ahmedalhammadi commited on
Commit
17fd767
1 Parent(s): 0cdee70

Model save

Browse files
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: gpt2
3
+ library_name: transformers
4
+ model_name: gpt2-cpt-wiki
5
+ tags:
6
+ - generated_from_trainer
7
+ - trl
8
+ - sft
9
+ licence: license
10
+ ---
11
+
12
+ # Model Card for gpt2-cpt-wiki
13
+
14
+ This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2).
15
+ It has been trained using [TRL](https://github.com/huggingface/trl).
16
+
17
+ ## Quick start
18
+
19
+ ```python
20
+ from transformers import pipeline
21
+
22
+ question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
23
+ generator = pipeline("text-generation", model="ahmedalhammadi/gpt2-cpt-wiki", device="cuda")
24
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
25
+ print(output["generated_text"])
26
+ ```
27
+
28
+ ## Training procedure
29
+
30
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ahmed-alhammadi-technology-innovation-institute/huggingface/runs/f3thys5q)
31
+
32
+ This model was trained with SFT.
33
+
34
+ ### Framework versions
35
+
36
+ - TRL: 0.12.0
37
+ - Transformers: 4.46.1
38
+ - Pytorch: 2.5.1
39
+ - Datasets: 3.1.0
40
+ - Tokenizers: 0.20.1
41
+
42
+ ## Citations
43
+
44
+
45
+
46
+ Cite TRL as:
47
+
48
+ ```bibtex
49
+ @misc{vonwerra2022trl,
50
+ title = {{TRL: Transformer Reinforcement Learning}},
51
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
52
+ year = 2020,
53
+ journal = {GitHub repository},
54
+ publisher = {GitHub},
55
+ howpublished = {\url{https://github.com/huggingface/trl}}
56
+ }
57
+ ```
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 82545915985920.0,
4
+ "train_loss": 3.1589166365606935,
5
+ "train_runtime": 248.1689,
6
+ "train_samples": 29567,
7
+ "train_samples_per_second": 445.922,
8
+ "train_steps_per_second": 3.486
9
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.46.1"
6
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 82545915985920.0,
4
+ "train_loss": 3.1589166365606935,
5
+ "train_runtime": 248.1689,
6
+ "train_samples": 29567,
7
+ "train_samples_per_second": 445.922,
8
+ "train_steps_per_second": 3.486
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1260 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 865,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0011560693641618498,
13
+ "grad_norm": 2.560949806695945,
14
+ "learning_rate": 2.2988505747126437e-06,
15
+ "loss": 3.4668,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.005780346820809248,
20
+ "grad_norm": 2.6052409820203866,
21
+ "learning_rate": 1.1494252873563218e-05,
22
+ "loss": 3.5049,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.011560693641618497,
27
+ "grad_norm": 1.6807278319503598,
28
+ "learning_rate": 2.2988505747126437e-05,
29
+ "loss": 3.4523,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.017341040462427744,
34
+ "grad_norm": 1.3872646318135757,
35
+ "learning_rate": 3.4482758620689657e-05,
36
+ "loss": 3.4305,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.023121387283236993,
41
+ "grad_norm": 0.8854199637857243,
42
+ "learning_rate": 4.597701149425287e-05,
43
+ "loss": 3.3984,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.028901734104046242,
48
+ "grad_norm": 1.1428954815654415,
49
+ "learning_rate": 5.747126436781609e-05,
50
+ "loss": 3.3641,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.03468208092485549,
55
+ "grad_norm": 0.7871424143353113,
56
+ "learning_rate": 6.896551724137931e-05,
57
+ "loss": 3.3285,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.04046242774566474,
62
+ "grad_norm": 0.6942416545211347,
63
+ "learning_rate": 8.045977011494253e-05,
64
+ "loss": 3.3348,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.046242774566473986,
69
+ "grad_norm": 0.7481862396744489,
70
+ "learning_rate": 9.195402298850575e-05,
71
+ "loss": 3.3031,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.05202312138728324,
76
+ "grad_norm": 0.7349744692819005,
77
+ "learning_rate": 0.00010344827586206898,
78
+ "loss": 3.3055,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.057803468208092484,
83
+ "grad_norm": 0.787528126925392,
84
+ "learning_rate": 0.00011494252873563218,
85
+ "loss": 3.266,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.06358381502890173,
90
+ "grad_norm": 0.6011067877083208,
91
+ "learning_rate": 0.0001264367816091954,
92
+ "loss": 3.2738,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.06936416184971098,
97
+ "grad_norm": 0.549726888731836,
98
+ "learning_rate": 0.00013793103448275863,
99
+ "loss": 3.252,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.07514450867052024,
104
+ "grad_norm": 0.4802594608855168,
105
+ "learning_rate": 0.00014942528735632183,
106
+ "loss": 3.2551,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.08092485549132948,
111
+ "grad_norm": 0.43506119404453325,
112
+ "learning_rate": 0.00016091954022988506,
113
+ "loss": 3.2531,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.08670520231213873,
118
+ "grad_norm": 0.43739695740996304,
119
+ "learning_rate": 0.00017241379310344826,
120
+ "loss": 3.2492,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.09248554913294797,
125
+ "grad_norm": 0.4001379123552416,
126
+ "learning_rate": 0.0001839080459770115,
127
+ "loss": 3.2371,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.09826589595375723,
132
+ "grad_norm": 0.3953084727624265,
133
+ "learning_rate": 0.00019540229885057472,
134
+ "loss": 3.2332,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.10404624277456648,
139
+ "grad_norm": 0.39141010946909405,
140
+ "learning_rate": 0.00019999266250608563,
141
+ "loss": 3.2234,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.10982658959537572,
146
+ "grad_norm": 0.3844664555693112,
147
+ "learning_rate": 0.00019994782616487538,
148
+ "loss": 3.2328,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.11560693641618497,
153
+ "grad_norm": 0.38501166250330954,
154
+ "learning_rate": 0.00019986224812243038,
155
+ "loss": 3.2289,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.12138728323699421,
160
+ "grad_norm": 0.367871059973961,
161
+ "learning_rate": 0.00019973596326290137,
162
+ "loss": 3.2289,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.12716763005780346,
167
+ "grad_norm": 0.3652422215592574,
168
+ "learning_rate": 0.00019956902306374636,
169
+ "loss": 3.2293,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.1329479768786127,
174
+ "grad_norm": 0.37757220530617325,
175
+ "learning_rate": 0.00019936149557474666,
176
+ "loss": 3.2363,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.13872832369942195,
181
+ "grad_norm": 0.3718158923309793,
182
+ "learning_rate": 0.00019911346539026794,
183
+ "loss": 3.2098,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.14450867052023122,
188
+ "grad_norm": 0.36307234840760944,
189
+ "learning_rate": 0.00019882503361477705,
190
+ "loss": 3.2133,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.15028901734104047,
195
+ "grad_norm": 0.36600016095606147,
196
+ "learning_rate": 0.0001984963178216287,
197
+ "loss": 3.2086,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.15606936416184972,
202
+ "grad_norm": 0.3476602101989908,
203
+ "learning_rate": 0.00019812745200513927,
204
+ "loss": 3.218,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.16184971098265896,
209
+ "grad_norm": 0.34906685233203877,
210
+ "learning_rate": 0.00019771858652596657,
211
+ "loss": 3.2246,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.1676300578034682,
216
+ "grad_norm": 0.3532865591665223,
217
+ "learning_rate": 0.00019726988804981844,
218
+ "loss": 3.1898,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.17341040462427745,
223
+ "grad_norm": 0.40460405755243584,
224
+ "learning_rate": 0.00019678153947951497,
225
+ "loss": 3.218,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.1791907514450867,
230
+ "grad_norm": 0.3304140989868754,
231
+ "learning_rate": 0.00019625373988043165,
232
+ "loss": 3.1992,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.18497109826589594,
237
+ "grad_norm": 0.308497812696352,
238
+ "learning_rate": 0.00019568670439935458,
239
+ "loss": 3.209,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.1907514450867052,
244
+ "grad_norm": 0.34528327664611236,
245
+ "learning_rate": 0.00019508066417678018,
246
+ "loss": 3.1914,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.19653179190751446,
251
+ "grad_norm": 0.4165583915689433,
252
+ "learning_rate": 0.00019443586625269562,
253
+ "loss": 3.1977,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.2023121387283237,
258
+ "grad_norm": 0.3650545500594017,
259
+ "learning_rate": 0.00019375257346587773,
260
+ "loss": 3.1801,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.20809248554913296,
265
+ "grad_norm": 0.33959159442022663,
266
+ "learning_rate": 0.00019303106434675224,
267
+ "loss": 3.1965,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.2138728323699422,
272
+ "grad_norm": 0.3590182979681496,
273
+ "learning_rate": 0.00019227163300385662,
274
+ "loss": 3.1719,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.21965317919075145,
279
+ "grad_norm": 0.41052957903807297,
280
+ "learning_rate": 0.00019147458900395245,
281
+ "loss": 3.1926,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.2254335260115607,
286
+ "grad_norm": 0.3794250436125987,
287
+ "learning_rate": 0.0001906402572458371,
288
+ "loss": 3.2074,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.23121387283236994,
293
+ "grad_norm": 0.3198984083774458,
294
+ "learning_rate": 0.00018976897782790512,
295
+ "loss": 3.1859,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.23699421965317918,
300
+ "grad_norm": 0.3163734942392586,
301
+ "learning_rate": 0.00018886110590951417,
302
+ "loss": 3.2047,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.24277456647398843,
307
+ "grad_norm": 0.31805084628607355,
308
+ "learning_rate": 0.0001879170115662114,
309
+ "loss": 3.1871,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.24855491329479767,
314
+ "grad_norm": 0.3432486403670197,
315
+ "learning_rate": 0.00018693707963887978,
316
+ "loss": 3.175,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.2543352601156069,
321
+ "grad_norm": 0.3138776566225917,
322
+ "learning_rate": 0.00018592170957686552,
323
+ "loss": 3.1988,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.26011560693641617,
328
+ "grad_norm": 0.30587921809108115,
329
+ "learning_rate": 0.0001848713152751506,
330
+ "loss": 3.1762,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.2658959537572254,
335
+ "grad_norm": 0.2997567171818308,
336
+ "learning_rate": 0.0001837863249056369,
337
+ "loss": 3.2027,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.27167630057803466,
342
+ "grad_norm": 0.335691454347307,
343
+ "learning_rate": 0.00018266718074261062,
344
+ "loss": 3.1688,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.2774566473988439,
349
+ "grad_norm": 0.3307527141328154,
350
+ "learning_rate": 0.00018151433898245826,
351
+ "loss": 3.1766,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.2832369942196532,
356
+ "grad_norm": 0.3141072784060351,
357
+ "learning_rate": 0.00018032826955770724,
358
+ "loss": 3.173,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.28901734104046245,
363
+ "grad_norm": 0.4424843940179431,
364
+ "learning_rate": 0.00017910945594546757,
365
+ "loss": 3.1637,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.2947976878612717,
370
+ "grad_norm": 0.30077059480155643,
371
+ "learning_rate": 0.00017785839497035222,
372
+ "loss": 3.1809,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.30057803468208094,
377
+ "grad_norm": 0.31634582525373184,
378
+ "learning_rate": 0.0001765755966019566,
379
+ "loss": 3.1828,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.3063583815028902,
384
+ "grad_norm": 0.29644760955094585,
385
+ "learning_rate": 0.00017526158374698,
386
+ "loss": 3.1691,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.31213872832369943,
391
+ "grad_norm": 0.29157149074265853,
392
+ "learning_rate": 0.0001739168920360729,
393
+ "loss": 3.1512,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.3179190751445087,
398
+ "grad_norm": 0.30009452294520444,
399
+ "learning_rate": 0.00017254206960549842,
400
+ "loss": 3.1816,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.3236994219653179,
405
+ "grad_norm": 0.349631013624792,
406
+ "learning_rate": 0.0001711376768736956,
407
+ "loss": 3.1547,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.32947976878612717,
412
+ "grad_norm": 0.33261830331078257,
413
+ "learning_rate": 0.000169704286312836,
414
+ "loss": 3.1684,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.3352601156069364,
419
+ "grad_norm": 0.29085302891804077,
420
+ "learning_rate": 0.00016824248221546735,
421
+ "loss": 3.1492,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.34104046242774566,
426
+ "grad_norm": 0.30061007694463854,
427
+ "learning_rate": 0.00016675286045633828,
428
+ "loss": 3.143,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.3468208092485549,
433
+ "grad_norm": 0.4170871249784612,
434
+ "learning_rate": 0.00016523602824950235,
435
+ "loss": 3.1484,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.35260115606936415,
440
+ "grad_norm": 0.2819705568636163,
441
+ "learning_rate": 0.00016369260390079933,
442
+ "loss": 3.1379,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.3583815028901734,
447
+ "grad_norm": 0.28557604100223866,
448
+ "learning_rate": 0.00016212321655581554,
449
+ "loss": 3.1453,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.36416184971098264,
454
+ "grad_norm": 0.29258283786258643,
455
+ "learning_rate": 0.00016052850594342534,
456
+ "loss": 3.1465,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.3699421965317919,
461
+ "grad_norm": 0.41981326824430054,
462
+ "learning_rate": 0.00015890912211501877,
463
+ "loss": 3.1355,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.37572254335260113,
468
+ "grad_norm": 0.27912148893790856,
469
+ "learning_rate": 0.00015726572517952122,
470
+ "loss": 3.1457,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.3815028901734104,
475
+ "grad_norm": 0.33056252135761416,
476
+ "learning_rate": 0.00015559898503431335,
477
+ "loss": 3.1422,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.3872832369942196,
482
+ "grad_norm": 0.3051613612126159,
483
+ "learning_rate": 0.0001539095810921612,
484
+ "loss": 3.159,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.3930635838150289,
489
+ "grad_norm": 0.2838497459947755,
490
+ "learning_rate": 0.00015219820200426727,
491
+ "loss": 3.1469,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.3988439306358382,
496
+ "grad_norm": 0.31465121621009734,
497
+ "learning_rate": 0.00015046554537955585,
498
+ "loss": 3.1395,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.4046242774566474,
503
+ "grad_norm": 0.33199154940321435,
504
+ "learning_rate": 0.00014871231750030698,
505
+ "loss": 3.1535,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.41040462427745666,
510
+ "grad_norm": 0.2789325679223692,
511
+ "learning_rate": 0.0001469392330342548,
512
+ "loss": 3.1359,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.4161849710982659,
517
+ "grad_norm": 0.26987258223987126,
518
+ "learning_rate": 0.0001451470147432676,
519
+ "loss": 3.1238,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.42196531791907516,
524
+ "grad_norm": 0.3824587738393317,
525
+ "learning_rate": 0.0001433363931887289,
526
+ "loss": 3.1187,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.4277456647398844,
531
+ "grad_norm": 0.31988281654092277,
532
+ "learning_rate": 0.0001415081064337388,
533
+ "loss": 3.1285,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.43352601156069365,
538
+ "grad_norm": 0.30612731851250463,
539
+ "learning_rate": 0.0001396628997422575,
540
+ "loss": 3.1437,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.4393063583815029,
545
+ "grad_norm": 0.28986666743465456,
546
+ "learning_rate": 0.00013780152527531362,
547
+ "loss": 3.1352,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.44508670520231214,
552
+ "grad_norm": 0.31394710597647135,
553
+ "learning_rate": 0.00013592474178440115,
554
+ "loss": 3.1621,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.4508670520231214,
559
+ "grad_norm": 0.4294903312732592,
560
+ "learning_rate": 0.00013403331430218964,
561
+ "loss": 3.1426,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.45664739884393063,
566
+ "grad_norm": 0.4265226280273843,
567
+ "learning_rate": 0.0001321280138306743,
568
+ "loss": 3.134,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.4624277456647399,
573
+ "grad_norm": 0.38492594733609664,
574
+ "learning_rate": 0.0001302096170268926,
575
+ "loss": 3.1453,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.4682080924855491,
580
+ "grad_norm": 0.29848798247224545,
581
+ "learning_rate": 0.0001282789058863359,
582
+ "loss": 3.1445,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.47398843930635837,
587
+ "grad_norm": 0.3447604928374673,
588
+ "learning_rate": 0.0001263366674241847,
589
+ "loss": 3.1395,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.4797687861271676,
594
+ "grad_norm": 0.3080929535135385,
595
+ "learning_rate": 0.0001243836933544982,
596
+ "loss": 3.1324,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.48554913294797686,
601
+ "grad_norm": 0.314220865898827,
602
+ "learning_rate": 0.00012242077976748784,
603
+ "loss": 3.1301,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.4913294797687861,
608
+ "grad_norm": 0.28685031067517336,
609
+ "learning_rate": 0.00012044872680500742,
610
+ "loss": 3.1313,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.49710982658959535,
615
+ "grad_norm": 0.2956236061720464,
616
+ "learning_rate": 0.00011846833833439153,
617
+ "loss": 3.1348,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.5028901734104047,
622
+ "grad_norm": 0.30651808915001155,
623
+ "learning_rate": 0.00011648042162077534,
624
+ "loss": 3.152,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.5086705202312138,
629
+ "grad_norm": 0.4239949281706778,
630
+ "learning_rate": 0.00011448578699802933,
631
+ "loss": 3.1437,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.5144508670520231,
636
+ "grad_norm": 0.27791759340010475,
637
+ "learning_rate": 0.00011248524753844325,
638
+ "loss": 3.1504,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.5202312138728323,
643
+ "grad_norm": 0.3326391549276525,
644
+ "learning_rate": 0.00011047961872129362,
645
+ "loss": 3.1398,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.5260115606936416,
650
+ "grad_norm": 0.3999790516242622,
651
+ "learning_rate": 0.00010846971810043016,
652
+ "loss": 3.1383,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.5317919075144508,
657
+ "grad_norm": 0.36328178971277675,
658
+ "learning_rate": 0.00010645636497101672,
659
+ "loss": 3.1367,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.5375722543352601,
664
+ "grad_norm": 0.30511312613079056,
665
+ "learning_rate": 0.000104440380035562,
666
+ "loss": 3.1348,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.5433526011560693,
671
+ "grad_norm": 0.34508796373702927,
672
+ "learning_rate": 0.00010242258506937705,
673
+ "loss": 3.1273,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.5491329479768786,
678
+ "grad_norm": 0.31298227959915587,
679
+ "learning_rate": 0.00010040380258559519,
680
+ "loss": 3.1055,
681
+ "step": 475
682
+ },
683
+ {
684
+ "epoch": 0.5549132947976878,
685
+ "grad_norm": 0.41126045157836544,
686
+ "learning_rate": 9.838485549989117e-05,
687
+ "loss": 3.1391,
688
+ "step": 480
689
+ },
690
+ {
691
+ "epoch": 0.5606936416184971,
692
+ "grad_norm": 0.31695235717793374,
693
+ "learning_rate": 9.636656679503647e-05,
694
+ "loss": 3.1027,
695
+ "step": 485
696
+ },
697
+ {
698
+ "epoch": 0.5664739884393064,
699
+ "grad_norm": 0.31731839716923793,
700
+ "learning_rate": 9.434975918542687e-05,
701
+ "loss": 3.1238,
702
+ "step": 490
703
+ },
704
+ {
705
+ "epoch": 0.5722543352601156,
706
+ "grad_norm": 0.30368775602371734,
707
+ "learning_rate": 9.233525478171985e-05,
708
+ "loss": 3.1328,
709
+ "step": 495
710
+ },
711
+ {
712
+ "epoch": 0.5780346820809249,
713
+ "grad_norm": 0.27566250598377473,
714
+ "learning_rate": 9.032387475571771e-05,
715
+ "loss": 3.1234,
716
+ "step": 500
717
+ },
718
+ {
719
+ "epoch": 0.5838150289017341,
720
+ "grad_norm": 0.42121488462702394,
721
+ "learning_rate": 8.831643900563372e-05,
722
+ "loss": 3.1527,
723
+ "step": 505
724
+ },
725
+ {
726
+ "epoch": 0.5895953757225434,
727
+ "grad_norm": 0.2983160621346518,
728
+ "learning_rate": 8.631376582187716e-05,
729
+ "loss": 3.1313,
730
+ "step": 510
731
+ },
732
+ {
733
+ "epoch": 0.5953757225433526,
734
+ "grad_norm": 0.383836042501806,
735
+ "learning_rate": 8.431667155349381e-05,
736
+ "loss": 3.125,
737
+ "step": 515
738
+ },
739
+ {
740
+ "epoch": 0.6011560693641619,
741
+ "grad_norm": 0.2946728067863111,
742
+ "learning_rate": 8.232597027539804e-05,
743
+ "loss": 3.1203,
744
+ "step": 520
745
+ },
746
+ {
747
+ "epoch": 0.6069364161849711,
748
+ "grad_norm": 0.40035002509511697,
749
+ "learning_rate": 8.034247345653148e-05,
750
+ "loss": 3.127,
751
+ "step": 525
752
+ },
753
+ {
754
+ "epoch": 0.6127167630057804,
755
+ "grad_norm": 0.30571803221597543,
756
+ "learning_rate": 7.836698962908432e-05,
757
+ "loss": 3.1051,
758
+ "step": 530
759
+ },
760
+ {
761
+ "epoch": 0.6184971098265896,
762
+ "grad_norm": 0.39524647237789706,
763
+ "learning_rate": 7.64003240589136e-05,
764
+ "loss": 3.1172,
765
+ "step": 535
766
+ },
767
+ {
768
+ "epoch": 0.6242774566473989,
769
+ "grad_norm": 0.28648345450162954,
770
+ "learning_rate": 7.444327841729282e-05,
771
+ "loss": 3.1266,
772
+ "step": 540
773
+ },
774
+ {
775
+ "epoch": 0.630057803468208,
776
+ "grad_norm": 0.28535372587420343,
777
+ "learning_rate": 7.249665045412703e-05,
778
+ "loss": 3.1211,
779
+ "step": 545
780
+ },
781
+ {
782
+ "epoch": 0.6358381502890174,
783
+ "grad_norm": 0.30735493866888736,
784
+ "learning_rate": 7.056123367276628e-05,
785
+ "loss": 3.1113,
786
+ "step": 550
787
+ },
788
+ {
789
+ "epoch": 0.6416184971098265,
790
+ "grad_norm": 0.35113611863875976,
791
+ "learning_rate": 6.863781700655011e-05,
792
+ "loss": 3.1145,
793
+ "step": 555
794
+ },
795
+ {
796
+ "epoch": 0.6473988439306358,
797
+ "grad_norm": 0.301896935911015,
798
+ "learning_rate": 6.67271844972147e-05,
799
+ "loss": 3.1109,
800
+ "step": 560
801
+ },
802
+ {
803
+ "epoch": 0.653179190751445,
804
+ "grad_norm": 0.2835016675616311,
805
+ "learning_rate": 6.483011497529456e-05,
806
+ "loss": 3.123,
807
+ "step": 565
808
+ },
809
+ {
810
+ "epoch": 0.6589595375722543,
811
+ "grad_norm": 0.3511471847470862,
812
+ "learning_rate": 6.29473817426477e-05,
813
+ "loss": 3.1207,
814
+ "step": 570
815
+ },
816
+ {
817
+ "epoch": 0.6647398843930635,
818
+ "grad_norm": 0.34719951816291245,
819
+ "learning_rate": 6.107975225723506e-05,
820
+ "loss": 3.1078,
821
+ "step": 575
822
+ },
823
+ {
824
+ "epoch": 0.6705202312138728,
825
+ "grad_norm": 0.32389493095679567,
826
+ "learning_rate": 5.922798782028186e-05,
827
+ "loss": 3.1172,
828
+ "step": 580
829
+ },
830
+ {
831
+ "epoch": 0.6763005780346821,
832
+ "grad_norm": 0.27935241278493833,
833
+ "learning_rate": 5.7392843265948445e-05,
834
+ "loss": 3.1367,
835
+ "step": 585
836
+ },
837
+ {
838
+ "epoch": 0.6820809248554913,
839
+ "grad_norm": 0.335471823945162,
840
+ "learning_rate": 5.5575066653637696e-05,
841
+ "loss": 3.1301,
842
+ "step": 590
843
+ },
844
+ {
845
+ "epoch": 0.6878612716763006,
846
+ "grad_norm": 0.28742846706476527,
847
+ "learning_rate": 5.377539896306363e-05,
848
+ "loss": 3.1074,
849
+ "step": 595
850
+ },
851
+ {
852
+ "epoch": 0.6936416184971098,
853
+ "grad_norm": 0.28846880995197993,
854
+ "learning_rate": 5.1994573792206156e-05,
855
+ "loss": 3.1301,
856
+ "step": 600
857
+ },
858
+ {
859
+ "epoch": 0.6994219653179191,
860
+ "grad_norm": 0.29195100089253184,
861
+ "learning_rate": 5.023331705827477e-05,
862
+ "loss": 3.1313,
863
+ "step": 605
864
+ },
865
+ {
866
+ "epoch": 0.7052023121387283,
867
+ "grad_norm": 0.31669385047045495,
868
+ "learning_rate": 4.8492346701803045e-05,
869
+ "loss": 3.1184,
870
+ "step": 610
871
+ },
872
+ {
873
+ "epoch": 0.7109826589595376,
874
+ "grad_norm": 0.28758180372925923,
875
+ "learning_rate": 4.677237239399489e-05,
876
+ "loss": 3.1281,
877
+ "step": 615
878
+ },
879
+ {
880
+ "epoch": 0.7167630057803468,
881
+ "grad_norm": 0.306876835225927,
882
+ "learning_rate": 4.507409524744151e-05,
883
+ "loss": 3.1086,
884
+ "step": 620
885
+ },
886
+ {
887
+ "epoch": 0.7225433526011561,
888
+ "grad_norm": 0.27410867188213767,
889
+ "learning_rate": 4.3398207530326915e-05,
890
+ "loss": 3.1129,
891
+ "step": 625
892
+ },
893
+ {
894
+ "epoch": 0.7283236994219653,
895
+ "grad_norm": 0.3366702488484758,
896
+ "learning_rate": 4.174539238423898e-05,
897
+ "loss": 3.1289,
898
+ "step": 630
899
+ },
900
+ {
901
+ "epoch": 0.7341040462427746,
902
+ "grad_norm": 0.2863969178824916,
903
+ "learning_rate": 4.0116323545700675e-05,
904
+ "loss": 3.1238,
905
+ "step": 635
906
+ },
907
+ {
908
+ "epoch": 0.7398843930635838,
909
+ "grad_norm": 0.3097945079410788,
910
+ "learning_rate": 3.8511665071535e-05,
911
+ "loss": 3.1031,
912
+ "step": 640
913
+ },
914
+ {
915
+ "epoch": 0.7456647398843931,
916
+ "grad_norm": 0.4123766504987303,
917
+ "learning_rate": 3.69320710681758e-05,
918
+ "loss": 3.1023,
919
+ "step": 645
920
+ },
921
+ {
922
+ "epoch": 0.7514450867052023,
923
+ "grad_norm": 0.3361752903628251,
924
+ "learning_rate": 3.537818542503443e-05,
925
+ "loss": 3.1113,
926
+ "step": 650
927
+ },
928
+ {
929
+ "epoch": 0.7572254335260116,
930
+ "grad_norm": 0.3077676593416445,
931
+ "learning_rate": 3.385064155203138e-05,
932
+ "loss": 3.1105,
933
+ "step": 655
934
+ },
935
+ {
936
+ "epoch": 0.7630057803468208,
937
+ "grad_norm": 0.2712348329777666,
938
+ "learning_rate": 3.2350062121399625e-05,
939
+ "loss": 3.1105,
940
+ "step": 660
941
+ },
942
+ {
943
+ "epoch": 0.7687861271676301,
944
+ "grad_norm": 0.29913041418922676,
945
+ "learning_rate": 3.087705881386486e-05,
946
+ "loss": 3.1219,
947
+ "step": 665
948
+ },
949
+ {
950
+ "epoch": 0.7745664739884393,
951
+ "grad_norm": 0.31812764724536047,
952
+ "learning_rate": 2.943223206930632e-05,
953
+ "loss": 3.1168,
954
+ "step": 670
955
+ },
956
+ {
957
+ "epoch": 0.7803468208092486,
958
+ "grad_norm": 0.35329118193515613,
959
+ "learning_rate": 2.8016170841999667e-05,
960
+ "loss": 3.109,
961
+ "step": 675
962
+ },
963
+ {
964
+ "epoch": 0.7861271676300579,
965
+ "grad_norm": 0.2990508230174604,
966
+ "learning_rate": 2.662945236054176e-05,
967
+ "loss": 3.1066,
968
+ "step": 680
969
+ },
970
+ {
971
+ "epoch": 0.791907514450867,
972
+ "grad_norm": 0.2863986880007164,
973
+ "learning_rate": 2.527264189255507e-05,
974
+ "loss": 3.1164,
975
+ "step": 685
976
+ },
977
+ {
978
+ "epoch": 0.7976878612716763,
979
+ "grad_norm": 0.30694277766185385,
980
+ "learning_rate": 2.3946292514267854e-05,
981
+ "loss": 3.1113,
982
+ "step": 690
983
+ },
984
+ {
985
+ "epoch": 0.8034682080924855,
986
+ "grad_norm": 0.3777893533757732,
987
+ "learning_rate": 2.2650944885063897e-05,
988
+ "loss": 3.1035,
989
+ "step": 695
990
+ },
991
+ {
992
+ "epoch": 0.8092485549132948,
993
+ "grad_norm": 0.30405287841305245,
994
+ "learning_rate": 2.138712702709359e-05,
995
+ "loss": 3.0957,
996
+ "step": 700
997
+ },
998
+ {
999
+ "epoch": 0.815028901734104,
1000
+ "grad_norm": 0.3025648475201123,
1001
+ "learning_rate": 2.0155354110036604e-05,
1002
+ "loss": 3.1332,
1003
+ "step": 705
1004
+ },
1005
+ {
1006
+ "epoch": 0.8208092485549133,
1007
+ "grad_norm": 0.2921917075952636,
1008
+ "learning_rate": 1.89561282411033e-05,
1009
+ "loss": 3.0969,
1010
+ "step": 710
1011
+ },
1012
+ {
1013
+ "epoch": 0.8265895953757225,
1014
+ "grad_norm": 0.2951570047218817,
1015
+ "learning_rate": 1.7789938260360904e-05,
1016
+ "loss": 3.1125,
1017
+ "step": 715
1018
+ },
1019
+ {
1020
+ "epoch": 0.8323699421965318,
1021
+ "grad_norm": 0.2941996616491899,
1022
+ "learning_rate": 1.6657259541467883e-05,
1023
+ "loss": 3.1,
1024
+ "step": 720
1025
+ },
1026
+ {
1027
+ "epoch": 0.838150289017341,
1028
+ "grad_norm": 0.3422952891961912,
1029
+ "learning_rate": 1.555855379789747e-05,
1030
+ "loss": 3.0969,
1031
+ "step": 725
1032
+ },
1033
+ {
1034
+ "epoch": 0.8439306358381503,
1035
+ "grad_norm": 0.29026242169978395,
1036
+ "learning_rate": 1.4494268894729546e-05,
1037
+ "loss": 3.1117,
1038
+ "step": 730
1039
+ },
1040
+ {
1041
+ "epoch": 0.8497109826589595,
1042
+ "grad_norm": 0.41808268263107873,
1043
+ "learning_rate": 1.346483866608751e-05,
1044
+ "loss": 3.1078,
1045
+ "step": 735
1046
+ },
1047
+ {
1048
+ "epoch": 0.8554913294797688,
1049
+ "grad_norm": 0.5577954106464427,
1050
+ "learning_rate": 1.2470682738294737e-05,
1051
+ "loss": 3.1344,
1052
+ "step": 740
1053
+ },
1054
+ {
1055
+ "epoch": 0.861271676300578,
1056
+ "grad_norm": 0.34387551123301874,
1057
+ "learning_rate": 1.1512206358822263e-05,
1058
+ "loss": 3.1223,
1059
+ "step": 745
1060
+ },
1061
+ {
1062
+ "epoch": 0.8670520231213873,
1063
+ "grad_norm": 0.3706950879303699,
1064
+ "learning_rate": 1.058980023109798e-05,
1065
+ "loss": 3.1148,
1066
+ "step": 750
1067
+ },
1068
+ {
1069
+ "epoch": 0.8728323699421965,
1070
+ "grad_norm": 0.558405963959258,
1071
+ "learning_rate": 9.703840355244286e-06,
1072
+ "loss": 3.1094,
1073
+ "step": 755
1074
+ },
1075
+ {
1076
+ "epoch": 0.8786127167630058,
1077
+ "grad_norm": 0.38255385526130775,
1078
+ "learning_rate": 8.85468787480932e-06,
1079
+ "loss": 3.1078,
1080
+ "step": 760
1081
+ },
1082
+ {
1083
+ "epoch": 0.884393063583815,
1084
+ "grad_norm": 0.36369947881012377,
1085
+ "learning_rate": 8.042688929554076e-06,
1086
+ "loss": 3.1289,
1087
+ "step": 765
1088
+ },
1089
+ {
1090
+ "epoch": 0.8901734104046243,
1091
+ "grad_norm": 0.35939189858543064,
1092
+ "learning_rate": 7.268174514355564e-06,
1093
+ "loss": 3.0895,
1094
+ "step": 770
1095
+ },
1096
+ {
1097
+ "epoch": 0.8959537572254336,
1098
+ "grad_norm": 0.28406418416514867,
1099
+ "learning_rate": 6.531460344283513e-06,
1100
+ "loss": 3.1125,
1101
+ "step": 775
1102
+ },
1103
+ {
1104
+ "epoch": 0.9017341040462428,
1105
+ "grad_norm": 0.7961530349923809,
1106
+ "learning_rate": 5.832846725905506e-06,
1107
+ "loss": 3.1148,
1108
+ "step": 780
1109
+ },
1110
+ {
1111
+ "epoch": 0.9075144508670521,
1112
+ "grad_norm": 0.31387781257967007,
1113
+ "learning_rate": 5.172618434873111e-06,
1114
+ "loss": 3.1273,
1115
+ "step": 785
1116
+ },
1117
+ {
1118
+ "epoch": 0.9132947976878613,
1119
+ "grad_norm": 0.35418591354001977,
1120
+ "learning_rate": 4.5510445998388386e-06,
1121
+ "loss": 3.1059,
1122
+ "step": 790
1123
+ },
1124
+ {
1125
+ "epoch": 0.9190751445086706,
1126
+ "grad_norm": 0.31552685028654576,
1127
+ "learning_rate": 3.968378592751398e-06,
1128
+ "loss": 3.1219,
1129
+ "step": 795
1130
+ },
1131
+ {
1132
+ "epoch": 0.9248554913294798,
1133
+ "grad_norm": 0.381623143871843,
1134
+ "learning_rate": 3.424857925573699e-06,
1135
+ "loss": 3.1105,
1136
+ "step": 800
1137
+ },
1138
+ {
1139
+ "epoch": 0.930635838150289,
1140
+ "grad_norm": 0.3259845681670356,
1141
+ "learning_rate": 2.9207041534659363e-06,
1142
+ "loss": 3.0871,
1143
+ "step": 805
1144
+ },
1145
+ {
1146
+ "epoch": 0.9364161849710982,
1147
+ "grad_norm": 0.30145173604175796,
1148
+ "learning_rate": 2.4561227844731138e-06,
1149
+ "loss": 3.118,
1150
+ "step": 810
1151
+ },
1152
+ {
1153
+ "epoch": 0.9421965317919075,
1154
+ "grad_norm": 0.3337714000115938,
1155
+ "learning_rate": 2.0313031957539197e-06,
1156
+ "loss": 3.102,
1157
+ "step": 815
1158
+ },
1159
+ {
1160
+ "epoch": 0.9479768786127167,
1161
+ "grad_norm": 0.30245031915454157,
1162
+ "learning_rate": 1.646418556384921e-06,
1163
+ "loss": 3.0863,
1164
+ "step": 820
1165
+ },
1166
+ {
1167
+ "epoch": 0.953757225433526,
1168
+ "grad_norm": 0.29912565847350114,
1169
+ "learning_rate": 1.3016257567717294e-06,
1170
+ "loss": 3.1043,
1171
+ "step": 825
1172
+ },
1173
+ {
1174
+ "epoch": 0.9595375722543352,
1175
+ "grad_norm": 0.31262691952047295,
1176
+ "learning_rate": 9.970653446958134e-07,
1177
+ "loss": 3.1074,
1178
+ "step": 830
1179
+ },
1180
+ {
1181
+ "epoch": 0.9653179190751445,
1182
+ "grad_norm": 0.3748247921614159,
1183
+ "learning_rate": 7.328614680230495e-07,
1184
+ "loss": 3.0965,
1185
+ "step": 835
1186
+ },
1187
+ {
1188
+ "epoch": 0.9710982658959537,
1189
+ "grad_norm": 0.30960477476352033,
1190
+ "learning_rate": 5.091218240973472e-07,
1191
+ "loss": 3.0949,
1192
+ "step": 840
1193
+ },
1194
+ {
1195
+ "epoch": 0.976878612716763,
1196
+ "grad_norm": 0.3368057888691073,
1197
+ "learning_rate": 3.259376158400329e-07,
1198
+ "loss": 3.1063,
1199
+ "step": 845
1200
+ },
1201
+ {
1202
+ "epoch": 0.9826589595375722,
1203
+ "grad_norm": 0.29119253652160076,
1204
+ "learning_rate": 1.8338351457284352e-07,
1205
+ "loss": 3.1402,
1206
+ "step": 850
1207
+ },
1208
+ {
1209
+ "epoch": 0.9884393063583815,
1210
+ "grad_norm": 0.310724087204439,
1211
+ "learning_rate": 8.15176295796638e-08,
1212
+ "loss": 3.1078,
1213
+ "step": 855
1214
+ },
1215
+ {
1216
+ "epoch": 0.9942196531791907,
1217
+ "grad_norm": 0.3151737727878063,
1218
+ "learning_rate": 2.0381484419451646e-08,
1219
+ "loss": 3.0969,
1220
+ "step": 860
1221
+ },
1222
+ {
1223
+ "epoch": 1.0,
1224
+ "grad_norm": 0.33281701073497355,
1225
+ "learning_rate": 0.0,
1226
+ "loss": 3.1109,
1227
+ "step": 865
1228
+ },
1229
+ {
1230
+ "epoch": 1.0,
1231
+ "step": 865,
1232
+ "total_flos": 82545915985920.0,
1233
+ "train_loss": 3.1589166365606935,
1234
+ "train_runtime": 248.1689,
1235
+ "train_samples_per_second": 445.922,
1236
+ "train_steps_per_second": 3.486
1237
+ }
1238
+ ],
1239
+ "logging_steps": 5,
1240
+ "max_steps": 865,
1241
+ "num_input_tokens_seen": 0,
1242
+ "num_train_epochs": 1,
1243
+ "save_steps": 100,
1244
+ "stateful_callbacks": {
1245
+ "TrainerControl": {
1246
+ "args": {
1247
+ "should_epoch_stop": false,
1248
+ "should_evaluate": false,
1249
+ "should_log": false,
1250
+ "should_save": true,
1251
+ "should_training_stop": true
1252
+ },
1253
+ "attributes": {}
1254
+ }
1255
+ },
1256
+ "total_flos": 82545915985920.0,
1257
+ "train_batch_size": 16,
1258
+ "trial_name": null,
1259
+ "trial_params": null
1260
+ }