sedrickkeh commited on
Commit
98899fb
1 Parent(s): 8d22c6d

End of training

Browse files
README.md CHANGED
@@ -4,6 +4,7 @@ license: llama3.1
4
  base_model: meta-llama/Meta-Llama-3.1-8B
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: dcft_orca-agentinstruct-1M-v1-cleaned-singleturn
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # dcft_orca-agentinstruct-1M-v1-cleaned-singleturn
17
 
18
- This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.4835
21
 
 
4
  base_model: meta-llama/Meta-Llama-3.1-8B
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: dcft_orca-agentinstruct-1M-v1-cleaned-singleturn
 
16
 
17
  # dcft_orca-agentinstruct-1M-v1-cleaned-singleturn
18
 
19
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/dcft_orca-agentinstruct-1M-v1-cleaned-singleturn dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.4835
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9977761304670127,
3
+ "eval_loss": 0.4834764897823334,
4
+ "eval_runtime": 117.4592,
5
+ "eval_samples_per_second": 154.718,
6
+ "eval_steps_per_second": 0.604,
7
+ "total_flos": 3386087791656960.0,
8
+ "train_loss": 0.4438282892800698,
9
+ "train_runtime": 17391.1323,
10
+ "train_samples_per_second": 59.561,
11
+ "train_steps_per_second": 0.116
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9977761304670127,
3
+ "eval_loss": 0.4834764897823334,
4
+ "eval_runtime": 117.4592,
5
+ "eval_samples_per_second": 154.718,
6
+ "eval_steps_per_second": 0.604
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9977761304670127,
3
+ "total_flos": 3386087791656960.0,
4
+ "train_loss": 0.4438282892800698,
5
+ "train_runtime": 17391.1323,
6
+ "train_samples_per_second": 59.561,
7
+ "train_steps_per_second": 0.116
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1480 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9977761304670127,
5
+ "eval_steps": 500,
6
+ "global_step": 2022,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.014825796886582653,
13
+ "grad_norm": 1.3803142660082024,
14
+ "learning_rate": 5e-06,
15
+ "loss": 0.6862,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.029651593773165306,
20
+ "grad_norm": 1.790122423429332,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.6305,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.04447739065974796,
27
+ "grad_norm": 0.8497603342076308,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.5946,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.05930318754633061,
34
+ "grad_norm": 0.7732974567839591,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.5858,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.07412898443291327,
41
+ "grad_norm": 0.8204168744024732,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.5662,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.08895478131949593,
48
+ "grad_norm": 0.7530005874020861,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.564,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.10378057820607858,
55
+ "grad_norm": 0.6979206993642474,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.5536,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.11860637509266123,
62
+ "grad_norm": 0.9504756484437652,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.5447,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.1334321719792439,
69
+ "grad_norm": 0.8937944128313379,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.5466,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.14825796886582654,
76
+ "grad_norm": 0.6670560083366487,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.5354,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.16308376575240918,
83
+ "grad_norm": 0.7364925811772932,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.535,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.17790956263899185,
90
+ "grad_norm": 0.7183776415658619,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.5338,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.1927353595255745,
97
+ "grad_norm": 0.5967155900573925,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.5301,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.20756115641215717,
104
+ "grad_norm": 0.5747353912092298,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.5263,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.2223869532987398,
111
+ "grad_norm": 0.6159997079939371,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.5248,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.23721275018532245,
118
+ "grad_norm": 0.5680164570830968,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.5279,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.2520385470719051,
125
+ "grad_norm": 0.5992456838263306,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.526,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.2668643439584878,
132
+ "grad_norm": 0.5930479122165856,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.5224,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.28169014084507044,
139
+ "grad_norm": 0.5912410054870685,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.52,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.2965159377316531,
146
+ "grad_norm": 0.5894696404162991,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.5179,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.3113417346182357,
153
+ "grad_norm": 0.5643703980877148,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.5182,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.32616753150481836,
160
+ "grad_norm": 0.5861129018729444,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.5104,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.34099332839140106,
167
+ "grad_norm": 0.6236624375674511,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.5131,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.3558191252779837,
174
+ "grad_norm": 0.5812434696304949,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.5191,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.37064492216456635,
181
+ "grad_norm": 0.7181156036216183,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.5093,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.385470719051149,
188
+ "grad_norm": 0.587369525728773,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.5161,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.40029651593773163,
195
+ "grad_norm": 0.5460966546871288,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.5178,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.41512231282431433,
202
+ "grad_norm": 0.5876447069011888,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.5142,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.429948109710897,
209
+ "grad_norm": 0.816294324192534,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.5125,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.4447739065974796,
216
+ "grad_norm": 0.5492628600148616,
217
+ "learning_rate": 5e-06,
218
+ "loss": 0.5078,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.45959970348406226,
223
+ "grad_norm": 0.579955709352068,
224
+ "learning_rate": 5e-06,
225
+ "loss": 0.5045,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.4744255003706449,
230
+ "grad_norm": 0.6279455964566482,
231
+ "learning_rate": 5e-06,
232
+ "loss": 0.5047,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.4892512972572276,
237
+ "grad_norm": 0.6390417903003635,
238
+ "learning_rate": 5e-06,
239
+ "loss": 0.5067,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.5040770941438102,
244
+ "grad_norm": 0.5816721190754486,
245
+ "learning_rate": 5e-06,
246
+ "loss": 0.5135,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.5189028910303929,
251
+ "grad_norm": 0.6458696214772466,
252
+ "learning_rate": 5e-06,
253
+ "loss": 0.5034,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.5337286879169756,
258
+ "grad_norm": 0.6957712465947605,
259
+ "learning_rate": 5e-06,
260
+ "loss": 0.5048,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.5485544848035582,
265
+ "grad_norm": 0.543098433920077,
266
+ "learning_rate": 5e-06,
267
+ "loss": 0.4991,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.5633802816901409,
272
+ "grad_norm": 0.7663819453316695,
273
+ "learning_rate": 5e-06,
274
+ "loss": 0.5025,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.5782060785767235,
279
+ "grad_norm": 0.5194777261335899,
280
+ "learning_rate": 5e-06,
281
+ "loss": 0.5072,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.5930318754633062,
286
+ "grad_norm": 0.8363946362832739,
287
+ "learning_rate": 5e-06,
288
+ "loss": 0.4948,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.6078576723498889,
293
+ "grad_norm": 0.5430505650241441,
294
+ "learning_rate": 5e-06,
295
+ "loss": 0.5024,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.6226834692364714,
300
+ "grad_norm": 0.5574129318838634,
301
+ "learning_rate": 5e-06,
302
+ "loss": 0.5034,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.6375092661230541,
307
+ "grad_norm": 0.701668057920261,
308
+ "learning_rate": 5e-06,
309
+ "loss": 0.4912,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.6523350630096367,
314
+ "grad_norm": 0.5952225478810055,
315
+ "learning_rate": 5e-06,
316
+ "loss": 0.4898,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.6671608598962194,
321
+ "grad_norm": 0.585331803107272,
322
+ "learning_rate": 5e-06,
323
+ "loss": 0.5027,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.6819866567828021,
328
+ "grad_norm": 0.5906175115867641,
329
+ "learning_rate": 5e-06,
330
+ "loss": 0.49,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.6968124536693847,
335
+ "grad_norm": 0.5782512807193211,
336
+ "learning_rate": 5e-06,
337
+ "loss": 0.4962,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.7116382505559674,
342
+ "grad_norm": 0.528401047427795,
343
+ "learning_rate": 5e-06,
344
+ "loss": 0.4979,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.72646404744255,
349
+ "grad_norm": 0.7128769222059271,
350
+ "learning_rate": 5e-06,
351
+ "loss": 0.4982,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.7412898443291327,
356
+ "grad_norm": 0.5767857437742224,
357
+ "learning_rate": 5e-06,
358
+ "loss": 0.4891,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.7561156412157154,
363
+ "grad_norm": 0.6930280814580314,
364
+ "learning_rate": 5e-06,
365
+ "loss": 0.5006,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.770941438102298,
370
+ "grad_norm": 0.6530314579756452,
371
+ "learning_rate": 5e-06,
372
+ "loss": 0.4966,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.7857672349888807,
377
+ "grad_norm": 0.6639683423874188,
378
+ "learning_rate": 5e-06,
379
+ "loss": 0.4962,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.8005930318754633,
384
+ "grad_norm": 0.5556537170587046,
385
+ "learning_rate": 5e-06,
386
+ "loss": 0.4947,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.815418828762046,
391
+ "grad_norm": 0.5740824829726571,
392
+ "learning_rate": 5e-06,
393
+ "loss": 0.4919,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.8302446256486287,
398
+ "grad_norm": 0.5307405473088794,
399
+ "learning_rate": 5e-06,
400
+ "loss": 0.4864,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.8450704225352113,
405
+ "grad_norm": 0.5249601710096029,
406
+ "learning_rate": 5e-06,
407
+ "loss": 0.4926,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.859896219421794,
412
+ "grad_norm": 0.5263542668413514,
413
+ "learning_rate": 5e-06,
414
+ "loss": 0.4877,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.8747220163083765,
419
+ "grad_norm": 0.5027236096291062,
420
+ "learning_rate": 5e-06,
421
+ "loss": 0.4903,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.8895478131949592,
426
+ "grad_norm": 0.687053549139694,
427
+ "learning_rate": 5e-06,
428
+ "loss": 0.4945,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.9043736100815419,
433
+ "grad_norm": 0.6064169430923966,
434
+ "learning_rate": 5e-06,
435
+ "loss": 0.4898,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.9191994069681245,
440
+ "grad_norm": 0.5127672913798731,
441
+ "learning_rate": 5e-06,
442
+ "loss": 0.4916,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.9340252038547072,
447
+ "grad_norm": 0.5911308230908845,
448
+ "learning_rate": 5e-06,
449
+ "loss": 0.4876,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.9488510007412898,
454
+ "grad_norm": 0.5318485612638623,
455
+ "learning_rate": 5e-06,
456
+ "loss": 0.4911,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.9636767976278725,
461
+ "grad_norm": 0.599135799828323,
462
+ "learning_rate": 5e-06,
463
+ "loss": 0.4907,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.9785025945144552,
468
+ "grad_norm": 0.5017158299240659,
469
+ "learning_rate": 5e-06,
470
+ "loss": 0.4864,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.9933283914010378,
475
+ "grad_norm": 0.638905966589537,
476
+ "learning_rate": 5e-06,
477
+ "loss": 0.4886,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.9992587101556709,
482
+ "eval_loss": 0.489400178194046,
483
+ "eval_runtime": 119.2986,
484
+ "eval_samples_per_second": 152.332,
485
+ "eval_steps_per_second": 0.595,
486
+ "step": 674
487
+ },
488
+ {
489
+ "epoch": 1.0081541882876204,
490
+ "grad_norm": 0.8019081623682851,
491
+ "learning_rate": 5e-06,
492
+ "loss": 0.4775,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.0229799851742032,
497
+ "grad_norm": 0.5833948483649493,
498
+ "learning_rate": 5e-06,
499
+ "loss": 0.4344,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.0378057820607858,
504
+ "grad_norm": 0.5717232078953663,
505
+ "learning_rate": 5e-06,
506
+ "loss": 0.4372,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.0526315789473684,
511
+ "grad_norm": 0.5320074952877888,
512
+ "learning_rate": 5e-06,
513
+ "loss": 0.4376,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.0674573758339512,
518
+ "grad_norm": 0.5726271946361784,
519
+ "learning_rate": 5e-06,
520
+ "loss": 0.4314,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.0822831727205338,
525
+ "grad_norm": 0.596509516956136,
526
+ "learning_rate": 5e-06,
527
+ "loss": 0.4347,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.0971089696071163,
532
+ "grad_norm": 0.5390515390075241,
533
+ "learning_rate": 5e-06,
534
+ "loss": 0.434,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.111934766493699,
539
+ "grad_norm": 0.6129914776744078,
540
+ "learning_rate": 5e-06,
541
+ "loss": 0.4354,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.1267605633802817,
546
+ "grad_norm": 0.5592764678336093,
547
+ "learning_rate": 5e-06,
548
+ "loss": 0.4368,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.1415863602668643,
553
+ "grad_norm": 0.7060047642916599,
554
+ "learning_rate": 5e-06,
555
+ "loss": 0.443,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.156412157153447,
560
+ "grad_norm": 0.5940229109864722,
561
+ "learning_rate": 5e-06,
562
+ "loss": 0.4433,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.1712379540400297,
567
+ "grad_norm": 0.5491622519034774,
568
+ "learning_rate": 5e-06,
569
+ "loss": 0.4304,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.1860637509266123,
574
+ "grad_norm": 0.6079761033641661,
575
+ "learning_rate": 5e-06,
576
+ "loss": 0.438,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.200889547813195,
581
+ "grad_norm": 0.5693457065422755,
582
+ "learning_rate": 5e-06,
583
+ "loss": 0.4403,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.2157153446997775,
588
+ "grad_norm": 0.6505910795677263,
589
+ "learning_rate": 5e-06,
590
+ "loss": 0.4375,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.2305411415863603,
595
+ "grad_norm": 0.6268213064250889,
596
+ "learning_rate": 5e-06,
597
+ "loss": 0.4373,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.2453669384729429,
602
+ "grad_norm": 0.5919676508645508,
603
+ "learning_rate": 5e-06,
604
+ "loss": 0.4306,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.2601927353595257,
609
+ "grad_norm": 0.5398299551449609,
610
+ "learning_rate": 5e-06,
611
+ "loss": 0.4353,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.2750185322461083,
616
+ "grad_norm": 0.5424618353666834,
617
+ "learning_rate": 5e-06,
618
+ "loss": 0.4376,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.2898443291326909,
623
+ "grad_norm": 0.5634395154305121,
624
+ "learning_rate": 5e-06,
625
+ "loss": 0.4361,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.3046701260192735,
630
+ "grad_norm": 0.5785455634852342,
631
+ "learning_rate": 5e-06,
632
+ "loss": 0.4367,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.3194959229058563,
637
+ "grad_norm": 0.620601502244543,
638
+ "learning_rate": 5e-06,
639
+ "loss": 0.4367,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.3343217197924389,
644
+ "grad_norm": 0.530395060539937,
645
+ "learning_rate": 5e-06,
646
+ "loss": 0.4347,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.3491475166790214,
651
+ "grad_norm": 0.5770452107287607,
652
+ "learning_rate": 5e-06,
653
+ "loss": 0.4391,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.3639733135656043,
658
+ "grad_norm": 0.5858170710249173,
659
+ "learning_rate": 5e-06,
660
+ "loss": 0.4343,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 1.3787991104521868,
665
+ "grad_norm": 0.5500756623276715,
666
+ "learning_rate": 5e-06,
667
+ "loss": 0.4346,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 1.3936249073387694,
672
+ "grad_norm": 0.6255449782390206,
673
+ "learning_rate": 5e-06,
674
+ "loss": 0.4389,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 1.408450704225352,
679
+ "grad_norm": 0.5460524509865728,
680
+ "learning_rate": 5e-06,
681
+ "loss": 0.4369,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 1.4232765011119348,
686
+ "grad_norm": 0.5924885663735421,
687
+ "learning_rate": 5e-06,
688
+ "loss": 0.4338,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 1.4381022979985174,
693
+ "grad_norm": 0.5764645405905721,
694
+ "learning_rate": 5e-06,
695
+ "loss": 0.4367,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 1.4529280948851,
700
+ "grad_norm": 0.5850117598054916,
701
+ "learning_rate": 5e-06,
702
+ "loss": 0.4362,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 1.4677538917716828,
707
+ "grad_norm": 0.6081832575580323,
708
+ "learning_rate": 5e-06,
709
+ "loss": 0.4406,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 1.4825796886582654,
714
+ "grad_norm": 0.543363234220218,
715
+ "learning_rate": 5e-06,
716
+ "loss": 0.4351,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 1.497405485544848,
721
+ "grad_norm": 0.5448664659996519,
722
+ "learning_rate": 5e-06,
723
+ "loss": 0.436,
724
+ "step": 1010
725
+ },
726
+ {
727
+ "epoch": 1.5122312824314306,
728
+ "grad_norm": 0.65441524183388,
729
+ "learning_rate": 5e-06,
730
+ "loss": 0.4372,
731
+ "step": 1020
732
+ },
733
+ {
734
+ "epoch": 1.5270570793180134,
735
+ "grad_norm": 0.5280772751509661,
736
+ "learning_rate": 5e-06,
737
+ "loss": 0.4357,
738
+ "step": 1030
739
+ },
740
+ {
741
+ "epoch": 1.541882876204596,
742
+ "grad_norm": 0.5723443909631686,
743
+ "learning_rate": 5e-06,
744
+ "loss": 0.4318,
745
+ "step": 1040
746
+ },
747
+ {
748
+ "epoch": 1.5567086730911788,
749
+ "grad_norm": 0.5085846011938958,
750
+ "learning_rate": 5e-06,
751
+ "loss": 0.4323,
752
+ "step": 1050
753
+ },
754
+ {
755
+ "epoch": 1.5715344699777614,
756
+ "grad_norm": 0.638285906027132,
757
+ "learning_rate": 5e-06,
758
+ "loss": 0.4415,
759
+ "step": 1060
760
+ },
761
+ {
762
+ "epoch": 1.586360266864344,
763
+ "grad_norm": 0.571218693857694,
764
+ "learning_rate": 5e-06,
765
+ "loss": 0.4346,
766
+ "step": 1070
767
+ },
768
+ {
769
+ "epoch": 1.6011860637509265,
770
+ "grad_norm": 0.517292661892654,
771
+ "learning_rate": 5e-06,
772
+ "loss": 0.4382,
773
+ "step": 1080
774
+ },
775
+ {
776
+ "epoch": 1.6160118606375091,
777
+ "grad_norm": 0.5102023179424974,
778
+ "learning_rate": 5e-06,
779
+ "loss": 0.4323,
780
+ "step": 1090
781
+ },
782
+ {
783
+ "epoch": 1.630837657524092,
784
+ "grad_norm": 0.5721112226520383,
785
+ "learning_rate": 5e-06,
786
+ "loss": 0.4378,
787
+ "step": 1100
788
+ },
789
+ {
790
+ "epoch": 1.6456634544106745,
791
+ "grad_norm": 0.5551329559644929,
792
+ "learning_rate": 5e-06,
793
+ "loss": 0.4348,
794
+ "step": 1110
795
+ },
796
+ {
797
+ "epoch": 1.6604892512972573,
798
+ "grad_norm": 0.6119221260699137,
799
+ "learning_rate": 5e-06,
800
+ "loss": 0.4274,
801
+ "step": 1120
802
+ },
803
+ {
804
+ "epoch": 1.67531504818384,
805
+ "grad_norm": 0.5333241050316515,
806
+ "learning_rate": 5e-06,
807
+ "loss": 0.432,
808
+ "step": 1130
809
+ },
810
+ {
811
+ "epoch": 1.6901408450704225,
812
+ "grad_norm": 0.564328179152952,
813
+ "learning_rate": 5e-06,
814
+ "loss": 0.4391,
815
+ "step": 1140
816
+ },
817
+ {
818
+ "epoch": 1.704966641957005,
819
+ "grad_norm": 0.5254085440281446,
820
+ "learning_rate": 5e-06,
821
+ "loss": 0.4359,
822
+ "step": 1150
823
+ },
824
+ {
825
+ "epoch": 1.7197924388435877,
826
+ "grad_norm": 0.5996709499991413,
827
+ "learning_rate": 5e-06,
828
+ "loss": 0.4355,
829
+ "step": 1160
830
+ },
831
+ {
832
+ "epoch": 1.7346182357301705,
833
+ "grad_norm": 0.5493385200435505,
834
+ "learning_rate": 5e-06,
835
+ "loss": 0.432,
836
+ "step": 1170
837
+ },
838
+ {
839
+ "epoch": 1.7494440326167533,
840
+ "grad_norm": 0.5906833738744632,
841
+ "learning_rate": 5e-06,
842
+ "loss": 0.4367,
843
+ "step": 1180
844
+ },
845
+ {
846
+ "epoch": 1.7642698295033359,
847
+ "grad_norm": 0.5341688856567031,
848
+ "learning_rate": 5e-06,
849
+ "loss": 0.4298,
850
+ "step": 1190
851
+ },
852
+ {
853
+ "epoch": 1.7790956263899185,
854
+ "grad_norm": 0.533463029816806,
855
+ "learning_rate": 5e-06,
856
+ "loss": 0.4344,
857
+ "step": 1200
858
+ },
859
+ {
860
+ "epoch": 1.793921423276501,
861
+ "grad_norm": 0.5606747279800302,
862
+ "learning_rate": 5e-06,
863
+ "loss": 0.4362,
864
+ "step": 1210
865
+ },
866
+ {
867
+ "epoch": 1.8087472201630836,
868
+ "grad_norm": 0.5183566067624092,
869
+ "learning_rate": 5e-06,
870
+ "loss": 0.4271,
871
+ "step": 1220
872
+ },
873
+ {
874
+ "epoch": 1.8235730170496665,
875
+ "grad_norm": 0.5326764319923035,
876
+ "learning_rate": 5e-06,
877
+ "loss": 0.4306,
878
+ "step": 1230
879
+ },
880
+ {
881
+ "epoch": 1.838398813936249,
882
+ "grad_norm": 0.5967407273470395,
883
+ "learning_rate": 5e-06,
884
+ "loss": 0.4344,
885
+ "step": 1240
886
+ },
887
+ {
888
+ "epoch": 1.8532246108228319,
889
+ "grad_norm": 0.569200724691502,
890
+ "learning_rate": 5e-06,
891
+ "loss": 0.4353,
892
+ "step": 1250
893
+ },
894
+ {
895
+ "epoch": 1.8680504077094144,
896
+ "grad_norm": 0.5364248806496852,
897
+ "learning_rate": 5e-06,
898
+ "loss": 0.4364,
899
+ "step": 1260
900
+ },
901
+ {
902
+ "epoch": 1.882876204595997,
903
+ "grad_norm": 0.5385402357985632,
904
+ "learning_rate": 5e-06,
905
+ "loss": 0.4379,
906
+ "step": 1270
907
+ },
908
+ {
909
+ "epoch": 1.8977020014825796,
910
+ "grad_norm": 0.5223344068630751,
911
+ "learning_rate": 5e-06,
912
+ "loss": 0.4347,
913
+ "step": 1280
914
+ },
915
+ {
916
+ "epoch": 1.9125277983691622,
917
+ "grad_norm": 0.5617283138858877,
918
+ "learning_rate": 5e-06,
919
+ "loss": 0.4319,
920
+ "step": 1290
921
+ },
922
+ {
923
+ "epoch": 1.927353595255745,
924
+ "grad_norm": 0.5893151487107228,
925
+ "learning_rate": 5e-06,
926
+ "loss": 0.4313,
927
+ "step": 1300
928
+ },
929
+ {
930
+ "epoch": 1.9421793921423276,
931
+ "grad_norm": 0.5366729507399915,
932
+ "learning_rate": 5e-06,
933
+ "loss": 0.4399,
934
+ "step": 1310
935
+ },
936
+ {
937
+ "epoch": 1.9570051890289104,
938
+ "grad_norm": 0.5521187635061144,
939
+ "learning_rate": 5e-06,
940
+ "loss": 0.4346,
941
+ "step": 1320
942
+ },
943
+ {
944
+ "epoch": 1.971830985915493,
945
+ "grad_norm": 0.5736814101430955,
946
+ "learning_rate": 5e-06,
947
+ "loss": 0.4344,
948
+ "step": 1330
949
+ },
950
+ {
951
+ "epoch": 1.9866567828020756,
952
+ "grad_norm": 0.6153323220981107,
953
+ "learning_rate": 5e-06,
954
+ "loss": 0.4288,
955
+ "step": 1340
956
+ },
957
+ {
958
+ "epoch": 2.0,
959
+ "eval_loss": 0.47887247800827026,
960
+ "eval_runtime": 117.4023,
961
+ "eval_samples_per_second": 154.793,
962
+ "eval_steps_per_second": 0.605,
963
+ "step": 1349
964
+ },
965
+ {
966
+ "epoch": 2.001482579688658,
967
+ "grad_norm": 0.8057512126070844,
968
+ "learning_rate": 5e-06,
969
+ "loss": 0.4465,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.0163083765752408,
974
+ "grad_norm": 0.6985686766657238,
975
+ "learning_rate": 5e-06,
976
+ "loss": 0.3758,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.031134173461824,
981
+ "grad_norm": 0.7516592382333935,
982
+ "learning_rate": 5e-06,
983
+ "loss": 0.3739,
984
+ "step": 1370
985
+ },
986
+ {
987
+ "epoch": 2.0459599703484064,
988
+ "grad_norm": 0.6560426338450871,
989
+ "learning_rate": 5e-06,
990
+ "loss": 0.3733,
991
+ "step": 1380
992
+ },
993
+ {
994
+ "epoch": 2.060785767234989,
995
+ "grad_norm": 0.6554981025712345,
996
+ "learning_rate": 5e-06,
997
+ "loss": 0.3738,
998
+ "step": 1390
999
+ },
1000
+ {
1001
+ "epoch": 2.0756115641215716,
1002
+ "grad_norm": 0.5777290379829684,
1003
+ "learning_rate": 5e-06,
1004
+ "loss": 0.373,
1005
+ "step": 1400
1006
+ },
1007
+ {
1008
+ "epoch": 2.090437361008154,
1009
+ "grad_norm": 0.6039864607065941,
1010
+ "learning_rate": 5e-06,
1011
+ "loss": 0.3726,
1012
+ "step": 1410
1013
+ },
1014
+ {
1015
+ "epoch": 2.1052631578947367,
1016
+ "grad_norm": 0.5737027873462299,
1017
+ "learning_rate": 5e-06,
1018
+ "loss": 0.3745,
1019
+ "step": 1420
1020
+ },
1021
+ {
1022
+ "epoch": 2.1200889547813193,
1023
+ "grad_norm": 0.5962503173170325,
1024
+ "learning_rate": 5e-06,
1025
+ "loss": 0.3793,
1026
+ "step": 1430
1027
+ },
1028
+ {
1029
+ "epoch": 2.1349147516679023,
1030
+ "grad_norm": 0.5896368959935617,
1031
+ "learning_rate": 5e-06,
1032
+ "loss": 0.3783,
1033
+ "step": 1440
1034
+ },
1035
+ {
1036
+ "epoch": 2.149740548554485,
1037
+ "grad_norm": 0.5817443097816994,
1038
+ "learning_rate": 5e-06,
1039
+ "loss": 0.3775,
1040
+ "step": 1450
1041
+ },
1042
+ {
1043
+ "epoch": 2.1645663454410675,
1044
+ "grad_norm": 0.5749673449125087,
1045
+ "learning_rate": 5e-06,
1046
+ "loss": 0.378,
1047
+ "step": 1460
1048
+ },
1049
+ {
1050
+ "epoch": 2.17939214232765,
1051
+ "grad_norm": 0.581781908254146,
1052
+ "learning_rate": 5e-06,
1053
+ "loss": 0.3694,
1054
+ "step": 1470
1055
+ },
1056
+ {
1057
+ "epoch": 2.1942179392142327,
1058
+ "grad_norm": 0.5991853455621899,
1059
+ "learning_rate": 5e-06,
1060
+ "loss": 0.3821,
1061
+ "step": 1480
1062
+ },
1063
+ {
1064
+ "epoch": 2.2090437361008153,
1065
+ "grad_norm": 0.5786028266566305,
1066
+ "learning_rate": 5e-06,
1067
+ "loss": 0.3761,
1068
+ "step": 1490
1069
+ },
1070
+ {
1071
+ "epoch": 2.223869532987398,
1072
+ "grad_norm": 0.6524631416486719,
1073
+ "learning_rate": 5e-06,
1074
+ "loss": 0.3733,
1075
+ "step": 1500
1076
+ },
1077
+ {
1078
+ "epoch": 2.238695329873981,
1079
+ "grad_norm": 0.66274701181455,
1080
+ "learning_rate": 5e-06,
1081
+ "loss": 0.3812,
1082
+ "step": 1510
1083
+ },
1084
+ {
1085
+ "epoch": 2.2535211267605635,
1086
+ "grad_norm": 0.5890654308630106,
1087
+ "learning_rate": 5e-06,
1088
+ "loss": 0.3785,
1089
+ "step": 1520
1090
+ },
1091
+ {
1092
+ "epoch": 2.268346923647146,
1093
+ "grad_norm": 0.5995580394178166,
1094
+ "learning_rate": 5e-06,
1095
+ "loss": 0.3766,
1096
+ "step": 1530
1097
+ },
1098
+ {
1099
+ "epoch": 2.2831727205337287,
1100
+ "grad_norm": 0.5621523912385117,
1101
+ "learning_rate": 5e-06,
1102
+ "loss": 0.3819,
1103
+ "step": 1540
1104
+ },
1105
+ {
1106
+ "epoch": 2.2979985174203112,
1107
+ "grad_norm": 0.5631391589331654,
1108
+ "learning_rate": 5e-06,
1109
+ "loss": 0.3831,
1110
+ "step": 1550
1111
+ },
1112
+ {
1113
+ "epoch": 2.312824314306894,
1114
+ "grad_norm": 0.598394877682484,
1115
+ "learning_rate": 5e-06,
1116
+ "loss": 0.3776,
1117
+ "step": 1560
1118
+ },
1119
+ {
1120
+ "epoch": 2.327650111193477,
1121
+ "grad_norm": 0.5751635376845493,
1122
+ "learning_rate": 5e-06,
1123
+ "loss": 0.3743,
1124
+ "step": 1570
1125
+ },
1126
+ {
1127
+ "epoch": 2.3424759080800595,
1128
+ "grad_norm": 0.7431168749670549,
1129
+ "learning_rate": 5e-06,
1130
+ "loss": 0.3806,
1131
+ "step": 1580
1132
+ },
1133
+ {
1134
+ "epoch": 2.357301704966642,
1135
+ "grad_norm": 0.6148778429363163,
1136
+ "learning_rate": 5e-06,
1137
+ "loss": 0.3792,
1138
+ "step": 1590
1139
+ },
1140
+ {
1141
+ "epoch": 2.3721275018532246,
1142
+ "grad_norm": 0.5904751763294604,
1143
+ "learning_rate": 5e-06,
1144
+ "loss": 0.3779,
1145
+ "step": 1600
1146
+ },
1147
+ {
1148
+ "epoch": 2.386953298739807,
1149
+ "grad_norm": 0.6160494878206139,
1150
+ "learning_rate": 5e-06,
1151
+ "loss": 0.3795,
1152
+ "step": 1610
1153
+ },
1154
+ {
1155
+ "epoch": 2.40177909562639,
1156
+ "grad_norm": 0.6601509703827891,
1157
+ "learning_rate": 5e-06,
1158
+ "loss": 0.381,
1159
+ "step": 1620
1160
+ },
1161
+ {
1162
+ "epoch": 2.4166048925129724,
1163
+ "grad_norm": 0.5557483892389672,
1164
+ "learning_rate": 5e-06,
1165
+ "loss": 0.38,
1166
+ "step": 1630
1167
+ },
1168
+ {
1169
+ "epoch": 2.431430689399555,
1170
+ "grad_norm": 0.5514157650195483,
1171
+ "learning_rate": 5e-06,
1172
+ "loss": 0.3785,
1173
+ "step": 1640
1174
+ },
1175
+ {
1176
+ "epoch": 2.446256486286138,
1177
+ "grad_norm": 0.5896166088948557,
1178
+ "learning_rate": 5e-06,
1179
+ "loss": 0.3785,
1180
+ "step": 1650
1181
+ },
1182
+ {
1183
+ "epoch": 2.4610822831727206,
1184
+ "grad_norm": 0.6187824694109818,
1185
+ "learning_rate": 5e-06,
1186
+ "loss": 0.3866,
1187
+ "step": 1660
1188
+ },
1189
+ {
1190
+ "epoch": 2.475908080059303,
1191
+ "grad_norm": 0.6196885650354601,
1192
+ "learning_rate": 5e-06,
1193
+ "loss": 0.3773,
1194
+ "step": 1670
1195
+ },
1196
+ {
1197
+ "epoch": 2.4907338769458858,
1198
+ "grad_norm": 0.6497541102453935,
1199
+ "learning_rate": 5e-06,
1200
+ "loss": 0.3792,
1201
+ "step": 1680
1202
+ },
1203
+ {
1204
+ "epoch": 2.5055596738324684,
1205
+ "grad_norm": 0.6221830439300937,
1206
+ "learning_rate": 5e-06,
1207
+ "loss": 0.3814,
1208
+ "step": 1690
1209
+ },
1210
+ {
1211
+ "epoch": 2.5203854707190514,
1212
+ "grad_norm": 0.5575748670805571,
1213
+ "learning_rate": 5e-06,
1214
+ "loss": 0.3788,
1215
+ "step": 1700
1216
+ },
1217
+ {
1218
+ "epoch": 2.535211267605634,
1219
+ "grad_norm": 0.5820255267213036,
1220
+ "learning_rate": 5e-06,
1221
+ "loss": 0.3797,
1222
+ "step": 1710
1223
+ },
1224
+ {
1225
+ "epoch": 2.5500370644922166,
1226
+ "grad_norm": 0.5778840920723647,
1227
+ "learning_rate": 5e-06,
1228
+ "loss": 0.3836,
1229
+ "step": 1720
1230
+ },
1231
+ {
1232
+ "epoch": 2.564862861378799,
1233
+ "grad_norm": 0.6369372874220104,
1234
+ "learning_rate": 5e-06,
1235
+ "loss": 0.3822,
1236
+ "step": 1730
1237
+ },
1238
+ {
1239
+ "epoch": 2.5796886582653817,
1240
+ "grad_norm": 0.5836272270823646,
1241
+ "learning_rate": 5e-06,
1242
+ "loss": 0.3825,
1243
+ "step": 1740
1244
+ },
1245
+ {
1246
+ "epoch": 2.5945144551519643,
1247
+ "grad_norm": 0.5893118830611698,
1248
+ "learning_rate": 5e-06,
1249
+ "loss": 0.382,
1250
+ "step": 1750
1251
+ },
1252
+ {
1253
+ "epoch": 2.609340252038547,
1254
+ "grad_norm": 0.691740548026418,
1255
+ "learning_rate": 5e-06,
1256
+ "loss": 0.3828,
1257
+ "step": 1760
1258
+ },
1259
+ {
1260
+ "epoch": 2.6241660489251295,
1261
+ "grad_norm": 0.6016891230542475,
1262
+ "learning_rate": 5e-06,
1263
+ "loss": 0.3841,
1264
+ "step": 1770
1265
+ },
1266
+ {
1267
+ "epoch": 2.6389918458117125,
1268
+ "grad_norm": 0.5709726000324739,
1269
+ "learning_rate": 5e-06,
1270
+ "loss": 0.38,
1271
+ "step": 1780
1272
+ },
1273
+ {
1274
+ "epoch": 2.653817642698295,
1275
+ "grad_norm": 0.5707418370568915,
1276
+ "learning_rate": 5e-06,
1277
+ "loss": 0.3819,
1278
+ "step": 1790
1279
+ },
1280
+ {
1281
+ "epoch": 2.6686434395848777,
1282
+ "grad_norm": 0.6121781418312778,
1283
+ "learning_rate": 5e-06,
1284
+ "loss": 0.3775,
1285
+ "step": 1800
1286
+ },
1287
+ {
1288
+ "epoch": 2.6834692364714603,
1289
+ "grad_norm": 0.5845205444282813,
1290
+ "learning_rate": 5e-06,
1291
+ "loss": 0.3794,
1292
+ "step": 1810
1293
+ },
1294
+ {
1295
+ "epoch": 2.698295033358043,
1296
+ "grad_norm": 0.6090204118467554,
1297
+ "learning_rate": 5e-06,
1298
+ "loss": 0.3749,
1299
+ "step": 1820
1300
+ },
1301
+ {
1302
+ "epoch": 2.713120830244626,
1303
+ "grad_norm": 0.6311725348745423,
1304
+ "learning_rate": 5e-06,
1305
+ "loss": 0.3875,
1306
+ "step": 1830
1307
+ },
1308
+ {
1309
+ "epoch": 2.7279466271312085,
1310
+ "grad_norm": 0.5855235496792751,
1311
+ "learning_rate": 5e-06,
1312
+ "loss": 0.3798,
1313
+ "step": 1840
1314
+ },
1315
+ {
1316
+ "epoch": 2.742772424017791,
1317
+ "grad_norm": 0.6360580241341309,
1318
+ "learning_rate": 5e-06,
1319
+ "loss": 0.3795,
1320
+ "step": 1850
1321
+ },
1322
+ {
1323
+ "epoch": 2.7575982209043737,
1324
+ "grad_norm": 0.6949332357026632,
1325
+ "learning_rate": 5e-06,
1326
+ "loss": 0.3833,
1327
+ "step": 1860
1328
+ },
1329
+ {
1330
+ "epoch": 2.7724240177909563,
1331
+ "grad_norm": 0.5661995725449918,
1332
+ "learning_rate": 5e-06,
1333
+ "loss": 0.3815,
1334
+ "step": 1870
1335
+ },
1336
+ {
1337
+ "epoch": 2.787249814677539,
1338
+ "grad_norm": 0.6181579391717933,
1339
+ "learning_rate": 5e-06,
1340
+ "loss": 0.3814,
1341
+ "step": 1880
1342
+ },
1343
+ {
1344
+ "epoch": 2.8020756115641214,
1345
+ "grad_norm": 0.621591189180585,
1346
+ "learning_rate": 5e-06,
1347
+ "loss": 0.3839,
1348
+ "step": 1890
1349
+ },
1350
+ {
1351
+ "epoch": 2.816901408450704,
1352
+ "grad_norm": 0.6102808235648141,
1353
+ "learning_rate": 5e-06,
1354
+ "loss": 0.386,
1355
+ "step": 1900
1356
+ },
1357
+ {
1358
+ "epoch": 2.8317272053372866,
1359
+ "grad_norm": 0.5570401466362744,
1360
+ "learning_rate": 5e-06,
1361
+ "loss": 0.3829,
1362
+ "step": 1910
1363
+ },
1364
+ {
1365
+ "epoch": 2.8465530022238696,
1366
+ "grad_norm": 0.605864801280795,
1367
+ "learning_rate": 5e-06,
1368
+ "loss": 0.3791,
1369
+ "step": 1920
1370
+ },
1371
+ {
1372
+ "epoch": 2.8613787991104522,
1373
+ "grad_norm": 0.5737361891170868,
1374
+ "learning_rate": 5e-06,
1375
+ "loss": 0.3831,
1376
+ "step": 1930
1377
+ },
1378
+ {
1379
+ "epoch": 2.876204595997035,
1380
+ "grad_norm": 0.5867020788912005,
1381
+ "learning_rate": 5e-06,
1382
+ "loss": 0.38,
1383
+ "step": 1940
1384
+ },
1385
+ {
1386
+ "epoch": 2.8910303928836174,
1387
+ "grad_norm": 0.557534237372008,
1388
+ "learning_rate": 5e-06,
1389
+ "loss": 0.3825,
1390
+ "step": 1950
1391
+ },
1392
+ {
1393
+ "epoch": 2.9058561897702,
1394
+ "grad_norm": 0.5964701402385094,
1395
+ "learning_rate": 5e-06,
1396
+ "loss": 0.3852,
1397
+ "step": 1960
1398
+ },
1399
+ {
1400
+ "epoch": 2.920681986656783,
1401
+ "grad_norm": 0.600588952238815,
1402
+ "learning_rate": 5e-06,
1403
+ "loss": 0.3876,
1404
+ "step": 1970
1405
+ },
1406
+ {
1407
+ "epoch": 2.9355077835433656,
1408
+ "grad_norm": 0.5765877577022089,
1409
+ "learning_rate": 5e-06,
1410
+ "loss": 0.3851,
1411
+ "step": 1980
1412
+ },
1413
+ {
1414
+ "epoch": 2.950333580429948,
1415
+ "grad_norm": 0.6187803453792526,
1416
+ "learning_rate": 5e-06,
1417
+ "loss": 0.3818,
1418
+ "step": 1990
1419
+ },
1420
+ {
1421
+ "epoch": 2.965159377316531,
1422
+ "grad_norm": 0.5518073320285379,
1423
+ "learning_rate": 5e-06,
1424
+ "loss": 0.3834,
1425
+ "step": 2000
1426
+ },
1427
+ {
1428
+ "epoch": 2.9799851742031134,
1429
+ "grad_norm": 0.5343617840090896,
1430
+ "learning_rate": 5e-06,
1431
+ "loss": 0.3772,
1432
+ "step": 2010
1433
+ },
1434
+ {
1435
+ "epoch": 2.994810971089696,
1436
+ "grad_norm": 0.5629835017462416,
1437
+ "learning_rate": 5e-06,
1438
+ "loss": 0.382,
1439
+ "step": 2020
1440
+ },
1441
+ {
1442
+ "epoch": 2.9977761304670127,
1443
+ "eval_loss": 0.4834764897823334,
1444
+ "eval_runtime": 117.0978,
1445
+ "eval_samples_per_second": 155.195,
1446
+ "eval_steps_per_second": 0.606,
1447
+ "step": 2022
1448
+ },
1449
+ {
1450
+ "epoch": 2.9977761304670127,
1451
+ "step": 2022,
1452
+ "total_flos": 3386087791656960.0,
1453
+ "train_loss": 0.4438282892800698,
1454
+ "train_runtime": 17391.1323,
1455
+ "train_samples_per_second": 59.561,
1456
+ "train_steps_per_second": 0.116
1457
+ }
1458
+ ],
1459
+ "logging_steps": 10,
1460
+ "max_steps": 2022,
1461
+ "num_input_tokens_seen": 0,
1462
+ "num_train_epochs": 3,
1463
+ "save_steps": 500,
1464
+ "stateful_callbacks": {
1465
+ "TrainerControl": {
1466
+ "args": {
1467
+ "should_epoch_stop": false,
1468
+ "should_evaluate": false,
1469
+ "should_log": false,
1470
+ "should_save": true,
1471
+ "should_training_stop": true
1472
+ },
1473
+ "attributes": {}
1474
+ }
1475
+ },
1476
+ "total_flos": 3386087791656960.0,
1477
+ "train_batch_size": 8,
1478
+ "trial_name": null,
1479
+ "trial_params": null
1480
+ }
training_eval_loss.png ADDED
training_loss.png ADDED