aadityap commited on
Commit
ffe27f6
·
verified ·
1 Parent(s): 2c61fe1

Model save

Browse files
Files changed (4) hide show
  1. README.md +67 -0
  2. all_results.json +9 -0
  3. train_results.json +9 -0
  4. trainer_state.json +1346 -0
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: mit
4
+ base_model: deepseek-ai/Deepseek-R1-Distill-Qwen-32B
5
+ tags:
6
+ - trl
7
+ - sft
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: sft-32b-continue
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # sft-32b-continue
18
+
19
+ This model is a fine-tuned version of [deepseek-ai/Deepseek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/Deepseek-R1-Distill-Qwen-32B) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.4810
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 1
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 8
46
+ - total_train_batch_size: 32
47
+ - total_eval_batch_size: 8
48
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
+ - lr_scheduler_type: cosine
50
+ - lr_scheduler_warmup_ratio: 0.1
51
+ - num_epochs: 2
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss |
56
+ |:-------------:|:-----:|:----:|:---------------:|
57
+ | 0.4298 | 1.0 | 92 | 0.4860 |
58
+ | 0.3989 | 2.0 | 184 | 0.4810 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - PEFT 0.13.2
64
+ - Transformers 4.47.0.dev0
65
+ - Pytorch 2.4.0+cu121
66
+ - Datasets 3.1.0
67
+ - Tokenizers 0.20.3
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 2780892130967552.0,
4
+ "train_loss": 0.43346462998053303,
5
+ "train_runtime": 8632.6044,
6
+ "train_samples": 2913,
7
+ "train_samples_per_second": 0.675,
8
+ "train_steps_per_second": 0.021
9
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 2780892130967552.0,
4
+ "train_loss": 0.43346462998053303,
5
+ "train_runtime": 8632.6044,
6
+ "train_samples": 2913,
7
+ "train_samples_per_second": 0.675,
8
+ "train_steps_per_second": 0.021
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1346 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 184,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.010869565217391304,
13
+ "grad_norm": 0.03240465296922696,
14
+ "learning_rate": 1.0526315789473685e-06,
15
+ "loss": 0.5318,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.021739130434782608,
20
+ "grad_norm": 0.031148191782486748,
21
+ "learning_rate": 2.105263157894737e-06,
22
+ "loss": 0.505,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.03260869565217391,
27
+ "grad_norm": 0.03287048185671828,
28
+ "learning_rate": 3.157894736842105e-06,
29
+ "loss": 0.517,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.043478260869565216,
34
+ "grad_norm": 0.03645975365762924,
35
+ "learning_rate": 4.210526315789474e-06,
36
+ "loss": 0.5547,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.05434782608695652,
41
+ "grad_norm": 0.03208238827298806,
42
+ "learning_rate": 5.263157894736842e-06,
43
+ "loss": 0.5284,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.06521739130434782,
48
+ "grad_norm": 0.038367637681218175,
49
+ "learning_rate": 6.31578947368421e-06,
50
+ "loss": 0.5838,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.07608695652173914,
55
+ "grad_norm": 0.03450300334168957,
56
+ "learning_rate": 7.368421052631579e-06,
57
+ "loss": 0.5382,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.08695652173913043,
62
+ "grad_norm": 0.03388554313817737,
63
+ "learning_rate": 8.421052631578948e-06,
64
+ "loss": 0.524,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.09782608695652174,
69
+ "grad_norm": 0.03544242363659419,
70
+ "learning_rate": 9.473684210526315e-06,
71
+ "loss": 0.5501,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.10869565217391304,
76
+ "grad_norm": 0.03352231239492054,
77
+ "learning_rate": 1.0526315789473684e-05,
78
+ "loss": 0.5069,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.11956521739130435,
83
+ "grad_norm": 0.03572670440459065,
84
+ "learning_rate": 1.1578947368421053e-05,
85
+ "loss": 0.5223,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.13043478260869565,
90
+ "grad_norm": 0.03663832921257728,
91
+ "learning_rate": 1.263157894736842e-05,
92
+ "loss": 0.5509,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.14130434782608695,
97
+ "grad_norm": 0.03809520900571492,
98
+ "learning_rate": 1.3684210526315791e-05,
99
+ "loss": 0.5401,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.15217391304347827,
104
+ "grad_norm": 0.03789719542276196,
105
+ "learning_rate": 1.4736842105263159e-05,
106
+ "loss": 0.5408,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.16304347826086957,
111
+ "grad_norm": 0.03420580590941963,
112
+ "learning_rate": 1.578947368421053e-05,
113
+ "loss": 0.4729,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.17391304347826086,
118
+ "grad_norm": 0.03602266807911341,
119
+ "learning_rate": 1.6842105263157896e-05,
120
+ "loss": 0.4934,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.18478260869565216,
125
+ "grad_norm": 0.04138637589841341,
126
+ "learning_rate": 1.7894736842105264e-05,
127
+ "loss": 0.5376,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.1956521739130435,
132
+ "grad_norm": 0.04435583894932485,
133
+ "learning_rate": 1.894736842105263e-05,
134
+ "loss": 0.5642,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.20652173913043478,
139
+ "grad_norm": 0.04141900808302216,
140
+ "learning_rate": 2e-05,
141
+ "loss": 0.5591,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.21739130434782608,
146
+ "grad_norm": 0.03675591300747317,
147
+ "learning_rate": 1.999818745523526e-05,
148
+ "loss": 0.5022,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.22826086956521738,
153
+ "grad_norm": 0.035936674391353805,
154
+ "learning_rate": 1.999275047800474e-05,
155
+ "loss": 0.5342,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.2391304347826087,
160
+ "grad_norm": 0.03766128882621122,
161
+ "learning_rate": 1.9983691039261358e-05,
162
+ "loss": 0.5437,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.25,
167
+ "grad_norm": 0.03747365385813838,
168
+ "learning_rate": 1.9971012423132776e-05,
169
+ "loss": 0.5113,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.2608695652173913,
174
+ "grad_norm": 0.037562789979165546,
175
+ "learning_rate": 1.9954719225730847e-05,
176
+ "loss": 0.5219,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.2717391304347826,
181
+ "grad_norm": 0.033732964863589725,
182
+ "learning_rate": 1.99348173534855e-05,
183
+ "loss": 0.4899,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.2826086956521739,
188
+ "grad_norm": 0.032706454390573285,
189
+ "learning_rate": 1.9911314021003614e-05,
190
+ "loss": 0.46,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.29347826086956524,
195
+ "grad_norm": 0.03299013215961956,
196
+ "learning_rate": 1.9884217748453625e-05,
197
+ "loss": 0.4464,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.30434782608695654,
202
+ "grad_norm": 0.036322686035091326,
203
+ "learning_rate": 1.9853538358476933e-05,
204
+ "loss": 0.525,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.31521739130434784,
209
+ "grad_norm": 0.035349035280986665,
210
+ "learning_rate": 1.9819286972627066e-05,
211
+ "loss": 0.481,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.32608695652173914,
216
+ "grad_norm": 0.03304667685973592,
217
+ "learning_rate": 1.9781476007338058e-05,
218
+ "loss": 0.486,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.33695652173913043,
223
+ "grad_norm": 0.03594690118986878,
224
+ "learning_rate": 1.9740119169423337e-05,
225
+ "loss": 0.4459,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.34782608695652173,
230
+ "grad_norm": 0.03722435746668587,
231
+ "learning_rate": 1.9695231451106914e-05,
232
+ "loss": 0.4884,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.358695652173913,
237
+ "grad_norm": 0.03234546772265382,
238
+ "learning_rate": 1.964682912458856e-05,
239
+ "loss": 0.4538,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.3695652173913043,
244
+ "grad_norm": 0.03332715856138033,
245
+ "learning_rate": 1.9594929736144978e-05,
246
+ "loss": 0.4684,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.3804347826086957,
251
+ "grad_norm": 0.03192258021162577,
252
+ "learning_rate": 1.9539552099769128e-05,
253
+ "loss": 0.5074,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.391304347826087,
258
+ "grad_norm": 0.028905879450475694,
259
+ "learning_rate": 1.9480716290349998e-05,
260
+ "loss": 0.4329,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.40217391304347827,
265
+ "grad_norm": 0.026272771750420486,
266
+ "learning_rate": 1.941844363639525e-05,
267
+ "loss": 0.4104,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.41304347826086957,
272
+ "grad_norm": 0.029512600659781462,
273
+ "learning_rate": 1.9352756712299467e-05,
274
+ "loss": 0.4352,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.42391304347826086,
279
+ "grad_norm": 0.03106074409081994,
280
+ "learning_rate": 1.9283679330160726e-05,
281
+ "loss": 0.4617,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.43478260869565216,
286
+ "grad_norm": 0.02877012176170005,
287
+ "learning_rate": 1.92112365311485e-05,
288
+ "loss": 0.4492,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.44565217391304346,
293
+ "grad_norm": 0.028504695790476927,
294
+ "learning_rate": 1.913545457642601e-05,
295
+ "loss": 0.4388,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.45652173913043476,
300
+ "grad_norm": 0.02776562257630969,
301
+ "learning_rate": 1.905636093763031e-05,
302
+ "loss": 0.457,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.4673913043478261,
307
+ "grad_norm": 0.02279898042963453,
308
+ "learning_rate": 1.8973984286913584e-05,
309
+ "loss": 0.4228,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.4782608695652174,
314
+ "grad_norm": 0.022273693107528456,
315
+ "learning_rate": 1.8888354486549238e-05,
316
+ "loss": 0.4141,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.4891304347826087,
321
+ "grad_norm": 0.022833837988057187,
322
+ "learning_rate": 1.8799502578106533e-05,
323
+ "loss": 0.4252,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.5,
328
+ "grad_norm": 0.021546758234096523,
329
+ "learning_rate": 1.8707460771197773e-05,
330
+ "loss": 0.4417,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.5108695652173914,
335
+ "grad_norm": 0.019884209926995258,
336
+ "learning_rate": 1.861226243180201e-05,
337
+ "loss": 0.4249,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.5217391304347826,
342
+ "grad_norm": 0.02067326340118169,
343
+ "learning_rate": 1.8513942070169572e-05,
344
+ "loss": 0.4498,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.532608695652174,
349
+ "grad_norm": 0.018558394593515687,
350
+ "learning_rate": 1.8412535328311813e-05,
351
+ "loss": 0.4188,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.5434782608695652,
356
+ "grad_norm": 0.019420981988919603,
357
+ "learning_rate": 1.8308078967080547e-05,
358
+ "loss": 0.425,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.5543478260869565,
363
+ "grad_norm": 0.01678791068237689,
364
+ "learning_rate": 1.8200610852841913e-05,
365
+ "loss": 0.3955,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.5652173913043478,
370
+ "grad_norm": 0.018788790486373518,
371
+ "learning_rate": 1.8090169943749477e-05,
372
+ "loss": 0.4273,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.5760869565217391,
377
+ "grad_norm": 0.01812533816051695,
378
+ "learning_rate": 1.7976796275621556e-05,
379
+ "loss": 0.3664,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.5869565217391305,
384
+ "grad_norm": 0.017190627828475347,
385
+ "learning_rate": 1.7860530947427878e-05,
386
+ "loss": 0.4481,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.5978260869565217,
391
+ "grad_norm": 0.019689749698733695,
392
+ "learning_rate": 1.7741416106390828e-05,
393
+ "loss": 0.4529,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.6086956521739131,
398
+ "grad_norm": 0.017252168109986435,
399
+ "learning_rate": 1.761949493270671e-05,
400
+ "loss": 0.4251,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.6195652173913043,
405
+ "grad_norm": 0.017554978035306083,
406
+ "learning_rate": 1.7494811623892543e-05,
407
+ "loss": 0.4348,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.6304347826086957,
412
+ "grad_norm": 0.01728596934943526,
413
+ "learning_rate": 1.736741137876405e-05,
414
+ "loss": 0.4298,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.6413043478260869,
419
+ "grad_norm": 0.016841718915483313,
420
+ "learning_rate": 1.72373403810507e-05,
421
+ "loss": 0.424,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.6521739130434783,
426
+ "grad_norm": 0.017988846143621267,
427
+ "learning_rate": 1.710464578265369e-05,
428
+ "loss": 0.4192,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.6630434782608695,
433
+ "grad_norm": 0.016118964656136582,
434
+ "learning_rate": 1.696937568655294e-05,
435
+ "loss": 0.4388,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.6739130434782609,
440
+ "grad_norm": 0.016980548999802704,
441
+ "learning_rate": 1.6831579129369347e-05,
442
+ "loss": 0.4337,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.6847826086956522,
447
+ "grad_norm": 0.016896592627422335,
448
+ "learning_rate": 1.6691306063588583e-05,
449
+ "loss": 0.4004,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.6956521739130435,
454
+ "grad_norm": 0.015889660322036148,
455
+ "learning_rate": 1.6548607339452853e-05,
456
+ "loss": 0.4393,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.7065217391304348,
461
+ "grad_norm": 0.016428852385924283,
462
+ "learning_rate": 1.6403534686527223e-05,
463
+ "loss": 0.4239,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.717391304347826,
468
+ "grad_norm": 0.01539489673351542,
469
+ "learning_rate": 1.6256140694947217e-05,
470
+ "loss": 0.3979,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.7282608695652174,
475
+ "grad_norm": 0.017016571801118784,
476
+ "learning_rate": 1.6106478796354382e-05,
477
+ "loss": 0.4531,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.7391304347826086,
482
+ "grad_norm": 0.018614609000821066,
483
+ "learning_rate": 1.595460324452688e-05,
484
+ "loss": 0.3969,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.75,
489
+ "grad_norm": 0.01603990010550668,
490
+ "learning_rate": 1.5800569095711983e-05,
491
+ "loss": 0.4444,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.7608695652173914,
496
+ "grad_norm": 0.016345231925260058,
497
+ "learning_rate": 1.5644432188667695e-05,
498
+ "loss": 0.43,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.7717391304347826,
503
+ "grad_norm": 0.014545507199229903,
504
+ "learning_rate": 1.5486249124420702e-05,
505
+ "loss": 0.4395,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.782608695652174,
510
+ "grad_norm": 0.016159427204217675,
511
+ "learning_rate": 1.5326077245747998e-05,
512
+ "loss": 0.4324,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.7934782608695652,
517
+ "grad_norm": 0.01577781927643107,
518
+ "learning_rate": 1.5163974616389621e-05,
519
+ "loss": 0.3783,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.8043478260869565,
524
+ "grad_norm": 0.020543349930487027,
525
+ "learning_rate": 1.5000000000000002e-05,
526
+ "loss": 0.4517,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.8152173913043478,
531
+ "grad_norm": 0.0162387560400049,
532
+ "learning_rate": 1.4834212838845639e-05,
533
+ "loss": 0.4323,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.8260869565217391,
538
+ "grad_norm": 0.017194073308575693,
539
+ "learning_rate": 1.4666673232256738e-05,
540
+ "loss": 0.4531,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.8369565217391305,
545
+ "grad_norm": 0.014830688698626977,
546
+ "learning_rate": 1.449744191484066e-05,
547
+ "loss": 0.4044,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.8478260869565217,
552
+ "grad_norm": 0.017667656527989815,
553
+ "learning_rate": 1.4326580234465084e-05,
554
+ "loss": 0.4084,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.8586956521739131,
559
+ "grad_norm": 0.01665626106397431,
560
+ "learning_rate": 1.4154150130018867e-05,
561
+ "loss": 0.3811,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.8695652173913043,
566
+ "grad_norm": 0.015487133239067268,
567
+ "learning_rate": 1.3980214108958626e-05,
568
+ "loss": 0.3792,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.8804347826086957,
573
+ "grad_norm": 0.015980794746876442,
574
+ "learning_rate": 1.380483522464923e-05,
575
+ "loss": 0.3567,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.8913043478260869,
580
+ "grad_norm": 0.01742924875832292,
581
+ "learning_rate": 1.362807705350641e-05,
582
+ "loss": 0.4108,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.9021739130434783,
587
+ "grad_norm": 0.01621883533665314,
588
+ "learning_rate": 1.3450003671949707e-05,
589
+ "loss": 0.3885,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.9130434782608695,
594
+ "grad_norm": 0.01816609517986378,
595
+ "learning_rate": 1.3270679633174219e-05,
596
+ "loss": 0.4195,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.9239130434782609,
601
+ "grad_norm": 0.01700022402834444,
602
+ "learning_rate": 1.3090169943749475e-05,
603
+ "loss": 0.4008,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.9347826086956522,
608
+ "grad_norm": 0.015423948003415178,
609
+ "learning_rate": 1.2908540040053992e-05,
610
+ "loss": 0.4284,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.9456521739130435,
615
+ "grad_norm": 0.016648244343970338,
616
+ "learning_rate": 1.2725855764553981e-05,
617
+ "loss": 0.4353,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.9565217391304348,
622
+ "grad_norm": 0.018695896408094728,
623
+ "learning_rate": 1.2542183341934873e-05,
624
+ "loss": 0.4454,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.967391304347826,
629
+ "grad_norm": 0.014985563910038587,
630
+ "learning_rate": 1.2357589355094275e-05,
631
+ "loss": 0.4254,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.9782608695652174,
636
+ "grad_norm": 0.0158615730686512,
637
+ "learning_rate": 1.217214072100508e-05,
638
+ "loss": 0.4141,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.9891304347826086,
643
+ "grad_norm": 0.01615877678103288,
644
+ "learning_rate": 1.1985904666457455e-05,
645
+ "loss": 0.3743,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 1.0,
650
+ "grad_norm": 0.017892852375543514,
651
+ "learning_rate": 1.179894870368854e-05,
652
+ "loss": 0.4298,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 1.0,
657
+ "eval_loss": 0.48603561520576477,
658
+ "eval_runtime": 5.8299,
659
+ "eval_samples_per_second": 0.172,
660
+ "eval_steps_per_second": 0.172,
661
+ "step": 92
662
+ },
663
+ {
664
+ "epoch": 1.0108695652173914,
665
+ "grad_norm": 0.017298462574072342,
666
+ "learning_rate": 1.1611340605908643e-05,
667
+ "loss": 0.4148,
668
+ "step": 93
669
+ },
670
+ {
671
+ "epoch": 1.0217391304347827,
672
+ "grad_norm": 0.017838476342072244,
673
+ "learning_rate": 1.1423148382732854e-05,
674
+ "loss": 0.4034,
675
+ "step": 94
676
+ },
677
+ {
678
+ "epoch": 1.0326086956521738,
679
+ "grad_norm": 0.01861199740817311,
680
+ "learning_rate": 1.1234440255526948e-05,
681
+ "loss": 0.4219,
682
+ "step": 95
683
+ },
684
+ {
685
+ "epoch": 1.0434782608695652,
686
+ "grad_norm": 0.01671425099245661,
687
+ "learning_rate": 1.1045284632676535e-05,
688
+ "loss": 0.4046,
689
+ "step": 96
690
+ },
691
+ {
692
+ "epoch": 1.0543478260869565,
693
+ "grad_norm": 0.01861001152790246,
694
+ "learning_rate": 1.08557500847884e-05,
695
+ "loss": 0.4009,
696
+ "step": 97
697
+ },
698
+ {
699
+ "epoch": 1.065217391304348,
700
+ "grad_norm": 0.018107901828337766,
701
+ "learning_rate": 1.066590531983304e-05,
702
+ "loss": 0.4089,
703
+ "step": 98
704
+ },
705
+ {
706
+ "epoch": 1.0760869565217392,
707
+ "grad_norm": 0.0174920546188433,
708
+ "learning_rate": 1.0475819158237426e-05,
709
+ "loss": 0.3954,
710
+ "step": 99
711
+ },
712
+ {
713
+ "epoch": 1.0869565217391304,
714
+ "grad_norm": 0.016682152706871897,
715
+ "learning_rate": 1.0285560507936962e-05,
716
+ "loss": 0.4289,
717
+ "step": 100
718
+ },
719
+ {
720
+ "epoch": 1.0978260869565217,
721
+ "grad_norm": 0.018098011701254673,
722
+ "learning_rate": 1.0095198339395769e-05,
723
+ "loss": 0.4302,
724
+ "step": 101
725
+ },
726
+ {
727
+ "epoch": 1.108695652173913,
728
+ "grad_norm": 0.015568335864025949,
729
+ "learning_rate": 9.904801660604234e-06,
730
+ "loss": 0.409,
731
+ "step": 102
732
+ },
733
+ {
734
+ "epoch": 1.1195652173913044,
735
+ "grad_norm": 0.016958799953214254,
736
+ "learning_rate": 9.71443949206304e-06,
737
+ "loss": 0.4039,
738
+ "step": 103
739
+ },
740
+ {
741
+ "epoch": 1.1304347826086956,
742
+ "grad_norm": 0.017521827484537653,
743
+ "learning_rate": 9.524180841762577e-06,
744
+ "loss": 0.4142,
745
+ "step": 104
746
+ },
747
+ {
748
+ "epoch": 1.141304347826087,
749
+ "grad_norm": 0.018438050806712614,
750
+ "learning_rate": 9.334094680166962e-06,
751
+ "loss": 0.4085,
752
+ "step": 105
753
+ },
754
+ {
755
+ "epoch": 1.1521739130434783,
756
+ "grad_norm": 0.01941444882552903,
757
+ "learning_rate": 9.144249915211605e-06,
758
+ "loss": 0.4298,
759
+ "step": 106
760
+ },
761
+ {
762
+ "epoch": 1.1630434782608696,
763
+ "grad_norm": 0.017649511484447825,
764
+ "learning_rate": 8.954715367323468e-06,
765
+ "loss": 0.4161,
766
+ "step": 107
767
+ },
768
+ {
769
+ "epoch": 1.1739130434782608,
770
+ "grad_norm": 0.01677483752186088,
771
+ "learning_rate": 8.765559744473054e-06,
772
+ "loss": 0.4042,
773
+ "step": 108
774
+ },
775
+ {
776
+ "epoch": 1.184782608695652,
777
+ "grad_norm": 0.017213373571849412,
778
+ "learning_rate": 8.576851617267151e-06,
779
+ "loss": 0.409,
780
+ "step": 109
781
+ },
782
+ {
783
+ "epoch": 1.1956521739130435,
784
+ "grad_norm": 0.01804604085921314,
785
+ "learning_rate": 8.388659394091362e-06,
786
+ "loss": 0.4195,
787
+ "step": 110
788
+ },
789
+ {
790
+ "epoch": 1.2065217391304348,
791
+ "grad_norm": 0.019524779611806008,
792
+ "learning_rate": 8.201051296311462e-06,
793
+ "loss": 0.4144,
794
+ "step": 111
795
+ },
796
+ {
797
+ "epoch": 1.2173913043478262,
798
+ "grad_norm": 0.01961583109753067,
799
+ "learning_rate": 8.014095333542548e-06,
800
+ "loss": 0.4169,
801
+ "step": 112
802
+ },
803
+ {
804
+ "epoch": 1.2282608695652173,
805
+ "grad_norm": 0.01828151965518523,
806
+ "learning_rate": 7.827859278994924e-06,
807
+ "loss": 0.3989,
808
+ "step": 113
809
+ },
810
+ {
811
+ "epoch": 1.2391304347826086,
812
+ "grad_norm": 0.01958662355054947,
813
+ "learning_rate": 7.642410644905726e-06,
814
+ "loss": 0.4166,
815
+ "step": 114
816
+ },
817
+ {
818
+ "epoch": 1.25,
819
+ "grad_norm": 0.018324698258002987,
820
+ "learning_rate": 7.4578166580651335e-06,
821
+ "loss": 0.4191,
822
+ "step": 115
823
+ },
824
+ {
825
+ "epoch": 1.2608695652173914,
826
+ "grad_norm": 0.01711860737234338,
827
+ "learning_rate": 7.274144235446024e-06,
828
+ "loss": 0.3976,
829
+ "step": 116
830
+ },
831
+ {
832
+ "epoch": 1.2717391304347827,
833
+ "grad_norm": 0.015977161100683545,
834
+ "learning_rate": 7.0914599599460095e-06,
835
+ "loss": 0.4301,
836
+ "step": 117
837
+ },
838
+ {
839
+ "epoch": 1.2826086956521738,
840
+ "grad_norm": 0.017423189335602548,
841
+ "learning_rate": 6.909830056250527e-06,
842
+ "loss": 0.3972,
843
+ "step": 118
844
+ },
845
+ {
846
+ "epoch": 1.2934782608695652,
847
+ "grad_norm": 0.020183820621289872,
848
+ "learning_rate": 6.729320366825785e-06,
849
+ "loss": 0.406,
850
+ "step": 119
851
+ },
852
+ {
853
+ "epoch": 1.3043478260869565,
854
+ "grad_norm": 0.0188473400999686,
855
+ "learning_rate": 6.549996328050296e-06,
856
+ "loss": 0.3886,
857
+ "step": 120
858
+ },
859
+ {
860
+ "epoch": 1.315217391304348,
861
+ "grad_norm": 0.02064149059917863,
862
+ "learning_rate": 6.3719229464935915e-06,
863
+ "loss": 0.456,
864
+ "step": 121
865
+ },
866
+ {
867
+ "epoch": 1.3260869565217392,
868
+ "grad_norm": 0.02178374309057221,
869
+ "learning_rate": 6.19516477535077e-06,
870
+ "loss": 0.4171,
871
+ "step": 122
872
+ },
873
+ {
874
+ "epoch": 1.3369565217391304,
875
+ "grad_norm": 0.02027707601043217,
876
+ "learning_rate": 6.019785891041381e-06,
877
+ "loss": 0.3642,
878
+ "step": 123
879
+ },
880
+ {
881
+ "epoch": 1.3478260869565217,
882
+ "grad_norm": 0.021269660172408174,
883
+ "learning_rate": 5.845849869981137e-06,
884
+ "loss": 0.4017,
885
+ "step": 124
886
+ },
887
+ {
888
+ "epoch": 1.358695652173913,
889
+ "grad_norm": 0.022411495134838297,
890
+ "learning_rate": 5.673419765534915e-06,
891
+ "loss": 0.4071,
892
+ "step": 125
893
+ },
894
+ {
895
+ "epoch": 1.3695652173913042,
896
+ "grad_norm": 0.01951721173355996,
897
+ "learning_rate": 5.502558085159344e-06,
898
+ "loss": 0.3481,
899
+ "step": 126
900
+ },
901
+ {
902
+ "epoch": 1.3804347826086958,
903
+ "grad_norm": 0.024116070335566953,
904
+ "learning_rate": 5.333326767743263e-06,
905
+ "loss": 0.4188,
906
+ "step": 127
907
+ },
908
+ {
909
+ "epoch": 1.391304347826087,
910
+ "grad_norm": 0.026359215985631845,
911
+ "learning_rate": 5.165787161154361e-06,
912
+ "loss": 0.4169,
913
+ "step": 128
914
+ },
915
+ {
916
+ "epoch": 1.4021739130434783,
917
+ "grad_norm": 0.022217706817923774,
918
+ "learning_rate": 5.000000000000003e-06,
919
+ "loss": 0.4236,
920
+ "step": 129
921
+ },
922
+ {
923
+ "epoch": 1.4130434782608696,
924
+ "grad_norm": 0.021753073317964423,
925
+ "learning_rate": 4.836025383610382e-06,
926
+ "loss": 0.432,
927
+ "step": 130
928
+ },
929
+ {
930
+ "epoch": 1.4239130434782608,
931
+ "grad_norm": 0.022436739303883135,
932
+ "learning_rate": 4.673922754252001e-06,
933
+ "loss": 0.4187,
934
+ "step": 131
935
+ },
936
+ {
937
+ "epoch": 1.434782608695652,
938
+ "grad_norm": 0.021898203612681105,
939
+ "learning_rate": 4.513750875579303e-06,
940
+ "loss": 0.4006,
941
+ "step": 132
942
+ },
943
+ {
944
+ "epoch": 1.4456521739130435,
945
+ "grad_norm": 0.022105558271218153,
946
+ "learning_rate": 4.355567811332311e-06,
947
+ "loss": 0.428,
948
+ "step": 133
949
+ },
950
+ {
951
+ "epoch": 1.4565217391304348,
952
+ "grad_norm": 0.02033202844138333,
953
+ "learning_rate": 4.19943090428802e-06,
954
+ "loss": 0.3973,
955
+ "step": 134
956
+ },
957
+ {
958
+ "epoch": 1.4673913043478262,
959
+ "grad_norm": 0.01963872298504158,
960
+ "learning_rate": 4.045396755473121e-06,
961
+ "loss": 0.4008,
962
+ "step": 135
963
+ },
964
+ {
965
+ "epoch": 1.4782608695652173,
966
+ "grad_norm": 0.020345281605454676,
967
+ "learning_rate": 3.893521203645618e-06,
968
+ "loss": 0.4147,
969
+ "step": 136
970
+ },
971
+ {
972
+ "epoch": 1.4891304347826086,
973
+ "grad_norm": 0.021452868059861192,
974
+ "learning_rate": 3.743859305052785e-06,
975
+ "loss": 0.4149,
976
+ "step": 137
977
+ },
978
+ {
979
+ "epoch": 1.5,
980
+ "grad_norm": 0.020207806262184335,
981
+ "learning_rate": 3.596465313472778e-06,
982
+ "loss": 0.3836,
983
+ "step": 138
984
+ },
985
+ {
986
+ "epoch": 1.5108695652173914,
987
+ "grad_norm": 0.02088539870362614,
988
+ "learning_rate": 3.4513926605471504e-06,
989
+ "loss": 0.4138,
990
+ "step": 139
991
+ },
992
+ {
993
+ "epoch": 1.5217391304347827,
994
+ "grad_norm": 0.019077086049604102,
995
+ "learning_rate": 3.308693936411421e-06,
996
+ "loss": 0.3832,
997
+ "step": 140
998
+ },
999
+ {
1000
+ "epoch": 1.5326086956521738,
1001
+ "grad_norm": 0.020912600263192083,
1002
+ "learning_rate": 3.1684208706306572e-06,
1003
+ "loss": 0.4136,
1004
+ "step": 141
1005
+ },
1006
+ {
1007
+ "epoch": 1.5434782608695652,
1008
+ "grad_norm": 0.02070907606152171,
1009
+ "learning_rate": 3.0306243134470668e-06,
1010
+ "loss": 0.4311,
1011
+ "step": 142
1012
+ },
1013
+ {
1014
+ "epoch": 1.5543478260869565,
1015
+ "grad_norm": 0.02054030797884719,
1016
+ "learning_rate": 2.8953542173463133e-06,
1017
+ "loss": 0.3938,
1018
+ "step": 143
1019
+ },
1020
+ {
1021
+ "epoch": 1.5652173913043477,
1022
+ "grad_norm": 0.022068383731631152,
1023
+ "learning_rate": 2.7626596189492983e-06,
1024
+ "loss": 0.3869,
1025
+ "step": 144
1026
+ },
1027
+ {
1028
+ "epoch": 1.5760869565217392,
1029
+ "grad_norm": 0.022095291706298183,
1030
+ "learning_rate": 2.6325886212359496e-06,
1031
+ "loss": 0.4151,
1032
+ "step": 145
1033
+ },
1034
+ {
1035
+ "epoch": 1.5869565217391304,
1036
+ "grad_norm": 0.021111713836599773,
1037
+ "learning_rate": 2.5051883761074613e-06,
1038
+ "loss": 0.4354,
1039
+ "step": 146
1040
+ },
1041
+ {
1042
+ "epoch": 1.5978260869565217,
1043
+ "grad_norm": 0.02237517232258718,
1044
+ "learning_rate": 2.380505067293293e-06,
1045
+ "loss": 0.4146,
1046
+ "step": 147
1047
+ },
1048
+ {
1049
+ "epoch": 1.608695652173913,
1050
+ "grad_norm": 0.019623457979118124,
1051
+ "learning_rate": 2.2585838936091753e-06,
1052
+ "loss": 0.4119,
1053
+ "step": 148
1054
+ },
1055
+ {
1056
+ "epoch": 1.6195652173913042,
1057
+ "grad_norm": 0.021829275784838623,
1058
+ "learning_rate": 2.1394690525721275e-06,
1059
+ "loss": 0.4135,
1060
+ "step": 149
1061
+ },
1062
+ {
1063
+ "epoch": 1.6304347826086958,
1064
+ "grad_norm": 0.021180171763894674,
1065
+ "learning_rate": 2.0232037243784475e-06,
1066
+ "loss": 0.423,
1067
+ "step": 150
1068
+ },
1069
+ {
1070
+ "epoch": 1.641304347826087,
1071
+ "grad_norm": 0.02703521598184206,
1072
+ "learning_rate": 1.9098300562505266e-06,
1073
+ "loss": 0.4279,
1074
+ "step": 151
1075
+ },
1076
+ {
1077
+ "epoch": 1.6521739130434783,
1078
+ "grad_norm": 0.020030953141784397,
1079
+ "learning_rate": 1.7993891471580894e-06,
1080
+ "loss": 0.3998,
1081
+ "step": 152
1082
+ },
1083
+ {
1084
+ "epoch": 1.6630434782608696,
1085
+ "grad_norm": 0.02096005243951767,
1086
+ "learning_rate": 1.6919210329194535e-06,
1087
+ "loss": 0.4117,
1088
+ "step": 153
1089
+ },
1090
+ {
1091
+ "epoch": 1.6739130434782608,
1092
+ "grad_norm": 0.02114720153165263,
1093
+ "learning_rate": 1.587464671688187e-06,
1094
+ "loss": 0.4267,
1095
+ "step": 154
1096
+ },
1097
+ {
1098
+ "epoch": 1.6847826086956523,
1099
+ "grad_norm": 0.025390809807677033,
1100
+ "learning_rate": 1.4860579298304311e-06,
1101
+ "loss": 0.415,
1102
+ "step": 155
1103
+ },
1104
+ {
1105
+ "epoch": 1.6956521739130435,
1106
+ "grad_norm": 0.021410687428214302,
1107
+ "learning_rate": 1.3877375681979944e-06,
1108
+ "loss": 0.4043,
1109
+ "step": 156
1110
+ },
1111
+ {
1112
+ "epoch": 1.7065217391304348,
1113
+ "grad_norm": 0.023909950655856917,
1114
+ "learning_rate": 1.2925392288022299e-06,
1115
+ "loss": 0.4445,
1116
+ "step": 157
1117
+ },
1118
+ {
1119
+ "epoch": 1.7173913043478262,
1120
+ "grad_norm": 0.021428679509317893,
1121
+ "learning_rate": 1.2004974218934695e-06,
1122
+ "loss": 0.4238,
1123
+ "step": 158
1124
+ },
1125
+ {
1126
+ "epoch": 1.7282608695652173,
1127
+ "grad_norm": 0.02137946805669467,
1128
+ "learning_rate": 1.1116455134507665e-06,
1129
+ "loss": 0.3674,
1130
+ "step": 159
1131
+ },
1132
+ {
1133
+ "epoch": 1.7391304347826086,
1134
+ "grad_norm": 0.022243431881806403,
1135
+ "learning_rate": 1.0260157130864178e-06,
1136
+ "loss": 0.426,
1137
+ "step": 160
1138
+ },
1139
+ {
1140
+ "epoch": 1.75,
1141
+ "grad_norm": 0.024681458739084422,
1142
+ "learning_rate": 9.436390623696911e-07,
1143
+ "loss": 0.4313,
1144
+ "step": 161
1145
+ },
1146
+ {
1147
+ "epoch": 1.7608695652173914,
1148
+ "grad_norm": 0.020315997518542663,
1149
+ "learning_rate": 8.645454235739903e-07,
1150
+ "loss": 0.3921,
1151
+ "step": 162
1152
+ },
1153
+ {
1154
+ "epoch": 1.7717391304347827,
1155
+ "grad_norm": 0.02332809992280282,
1156
+ "learning_rate": 7.887634688515e-07,
1157
+ "loss": 0.4273,
1158
+ "step": 163
1159
+ },
1160
+ {
1161
+ "epoch": 1.7826086956521738,
1162
+ "grad_norm": 0.020023620557189287,
1163
+ "learning_rate": 7.163206698392744e-07,
1164
+ "loss": 0.3738,
1165
+ "step": 164
1166
+ },
1167
+ {
1168
+ "epoch": 1.7934782608695652,
1169
+ "grad_norm": 0.022892114041331832,
1170
+ "learning_rate": 6.472432877005341e-07,
1171
+ "loss": 0.404,
1172
+ "step": 165
1173
+ },
1174
+ {
1175
+ "epoch": 1.8043478260869565,
1176
+ "grad_norm": 0.021905535119289433,
1177
+ "learning_rate": 5.815563636047539e-07,
1178
+ "loss": 0.4049,
1179
+ "step": 166
1180
+ },
1181
+ {
1182
+ "epoch": 1.8152173913043477,
1183
+ "grad_norm": 0.02074267534357053,
1184
+ "learning_rate": 5.192837096500058e-07,
1185
+ "loss": 0.4166,
1186
+ "step": 167
1187
+ },
1188
+ {
1189
+ "epoch": 1.8260869565217392,
1190
+ "grad_norm": 0.01843268176253824,
1191
+ "learning_rate": 4.6044790023087373e-07,
1192
+ "loss": 0.357,
1193
+ "step": 168
1194
+ },
1195
+ {
1196
+ "epoch": 1.8369565217391304,
1197
+ "grad_norm": 0.02079361540838812,
1198
+ "learning_rate": 4.0507026385502747e-07,
1199
+ "loss": 0.4344,
1200
+ "step": 169
1201
+ },
1202
+ {
1203
+ "epoch": 1.8478260869565217,
1204
+ "grad_norm": 0.021623517427470682,
1205
+ "learning_rate": 3.531708754114438e-07,
1206
+ "loss": 0.3878,
1207
+ "step": 170
1208
+ },
1209
+ {
1210
+ "epoch": 1.858695652173913,
1211
+ "grad_norm": 0.02038214952768136,
1212
+ "learning_rate": 3.0476854889308737e-07,
1213
+ "loss": 0.3856,
1214
+ "step": 171
1215
+ },
1216
+ {
1217
+ "epoch": 1.8695652173913042,
1218
+ "grad_norm": 0.023803627119720294,
1219
+ "learning_rate": 2.5988083057666534e-07,
1220
+ "loss": 0.416,
1221
+ "step": 172
1222
+ },
1223
+ {
1224
+ "epoch": 1.8804347826086958,
1225
+ "grad_norm": 0.02284511042725229,
1226
+ "learning_rate": 2.1852399266194312e-07,
1227
+ "loss": 0.4268,
1228
+ "step": 173
1229
+ },
1230
+ {
1231
+ "epoch": 1.891304347826087,
1232
+ "grad_norm": 0.022105485087235137,
1233
+ "learning_rate": 1.8071302737293294e-07,
1234
+ "loss": 0.3996,
1235
+ "step": 174
1236
+ },
1237
+ {
1238
+ "epoch": 1.9021739130434783,
1239
+ "grad_norm": 0.02196082349655336,
1240
+ "learning_rate": 1.464616415230702e-07,
1241
+ "loss": 0.3977,
1242
+ "step": 175
1243
+ },
1244
+ {
1245
+ "epoch": 1.9130434782608696,
1246
+ "grad_norm": 0.02582111983328924,
1247
+ "learning_rate": 1.1578225154637579e-07,
1248
+ "loss": 0.4167,
1249
+ "step": 176
1250
+ },
1251
+ {
1252
+ "epoch": 1.9239130434782608,
1253
+ "grad_norm": 0.020467066579464847,
1254
+ "learning_rate": 8.868597899638897e-08,
1255
+ "loss": 0.4022,
1256
+ "step": 177
1257
+ },
1258
+ {
1259
+ "epoch": 1.9347826086956523,
1260
+ "grad_norm": 0.018578643308574946,
1261
+ "learning_rate": 6.51826465144978e-08,
1262
+ "loss": 0.4305,
1263
+ "step": 178
1264
+ },
1265
+ {
1266
+ "epoch": 1.9456521739130435,
1267
+ "grad_norm": 0.020351166995274374,
1268
+ "learning_rate": 4.528077426915412e-08,
1269
+ "loss": 0.4323,
1270
+ "step": 179
1271
+ },
1272
+ {
1273
+ "epoch": 1.9565217391304348,
1274
+ "grad_norm": 0.01983648675971413,
1275
+ "learning_rate": 2.898757686722542e-08,
1276
+ "loss": 0.3953,
1277
+ "step": 180
1278
+ },
1279
+ {
1280
+ "epoch": 1.9673913043478262,
1281
+ "grad_norm": 0.01924389485648581,
1282
+ "learning_rate": 1.630896073864352e-08,
1283
+ "loss": 0.4024,
1284
+ "step": 181
1285
+ },
1286
+ {
1287
+ "epoch": 1.9782608695652173,
1288
+ "grad_norm": 0.021496764470333395,
1289
+ "learning_rate": 7.2495219952639636e-09,
1290
+ "loss": 0.4284,
1291
+ "step": 182
1292
+ },
1293
+ {
1294
+ "epoch": 1.9891304347826086,
1295
+ "grad_norm": 0.02172124469681476,
1296
+ "learning_rate": 1.8125447647421302e-09,
1297
+ "loss": 0.3954,
1298
+ "step": 183
1299
+ },
1300
+ {
1301
+ "epoch": 2.0,
1302
+ "grad_norm": 0.021341261717375007,
1303
+ "learning_rate": 0.0,
1304
+ "loss": 0.3989,
1305
+ "step": 184
1306
+ },
1307
+ {
1308
+ "epoch": 2.0,
1309
+ "eval_loss": 0.481020450592041,
1310
+ "eval_runtime": 2.8131,
1311
+ "eval_samples_per_second": 0.355,
1312
+ "eval_steps_per_second": 0.355,
1313
+ "step": 184
1314
+ },
1315
+ {
1316
+ "epoch": 2.0,
1317
+ "step": 184,
1318
+ "total_flos": 2780892130967552.0,
1319
+ "train_loss": 0.43346462998053303,
1320
+ "train_runtime": 8632.6044,
1321
+ "train_samples_per_second": 0.675,
1322
+ "train_steps_per_second": 0.021
1323
+ }
1324
+ ],
1325
+ "logging_steps": 1,
1326
+ "max_steps": 184,
1327
+ "num_input_tokens_seen": 0,
1328
+ "num_train_epochs": 2,
1329
+ "save_steps": 500,
1330
+ "stateful_callbacks": {
1331
+ "TrainerControl": {
1332
+ "args": {
1333
+ "should_epoch_stop": false,
1334
+ "should_evaluate": false,
1335
+ "should_log": false,
1336
+ "should_save": true,
1337
+ "should_training_stop": true
1338
+ },
1339
+ "attributes": {}
1340
+ }
1341
+ },
1342
+ "total_flos": 2780892130967552.0,
1343
+ "train_batch_size": 4,
1344
+ "trial_name": null,
1345
+ "trial_params": null
1346
+ }