jeiku commited on
Commit
49604a8
·
verified ·
1 Parent(s): c0a0519

Upload 10 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|finetune_right_pad_id|>": 151646,
4
+ "<|im_end|>": 151645,
5
+ "<|im_start|>": 151644
6
+ }
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2-1.5B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 1536,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 8960,
12
+ "max_position_embeddings": 32768,
13
+ "max_window_layers": 28,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 12,
16
+ "num_hidden_layers": 28,
17
+ "num_key_value_heads": 2,
18
+ "rms_norm_eps": 1e-06,
19
+ "rope_theta": 1000000.0,
20
+ "sliding_window": null,
21
+ "tie_word_embeddings": true,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.45.0.dev0",
24
+ "use_cache": false,
25
+ "use_sliding_window": false,
26
+ "vocab_size": 151936
27
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.45.0.dev0"
14
+ }
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:e730482c3c1de436e09867df4f2d26c7cc1933c8b8e3c96480e3394138c12fc2
3
+ size 3087467144
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|finetune_right_pad_id|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|finetune_right_pad_id|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "additional_special_tokens": [
38
+ "<|im_start|>",
39
+ "<|im_end|>"
40
+ ],
41
+ "bos_token": null,
42
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
43
+ "clean_up_tokenization_spaces": false,
44
+ "eos_token": "<|im_end|>",
45
+ "errors": "replace",
46
+ "model_max_length": 32768,
47
+ "pad_token": "<|finetune_right_pad_id|>",
48
+ "split_special_tokens": false,
49
+ "tokenizer_class": "Qwen2Tokenizer",
50
+ "unk_token": null
51
+ }
trainer_state.json ADDED
@@ -0,0 +1,1119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9923175416133163,
5
+ "eval_steps": 19,
6
+ "global_step": 146,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.013663535439795047,
13
+ "grad_norm": 2.015625,
14
+ "learning_rate": 5.714285714285714e-07,
15
+ "loss": 2.0297,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.013663535439795047,
20
+ "eval_loss": 2.0118041038513184,
21
+ "eval_runtime": 36.5931,
22
+ "eval_samples_per_second": 13.472,
23
+ "eval_steps_per_second": 3.389,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.027327070879590094,
28
+ "grad_norm": 1.96875,
29
+ "learning_rate": 1.1428571428571428e-06,
30
+ "loss": 2.0165,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.04099060631938514,
35
+ "grad_norm": 2.03125,
36
+ "learning_rate": 1.714285714285714e-06,
37
+ "loss": 2.031,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.05465414175918019,
42
+ "grad_norm": 1.9921875,
43
+ "learning_rate": 2.2857142857142856e-06,
44
+ "loss": 2.0347,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.06831767719897523,
49
+ "grad_norm": 1.875,
50
+ "learning_rate": 2.8571428571428573e-06,
51
+ "loss": 2.0388,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.08198121263877028,
56
+ "grad_norm": 1.765625,
57
+ "learning_rate": 3.428571428571428e-06,
58
+ "loss": 2.0397,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.09564474807856532,
63
+ "grad_norm": 1.53125,
64
+ "learning_rate": 4e-06,
65
+ "loss": 2.0434,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.10930828351836037,
70
+ "grad_norm": 1.4140625,
71
+ "learning_rate": 4.571428571428571e-06,
72
+ "loss": 2.0087,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.12297181895815543,
77
+ "grad_norm": 1.1640625,
78
+ "learning_rate": 5.142857142857143e-06,
79
+ "loss": 2.0519,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.13663535439795046,
84
+ "grad_norm": 0.9765625,
85
+ "learning_rate": 5.7142857142857145e-06,
86
+ "loss": 1.9951,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.1502988898377455,
91
+ "grad_norm": 0.875,
92
+ "learning_rate": 6.285714285714285e-06,
93
+ "loss": 2.0071,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.16396242527754057,
98
+ "grad_norm": 0.87109375,
99
+ "learning_rate": 6.857142857142856e-06,
100
+ "loss": 2.0082,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.1776259607173356,
105
+ "grad_norm": 0.88671875,
106
+ "learning_rate": 7.428571428571428e-06,
107
+ "loss": 1.9933,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.19128949615713065,
112
+ "grad_norm": 0.90625,
113
+ "learning_rate": 8e-06,
114
+ "loss": 2.0326,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.2049530315969257,
119
+ "grad_norm": 0.87890625,
120
+ "learning_rate": 7.998867178772516e-06,
121
+ "loss": 2.0448,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.21861656703672075,
126
+ "grad_norm": 0.78515625,
127
+ "learning_rate": 7.995469356732032e-06,
128
+ "loss": 2.0034,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.2322801024765158,
133
+ "grad_norm": 0.7109375,
134
+ "learning_rate": 7.989808458441014e-06,
135
+ "loss": 1.9929,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.24594363791631085,
140
+ "grad_norm": 0.703125,
141
+ "learning_rate": 7.981887690292338e-06,
142
+ "loss": 1.949,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.2596071733561059,
147
+ "grad_norm": 0.68359375,
148
+ "learning_rate": 7.971711538693153e-06,
149
+ "loss": 2.0034,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.2596071733561059,
154
+ "eval_loss": 1.9669320583343506,
155
+ "eval_runtime": 36.3557,
156
+ "eval_samples_per_second": 13.56,
157
+ "eval_steps_per_second": 3.411,
158
+ "step": 19
159
+ },
160
+ {
161
+ "epoch": 0.27327070879590093,
162
+ "grad_norm": 0.65234375,
163
+ "learning_rate": 7.95928576752373e-06,
164
+ "loss": 2.0095,
165
+ "step": 20
166
+ },
167
+ {
168
+ "epoch": 0.28693424423569597,
169
+ "grad_norm": 0.61328125,
170
+ "learning_rate": 7.944617414872746e-06,
171
+ "loss": 2.0096,
172
+ "step": 21
173
+ },
174
+ {
175
+ "epoch": 0.300597779675491,
176
+ "grad_norm": 0.65625,
177
+ "learning_rate": 7.927714789050827e-06,
178
+ "loss": 2.0187,
179
+ "step": 22
180
+ },
181
+ {
182
+ "epoch": 0.3142613151152861,
183
+ "grad_norm": 0.57421875,
184
+ "learning_rate": 7.908587463884638e-06,
185
+ "loss": 1.9755,
186
+ "step": 23
187
+ },
188
+ {
189
+ "epoch": 0.32792485055508114,
190
+ "grad_norm": 0.54296875,
191
+ "learning_rate": 7.887246273294166e-06,
192
+ "loss": 1.9908,
193
+ "step": 24
194
+ },
195
+ {
196
+ "epoch": 0.3415883859948762,
197
+ "grad_norm": 0.53515625,
198
+ "learning_rate": 7.863703305156273e-06,
199
+ "loss": 1.9447,
200
+ "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.3552519214346712,
204
+ "grad_norm": 0.5625,
205
+ "learning_rate": 7.837971894457989e-06,
206
+ "loss": 1.9833,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.36891545687446625,
211
+ "grad_norm": 0.55859375,
212
+ "learning_rate": 7.810066615743442e-06,
213
+ "loss": 2.0089,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.3825789923142613,
218
+ "grad_norm": 0.50390625,
219
+ "learning_rate": 7.780003274858673e-06,
220
+ "loss": 2.0116,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.3962425277540564,
225
+ "grad_norm": 0.5078125,
226
+ "learning_rate": 7.747798899999048e-06,
227
+ "loss": 2.0061,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.4099060631938514,
232
+ "grad_norm": 0.49609375,
233
+ "learning_rate": 7.71347173206429e-06,
234
+ "loss": 1.923,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.42356959863364646,
239
+ "grad_norm": 0.51171875,
240
+ "learning_rate": 7.677041214326663e-06,
241
+ "loss": 1.9959,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.4372331340734415,
246
+ "grad_norm": 0.478515625,
247
+ "learning_rate": 7.638527981418074e-06,
248
+ "loss": 1.9421,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.45089666951323654,
253
+ "grad_norm": 0.470703125,
254
+ "learning_rate": 7.5979538476424126e-06,
255
+ "loss": 1.9684,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.4645602049530316,
260
+ "grad_norm": 0.45703125,
261
+ "learning_rate": 7.555341794619694e-06,
262
+ "loss": 1.9564,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.47822374039282667,
267
+ "grad_norm": 0.455078125,
268
+ "learning_rate": 7.510715958269022e-06,
269
+ "loss": 1.9902,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.4918872758326217,
274
+ "grad_norm": 0.462890625,
275
+ "learning_rate": 7.4641016151377545e-06,
276
+ "loss": 1.983,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.5055508112724167,
281
+ "grad_norm": 0.47265625,
282
+ "learning_rate": 7.415525168084592e-06,
283
+ "loss": 1.9775,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.5192143467122118,
288
+ "grad_norm": 0.451171875,
289
+ "learning_rate": 7.365014131324725e-06,
290
+ "loss": 1.9595,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.5192143467122118,
295
+ "eval_loss": 1.9398664236068726,
296
+ "eval_runtime": 36.4379,
297
+ "eval_samples_per_second": 13.53,
298
+ "eval_steps_per_second": 3.403,
299
+ "step": 38
300
+ },
301
+ {
302
+ "epoch": 0.5328778821520068,
303
+ "grad_norm": 0.44140625,
304
+ "learning_rate": 7.3125971148454824e-06,
305
+ "loss": 1.9414,
306
+ "step": 39
307
+ },
308
+ {
309
+ "epoch": 0.5465414175918019,
310
+ "grad_norm": 0.498046875,
311
+ "learning_rate": 7.258303808201343e-06,
312
+ "loss": 1.9589,
313
+ "step": 40
314
+ },
315
+ {
316
+ "epoch": 0.5602049530315969,
317
+ "grad_norm": 0.4609375,
318
+ "learning_rate": 7.202164963697441e-06,
319
+ "loss": 1.9913,
320
+ "step": 41
321
+ },
322
+ {
323
+ "epoch": 0.5738684884713919,
324
+ "grad_norm": 0.447265625,
325
+ "learning_rate": 7.1442123789711495e-06,
326
+ "loss": 1.9872,
327
+ "step": 42
328
+ },
329
+ {
330
+ "epoch": 0.587532023911187,
331
+ "grad_norm": 0.451171875,
332
+ "learning_rate": 7.08447887898155e-06,
333
+ "loss": 1.9749,
334
+ "step": 43
335
+ },
336
+ {
337
+ "epoch": 0.601195559350982,
338
+ "grad_norm": 0.4375,
339
+ "learning_rate": 7.022998297417033e-06,
340
+ "loss": 1.9547,
341
+ "step": 44
342
+ },
343
+ {
344
+ "epoch": 0.6148590947907772,
345
+ "grad_norm": 0.451171875,
346
+ "learning_rate": 6.959805457531536e-06,
347
+ "loss": 1.959,
348
+ "step": 45
349
+ },
350
+ {
351
+ "epoch": 0.6285226302305722,
352
+ "grad_norm": 0.43359375,
353
+ "learning_rate": 6.89493615242028e-06,
354
+ "loss": 1.9369,
355
+ "step": 46
356
+ },
357
+ {
358
+ "epoch": 0.6421861656703672,
359
+ "grad_norm": 0.44921875,
360
+ "learning_rate": 6.82842712474619e-06,
361
+ "loss": 1.9256,
362
+ "step": 47
363
+ },
364
+ {
365
+ "epoch": 0.6558497011101623,
366
+ "grad_norm": 0.42578125,
367
+ "learning_rate": 6.760316045928448e-06,
368
+ "loss": 1.9476,
369
+ "step": 48
370
+ },
371
+ {
372
+ "epoch": 0.6695132365499573,
373
+ "grad_norm": 0.43359375,
374
+ "learning_rate": 6.690641494805011e-06,
375
+ "loss": 1.9738,
376
+ "step": 49
377
+ },
378
+ {
379
+ "epoch": 0.6831767719897524,
380
+ "grad_norm": 0.421875,
381
+ "learning_rate": 6.619442935781141e-06,
382
+ "loss": 1.9385,
383
+ "step": 50
384
+ },
385
+ {
386
+ "epoch": 0.6968403074295474,
387
+ "grad_norm": 0.470703125,
388
+ "learning_rate": 6.546760696476353e-06,
389
+ "loss": 2.0047,
390
+ "step": 51
391
+ },
392
+ {
393
+ "epoch": 0.7105038428693424,
394
+ "grad_norm": 0.419921875,
395
+ "learning_rate": 6.472635944882421e-06,
396
+ "loss": 1.9871,
397
+ "step": 52
398
+ },
399
+ {
400
+ "epoch": 0.7241673783091375,
401
+ "grad_norm": 0.421875,
402
+ "learning_rate": 6.397110666045387e-06,
403
+ "loss": 1.9662,
404
+ "step": 53
405
+ },
406
+ {
407
+ "epoch": 0.7378309137489325,
408
+ "grad_norm": 0.447265625,
409
+ "learning_rate": 6.3202276382847925e-06,
410
+ "loss": 1.9604,
411
+ "step": 54
412
+ },
413
+ {
414
+ "epoch": 0.7514944491887275,
415
+ "grad_norm": 0.43359375,
416
+ "learning_rate": 6.242030408963575e-06,
417
+ "loss": 1.9581,
418
+ "step": 55
419
+ },
420
+ {
421
+ "epoch": 0.7651579846285226,
422
+ "grad_norm": 0.419921875,
423
+ "learning_rate": 6.162563269822391e-06,
424
+ "loss": 1.9354,
425
+ "step": 56
426
+ },
427
+ {
428
+ "epoch": 0.7788215200683177,
429
+ "grad_norm": 0.431640625,
430
+ "learning_rate": 6.081871231892289e-06,
431
+ "loss": 1.9519,
432
+ "step": 57
433
+ },
434
+ {
435
+ "epoch": 0.7788215200683177,
436
+ "eval_loss": 1.9265698194503784,
437
+ "eval_runtime": 36.375,
438
+ "eval_samples_per_second": 13.553,
439
+ "eval_steps_per_second": 3.409,
440
+ "step": 57
441
+ },
442
+ {
443
+ "epoch": 0.7924850555081128,
444
+ "grad_norm": 0.40625,
445
+ "learning_rate": 6e-06,
446
+ "loss": 1.9568,
447
+ "step": 58
448
+ },
449
+ {
450
+ "epoch": 0.8061485909479078,
451
+ "grad_norm": 0.416015625,
452
+ "learning_rate": 5.916995946880227e-06,
453
+ "loss": 1.9888,
454
+ "step": 59
455
+ },
456
+ {
457
+ "epoch": 0.8198121263877028,
458
+ "grad_norm": 0.41015625,
459
+ "learning_rate": 5.832906086909641e-06,
460
+ "loss": 1.9502,
461
+ "step": 60
462
+ },
463
+ {
464
+ "epoch": 0.8334756618274979,
465
+ "grad_norm": 0.404296875,
466
+ "learning_rate": 5.7477780494774375e-06,
467
+ "loss": 1.987,
468
+ "step": 61
469
+ },
470
+ {
471
+ "epoch": 0.8471391972672929,
472
+ "grad_norm": 0.412109375,
473
+ "learning_rate": 5.661660052007546e-06,
474
+ "loss": 1.9504,
475
+ "step": 62
476
+ },
477
+ {
478
+ "epoch": 0.860802732707088,
479
+ "grad_norm": 0.423828125,
480
+ "learning_rate": 5.574600872647766e-06,
481
+ "loss": 1.9838,
482
+ "step": 63
483
+ },
484
+ {
485
+ "epoch": 0.874466268146883,
486
+ "grad_norm": 0.421875,
487
+ "learning_rate": 5.48664982264131e-06,
488
+ "loss": 1.9554,
489
+ "step": 64
490
+ },
491
+ {
492
+ "epoch": 0.888129803586678,
493
+ "grad_norm": 0.419921875,
494
+ "learning_rate": 5.397856718396394e-06,
495
+ "loss": 1.994,
496
+ "step": 65
497
+ },
498
+ {
499
+ "epoch": 0.9017933390264731,
500
+ "grad_norm": 0.416015625,
501
+ "learning_rate": 5.308271853269687e-06,
502
+ "loss": 1.9496,
503
+ "step": 66
504
+ },
505
+ {
506
+ "epoch": 0.9154568744662681,
507
+ "grad_norm": 0.396484375,
508
+ "learning_rate": 5.2179459690796286e-06,
509
+ "loss": 1.9508,
510
+ "step": 67
511
+ },
512
+ {
513
+ "epoch": 0.9291204099060631,
514
+ "grad_norm": 0.40234375,
515
+ "learning_rate": 5.126930227365719e-06,
516
+ "loss": 1.9268,
517
+ "step": 68
518
+ },
519
+ {
520
+ "epoch": 0.9427839453458582,
521
+ "grad_norm": 0.4140625,
522
+ "learning_rate": 5.035276180410083e-06,
523
+ "loss": 1.9589,
524
+ "step": 69
525
+ },
526
+ {
527
+ "epoch": 0.9564474807856533,
528
+ "grad_norm": 0.439453125,
529
+ "learning_rate": 4.943035742037709e-06,
530
+ "loss": 1.9929,
531
+ "step": 70
532
+ },
533
+ {
534
+ "epoch": 0.9701110162254484,
535
+ "grad_norm": 0.396484375,
536
+ "learning_rate": 4.850261158211906e-06,
537
+ "loss": 1.9219,
538
+ "step": 71
539
+ },
540
+ {
541
+ "epoch": 0.9837745516652434,
542
+ "grad_norm": 0.41015625,
543
+ "learning_rate": 4.7570049774416405e-06,
544
+ "loss": 1.9546,
545
+ "step": 72
546
+ },
547
+ {
548
+ "epoch": 0.9974380871050385,
549
+ "grad_norm": 0.400390625,
550
+ "learning_rate": 4.663320021017497e-06,
551
+ "loss": 1.9449,
552
+ "step": 73
553
+ },
554
+ {
555
+ "epoch": 1.0089628681177978,
556
+ "grad_norm": 0.427734375,
557
+ "learning_rate": 4.569259353093141e-06,
558
+ "loss": 1.972,
559
+ "step": 74
560
+ },
561
+ {
562
+ "epoch": 1.0226205719163466,
563
+ "grad_norm": 0.400390625,
564
+ "learning_rate": 4.47487625062922e-06,
565
+ "loss": 1.9305,
566
+ "step": 75
567
+ },
568
+ {
569
+ "epoch": 1.0362782757148954,
570
+ "grad_norm": 0.4296875,
571
+ "learning_rate": 4.38022417321673e-06,
572
+ "loss": 1.9479,
573
+ "step": 76
574
+ },
575
+ {
576
+ "epoch": 1.0362782757148954,
577
+ "eval_loss": 1.9197667837142944,
578
+ "eval_runtime": 36.1856,
579
+ "eval_samples_per_second": 13.624,
580
+ "eval_steps_per_second": 3.427,
581
+ "step": 76
582
+ },
583
+ {
584
+ "epoch": 1.0499359795134442,
585
+ "grad_norm": 0.466796875,
586
+ "learning_rate": 4.285356732796929e-06,
587
+ "loss": 1.9611,
588
+ "step": 77
589
+ },
590
+ {
591
+ "epoch": 1.0635936833119932,
592
+ "grad_norm": 0.40234375,
593
+ "learning_rate": 4.1903276632949695e-06,
594
+ "loss": 1.9134,
595
+ "step": 78
596
+ },
597
+ {
598
+ "epoch": 1.077251387110542,
599
+ "grad_norm": 0.3984375,
600
+ "learning_rate": 4.09519079018443e-06,
601
+ "loss": 1.9607,
602
+ "step": 79
603
+ },
604
+ {
605
+ "epoch": 1.0909090909090908,
606
+ "grad_norm": 0.412109375,
607
+ "learning_rate": 4e-06,
608
+ "loss": 1.9168,
609
+ "step": 80
610
+ },
611
+ {
612
+ "epoch": 1.1045667947076399,
613
+ "grad_norm": 0.41796875,
614
+ "learning_rate": 3.90480920981557e-06,
615
+ "loss": 1.9901,
616
+ "step": 81
617
+ },
618
+ {
619
+ "epoch": 1.1182244985061887,
620
+ "grad_norm": 0.40234375,
621
+ "learning_rate": 3.8096723367050306e-06,
622
+ "loss": 1.9429,
623
+ "step": 82
624
+ },
625
+ {
626
+ "epoch": 1.1318822023047375,
627
+ "grad_norm": 0.39453125,
628
+ "learning_rate": 3.7146432672030706e-06,
629
+ "loss": 1.9432,
630
+ "step": 83
631
+ },
632
+ {
633
+ "epoch": 1.1455399061032865,
634
+ "grad_norm": 0.4140625,
635
+ "learning_rate": 3.61977582678327e-06,
636
+ "loss": 1.9166,
637
+ "step": 84
638
+ },
639
+ {
640
+ "epoch": 1.1591976099018353,
641
+ "grad_norm": 0.416015625,
642
+ "learning_rate": 3.52512374937078e-06,
643
+ "loss": 1.9604,
644
+ "step": 85
645
+ },
646
+ {
647
+ "epoch": 1.172855313700384,
648
+ "grad_norm": 0.40234375,
649
+ "learning_rate": 3.4307406469068596e-06,
650
+ "loss": 1.9634,
651
+ "step": 86
652
+ },
653
+ {
654
+ "epoch": 1.186513017498933,
655
+ "grad_norm": 0.3984375,
656
+ "learning_rate": 3.336679978982504e-06,
657
+ "loss": 1.9572,
658
+ "step": 87
659
+ },
660
+ {
661
+ "epoch": 1.200170721297482,
662
+ "grad_norm": 0.396484375,
663
+ "learning_rate": 3.2429950225583604e-06,
664
+ "loss": 1.9414,
665
+ "step": 88
666
+ },
667
+ {
668
+ "epoch": 1.2138284250960307,
669
+ "grad_norm": 0.396484375,
670
+ "learning_rate": 3.149738841788093e-06,
671
+ "loss": 1.9492,
672
+ "step": 89
673
+ },
674
+ {
675
+ "epoch": 1.2274861288945795,
676
+ "grad_norm": 0.408203125,
677
+ "learning_rate": 3.0569642579622904e-06,
678
+ "loss": 1.9323,
679
+ "step": 90
680
+ },
681
+ {
682
+ "epoch": 1.2411438326931286,
683
+ "grad_norm": 0.41015625,
684
+ "learning_rate": 2.9647238195899164e-06,
685
+ "loss": 1.9547,
686
+ "step": 91
687
+ },
688
+ {
689
+ "epoch": 1.2548015364916774,
690
+ "grad_norm": 0.4140625,
691
+ "learning_rate": 2.873069772634281e-06,
692
+ "loss": 1.9388,
693
+ "step": 92
694
+ },
695
+ {
696
+ "epoch": 1.2684592402902262,
697
+ "grad_norm": 0.3984375,
698
+ "learning_rate": 2.7820540309203724e-06,
699
+ "loss": 1.9594,
700
+ "step": 93
701
+ },
702
+ {
703
+ "epoch": 1.282116944088775,
704
+ "grad_norm": 0.3984375,
705
+ "learning_rate": 2.6917281467303133e-06,
706
+ "loss": 1.912,
707
+ "step": 94
708
+ },
709
+ {
710
+ "epoch": 1.295774647887324,
711
+ "grad_norm": 0.400390625,
712
+ "learning_rate": 2.602143281603607e-06,
713
+ "loss": 1.9381,
714
+ "step": 95
715
+ },
716
+ {
717
+ "epoch": 1.295774647887324,
718
+ "eval_loss": 1.9166765213012695,
719
+ "eval_runtime": 36.3011,
720
+ "eval_samples_per_second": 13.581,
721
+ "eval_steps_per_second": 3.416,
722
+ "step": 95
723
+ },
724
+ {
725
+ "epoch": 1.3094323516858728,
726
+ "grad_norm": 0.392578125,
727
+ "learning_rate": 2.5133501773586904e-06,
728
+ "loss": 1.9297,
729
+ "step": 96
730
+ },
731
+ {
732
+ "epoch": 1.3230900554844216,
733
+ "grad_norm": 0.408203125,
734
+ "learning_rate": 2.4253991273522344e-06,
735
+ "loss": 1.94,
736
+ "step": 97
737
+ },
738
+ {
739
+ "epoch": 1.3367477592829706,
740
+ "grad_norm": 0.40625,
741
+ "learning_rate": 2.3383399479924544e-06,
742
+ "loss": 1.9836,
743
+ "step": 98
744
+ },
745
+ {
746
+ "epoch": 1.3504054630815194,
747
+ "grad_norm": 0.40234375,
748
+ "learning_rate": 2.252221950522562e-06,
749
+ "loss": 1.936,
750
+ "step": 99
751
+ },
752
+ {
753
+ "epoch": 1.3640631668800682,
754
+ "grad_norm": 0.41015625,
755
+ "learning_rate": 2.1670939130903583e-06,
756
+ "loss": 2.0112,
757
+ "step": 100
758
+ },
759
+ {
760
+ "epoch": 1.3777208706786173,
761
+ "grad_norm": 0.408203125,
762
+ "learning_rate": 2.0830040531197743e-06,
763
+ "loss": 1.9661,
764
+ "step": 101
765
+ },
766
+ {
767
+ "epoch": 1.391378574477166,
768
+ "grad_norm": 0.40234375,
769
+ "learning_rate": 2.0000000000000008e-06,
770
+ "loss": 1.9627,
771
+ "step": 102
772
+ },
773
+ {
774
+ "epoch": 1.4050362782757149,
775
+ "grad_norm": 0.40234375,
776
+ "learning_rate": 1.9181287681077113e-06,
777
+ "loss": 1.9496,
778
+ "step": 103
779
+ },
780
+ {
781
+ "epoch": 1.418693982074264,
782
+ "grad_norm": 0.396484375,
783
+ "learning_rate": 1.837436730177611e-06,
784
+ "loss": 1.9493,
785
+ "step": 104
786
+ },
787
+ {
788
+ "epoch": 1.4323516858728127,
789
+ "grad_norm": 0.41015625,
790
+ "learning_rate": 1.7579695910364233e-06,
791
+ "loss": 1.9523,
792
+ "step": 105
793
+ },
794
+ {
795
+ "epoch": 1.4460093896713615,
796
+ "grad_norm": 0.3984375,
797
+ "learning_rate": 1.6797723617152077e-06,
798
+ "loss": 1.9495,
799
+ "step": 106
800
+ },
801
+ {
802
+ "epoch": 1.4596670934699103,
803
+ "grad_norm": 0.39453125,
804
+ "learning_rate": 1.6028893339546122e-06,
805
+ "loss": 1.9722,
806
+ "step": 107
807
+ },
808
+ {
809
+ "epoch": 1.473324797268459,
810
+ "grad_norm": 0.400390625,
811
+ "learning_rate": 1.527364055117579e-06,
812
+ "loss": 1.9264,
813
+ "step": 108
814
+ },
815
+ {
816
+ "epoch": 1.4869825010670081,
817
+ "grad_norm": 0.392578125,
818
+ "learning_rate": 1.4532393035236475e-06,
819
+ "loss": 1.9395,
820
+ "step": 109
821
+ },
822
+ {
823
+ "epoch": 1.500640204865557,
824
+ "grad_norm": 0.421875,
825
+ "learning_rate": 1.38055706421886e-06,
826
+ "loss": 1.927,
827
+ "step": 110
828
+ },
829
+ {
830
+ "epoch": 1.5142979086641057,
831
+ "grad_norm": 0.412109375,
832
+ "learning_rate": 1.3093585051949898e-06,
833
+ "loss": 1.9362,
834
+ "step": 111
835
+ },
836
+ {
837
+ "epoch": 1.5279556124626548,
838
+ "grad_norm": 0.412109375,
839
+ "learning_rate": 1.2396839540715527e-06,
840
+ "loss": 1.9238,
841
+ "step": 112
842
+ },
843
+ {
844
+ "epoch": 1.5416133162612036,
845
+ "grad_norm": 0.3984375,
846
+ "learning_rate": 1.1715728752538101e-06,
847
+ "loss": 1.9462,
848
+ "step": 113
849
+ },
850
+ {
851
+ "epoch": 1.5552710200597524,
852
+ "grad_norm": 0.400390625,
853
+ "learning_rate": 1.1050638475797191e-06,
854
+ "loss": 1.9258,
855
+ "step": 114
856
+ },
857
+ {
858
+ "epoch": 1.5552710200597524,
859
+ "eval_loss": 1.9157997369766235,
860
+ "eval_runtime": 36.0542,
861
+ "eval_samples_per_second": 13.674,
862
+ "eval_steps_per_second": 3.439,
863
+ "step": 114
864
+ },
865
+ {
866
+ "epoch": 1.5689287238583014,
867
+ "grad_norm": 0.400390625,
868
+ "learning_rate": 1.0401945424684652e-06,
869
+ "loss": 1.9553,
870
+ "step": 115
871
+ },
872
+ {
873
+ "epoch": 1.5825864276568502,
874
+ "grad_norm": 0.3828125,
875
+ "learning_rate": 9.770017025829674e-07,
876
+ "loss": 1.9163,
877
+ "step": 116
878
+ },
879
+ {
880
+ "epoch": 1.596244131455399,
881
+ "grad_norm": 0.412109375,
882
+ "learning_rate": 9.155211210184495e-07,
883
+ "loss": 1.9958,
884
+ "step": 117
885
+ },
886
+ {
887
+ "epoch": 1.609901835253948,
888
+ "grad_norm": 0.40234375,
889
+ "learning_rate": 8.557876210288508e-07,
890
+ "loss": 1.9564,
891
+ "step": 118
892
+ },
893
+ {
894
+ "epoch": 1.6235595390524968,
895
+ "grad_norm": 0.42578125,
896
+ "learning_rate": 7.978350363025587e-07,
897
+ "loss": 1.984,
898
+ "step": 119
899
+ },
900
+ {
901
+ "epoch": 1.6372172428510456,
902
+ "grad_norm": 0.412109375,
903
+ "learning_rate": 7.416961917986571e-07,
904
+ "loss": 1.9543,
905
+ "step": 120
906
+ },
907
+ {
908
+ "epoch": 1.6508749466495947,
909
+ "grad_norm": 0.390625,
910
+ "learning_rate": 6.874028851545173e-07,
911
+ "loss": 1.927,
912
+ "step": 121
913
+ },
914
+ {
915
+ "epoch": 1.6645326504481432,
916
+ "grad_norm": 0.427734375,
917
+ "learning_rate": 6.349858686752747e-07,
918
+ "loss": 1.9333,
919
+ "step": 122
920
+ },
921
+ {
922
+ "epoch": 1.6781903542466923,
923
+ "grad_norm": 0.412109375,
924
+ "learning_rate": 5.844748319154078e-07,
925
+ "loss": 1.9837,
926
+ "step": 123
927
+ },
928
+ {
929
+ "epoch": 1.6918480580452413,
930
+ "grad_norm": 0.416015625,
931
+ "learning_rate": 5.358983848622451e-07,
932
+ "loss": 1.9233,
933
+ "step": 124
934
+ },
935
+ {
936
+ "epoch": 1.7055057618437899,
937
+ "grad_norm": 0.4140625,
938
+ "learning_rate": 4.892840417309774e-07,
939
+ "loss": 1.9787,
940
+ "step": 125
941
+ },
942
+ {
943
+ "epoch": 1.719163465642339,
944
+ "grad_norm": 0.390625,
945
+ "learning_rate": 4.4465820538030653e-07,
946
+ "loss": 1.9822,
947
+ "step": 126
948
+ },
949
+ {
950
+ "epoch": 1.7328211694408877,
951
+ "grad_norm": 0.392578125,
952
+ "learning_rate": 4.0204615235758734e-07,
953
+ "loss": 1.9564,
954
+ "step": 127
955
+ },
956
+ {
957
+ "epoch": 1.7464788732394365,
958
+ "grad_norm": 0.3984375,
959
+ "learning_rate": 3.6147201858192623e-07,
960
+ "loss": 1.9345,
961
+ "step": 128
962
+ },
963
+ {
964
+ "epoch": 1.7601365770379855,
965
+ "grad_norm": 0.396484375,
966
+ "learning_rate": 3.229587856733378e-07,
967
+ "loss": 1.9379,
968
+ "step": 129
969
+ },
970
+ {
971
+ "epoch": 1.7737942808365343,
972
+ "grad_norm": 0.39453125,
973
+ "learning_rate": 2.865282679357097e-07,
974
+ "loss": 1.9308,
975
+ "step": 130
976
+ },
977
+ {
978
+ "epoch": 1.7874519846350831,
979
+ "grad_norm": 0.40234375,
980
+ "learning_rate": 2.522011000009536e-07,
981
+ "loss": 1.9508,
982
+ "step": 131
983
+ },
984
+ {
985
+ "epoch": 1.8011096884336322,
986
+ "grad_norm": 0.40625,
987
+ "learning_rate": 2.1999672514132617e-07,
988
+ "loss": 1.9122,
989
+ "step": 132
990
+ },
991
+ {
992
+ "epoch": 1.814767392232181,
993
+ "grad_norm": 0.41015625,
994
+ "learning_rate": 1.8993338425655802e-07,
995
+ "loss": 1.9508,
996
+ "step": 133
997
+ },
998
+ {
999
+ "epoch": 1.814767392232181,
1000
+ "eval_loss": 1.915639042854309,
1001
+ "eval_runtime": 36.4567,
1002
+ "eval_samples_per_second": 13.523,
1003
+ "eval_steps_per_second": 3.401,
1004
+ "step": 133
1005
+ },
1006
+ {
1007
+ "epoch": 1.8284250960307298,
1008
+ "grad_norm": 0.412109375,
1009
+ "learning_rate": 1.6202810554201097e-07,
1010
+ "loss": 1.9649,
1011
+ "step": 134
1012
+ },
1013
+ {
1014
+ "epoch": 1.8420827998292788,
1015
+ "grad_norm": 0.39453125,
1016
+ "learning_rate": 1.3629669484372718e-07,
1017
+ "loss": 1.9101,
1018
+ "step": 135
1019
+ },
1020
+ {
1021
+ "epoch": 1.8557405036278276,
1022
+ "grad_norm": 0.396484375,
1023
+ "learning_rate": 1.1275372670583338e-07,
1024
+ "loss": 1.9386,
1025
+ "step": 136
1026
+ },
1027
+ {
1028
+ "epoch": 1.8693982074263764,
1029
+ "grad_norm": 0.3984375,
1030
+ "learning_rate": 9.141253611536238e-08,
1031
+ "loss": 1.9315,
1032
+ "step": 137
1033
+ },
1034
+ {
1035
+ "epoch": 1.8830559112249254,
1036
+ "grad_norm": 0.408203125,
1037
+ "learning_rate": 7.228521094917317e-08,
1038
+ "loss": 1.929,
1039
+ "step": 138
1040
+ },
1041
+ {
1042
+ "epoch": 1.896713615023474,
1043
+ "grad_norm": 0.400390625,
1044
+ "learning_rate": 5.5382585127254025e-08,
1045
+ "loss": 1.9361,
1046
+ "step": 139
1047
+ },
1048
+ {
1049
+ "epoch": 1.910371318822023,
1050
+ "grad_norm": 0.3984375,
1051
+ "learning_rate": 4.071423247626926e-08,
1052
+ "loss": 1.961,
1053
+ "step": 140
1054
+ },
1055
+ {
1056
+ "epoch": 1.924029022620572,
1057
+ "grad_norm": 0.421875,
1058
+ "learning_rate": 2.828846130684681e-08,
1059
+ "loss": 1.9462,
1060
+ "step": 141
1061
+ },
1062
+ {
1063
+ "epoch": 1.9376867264191207,
1064
+ "grad_norm": 0.40234375,
1065
+ "learning_rate": 1.8112309707661643e-08,
1066
+ "loss": 1.9729,
1067
+ "step": 142
1068
+ },
1069
+ {
1070
+ "epoch": 1.9513444302176697,
1071
+ "grad_norm": 0.40625,
1072
+ "learning_rate": 1.0191541558985939e-08,
1073
+ "loss": 1.9747,
1074
+ "step": 143
1075
+ },
1076
+ {
1077
+ "epoch": 1.9650021340162185,
1078
+ "grad_norm": 0.388671875,
1079
+ "learning_rate": 4.5306432679681486e-09,
1080
+ "loss": 1.916,
1081
+ "step": 144
1082
+ },
1083
+ {
1084
+ "epoch": 1.9786598378147673,
1085
+ "grad_norm": 0.3828125,
1086
+ "learning_rate": 1.1328212274839266e-09,
1087
+ "loss": 1.9484,
1088
+ "step": 145
1089
+ },
1090
+ {
1091
+ "epoch": 1.9923175416133163,
1092
+ "grad_norm": 0.3984375,
1093
+ "learning_rate": 0.0,
1094
+ "loss": 1.9286,
1095
+ "step": 146
1096
+ }
1097
+ ],
1098
+ "logging_steps": 1,
1099
+ "max_steps": 146,
1100
+ "num_input_tokens_seen": 0,
1101
+ "num_train_epochs": 2,
1102
+ "save_steps": 37,
1103
+ "stateful_callbacks": {
1104
+ "TrainerControl": {
1105
+ "args": {
1106
+ "should_epoch_stop": false,
1107
+ "should_evaluate": false,
1108
+ "should_log": false,
1109
+ "should_save": true,
1110
+ "should_training_stop": true
1111
+ },
1112
+ "attributes": {}
1113
+ }
1114
+ },
1115
+ "total_flos": 1.2034879291926774e+18,
1116
+ "train_batch_size": 4,
1117
+ "trial_name": null,
1118
+ "trial_params": null
1119
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff