180
+ },
1181
+ {
1182
+ "epoch": 1.8952824201396234,
1183
+ "grad_norm": 239.0,
1184
+ "learning_rate": 3.799185888738128e-06,
1185
+ "loss": 33.1375,
1186
+ "step": 3360
1187
+ },
1188
+ {
1189
+ "epoch": 1.906565122346802,
1190
+ "grad_norm": 178.0,
1191
+ "learning_rate": 3.7604186857918207e-06,
1192
+ "loss": 34.1163,
1193
+ "step": 3380
1194
+ },
1195
+ {
1196
+ "epoch": 1.9178478245539807,
1197
+ "grad_norm": 185.0,
1198
+ "learning_rate": 3.7216514828455132e-06,
1199
+ "loss": 34.4329,
1200
+ "step": 3400
1201
+ },
1202
+ {
1203
+ "epoch": 1.9291305267611594,
1204
+ "grad_norm": 195.0,
1205
+ "learning_rate": 3.6828842798992053e-06,
1206
+ "loss": 33.4928,
1207
+ "step": 3420
1208
+ },
1209
+ {
1210
+ "epoch": 1.940413228968338,
1211
+ "grad_norm": 162.0,
1212
+ "learning_rate": 3.644117076952898e-06,
1213
+ "loss": 34.0265,
1214
+ "step": 3440
1215
+ },
1216
+ {
1217
+ "epoch": 1.9516959311755167,
1218
+ "grad_norm": 195.0,
1219
+ "learning_rate": 3.6053498740065907e-06,
1220
+ "loss": 33.9424,
1221
+ "step": 3460
1222
+ },
1223
+ {
1224
+ "epoch": 1.9629786333826953,
1225
+ "grad_norm": 185.0,
1226
+ "learning_rate": 3.5665826710602836e-06,
1227
+ "loss": 34.3252,
1228
+ "step": 3480
1229
+ },
1230
+ {
1231
+ "epoch": 1.974261335589874,
1232
+ "grad_norm": 195.0,
1233
+ "learning_rate": 3.527815468113976e-06,
1234
+ "loss": 34.5225,
1235
+ "step": 3500
1236
+ },
1237
+ {
1238
+ "epoch": 1.9855440377970524,
1239
+ "grad_norm": 214.0,
1240
+ "learning_rate": 3.489048265167668e-06,
1241
+ "loss": 34.5155,
1242
+ "step": 3520
1243
+ },
1244
+ {
1245
+ "epoch": 1.996826740004231,
1246
+ "grad_norm": 182.0,
1247
+ "learning_rate": 3.450281062221361e-06,
1248
+ "loss": 34.1097,
1249
+ "step": 3540
1250
+ },
1251
+ {
1252
+ "epoch": 2.007897891545025,
1253
+ "grad_norm": 164.0,
1254
+ "learning_rate": 3.4115138592750535e-06,
1255
+ "loss": 33.4037,
1256
+ "step": 3560
1257
+ },
1258
+ {
1259
+ "epoch": 2.019180593752204,
1260
+ "grad_norm": 164.0,
1261
+ "learning_rate": 3.3727466563287464e-06,
1262
+ "loss": 33.2511,
1263
+ "step": 3580
1264
+ },
1265
+ {
1266
+ "epoch": 2.0304632959593825,
1267
+ "grad_norm": 228.0,
1268
+ "learning_rate": 3.333979453382439e-06,
1269
+ "loss": 33.3459,
1270
+ "step": 3600
1271
+ },
1272
+ {
1273
+ "epoch": 2.041745998166561,
1274
+ "grad_norm": 201.0,
1275
+ "learning_rate": 3.2952122504361313e-06,
1276
+ "loss": 33.6336,
1277
+ "step": 3620
1278
+ },
1279
+ {
1280
+ "epoch": 2.0530287003737393,
1281
+ "grad_norm": 243.0,
1282
+ "learning_rate": 3.2564450474898242e-06,
1283
+ "loss": 33.4227,
1284
+ "step": 3640
1285
+ },
1286
+ {
1287
+ "epoch": 2.064311402580918,
1288
+ "grad_norm": 188.0,
1289
+ "learning_rate": 3.2176778445435163e-06,
1290
+ "loss": 33.9483,
1291
+ "step": 3660
1292
+ },
1293
+ {
1294
+ "epoch": 2.0755941047880966,
1295
+ "grad_norm": 177.0,
1296
+ "learning_rate": 3.1789106415972088e-06,
1297
+ "loss": 32.5607,
1298
+ "step": 3680
1299
+ },
1300
+ {
1301
+ "epoch": 2.0868768069952752,
1302
+ "grad_norm": 195.0,
1303
+ "learning_rate": 3.1401434386509017e-06,
1304
+ "loss": 33.2094,
1305
+ "step": 3700
1306
+ },
1307
+ {
1308
+ "epoch": 2.098159509202454,
1309
+ "grad_norm": 194.0,
1310
+ "learning_rate": 3.101376235704594e-06,
1311
+ "loss": 32.5983,
1312
+ "step": 3720
1313
+ },
1314
+ {
1315
+ "epoch": 2.1094422114096325,
1316
+ "grad_norm": 171.0,
1317
+ "learning_rate": 3.062609032758287e-06,
1318
+ "loss": 33.4583,
1319
+ "step": 3740
1320
+ },
1321
+ {
1322
+ "epoch": 2.120724913616811,
1323
+ "grad_norm": 196.0,
1324
+ "learning_rate": 3.023841829811979e-06,
1325
+ "loss": 33.2525,
1326
+ "step": 3760
1327
+ },
1328
+ {
1329
+ "epoch": 2.13200761582399,
1330
+ "grad_norm": 185.0,
1331
+ "learning_rate": 2.9850746268656716e-06,
1332
+ "loss": 32.8658,
1333
+ "step": 3780
1334
+ },
1335
+ {
1336
+ "epoch": 2.1432903180311684,
1337
+ "grad_norm": 211.0,
1338
+ "learning_rate": 2.9463074239193645e-06,
1339
+ "loss": 33.584,
1340
+ "step": 3800
1341
+ },
1342
+ {
1343
+ "epoch": 2.154573020238347,
1344
+ "grad_norm": 177.0,
1345
+ "learning_rate": 2.907540220973057e-06,
1346
+ "loss": 32.7506,
1347
+ "step": 3820
1348
+ },
1349
+ {
1350
+ "epoch": 2.1658557224455257,
1351
+ "grad_norm": 201.0,
1352
+ "learning_rate": 2.86877301802675e-06,
1353
+ "loss": 33.6909,
1354
+ "step": 3840
1355
+ },
1356
+ {
1357
+ "epoch": 2.1771384246527044,
1358
+ "grad_norm": 187.0,
1359
+ "learning_rate": 2.8300058150804423e-06,
1360
+ "loss": 32.9226,
1361
+ "step": 3860
1362
+ },
1363
+ {
1364
+ "epoch": 2.188421126859883,
1365
+ "grad_norm": 186.0,
1366
+ "learning_rate": 2.7912386121341344e-06,
1367
+ "loss": 33.2277,
1368
+ "step": 3880
1369
+ },
1370
+ {
1371
+ "epoch": 2.1997038290670616,
1372
+ "grad_norm": 198.0,
1373
+ "learning_rate": 2.7524714091878273e-06,
1374
+ "loss": 32.8508,
1375
+ "step": 3900
1376
+ },
1377
+ {
1378
+ "epoch": 2.2109865312742403,
1379
+ "grad_norm": 186.0,
1380
+ "learning_rate": 2.7137042062415198e-06,
1381
+ "loss": 33.2497,
1382
+ "step": 3920
1383
+ },
1384
+ {
1385
+ "epoch": 2.222269233481419,
1386
+ "grad_norm": 222.0,
1387
+ "learning_rate": 2.6749370032952127e-06,
1388
+ "loss": 33.5576,
1389
+ "step": 3940
1390
+ },
1391
+ {
1392
+ "epoch": 2.2335519356885976,
1393
+ "grad_norm": 161.0,
1394
+ "learning_rate": 2.636169800348905e-06,
1395
+ "loss": 33.4056,
1396
+ "step": 3960
1397
+ },
1398
+ {
1399
+ "epoch": 2.244834637895776,
1400
+ "grad_norm": 163.0,
1401
+ "learning_rate": 2.597402597402597e-06,
1402
+ "loss": 33.0674,
1403
+ "step": 3980
1404
+ },
1405
+ {
1406
+ "epoch": 2.256117340102955,
1407
+ "grad_norm": 177.0,
1408
+ "learning_rate": 2.55863539445629e-06,
1409
+ "loss": 32.9768,
1410
+ "step": 4000
1411
+ },
1412
+ {
1413
+ "epoch": 2.2674000423101335,
1414
+ "grad_norm": 220.0,
1415
+ "learning_rate": 2.5198681915099826e-06,
1416
+ "loss": 33.1559,
1417
+ "step": 4020
1418
+ },
1419
+ {
1420
+ "epoch": 2.2786827445173117,
1421
+ "grad_norm": 175.0,
1422
+ "learning_rate": 2.481100988563675e-06,
1423
+ "loss": 33.5091,
1424
+ "step": 4040
1425
+ },
1426
+ {
1427
+ "epoch": 2.2899654467244908,
1428
+ "grad_norm": 180.0,
1429
+ "learning_rate": 2.442333785617368e-06,
1430
+ "loss": 33.3984,
1431
+ "step": 4060
1432
+ },
1433
+ {
1434
+ "epoch": 2.301248148931669,
1435
+ "grad_norm": 192.0,
1436
+ "learning_rate": 2.4035665826710604e-06,
1437
+ "loss": 33.3091,
1438
+ "step": 4080
1439
+ },
1440
+ {
1441
+ "epoch": 2.3125308511388476,
1442
+ "grad_norm": 200.0,
1443
+ "learning_rate": 2.3647993797247533e-06,
1444
+ "loss": 33.9978,
1445
+ "step": 4100
1446
+ },
1447
+ {
1448
+ "epoch": 2.3238135533460262,
1449
+ "grad_norm": 202.0,
1450
+ "learning_rate": 2.3260321767784454e-06,
1451
+ "loss": 33.4988,
1452
+ "step": 4120
1453
+ },
1454
+ {
1455
+ "epoch": 2.335096255553205,
1456
+ "grad_norm": 220.0,
1457
+ "learning_rate": 2.2872649738321383e-06,
1458
+ "loss": 32.5648,
1459
+ "step": 4140
1460
+ },
1461
+ {
1462
+ "epoch": 2.3463789577603835,
1463
+ "grad_norm": 188.0,
1464
+ "learning_rate": 2.2484977708858308e-06,
1465
+ "loss": 33.3508,
1466
+ "step": 4160
1467
+ },
1468
+ {
1469
+ "epoch": 2.357661659967562,
1470
+ "grad_norm": 166.0,
1471
+ "learning_rate": 2.2097305679395232e-06,
1472
+ "loss": 33.5085,
1473
+ "step": 4180
1474
+ },
1475
+ {
1476
+ "epoch": 2.368944362174741,
1477
+ "grad_norm": 192.0,
1478
+ "learning_rate": 2.170963364993216e-06,
1479
+ "loss": 33.5222,
1480
+ "step": 4200
1481
+ },
1482
+ {
1483
+ "epoch": 2.3802270643819194,
1484
+ "grad_norm": 168.0,
1485
+ "learning_rate": 2.132196162046908e-06,
1486
+ "loss": 33.5567,
1487
+ "step": 4220
1488
+ },
1489
+ {
1490
+ "epoch": 2.391509766589098,
1491
+ "grad_norm": 189.0,
1492
+ "learning_rate": 2.093428959100601e-06,
1493
+ "loss": 32.6794,
1494
+ "step": 4240
1495
+ },
1496
+ {
1497
+ "epoch": 2.4027924687962767,
1498
+ "grad_norm": 208.0,
1499
+ "learning_rate": 2.0546617561542936e-06,
1500
+ "loss": 33.1244,
1501
+ "step": 4260
1502
+ },
1503
+ {
1504
+ "epoch": 2.4140751710034554,
1505
+ "grad_norm": 222.0,
1506
+ "learning_rate": 2.015894553207986e-06,
1507
+ "loss": 33.2899,
1508
+ "step": 4280
1509
+ },
1510
+ {
1511
+ "epoch": 2.425357873210634,
1512
+ "grad_norm": 165.0,
1513
+ "learning_rate": 1.977127350261679e-06,
1514
+ "loss": 33.3089,
1515
+ "step": 4300
1516
+ },
1517
+ {
1518
+ "epoch": 2.4366405754178126,
1519
+ "grad_norm": 186.0,
1520
+ "learning_rate": 1.9383601473153714e-06,
1521
+ "loss": 33.8634,
1522
+ "step": 4320
1523
+ },
1524
+ {
1525
+ "epoch": 2.4479232776249913,
1526
+ "grad_norm": 189.0,
1527
+ "learning_rate": 1.899592944369064e-06,
1528
+ "loss": 33.6295,
1529
+ "step": 4340
1530
+ },
1531
+ {
1532
+ "epoch": 2.45920597983217,
1533
+ "grad_norm": 194.0,
1534
+ "learning_rate": 1.8608257414227566e-06,
1535
+ "loss": 33.7899,
1536
+ "step": 4360
1537
+ },
1538
+ {
1539
+ "epoch": 2.4704886820393486,
1540
+ "grad_norm": 176.0,
1541
+ "learning_rate": 1.822058538476449e-06,
1542
+ "loss": 33.4224,
1543
+ "step": 4380
1544
+ },
1545
+ {
1546
+ "epoch": 2.481771384246527,
1547
+ "grad_norm": 178.0,
1548
+ "learning_rate": 1.7832913355301418e-06,
1549
+ "loss": 33.2276,
1550
+ "step": 4400
1551
+ },
1552
+ {
1553
+ "epoch": 2.493054086453706,
1554
+ "grad_norm": 204.0,
1555
+ "learning_rate": 1.744524132583834e-06,
1556
+ "loss": 33.7431,
1557
+ "step": 4420
1558
+ },
1559
+ {
1560
+ "epoch": 2.5043367886608845,
1561
+ "grad_norm": 195.0,
1562
+ "learning_rate": 1.7057569296375267e-06,
1563
+ "loss": 33.1986,
1564
+ "step": 4440
1565
+ },
1566
+ {
1567
+ "epoch": 2.5156194908680627,
1568
+ "grad_norm": 191.0,
1569
+ "learning_rate": 1.6669897266912194e-06,
1570
+ "loss": 33.1506,
1571
+ "step": 4460
1572
+ },
1573
+ {
1574
+ "epoch": 2.5269021930752418,
1575
+ "grad_norm": 193.0,
1576
+ "learning_rate": 1.6282225237449121e-06,
1577
+ "loss": 33.1911,
1578
+ "step": 4480
1579
+ },
1580
+ {
1581
+ "epoch": 2.53818489528242,
1582
+ "grad_norm": 230.0,
1583
+ "learning_rate": 1.5894553207986044e-06,
1584
+ "loss": 33.6828,
1585
+ "step": 4500
1586
+ }
1587
+ ],
1588
+ "logging_steps": 20,
1589
+ "max_steps": 5319,
1590
+ "num_input_tokens_seen": 0,
1591
+ "num_train_epochs": 3,
1592
+ "save_steps": 500,
1593
+ "stateful_callbacks": {
1594
+ "TrainerControl": {
1595
+ "args": {
1596
+ "should_epoch_stop": false,
1597
+ "should_evaluate": false,
1598
+ "should_log": false,
1599
+ "should_save": true,
1600
+ "should_training_stop": false
1601
+ },
1602
+ "attributes": {}
1603
+ }
1604
+ },
1605
+ "total_flos": 0.0,
1606
+ "train_batch_size": 2,
1607
+ "trial_name": null,
1608
+ "trial_params": null
1609
+ }
checkpoint-4500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c7a3d84d5c920a1183e32aa8591078ae7fabd64ef9226b2cb2211eab73f936d
3
+ size 5841
checkpoint-5000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fd23e7c8cfb528c50c8b6ca0369595edca17dab3f8f016b6f5aa3c66e380515
3
+ size 1483239819
checkpoint-5000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9272ecf78721fd36556854353c19b93b2188cbe0de13fc1231a7b15b6ad67e3
3
+ size 1014303003
checkpoint-5000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
3
+ size 14645
checkpoint-5000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2707ff35a95e38bb70e044a72f454dd937c1cbeb2fdb8d28eacb8bea4d3bf599
3
+ size 1465
checkpoint-5000/trainer_state.json ADDED
@@ -0,0 +1,1784 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.8202524504618856,
6
+ "eval_steps": 500,
7
+ "global_step": 5000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.01128270220717862,
14
+ "grad_norm": 684.0,
15
+ "learning_rate": 1.1875e-06,
16
+ "loss": 42.923,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 0.02256540441435724,
21
+ "grad_norm": 378.0,
22
+ "learning_rate": 2.4375e-06,
23
+ "loss": 41.9073,
24
+ "step": 40
25
+ },
26
+ {
27
+ "epoch": 0.03384810662153586,
28
+ "grad_norm": 322.0,
29
+ "learning_rate": 3.6875000000000007e-06,
30
+ "loss": 39.9877,
31
+ "step": 60
32
+ },
33
+ {
34
+ "epoch": 0.04513080882871448,
35
+ "grad_norm": 280.0,
36
+ "learning_rate": 4.937500000000001e-06,
37
+ "loss": 38.0747,
38
+ "step": 80
39
+ },
40
+ {
41
+ "epoch": 0.056413511035893094,
42
+ "grad_norm": 1328.0,
43
+ "learning_rate": 6.1875000000000005e-06,
44
+ "loss": 36.2999,
45
+ "step": 100
46
+ },
47
+ {
48
+ "epoch": 0.06769621324307172,
49
+ "grad_norm": 212.0,
50
+ "learning_rate": 7.437500000000001e-06,
51
+ "loss": 35.0646,
52
+ "step": 120
53
+ },
54
+ {
55
+ "epoch": 0.07897891545025033,
56
+ "grad_norm": 208.0,
57
+ "learning_rate": 8.687500000000001e-06,
58
+ "loss": 34.4917,
59
+ "step": 140
60
+ },
61
+ {
62
+ "epoch": 0.09026161765742896,
63
+ "grad_norm": 180.0,
64
+ "learning_rate": 9.937500000000001e-06,
65
+ "loss": 34.5205,
66
+ "step": 160
67
+ },
68
+ {
69
+ "epoch": 0.10154431986460757,
70
+ "grad_norm": 213.0,
71
+ "learning_rate": 9.96317115720101e-06,
72
+ "loss": 33.3244,
73
+ "step": 180
74
+ },
75
+ {
76
+ "epoch": 0.11282702207178619,
77
+ "grad_norm": 174.0,
78
+ "learning_rate": 9.9244039542547e-06,
79
+ "loss": 33.6509,
80
+ "step": 200
81
+ },
82
+ {
83
+ "epoch": 0.12410972427896481,
84
+ "grad_norm": 234.0,
85
+ "learning_rate": 9.885636751308394e-06,
86
+ "loss": 34.1064,
87
+ "step": 220
88
+ },
89
+ {
90
+ "epoch": 0.13539242648614344,
91
+ "grad_norm": 176.0,
92
+ "learning_rate": 9.846869548362087e-06,
93
+ "loss": 34.0945,
94
+ "step": 240
95
+ },
96
+ {
97
+ "epoch": 0.14667512869332205,
98
+ "grad_norm": 222.0,
99
+ "learning_rate": 9.80810234541578e-06,
100
+ "loss": 33.8671,
101
+ "step": 260
102
+ },
103
+ {
104
+ "epoch": 0.15795783090050067,
105
+ "grad_norm": 164.0,
106
+ "learning_rate": 9.769335142469472e-06,
107
+ "loss": 33.4257,
108
+ "step": 280
109
+ },
110
+ {
111
+ "epoch": 0.16924053310767928,
112
+ "grad_norm": 185.0,
113
+ "learning_rate": 9.730567939523164e-06,
114
+ "loss": 33.4832,
115
+ "step": 300
116
+ },
117
+ {
118
+ "epoch": 0.18052323531485792,
119
+ "grad_norm": 188.0,
120
+ "learning_rate": 9.691800736576857e-06,
121
+ "loss": 33.4079,
122
+ "step": 320
123
+ },
124
+ {
125
+ "epoch": 0.19180593752203653,
126
+ "grad_norm": 195.0,
127
+ "learning_rate": 9.65303353363055e-06,
128
+ "loss": 34.1975,
129
+ "step": 340
130
+ },
131
+ {
132
+ "epoch": 0.20308863972921515,
133
+ "grad_norm": 186.0,
134
+ "learning_rate": 9.614266330684242e-06,
135
+ "loss": 33.3613,
136
+ "step": 360
137
+ },
138
+ {
139
+ "epoch": 0.21437134193639376,
140
+ "grad_norm": 172.0,
141
+ "learning_rate": 9.575499127737934e-06,
142
+ "loss": 32.6162,
143
+ "step": 380
144
+ },
145
+ {
146
+ "epoch": 0.22565404414357237,
147
+ "grad_norm": 170.0,
148
+ "learning_rate": 9.536731924791627e-06,
149
+ "loss": 33.3925,
150
+ "step": 400
151
+ },
152
+ {
153
+ "epoch": 0.23693674635075102,
154
+ "grad_norm": 168.0,
155
+ "learning_rate": 9.49796472184532e-06,
156
+ "loss": 33.4435,
157
+ "step": 420
158
+ },
159
+ {
160
+ "epoch": 0.24821944855792963,
161
+ "grad_norm": 197.0,
162
+ "learning_rate": 9.459197518899013e-06,
163
+ "loss": 32.9941,
164
+ "step": 440
165
+ },
166
+ {
167
+ "epoch": 0.25950215076510824,
168
+ "grad_norm": 190.0,
169
+ "learning_rate": 9.420430315952704e-06,
170
+ "loss": 33.2245,
171
+ "step": 460
172
+ },
173
+ {
174
+ "epoch": 0.2707848529722869,
175
+ "grad_norm": 185.0,
176
+ "learning_rate": 9.381663113006397e-06,
177
+ "loss": 33.2802,
178
+ "step": 480
179
+ },
180
+ {
181
+ "epoch": 0.28206755517946547,
182
+ "grad_norm": 201.0,
183
+ "learning_rate": 9.34289591006009e-06,
184
+ "loss": 33.3563,
185
+ "step": 500
186
+ },
187
+ {
188
+ "epoch": 0.2933502573866441,
189
+ "grad_norm": 160.0,
190
+ "learning_rate": 9.304128707113782e-06,
191
+ "loss": 32.8094,
192
+ "step": 520
193
+ },
194
+ {
195
+ "epoch": 0.3046329595938227,
196
+ "grad_norm": 171.0,
197
+ "learning_rate": 9.265361504167476e-06,
198
+ "loss": 33.967,
199
+ "step": 540
200
+ },
201
+ {
202
+ "epoch": 0.31591566180100134,
203
+ "grad_norm": 185.0,
204
+ "learning_rate": 9.226594301221168e-06,
205
+ "loss": 33.9071,
206
+ "step": 560
207
+ },
208
+ {
209
+ "epoch": 0.32719836400818,
210
+ "grad_norm": 168.0,
211
+ "learning_rate": 9.18782709827486e-06,
212
+ "loss": 33.5103,
213
+ "step": 580
214
+ },
215
+ {
216
+ "epoch": 0.33848106621535856,
217
+ "grad_norm": 185.0,
218
+ "learning_rate": 9.149059895328553e-06,
219
+ "loss": 33.2943,
220
+ "step": 600
221
+ },
222
+ {
223
+ "epoch": 0.3497637684225372,
224
+ "grad_norm": 235.0,
225
+ "learning_rate": 9.110292692382246e-06,
226
+ "loss": 33.8674,
227
+ "step": 620
228
+ },
229
+ {
230
+ "epoch": 0.36104647062971584,
231
+ "grad_norm": 171.0,
232
+ "learning_rate": 9.071525489435938e-06,
233
+ "loss": 34.1437,
234
+ "step": 640
235
+ },
236
+ {
237
+ "epoch": 0.37232917283689443,
238
+ "grad_norm": 176.0,
239
+ "learning_rate": 9.03275828648963e-06,
240
+ "loss": 32.9577,
241
+ "step": 660
242
+ },
243
+ {
244
+ "epoch": 0.38361187504407307,
245
+ "grad_norm": 179.0,
246
+ "learning_rate": 8.993991083543323e-06,
247
+ "loss": 33.5755,
248
+ "step": 680
249
+ },
250
+ {
251
+ "epoch": 0.39489457725125165,
252
+ "grad_norm": 187.0,
253
+ "learning_rate": 8.955223880597016e-06,
254
+ "loss": 34.03,
255
+ "step": 700
256
+ },
257
+ {
258
+ "epoch": 0.4061772794584303,
259
+ "grad_norm": 175.0,
260
+ "learning_rate": 8.916456677650708e-06,
261
+ "loss": 34.0341,
262
+ "step": 720
263
+ },
264
+ {
265
+ "epoch": 0.41745998166560894,
266
+ "grad_norm": 184.0,
267
+ "learning_rate": 8.8776894747044e-06,
268
+ "loss": 34.1199,
269
+ "step": 740
270
+ },
271
+ {
272
+ "epoch": 0.4287426838727875,
273
+ "grad_norm": 214.0,
274
+ "learning_rate": 8.838922271758093e-06,
275
+ "loss": 34.5299,
276
+ "step": 760
277
+ },
278
+ {
279
+ "epoch": 0.44002538607996616,
280
+ "grad_norm": 187.0,
281
+ "learning_rate": 8.800155068811787e-06,
282
+ "loss": 33.6687,
283
+ "step": 780
284
+ },
285
+ {
286
+ "epoch": 0.45130808828714475,
287
+ "grad_norm": 207.0,
288
+ "learning_rate": 8.761387865865478e-06,
289
+ "loss": 33.4913,
290
+ "step": 800
291
+ },
292
+ {
293
+ "epoch": 0.4625907904943234,
294
+ "grad_norm": 199.0,
295
+ "learning_rate": 8.72262066291917e-06,
296
+ "loss": 34.6043,
297
+ "step": 820
298
+ },
299
+ {
300
+ "epoch": 0.47387349270150203,
301
+ "grad_norm": 308.0,
302
+ "learning_rate": 8.683853459972865e-06,
303
+ "loss": 34.1107,
304
+ "step": 840
305
+ },
306
+ {
307
+ "epoch": 0.4851561949086806,
308
+ "grad_norm": 219.0,
309
+ "learning_rate": 8.645086257026555e-06,
310
+ "loss": 33.5659,
311
+ "step": 860
312
+ },
313
+ {
314
+ "epoch": 0.49643889711585926,
315
+ "grad_norm": 184.0,
316
+ "learning_rate": 8.60631905408025e-06,
317
+ "loss": 34.6702,
318
+ "step": 880
319
+ },
320
+ {
321
+ "epoch": 0.5077215993230378,
322
+ "grad_norm": 188.0,
323
+ "learning_rate": 8.567551851133942e-06,
324
+ "loss": 33.9021,
325
+ "step": 900
326
+ },
327
+ {
328
+ "epoch": 0.5190043015302165,
329
+ "grad_norm": 189.0,
330
+ "learning_rate": 8.528784648187633e-06,
331
+ "loss": 33.8139,
332
+ "step": 920
333
+ },
334
+ {
335
+ "epoch": 0.5302870037373951,
336
+ "grad_norm": 202.0,
337
+ "learning_rate": 8.490017445241327e-06,
338
+ "loss": 33.9562,
339
+ "step": 940
340
+ },
341
+ {
342
+ "epoch": 0.5415697059445738,
343
+ "grad_norm": 184.0,
344
+ "learning_rate": 8.45125024229502e-06,
345
+ "loss": 34.1304,
346
+ "step": 960
347
+ },
348
+ {
349
+ "epoch": 0.5528524081517523,
350
+ "grad_norm": 210.0,
351
+ "learning_rate": 8.412483039348712e-06,
352
+ "loss": 34.3385,
353
+ "step": 980
354
+ },
355
+ {
356
+ "epoch": 0.5641351103589309,
357
+ "grad_norm": 167.0,
358
+ "learning_rate": 8.373715836402404e-06,
359
+ "loss": 34.2957,
360
+ "step": 1000
361
+ },
362
+ {
363
+ "epoch": 0.5754178125661096,
364
+ "grad_norm": 197.0,
365
+ "learning_rate": 8.334948633456097e-06,
366
+ "loss": 34.701,
367
+ "step": 1020
368
+ },
369
+ {
370
+ "epoch": 0.5867005147732882,
371
+ "grad_norm": 220.0,
372
+ "learning_rate": 8.29618143050979e-06,
373
+ "loss": 34.1251,
374
+ "step": 1040
375
+ },
376
+ {
377
+ "epoch": 0.5979832169804669,
378
+ "grad_norm": 199.0,
379
+ "learning_rate": 8.257414227563482e-06,
380
+ "loss": 34.2395,
381
+ "step": 1060
382
+ },
383
+ {
384
+ "epoch": 0.6092659191876454,
385
+ "grad_norm": 210.0,
386
+ "learning_rate": 8.218647024617174e-06,
387
+ "loss": 33.7562,
388
+ "step": 1080
389
+ },
390
+ {
391
+ "epoch": 0.620548621394824,
392
+ "grad_norm": 213.0,
393
+ "learning_rate": 8.179879821670867e-06,
394
+ "loss": 35.2014,
395
+ "step": 1100
396
+ },
397
+ {
398
+ "epoch": 0.6318313236020027,
399
+ "grad_norm": 214.0,
400
+ "learning_rate": 8.14111261872456e-06,
401
+ "loss": 33.6772,
402
+ "step": 1120
403
+ },
404
+ {
405
+ "epoch": 0.6431140258091813,
406
+ "grad_norm": 220.0,
407
+ "learning_rate": 8.102345415778252e-06,
408
+ "loss": 34.0573,
409
+ "step": 1140
410
+ },
411
+ {
412
+ "epoch": 0.65439672801636,
413
+ "grad_norm": 162.0,
414
+ "learning_rate": 8.063578212831944e-06,
415
+ "loss": 34.1778,
416
+ "step": 1160
417
+ },
418
+ {
419
+ "epoch": 0.6656794302235386,
420
+ "grad_norm": 171.0,
421
+ "learning_rate": 8.024811009885637e-06,
422
+ "loss": 34.7704,
423
+ "step": 1180
424
+ },
425
+ {
426
+ "epoch": 0.6769621324307171,
427
+ "grad_norm": 192.0,
428
+ "learning_rate": 7.98604380693933e-06,
429
+ "loss": 34.5073,
430
+ "step": 1200
431
+ },
432
+ {
433
+ "epoch": 0.6882448346378958,
434
+ "grad_norm": 199.0,
435
+ "learning_rate": 7.947276603993023e-06,
436
+ "loss": 35.1462,
437
+ "step": 1220
438
+ },
439
+ {
440
+ "epoch": 0.6995275368450744,
441
+ "grad_norm": 194.0,
442
+ "learning_rate": 7.908509401046716e-06,
443
+ "loss": 35.0324,
444
+ "step": 1240
445
+ },
446
+ {
447
+ "epoch": 0.710810239052253,
448
+ "grad_norm": 180.0,
449
+ "learning_rate": 7.869742198100407e-06,
450
+ "loss": 34.4355,
451
+ "step": 1260
452
+ },
453
+ {
454
+ "epoch": 0.7220929412594317,
455
+ "grad_norm": 171.0,
456
+ "learning_rate": 7.8309749951541e-06,
457
+ "loss": 34.3484,
458
+ "step": 1280
459
+ },
460
+ {
461
+ "epoch": 0.7333756434666102,
462
+ "grad_norm": 234.0,
463
+ "learning_rate": 7.792207792207793e-06,
464
+ "loss": 34.3537,
465
+ "step": 1300
466
+ },
467
+ {
468
+ "epoch": 0.7446583456737889,
469
+ "grad_norm": 217.0,
470
+ "learning_rate": 7.753440589261486e-06,
471
+ "loss": 34.4467,
472
+ "step": 1320
473
+ },
474
+ {
475
+ "epoch": 0.7559410478809675,
476
+ "grad_norm": 183.0,
477
+ "learning_rate": 7.714673386315178e-06,
478
+ "loss": 34.5935,
479
+ "step": 1340
480
+ },
481
+ {
482
+ "epoch": 0.7672237500881461,
483
+ "grad_norm": 167.0,
484
+ "learning_rate": 7.67590618336887e-06,
485
+ "loss": 34.1833,
486
+ "step": 1360
487
+ },
488
+ {
489
+ "epoch": 0.7785064522953248,
490
+ "grad_norm": 182.0,
491
+ "learning_rate": 7.637138980422563e-06,
492
+ "loss": 34.5052,
493
+ "step": 1380
494
+ },
495
+ {
496
+ "epoch": 0.7897891545025033,
497
+ "grad_norm": 170.0,
498
+ "learning_rate": 7.598371777476256e-06,
499
+ "loss": 34.5334,
500
+ "step": 1400
501
+ },
502
+ {
503
+ "epoch": 0.801071856709682,
504
+ "grad_norm": 181.0,
505
+ "learning_rate": 7.559604574529948e-06,
506
+ "loss": 34.1411,
507
+ "step": 1420
508
+ },
509
+ {
510
+ "epoch": 0.8123545589168606,
511
+ "grad_norm": 163.0,
512
+ "learning_rate": 7.5208373715836415e-06,
513
+ "loss": 34.7683,
514
+ "step": 1440
515
+ },
516
+ {
517
+ "epoch": 0.8236372611240392,
518
+ "grad_norm": 176.0,
519
+ "learning_rate": 7.482070168637333e-06,
520
+ "loss": 34.7674,
521
+ "step": 1460
522
+ },
523
+ {
524
+ "epoch": 0.8349199633312179,
525
+ "grad_norm": 165.0,
526
+ "learning_rate": 7.4433029656910264e-06,
527
+ "loss": 34.7617,
528
+ "step": 1480
529
+ },
530
+ {
531
+ "epoch": 0.8462026655383964,
532
+ "grad_norm": 194.0,
533
+ "learning_rate": 7.404535762744719e-06,
534
+ "loss": 34.7591,
535
+ "step": 1500
536
+ },
537
+ {
538
+ "epoch": 0.857485367745575,
539
+ "grad_norm": 175.0,
540
+ "learning_rate": 7.3657685597984105e-06,
541
+ "loss": 34.0827,
542
+ "step": 1520
543
+ },
544
+ {
545
+ "epoch": 0.8687680699527537,
546
+ "grad_norm": 179.0,
547
+ "learning_rate": 7.327001356852104e-06,
548
+ "loss": 34.5944,
549
+ "step": 1540
550
+ },
551
+ {
552
+ "epoch": 0.8800507721599323,
553
+ "grad_norm": 198.0,
554
+ "learning_rate": 7.288234153905796e-06,
555
+ "loss": 35.1967,
556
+ "step": 1560
557
+ },
558
+ {
559
+ "epoch": 0.891333474367111,
560
+ "grad_norm": 192.0,
561
+ "learning_rate": 7.249466950959488e-06,
562
+ "loss": 35.0658,
563
+ "step": 1580
564
+ },
565
+ {
566
+ "epoch": 0.9026161765742895,
567
+ "grad_norm": 207.0,
568
+ "learning_rate": 7.210699748013181e-06,
569
+ "loss": 34.9624,
570
+ "step": 1600
571
+ },
572
+ {
573
+ "epoch": 0.9138988787814681,
574
+ "grad_norm": 195.0,
575
+ "learning_rate": 7.171932545066874e-06,
576
+ "loss": 34.5503,
577
+ "step": 1620
578
+ },
579
+ {
580
+ "epoch": 0.9251815809886468,
581
+ "grad_norm": 187.0,
582
+ "learning_rate": 7.133165342120567e-06,
583
+ "loss": 34.6947,
584
+ "step": 1640
585
+ },
586
+ {
587
+ "epoch": 0.9364642831958254,
588
+ "grad_norm": 178.0,
589
+ "learning_rate": 7.094398139174259e-06,
590
+ "loss": 34.7273,
591
+ "step": 1660
592
+ },
593
+ {
594
+ "epoch": 0.9477469854030041,
595
+ "grad_norm": 195.0,
596
+ "learning_rate": 7.055630936227952e-06,
597
+ "loss": 35.1698,
598
+ "step": 1680
599
+ },
600
+ {
601
+ "epoch": 0.9590296876101826,
602
+ "grad_norm": 194.0,
603
+ "learning_rate": 7.0168637332816445e-06,
604
+ "loss": 34.8608,
605
+ "step": 1700
606
+ },
607
+ {
608
+ "epoch": 0.9703123898173612,
609
+ "grad_norm": 209.0,
610
+ "learning_rate": 6.978096530335336e-06,
611
+ "loss": 34.3997,
612
+ "step": 1720
613
+ },
614
+ {
615
+ "epoch": 0.9815950920245399,
616
+ "grad_norm": 142.0,
617
+ "learning_rate": 6.9393293273890295e-06,
618
+ "loss": 34.856,
619
+ "step": 1740
620
+ },
621
+ {
622
+ "epoch": 0.9928777942317185,
623
+ "grad_norm": 186.0,
624
+ "learning_rate": 6.900562124442722e-06,
625
+ "loss": 34.3359,
626
+ "step": 1760
627
+ },
628
+ {
629
+ "epoch": 1.0039489457725126,
630
+ "grad_norm": 169.0,
631
+ "learning_rate": 6.8617949214964145e-06,
632
+ "loss": 33.62,
633
+ "step": 1780
634
+ },
635
+ {
636
+ "epoch": 1.0152316479796912,
637
+ "grad_norm": 189.0,
638
+ "learning_rate": 6.823027718550107e-06,
639
+ "loss": 33.4374,
640
+ "step": 1800
641
+ },
642
+ {
643
+ "epoch": 1.0265143501868697,
644
+ "grad_norm": 191.0,
645
+ "learning_rate": 6.7842605156038e-06,
646
+ "loss": 32.8082,
647
+ "step": 1820
648
+ },
649
+ {
650
+ "epoch": 1.0377970523940483,
651
+ "grad_norm": 151.0,
652
+ "learning_rate": 6.745493312657493e-06,
653
+ "loss": 33.2524,
654
+ "step": 1840
655
+ },
656
+ {
657
+ "epoch": 1.049079754601227,
658
+ "grad_norm": 153.0,
659
+ "learning_rate": 6.706726109711184e-06,
660
+ "loss": 32.7946,
661
+ "step": 1860
662
+ },
663
+ {
664
+ "epoch": 1.0603624568084056,
665
+ "grad_norm": 190.0,
666
+ "learning_rate": 6.667958906764878e-06,
667
+ "loss": 34.0579,
668
+ "step": 1880
669
+ },
670
+ {
671
+ "epoch": 1.0716451590155842,
672
+ "grad_norm": 169.0,
673
+ "learning_rate": 6.62919170381857e-06,
674
+ "loss": 33.6604,
675
+ "step": 1900
676
+ },
677
+ {
678
+ "epoch": 1.0829278612227629,
679
+ "grad_norm": 203.0,
680
+ "learning_rate": 6.590424500872263e-06,
681
+ "loss": 33.566,
682
+ "step": 1920
683
+ },
684
+ {
685
+ "epoch": 1.0942105634299415,
686
+ "grad_norm": 166.0,
687
+ "learning_rate": 6.551657297925955e-06,
688
+ "loss": 32.8621,
689
+ "step": 1940
690
+ },
691
+ {
692
+ "epoch": 1.1054932656371201,
693
+ "grad_norm": 190.0,
694
+ "learning_rate": 6.5128900949796484e-06,
695
+ "loss": 32.7915,
696
+ "step": 1960
697
+ },
698
+ {
699
+ "epoch": 1.1167759678442988,
700
+ "grad_norm": 159.0,
701
+ "learning_rate": 6.47412289203334e-06,
702
+ "loss": 32.8263,
703
+ "step": 1980
704
+ },
705
+ {
706
+ "epoch": 1.1280586700514774,
707
+ "grad_norm": 213.0,
708
+ "learning_rate": 6.4353556890870326e-06,
709
+ "loss": 33.4649,
710
+ "step": 2000
711
+ },
712
+ {
713
+ "epoch": 1.1393413722586558,
714
+ "grad_norm": 170.0,
715
+ "learning_rate": 6.396588486140726e-06,
716
+ "loss": 33.0993,
717
+ "step": 2020
718
+ },
719
+ {
720
+ "epoch": 1.1506240744658345,
721
+ "grad_norm": 178.0,
722
+ "learning_rate": 6.3578212831944175e-06,
723
+ "loss": 32.8403,
724
+ "step": 2040
725
+ },
726
+ {
727
+ "epoch": 1.1619067766730131,
728
+ "grad_norm": 192.0,
729
+ "learning_rate": 6.31905408024811e-06,
730
+ "loss": 33.212,
731
+ "step": 2060
732
+ },
733
+ {
734
+ "epoch": 1.1731894788801918,
735
+ "grad_norm": 177.0,
736
+ "learning_rate": 6.280286877301803e-06,
737
+ "loss": 32.9688,
738
+ "step": 2080
739
+ },
740
+ {
741
+ "epoch": 1.1844721810873704,
742
+ "grad_norm": 176.0,
743
+ "learning_rate": 6.241519674355496e-06,
744
+ "loss": 33.0461,
745
+ "step": 2100
746
+ },
747
+ {
748
+ "epoch": 1.195754883294549,
749
+ "grad_norm": 191.0,
750
+ "learning_rate": 6.202752471409188e-06,
751
+ "loss": 33.4505,
752
+ "step": 2120
753
+ },
754
+ {
755
+ "epoch": 1.2070375855017277,
756
+ "grad_norm": 165.0,
757
+ "learning_rate": 6.163985268462881e-06,
758
+ "loss": 33.6436,
759
+ "step": 2140
760
+ },
761
+ {
762
+ "epoch": 1.2183202877089063,
763
+ "grad_norm": 177.0,
764
+ "learning_rate": 6.125218065516574e-06,
765
+ "loss": 32.9951,
766
+ "step": 2160
767
+ },
768
+ {
769
+ "epoch": 1.229602989916085,
770
+ "grad_norm": 181.0,
771
+ "learning_rate": 6.086450862570266e-06,
772
+ "loss": 34.0142,
773
+ "step": 2180
774
+ },
775
+ {
776
+ "epoch": 1.2408856921232636,
777
+ "grad_norm": 174.0,
778
+ "learning_rate": 6.047683659623958e-06,
779
+ "loss": 33.6973,
780
+ "step": 2200
781
+ },
782
+ {
783
+ "epoch": 1.2521683943304422,
784
+ "grad_norm": 160.0,
785
+ "learning_rate": 6.0089164566776515e-06,
786
+ "loss": 32.4556,
787
+ "step": 2220
788
+ },
789
+ {
790
+ "epoch": 1.2634510965376209,
791
+ "grad_norm": 165.0,
792
+ "learning_rate": 5.970149253731343e-06,
793
+ "loss": 33.3473,
794
+ "step": 2240
795
+ },
796
+ {
797
+ "epoch": 1.2747337987447993,
798
+ "grad_norm": 192.0,
799
+ "learning_rate": 5.9313820507850365e-06,
800
+ "loss": 32.9415,
801
+ "step": 2260
802
+ },
803
+ {
804
+ "epoch": 1.286016500951978,
805
+ "grad_norm": 169.0,
806
+ "learning_rate": 5.892614847838729e-06,
807
+ "loss": 33.7312,
808
+ "step": 2280
809
+ },
810
+ {
811
+ "epoch": 1.2972992031591566,
812
+ "grad_norm": 172.0,
813
+ "learning_rate": 5.853847644892422e-06,
814
+ "loss": 33.2523,
815
+ "step": 2300
816
+ },
817
+ {
818
+ "epoch": 1.3085819053663352,
819
+ "grad_norm": 166.0,
820
+ "learning_rate": 5.815080441946114e-06,
821
+ "loss": 33.4629,
822
+ "step": 2320
823
+ },
824
+ {
825
+ "epoch": 1.3198646075735139,
826
+ "grad_norm": 220.0,
827
+ "learning_rate": 5.776313238999806e-06,
828
+ "loss": 33.6943,
829
+ "step": 2340
830
+ },
831
+ {
832
+ "epoch": 1.3311473097806925,
833
+ "grad_norm": 163.0,
834
+ "learning_rate": 5.7375460360535e-06,
835
+ "loss": 33.2026,
836
+ "step": 2360
837
+ },
838
+ {
839
+ "epoch": 1.3424300119878712,
840
+ "grad_norm": 227.0,
841
+ "learning_rate": 5.698778833107191e-06,
842
+ "loss": 33.3166,
843
+ "step": 2380
844
+ },
845
+ {
846
+ "epoch": 1.3537127141950498,
847
+ "grad_norm": 198.0,
848
+ "learning_rate": 5.660011630160885e-06,
849
+ "loss": 33.5236,
850
+ "step": 2400
851
+ },
852
+ {
853
+ "epoch": 1.3649954164022282,
854
+ "grad_norm": 178.0,
855
+ "learning_rate": 5.621244427214577e-06,
856
+ "loss": 33.3746,
857
+ "step": 2420
858
+ },
859
+ {
860
+ "epoch": 1.3762781186094069,
861
+ "grad_norm": 182.0,
862
+ "learning_rate": 5.582477224268269e-06,
863
+ "loss": 33.2293,
864
+ "step": 2440
865
+ },
866
+ {
867
+ "epoch": 1.3875608208165855,
868
+ "grad_norm": 232.0,
869
+ "learning_rate": 5.543710021321962e-06,
870
+ "loss": 34.0862,
871
+ "step": 2460
872
+ },
873
+ {
874
+ "epoch": 1.3988435230237641,
875
+ "grad_norm": 175.0,
876
+ "learning_rate": 5.5049428183756546e-06,
877
+ "loss": 33.4116,
878
+ "step": 2480
879
+ },
880
+ {
881
+ "epoch": 1.4101262252309428,
882
+ "grad_norm": 198.0,
883
+ "learning_rate": 5.466175615429348e-06,
884
+ "loss": 32.8442,
885
+ "step": 2500
886
+ },
887
+ {
888
+ "epoch": 1.4214089274381214,
889
+ "grad_norm": 162.0,
890
+ "learning_rate": 5.4274084124830395e-06,
891
+ "loss": 33.7111,
892
+ "step": 2520
893
+ },
894
+ {
895
+ "epoch": 1.4326916296453,
896
+ "grad_norm": 208.0,
897
+ "learning_rate": 5.388641209536732e-06,
898
+ "loss": 33.0033,
899
+ "step": 2540
900
+ },
901
+ {
902
+ "epoch": 1.4439743318524787,
903
+ "grad_norm": 192.0,
904
+ "learning_rate": 5.349874006590425e-06,
905
+ "loss": 33.8201,
906
+ "step": 2560
907
+ },
908
+ {
909
+ "epoch": 1.4552570340596573,
910
+ "grad_norm": 169.0,
911
+ "learning_rate": 5.311106803644117e-06,
912
+ "loss": 32.9213,
913
+ "step": 2580
914
+ },
915
+ {
916
+ "epoch": 1.466539736266836,
917
+ "grad_norm": 181.0,
918
+ "learning_rate": 5.27233960069781e-06,
919
+ "loss": 33.9638,
920
+ "step": 2600
921
+ },
922
+ {
923
+ "epoch": 1.4778224384740146,
924
+ "grad_norm": 173.0,
925
+ "learning_rate": 5.233572397751503e-06,
926
+ "loss": 33.5811,
927
+ "step": 2620
928
+ },
929
+ {
930
+ "epoch": 1.4891051406811933,
931
+ "grad_norm": 190.0,
932
+ "learning_rate": 5.194805194805194e-06,
933
+ "loss": 33.8197,
934
+ "step": 2640
935
+ },
936
+ {
937
+ "epoch": 1.500387842888372,
938
+ "grad_norm": 197.0,
939
+ "learning_rate": 5.156037991858888e-06,
940
+ "loss": 33.6394,
941
+ "step": 2660
942
+ },
943
+ {
944
+ "epoch": 1.5116705450955505,
945
+ "grad_norm": 290.0,
946
+ "learning_rate": 5.11727078891258e-06,
947
+ "loss": 33.2235,
948
+ "step": 2680
949
+ },
950
+ {
951
+ "epoch": 1.522953247302729,
952
+ "grad_norm": 148.0,
953
+ "learning_rate": 5.0785035859662735e-06,
954
+ "loss": 33.6943,
955
+ "step": 2700
956
+ },
957
+ {
958
+ "epoch": 1.5342359495099076,
959
+ "grad_norm": 183.0,
960
+ "learning_rate": 5.039736383019965e-06,
961
+ "loss": 33.5758,
962
+ "step": 2720
963
+ },
964
+ {
965
+ "epoch": 1.5455186517170862,
966
+ "grad_norm": 175.0,
967
+ "learning_rate": 5.0009691800736585e-06,
968
+ "loss": 34.077,
969
+ "step": 2740
970
+ },
971
+ {
972
+ "epoch": 1.5568013539242649,
973
+ "grad_norm": 178.0,
974
+ "learning_rate": 4.96220197712735e-06,
975
+ "loss": 33.2421,
976
+ "step": 2760
977
+ },
978
+ {
979
+ "epoch": 1.5680840561314435,
980
+ "grad_norm": 169.0,
981
+ "learning_rate": 4.9234347741810434e-06,
982
+ "loss": 34.0267,
983
+ "step": 2780
984
+ },
985
+ {
986
+ "epoch": 1.579366758338622,
987
+ "grad_norm": 171.0,
988
+ "learning_rate": 4.884667571234736e-06,
989
+ "loss": 33.5599,
990
+ "step": 2800
991
+ },
992
+ {
993
+ "epoch": 1.5906494605458006,
994
+ "grad_norm": 206.0,
995
+ "learning_rate": 4.845900368288428e-06,
996
+ "loss": 33.7535,
997
+ "step": 2820
998
+ },
999
+ {
1000
+ "epoch": 1.6019321627529792,
1001
+ "grad_norm": 168.0,
1002
+ "learning_rate": 4.807133165342121e-06,
1003
+ "loss": 33.4231,
1004
+ "step": 2840
1005
+ },
1006
+ {
1007
+ "epoch": 1.6132148649601579,
1008
+ "grad_norm": 208.0,
1009
+ "learning_rate": 4.768365962395813e-06,
1010
+ "loss": 33.1695,
1011
+ "step": 2860
1012
+ },
1013
+ {
1014
+ "epoch": 1.6244975671673365,
1015
+ "grad_norm": 213.0,
1016
+ "learning_rate": 4.729598759449507e-06,
1017
+ "loss": 33.2739,
1018
+ "step": 2880
1019
+ },
1020
+ {
1021
+ "epoch": 1.6357802693745152,
1022
+ "grad_norm": 177.0,
1023
+ "learning_rate": 4.690831556503198e-06,
1024
+ "loss": 33.3967,
1025
+ "step": 2900
1026
+ },
1027
+ {
1028
+ "epoch": 1.6470629715816938,
1029
+ "grad_norm": 234.0,
1030
+ "learning_rate": 4.652064353556891e-06,
1031
+ "loss": 34.2787,
1032
+ "step": 2920
1033
+ },
1034
+ {
1035
+ "epoch": 1.6583456737888724,
1036
+ "grad_norm": 163.0,
1037
+ "learning_rate": 4.613297150610584e-06,
1038
+ "loss": 34.1793,
1039
+ "step": 2940
1040
+ },
1041
+ {
1042
+ "epoch": 1.669628375996051,
1043
+ "grad_norm": 192.0,
1044
+ "learning_rate": 4.574529947664277e-06,
1045
+ "loss": 33.67,
1046
+ "step": 2960
1047
+ },
1048
+ {
1049
+ "epoch": 1.6809110782032297,
1050
+ "grad_norm": 188.0,
1051
+ "learning_rate": 4.535762744717969e-06,
1052
+ "loss": 34.1299,
1053
+ "step": 2980
1054
+ },
1055
+ {
1056
+ "epoch": 1.6921937804104084,
1057
+ "grad_norm": 210.0,
1058
+ "learning_rate": 4.4969955417716615e-06,
1059
+ "loss": 33.6063,
1060
+ "step": 3000
1061
+ },
1062
+ {
1063
+ "epoch": 1.703476482617587,
1064
+ "grad_norm": 222.0,
1065
+ "learning_rate": 4.458228338825354e-06,
1066
+ "loss": 33.864,
1067
+ "step": 3020
1068
+ },
1069
+ {
1070
+ "epoch": 1.7147591848247656,
1071
+ "grad_norm": 167.0,
1072
+ "learning_rate": 4.4194611358790465e-06,
1073
+ "loss": 33.9385,
1074
+ "step": 3040
1075
+ },
1076
+ {
1077
+ "epoch": 1.7260418870319443,
1078
+ "grad_norm": 201.0,
1079
+ "learning_rate": 4.380693932932739e-06,
1080
+ "loss": 33.4324,
1081
+ "step": 3060
1082
+ },
1083
+ {
1084
+ "epoch": 1.737324589239123,
1085
+ "grad_norm": 171.0,
1086
+ "learning_rate": 4.341926729986432e-06,
1087
+ "loss": 33.6625,
1088
+ "step": 3080
1089
+ },
1090
+ {
1091
+ "epoch": 1.7486072914463013,
1092
+ "grad_norm": 166.0,
1093
+ "learning_rate": 4.303159527040125e-06,
1094
+ "loss": 33.1414,
1095
+ "step": 3100
1096
+ },
1097
+ {
1098
+ "epoch": 1.75988999365348,
1099
+ "grad_norm": 151.0,
1100
+ "learning_rate": 4.264392324093816e-06,
1101
+ "loss": 34.045,
1102
+ "step": 3120
1103
+ },
1104
+ {
1105
+ "epoch": 1.7711726958606586,
1106
+ "grad_norm": 179.0,
1107
+ "learning_rate": 4.22562512114751e-06,
1108
+ "loss": 33.642,
1109
+ "step": 3140
1110
+ },
1111
+ {
1112
+ "epoch": 1.7824553980678373,
1113
+ "grad_norm": 204.0,
1114
+ "learning_rate": 4.186857918201202e-06,
1115
+ "loss": 33.6747,
1116
+ "step": 3160
1117
+ },
1118
+ {
1119
+ "epoch": 1.793738100275016,
1120
+ "grad_norm": 156.0,
1121
+ "learning_rate": 4.148090715254895e-06,
1122
+ "loss": 33.6803,
1123
+ "step": 3180
1124
+ },
1125
+ {
1126
+ "epoch": 1.8050208024821943,
1127
+ "grad_norm": 181.0,
1128
+ "learning_rate": 4.109323512308587e-06,
1129
+ "loss": 33.9288,
1130
+ "step": 3200
1131
+ },
1132
+ {
1133
+ "epoch": 1.816303504689373,
1134
+ "grad_norm": 167.0,
1135
+ "learning_rate": 4.07055630936228e-06,
1136
+ "loss": 33.6484,
1137
+ "step": 3220
1138
+ },
1139
+ {
1140
+ "epoch": 1.8275862068965516,
1141
+ "grad_norm": 179.0,
1142
+ "learning_rate": 4.031789106415972e-06,
1143
+ "loss": 33.5411,
1144
+ "step": 3240
1145
+ },
1146
+ {
1147
+ "epoch": 1.8388689091037302,
1148
+ "grad_norm": 202.0,
1149
+ "learning_rate": 3.993021903469665e-06,
1150
+ "loss": 33.7925,
1151
+ "step": 3260
1152
+ },
1153
+ {
1154
+ "epoch": 1.8501516113109089,
1155
+ "grad_norm": 211.0,
1156
+ "learning_rate": 3.954254700523358e-06,
1157
+ "loss": 34.3101,
1158
+ "step": 3280
1159
+ },
1160
+ {
1161
+ "epoch": 1.8614343135180875,
1162
+ "grad_norm": 187.0,
1163
+ "learning_rate": 3.91548749757705e-06,
1164
+ "loss": 33.674,
1165
+ "step": 3300
1166
+ },
1167
+ {
1168
+ "epoch": 1.8727170157252662,
1169
+ "grad_norm": 186.0,
1170
+ "learning_rate": 3.876720294630743e-06,
1171
+ "loss": 34.4049,
1172
+ "step": 3320
1173
+ },
1174
+ {
1175
+ "epoch": 1.8839997179324448,
1176
+ "grad_norm": 170.0,
1177
+ "learning_rate": 3.837953091684435e-06,
1178
+ "loss": 33.3274,
1179
+ "step": 3340
1180
+ },
1181
+ {
1182
+ "epoch": 1.8952824201396234,
1183
+ "grad_norm": 239.0,
1184
+ "learning_rate": 3.799185888738128e-06,
1185
+ "loss": 33.1375,
1186
+ "step": 3360
1187
+ },
1188
+ {
1189
+ "epoch": 1.906565122346802,
1190
+ "grad_norm": 178.0,
1191
+ "learning_rate": 3.7604186857918207e-06,
1192
+ "loss": 34.1163,
1193
+ "step": 3380
1194
+ },
1195
+ {
1196
+ "epoch": 1.9178478245539807,
1197
+ "grad_norm": 185.0,
1198
+ "learning_rate": 3.7216514828455132e-06,
1199
+ "loss": 34.4329,
1200
+ "step": 3400
1201
+ },
1202
+ {
1203
+ "epoch": 1.9291305267611594,
1204
+ "grad_norm": 195.0,
1205
+ "learning_rate": 3.6828842798992053e-06,
1206
+ "loss": 33.4928,
1207
+ "step": 3420
1208
+ },
1209
+ {
1210
+ "epoch": 1.940413228968338,
1211
+ "grad_norm": 162.0,
1212
+ "learning_rate": 3.644117076952898e-06,
1213
+ "loss": 34.0265,
1214
+ "step": 3440
1215
+ },
1216
+ {
1217
+ "epoch": 1.9516959311755167,
1218
+ "grad_norm": 195.0,
1219
+ "learning_rate": 3.6053498740065907e-06,
1220
+ "loss": 33.9424,
1221
+ "step": 3460
1222
+ },
1223
+ {
1224
+ "epoch": 1.9629786333826953,
1225
+ "grad_norm": 185.0,
1226
+ "learning_rate": 3.5665826710602836e-06,
1227
+ "loss": 34.3252,
1228
+ "step": 3480
1229
+ },
1230
+ {
1231
+ "epoch": 1.974261335589874,
1232
+ "grad_norm": 195.0,
1233
+ "learning_rate": 3.527815468113976e-06,
1234
+ "loss": 34.5225,
1235
+ "step": 3500
1236
+ },
1237
+ {
1238
+ "epoch": 1.9855440377970524,
1239
+ "grad_norm": 214.0,
1240
+ "learning_rate": 3.489048265167668e-06,
1241
+ "loss": 34.5155,
1242
+ "step": 3520
1243
+ },
1244
+ {
1245
+ "epoch": 1.996826740004231,
1246
+ "grad_norm": 182.0,
1247
+ "learning_rate": 3.450281062221361e-06,
1248
+ "loss": 34.1097,
1249
+ "step": 3540
1250
+ },
1251
+ {
1252
+ "epoch": 2.007897891545025,
1253
+ "grad_norm": 164.0,
1254
+ "learning_rate": 3.4115138592750535e-06,
1255
+ "loss": 33.4037,
1256
+ "step": 3560
1257
+ },
1258
+ {
1259
+ "epoch": 2.019180593752204,
1260
+ "grad_norm": 164.0,
1261
+ "learning_rate": 3.3727466563287464e-06,
1262
+ "loss": 33.2511,
1263
+ "step": 3580
1264
+ },
1265
+ {
1266
+ "epoch": 2.0304632959593825,
1267
+ "grad_norm": 228.0,
1268
+ "learning_rate": 3.333979453382439e-06,
1269
+ "loss": 33.3459,
1270
+ "step": 3600
1271
+ },
1272
+ {
1273
+ "epoch": 2.041745998166561,
1274
+ "grad_norm": 201.0,
1275
+ "learning_rate": 3.2952122504361313e-06,
1276
+ "loss": 33.6336,
1277
+ "step": 3620
1278
+ },
1279
+ {
1280
+ "epoch": 2.0530287003737393,
1281
+ "grad_norm": 243.0,
1282
+ "learning_rate": 3.2564450474898242e-06,
1283
+ "loss": 33.4227,
1284
+ "step": 3640
1285
+ },
1286
+ {
1287
+ "epoch": 2.064311402580918,
1288
+ "grad_norm": 188.0,
1289
+ "learning_rate": 3.2176778445435163e-06,
1290
+ "loss": 33.9483,
1291
+ "step": 3660
1292
+ },
1293
+ {
1294
+ "epoch": 2.0755941047880966,
1295
+ "grad_norm": 177.0,
1296
+ "learning_rate": 3.1789106415972088e-06,
1297
+ "loss": 32.5607,
1298
+ "step": 3680
1299
+ },
1300
+ {
1301
+ "epoch": 2.0868768069952752,
1302
+ "grad_norm": 195.0,
1303
+ "learning_rate": 3.1401434386509017e-06,
1304
+ "loss": 33.2094,
1305
+ "step": 3700
1306
+ },
1307
+ {
1308
+ "epoch": 2.098159509202454,
1309
+ "grad_norm": 194.0,
1310
+ "learning_rate": 3.101376235704594e-06,
1311
+ "loss": 32.5983,
1312
+ "step": 3720
1313
+ },
1314
+ {
1315
+ "epoch": 2.1094422114096325,
1316
+ "grad_norm": 171.0,
1317
+ "learning_rate": 3.062609032758287e-06,
1318
+ "loss": 33.4583,
1319
+ "step": 3740
1320
+ },
1321
+ {
1322
+ "epoch": 2.120724913616811,
1323
+ "grad_norm": 196.0,
1324
+ "learning_rate": 3.023841829811979e-06,
1325
+ "loss": 33.2525,
1326
+ "step": 3760
1327
+ },
1328
+ {
1329
+ "epoch": 2.13200761582399,
1330
+ "grad_norm": 185.0,
1331
+ "learning_rate": 2.9850746268656716e-06,
1332
+ "loss": 32.8658,
1333
+ "step": 3780
1334
+ },
1335
+ {
1336
+ "epoch": 2.1432903180311684,
1337
+ "grad_norm": 211.0,
1338
+ "learning_rate": 2.9463074239193645e-06,
1339
+ "loss": 33.584,
1340
+ "step": 3800
1341
+ },
1342
+ {
1343
+ "epoch": 2.154573020238347,
1344
+ "grad_norm": 177.0,
1345
+ "learning_rate": 2.907540220973057e-06,
1346
+ "loss": 32.7506,
1347
+ "step": 3820
1348
+ },
1349
+ {
1350
+ "epoch": 2.1658557224455257,
1351
+ "grad_norm": 201.0,
1352
+ "learning_rate": 2.86877301802675e-06,
1353
+ "loss": 33.6909,
1354
+ "step": 3840
1355
+ },
1356
+ {
1357
+ "epoch": 2.1771384246527044,
1358
+ "grad_norm": 187.0,
1359
+ "learning_rate": 2.8300058150804423e-06,
1360
+ "loss": 32.9226,
1361
+ "step": 3860
1362
+ },
1363
+ {
1364
+ "epoch": 2.188421126859883,
1365
+ "grad_norm": 186.0,
1366
+ "learning_rate": 2.7912386121341344e-06,
1367
+ "loss": 33.2277,
1368
+ "step": 3880
1369
+ },
1370
+ {
1371
+ "epoch": 2.1997038290670616,
1372
+ "grad_norm": 198.0,
1373
+ "learning_rate": 2.7524714091878273e-06,
1374
+ "loss": 32.8508,
1375
+ "step": 3900
1376
+ },
1377
+ {
1378
+ "epoch": 2.2109865312742403,
1379
+ "grad_norm": 186.0,
1380
+ "learning_rate": 2.7137042062415198e-06,
1381
+ "loss": 33.2497,
1382
+ "step": 3920
1383
+ },
1384
+ {
1385
+ "epoch": 2.222269233481419,
1386
+ "grad_norm": 222.0,
1387
+ "learning_rate": 2.6749370032952127e-06,
1388
+ "loss": 33.5576,
1389
+ "step": 3940
1390
+ },
1391
+ {
1392
+ "epoch": 2.2335519356885976,
1393
+ "grad_norm": 161.0,
1394
+ "learning_rate": 2.636169800348905e-06,
1395
+ "loss": 33.4056,
1396
+ "step": 3960
1397
+ },
1398
+ {
1399
+ "epoch": 2.244834637895776,
1400
+ "grad_norm": 163.0,
1401
+ "learning_rate": 2.597402597402597e-06,
1402
+ "loss": 33.0674,
1403
+ "step": 3980
1404
+ },
1405
+ {
1406
+ "epoch": 2.256117340102955,
1407
+ "grad_norm": 177.0,
1408
+ "learning_rate": 2.55863539445629e-06,
1409
+ "loss": 32.9768,
1410
+ "step": 4000
1411
+ },
1412
+ {
1413
+ "epoch": 2.2674000423101335,
1414
+ "grad_norm": 220.0,
1415
+ "learning_rate": 2.5198681915099826e-06,
1416
+ "loss": 33.1559,
1417
+ "step": 4020
1418
+ },
1419
+ {
1420
+ "epoch": 2.2786827445173117,
1421
+ "grad_norm": 175.0,
1422
+ "learning_rate": 2.481100988563675e-06,
1423
+ "loss": 33.5091,
1424
+ "step": 4040
1425
+ },
1426
+ {
1427
+ "epoch": 2.2899654467244908,
1428
+ "grad_norm": 180.0,
1429
+ "learning_rate": 2.442333785617368e-06,
1430
+ "loss": 33.3984,
1431
+ "step": 4060
1432
+ },
1433
+ {
1434
+ "epoch": 2.301248148931669,
1435
+ "grad_norm": 192.0,
1436
+ "learning_rate": 2.4035665826710604e-06,
1437
+ "loss": 33.3091,
1438
+ "step": 4080
1439
+ },
1440
+ {
1441
+ "epoch": 2.3125308511388476,
1442
+ "grad_norm": 200.0,
1443
+ "learning_rate": 2.3647993797247533e-06,
1444
+ "loss": 33.9978,
1445
+ "step": 4100
1446
+ },
1447
+ {
1448
+ "epoch": 2.3238135533460262,
1449
+ "grad_norm": 202.0,
1450
+ "learning_rate": 2.3260321767784454e-06,
1451
+ "loss": 33.4988,
1452
+ "step": 4120
1453
+ },
1454
+ {
1455
+ "epoch": 2.335096255553205,
1456
+ "grad_norm": 220.0,
1457
+ "learning_rate": 2.2872649738321383e-06,
1458
+ "loss": 32.5648,
1459
+ "step": 4140
1460
+ },
1461
+ {
1462
+ "epoch": 2.3463789577603835,
1463
+ "grad_norm": 188.0,
1464
+ "learning_rate": 2.2484977708858308e-06,
1465
+ "loss": 33.3508,
1466
+ "step": 4160
1467
+ },
1468
+ {
1469
+ "epoch": 2.357661659967562,
1470
+ "grad_norm": 166.0,
1471
+ "learning_rate": 2.2097305679395232e-06,
1472
+ "loss": 33.5085,
1473
+ "step": 4180
1474
+ },
1475
+ {
1476
+ "epoch": 2.368944362174741,
1477
+ "grad_norm": 192.0,
1478
+ "learning_rate": 2.170963364993216e-06,
1479
+ "loss": 33.5222,
1480
+ "step": 4200
1481
+ },
1482
+ {
1483
+ "epoch": 2.3802270643819194,
1484
+ "grad_norm": 168.0,
1485
+ "learning_rate": 2.132196162046908e-06,
1486
+ "loss": 33.5567,
1487
+ "step": 4220
1488
+ },
1489
+ {
1490
+ "epoch": 2.391509766589098,
1491
+ "grad_norm": 189.0,
1492
+ "learning_rate": 2.093428959100601e-06,
1493
+ "loss": 32.6794,
1494
+ "step": 4240
1495
+ },
1496
+ {
1497
+ "epoch": 2.4027924687962767,
1498
+ "grad_norm": 208.0,
1499
+ "learning_rate": 2.0546617561542936e-06,
1500
+ "loss": 33.1244,
1501
+ "step": 4260
1502
+ },
1503
+ {
1504
+ "epoch": 2.4140751710034554,
1505
+ "grad_norm": 222.0,
1506
+ "learning_rate": 2.015894553207986e-06,
1507
+ "loss": 33.2899,
1508
+ "step": 4280
1509
+ },
1510
+ {
1511
+ "epoch": 2.425357873210634,
1512
+ "grad_norm": 165.0,
1513
+ "learning_rate": 1.977127350261679e-06,
1514
+ "loss": 33.3089,
1515
+ "step": 4300
1516
+ },
1517
+ {
1518
+ "epoch": 2.4366405754178126,
1519
+ "grad_norm": 186.0,
1520
+ "learning_rate": 1.9383601473153714e-06,
1521
+ "loss": 33.8634,
1522
+ "step": 4320
1523
+ },
1524
+ {
1525
+ "epoch": 2.4479232776249913,
1526
+ "grad_norm": 189.0,
1527
+ "learning_rate": 1.899592944369064e-06,
1528
+ "loss": 33.6295,
1529
+ "step": 4340
1530
+ },
1531
+ {
1532
+ "epoch": 2.45920597983217,
1533
+ "grad_norm": 194.0,
1534
+ "learning_rate": 1.8608257414227566e-06,
1535
+ "loss": 33.7899,
1536
+ "step": 4360
1537
+ },
1538
+ {
1539
+ "epoch": 2.4704886820393486,
1540
+ "grad_norm": 176.0,
1541
+ "learning_rate": 1.822058538476449e-06,
1542
+ "loss": 33.4224,
1543
+ "step": 4380
1544
+ },
1545
+ {
1546
+ "epoch": 2.481771384246527,
1547
+ "grad_norm": 178.0,
1548
+ "learning_rate": 1.7832913355301418e-06,
1549
+ "loss": 33.2276,
1550
+ "step": 4400
1551
+ },
1552
+ {
1553
+ "epoch": 2.493054086453706,
1554
+ "grad_norm": 204.0,
1555
+ "learning_rate": 1.744524132583834e-06,
1556
+ "loss": 33.7431,
1557
+ "step": 4420
1558
+ },
1559
+ {
1560
+ "epoch": 2.5043367886608845,
1561
+ "grad_norm": 195.0,
1562
+ "learning_rate": 1.7057569296375267e-06,
1563
+ "loss": 33.1986,
1564
+ "step": 4440
1565
+ },
1566
+ {
1567
+ "epoch": 2.5156194908680627,
1568
+ "grad_norm": 191.0,
1569
+ "learning_rate": 1.6669897266912194e-06,
1570
+ "loss": 33.1506,
1571
+ "step": 4460
1572
+ },
1573
+ {
1574
+ "epoch": 2.5269021930752418,
1575
+ "grad_norm": 193.0,
1576
+ "learning_rate": 1.6282225237449121e-06,
1577
+ "loss": 33.1911,
1578
+ "step": 4480
1579
+ },
1580
+ {
1581
+ "epoch": 2.53818489528242,
1582
+ "grad_norm": 230.0,
1583
+ "learning_rate": 1.5894553207986044e-06,
1584
+ "loss": 33.6828,
1585
+ "step": 4500
1586
+ },
1587
+ {
1588
+ "epoch": 2.5494675974895986,
1589
+ "grad_norm": 219.0,
1590
+ "learning_rate": 1.550688117852297e-06,
1591
+ "loss": 33.9657,
1592
+ "step": 4520
1593
+ },
1594
+ {
1595
+ "epoch": 2.5607502996967773,
1596
+ "grad_norm": 197.0,
1597
+ "learning_rate": 1.5119209149059895e-06,
1598
+ "loss": 33.2005,
1599
+ "step": 4540
1600
+ },
1601
+ {
1602
+ "epoch": 2.572033001903956,
1603
+ "grad_norm": 214.0,
1604
+ "learning_rate": 1.4731537119596822e-06,
1605
+ "loss": 33.5472,
1606
+ "step": 4560
1607
+ },
1608
+ {
1609
+ "epoch": 2.5833157041111345,
1610
+ "grad_norm": 167.0,
1611
+ "learning_rate": 1.434386509013375e-06,
1612
+ "loss": 34.237,
1613
+ "step": 4580
1614
+ },
1615
+ {
1616
+ "epoch": 2.594598406318313,
1617
+ "grad_norm": 162.0,
1618
+ "learning_rate": 1.3956193060670672e-06,
1619
+ "loss": 34.3779,
1620
+ "step": 4600
1621
+ },
1622
+ {
1623
+ "epoch": 2.605881108525492,
1624
+ "grad_norm": 240.0,
1625
+ "learning_rate": 1.3568521031207599e-06,
1626
+ "loss": 33.7256,
1627
+ "step": 4620
1628
+ },
1629
+ {
1630
+ "epoch": 2.6171638107326705,
1631
+ "grad_norm": 187.0,
1632
+ "learning_rate": 1.3180849001744526e-06,
1633
+ "loss": 32.9692,
1634
+ "step": 4640
1635
+ },
1636
+ {
1637
+ "epoch": 2.628446512939849,
1638
+ "grad_norm": 164.0,
1639
+ "learning_rate": 1.279317697228145e-06,
1640
+ "loss": 33.8773,
1641
+ "step": 4660
1642
+ },
1643
+ {
1644
+ "epoch": 2.6397292151470277,
1645
+ "grad_norm": 188.0,
1646
+ "learning_rate": 1.2405504942818375e-06,
1647
+ "loss": 33.5338,
1648
+ "step": 4680
1649
+ },
1650
+ {
1651
+ "epoch": 2.6510119173542064,
1652
+ "grad_norm": 185.0,
1653
+ "learning_rate": 1.2017832913355302e-06,
1654
+ "loss": 33.9084,
1655
+ "step": 4700
1656
+ },
1657
+ {
1658
+ "epoch": 2.662294619561385,
1659
+ "grad_norm": 190.0,
1660
+ "learning_rate": 1.1630160883892227e-06,
1661
+ "loss": 33.0886,
1662
+ "step": 4720
1663
+ },
1664
+ {
1665
+ "epoch": 2.6735773217685637,
1666
+ "grad_norm": 169.0,
1667
+ "learning_rate": 1.1242488854429154e-06,
1668
+ "loss": 33.0422,
1669
+ "step": 4740
1670
+ },
1671
+ {
1672
+ "epoch": 2.6848600239757423,
1673
+ "grad_norm": 185.0,
1674
+ "learning_rate": 1.085481682496608e-06,
1675
+ "loss": 33.4596,
1676
+ "step": 4760
1677
+ },
1678
+ {
1679
+ "epoch": 2.696142726182921,
1680
+ "grad_norm": 169.0,
1681
+ "learning_rate": 1.0467144795503006e-06,
1682
+ "loss": 33.3788,
1683
+ "step": 4780
1684
+ },
1685
+ {
1686
+ "epoch": 2.7074254283900996,
1687
+ "grad_norm": 214.0,
1688
+ "learning_rate": 1.007947276603993e-06,
1689
+ "loss": 33.6668,
1690
+ "step": 4800
1691
+ },
1692
+ {
1693
+ "epoch": 2.7187081305972782,
1694
+ "grad_norm": 170.0,
1695
+ "learning_rate": 9.691800736576857e-07,
1696
+ "loss": 33.1791,
1697
+ "step": 4820
1698
+ },
1699
+ {
1700
+ "epoch": 2.7299908328044564,
1701
+ "grad_norm": 192.0,
1702
+ "learning_rate": 9.304128707113783e-07,
1703
+ "loss": 33.7457,
1704
+ "step": 4840
1705
+ },
1706
+ {
1707
+ "epoch": 2.7412735350116355,
1708
+ "grad_norm": 171.0,
1709
+ "learning_rate": 8.916456677650709e-07,
1710
+ "loss": 33.7942,
1711
+ "step": 4860
1712
+ },
1713
+ {
1714
+ "epoch": 2.7525562372188137,
1715
+ "grad_norm": 164.0,
1716
+ "learning_rate": 8.528784648187634e-07,
1717
+ "loss": 33.0871,
1718
+ "step": 4880
1719
+ },
1720
+ {
1721
+ "epoch": 2.763838939425993,
1722
+ "grad_norm": 179.0,
1723
+ "learning_rate": 8.141112618724561e-07,
1724
+ "loss": 33.5948,
1725
+ "step": 4900
1726
+ },
1727
+ {
1728
+ "epoch": 2.775121641633171,
1729
+ "grad_norm": 197.0,
1730
+ "learning_rate": 7.753440589261485e-07,
1731
+ "loss": 33.451,
1732
+ "step": 4920
1733
+ },
1734
+ {
1735
+ "epoch": 2.7864043438403496,
1736
+ "grad_norm": 176.0,
1737
+ "learning_rate": 7.365768559798411e-07,
1738
+ "loss": 33.3747,
1739
+ "step": 4940
1740
+ },
1741
+ {
1742
+ "epoch": 2.7976870460475283,
1743
+ "grad_norm": 221.0,
1744
+ "learning_rate": 6.978096530335336e-07,
1745
+ "loss": 33.7778,
1746
+ "step": 4960
1747
+ },
1748
+ {
1749
+ "epoch": 2.808969748254707,
1750
+ "grad_norm": 198.0,
1751
+ "learning_rate": 6.590424500872263e-07,
1752
+ "loss": 33.2167,
1753
+ "step": 4980
1754
+ },
1755
+ {
1756
+ "epoch": 2.8202524504618856,
1757
+ "grad_norm": 208.0,
1758
+ "learning_rate": 6.202752471409188e-07,
1759
+ "loss": 33.0164,
1760
+ "step": 5000
1761
+ }
1762
+ ],
1763
+ "logging_steps": 20,
1764
+ "max_steps": 5319,
1765
+ "num_input_tokens_seen": 0,
1766
+ "num_train_epochs": 3,
1767
+ "save_steps": 500,
1768
+ "stateful_callbacks": {
1769
+ "TrainerControl": {
1770
+ "args": {
1771
+ "should_epoch_stop": false,
1772
+ "should_evaluate": false,
1773
+ "should_log": false,
1774
+ "should_save": true,
1775
+ "should_training_stop": false
1776
+ },
1777
+ "attributes": {}
1778
+ }
1779
+ },
1780
+ "total_flos": 0.0,
1781
+ "train_batch_size": 2,
1782
+ "trial_name": null,
1783
+ "trial_params": null
1784
+ }
checkpoint-5000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c7a3d84d5c920a1183e32aa8591078ae7fabd64ef9226b2cb2211eab73f936d
3
+ size 5841
checkpoint-5319/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd3e326982200d0a47e247aa6c7a58178f13aaf20317701b7aa60eeaf62ceb43
3
+ size 1483239819
checkpoint-5319/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d0e74684dc14f52619baeb2f8cbc824f2a9da0cb00f745cc3f32ba421e800dc
3
+ size 1014303003
checkpoint-5319/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
3
+ size 14645
checkpoint-5319/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2e3acd99255b989ecac3978b00e8f7883db386d7a69a00be53ccebe21bf58a7
3
+ size 1465
checkpoint-5319/trainer_state.json ADDED
@@ -0,0 +1,1889 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 5319,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.01128270220717862,
14
+ "grad_norm": 684.0,
15
+ "learning_rate": 1.1875e-06,
16
+ "loss": 42.923,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 0.02256540441435724,
21
+ "grad_norm": 378.0,
22
+ "learning_rate": 2.4375e-06,
23
+ "loss": 41.9073,
24
+ "step": 40
25
+ },
26
+ {
27
+ "epoch": 0.03384810662153586,
28
+ "grad_norm": 322.0,
29
+ "learning_rate": 3.6875000000000007e-06,
30
+ "loss": 39.9877,
31
+ "step": 60
32
+ },
33
+ {
34
+ "epoch": 0.04513080882871448,
35
+ "grad_norm": 280.0,
36
+ "learning_rate": 4.937500000000001e-06,
37
+ "loss": 38.0747,
38
+ "step": 80
39
+ },
40
+ {
41
+ "epoch": 0.056413511035893094,
42
+ "grad_norm": 1328.0,
43
+ "learning_rate": 6.1875000000000005e-06,
44
+ "loss": 36.2999,
45
+ "step": 100
46
+ },
47
+ {
48
+ "epoch": 0.06769621324307172,
49
+ "grad_norm": 212.0,
50
+ "learning_rate": 7.437500000000001e-06,
51
+ "loss": 35.0646,
52
+ "step": 120
53
+ },
54
+ {
55
+ "epoch": 0.07897891545025033,
56
+ "grad_norm": 208.0,
57
+ "learning_rate": 8.687500000000001e-06,
58
+ "loss": 34.4917,
59
+ "step": 140
60
+ },
61
+ {
62
+ "epoch": 0.09026161765742896,
63
+ "grad_norm": 180.0,
64
+ "learning_rate": 9.937500000000001e-06,
65
+ "loss": 34.5205,
66
+ "step": 160
67
+ },
68
+ {
69
+ "epoch": 0.10154431986460757,
70
+ "grad_norm": 213.0,
71
+ "learning_rate": 9.96317115720101e-06,
72
+ "loss": 33.3244,
73
+ "step": 180
74
+ },
75
+ {
76
+ "epoch": 0.11282702207178619,
77
+ "grad_norm": 174.0,
78
+ "learning_rate": 9.9244039542547e-06,
79
+ "loss": 33.6509,
80
+ "step": 200
81
+ },
82
+ {
83
+ "epoch": 0.12410972427896481,
84
+ "grad_norm": 234.0,
85
+ "learning_rate": 9.885636751308394e-06,
86
+ "loss": 34.1064,
87
+ "step": 220
88
+ },
89
+ {
90
+ "epoch": 0.13539242648614344,
91
+ "grad_norm": 176.0,
92
+ "learning_rate": 9.846869548362087e-06,
93
+ "loss": 34.0945,
94
+ "step": 240
95
+ },
96
+ {
97
+ "epoch": 0.14667512869332205,
98
+ "grad_norm": 222.0,
99
+ "learning_rate": 9.80810234541578e-06,
100
+ "loss": 33.8671,
101
+ "step": 260
102
+ },
103
+ {
104
+ "epoch": 0.15795783090050067,
105
+ "grad_norm": 164.0,
106
+ "learning_rate": 9.769335142469472e-06,
107
+ "loss": 33.4257,
108
+ "step": 280
109
+ },
110
+ {
111
+ "epoch": 0.16924053310767928,
112
+ "grad_norm": 185.0,
113
+ "learning_rate": 9.730567939523164e-06,
114
+ "loss": 33.4832,
115
+ "step": 300
116
+ },
117
+ {
118
+ "epoch": 0.18052323531485792,
119
+ "grad_norm": 188.0,
120
+ "learning_rate": 9.691800736576857e-06,
121
+ "loss": 33.4079,
122
+ "step": 320
123
+ },
124
+ {
125
+ "epoch": 0.19180593752203653,
126
+ "grad_norm": 195.0,
127
+ "learning_rate": 9.65303353363055e-06,
128
+ "loss": 34.1975,
129
+ "step": 340
130
+ },
131
+ {
132
+ "epoch": 0.20308863972921515,
133
+ "grad_norm": 186.0,
134
+ "learning_rate": 9.614266330684242e-06,
135
+ "loss": 33.3613,
136
+ "step": 360
137
+ },
138
+ {
139
+ "epoch": 0.21437134193639376,
140
+ "grad_norm": 172.0,
141
+ "learning_rate": 9.575499127737934e-06,
142
+ "loss": 32.6162,
143
+ "step": 380
144
+ },
145
+ {
146
+ "epoch": 0.22565404414357237,
147
+ "grad_norm": 170.0,
148
+ "learning_rate": 9.536731924791627e-06,
149
+ "loss": 33.3925,
150
+ "step": 400
151
+ },
152
+ {
153
+ "epoch": 0.23693674635075102,
154
+ "grad_norm": 168.0,
155
+ "learning_rate": 9.49796472184532e-06,
156
+ "loss": 33.4435,
157
+ "step": 420
158
+ },
159
+ {
160
+ "epoch": 0.24821944855792963,
161
+ "grad_norm": 197.0,
162
+ "learning_rate": 9.459197518899013e-06,
163
+ "loss": 32.9941,
164
+ "step": 440
165
+ },
166
+ {
167
+ "epoch": 0.25950215076510824,
168
+ "grad_norm": 190.0,
169
+ "learning_rate": 9.420430315952704e-06,
170
+ "loss": 33.2245,
171
+ "step": 460
172
+ },
173
+ {
174
+ "epoch": 0.2707848529722869,
175
+ "grad_norm": 185.0,
176
+ "learning_rate": 9.381663113006397e-06,
177
+ "loss": 33.2802,
178
+ "step": 480
179
+ },
180
+ {
181
+ "epoch": 0.28206755517946547,
182
+ "grad_norm": 201.0,
183
+ "learning_rate": 9.34289591006009e-06,
184
+ "loss": 33.3563,
185
+ "step": 500
186
+ },
187
+ {
188
+ "epoch": 0.2933502573866441,
189
+ "grad_norm": 160.0,
190
+ "learning_rate": 9.304128707113782e-06,
191
+ "loss": 32.8094,
192
+ "step": 520
193
+ },
194
+ {
195
+ "epoch": 0.3046329595938227,
196
+ "grad_norm": 171.0,
197
+ "learning_rate": 9.265361504167476e-06,
198
+ "loss": 33.967,
199
+ "step": 540
200
+ },
201
+ {
202
+ "epoch": 0.31591566180100134,
203
+ "grad_norm": 185.0,
204
+ "learning_rate": 9.226594301221168e-06,
205
+ "loss": 33.9071,
206
+ "step": 560
207
+ },
208
+ {
209
+ "epoch": 0.32719836400818,
210
+ "grad_norm": 168.0,
211
+ "learning_rate": 9.18782709827486e-06,
212
+ "loss": 33.5103,
213
+ "step": 580
214
+ },
215
+ {
216
+ "epoch": 0.33848106621535856,
217
+ "grad_norm": 185.0,
218
+ "learning_rate": 9.149059895328553e-06,
219
+ "loss": 33.2943,
220
+ "step": 600
221
+ },
222
+ {
223
+ "epoch": 0.3497637684225372,
224
+ "grad_norm": 235.0,
225
+ "learning_rate": 9.110292692382246e-06,
226
+ "loss": 33.8674,
227
+ "step": 620
228
+ },
229
+ {
230
+ "epoch": 0.36104647062971584,
231
+ "grad_norm": 171.0,
232
+ "learning_rate": 9.071525489435938e-06,
233
+ "loss": 34.1437,
234
+ "step": 640
235
+ },
236
+ {
237
+ "epoch": 0.37232917283689443,
238
+ "grad_norm": 176.0,
239
+ "learning_rate": 9.03275828648963e-06,
240
+ "loss": 32.9577,
241
+ "step": 660
242
+ },
243
+ {
244
+ "epoch": 0.38361187504407307,
245
+ "grad_norm": 179.0,
246
+ "learning_rate": 8.993991083543323e-06,
247
+ "loss": 33.5755,
248
+ "step": 680
249
+ },
250
+ {
251
+ "epoch": 0.39489457725125165,
252
+ "grad_norm": 187.0,
253
+ "learning_rate": 8.955223880597016e-06,
254
+ "loss": 34.03,
255
+ "step": 700
256
+ },
257
+ {
258
+ "epoch": 0.4061772794584303,
259
+ "grad_norm": 175.0,
260
+ "learning_rate": 8.916456677650708e-06,
261
+ "loss": 34.0341,
262
+ "step": 720
263
+ },
264
+ {
265
+ "epoch": 0.41745998166560894,
266
+ "grad_norm": 184.0,
267
+ "learning_rate": 8.8776894747044e-06,
268
+ "loss": 34.1199,
269
+ "step": 740
270
+ },
271
+ {
272
+ "epoch": 0.4287426838727875,
273
+ "grad_norm": 214.0,
274
+ "learning_rate": 8.838922271758093e-06,
275
+ "loss": 34.5299,
276
+ "step": 760
277
+ },
278
+ {
279
+ "epoch": 0.44002538607996616,
280
+ "grad_norm": 187.0,
281
+ "learning_rate": 8.800155068811787e-06,
282
+ "loss": 33.6687,
283
+ "step": 780
284
+ },
285
+ {
286
+ "epoch": 0.45130808828714475,
287
+ "grad_norm": 207.0,
288
+ "learning_rate": 8.761387865865478e-06,
289
+ "loss": 33.4913,
290
+ "step": 800
291
+ },
292
+ {
293
+ "epoch": 0.4625907904943234,
294
+ "grad_norm": 199.0,
295
+ "learning_rate": 8.72262066291917e-06,
296
+ "loss": 34.6043,
297
+ "step": 820
298
+ },
299
+ {
300
+ "epoch": 0.47387349270150203,
301
+ "grad_norm": 308.0,
302
+ "learning_rate": 8.683853459972865e-06,
303
+ "loss": 34.1107,
304
+ "step": 840
305
+ },
306
+ {
307
+ "epoch": 0.4851561949086806,
308
+ "grad_norm": 219.0,
309
+ "learning_rate": 8.645086257026555e-06,
310
+ "loss": 33.5659,
311
+ "step": 860
312
+ },
313
+ {
314
+ "epoch": 0.49643889711585926,
315
+ "grad_norm": 184.0,
316
+ "learning_rate": 8.60631905408025e-06,
317
+ "loss": 34.6702,
318
+ "step": 880
319
+ },
320
+ {
321
+ "epoch": 0.5077215993230378,
322
+ "grad_norm": 188.0,
323
+ "learning_rate": 8.567551851133942e-06,
324
+ "loss": 33.9021,
325
+ "step": 900
326
+ },
327
+ {
328
+ "epoch": 0.5190043015302165,
329
+ "grad_norm": 189.0,
330
+ "learning_rate": 8.528784648187633e-06,
331
+ "loss": 33.8139,
332
+ "step": 920
333
+ },
334
+ {
335
+ "epoch": 0.5302870037373951,
336
+ "grad_norm": 202.0,
337
+ "learning_rate": 8.490017445241327e-06,
338
+ "loss": 33.9562,
339
+ "step": 940
340
+ },
341
+ {
342
+ "epoch": 0.5415697059445738,
343
+ "grad_norm": 184.0,
344
+ "learning_rate": 8.45125024229502e-06,
345
+ "loss": 34.1304,
346
+ "step": 960
347
+ },
348
+ {
349
+ "epoch": 0.5528524081517523,
350
+ "grad_norm": 210.0,
351
+ "learning_rate": 8.412483039348712e-06,
352
+ "loss": 34.3385,
353
+ "step": 980
354
+ },
355
+ {
356
+ "epoch": 0.5641351103589309,
357
+ "grad_norm": 167.0,
358
+ "learning_rate": 8.373715836402404e-06,
359
+ "loss": 34.2957,
360
+ "step": 1000
361
+ },
362
+ {
363
+ "epoch": 0.5754178125661096,
364
+ "grad_norm": 197.0,
365
+ "learning_rate": 8.334948633456097e-06,
366
+ "loss": 34.701,
367
+ "step": 1020
368
+ },
369
+ {
370
+ "epoch": 0.5867005147732882,
371
+ "grad_norm": 220.0,
372
+ "learning_rate": 8.29618143050979e-06,
373
+ "loss": 34.1251,
374
+ "step": 1040
375
+ },
376
+ {
377
+ "epoch": 0.5979832169804669,
378
+ "grad_norm": 199.0,
379
+ "learning_rate": 8.257414227563482e-06,
380
+ "loss": 34.2395,
381
+ "step": 1060
382
+ },
383
+ {
384
+ "epoch": 0.6092659191876454,
385
+ "grad_norm": 210.0,
386
+ "learning_rate": 8.218647024617174e-06,
387
+ "loss": 33.7562,
388
+ "step": 1080
389
+ },
390
+ {
391
+ "epoch": 0.620548621394824,
392
+ "grad_norm": 213.0,
393
+ "learning_rate": 8.179879821670867e-06,
394
+ "loss": 35.2014,
395
+ "step": 1100
396
+ },
397
+ {
398
+ "epoch": 0.6318313236020027,
399
+ "grad_norm": 214.0,
400
+ "learning_rate": 8.14111261872456e-06,
401
+ "loss": 33.6772,
402
+ "step": 1120
403
+ },
404
+ {
405
+ "epoch": 0.6431140258091813,
406
+ "grad_norm": 220.0,
407
+ "learning_rate": 8.102345415778252e-06,
408
+ "loss": 34.0573,
409
+ "step": 1140
410
+ },
411
+ {
412
+ "epoch": 0.65439672801636,
413
+ "grad_norm": 162.0,
414
+ "learning_rate": 8.063578212831944e-06,
415
+ "loss": 34.1778,
416
+ "step": 1160
417
+ },
418
+ {
419
+ "epoch": 0.6656794302235386,
420
+ "grad_norm": 171.0,
421
+ "learning_rate": 8.024811009885637e-06,
422
+ "loss": 34.7704,
423
+ "step": 1180
424
+ },
425
+ {
426
+ "epoch": 0.6769621324307171,
427
+ "grad_norm": 192.0,
428
+ "learning_rate": 7.98604380693933e-06,
429
+ "loss": 34.5073,
430
+ "step": 1200
431
+ },
432
+ {
433
+ "epoch": 0.6882448346378958,
434
+ "grad_norm": 199.0,
435
+ "learning_rate": 7.947276603993023e-06,
436
+ "loss": 35.1462,
437
+ "step": 1220
438
+ },
439
+ {
440
+ "epoch": 0.6995275368450744,
441
+ "grad_norm": 194.0,
442
+ "learning_rate": 7.908509401046716e-06,
443
+ "loss": 35.0324,
444
+ "step": 1240
445
+ },
446
+ {
447
+ "epoch": 0.710810239052253,
448
+ "grad_norm": 180.0,
449
+ "learning_rate": 7.869742198100407e-06,
450
+ "loss": 34.4355,
451
+ "step": 1260
452
+ },
453
+ {
454
+ "epoch": 0.7220929412594317,
455
+ "grad_norm": 171.0,
456
+ "learning_rate": 7.8309749951541e-06,
457
+ "loss": 34.3484,
458
+ "step": 1280
459
+ },
460
+ {
461
+ "epoch": 0.7333756434666102,
462
+ "grad_norm": 234.0,
463
+ "learning_rate": 7.792207792207793e-06,
464
+ "loss": 34.3537,
465
+ "step": 1300
466
+ },
467
+ {
468
+ "epoch": 0.7446583456737889,
469
+ "grad_norm": 217.0,
470
+ "learning_rate": 7.753440589261486e-06,
471
+ "loss": 34.4467,
472
+ "step": 1320
473
+ },
474
+ {
475
+ "epoch": 0.7559410478809675,
476
+ "grad_norm": 183.0,
477
+ "learning_rate": 7.714673386315178e-06,
478
+ "loss": 34.5935,
479
+ "step": 1340
480
+ },
481
+ {
482
+ "epoch": 0.7672237500881461,
483
+ "grad_norm": 167.0,
484
+ "learning_rate": 7.67590618336887e-06,
485
+ "loss": 34.1833,
486
+ "step": 1360
487
+ },
488
+ {
489
+ "epoch": 0.7785064522953248,
490
+ "grad_norm": 182.0,
491
+ "learning_rate": 7.637138980422563e-06,
492
+ "loss": 34.5052,
493
+ "step": 1380
494
+ },
495
+ {
496
+ "epoch": 0.7897891545025033,
497
+ "grad_norm": 170.0,
498
+ "learning_rate": 7.598371777476256e-06,
499
+ "loss": 34.5334,
500
+ "step": 1400
501
+ },
502
+ {
503
+ "epoch": 0.801071856709682,
504
+ "grad_norm": 181.0,
505
+ "learning_rate": 7.559604574529948e-06,
506
+ "loss": 34.1411,
507
+ "step": 1420
508
+ },
509
+ {
510
+ "epoch": 0.8123545589168606,
511
+ "grad_norm": 163.0,
512
+ "learning_rate": 7.5208373715836415e-06,
513
+ "loss": 34.7683,
514
+ "step": 1440
515
+ },
516
+ {
517
+ "epoch": 0.8236372611240392,
518
+ "grad_norm": 176.0,
519
+ "learning_rate": 7.482070168637333e-06,
520
+ "loss": 34.7674,
521
+ "step": 1460
522
+ },
523
+ {
524
+ "epoch": 0.8349199633312179,
525
+ "grad_norm": 165.0,
526
+ "learning_rate": 7.4433029656910264e-06,
527
+ "loss": 34.7617,
528
+ "step": 1480
529
+ },
530
+ {
531
+ "epoch": 0.8462026655383964,
532
+ "grad_norm": 194.0,
533
+ "learning_rate": 7.404535762744719e-06,
534
+ "loss": 34.7591,
535
+ "step": 1500
536
+ },
537
+ {
538
+ "epoch": 0.857485367745575,
539
+ "grad_norm": 175.0,
540
+ "learning_rate": 7.3657685597984105e-06,
541
+ "loss": 34.0827,
542
+ "step": 1520
543
+ },
544
+ {
545
+ "epoch": 0.8687680699527537,
546
+ "grad_norm": 179.0,
547
+ "learning_rate": 7.327001356852104e-06,
548
+ "loss": 34.5944,
549
+ "step": 1540
550
+ },
551
+ {
552
+ "epoch": 0.8800507721599323,
553
+ "grad_norm": 198.0,
554
+ "learning_rate": 7.288234153905796e-06,
555
+ "loss": 35.1967,
556
+ "step": 1560
557
+ },
558
+ {
559
+ "epoch": 0.891333474367111,
560
+ "grad_norm": 192.0,
561
+ "learning_rate": 7.249466950959488e-06,
562
+ "loss": 35.0658,
563
+ "step": 1580
564
+ },
565
+ {
566
+ "epoch": 0.9026161765742895,
567
+ "grad_norm": 207.0,
568
+ "learning_rate": 7.210699748013181e-06,
569
+ "loss": 34.9624,
570
+ "step": 1600
571
+ },
572
+ {
573
+ "epoch": 0.9138988787814681,
574
+ "grad_norm": 195.0,
575
+ "learning_rate": 7.171932545066874e-06,
576
+ "loss": 34.5503,
577
+ "step": 1620
578
+ },
579
+ {
580
+ "epoch": 0.9251815809886468,
581
+ "grad_norm": 187.0,
582
+ "learning_rate": 7.133165342120567e-06,
583
+ "loss": 34.6947,
584
+ "step": 1640
585
+ },
586
+ {
587
+ "epoch": 0.9364642831958254,
588
+ "grad_norm": 178.0,
589
+ "learning_rate": 7.094398139174259e-06,
590
+ "loss": 34.7273,
591
+ "step": 1660
592
+ },
593
+ {
594
+ "epoch": 0.9477469854030041,
595
+ "grad_norm": 195.0,
596
+ "learning_rate": 7.055630936227952e-06,
597
+ "loss": 35.1698,
598
+ "step": 1680
599
+ },
600
+ {
601
+ "epoch": 0.9590296876101826,
602
+ "grad_norm": 194.0,
603
+ "learning_rate": 7.0168637332816445e-06,
604
+ "loss": 34.8608,
605
+ "step": 1700
606
+ },
607
+ {
608
+ "epoch": 0.9703123898173612,
609
+ "grad_norm": 209.0,
610
+ "learning_rate": 6.978096530335336e-06,
611
+ "loss": 34.3997,
612
+ "step": 1720
613
+ },
614
+ {
615
+ "epoch": 0.9815950920245399,
616
+ "grad_norm": 142.0,
617
+ "learning_rate": 6.9393293273890295e-06,
618
+ "loss": 34.856,
619
+ "step": 1740
620
+ },
621
+ {
622
+ "epoch": 0.9928777942317185,
623
+ "grad_norm": 186.0,
624
+ "learning_rate": 6.900562124442722e-06,
625
+ "loss": 34.3359,
626
+ "step": 1760
627
+ },
628
+ {
629
+ "epoch": 1.0039489457725126,
630
+ "grad_norm": 169.0,
631
+ "learning_rate": 6.8617949214964145e-06,
632
+ "loss": 33.62,
633
+ "step": 1780
634
+ },
635
+ {
636
+ "epoch": 1.0152316479796912,
637
+ "grad_norm": 189.0,
638
+ "learning_rate": 6.823027718550107e-06,
639
+ "loss": 33.4374,
640
+ "step": 1800
641
+ },
642
+ {
643
+ "epoch": 1.0265143501868697,
644
+ "grad_norm": 191.0,
645
+ "learning_rate": 6.7842605156038e-06,
646
+ "loss": 32.8082,
647
+ "step": 1820
648
+ },
649
+ {
650
+ "epoch": 1.0377970523940483,
651
+ "grad_norm": 151.0,
652
+ "learning_rate": 6.745493312657493e-06,
653
+ "loss": 33.2524,
654
+ "step": 1840
655
+ },
656
+ {
657
+ "epoch": 1.049079754601227,
658
+ "grad_norm": 153.0,
659
+ "learning_rate": 6.706726109711184e-06,
660
+ "loss": 32.7946,
661
+ "step": 1860
662
+ },
663
+ {
664
+ "epoch": 1.0603624568084056,
665
+ "grad_norm": 190.0,
666
+ "learning_rate": 6.667958906764878e-06,
667
+ "loss": 34.0579,
668
+ "step": 1880
669
+ },
670
+ {
671
+ "epoch": 1.0716451590155842,
672
+ "grad_norm": 169.0,
673
+ "learning_rate": 6.62919170381857e-06,
674
+ "loss": 33.6604,
675
+ "step": 1900
676
+ },
677
+ {
678
+ "epoch": 1.0829278612227629,
679
+ "grad_norm": 203.0,
680
+ "learning_rate": 6.590424500872263e-06,
681
+ "loss": 33.566,
682
+ "step": 1920
683
+ },
684
+ {
685
+ "epoch": 1.0942105634299415,
686
+ "grad_norm": 166.0,
687
+ "learning_rate": 6.551657297925955e-06,
688
+ "loss": 32.8621,
689
+ "step": 1940
690
+ },
691
+ {
692
+ "epoch": 1.1054932656371201,
693
+ "grad_norm": 190.0,
694
+ "learning_rate": 6.5128900949796484e-06,
695
+ "loss": 32.7915,
696
+ "step": 1960
697
+ },
698
+ {
699
+ "epoch": 1.1167759678442988,
700
+ "grad_norm": 159.0,
701
+ "learning_rate": 6.47412289203334e-06,
702
+ "loss": 32.8263,
703
+ "step": 1980
704
+ },
705
+ {
706
+ "epoch": 1.1280586700514774,
707
+ "grad_norm": 213.0,
708
+ "learning_rate": 6.4353556890870326e-06,
709
+ "loss": 33.4649,
710
+ "step": 2000
711
+ },
712
+ {
713
+ "epoch": 1.1393413722586558,
714
+ "grad_norm": 170.0,
715
+ "learning_rate": 6.396588486140726e-06,
716
+ "loss": 33.0993,
717
+ "step": 2020
718
+ },
719
+ {
720
+ "epoch": 1.1506240744658345,
721
+ "grad_norm": 178.0,
722
+ "learning_rate": 6.3578212831944175e-06,
723
+ "loss": 32.8403,
724
+ "step": 2040
725
+ },
726
+ {
727
+ "epoch": 1.1619067766730131,
728
+ "grad_norm": 192.0,
729
+ "learning_rate": 6.31905408024811e-06,
730
+ "loss": 33.212,
731
+ "step": 2060
732
+ },
733
+ {
734
+ "epoch": 1.1731894788801918,
735
+ "grad_norm": 177.0,
736
+ "learning_rate": 6.280286877301803e-06,
737
+ "loss": 32.9688,
738
+ "step": 2080
739
+ },
740
+ {
741
+ "epoch": 1.1844721810873704,
742
+ "grad_norm": 176.0,
743
+ "learning_rate": 6.241519674355496e-06,
744
+ "loss": 33.0461,
745
+ "step": 2100
746
+ },
747
+ {
748
+ "epoch": 1.195754883294549,
749
+ "grad_norm": 191.0,
750
+ "learning_rate": 6.202752471409188e-06,
751
+ "loss": 33.4505,
752
+ "step": 2120
753
+ },
754
+ {
755
+ "epoch": 1.2070375855017277,
756
+ "grad_norm": 165.0,
757
+ "learning_rate": 6.163985268462881e-06,
758
+ "loss": 33.6436,
759
+ "step": 2140
760
+ },
761
+ {
762
+ "epoch": 1.2183202877089063,
763
+ "grad_norm": 177.0,
764
+ "learning_rate": 6.125218065516574e-06,
765
+ "loss": 32.9951,
766
+ "step": 2160
767
+ },
768
+ {
769
+ "epoch": 1.229602989916085,
770
+ "grad_norm": 181.0,
771
+ "learning_rate": 6.086450862570266e-06,
772
+ "loss": 34.0142,
773
+ "step": 2180
774
+ },
775
+ {
776
+ "epoch": 1.2408856921232636,
777
+ "grad_norm": 174.0,
778
+ "learning_rate": 6.047683659623958e-06,
779
+ "loss": 33.6973,
780
+ "step": 2200
781
+ },
782
+ {
783
+ "epoch": 1.2521683943304422,
784
+ "grad_norm": 160.0,
785
+ "learning_rate": 6.0089164566776515e-06,
786
+ "loss": 32.4556,
787
+ "step": 2220
788
+ },
789
+ {
790
+ "epoch": 1.2634510965376209,
791
+ "grad_norm": 165.0,
792
+ "learning_rate": 5.970149253731343e-06,
793
+ "loss": 33.3473,
794
+ "step": 2240
795
+ },
796
+ {
797
+ "epoch": 1.2747337987447993,
798
+ "grad_norm": 192.0,
799
+ "learning_rate": 5.9313820507850365e-06,
800
+ "loss": 32.9415,
801
+ "step": 2260
802
+ },
803
+ {
804
+ "epoch": 1.286016500951978,
805
+ "grad_norm": 169.0,
806
+ "learning_rate": 5.892614847838729e-06,
807
+ "loss": 33.7312,
808
+ "step": 2280
809
+ },
810
+ {
811
+ "epoch": 1.2972992031591566,
812
+ "grad_norm": 172.0,
813
+ "learning_rate": 5.853847644892422e-06,
814
+ "loss": 33.2523,
815
+ "step": 2300
816
+ },
817
+ {
818
+ "epoch": 1.3085819053663352,
819
+ "grad_norm": 166.0,
820
+ "learning_rate": 5.815080441946114e-06,
821
+ "loss": 33.4629,
822
+ "step": 2320
823
+ },
824
+ {
825
+ "epoch": 1.3198646075735139,
826
+ "grad_norm": 220.0,
827
+ "learning_rate": 5.776313238999806e-06,
828
+ "loss": 33.6943,
829
+ "step": 2340
830
+ },
831
+ {
832
+ "epoch": 1.3311473097806925,
833
+ "grad_norm": 163.0,
834
+ "learning_rate": 5.7375460360535e-06,
835
+ "loss": 33.2026,
836
+ "step": 2360
837
+ },
838
+ {
839
+ "epoch": 1.3424300119878712,
840
+ "grad_norm": 227.0,
841
+ "learning_rate": 5.698778833107191e-06,
842
+ "loss": 33.3166,
843
+ "step": 2380
844
+ },
845
+ {
846
+ "epoch": 1.3537127141950498,
847
+ "grad_norm": 198.0,
848
+ "learning_rate": 5.660011630160885e-06,
849
+ "loss": 33.5236,
850
+ "step": 2400
851
+ },
852
+ {
853
+ "epoch": 1.3649954164022282,
854
+ "grad_norm": 178.0,
855
+ "learning_rate": 5.621244427214577e-06,
856
+ "loss": 33.3746,
857
+ "step": 2420
858
+ },
859
+ {
860
+ "epoch": 1.3762781186094069,
861
+ "grad_norm": 182.0,
862
+ "learning_rate": 5.582477224268269e-06,
863
+ "loss": 33.2293,
864
+ "step": 2440
865
+ },
866
+ {
867
+ "epoch": 1.3875608208165855,
868
+ "grad_norm": 232.0,
869
+ "learning_rate": 5.543710021321962e-06,
870
+ "loss": 34.0862,
871
+ "step": 2460
872
+ },
873
+ {
874
+ "epoch": 1.3988435230237641,
875
+ "grad_norm": 175.0,
876
+ "learning_rate": 5.5049428183756546e-06,
877
+ "loss": 33.4116,
878
+ "step": 2480
879
+ },
880
+ {
881
+ "epoch": 1.4101262252309428,
882
+ "grad_norm": 198.0,
883
+ "learning_rate": 5.466175615429348e-06,
884
+ "loss": 32.8442,
885
+ "step": 2500
886
+ },
887
+ {
888
+ "epoch": 1.4214089274381214,
889
+ "grad_norm": 162.0,
890
+ "learning_rate": 5.4274084124830395e-06,
891
+ "loss": 33.7111,
892
+ "step": 2520
893
+ },
894
+ {
895
+ "epoch": 1.4326916296453,
896
+ "grad_norm": 208.0,
897
+ "learning_rate": 5.388641209536732e-06,
898
+ "loss": 33.0033,
899
+ "step": 2540
900
+ },
901
+ {
902
+ "epoch": 1.4439743318524787,
903
+ "grad_norm": 192.0,
904
+ "learning_rate": 5.349874006590425e-06,
905
+ "loss": 33.8201,
906
+ "step": 2560
907
+ },
908
+ {
909
+ "epoch": 1.4552570340596573,
910
+ "grad_norm": 169.0,
911
+ "learning_rate": 5.311106803644117e-06,
912
+ "loss": 32.9213,
913
+ "step": 2580
914
+ },
915
+ {
916
+ "epoch": 1.466539736266836,
917
+ "grad_norm": 181.0,
918
+ "learning_rate": 5.27233960069781e-06,
919
+ "loss": 33.9638,
920
+ "step": 2600
921
+ },
922
+ {
923
+ "epoch": 1.4778224384740146,
924
+ "grad_norm": 173.0,
925
+ "learning_rate": 5.233572397751503e-06,
926
+ "loss": 33.5811,
927
+ "step": 2620
928
+ },
929
+ {
930
+ "epoch": 1.4891051406811933,
931
+ "grad_norm": 190.0,
932
+ "learning_rate": 5.194805194805194e-06,
933
+ "loss": 33.8197,
934
+ "step": 2640
935
+ },
936
+ {
937
+ "epoch": 1.500387842888372,
938
+ "grad_norm": 197.0,
939
+ "learning_rate": 5.156037991858888e-06,
940
+ "loss": 33.6394,
941
+ "step": 2660
942
+ },
943
+ {
944
+ "epoch": 1.5116705450955505,
945
+ "grad_norm": 290.0,
946
+ "learning_rate": 5.11727078891258e-06,
947
+ "loss": 33.2235,
948
+ "step": 2680
949
+ },
950
+ {
951
+ "epoch": 1.522953247302729,
952
+ "grad_norm": 148.0,
953
+ "learning_rate": 5.0785035859662735e-06,
954
+ "loss": 33.6943,
955
+ "step": 2700
956
+ },
957
+ {
958
+ "epoch": 1.5342359495099076,
959
+ "grad_norm": 183.0,
960
+ "learning_rate": 5.039736383019965e-06,
961
+ "loss": 33.5758,
962
+ "step": 2720
963
+ },
964
+ {
965
+ "epoch": 1.5455186517170862,
966
+ "grad_norm": 175.0,
967
+ "learning_rate": 5.0009691800736585e-06,
968
+ "loss": 34.077,
969
+ "step": 2740
970
+ },
971
+ {
972
+ "epoch": 1.5568013539242649,
973
+ "grad_norm": 178.0,
974
+ "learning_rate": 4.96220197712735e-06,
975
+ "loss": 33.2421,
976
+ "step": 2760
977
+ },
978
+ {
979
+ "epoch": 1.5680840561314435,
980
+ "grad_norm": 169.0,
981
+ "learning_rate": 4.9234347741810434e-06,
982
+ "loss": 34.0267,
983
+ "step": 2780
984
+ },
985
+ {
986
+ "epoch": 1.579366758338622,
987
+ "grad_norm": 171.0,
988
+ "learning_rate": 4.884667571234736e-06,
989
+ "loss": 33.5599,
990
+ "step": 2800
991
+ },
992
+ {
993
+ "epoch": 1.5906494605458006,
994
+ "grad_norm": 206.0,
995
+ "learning_rate": 4.845900368288428e-06,
996
+ "loss": 33.7535,
997
+ "step": 2820
998
+ },
999
+ {
1000
+ "epoch": 1.6019321627529792,
1001
+ "grad_norm": 168.0,
1002
+ "learning_rate": 4.807133165342121e-06,
1003
+ "loss": 33.4231,
1004
+ "step": 2840
1005
+ },
1006
+ {
1007
+ "epoch": 1.6132148649601579,
1008
+ "grad_norm": 208.0,
1009
+ "learning_rate": 4.768365962395813e-06,
1010
+ "loss": 33.1695,
1011
+ "step": 2860
1012
+ },
1013
+ {
1014
+ "epoch": 1.6244975671673365,
1015
+ "grad_norm": 213.0,
1016
+ "learning_rate": 4.729598759449507e-06,
1017
+ "loss": 33.2739,
1018
+ "step": 2880
1019
+ },
1020
+ {
1021
+ "epoch": 1.6357802693745152,
1022
+ "grad_norm": 177.0,
1023
+ "learning_rate": 4.690831556503198e-06,
1024
+ "loss": 33.3967,
1025
+ "step": 2900
1026
+ },
1027
+ {
1028
+ "epoch": 1.6470629715816938,
1029
+ "grad_norm": 234.0,
1030
+ "learning_rate": 4.652064353556891e-06,
1031
+ "loss": 34.2787,
1032
+ "step": 2920
1033
+ },
1034
+ {
1035
+ "epoch": 1.6583456737888724,
1036
+ "grad_norm": 163.0,
1037
+ "learning_rate": 4.613297150610584e-06,
1038
+ "loss": 34.1793,
1039
+ "step": 2940
1040
+ },
1041
+ {
1042
+ "epoch": 1.669628375996051,
1043
+ "grad_norm": 192.0,
1044
+ "learning_rate": 4.574529947664277e-06,
1045
+ "loss": 33.67,
1046
+ "step": 2960
1047
+ },
1048
+ {
1049
+ "epoch": 1.6809110782032297,
1050
+ "grad_norm": 188.0,
1051
+ "learning_rate": 4.535762744717969e-06,
1052
+ "loss": 34.1299,
1053
+ "step": 2980
1054
+ },
1055
+ {
1056
+ "epoch": 1.6921937804104084,
1057
+ "grad_norm": 210.0,
1058
+ "learning_rate": 4.4969955417716615e-06,
1059
+ "loss": 33.6063,
1060
+ "step": 3000
1061
+ },
1062
+ {
1063
+ "epoch": 1.703476482617587,
1064
+ "grad_norm": 222.0,
1065
+ "learning_rate": 4.458228338825354e-06,
1066
+ "loss": 33.864,
1067
+ "step": 3020
1068
+ },
1069
+ {
1070
+ "epoch": 1.7147591848247656,
1071
+ "grad_norm": 167.0,
1072
+ "learning_rate": 4.4194611358790465e-06,
1073
+ "loss": 33.9385,
1074
+ "step": 3040
1075
+ },
1076
+ {
1077
+ "epoch": 1.7260418870319443,
1078
+ "grad_norm": 201.0,
1079
+ "learning_rate": 4.380693932932739e-06,
1080
+ "loss": 33.4324,
1081
+ "step": 3060
1082
+ },
1083
+ {
1084
+ "epoch": 1.737324589239123,
1085
+ "grad_norm": 171.0,
1086
+ "learning_rate": 4.341926729986432e-06,
1087
+ "loss": 33.6625,
1088
+ "step": 3080
1089
+ },
1090
+ {
1091
+ "epoch": 1.7486072914463013,
1092
+ "grad_norm": 166.0,
1093
+ "learning_rate": 4.303159527040125e-06,
1094
+ "loss": 33.1414,
1095
+ "step": 3100
1096
+ },
1097
+ {
1098
+ "epoch": 1.75988999365348,
1099
+ "grad_norm": 151.0,
1100
+ "learning_rate": 4.264392324093816e-06,
1101
+ "loss": 34.045,
1102
+ "step": 3120
1103
+ },
1104
+ {
1105
+ "epoch": 1.7711726958606586,
1106
+ "grad_norm": 179.0,
1107
+ "learning_rate": 4.22562512114751e-06,
1108
+ "loss": 33.642,
1109
+ "step": 3140
1110
+ },
1111
+ {
1112
+ "epoch": 1.7824553980678373,
1113
+ "grad_norm": 204.0,
1114
+ "learning_rate": 4.186857918201202e-06,
1115
+ "loss": 33.6747,
1116
+ "step": 3160
1117
+ },
1118
+ {
1119
+ "epoch": 1.793738100275016,
1120
+ "grad_norm": 156.0,
1121
+ "learning_rate": 4.148090715254895e-06,
1122
+ "loss": 33.6803,
1123
+ "step": 3180
1124
+ },
1125
+ {
1126
+ "epoch": 1.8050208024821943,
1127
+ "grad_norm": 181.0,
1128
+ "learning_rate": 4.109323512308587e-06,
1129
+ "loss": 33.9288,
1130
+ "step": 3200
1131
+ },
1132
+ {
1133
+ "epoch": 1.816303504689373,
1134
+ "grad_norm": 167.0,
1135
+ "learning_rate": 4.07055630936228e-06,
1136
+ "loss": 33.6484,
1137
+ "step": 3220
1138
+ },
1139
+ {
1140
+ "epoch": 1.8275862068965516,
1141
+ "grad_norm": 179.0,
1142
+ "learning_rate": 4.031789106415972e-06,
1143
+ "loss": 33.5411,
1144
+ "step": 3240
1145
+ },
1146
+ {
1147
+ "epoch": 1.8388689091037302,
1148
+ "grad_norm": 202.0,
1149
+ "learning_rate": 3.993021903469665e-06,
1150
+ "loss": 33.7925,
1151
+ "step": 3260
1152
+ },
1153
+ {
1154
+ "epoch": 1.8501516113109089,
1155
+ "grad_norm": 211.0,
1156
+ "learning_rate": 3.954254700523358e-06,
1157
+ "loss": 34.3101,
1158
+ "step": 3280
1159
+ },
1160
+ {
1161
+ "epoch": 1.8614343135180875,
1162
+ "grad_norm": 187.0,
1163
+ "learning_rate": 3.91548749757705e-06,
1164
+ "loss": 33.674,
1165
+ "step": 3300
1166
+ },
1167
+ {
1168
+ "epoch": 1.8727170157252662,
1169
+ "grad_norm": 186.0,
1170
+ "learning_rate": 3.876720294630743e-06,
1171
+ "loss": 34.4049,
1172
+ "step": 3320
1173
+ },
1174
+ {
1175
+ "epoch": 1.8839997179324448,
1176
+ "grad_norm": 170.0,
1177
+ "learning_rate": 3.837953091684435e-06,
1178
+ "loss": 33.3274,
1179
+ "step": 3340
1180
+ },
1181
+ {
1182
+ "epoch": 1.8952824201396234,
1183
+ "grad_norm": 239.0,
1184
+ "learning_rate": 3.799185888738128e-06,
1185
+ "loss": 33.1375,
1186
+ "step": 3360
1187
+ },
1188
+ {
1189
+ "epoch": 1.906565122346802,
1190
+ "grad_norm": 178.0,
1191
+ "learning_rate": 3.7604186857918207e-06,
1192
+ "loss": 34.1163,
1193
+ "step": 3380
1194
+ },
1195
+ {
1196
+ "epoch": 1.9178478245539807,
1197
+ "grad_norm": 185.0,
1198
+ "learning_rate": 3.7216514828455132e-06,
1199
+ "loss": 34.4329,
1200
+ "step": 3400
1201
+ },
1202
+ {
1203
+ "epoch": 1.9291305267611594,
1204
+ "grad_norm": 195.0,
1205
+ "learning_rate": 3.6828842798992053e-06,
1206
+ "loss": 33.4928,
1207
+ "step": 3420
1208
+ },
1209
+ {
1210
+ "epoch": 1.940413228968338,
1211
+ "grad_norm": 162.0,
1212
+ "learning_rate": 3.644117076952898e-06,
1213
+ "loss": 34.0265,
1214
+ "step": 3440
1215
+ },
1216
+ {
1217
+ "epoch": 1.9516959311755167,
1218
+ "grad_norm": 195.0,
1219
+ "learning_rate": 3.6053498740065907e-06,
1220
+ "loss": 33.9424,
1221
+ "step": 3460
1222
+ },
1223
+ {
1224
+ "epoch": 1.9629786333826953,
1225
+ "grad_norm": 185.0,
1226
+ "learning_rate": 3.5665826710602836e-06,
1227
+ "loss": 34.3252,
1228
+ "step": 3480
1229
+ },
1230
+ {
1231
+ "epoch": 1.974261335589874,
1232
+ "grad_norm": 195.0,
1233
+ "learning_rate": 3.527815468113976e-06,
1234
+ "loss": 34.5225,
1235
+ "step": 3500
1236
+ },
1237
+ {
1238
+ "epoch": 1.9855440377970524,
1239
+ "grad_norm": 214.0,
1240
+ "learning_rate": 3.489048265167668e-06,
1241
+ "loss": 34.5155,
1242
+ "step": 3520
1243
+ },
1244
+ {
1245
+ "epoch": 1.996826740004231,
1246
+ "grad_norm": 182.0,
1247
+ "learning_rate": 3.450281062221361e-06,
1248
+ "loss": 34.1097,
1249
+ "step": 3540
1250
+ },
1251
+ {
1252
+ "epoch": 2.007897891545025,
1253
+ "grad_norm": 164.0,
1254
+ "learning_rate": 3.4115138592750535e-06,
1255
+ "loss": 33.4037,
1256
+ "step": 3560
1257
+ },
1258
+ {
1259
+ "epoch": 2.019180593752204,
1260
+ "grad_norm": 164.0,
1261
+ "learning_rate": 3.3727466563287464e-06,
1262
+ "loss": 33.2511,
1263
+ "step": 3580
1264
+ },
1265
+ {
1266
+ "epoch": 2.0304632959593825,
1267
+ "grad_norm": 228.0,
1268
+ "learning_rate": 3.333979453382439e-06,
1269
+ "loss": 33.3459,
1270
+ "step": 3600
1271
+ },
1272
+ {
1273
+ "epoch": 2.041745998166561,
1274
+ "grad_norm": 201.0,
1275
+ "learning_rate": 3.2952122504361313e-06,
1276
+ "loss": 33.6336,
1277
+ "step": 3620
1278
+ },
1279
+ {
1280
+ "epoch": 2.0530287003737393,
1281
+ "grad_norm": 243.0,
1282
+ "learning_rate": 3.2564450474898242e-06,
1283
+ "loss": 33.4227,
1284
+ "step": 3640
1285
+ },
1286
+ {
1287
+ "epoch": 2.064311402580918,
1288
+ "grad_norm": 188.0,
1289
+ "learning_rate": 3.2176778445435163e-06,
1290
+ "loss": 33.9483,
1291
+ "step": 3660
1292
+ },
1293
+ {
1294
+ "epoch": 2.0755941047880966,
1295
+ "grad_norm": 177.0,
1296
+ "learning_rate": 3.1789106415972088e-06,
1297
+ "loss": 32.5607,
1298
+ "step": 3680
1299
+ },
1300
+ {
1301
+ "epoch": 2.0868768069952752,
1302
+ "grad_norm": 195.0,
1303
+ "learning_rate": 3.1401434386509017e-06,
1304
+ "loss": 33.2094,
1305
+ "step": 3700
1306
+ },
1307
+ {
1308
+ "epoch": 2.098159509202454,
1309
+ "grad_norm": 194.0,
1310
+ "learning_rate": 3.101376235704594e-06,
1311
+ "loss": 32.5983,
1312
+ "step": 3720
1313
+ },
1314
+ {
1315
+ "epoch": 2.1094422114096325,
1316
+ "grad_norm": 171.0,
1317
+ "learning_rate": 3.062609032758287e-06,
1318
+ "loss": 33.4583,
1319
+ "step": 3740
1320
+ },
1321
+ {
1322
+ "epoch": 2.120724913616811,
1323
+ "grad_norm": 196.0,
1324
+ "learning_rate": 3.023841829811979e-06,
1325
+ "loss": 33.2525,
1326
+ "step": 3760
1327
+ },
1328
+ {
1329
+ "epoch": 2.13200761582399,
1330
+ "grad_norm": 185.0,
1331
+ "learning_rate": 2.9850746268656716e-06,
1332
+ "loss": 32.8658,
1333
+ "step": 3780
1334
+ },
1335
+ {
1336
+ "epoch": 2.1432903180311684,
1337
+ "grad_norm": 211.0,
1338
+ "learning_rate": 2.9463074239193645e-06,
1339
+ "loss": 33.584,
1340
+ "step": 3800
1341
+ },
1342
+ {
1343
+ "epoch": 2.154573020238347,
1344
+ "grad_norm": 177.0,
1345
+ "learning_rate": 2.907540220973057e-06,
1346
+ "loss": 32.7506,
1347
+ "step": 3820
1348
+ },
1349
+ {
1350
+ "epoch": 2.1658557224455257,
1351
+ "grad_norm": 201.0,
1352
+ "learning_rate": 2.86877301802675e-06,
1353
+ "loss": 33.6909,
1354
+ "step": 3840
1355
+ },
1356
+ {
1357
+ "epoch": 2.1771384246527044,
1358
+ "grad_norm": 187.0,
1359
+ "learning_rate": 2.8300058150804423e-06,
1360
+ "loss": 32.9226,
1361
+ "step": 3860
1362
+ },
1363
+ {
1364
+ "epoch": 2.188421126859883,
1365
+ "grad_norm": 186.0,
1366
+ "learning_rate": 2.7912386121341344e-06,
1367
+ "loss": 33.2277,
1368
+ "step": 3880
1369
+ },
1370
+ {
1371
+ "epoch": 2.1997038290670616,
1372
+ "grad_norm": 198.0,
1373
+ "learning_rate": 2.7524714091878273e-06,
1374
+ "loss": 32.8508,
1375
+ "step": 3900
1376
+ },
1377
+ {
1378
+ "epoch": 2.2109865312742403,
1379
+ "grad_norm": 186.0,
1380
+ "learning_rate": 2.7137042062415198e-06,
1381
+ "loss": 33.2497,
1382
+ "step": 3920
1383
+ },
1384
+ {
1385
+ "epoch": 2.222269233481419,
1386
+ "grad_norm": 222.0,
1387
+ "learning_rate": 2.6749370032952127e-06,
1388
+ "loss": 33.5576,
1389
+ "step": 3940
1390
+ },
1391
+ {
1392
+ "epoch": 2.2335519356885976,
1393
+ "grad_norm": 161.0,
1394
+ "learning_rate": 2.636169800348905e-06,
1395
+ "loss": 33.4056,
1396
+ "step": 3960
1397
+ },
1398
+ {
1399
+ "epoch": 2.244834637895776,
1400
+ "grad_norm": 163.0,
1401
+ "learning_rate": 2.597402597402597e-06,
1402
+ "loss": 33.0674,
1403
+ "step": 3980
1404
+ },
1405
+ {
1406
+ "epoch": 2.256117340102955,
1407
+ "grad_norm": 177.0,
1408
+ "learning_rate": 2.55863539445629e-06,
1409
+ "loss": 32.9768,
1410
+ "step": 4000
1411
+ },
1412
+ {
1413
+ "epoch": 2.2674000423101335,
1414
+ "grad_norm": 220.0,
1415
+ "learning_rate": 2.5198681915099826e-06,
1416
+ "loss": 33.1559,
1417
+ "step": 4020
1418
+ },
1419
+ {
1420
+ "epoch": 2.2786827445173117,
1421
+ "grad_norm": 175.0,
1422
+ "learning_rate": 2.481100988563675e-06,
1423
+ "loss": 33.5091,
1424
+ "step": 4040
1425
+ },
1426
+ {
1427
+ "epoch": 2.2899654467244908,
1428
+ "grad_norm": 180.0,
1429
+ "learning_rate": 2.442333785617368e-06,
1430
+ "loss": 33.3984,
1431
+ "step": 4060
1432
+ },
1433
+ {
1434
+ "epoch": 2.301248148931669,
1435
+ "grad_norm": 192.0,
1436
+ "learning_rate": 2.4035665826710604e-06,
1437
+ "loss": 33.3091,
1438
+ "step": 4080
1439
+ },
1440
+ {
1441
+ "epoch": 2.3125308511388476,
1442
+ "grad_norm": 200.0,
1443
+ "learning_rate": 2.3647993797247533e-06,
1444
+ "loss": 33.9978,
1445
+ "step": 4100
1446
+ },
1447
+ {
1448
+ "epoch": 2.3238135533460262,
1449
+ "grad_norm": 202.0,
1450
+ "learning_rate": 2.3260321767784454e-06,
1451
+ "loss": 33.4988,
1452
+ "step": 4120
1453
+ },
1454
+ {
1455
+ "epoch": 2.335096255553205,
1456
+ "grad_norm": 220.0,
1457
+ "learning_rate": 2.2872649738321383e-06,
1458
+ "loss": 32.5648,
1459
+ "step": 4140
1460
+ },
1461
+ {
1462
+ "epoch": 2.3463789577603835,
1463
+ "grad_norm": 188.0,
1464
+ "learning_rate": 2.2484977708858308e-06,
1465
+ "loss": 33.3508,
1466
+ "step": 4160
1467
+ },
1468
+ {
1469
+ "epoch": 2.357661659967562,
1470
+ "grad_norm": 166.0,
1471
+ "learning_rate": 2.2097305679395232e-06,
1472
+ "loss": 33.5085,
1473
+ "step": 4180
1474
+ },
1475
+ {
1476
+ "epoch": 2.368944362174741,
1477
+ "grad_norm": 192.0,
1478
+ "learning_rate": 2.170963364993216e-06,
1479
+ "loss": 33.5222,
1480
+ "step": 4200
1481
+ },
1482
+ {
1483
+ "epoch": 2.3802270643819194,
1484
+ "grad_norm": 168.0,
1485
+ "learning_rate": 2.132196162046908e-06,
1486
+ "loss": 33.5567,
1487
+ "step": 4220
1488
+ },
1489
+ {
1490
+ "epoch": 2.391509766589098,
1491
+ "grad_norm": 189.0,
1492
+ "learning_rate": 2.093428959100601e-06,
1493
+ "loss": 32.6794,
1494
+ "step": 4240
1495
+ },
1496
+ {
1497
+ "epoch": 2.4027924687962767,
1498
+ "grad_norm": 208.0,
1499
+ "learning_rate": 2.0546617561542936e-06,
1500
+ "loss": 33.1244,
1501
+ "step": 4260
1502
+ },
1503
+ {
1504
+ "epoch": 2.4140751710034554,
1505
+ "grad_norm": 222.0,
1506
+ "learning_rate": 2.015894553207986e-06,
1507
+ "loss": 33.2899,
1508
+ "step": 4280
1509
+ },
1510
+ {
1511
+ "epoch": 2.425357873210634,
1512
+ "grad_norm": 165.0,
1513
+ "learning_rate": 1.977127350261679e-06,
1514
+ "loss": 33.3089,
1515
+ "step": 4300
1516
+ },
1517
+ {
1518
+ "epoch": 2.4366405754178126,
1519
+ "grad_norm": 186.0,
1520
+ "learning_rate": 1.9383601473153714e-06,
1521
+ "loss": 33.8634,
1522
+ "step": 4320
1523
+ },
1524
+ {
1525
+ "epoch": 2.4479232776249913,
1526
+ "grad_norm": 189.0,
1527
+ "learning_rate": 1.899592944369064e-06,
1528
+ "loss": 33.6295,
1529
+ "step": 4340
1530
+ },
1531
+ {
1532
+ "epoch": 2.45920597983217,
1533
+ "grad_norm": 194.0,
1534
+ "learning_rate": 1.8608257414227566e-06,
1535
+ "loss": 33.7899,
1536
+ "step": 4360
1537
+ },
1538
+ {
1539
+ "epoch": 2.4704886820393486,
1540
+ "grad_norm": 176.0,
1541
+ "learning_rate": 1.822058538476449e-06,
1542
+ "loss": 33.4224,
1543
+ "step": 4380
1544
+ },
1545
+ {
1546
+ "epoch": 2.481771384246527,
1547
+ "grad_norm": 178.0,
1548
+ "learning_rate": 1.7832913355301418e-06,
1549
+ "loss": 33.2276,
1550
+ "step": 4400
1551
+ },
1552
+ {
1553
+ "epoch": 2.493054086453706,
1554
+ "grad_norm": 204.0,
1555
+ "learning_rate": 1.744524132583834e-06,
1556
+ "loss": 33.7431,
1557
+ "step": 4420
1558
+ },
1559
+ {
1560
+ "epoch": 2.5043367886608845,
1561
+ "grad_norm": 195.0,
1562
+ "learning_rate": 1.7057569296375267e-06,
1563
+ "loss": 33.1986,
1564
+ "step": 4440
1565
+ },
1566
+ {
1567
+ "epoch": 2.5156194908680627,
1568
+ "grad_norm": 191.0,
1569
+ "learning_rate": 1.6669897266912194e-06,
1570
+ "loss": 33.1506,
1571
+ "step": 4460
1572
+ },
1573
+ {
1574
+ "epoch": 2.5269021930752418,
1575
+ "grad_norm": 193.0,
1576
+ "learning_rate": 1.6282225237449121e-06,
1577
+ "loss": 33.1911,
1578
+ "step": 4480
1579
+ },
1580
+ {
1581
+ "epoch": 2.53818489528242,
1582
+ "grad_norm": 230.0,
1583
+ "learning_rate": 1.5894553207986044e-06,
1584
+ "loss": 33.6828,
1585
+ "step": 4500
1586
+ },
1587
+ {
1588
+ "epoch": 2.5494675974895986,
1589
+ "grad_norm": 219.0,
1590
+ "learning_rate": 1.550688117852297e-06,
1591
+ "loss": 33.9657,
1592
+ "step": 4520
1593
+ },
1594
+ {
1595
+ "epoch": 2.5607502996967773,
1596
+ "grad_norm": 197.0,
1597
+ "learning_rate": 1.5119209149059895e-06,
1598
+ "loss": 33.2005,
1599
+ "step": 4540
1600
+ },
1601
+ {
1602
+ "epoch": 2.572033001903956,
1603
+ "grad_norm": 214.0,
1604
+ "learning_rate": 1.4731537119596822e-06,
1605
+ "loss": 33.5472,
1606
+ "step": 4560
1607
+ },
1608
+ {
1609
+ "epoch": 2.5833157041111345,
1610
+ "grad_norm": 167.0,
1611
+ "learning_rate": 1.434386509013375e-06,
1612
+ "loss": 34.237,
1613
+ "step": 4580
1614
+ },
1615
+ {
1616
+ "epoch": 2.594598406318313,
1617
+ "grad_norm": 162.0,
1618
+ "learning_rate": 1.3956193060670672e-06,
1619
+ "loss": 34.3779,
1620
+ "step": 4600
1621
+ },
1622
+ {
1623
+ "epoch": 2.605881108525492,
1624
+ "grad_norm": 240.0,
1625
+ "learning_rate": 1.3568521031207599e-06,
1626
+ "loss": 33.7256,
1627
+ "step": 4620
1628
+ },
1629
+ {
1630
+ "epoch": 2.6171638107326705,
1631
+ "grad_norm": 187.0,
1632
+ "learning_rate": 1.3180849001744526e-06,
1633
+ "loss": 32.9692,
1634
+ "step": 4640
1635
+ },
1636
+ {
1637
+ "epoch": 2.628446512939849,
1638
+ "grad_norm": 164.0,
1639
+ "learning_rate": 1.279317697228145e-06,
1640
+ "loss": 33.8773,
1641
+ "step": 4660
1642
+ },
1643
+ {
1644
+ "epoch": 2.6397292151470277,
1645
+ "grad_norm": 188.0,
1646
+ "learning_rate": 1.2405504942818375e-06,
1647
+ "loss": 33.5338,
1648
+ "step": 4680
1649
+ },
1650
+ {
1651
+ "epoch": 2.6510119173542064,
1652
+ "grad_norm": 185.0,
1653
+ "learning_rate": 1.2017832913355302e-06,
1654
+ "loss": 33.9084,
1655
+ "step": 4700
1656
+ },
1657
+ {
1658
+ "epoch": 2.662294619561385,
1659
+ "grad_norm": 190.0,
1660
+ "learning_rate": 1.1630160883892227e-06,
1661
+ "loss": 33.0886,
1662
+ "step": 4720
1663
+ },
1664
+ {
1665
+ "epoch": 2.6735773217685637,
1666
+ "grad_norm": 169.0,
1667
+ "learning_rate": 1.1242488854429154e-06,
1668
+ "loss": 33.0422,
1669
+ "step": 4740
1670
+ },
1671
+ {
1672
+ "epoch": 2.6848600239757423,
1673
+ "grad_norm": 185.0,
1674
+ "learning_rate": 1.085481682496608e-06,
1675
+ "loss": 33.4596,
1676
+ "step": 4760
1677
+ },
1678
+ {
1679
+ "epoch": 2.696142726182921,
1680
+ "grad_norm": 169.0,
1681
+ "learning_rate": 1.0467144795503006e-06,
1682
+ "loss": 33.3788,
1683
+ "step": 4780
1684
+ },
1685
+ {
1686
+ "epoch": 2.7074254283900996,
1687
+ "grad_norm": 214.0,
1688
+ "learning_rate": 1.007947276603993e-06,
1689
+ "loss": 33.6668,
1690
+ "step": 4800
1691
+ },
1692
+ {
1693
+ "epoch": 2.7187081305972782,
1694
+ "grad_norm": 170.0,
1695
+ "learning_rate": 9.691800736576857e-07,
1696
+ "loss": 33.1791,
1697
+ "step": 4820
1698
+ },
1699
+ {
1700
+ "epoch": 2.7299908328044564,
1701
+ "grad_norm": 192.0,
1702
+ "learning_rate": 9.304128707113783e-07,
1703
+ "loss": 33.7457,
1704
+ "step": 4840
1705
+ },
1706
+ {
1707
+ "epoch": 2.7412735350116355,
1708
+ "grad_norm": 171.0,
1709
+ "learning_rate": 8.916456677650709e-07,
1710
+ "loss": 33.7942,
1711
+ "step": 4860
1712
+ },
1713
+ {
1714
+ "epoch": 2.7525562372188137,
1715
+ "grad_norm": 164.0,
1716
+ "learning_rate": 8.528784648187634e-07,
1717
+ "loss": 33.0871,
1718
+ "step": 4880
1719
+ },
1720
+ {
1721
+ "epoch": 2.763838939425993,
1722
+ "grad_norm": 179.0,
1723
+ "learning_rate": 8.141112618724561e-07,
1724
+ "loss": 33.5948,
1725
+ "step": 4900
1726
+ },
1727
+ {
1728
+ "epoch": 2.775121641633171,
1729
+ "grad_norm": 197.0,
1730
+ "learning_rate": 7.753440589261485e-07,
1731
+ "loss": 33.451,
1732
+ "step": 4920
1733
+ },
1734
+ {
1735
+ "epoch": 2.7864043438403496,
1736
+ "grad_norm": 176.0,
1737
+ "learning_rate": 7.365768559798411e-07,
1738
+ "loss": 33.3747,
1739
+ "step": 4940
1740
+ },
1741
+ {
1742
+ "epoch": 2.7976870460475283,
1743
+ "grad_norm": 221.0,
1744
+ "learning_rate": 6.978096530335336e-07,
1745
+ "loss": 33.7778,
1746
+ "step": 4960
1747
+ },
1748
+ {
1749
+ "epoch": 2.808969748254707,
1750
+ "grad_norm": 198.0,
1751
+ "learning_rate": 6.590424500872263e-07,
1752
+ "loss": 33.2167,
1753
+ "step": 4980
1754
+ },
1755
+ {
1756
+ "epoch": 2.8202524504618856,
1757
+ "grad_norm": 208.0,
1758
+ "learning_rate": 6.202752471409188e-07,
1759
+ "loss": 33.0164,
1760
+ "step": 5000
1761
+ },
1762
+ {
1763
+ "epoch": 2.831535152669064,
1764
+ "grad_norm": 199.0,
1765
+ "learning_rate": 5.815080441946113e-07,
1766
+ "loss": 32.8762,
1767
+ "step": 5020
1768
+ },
1769
+ {
1770
+ "epoch": 2.842817854876243,
1771
+ "grad_norm": 205.0,
1772
+ "learning_rate": 5.42740841248304e-07,
1773
+ "loss": 34.0191,
1774
+ "step": 5040
1775
+ },
1776
+ {
1777
+ "epoch": 2.8541005570834215,
1778
+ "grad_norm": 180.0,
1779
+ "learning_rate": 5.039736383019965e-07,
1780
+ "loss": 33.2017,
1781
+ "step": 5060
1782
+ },
1783
+ {
1784
+ "epoch": 2.8653832592906,
1785
+ "grad_norm": 188.0,
1786
+ "learning_rate": 4.6520643535568915e-07,
1787
+ "loss": 33.3916,
1788
+ "step": 5080
1789
+ },
1790
+ {
1791
+ "epoch": 2.8766659614977788,
1792
+ "grad_norm": 203.0,
1793
+ "learning_rate": 4.264392324093817e-07,
1794
+ "loss": 33.0174,
1795
+ "step": 5100
1796
+ },
1797
+ {
1798
+ "epoch": 2.8879486637049574,
1799
+ "grad_norm": 162.0,
1800
+ "learning_rate": 3.8767202946307427e-07,
1801
+ "loss": 33.8547,
1802
+ "step": 5120
1803
+ },
1804
+ {
1805
+ "epoch": 2.899231365912136,
1806
+ "grad_norm": 247.0,
1807
+ "learning_rate": 3.489048265167668e-07,
1808
+ "loss": 34.1972,
1809
+ "step": 5140
1810
+ },
1811
+ {
1812
+ "epoch": 2.9105140681193147,
1813
+ "grad_norm": 178.0,
1814
+ "learning_rate": 3.101376235704594e-07,
1815
+ "loss": 33.093,
1816
+ "step": 5160
1817
+ },
1818
+ {
1819
+ "epoch": 2.9217967703264933,
1820
+ "grad_norm": 170.0,
1821
+ "learning_rate": 2.71370420624152e-07,
1822
+ "loss": 33.1222,
1823
+ "step": 5180
1824
+ },
1825
+ {
1826
+ "epoch": 2.933079472533672,
1827
+ "grad_norm": 197.0,
1828
+ "learning_rate": 2.3260321767784458e-07,
1829
+ "loss": 32.5735,
1830
+ "step": 5200
1831
+ },
1832
+ {
1833
+ "epoch": 2.94436217474085,
1834
+ "grad_norm": 213.0,
1835
+ "learning_rate": 1.9383601473153713e-07,
1836
+ "loss": 33.4369,
1837
+ "step": 5220
1838
+ },
1839
+ {
1840
+ "epoch": 2.9556448769480292,
1841
+ "grad_norm": 181.0,
1842
+ "learning_rate": 1.550688117852297e-07,
1843
+ "loss": 33.7,
1844
+ "step": 5240
1845
+ },
1846
+ {
1847
+ "epoch": 2.9669275791552074,
1848
+ "grad_norm": 165.0,
1849
+ "learning_rate": 1.1630160883892229e-07,
1850
+ "loss": 33.2835,
1851
+ "step": 5260
1852
+ },
1853
+ {
1854
+ "epoch": 2.9782102813623865,
1855
+ "grad_norm": 219.0,
1856
+ "learning_rate": 7.753440589261485e-08,
1857
+ "loss": 33.8382,
1858
+ "step": 5280
1859
+ },
1860
+ {
1861
+ "epoch": 2.9894929835695647,
1862
+ "grad_norm": 185.0,
1863
+ "learning_rate": 3.876720294630742e-08,
1864
+ "loss": 33.0738,
1865
+ "step": 5300
1866
+ }
1867
+ ],
1868
+ "logging_steps": 20,
1869
+ "max_steps": 5319,
1870
+ "num_input_tokens_seen": 0,
1871
+ "num_train_epochs": 3,
1872
+ "save_steps": 500,
1873
+ "stateful_callbacks": {
1874
+ "TrainerControl": {
1875
+ "args": {
1876
+ "should_epoch_stop": false,
1877
+ "should_evaluate": false,
1878
+ "should_log": false,
1879
+ "should_save": true,
1880
+ "should_training_stop": true
1881
+ },
1882
+ "attributes": {}
1883
+ }
1884
+ },
1885
+ "total_flos": 0.0,
1886
+ "train_batch_size": 2,
1887
+ "trial_name": null,
1888
+ "trial_params": null
1889
+ }
checkpoint-5319/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c7a3d84d5c920a1183e32aa8591078ae7fabd64ef9226b2cb2211eab73f936d
3
+ size 5841
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 896,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4864,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention"
38
+ ],
39
+ "max_position_embeddings": 32768,
40
+ "max_window_layers": 24,
41
+ "model_type": "qwen2",
42
+ "num_attention_heads": 14,
43
+ "num_hidden_layers": 24,
44
+ "num_key_value_heads": 2,
45
+ "rms_norm_eps": 1e-06,
46
+ "rope_parameters": {
47
+ "rope_theta": 1000000.0,
48
+ "rope_type": "default"
49
+ },
50
+ "rope_scaling": null,
51
+ "rope_theta": 10000.0,
52
+ "sliding_window": null,
53
+ "tie_word_embeddings": true,
54
+ "transformers_version": "4.57.6",
55
+ "use_cache": false,
56
+ "use_mrope": false,
57
+ "use_sliding_window": false,
58
+ "vocab_size": 152167
59
+ }
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": "4.57.6"
6
+ }
logs/events.out.tfevents.1778526155.2183d5a8cefc.13908.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf81cddabbf983157940411d6251d2f8b03f8a28226e4c4138db7070f846c07f
3
+ size 60546
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 sha256:9a6e66bb661216ba066dceeec096a278a9dadfee176dc5a646b3bdf0a3ba1add
3
+ size 988511776
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
+ }
speech_patch_encoder.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c0f570f2683201791a0ee26ba903b810df779669661f76bb43f2c188df7747b
3
+ size 25702953
speech_token_meta.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_name_or_path": "train/qwen_freeze_emb",
3
+ "text_vocab_size": 151665,
4
+ "s_id": 151665,
5
+ "t_id": 151666,
6
+ "hubert_offset": 151667,
7
+ "total_vocab_size": 152167,
8
+ "codebook_size": 500,
9
+ "patch_mode": "align",
10
+ "patch_size": 4,
11
+ "max_patch_length": 32,
12
+ "pooling": "mean",
13
+ "local_layers": 1,
14
+ "local_heads": 8,
15
+ "cross_heads": 8,
16
+ "bidirectional_local_encoder": false,
17
+ "input_embeddings_frozen": true,
18
+ "freeze_lm_head": false,
19
+ "objective": "speech_patches_to_text_only",
20
+ "patch_encoder_state": "speech_patch_encoder.pt"
21
+ }
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 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|endoftext|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff