terry69 commited on
Commit
d581a03
·
verified ·
1 Parent(s): 5f47cf5

Model save

Browse files
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ base_model: mistralai/Mistral-7B-v0.1
9
+ model-index:
10
+ - name: zephyr-7b-sft-qlora-50p
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
+ # zephyr-7b-sft-qlora-50p
18
+
19
+ This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.9261
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: 0.0002
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 4
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - gradient_accumulation_steps: 2
47
+ - total_train_batch_size: 64
48
+ - total_eval_batch_size: 16
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: cosine
51
+ - lr_scheduler_warmup_ratio: 0.1
52
+ - num_epochs: 1
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss |
57
+ |:-------------:|:-----:|:----:|:---------------:|
58
+ | 0.6774 | 1.0 | 812 | 0.9261 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - PEFT 0.7.1
64
+ - Transformers 4.39.0.dev0
65
+ - Pytorch 2.2.2+cu121
66
+ - Datasets 2.14.6
67
+ - Tokenizers 0.15.2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad266861e8b51b4f6444c64586332e1cdad980b21ecdb49d56594f5a5bf80943
3
  size 31516744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a2fb1f5fe0bb9d33de166d72f05689aad2ae6f4817b72b25c11657f34e8337b
3
  size 31516744
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.7061199183240899,
4
+ "train_runtime": 29649.4111,
5
+ "train_samples": 51965,
6
+ "train_samples_per_second": 1.753,
7
+ "train_steps_per_second": 0.027
8
+ }
runs/May04_05-18-00_ip-172-31-69-60.ec2.internal/events.out.tfevents.1714800161.ip-172-31-69-60.ec2.internal.42244.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b874ff8f044dd76ddcc7a0d3877aea7c5ab8358b3d9554cdd3ca3d12febdb7b0
3
- size 38573
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc30cca49b9258c77b50fad09437c4f678e56381ce72400c45125064402b31d8
3
+ size 39620
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.7061199183240899,
4
+ "train_runtime": 29649.4111,
5
+ "train_samples": 51965,
6
+ "train_samples_per_second": 1.753,
7
+ "train_steps_per_second": 0.027
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 812,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 0.22422564560903913,
14
+ "learning_rate": 2.4390243902439027e-06,
15
+ "loss": 0.8165,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.01,
20
+ "grad_norm": 0.24393612584966326,
21
+ "learning_rate": 1.2195121951219513e-05,
22
+ "loss": 0.8171,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.01,
27
+ "grad_norm": 0.32976460652590056,
28
+ "learning_rate": 2.4390243902439026e-05,
29
+ "loss": 0.8001,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.02,
34
+ "grad_norm": 0.22143488102760825,
35
+ "learning_rate": 3.6585365853658535e-05,
36
+ "loss": 0.7749,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.02,
41
+ "grad_norm": 0.27241208120124494,
42
+ "learning_rate": 4.878048780487805e-05,
43
+ "loss": 0.7399,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.03,
48
+ "grad_norm": 0.22476497302964527,
49
+ "learning_rate": 6.097560975609756e-05,
50
+ "loss": 0.765,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.04,
55
+ "grad_norm": 0.23267051655279075,
56
+ "learning_rate": 7.317073170731707e-05,
57
+ "loss": 0.7434,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.04,
62
+ "grad_norm": 0.22352973519663066,
63
+ "learning_rate": 8.53658536585366e-05,
64
+ "loss": 0.7884,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.05,
69
+ "grad_norm": 0.23366158183718752,
70
+ "learning_rate": 9.75609756097561e-05,
71
+ "loss": 0.767,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.06,
76
+ "grad_norm": 0.21853843372631854,
77
+ "learning_rate": 0.00010975609756097563,
78
+ "loss": 0.76,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.06,
83
+ "grad_norm": 0.1997879106921521,
84
+ "learning_rate": 0.00012195121951219512,
85
+ "loss": 0.7516,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.07,
90
+ "grad_norm": 0.2251793056206077,
91
+ "learning_rate": 0.00013414634146341464,
92
+ "loss": 0.7173,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.07,
97
+ "grad_norm": 0.21081648300798228,
98
+ "learning_rate": 0.00014634146341463414,
99
+ "loss": 0.7528,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.08,
104
+ "grad_norm": 0.23666214760062876,
105
+ "learning_rate": 0.00015853658536585366,
106
+ "loss": 0.7404,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.09,
111
+ "grad_norm": 0.23722379969745064,
112
+ "learning_rate": 0.0001707317073170732,
113
+ "loss": 0.7612,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.09,
118
+ "grad_norm": 0.24333660134577043,
119
+ "learning_rate": 0.0001829268292682927,
120
+ "loss": 0.717,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.1,
125
+ "grad_norm": 0.24793258937714172,
126
+ "learning_rate": 0.0001951219512195122,
127
+ "loss": 0.7233,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.1,
132
+ "grad_norm": 0.21823934898390882,
133
+ "learning_rate": 0.0001999916658654738,
134
+ "loss": 0.7168,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.11,
139
+ "grad_norm": 0.2468304527466075,
140
+ "learning_rate": 0.0001999407400739705,
141
+ "loss": 0.7519,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.12,
146
+ "grad_norm": 0.2481744524594569,
147
+ "learning_rate": 0.00019984354211555644,
148
+ "loss": 0.7212,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.12,
153
+ "grad_norm": 0.22553056449126135,
154
+ "learning_rate": 0.00019970011699250152,
155
+ "loss": 0.7351,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.13,
160
+ "grad_norm": 0.20832972377638914,
161
+ "learning_rate": 0.00019951053111006976,
162
+ "loss": 0.7611,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.14,
167
+ "grad_norm": 0.2276942421072934,
168
+ "learning_rate": 0.00019927487224577402,
169
+ "loss": 0.7373,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.14,
174
+ "grad_norm": 0.22785202882473857,
175
+ "learning_rate": 0.0001989932495087353,
176
+ "loss": 0.7777,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.15,
181
+ "grad_norm": 0.23403114621707224,
182
+ "learning_rate": 0.0001986657932891657,
183
+ "loss": 0.7814,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.15,
188
+ "grad_norm": 0.21032447129887216,
189
+ "learning_rate": 0.0001982926551979982,
190
+ "loss": 0.7601,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.16,
195
+ "grad_norm": 0.21778287055015214,
196
+ "learning_rate": 0.00019787400799669154,
197
+ "loss": 0.7465,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.17,
202
+ "grad_norm": 0.23068074124934998,
203
+ "learning_rate": 0.00019741004551724207,
204
+ "loss": 0.7671,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.17,
209
+ "grad_norm": 0.21498665804807518,
210
+ "learning_rate": 0.00019690098257244064,
211
+ "loss": 0.7448,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.18,
216
+ "grad_norm": 0.2217460126233852,
217
+ "learning_rate": 0.00019634705485641488,
218
+ "loss": 0.7508,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.18,
223
+ "grad_norm": 0.22491198578150204,
224
+ "learning_rate": 0.00019574851883550395,
225
+ "loss": 0.7528,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.19,
230
+ "grad_norm": 0.21656015924096556,
231
+ "learning_rate": 0.00019510565162951537,
232
+ "loss": 0.7528,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.2,
237
+ "grad_norm": 0.21231516089906458,
238
+ "learning_rate": 0.00019441875088341997,
239
+ "loss": 0.7334,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.2,
244
+ "grad_norm": 0.20043526486232421,
245
+ "learning_rate": 0.00019368813462954316,
246
+ "loss": 0.7092,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.21,
251
+ "grad_norm": 0.2066905562271494,
252
+ "learning_rate": 0.00019291414114031743,
253
+ "loss": 0.69,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.22,
258
+ "grad_norm": 0.2409977578699428,
259
+ "learning_rate": 0.00019209712877166349,
260
+ "loss": 0.7274,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.22,
265
+ "grad_norm": 0.21478894589801012,
266
+ "learning_rate": 0.00019123747579707275,
267
+ "loss": 0.702,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.23,
272
+ "grad_norm": 0.21830847034248066,
273
+ "learning_rate": 0.00019033558023246844,
274
+ "loss": 0.7474,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.23,
279
+ "grad_norm": 0.22565415608082542,
280
+ "learning_rate": 0.0001893918596519257,
281
+ "loss": 0.7263,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.24,
286
+ "grad_norm": 0.22451701734198667,
287
+ "learning_rate": 0.00018840675099433636,
288
+ "loss": 0.7376,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.25,
293
+ "grad_norm": 0.22016338896296778,
294
+ "learning_rate": 0.00018738071036110808,
295
+ "loss": 0.6939,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.25,
300
+ "grad_norm": 0.20607069335042727,
301
+ "learning_rate": 0.00018631421280499116,
302
+ "loss": 0.7351,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.26,
307
+ "grad_norm": 0.20601552052171884,
308
+ "learning_rate": 0.00018520775211013093,
309
+ "loss": 0.7082,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.26,
314
+ "grad_norm": 0.21774646892016394,
315
+ "learning_rate": 0.00018406184056344782,
316
+ "loss": 0.745,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.27,
321
+ "grad_norm": 0.23099746146509867,
322
+ "learning_rate": 0.00018287700871745036,
323
+ "loss": 0.7707,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.28,
328
+ "grad_norm": 0.2225513878139953,
329
+ "learning_rate": 0.0001816538051445916,
330
+ "loss": 0.72,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.28,
335
+ "grad_norm": 0.2810648109589189,
336
+ "learning_rate": 0.00018039279618328212,
337
+ "loss": 0.7159,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.29,
342
+ "grad_norm": 0.23360820743854752,
343
+ "learning_rate": 0.00017909456567567772,
344
+ "loss": 0.7916,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.3,
349
+ "grad_norm": 0.2346981575638156,
350
+ "learning_rate": 0.0001777597146973627,
351
+ "loss": 0.7543,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.3,
356
+ "grad_norm": 0.22472791649678256,
357
+ "learning_rate": 0.00017638886127905427,
358
+ "loss": 0.7145,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.31,
363
+ "grad_norm": 0.2330382456080435,
364
+ "learning_rate": 0.00017498264012045687,
365
+ "loss": 0.6951,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.31,
370
+ "grad_norm": 0.28462945710570964,
371
+ "learning_rate": 0.00017354170229639856,
372
+ "loss": 0.7218,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.32,
377
+ "grad_norm": 0.23120564986808903,
378
+ "learning_rate": 0.00017206671495538612,
379
+ "loss": 0.6954,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.33,
384
+ "grad_norm": 0.21787726424323484,
385
+ "learning_rate": 0.0001705583610107178,
386
+ "loss": 0.6993,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.33,
391
+ "grad_norm": 0.22337741579847503,
392
+ "learning_rate": 0.0001690173388242972,
393
+ "loss": 0.7742,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.34,
398
+ "grad_norm": 0.2418352997312942,
399
+ "learning_rate": 0.00016744436188329456,
400
+ "loss": 0.7385,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.34,
405
+ "grad_norm": 0.25104847122600993,
406
+ "learning_rate": 0.0001658401584698049,
407
+ "loss": 0.7142,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.35,
412
+ "grad_norm": 0.21545698908596508,
413
+ "learning_rate": 0.00016420547132365635,
414
+ "loss": 0.7043,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.36,
419
+ "grad_norm": 0.24534521084917407,
420
+ "learning_rate": 0.00016254105729852464,
421
+ "loss": 0.6988,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.36,
426
+ "grad_norm": 0.24621959592804224,
427
+ "learning_rate": 0.00016084768701151263,
428
+ "loss": 0.701,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.37,
433
+ "grad_norm": 0.2441445089915858,
434
+ "learning_rate": 0.00015912614448635782,
435
+ "loss": 0.713,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.38,
440
+ "grad_norm": 0.23144503509205255,
441
+ "learning_rate": 0.00015737722679043248,
442
+ "loss": 0.7185,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.38,
447
+ "grad_norm": 0.23779196053246493,
448
+ "learning_rate": 0.00015560174366570446,
449
+ "loss": 0.6585,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.39,
454
+ "grad_norm": 0.23922306500283833,
455
+ "learning_rate": 0.00015380051715382996,
456
+ "loss": 0.7025,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.39,
461
+ "grad_norm": 0.25732276520746106,
462
+ "learning_rate": 0.0001519743812155516,
463
+ "loss": 0.6496,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.4,
468
+ "grad_norm": 0.25676931335616193,
469
+ "learning_rate": 0.00015012418134457755,
470
+ "loss": 0.6946,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.41,
475
+ "grad_norm": 0.25925282419918827,
476
+ "learning_rate": 0.00014825077417612186,
477
+ "loss": 0.7309,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.41,
482
+ "grad_norm": 0.25723625109413206,
483
+ "learning_rate": 0.0001463550270902851,
484
+ "loss": 0.6929,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.42,
489
+ "grad_norm": 0.2758091340120669,
490
+ "learning_rate": 0.00014443781781046136,
491
+ "loss": 0.7016,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.42,
496
+ "grad_norm": 0.2368505670464136,
497
+ "learning_rate": 0.0001425000339969554,
498
+ "loss": 0.703,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.43,
503
+ "grad_norm": 0.23084399243795903,
504
+ "learning_rate": 0.00014054257283599973,
505
+ "loss": 0.7102,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.44,
510
+ "grad_norm": 0.2503463601524904,
511
+ "learning_rate": 0.0001385663406243607,
512
+ "loss": 0.7278,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.44,
517
+ "grad_norm": 0.22226083699821775,
518
+ "learning_rate": 0.00013657225234972695,
519
+ "loss": 0.6753,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.45,
524
+ "grad_norm": 0.26300812718557964,
525
+ "learning_rate": 0.00013456123126707334,
526
+ "loss": 0.6871,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.46,
531
+ "grad_norm": 0.257794988184064,
532
+ "learning_rate": 0.00013253420847119803,
533
+ "loss": 0.737,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.46,
538
+ "grad_norm": 0.23283253484592037,
539
+ "learning_rate": 0.0001304921224656289,
540
+ "loss": 0.6948,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.47,
545
+ "grad_norm": 0.2489222484332262,
546
+ "learning_rate": 0.0001284359187281004,
547
+ "loss": 0.6807,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.47,
552
+ "grad_norm": 0.24773496287366326,
553
+ "learning_rate": 0.00012636654927280073,
554
+ "loss": 0.7322,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.48,
559
+ "grad_norm": 0.25284782064647693,
560
+ "learning_rate": 0.0001242849722095936,
561
+ "loss": 0.7038,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.49,
566
+ "grad_norm": 0.2640705980904302,
567
+ "learning_rate": 0.00012219215130041656,
568
+ "loss": 0.6818,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.49,
573
+ "grad_norm": 0.244353569188838,
574
+ "learning_rate": 0.00012008905551306356,
575
+ "loss": 0.6888,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.5,
580
+ "grad_norm": 0.2582385397817055,
581
+ "learning_rate": 0.00011797665857255621,
582
+ "loss": 0.7347,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.5,
587
+ "grad_norm": 0.2657939654189472,
588
+ "learning_rate": 0.00011585593851031347,
589
+ "loss": 0.7292,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.51,
594
+ "grad_norm": 0.2412402754418769,
595
+ "learning_rate": 0.00011372787721132648,
596
+ "loss": 0.6793,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.52,
601
+ "grad_norm": 0.25269309847633625,
602
+ "learning_rate": 0.00011159345995955006,
603
+ "loss": 0.6811,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.52,
608
+ "grad_norm": 0.3555199335436584,
609
+ "learning_rate": 0.00010945367498171993,
610
+ "loss": 0.6632,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.53,
615
+ "grad_norm": 0.2807299993278487,
616
+ "learning_rate": 0.00010730951298980776,
617
+ "loss": 0.7121,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.54,
622
+ "grad_norm": 0.2676168527706757,
623
+ "learning_rate": 0.00010516196672232539,
624
+ "loss": 0.6897,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.54,
629
+ "grad_norm": 0.2696033985636684,
630
+ "learning_rate": 0.00010301203048469083,
631
+ "loss": 0.7149,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.55,
636
+ "grad_norm": 0.264343040293582,
637
+ "learning_rate": 0.00010086069968886885,
638
+ "loss": 0.697,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.55,
643
+ "grad_norm": 0.24941452883154777,
644
+ "learning_rate": 9.870897039249911e-05,
645
+ "loss": 0.6739,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.56,
650
+ "grad_norm": 0.27184754304212144,
651
+ "learning_rate": 9.655783883772545e-05,
652
+ "loss": 0.6771,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.57,
657
+ "grad_norm": 0.25069232194770324,
658
+ "learning_rate": 9.440830098993969e-05,
659
+ "loss": 0.6628,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.57,
664
+ "grad_norm": 0.26945962491120906,
665
+ "learning_rate": 9.22613520766537e-05,
666
+ "loss": 0.6501,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.58,
671
+ "grad_norm": 0.27595385280343615,
672
+ "learning_rate": 9.011798612671286e-05,
673
+ "loss": 0.6923,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.58,
678
+ "grad_norm": 0.23254427170051437,
679
+ "learning_rate": 8.797919551006475e-05,
680
+ "loss": 0.6687,
681
+ "step": 475
682
+ },
683
+ {
684
+ "epoch": 0.59,
685
+ "grad_norm": 0.2700843553748168,
686
+ "learning_rate": 8.58459704782957e-05,
687
+ "loss": 0.6922,
688
+ "step": 480
689
+ },
690
+ {
691
+ "epoch": 0.6,
692
+ "grad_norm": 0.29075126290562925,
693
+ "learning_rate": 8.371929870614833e-05,
694
+ "loss": 0.6838,
695
+ "step": 485
696
+ },
697
+ {
698
+ "epoch": 0.6,
699
+ "grad_norm": 0.2582533489019304,
700
+ "learning_rate": 8.160016483423199e-05,
701
+ "loss": 0.709,
702
+ "step": 490
703
+ },
704
+ {
705
+ "epoch": 0.61,
706
+ "grad_norm": 0.24306629955384693,
707
+ "learning_rate": 7.948955001313811e-05,
708
+ "loss": 0.6644,
709
+ "step": 495
710
+ },
711
+ {
712
+ "epoch": 0.62,
713
+ "grad_norm": 0.2792860639380007,
714
+ "learning_rate": 7.738843144917119e-05,
715
+ "loss": 0.7122,
716
+ "step": 500
717
+ },
718
+ {
719
+ "epoch": 0.62,
720
+ "grad_norm": 0.2717162268363558,
721
+ "learning_rate": 7.529778195190645e-05,
722
+ "loss": 0.7235,
723
+ "step": 505
724
+ },
725
+ {
726
+ "epoch": 0.63,
727
+ "grad_norm": 0.284678632001059,
728
+ "learning_rate": 7.321856948378259e-05,
729
+ "loss": 0.6916,
730
+ "step": 510
731
+ },
732
+ {
733
+ "epoch": 0.63,
734
+ "grad_norm": 0.26262649770739277,
735
+ "learning_rate": 7.115175671193913e-05,
736
+ "loss": 0.6741,
737
+ "step": 515
738
+ },
739
+ {
740
+ "epoch": 0.64,
741
+ "grad_norm": 0.2529748057506211,
742
+ "learning_rate": 6.909830056250527e-05,
743
+ "loss": 0.7025,
744
+ "step": 520
745
+ },
746
+ {
747
+ "epoch": 0.65,
748
+ "grad_norm": 0.28817490304932813,
749
+ "learning_rate": 6.7059151777547e-05,
750
+ "loss": 0.7071,
751
+ "step": 525
752
+ },
753
+ {
754
+ "epoch": 0.65,
755
+ "grad_norm": 0.28586738996038136,
756
+ "learning_rate": 6.503525447487715e-05,
757
+ "loss": 0.7223,
758
+ "step": 530
759
+ },
760
+ {
761
+ "epoch": 0.66,
762
+ "grad_norm": 0.27355383837426006,
763
+ "learning_rate": 6.30275457109327e-05,
764
+ "loss": 0.6878,
765
+ "step": 535
766
+ },
767
+ {
768
+ "epoch": 0.67,
769
+ "grad_norm": 0.2696146366032459,
770
+ "learning_rate": 6.103695504692122e-05,
771
+ "loss": 0.666,
772
+ "step": 540
773
+ },
774
+ {
775
+ "epoch": 0.67,
776
+ "grad_norm": 0.293084107951244,
777
+ "learning_rate": 5.906440411843787e-05,
778
+ "loss": 0.7165,
779
+ "step": 545
780
+ },
781
+ {
782
+ "epoch": 0.68,
783
+ "grad_norm": 0.2744477897912315,
784
+ "learning_rate": 5.7110806208751655e-05,
785
+ "loss": 0.6791,
786
+ "step": 550
787
+ },
788
+ {
789
+ "epoch": 0.68,
790
+ "grad_norm": 0.2719074571288193,
791
+ "learning_rate": 5.5177065825958966e-05,
792
+ "loss": 0.7183,
793
+ "step": 555
794
+ },
795
+ {
796
+ "epoch": 0.69,
797
+ "grad_norm": 0.29658031172179306,
798
+ "learning_rate": 5.326407828419979e-05,
799
+ "loss": 0.6741,
800
+ "step": 560
801
+ },
802
+ {
803
+ "epoch": 0.7,
804
+ "grad_norm": 0.25304272831172997,
805
+ "learning_rate": 5.137272928913097e-05,
806
+ "loss": 0.68,
807
+ "step": 565
808
+ },
809
+ {
810
+ "epoch": 0.7,
811
+ "grad_norm": 0.2676461633502972,
812
+ "learning_rate": 4.9503894527847964e-05,
813
+ "loss": 0.6593,
814
+ "step": 570
815
+ },
816
+ {
817
+ "epoch": 0.71,
818
+ "grad_norm": 0.31247663625681804,
819
+ "learning_rate": 4.765843926344501e-05,
820
+ "loss": 0.6863,
821
+ "step": 575
822
+ },
823
+ {
824
+ "epoch": 0.71,
825
+ "grad_norm": 0.2955325664002294,
826
+ "learning_rate": 4.583721793440188e-05,
827
+ "loss": 0.6728,
828
+ "step": 580
829
+ },
830
+ {
831
+ "epoch": 0.72,
832
+ "grad_norm": 0.2807174542636257,
833
+ "learning_rate": 4.4041073758982335e-05,
834
+ "loss": 0.6913,
835
+ "step": 585
836
+ },
837
+ {
838
+ "epoch": 0.73,
839
+ "grad_norm": 0.2989395763460932,
840
+ "learning_rate": 4.227083834482728e-05,
841
+ "loss": 0.6085,
842
+ "step": 590
843
+ },
844
+ {
845
+ "epoch": 0.73,
846
+ "grad_norm": 0.2636409419874345,
847
+ "learning_rate": 4.052733130392367e-05,
848
+ "loss": 0.676,
849
+ "step": 595
850
+ },
851
+ {
852
+ "epoch": 0.74,
853
+ "grad_norm": 0.2735419958012749,
854
+ "learning_rate": 3.881135987312757e-05,
855
+ "loss": 0.697,
856
+ "step": 600
857
+ },
858
+ {
859
+ "epoch": 0.75,
860
+ "grad_norm": 0.29812585759610105,
861
+ "learning_rate": 3.712371854041654e-05,
862
+ "loss": 0.6788,
863
+ "step": 605
864
+ },
865
+ {
866
+ "epoch": 0.75,
867
+ "grad_norm": 0.2858805204008935,
868
+ "learning_rate": 3.546518867704499e-05,
869
+ "loss": 0.6891,
870
+ "step": 610
871
+ },
872
+ {
873
+ "epoch": 0.76,
874
+ "grad_norm": 0.2711930626215174,
875
+ "learning_rate": 3.383653817577216e-05,
876
+ "loss": 0.6626,
877
+ "step": 615
878
+ },
879
+ {
880
+ "epoch": 0.76,
881
+ "grad_norm": 0.30583390146359735,
882
+ "learning_rate": 3.223852109533112e-05,
883
+ "loss": 0.6977,
884
+ "step": 620
885
+ },
886
+ {
887
+ "epoch": 0.77,
888
+ "grad_norm": 0.31918222012772746,
889
+ "learning_rate": 3.0671877311302244e-05,
890
+ "loss": 0.6546,
891
+ "step": 625
892
+ },
893
+ {
894
+ "epoch": 0.78,
895
+ "grad_norm": 0.27113125300550006,
896
+ "learning_rate": 2.9137332173554043e-05,
897
+ "loss": 0.6718,
898
+ "step": 630
899
+ },
900
+ {
901
+ "epoch": 0.78,
902
+ "grad_norm": 0.2933116316225334,
903
+ "learning_rate": 2.763559617040876e-05,
904
+ "loss": 0.677,
905
+ "step": 635
906
+ },
907
+ {
908
+ "epoch": 0.79,
909
+ "grad_norm": 0.3236593994578141,
910
+ "learning_rate": 2.616736459968936e-05,
911
+ "loss": 0.6685,
912
+ "step": 640
913
+ },
914
+ {
915
+ "epoch": 0.79,
916
+ "grad_norm": 0.30406592976690633,
917
+ "learning_rate": 2.473331724679917e-05,
918
+ "loss": 0.6746,
919
+ "step": 645
920
+ },
921
+ {
922
+ "epoch": 0.8,
923
+ "grad_norm": 0.27899362724771787,
924
+ "learning_rate": 2.33341180699841e-05,
925
+ "loss": 0.6667,
926
+ "step": 650
927
+ },
928
+ {
929
+ "epoch": 0.81,
930
+ "grad_norm": 0.2954598561484786,
931
+ "learning_rate": 2.1970414892922442e-05,
932
+ "loss": 0.7175,
933
+ "step": 655
934
+ },
935
+ {
936
+ "epoch": 0.81,
937
+ "grad_norm": 0.3100581301740447,
938
+ "learning_rate": 2.0642839104785272e-05,
939
+ "loss": 0.6979,
940
+ "step": 660
941
+ },
942
+ {
943
+ "epoch": 0.82,
944
+ "grad_norm": 0.2759099798186259,
945
+ "learning_rate": 1.9352005367905536e-05,
946
+ "loss": 0.7098,
947
+ "step": 665
948
+ },
949
+ {
950
+ "epoch": 0.83,
951
+ "grad_norm": 0.30931195338097267,
952
+ "learning_rate": 1.8098511333192024e-05,
953
+ "loss": 0.6593,
954
+ "step": 670
955
+ },
956
+ {
957
+ "epoch": 0.83,
958
+ "grad_norm": 0.32368942926694433,
959
+ "learning_rate": 1.6882937363419203e-05,
960
+ "loss": 0.6869,
961
+ "step": 675
962
+ },
963
+ {
964
+ "epoch": 0.84,
965
+ "grad_norm": 0.2776307386865438,
966
+ "learning_rate": 1.570584626452173e-05,
967
+ "loss": 0.6717,
968
+ "step": 680
969
+ },
970
+ {
971
+ "epoch": 0.84,
972
+ "grad_norm": 0.30301564173702233,
973
+ "learning_rate": 1.4567783025017301e-05,
974
+ "loss": 0.6681,
975
+ "step": 685
976
+ },
977
+ {
978
+ "epoch": 0.85,
979
+ "grad_norm": 0.31904417802084467,
980
+ "learning_rate": 1.3469274563679402e-05,
981
+ "loss": 0.6851,
982
+ "step": 690
983
+ },
984
+ {
985
+ "epoch": 0.86,
986
+ "grad_norm": 0.2774036633854793,
987
+ "learning_rate": 1.2410829485575704e-05,
988
+ "loss": 0.7023,
989
+ "step": 695
990
+ },
991
+ {
992
+ "epoch": 0.86,
993
+ "grad_norm": 0.2965220463492153,
994
+ "learning_rate": 1.1392937846586215e-05,
995
+ "loss": 0.6565,
996
+ "step": 700
997
+ },
998
+ {
999
+ "epoch": 0.87,
1000
+ "grad_norm": 0.32675908474718157,
1001
+ "learning_rate": 1.0416070926509113e-05,
1002
+ "loss": 0.6487,
1003
+ "step": 705
1004
+ },
1005
+ {
1006
+ "epoch": 0.87,
1007
+ "grad_norm": 0.3090900072007822,
1008
+ "learning_rate": 9.48068101086026e-06,
1009
+ "loss": 0.6976,
1010
+ "step": 710
1011
+ },
1012
+ {
1013
+ "epoch": 0.88,
1014
+ "grad_norm": 0.309037705156712,
1015
+ "learning_rate": 8.58720118146662e-06,
1016
+ "loss": 0.66,
1017
+ "step": 715
1018
+ },
1019
+ {
1020
+ "epoch": 0.89,
1021
+ "grad_norm": 0.3087738006371124,
1022
+ "learning_rate": 7.736045115951251e-06,
1023
+ "loss": 0.7067,
1024
+ "step": 720
1025
+ },
1026
+ {
1027
+ "epoch": 0.89,
1028
+ "grad_norm": 0.3443047214751086,
1029
+ "learning_rate": 6.927606896202066e-06,
1030
+ "loss": 0.6968,
1031
+ "step": 725
1032
+ },
1033
+ {
1034
+ "epoch": 0.9,
1035
+ "grad_norm": 0.30866169616965344,
1036
+ "learning_rate": 6.16226082591359e-06,
1037
+ "loss": 0.6595,
1038
+ "step": 730
1039
+ },
1040
+ {
1041
+ "epoch": 0.91,
1042
+ "grad_norm": 0.26453835920017715,
1043
+ "learning_rate": 5.440361257285742e-06,
1044
+ "loss": 0.6873,
1045
+ "step": 735
1046
+ },
1047
+ {
1048
+ "epoch": 0.91,
1049
+ "grad_norm": 0.2870240594644306,
1050
+ "learning_rate": 4.762242426960262e-06,
1051
+ "loss": 0.6897,
1052
+ "step": 740
1053
+ },
1054
+ {
1055
+ "epoch": 0.92,
1056
+ "grad_norm": 0.31907803929807727,
1057
+ "learning_rate": 4.128218301270359e-06,
1058
+ "loss": 0.7062,
1059
+ "step": 745
1060
+ },
1061
+ {
1062
+ "epoch": 0.92,
1063
+ "grad_norm": 0.3461230801807586,
1064
+ "learning_rate": 3.5385824308756587e-06,
1065
+ "loss": 0.6506,
1066
+ "step": 750
1067
+ },
1068
+ {
1069
+ "epoch": 0.93,
1070
+ "grad_norm": 0.2982663104307397,
1071
+ "learning_rate": 2.9936078148492973e-06,
1072
+ "loss": 0.6722,
1073
+ "step": 755
1074
+ },
1075
+ {
1076
+ "epoch": 0.94,
1077
+ "grad_norm": 0.27990503389995286,
1078
+ "learning_rate": 2.493546774280531e-06,
1079
+ "loss": 0.7049,
1080
+ "step": 760
1081
+ },
1082
+ {
1083
+ "epoch": 0.94,
1084
+ "grad_norm": 0.3112912132178525,
1085
+ "learning_rate": 2.0386308354509942e-06,
1086
+ "loss": 0.7125,
1087
+ "step": 765
1088
+ },
1089
+ {
1090
+ "epoch": 0.95,
1091
+ "grad_norm": 0.31758074243604545,
1092
+ "learning_rate": 1.6290706226390285e-06,
1093
+ "loss": 0.6857,
1094
+ "step": 770
1095
+ },
1096
+ {
1097
+ "epoch": 0.95,
1098
+ "grad_norm": 0.3210813944651733,
1099
+ "learning_rate": 1.2650557606013635e-06,
1100
+ "loss": 0.6829,
1101
+ "step": 775
1102
+ },
1103
+ {
1104
+ "epoch": 0.96,
1105
+ "grad_norm": 0.2880839335185284,
1106
+ "learning_rate": 9.46754786777726e-07,
1107
+ "loss": 0.7146,
1108
+ "step": 780
1109
+ },
1110
+ {
1111
+ "epoch": 0.97,
1112
+ "grad_norm": 0.29564960884643837,
1113
+ "learning_rate": 6.74315073258569e-07,
1114
+ "loss": 0.7101,
1115
+ "step": 785
1116
+ },
1117
+ {
1118
+ "epoch": 0.97,
1119
+ "grad_norm": 0.29256820612374973,
1120
+ "learning_rate": 4.4786275855247527e-07,
1121
+ "loss": 0.6478,
1122
+ "step": 790
1123
+ },
1124
+ {
1125
+ "epoch": 0.98,
1126
+ "grad_norm": 0.33071981852297627,
1127
+ "learning_rate": 2.675026891844512e-07,
1128
+ "loss": 0.672,
1129
+ "step": 795
1130
+ },
1131
+ {
1132
+ "epoch": 0.99,
1133
+ "grad_norm": 0.329286091376579,
1134
+ "learning_rate": 1.333183711524133e-07,
1135
+ "loss": 0.6438,
1136
+ "step": 800
1137
+ },
1138
+ {
1139
+ "epoch": 0.99,
1140
+ "grad_norm": 0.3104373424505981,
1141
+ "learning_rate": 4.5371931264270864e-08,
1142
+ "loss": 0.6555,
1143
+ "step": 805
1144
+ },
1145
+ {
1146
+ "epoch": 1.0,
1147
+ "grad_norm": 0.2971195933385636,
1148
+ "learning_rate": 3.7040883734462683e-09,
1149
+ "loss": 0.6774,
1150
+ "step": 810
1151
+ },
1152
+ {
1153
+ "epoch": 1.0,
1154
+ "eval_loss": 0.926139771938324,
1155
+ "eval_runtime": 459.5724,
1156
+ "eval_samples_per_second": 5.026,
1157
+ "eval_steps_per_second": 0.316,
1158
+ "step": 812
1159
+ },
1160
+ {
1161
+ "epoch": 1.0,
1162
+ "step": 812,
1163
+ "total_flos": 9607955794100224.0,
1164
+ "train_loss": 0.7061199183240899,
1165
+ "train_runtime": 29649.4111,
1166
+ "train_samples_per_second": 1.753,
1167
+ "train_steps_per_second": 0.027
1168
+ }
1169
+ ],
1170
+ "logging_steps": 5,
1171
+ "max_steps": 812,
1172
+ "num_input_tokens_seen": 0,
1173
+ "num_train_epochs": 1,
1174
+ "save_steps": 100,
1175
+ "total_flos": 9607955794100224.0,
1176
+ "train_batch_size": 8,
1177
+ "trial_name": null,
1178
+ "trial_params": null
1179
+ }