OpenLeecher commited on
Commit
2104fff
·
verified ·
1 Parent(s): bcc4f8b

End of training

Browse files
Files changed (5) hide show
  1. README.md +3 -2
  2. all_results.json +12 -0
  3. eval_results.json +7 -0
  4. train_results.json +8 -0
  5. trainer_state.json +1785 -0
README.md CHANGED
@@ -4,6 +4,7 @@ license: llama3.1
4
  base_model: meta-llama/Llama-3.1-8B
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: llama_8b_lima_42
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # llama_8b_lima_42
17
 
18
- This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.9002
21
 
22
  ## Model description
23
 
 
4
  base_model: meta-llama/Llama-3.1-8B
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: llama_8b_lima_42
 
16
 
17
  # llama_8b_lima_42
18
 
19
+ This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the open_webui_dataset dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.9014
22
 
23
  ## Model description
24
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9998570816064027,
3
+ "eval_loss": 0.9013698101043701,
4
+ "eval_runtime": 19.0091,
5
+ "eval_samples_per_second": 10.521,
6
+ "eval_steps_per_second": 2.63,
7
+ "total_flos": 1.7681949461682586e+17,
8
+ "train_loss": 0.944941889564946,
9
+ "train_runtime": 15099.9882,
10
+ "train_samples_per_second": 2.78,
11
+ "train_steps_per_second": 0.077
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9998570816064027,
3
+ "eval_loss": 0.9013698101043701,
4
+ "eval_runtime": 19.0091,
5
+ "eval_samples_per_second": 10.521,
6
+ "eval_steps_per_second": 2.63
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9998570816064027,
3
+ "total_flos": 1.7681949461682586e+17,
4
+ "train_loss": 0.944941889564946,
5
+ "train_runtime": 15099.9882,
6
+ "train_samples_per_second": 2.78,
7
+ "train_steps_per_second": 0.077
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1785 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9998570816064027,
5
+ "eval_steps": 80,
6
+ "global_step": 1166,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.004287551807917679,
13
+ "grad_norm": 49.0459476401418,
14
+ "learning_rate": 5.000000000000001e-07,
15
+ "loss": 1.2482,
16
+ "step": 5
17
+ },
18
+ {
19
+ "epoch": 0.008575103615835357,
20
+ "grad_norm": 46.49636895863856,
21
+ "learning_rate": 1.0000000000000002e-06,
22
+ "loss": 1.2111,
23
+ "step": 10
24
+ },
25
+ {
26
+ "epoch": 0.012862655423753037,
27
+ "grad_norm": 75.02893655779658,
28
+ "learning_rate": 1.5e-06,
29
+ "loss": 1.2375,
30
+ "step": 15
31
+ },
32
+ {
33
+ "epoch": 0.017150207231670715,
34
+ "grad_norm": 3.8741623300934016,
35
+ "learning_rate": 2.0000000000000003e-06,
36
+ "loss": 1.0833,
37
+ "step": 20
38
+ },
39
+ {
40
+ "epoch": 0.021437759039588396,
41
+ "grad_norm": 8.80211103072482,
42
+ "learning_rate": 2.5e-06,
43
+ "loss": 1.0052,
44
+ "step": 25
45
+ },
46
+ {
47
+ "epoch": 0.025725310847506073,
48
+ "grad_norm": 11.672065444786128,
49
+ "learning_rate": 3e-06,
50
+ "loss": 1.0283,
51
+ "step": 30
52
+ },
53
+ {
54
+ "epoch": 0.030012862655423755,
55
+ "grad_norm": 4.987083560214949,
56
+ "learning_rate": 3.5e-06,
57
+ "loss": 1.0801,
58
+ "step": 35
59
+ },
60
+ {
61
+ "epoch": 0.03430041446334143,
62
+ "grad_norm": 2.966299005953653,
63
+ "learning_rate": 4.000000000000001e-06,
64
+ "loss": 1.0753,
65
+ "step": 40
66
+ },
67
+ {
68
+ "epoch": 0.038587966271259114,
69
+ "grad_norm": 3.0065164197825074,
70
+ "learning_rate": 4.5e-06,
71
+ "loss": 0.9409,
72
+ "step": 45
73
+ },
74
+ {
75
+ "epoch": 0.04287551807917679,
76
+ "grad_norm": 3.381394216826962,
77
+ "learning_rate": 5e-06,
78
+ "loss": 1.0198,
79
+ "step": 50
80
+ },
81
+ {
82
+ "epoch": 0.04716306988709447,
83
+ "grad_norm": 3.6309559490350654,
84
+ "learning_rate": 4.926711109482401e-06,
85
+ "loss": 1.0699,
86
+ "step": 55
87
+ },
88
+ {
89
+ "epoch": 0.05145062169501215,
90
+ "grad_norm": 4.134626791396976,
91
+ "learning_rate": 4.854242179361151e-06,
92
+ "loss": 1.0268,
93
+ "step": 60
94
+ },
95
+ {
96
+ "epoch": 0.055738173502929825,
97
+ "grad_norm": 3.3445998120937954,
98
+ "learning_rate": 4.782587680591894e-06,
99
+ "loss": 1.2315,
100
+ "step": 65
101
+ },
102
+ {
103
+ "epoch": 0.06002572531084751,
104
+ "grad_norm": 2.4730316039429288,
105
+ "learning_rate": 4.711742096614044e-06,
106
+ "loss": 0.9914,
107
+ "step": 70
108
+ },
109
+ {
110
+ "epoch": 0.06431327711876518,
111
+ "grad_norm": 3.063463397168402,
112
+ "learning_rate": 4.641699923379107e-06,
113
+ "loss": 0.9354,
114
+ "step": 75
115
+ },
116
+ {
117
+ "epoch": 0.06860082892668286,
118
+ "grad_norm": 3.72217017018073,
119
+ "learning_rate": 4.5724556693791996e-06,
120
+ "loss": 1.0356,
121
+ "step": 80
122
+ },
123
+ {
124
+ "epoch": 0.06860082892668286,
125
+ "eval_loss": 0.9710695743560791,
126
+ "eval_runtime": 20.9077,
127
+ "eval_samples_per_second": 9.566,
128
+ "eval_steps_per_second": 2.391,
129
+ "step": 80
130
+ },
131
+ {
132
+ "epoch": 0.07288838073460055,
133
+ "grad_norm": 2.8296964090488466,
134
+ "learning_rate": 4.504003855675734e-06,
135
+ "loss": 1.0218,
136
+ "step": 85
137
+ },
138
+ {
139
+ "epoch": 0.07717593254251823,
140
+ "grad_norm": 3.9492533196858313,
141
+ "learning_rate": 4.436339015928335e-06,
142
+ "loss": 0.9059,
143
+ "step": 90
144
+ },
145
+ {
146
+ "epoch": 0.0814634843504359,
147
+ "grad_norm": 2.945729589644999,
148
+ "learning_rate": 4.369455696423936e-06,
149
+ "loss": 0.9862,
150
+ "step": 95
151
+ },
152
+ {
153
+ "epoch": 0.08575103615835358,
154
+ "grad_norm": 2.8934728265120553,
155
+ "learning_rate": 4.303348456106082e-06,
156
+ "loss": 0.9869,
157
+ "step": 100
158
+ },
159
+ {
160
+ "epoch": 0.09003858796627126,
161
+ "grad_norm": 3.6370231743108636,
162
+ "learning_rate": 4.238011866604447e-06,
163
+ "loss": 1.0137,
164
+ "step": 105
165
+ },
166
+ {
167
+ "epoch": 0.09432613977418894,
168
+ "grad_norm": 2.8095030003011976,
169
+ "learning_rate": 4.173440512264544e-06,
170
+ "loss": 0.9834,
171
+ "step": 110
172
+ },
173
+ {
174
+ "epoch": 0.09861369158210662,
175
+ "grad_norm": 2.5605385368574205,
176
+ "learning_rate": 4.109628990177651e-06,
177
+ "loss": 0.9828,
178
+ "step": 115
179
+ },
180
+ {
181
+ "epoch": 0.1029012433900243,
182
+ "grad_norm": 3.328262187145733,
183
+ "learning_rate": 4.04657191021096e-06,
184
+ "loss": 0.9892,
185
+ "step": 120
186
+ },
187
+ {
188
+ "epoch": 0.10718879519794197,
189
+ "grad_norm": 3.4906689890189835,
190
+ "learning_rate": 3.984263895037921e-06,
191
+ "loss": 0.9903,
192
+ "step": 125
193
+ },
194
+ {
195
+ "epoch": 0.11147634700585965,
196
+ "grad_norm": 2.845690441710927,
197
+ "learning_rate": 3.9226995801688165e-06,
198
+ "loss": 1.1259,
199
+ "step": 130
200
+ },
201
+ {
202
+ "epoch": 0.11576389881377733,
203
+ "grad_norm": 2.7267526391731334,
204
+ "learning_rate": 3.8618736139815605e-06,
205
+ "loss": 0.9734,
206
+ "step": 135
207
+ },
208
+ {
209
+ "epoch": 0.12005145062169502,
210
+ "grad_norm": 2.062870391280079,
211
+ "learning_rate": 3.8017806577526982e-06,
212
+ "loss": 1.0515,
213
+ "step": 140
214
+ },
215
+ {
216
+ "epoch": 0.1243390024296127,
217
+ "grad_norm": 2.814034294378353,
218
+ "learning_rate": 3.7424153856886596e-06,
219
+ "loss": 0.8449,
220
+ "step": 145
221
+ },
222
+ {
223
+ "epoch": 0.12862655423753036,
224
+ "grad_norm": 3.0711652275263357,
225
+ "learning_rate": 3.6837724849572175e-06,
226
+ "loss": 0.8388,
227
+ "step": 150
228
+ },
229
+ {
230
+ "epoch": 0.13291410604544804,
231
+ "grad_norm": 3.437400624778036,
232
+ "learning_rate": 3.6258466557191907e-06,
233
+ "loss": 1.1761,
234
+ "step": 155
235
+ },
236
+ {
237
+ "epoch": 0.13720165785336572,
238
+ "grad_norm": 3.081997188340036,
239
+ "learning_rate": 3.5686326111603775e-06,
240
+ "loss": 1.0348,
241
+ "step": 160
242
+ },
243
+ {
244
+ "epoch": 0.13720165785336572,
245
+ "eval_loss": 0.9355081915855408,
246
+ "eval_runtime": 19.1453,
247
+ "eval_samples_per_second": 10.446,
248
+ "eval_steps_per_second": 2.612,
249
+ "step": 160
250
+ },
251
+ {
252
+ "epoch": 0.1414892096612834,
253
+ "grad_norm": 2.8114117836276513,
254
+ "learning_rate": 3.512125077523717e-06,
255
+ "loss": 1.0048,
256
+ "step": 165
257
+ },
258
+ {
259
+ "epoch": 0.1457767614692011,
260
+ "grad_norm": 2.707619981442126,
261
+ "learning_rate": 3.456318794141709e-06,
262
+ "loss": 0.8126,
263
+ "step": 170
264
+ },
265
+ {
266
+ "epoch": 0.15006431327711878,
267
+ "grad_norm": 2.6357116905007856,
268
+ "learning_rate": 3.4012085134690555e-06,
269
+ "loss": 0.8684,
270
+ "step": 175
271
+ },
272
+ {
273
+ "epoch": 0.15435186508503645,
274
+ "grad_norm": 2.902285405452677,
275
+ "learning_rate": 3.346789001115556e-06,
276
+ "loss": 1.023,
277
+ "step": 180
278
+ },
279
+ {
280
+ "epoch": 0.15863941689295413,
281
+ "grad_norm": 3.1470604950987546,
282
+ "learning_rate": 3.293055035879266e-06,
283
+ "loss": 0.979,
284
+ "step": 185
285
+ },
286
+ {
287
+ "epoch": 0.1629269687008718,
288
+ "grad_norm": 2.429084645315808,
289
+ "learning_rate": 3.2400014097798766e-06,
290
+ "loss": 0.9414,
291
+ "step": 190
292
+ },
293
+ {
294
+ "epoch": 0.1672145205087895,
295
+ "grad_norm": 2.6607376091673283,
296
+ "learning_rate": 3.187622928092377e-06,
297
+ "loss": 1.0719,
298
+ "step": 195
299
+ },
300
+ {
301
+ "epoch": 0.17150207231670717,
302
+ "grad_norm": 3.064466109382867,
303
+ "learning_rate": 3.1359144093809653e-06,
304
+ "loss": 0.9007,
305
+ "step": 200
306
+ },
307
+ {
308
+ "epoch": 0.17578962412462484,
309
+ "grad_norm": 3.3202976410761815,
310
+ "learning_rate": 3.084870685533213e-06,
311
+ "loss": 1.0225,
312
+ "step": 205
313
+ },
314
+ {
315
+ "epoch": 0.18007717593254252,
316
+ "grad_norm": 9.376729410524437,
317
+ "learning_rate": 3.034486601794506e-06,
318
+ "loss": 0.8927,
319
+ "step": 210
320
+ },
321
+ {
322
+ "epoch": 0.1843647277404602,
323
+ "grad_norm": 4.24264134885146,
324
+ "learning_rate": 2.984757016802754e-06,
325
+ "loss": 0.8904,
326
+ "step": 215
327
+ },
328
+ {
329
+ "epoch": 0.18865227954837788,
330
+ "grad_norm": 3.401996163001482,
331
+ "learning_rate": 2.935676802623359e-06,
332
+ "loss": 0.89,
333
+ "step": 220
334
+ },
335
+ {
336
+ "epoch": 0.19293983135629555,
337
+ "grad_norm": 2.811911382062161,
338
+ "learning_rate": 2.887240844784472e-06,
339
+ "loss": 1.0528,
340
+ "step": 225
341
+ },
342
+ {
343
+ "epoch": 0.19722738316421323,
344
+ "grad_norm": 6.117694360086105,
345
+ "learning_rate": 2.8394440423125295e-06,
346
+ "loss": 0.957,
347
+ "step": 230
348
+ },
349
+ {
350
+ "epoch": 0.2015149349721309,
351
+ "grad_norm": 2.5418193456876024,
352
+ "learning_rate": 2.7922813077680564e-06,
353
+ "loss": 0.8757,
354
+ "step": 235
355
+ },
356
+ {
357
+ "epoch": 0.2058024867800486,
358
+ "grad_norm": 2.980094551138022,
359
+ "learning_rate": 2.7457475672817817e-06,
360
+ "loss": 0.7212,
361
+ "step": 240
362
+ },
363
+ {
364
+ "epoch": 0.2058024867800486,
365
+ "eval_loss": 0.9225141406059265,
366
+ "eval_runtime": 19.142,
367
+ "eval_samples_per_second": 10.448,
368
+ "eval_steps_per_second": 2.612,
369
+ "step": 240
370
+ },
371
+ {
372
+ "epoch": 0.21009003858796627,
373
+ "grad_norm": 2.8229472248870113,
374
+ "learning_rate": 2.6998377605910153e-06,
375
+ "loss": 0.7847,
376
+ "step": 245
377
+ },
378
+ {
379
+ "epoch": 0.21437759039588394,
380
+ "grad_norm": 3.313576806878507,
381
+ "learning_rate": 2.6545468410763466e-06,
382
+ "loss": 0.7885,
383
+ "step": 250
384
+ },
385
+ {
386
+ "epoch": 0.21866514220380162,
387
+ "grad_norm": 2.7546057206480863,
388
+ "learning_rate": 2.60986977579862e-06,
389
+ "loss": 0.9853,
390
+ "step": 255
391
+ },
392
+ {
393
+ "epoch": 0.2229526940117193,
394
+ "grad_norm": 2.62325989569962,
395
+ "learning_rate": 2.565801545536224e-06,
396
+ "loss": 0.8693,
397
+ "step": 260
398
+ },
399
+ {
400
+ "epoch": 0.22724024581963698,
401
+ "grad_norm": 2.494330977302947,
402
+ "learning_rate": 2.52233714482269e-06,
403
+ "loss": 0.8483,
404
+ "step": 265
405
+ },
406
+ {
407
+ "epoch": 0.23152779762755465,
408
+ "grad_norm": 3.0508796153780815,
409
+ "learning_rate": 2.479471581984588e-06,
410
+ "loss": 0.9198,
411
+ "step": 270
412
+ },
413
+ {
414
+ "epoch": 0.23581534943547233,
415
+ "grad_norm": 2.8596047579477077,
416
+ "learning_rate": 2.437199879179748e-06,
417
+ "loss": 0.8111,
418
+ "step": 275
419
+ },
420
+ {
421
+ "epoch": 0.24010290124339004,
422
+ "grad_norm": 2.9634105907172676,
423
+ "learning_rate": 2.395517072435804e-06,
424
+ "loss": 0.9249,
425
+ "step": 280
426
+ },
427
+ {
428
+ "epoch": 0.24439045305130772,
429
+ "grad_norm": 2.876075717907315,
430
+ "learning_rate": 2.35441821168905e-06,
431
+ "loss": 0.8466,
432
+ "step": 285
433
+ },
434
+ {
435
+ "epoch": 0.2486780048592254,
436
+ "grad_norm": 2.707429407550077,
437
+ "learning_rate": 2.313898360823632e-06,
438
+ "loss": 0.8335,
439
+ "step": 290
440
+ },
441
+ {
442
+ "epoch": 0.25296555666714304,
443
+ "grad_norm": 2.424659422914543,
444
+ "learning_rate": 2.2739525977110787e-06,
445
+ "loss": 0.9591,
446
+ "step": 295
447
+ },
448
+ {
449
+ "epoch": 0.2572531084750607,
450
+ "grad_norm": 2.3503862613323054,
451
+ "learning_rate": 2.234576014250154e-06,
452
+ "loss": 0.8867,
453
+ "step": 300
454
+ },
455
+ {
456
+ "epoch": 0.2615406602829784,
457
+ "grad_norm": 2.487930933633346,
458
+ "learning_rate": 2.195763716407068e-06,
459
+ "loss": 0.9301,
460
+ "step": 305
461
+ },
462
+ {
463
+ "epoch": 0.2658282120908961,
464
+ "grad_norm": 2.9951853980801206,
465
+ "learning_rate": 2.15751082425603e-06,
466
+ "loss": 0.8933,
467
+ "step": 310
468
+ },
469
+ {
470
+ "epoch": 0.27011576389881375,
471
+ "grad_norm": 2.6479548343780044,
472
+ "learning_rate": 2.119812472020151e-06,
473
+ "loss": 1.1902,
474
+ "step": 315
475
+ },
476
+ {
477
+ "epoch": 0.27440331570673143,
478
+ "grad_norm": 3.031373376327646,
479
+ "learning_rate": 2.082663808112706e-06,
480
+ "loss": 0.8077,
481
+ "step": 320
482
+ },
483
+ {
484
+ "epoch": 0.27440331570673143,
485
+ "eval_loss": 0.9141628742218018,
486
+ "eval_runtime": 19.1329,
487
+ "eval_samples_per_second": 10.453,
488
+ "eval_steps_per_second": 2.613,
489
+ "step": 320
490
+ },
491
+ {
492
+ "epoch": 0.2786908675146491,
493
+ "grad_norm": 3.8925204318472777,
494
+ "learning_rate": 2.0460599951787676e-06,
495
+ "loss": 1.003,
496
+ "step": 325
497
+ },
498
+ {
499
+ "epoch": 0.2829784193225668,
500
+ "grad_norm": 2.8374998009671213,
501
+ "learning_rate": 2.0099962101371912e-06,
502
+ "loss": 0.9517,
503
+ "step": 330
504
+ },
505
+ {
506
+ "epoch": 0.2872659711304845,
507
+ "grad_norm": 2.7039222330267725,
508
+ "learning_rate": 1.9744676442229893e-06,
509
+ "loss": 0.8129,
510
+ "step": 335
511
+ },
512
+ {
513
+ "epoch": 0.2915535229384022,
514
+ "grad_norm": 3.5945398321446014,
515
+ "learning_rate": 1.9394695030300814e-06,
516
+ "loss": 0.9616,
517
+ "step": 340
518
+ },
519
+ {
520
+ "epoch": 0.2958410747463199,
521
+ "grad_norm": 4.022714585976749,
522
+ "learning_rate": 1.904997006554424e-06,
523
+ "loss": 0.9347,
524
+ "step": 345
525
+ },
526
+ {
527
+ "epoch": 0.30012862655423755,
528
+ "grad_norm": 2.449025495886818,
529
+ "learning_rate": 1.8710453892375372e-06,
530
+ "loss": 0.9365,
531
+ "step": 350
532
+ },
533
+ {
534
+ "epoch": 0.30441617836215523,
535
+ "grad_norm": 1.97102566822208,
536
+ "learning_rate": 1.837609900010423e-06,
537
+ "loss": 1.0678,
538
+ "step": 355
539
+ },
540
+ {
541
+ "epoch": 0.3087037301700729,
542
+ "grad_norm": 2.9794081240205292,
543
+ "learning_rate": 1.8046858023378982e-06,
544
+ "loss": 0.8233,
545
+ "step": 360
546
+ },
547
+ {
548
+ "epoch": 0.3129912819779906,
549
+ "grad_norm": 2.623718879014175,
550
+ "learning_rate": 1.7722683742633203e-06,
551
+ "loss": 1.089,
552
+ "step": 365
553
+ },
554
+ {
555
+ "epoch": 0.31727883378590827,
556
+ "grad_norm": 3.1393160530750808,
557
+ "learning_rate": 1.7403529084537394e-06,
558
+ "loss": 0.8982,
559
+ "step": 370
560
+ },
561
+ {
562
+ "epoch": 0.32156638559382594,
563
+ "grad_norm": 3.5048967956402506,
564
+ "learning_rate": 1.708934712245474e-06,
565
+ "loss": 0.8602,
566
+ "step": 375
567
+ },
568
+ {
569
+ "epoch": 0.3258539374017436,
570
+ "grad_norm": 2.731824579589462,
571
+ "learning_rate": 1.6780091076901074e-06,
572
+ "loss": 0.9206,
573
+ "step": 380
574
+ },
575
+ {
576
+ "epoch": 0.3301414892096613,
577
+ "grad_norm": 2.6508962987997164,
578
+ "learning_rate": 1.6475714316009228e-06,
579
+ "loss": 0.9,
580
+ "step": 385
581
+ },
582
+ {
583
+ "epoch": 0.334429041017579,
584
+ "grad_norm": 3.3563303629070194,
585
+ "learning_rate": 1.6176170355997885e-06,
586
+ "loss": 0.9077,
587
+ "step": 390
588
+ },
589
+ {
590
+ "epoch": 0.33871659282549665,
591
+ "grad_norm": 2.510811889533464,
592
+ "learning_rate": 1.5881412861644783e-06,
593
+ "loss": 0.8796,
594
+ "step": 395
595
+ },
596
+ {
597
+ "epoch": 0.34300414463341433,
598
+ "grad_norm": 2.7025767408039423,
599
+ "learning_rate": 1.559139564676459e-06,
600
+ "loss": 0.8442,
601
+ "step": 400
602
+ },
603
+ {
604
+ "epoch": 0.34300414463341433,
605
+ "eval_loss": 0.9068123698234558,
606
+ "eval_runtime": 19.1503,
607
+ "eval_samples_per_second": 10.444,
608
+ "eval_steps_per_second": 2.611,
609
+ "step": 400
610
+ },
611
+ {
612
+ "epoch": 0.347291696441332,
613
+ "grad_norm": 2.3723461526691687,
614
+ "learning_rate": 1.530607267469142e-06,
615
+ "loss": 0.8776,
616
+ "step": 405
617
+ },
618
+ {
619
+ "epoch": 0.3515792482492497,
620
+ "grad_norm": 2.326426360163379,
621
+ "learning_rate": 1.502539805876598e-06,
622
+ "loss": 0.8368,
623
+ "step": 410
624
+ },
625
+ {
626
+ "epoch": 0.35586680005716737,
627
+ "grad_norm": 2.609797589938526,
628
+ "learning_rate": 1.4749326062827624e-06,
629
+ "loss": 0.8314,
630
+ "step": 415
631
+ },
632
+ {
633
+ "epoch": 0.36015435186508504,
634
+ "grad_norm": 3.018034878541378,
635
+ "learning_rate": 1.447781110171118e-06,
636
+ "loss": 0.8639,
637
+ "step": 420
638
+ },
639
+ {
640
+ "epoch": 0.3644419036730027,
641
+ "grad_norm": 2.9665919577118394,
642
+ "learning_rate": 1.421080774174884e-06,
643
+ "loss": 0.8738,
644
+ "step": 425
645
+ },
646
+ {
647
+ "epoch": 0.3687294554809204,
648
+ "grad_norm": 2.7395052466656082,
649
+ "learning_rate": 1.3948270701276901e-06,
650
+ "loss": 0.8124,
651
+ "step": 430
652
+ },
653
+ {
654
+ "epoch": 0.3730170072888381,
655
+ "grad_norm": 2.4814426410417547,
656
+ "learning_rate": 1.3690154851147892e-06,
657
+ "loss": 0.8018,
658
+ "step": 435
659
+ },
660
+ {
661
+ "epoch": 0.37730455909675575,
662
+ "grad_norm": 2.9039262323143697,
663
+ "learning_rate": 1.3436415215247681e-06,
664
+ "loss": 0.7621,
665
+ "step": 440
666
+ },
667
+ {
668
+ "epoch": 0.38159211090467343,
669
+ "grad_norm": 2.776860383566422,
670
+ "learning_rate": 1.3187006971017973e-06,
671
+ "loss": 0.9082,
672
+ "step": 445
673
+ },
674
+ {
675
+ "epoch": 0.3858796627125911,
676
+ "grad_norm": 2.1181970553123257,
677
+ "learning_rate": 1.2941885449984206e-06,
678
+ "loss": 0.8821,
679
+ "step": 450
680
+ },
681
+ {
682
+ "epoch": 0.3901672145205088,
683
+ "grad_norm": 2.5660032110684767,
684
+ "learning_rate": 1.2701006138288915e-06,
685
+ "loss": 0.9639,
686
+ "step": 455
687
+ },
688
+ {
689
+ "epoch": 0.39445476632842646,
690
+ "grad_norm": 4.632813592554,
691
+ "learning_rate": 1.2464324677230652e-06,
692
+ "loss": 0.9052,
693
+ "step": 460
694
+ },
695
+ {
696
+ "epoch": 0.39874231813634414,
697
+ "grad_norm": 3.394837987828098,
698
+ "learning_rate": 1.22317968638086e-06,
699
+ "loss": 0.8723,
700
+ "step": 465
701
+ },
702
+ {
703
+ "epoch": 0.4030298699442618,
704
+ "grad_norm": 2.716611388027132,
705
+ "learning_rate": 1.2003378651272997e-06,
706
+ "loss": 0.8457,
707
+ "step": 470
708
+ },
709
+ {
710
+ "epoch": 0.4073174217521795,
711
+ "grad_norm": 2.1520375204146625,
712
+ "learning_rate": 1.1779026149681347e-06,
713
+ "loss": 0.9502,
714
+ "step": 475
715
+ },
716
+ {
717
+ "epoch": 0.4116049735600972,
718
+ "grad_norm": 2.7552080232688696,
719
+ "learning_rate": 1.155869562646071e-06,
720
+ "loss": 0.831,
721
+ "step": 480
722
+ },
723
+ {
724
+ "epoch": 0.4116049735600972,
725
+ "eval_loss": 0.9032189846038818,
726
+ "eval_runtime": 19.1348,
727
+ "eval_samples_per_second": 10.452,
728
+ "eval_steps_per_second": 2.613,
729
+ "step": 480
730
+ },
731
+ {
732
+ "epoch": 0.41589252536801485,
733
+ "grad_norm": 2.0689491545152663,
734
+ "learning_rate": 1.1342343506976044e-06,
735
+ "loss": 0.8338,
736
+ "step": 485
737
+ },
738
+ {
739
+ "epoch": 0.42018007717593253,
740
+ "grad_norm": 3.2134570774473494,
741
+ "learning_rate": 1.1129926375104734e-06,
742
+ "loss": 0.8289,
743
+ "step": 490
744
+ },
745
+ {
746
+ "epoch": 0.4244676289838502,
747
+ "grad_norm": 2.822597617038844,
748
+ "learning_rate": 1.0921400973817452e-06,
749
+ "loss": 0.9218,
750
+ "step": 495
751
+ },
752
+ {
753
+ "epoch": 0.4287551807917679,
754
+ "grad_norm": 3.1918997161652003,
755
+ "learning_rate": 1.071672420576549e-06,
756
+ "loss": 0.8467,
757
+ "step": 500
758
+ },
759
+ {
760
+ "epoch": 0.43304273259968556,
761
+ "grad_norm": 3.0230981418285885,
762
+ "learning_rate": 1.051585313387455e-06,
763
+ "loss": 0.8871,
764
+ "step": 505
765
+ },
766
+ {
767
+ "epoch": 0.43733028440760324,
768
+ "grad_norm": 2.345223930068171,
769
+ "learning_rate": 1.0318744981945303e-06,
770
+ "loss": 1.1172,
771
+ "step": 510
772
+ },
773
+ {
774
+ "epoch": 0.4416178362155209,
775
+ "grad_norm": 2.23873439529607,
776
+ "learning_rate": 1.0125357135260713e-06,
777
+ "loss": 1.0281,
778
+ "step": 515
779
+ },
780
+ {
781
+ "epoch": 0.4459053880234386,
782
+ "grad_norm": 2.17521388870601,
783
+ "learning_rate": 9.93564714120029e-07,
784
+ "loss": 0.9027,
785
+ "step": 520
786
+ },
787
+ {
788
+ "epoch": 0.4501929398313563,
789
+ "grad_norm": 2.805982076338286,
790
+ "learning_rate": 9.749572709861371e-07,
791
+ "loss": 0.8424,
792
+ "step": 525
793
+ },
794
+ {
795
+ "epoch": 0.45448049163927395,
796
+ "grad_norm": 3.076865463356093,
797
+ "learning_rate": 9.5670917146877e-07,
798
+ "loss": 1.0317,
799
+ "step": 530
800
+ },
801
+ {
802
+ "epoch": 0.45876804344719163,
803
+ "grad_norm": 2.351075063586948,
804
+ "learning_rate": 9.38816219310525e-07,
805
+ "loss": 0.9455,
806
+ "step": 535
807
+ },
808
+ {
809
+ "epoch": 0.4630555952551093,
810
+ "grad_norm": 3.042494238619368,
811
+ "learning_rate": 9.212742347165562e-07,
812
+ "loss": 0.914,
813
+ "step": 540
814
+ },
815
+ {
816
+ "epoch": 0.467343147063027,
817
+ "grad_norm": 2.51152797954818,
818
+ "learning_rate": 9.040790544196722e-07,
819
+ "loss": 0.8507,
820
+ "step": 545
821
+ },
822
+ {
823
+ "epoch": 0.47163069887094466,
824
+ "grad_norm": 2.2530854319732647,
825
+ "learning_rate": 8.872265317462145e-07,
826
+ "loss": 0.7923,
827
+ "step": 550
828
+ },
829
+ {
830
+ "epoch": 0.47591825067886234,
831
+ "grad_norm": 2.4496883783363876,
832
+ "learning_rate": 8.707125366827236e-07,
833
+ "loss": 0.8219,
834
+ "step": 555
835
+ },
836
+ {
837
+ "epoch": 0.4802058024867801,
838
+ "grad_norm": 2.85322554374369,
839
+ "learning_rate": 8.54532955943421e-07,
840
+ "loss": 0.9696,
841
+ "step": 560
842
+ },
843
+ {
844
+ "epoch": 0.4802058024867801,
845
+ "eval_loss": 0.8974508047103882,
846
+ "eval_runtime": 19.0314,
847
+ "eval_samples_per_second": 10.509,
848
+ "eval_steps_per_second": 2.627,
849
+ "step": 560
850
+ },
851
+ {
852
+ "epoch": 0.48449335429469775,
853
+ "grad_norm": 2.657892610245309,
854
+ "learning_rate": 8.386836930385165e-07,
855
+ "loss": 0.8421,
856
+ "step": 565
857
+ },
858
+ {
859
+ "epoch": 0.48878090610261543,
860
+ "grad_norm": 2.602711920187755,
861
+ "learning_rate": 8.231606683433569e-07,
862
+ "loss": 0.8295,
863
+ "step": 570
864
+ },
865
+ {
866
+ "epoch": 0.4930684579105331,
867
+ "grad_norm": 2.1213399589470616,
868
+ "learning_rate": 8.079598191684382e-07,
869
+ "loss": 0.8803,
870
+ "step": 575
871
+ },
872
+ {
873
+ "epoch": 0.4973560097184508,
874
+ "grad_norm": 2.244791995121278,
875
+ "learning_rate": 7.930770998302978e-07,
876
+ "loss": 0.8343,
877
+ "step": 580
878
+ },
879
+ {
880
+ "epoch": 0.5016435615263685,
881
+ "grad_norm": 2.566423079642009,
882
+ "learning_rate": 7.785084817233009e-07,
883
+ "loss": 0.8736,
884
+ "step": 585
885
+ },
886
+ {
887
+ "epoch": 0.5059311133342861,
888
+ "grad_norm": 2.3039665634657487,
889
+ "learning_rate": 7.642499533923466e-07,
890
+ "loss": 0.8449,
891
+ "step": 590
892
+ },
893
+ {
894
+ "epoch": 0.5102186651422038,
895
+ "grad_norm": 2.6413196407680095,
896
+ "learning_rate": 7.502975206065118e-07,
897
+ "loss": 0.9765,
898
+ "step": 595
899
+ },
900
+ {
901
+ "epoch": 0.5145062169501214,
902
+ "grad_norm": 2.6494694608389806,
903
+ "learning_rate": 7.366472064336485e-07,
904
+ "loss": 1.041,
905
+ "step": 600
906
+ },
907
+ {
908
+ "epoch": 0.5187937687580392,
909
+ "grad_norm": 2.777084503723626,
910
+ "learning_rate": 7.232950513159591e-07,
911
+ "loss": 0.7932,
912
+ "step": 605
913
+ },
914
+ {
915
+ "epoch": 0.5230813205659568,
916
+ "grad_norm": 2.487662762486022,
917
+ "learning_rate": 7.102371131465766e-07,
918
+ "loss": 0.8704,
919
+ "step": 610
920
+ },
921
+ {
922
+ "epoch": 0.5273688723738745,
923
+ "grad_norm": 2.55250344248028,
924
+ "learning_rate": 6.974694673471581e-07,
925
+ "loss": 0.8656,
926
+ "step": 615
927
+ },
928
+ {
929
+ "epoch": 0.5316564241817922,
930
+ "grad_norm": 3.215607059371808,
931
+ "learning_rate": 6.849882069465297e-07,
932
+ "loss": 0.8775,
933
+ "step": 620
934
+ },
935
+ {
936
+ "epoch": 0.5359439759897099,
937
+ "grad_norm": 2.663679299659993,
938
+ "learning_rate": 6.727894426603947e-07,
939
+ "loss": 0.9558,
940
+ "step": 625
941
+ },
942
+ {
943
+ "epoch": 0.5402315277976275,
944
+ "grad_norm": 1.8863771094416066,
945
+ "learning_rate": 6.608693029721375e-07,
946
+ "loss": 1.0649,
947
+ "step": 630
948
+ },
949
+ {
950
+ "epoch": 0.5445190796055452,
951
+ "grad_norm": 2.3166038184540345,
952
+ "learning_rate": 6.492239342147439e-07,
953
+ "loss": 0.9116,
954
+ "step": 635
955
+ },
956
+ {
957
+ "epoch": 0.5488066314134629,
958
+ "grad_norm": 2.451365227453816,
959
+ "learning_rate": 6.378495006538639e-07,
960
+ "loss": 0.9949,
961
+ "step": 640
962
+ },
963
+ {
964
+ "epoch": 0.5488066314134629,
965
+ "eval_loss": 0.8972450494766235,
966
+ "eval_runtime": 19.0746,
967
+ "eval_samples_per_second": 10.485,
968
+ "eval_steps_per_second": 2.621,
969
+ "step": 640
970
+ },
971
+ {
972
+ "epoch": 0.5530941832213806,
973
+ "grad_norm": 2.431525558235171,
974
+ "learning_rate": 6.267421845720492e-07,
975
+ "loss": 0.9208,
976
+ "step": 645
977
+ },
978
+ {
979
+ "epoch": 0.5573817350292982,
980
+ "grad_norm": 3.025842320604373,
981
+ "learning_rate": 6.158981863541822e-07,
982
+ "loss": 0.8782,
983
+ "step": 650
984
+ },
985
+ {
986
+ "epoch": 0.561669286837216,
987
+ "grad_norm": 2.713593393993989,
988
+ "learning_rate": 6.053137245741388e-07,
989
+ "loss": 0.8848,
990
+ "step": 655
991
+ },
992
+ {
993
+ "epoch": 0.5659568386451336,
994
+ "grad_norm": 2.364400143996411,
995
+ "learning_rate": 5.949850360827048e-07,
996
+ "loss": 0.8214,
997
+ "step": 660
998
+ },
999
+ {
1000
+ "epoch": 0.5702443904530513,
1001
+ "grad_norm": 3.1249075781445654,
1002
+ "learning_rate": 5.849083760967786e-07,
1003
+ "loss": 0.9232,
1004
+ "step": 665
1005
+ },
1006
+ {
1007
+ "epoch": 0.574531942260969,
1008
+ "grad_norm": 2.371939438179526,
1009
+ "learning_rate": 5.750800182898949e-07,
1010
+ "loss": 0.9599,
1011
+ "step": 670
1012
+ },
1013
+ {
1014
+ "epoch": 0.5788194940688867,
1015
+ "grad_norm": 2.657320971034355,
1016
+ "learning_rate": 5.654962548840998e-07,
1017
+ "loss": 0.957,
1018
+ "step": 675
1019
+ },
1020
+ {
1021
+ "epoch": 0.5831070458768044,
1022
+ "grad_norm": 1.9610510581627134,
1023
+ "learning_rate": 5.561533967432111e-07,
1024
+ "loss": 0.8544,
1025
+ "step": 680
1026
+ },
1027
+ {
1028
+ "epoch": 0.587394597684722,
1029
+ "grad_norm": 1.9590021785129759,
1030
+ "learning_rate": 5.470477734675006e-07,
1031
+ "loss": 0.9022,
1032
+ "step": 685
1033
+ },
1034
+ {
1035
+ "epoch": 0.5916821494926398,
1036
+ "grad_norm": 3.0946081747543532,
1037
+ "learning_rate": 5.381757334898326e-07,
1038
+ "loss": 0.8607,
1039
+ "step": 690
1040
+ },
1041
+ {
1042
+ "epoch": 0.5959697013005574,
1043
+ "grad_norm": 2.6523600890631447,
1044
+ "learning_rate": 5.295336441732995e-07,
1045
+ "loss": 0.9483,
1046
+ "step": 695
1047
+ },
1048
+ {
1049
+ "epoch": 0.6002572531084751,
1050
+ "grad_norm": 2.6162593545931943,
1051
+ "learning_rate": 5.211178919103908e-07,
1052
+ "loss": 0.8484,
1053
+ "step": 700
1054
+ },
1055
+ {
1056
+ "epoch": 0.6045448049163927,
1057
+ "grad_norm": 2.7584028741566935,
1058
+ "learning_rate": 5.129248822237369e-07,
1059
+ "loss": 0.8153,
1060
+ "step": 705
1061
+ },
1062
+ {
1063
+ "epoch": 0.6088323567243105,
1064
+ "grad_norm": 2.2177368688014263,
1065
+ "learning_rate": 5.049510398684706e-07,
1066
+ "loss": 0.8865,
1067
+ "step": 710
1068
+ },
1069
+ {
1070
+ "epoch": 0.6131199085322281,
1071
+ "grad_norm": 2.7385320493457175,
1072
+ "learning_rate": 4.97192808936251e-07,
1073
+ "loss": 0.8288,
1074
+ "step": 715
1075
+ },
1076
+ {
1077
+ "epoch": 0.6174074603401458,
1078
+ "grad_norm": 2.969022490845044,
1079
+ "learning_rate": 4.896466529609901e-07,
1080
+ "loss": 0.8154,
1081
+ "step": 720
1082
+ },
1083
+ {
1084
+ "epoch": 0.6174074603401458,
1085
+ "eval_loss": 0.8948369026184082,
1086
+ "eval_runtime": 19.0474,
1087
+ "eval_samples_per_second": 10.5,
1088
+ "eval_steps_per_second": 2.625,
1089
+ "step": 720
1090
+ },
1091
+ {
1092
+ "epoch": 0.6216950121480634,
1093
+ "grad_norm": 2.4080414960336576,
1094
+ "learning_rate": 4.823090550263373e-07,
1095
+ "loss": 0.8132,
1096
+ "step": 725
1097
+ },
1098
+ {
1099
+ "epoch": 0.6259825639559812,
1100
+ "grad_norm": 2.4062548632108305,
1101
+ "learning_rate": 4.7517651787496393e-07,
1102
+ "loss": 0.8563,
1103
+ "step": 730
1104
+ },
1105
+ {
1106
+ "epoch": 0.6302701157638988,
1107
+ "grad_norm": 2.4974176263678145,
1108
+ "learning_rate": 4.682455640197012e-07,
1109
+ "loss": 0.83,
1110
+ "step": 735
1111
+ },
1112
+ {
1113
+ "epoch": 0.6345576675718165,
1114
+ "grad_norm": 2.782934403189113,
1115
+ "learning_rate": 4.6151273585658703e-07,
1116
+ "loss": 0.7722,
1117
+ "step": 740
1118
+ },
1119
+ {
1120
+ "epoch": 0.6388452193797342,
1121
+ "grad_norm": 3.589995905013926,
1122
+ "learning_rate": 4.549745957798709e-07,
1123
+ "loss": 0.9013,
1124
+ "step": 745
1125
+ },
1126
+ {
1127
+ "epoch": 0.6431327711876519,
1128
+ "grad_norm": 1.5164412373226497,
1129
+ "learning_rate": 4.486277262990414e-07,
1130
+ "loss": 0.8061,
1131
+ "step": 750
1132
+ },
1133
+ {
1134
+ "epoch": 0.6474203229955695,
1135
+ "grad_norm": 2.4822941257221496,
1136
+ "learning_rate": 4.424687301579312e-07,
1137
+ "loss": 0.8018,
1138
+ "step": 755
1139
+ },
1140
+ {
1141
+ "epoch": 0.6517078748034872,
1142
+ "grad_norm": 2.3163460863010044,
1143
+ "learning_rate": 4.364942304559619e-07,
1144
+ "loss": 0.97,
1145
+ "step": 760
1146
+ },
1147
+ {
1148
+ "epoch": 0.6559954266114049,
1149
+ "grad_norm": 2.5709552598683048,
1150
+ "learning_rate": 4.307008707715972e-07,
1151
+ "loss": 0.8424,
1152
+ "step": 765
1153
+ },
1154
+ {
1155
+ "epoch": 0.6602829784193226,
1156
+ "grad_norm": 2.97580695190474,
1157
+ "learning_rate": 4.250853152880694e-07,
1158
+ "loss": 0.9495,
1159
+ "step": 770
1160
+ },
1161
+ {
1162
+ "epoch": 0.6645705302272402,
1163
+ "grad_norm": 2.780816600415984,
1164
+ "learning_rate": 4.1964424892144836e-07,
1165
+ "loss": 0.9217,
1166
+ "step": 775
1167
+ },
1168
+ {
1169
+ "epoch": 0.668858082035158,
1170
+ "grad_norm": 3.106789897489022,
1171
+ "learning_rate": 4.143743774511321e-07,
1172
+ "loss": 0.7872,
1173
+ "step": 780
1174
+ },
1175
+ {
1176
+ "epoch": 0.6731456338430756,
1177
+ "grad_norm": 2.6180834213520425,
1178
+ "learning_rate": 4.0927242765282987e-07,
1179
+ "loss": 0.9516,
1180
+ "step": 785
1181
+ },
1182
+ {
1183
+ "epoch": 0.6774331856509933,
1184
+ "grad_norm": 3.3693090699327675,
1185
+ "learning_rate": 4.043351474341226e-07,
1186
+ "loss": 0.918,
1187
+ "step": 790
1188
+ },
1189
+ {
1190
+ "epoch": 0.6817207374589109,
1191
+ "grad_norm": 2.6455267685583292,
1192
+ "learning_rate": 3.995593059726841e-07,
1193
+ "loss": 0.8869,
1194
+ "step": 795
1195
+ },
1196
+ {
1197
+ "epoch": 0.6860082892668287,
1198
+ "grad_norm": 2.6976779093683985,
1199
+ "learning_rate": 3.9494169385724855e-07,
1200
+ "loss": 0.9682,
1201
+ "step": 800
1202
+ },
1203
+ {
1204
+ "epoch": 0.6860082892668287,
1205
+ "eval_loss": 0.8931262493133545,
1206
+ "eval_runtime": 19.039,
1207
+ "eval_samples_per_second": 10.505,
1208
+ "eval_steps_per_second": 2.626,
1209
+ "step": 800
1210
+ },
1211
+ {
1212
+ "epoch": 0.6902958410747463,
1213
+ "grad_norm": 2.73935107332009,
1214
+ "learning_rate": 3.904791232314207e-07,
1215
+ "loss": 0.9497,
1216
+ "step": 805
1217
+ },
1218
+ {
1219
+ "epoch": 0.694583392882664,
1220
+ "grad_norm": 2.594513781497614,
1221
+ "learning_rate": 3.861684279404229e-07,
1222
+ "loss": 0.9616,
1223
+ "step": 810
1224
+ },
1225
+ {
1226
+ "epoch": 0.6988709446905816,
1227
+ "grad_norm": 2.2189306808012694,
1228
+ "learning_rate": 3.820064636808802e-07,
1229
+ "loss": 1.0817,
1230
+ "step": 815
1231
+ },
1232
+ {
1233
+ "epoch": 0.7031584964984994,
1234
+ "grad_norm": 2.636673641067638,
1235
+ "learning_rate": 3.7799010815375107e-07,
1236
+ "loss": 0.9003,
1237
+ "step": 820
1238
+ },
1239
+ {
1240
+ "epoch": 0.707446048306417,
1241
+ "grad_norm": 2.074697655719305,
1242
+ "learning_rate": 3.741162612205157e-07,
1243
+ "loss": 1.1193,
1244
+ "step": 825
1245
+ },
1246
+ {
1247
+ "epoch": 0.7117336001143347,
1248
+ "grad_norm": 2.4627913841496425,
1249
+ "learning_rate": 3.703818450627364e-07,
1250
+ "loss": 0.8603,
1251
+ "step": 830
1252
+ },
1253
+ {
1254
+ "epoch": 0.7160211519222524,
1255
+ "grad_norm": 2.4468198599625044,
1256
+ "learning_rate": 3.6678380434511737e-07,
1257
+ "loss": 1.012,
1258
+ "step": 835
1259
+ },
1260
+ {
1261
+ "epoch": 0.7203087037301701,
1262
+ "grad_norm": 2.231882643368985,
1263
+ "learning_rate": 3.6331910638219e-07,
1264
+ "loss": 1.0174,
1265
+ "step": 840
1266
+ },
1267
+ {
1268
+ "epoch": 0.7245962555380877,
1269
+ "grad_norm": 3.0961788514759374,
1270
+ "learning_rate": 3.5998474130876195e-07,
1271
+ "loss": 0.982,
1272
+ "step": 845
1273
+ },
1274
+ {
1275
+ "epoch": 0.7288838073460054,
1276
+ "grad_norm": 2.699948117104775,
1277
+ "learning_rate": 3.567777222542744e-07,
1278
+ "loss": 0.9954,
1279
+ "step": 850
1280
+ },
1281
+ {
1282
+ "epoch": 0.7331713591539231,
1283
+ "grad_norm": 2.0352300295309815,
1284
+ "learning_rate": 3.536950855212165e-07,
1285
+ "loss": 0.9349,
1286
+ "step": 855
1287
+ },
1288
+ {
1289
+ "epoch": 0.7374589109618408,
1290
+ "grad_norm": 2.3439290267355664,
1291
+ "learning_rate": 3.5073389076775976e-07,
1292
+ "loss": 1.1525,
1293
+ "step": 860
1294
+ },
1295
+ {
1296
+ "epoch": 0.7417464627697584,
1297
+ "grad_norm": 1.8013900413258555,
1298
+ "learning_rate": 3.4789122119478064e-07,
1299
+ "loss": 1.0404,
1300
+ "step": 865
1301
+ },
1302
+ {
1303
+ "epoch": 0.7460340145776762,
1304
+ "grad_norm": 2.432177798756092,
1305
+ "learning_rate": 3.451641837374477e-07,
1306
+ "loss": 1.1018,
1307
+ "step": 870
1308
+ },
1309
+ {
1310
+ "epoch": 0.7503215663855938,
1311
+ "grad_norm": 2.339931147492053,
1312
+ "learning_rate": 3.425499092615662e-07,
1313
+ "loss": 1.0088,
1314
+ "step": 875
1315
+ },
1316
+ {
1317
+ "epoch": 0.7546091181935115,
1318
+ "grad_norm": 2.865649768086174,
1319
+ "learning_rate": 3.4004555276487614e-07,
1320
+ "loss": 0.9491,
1321
+ "step": 880
1322
+ },
1323
+ {
1324
+ "epoch": 0.7546091181935115,
1325
+ "eval_loss": 0.9030270576477051,
1326
+ "eval_runtime": 19.0612,
1327
+ "eval_samples_per_second": 10.493,
1328
+ "eval_steps_per_second": 2.623,
1329
+ "step": 880
1330
+ },
1331
+ {
1332
+ "epoch": 0.7588966700014291,
1333
+ "grad_norm": 1.9608521922901478,
1334
+ "learning_rate": 3.376482935835186e-07,
1335
+ "loss": 1.0566,
1336
+ "step": 885
1337
+ },
1338
+ {
1339
+ "epoch": 0.7631842218093469,
1340
+ "grad_norm": 2.001405740517041,
1341
+ "learning_rate": 3.3535533560389486e-07,
1342
+ "loss": 1.0203,
1343
+ "step": 890
1344
+ },
1345
+ {
1346
+ "epoch": 0.7674717736172646,
1347
+ "grad_norm": 3.114574828020116,
1348
+ "learning_rate": 3.331639074801548e-07,
1349
+ "loss": 0.9489,
1350
+ "step": 895
1351
+ },
1352
+ {
1353
+ "epoch": 0.7717593254251822,
1354
+ "grad_norm": 2.3092110155282985,
1355
+ "learning_rate": 3.3107126285757256e-07,
1356
+ "loss": 0.9057,
1357
+ "step": 900
1358
+ },
1359
+ {
1360
+ "epoch": 0.7760468772331,
1361
+ "grad_norm": 2.714773467015402,
1362
+ "learning_rate": 3.290746806020766e-07,
1363
+ "loss": 0.9441,
1364
+ "step": 905
1365
+ },
1366
+ {
1367
+ "epoch": 0.7803344290410176,
1368
+ "grad_norm": 3.186486155591397,
1369
+ "learning_rate": 3.271714650362233e-07,
1370
+ "loss": 1.0213,
1371
+ "step": 910
1372
+ },
1373
+ {
1374
+ "epoch": 0.7846219808489353,
1375
+ "grad_norm": 2.5861267874594174,
1376
+ "learning_rate": 3.2535894618192186e-07,
1377
+ "loss": 0.9689,
1378
+ "step": 915
1379
+ },
1380
+ {
1381
+ "epoch": 0.7889095326568529,
1382
+ "grad_norm": 3.826794117846477,
1383
+ "learning_rate": 3.236344800102375e-07,
1384
+ "loss": 0.8944,
1385
+ "step": 920
1386
+ },
1387
+ {
1388
+ "epoch": 0.7931970844647707,
1389
+ "grad_norm": 2.7462154972645814,
1390
+ "learning_rate": 3.2199544869862547e-07,
1391
+ "loss": 1.0624,
1392
+ "step": 925
1393
+ },
1394
+ {
1395
+ "epoch": 0.7974846362726883,
1396
+ "grad_norm": 2.8358584012860777,
1397
+ "learning_rate": 3.204392608959703e-07,
1398
+ "loss": 0.9327,
1399
+ "step": 930
1400
+ },
1401
+ {
1402
+ "epoch": 0.801772188080606,
1403
+ "grad_norm": 2.101011305773841,
1404
+ "learning_rate": 3.1896335199583363e-07,
1405
+ "loss": 0.9159,
1406
+ "step": 935
1407
+ },
1408
+ {
1409
+ "epoch": 0.8060597398885236,
1410
+ "grad_norm": 2.5833966453921198,
1411
+ "learning_rate": 3.1756518441834397e-07,
1412
+ "loss": 1.0248,
1413
+ "step": 940
1414
+ },
1415
+ {
1416
+ "epoch": 0.8103472916964414,
1417
+ "grad_norm": 6.2684841674997775,
1418
+ "learning_rate": 3.151927901941027e-07,
1419
+ "loss": 1.0413,
1420
+ "step": 945
1421
+ },
1422
+ {
1423
+ "epoch": 0.814634843504359,
1424
+ "grad_norm": 2.276372461235212,
1425
+ "learning_rate": 3.1032417503134016e-07,
1426
+ "loss": 1.1134,
1427
+ "step": 950
1428
+ },
1429
+ {
1430
+ "epoch": 0.8189223953122767,
1431
+ "grad_norm": 2.6812797606926555,
1432
+ "learning_rate": 3.054555598685777e-07,
1433
+ "loss": 0.9336,
1434
+ "step": 955
1435
+ },
1436
+ {
1437
+ "epoch": 0.8232099471201944,
1438
+ "grad_norm": 2.417389224635538,
1439
+ "learning_rate": 3.0058694470581514e-07,
1440
+ "loss": 1.068,
1441
+ "step": 960
1442
+ },
1443
+ {
1444
+ "epoch": 0.8232099471201944,
1445
+ "eval_loss": 0.9022178053855896,
1446
+ "eval_runtime": 19.0566,
1447
+ "eval_samples_per_second": 10.495,
1448
+ "eval_steps_per_second": 2.624,
1449
+ "step": 960
1450
+ },
1451
+ {
1452
+ "epoch": 0.8274974989281121,
1453
+ "grad_norm": 2.503558384043619,
1454
+ "learning_rate": 2.9571832954305265e-07,
1455
+ "loss": 1.0307,
1456
+ "step": 965
1457
+ },
1458
+ {
1459
+ "epoch": 0.8317850507360297,
1460
+ "grad_norm": 2.249581998288759,
1461
+ "learning_rate": 2.9084971438029017e-07,
1462
+ "loss": 0.9962,
1463
+ "step": 970
1464
+ },
1465
+ {
1466
+ "epoch": 0.8360726025439474,
1467
+ "grad_norm": 3.875121879524354,
1468
+ "learning_rate": 2.8598109921752763e-07,
1469
+ "loss": 1.0143,
1470
+ "step": 975
1471
+ },
1472
+ {
1473
+ "epoch": 0.8403601543518651,
1474
+ "grad_norm": 1.730446489555693,
1475
+ "learning_rate": 2.8111248405476515e-07,
1476
+ "loss": 0.9869,
1477
+ "step": 980
1478
+ },
1479
+ {
1480
+ "epoch": 0.8446477061597828,
1481
+ "grad_norm": 3.3232425457372745,
1482
+ "learning_rate": 2.7624386889200266e-07,
1483
+ "loss": 1.0683,
1484
+ "step": 985
1485
+ },
1486
+ {
1487
+ "epoch": 0.8489352579677004,
1488
+ "grad_norm": 2.4807364391304225,
1489
+ "learning_rate": 2.713752537292401e-07,
1490
+ "loss": 0.9797,
1491
+ "step": 990
1492
+ },
1493
+ {
1494
+ "epoch": 0.8532228097756182,
1495
+ "grad_norm": 2.3616731714440724,
1496
+ "learning_rate": 2.6650663856647764e-07,
1497
+ "loss": 1.0389,
1498
+ "step": 995
1499
+ },
1500
+ {
1501
+ "epoch": 0.8575103615835358,
1502
+ "grad_norm": 2.6062865385957514,
1503
+ "learning_rate": 2.616380234037151e-07,
1504
+ "loss": 1.0267,
1505
+ "step": 1000
1506
+ },
1507
+ {
1508
+ "epoch": 0.8617979133914535,
1509
+ "grad_norm": 2.907979106229624,
1510
+ "learning_rate": 2.567694082409526e-07,
1511
+ "loss": 0.9329,
1512
+ "step": 1005
1513
+ },
1514
+ {
1515
+ "epoch": 0.8660854651993711,
1516
+ "grad_norm": 2.6968962865268407,
1517
+ "learning_rate": 2.5190079307819013e-07,
1518
+ "loss": 0.9386,
1519
+ "step": 1010
1520
+ },
1521
+ {
1522
+ "epoch": 0.8703730170072889,
1523
+ "grad_norm": 2.21037904641155,
1524
+ "learning_rate": 2.4703217791542765e-07,
1525
+ "loss": 1.0709,
1526
+ "step": 1015
1527
+ },
1528
+ {
1529
+ "epoch": 0.8746605688152065,
1530
+ "grad_norm": 2.8255592337377915,
1531
+ "learning_rate": 2.421635627526651e-07,
1532
+ "loss": 0.8629,
1533
+ "step": 1020
1534
+ },
1535
+ {
1536
+ "epoch": 0.8789481206231242,
1537
+ "grad_norm": 2.6598508915895516,
1538
+ "learning_rate": 2.3729494758990262e-07,
1539
+ "loss": 0.9564,
1540
+ "step": 1025
1541
+ },
1542
+ {
1543
+ "epoch": 0.8832356724310418,
1544
+ "grad_norm": 2.5349227338549043,
1545
+ "learning_rate": 2.3242633242714014e-07,
1546
+ "loss": 0.9884,
1547
+ "step": 1030
1548
+ },
1549
+ {
1550
+ "epoch": 0.8875232242389596,
1551
+ "grad_norm": 1.8000674399648018,
1552
+ "learning_rate": 2.275577172643776e-07,
1553
+ "loss": 1.1607,
1554
+ "step": 1035
1555
+ },
1556
+ {
1557
+ "epoch": 0.8918107760468772,
1558
+ "grad_norm": 2.0150522007599654,
1559
+ "learning_rate": 2.2268910210161506e-07,
1560
+ "loss": 1.06,
1561
+ "step": 1040
1562
+ },
1563
+ {
1564
+ "epoch": 0.8918107760468772,
1565
+ "eval_loss": 0.9013447761535645,
1566
+ "eval_runtime": 19.0476,
1567
+ "eval_samples_per_second": 10.5,
1568
+ "eval_steps_per_second": 2.625,
1569
+ "step": 1040
1570
+ },
1571
+ {
1572
+ "epoch": 0.8960983278547949,
1573
+ "grad_norm": 2.714964092055051,
1574
+ "learning_rate": 2.1782048693885258e-07,
1575
+ "loss": 0.8408,
1576
+ "step": 1045
1577
+ },
1578
+ {
1579
+ "epoch": 0.9003858796627126,
1580
+ "grad_norm": 2.328572268378804,
1581
+ "learning_rate": 2.129518717760901e-07,
1582
+ "loss": 0.9585,
1583
+ "step": 1050
1584
+ },
1585
+ {
1586
+ "epoch": 0.9046734314706303,
1587
+ "grad_norm": 3.3294058341520847,
1588
+ "learning_rate": 2.0808325661332756e-07,
1589
+ "loss": 1.0169,
1590
+ "step": 1055
1591
+ },
1592
+ {
1593
+ "epoch": 0.9089609832785479,
1594
+ "grad_norm": 2.3567378214154453,
1595
+ "learning_rate": 2.0321464145056507e-07,
1596
+ "loss": 1.0411,
1597
+ "step": 1060
1598
+ },
1599
+ {
1600
+ "epoch": 0.9132485350864656,
1601
+ "grad_norm": 2.3516481223731702,
1602
+ "learning_rate": 1.9834602628780256e-07,
1603
+ "loss": 1.0731,
1604
+ "step": 1065
1605
+ },
1606
+ {
1607
+ "epoch": 0.9175360868943833,
1608
+ "grad_norm": 2.3183322496467484,
1609
+ "learning_rate": 1.934774111250401e-07,
1610
+ "loss": 0.9489,
1611
+ "step": 1070
1612
+ },
1613
+ {
1614
+ "epoch": 0.921823638702301,
1615
+ "grad_norm": 1.97960646392379,
1616
+ "learning_rate": 1.8860879596227757e-07,
1617
+ "loss": 1.0331,
1618
+ "step": 1075
1619
+ },
1620
+ {
1621
+ "epoch": 0.9261111905102186,
1622
+ "grad_norm": 2.3395284448987086,
1623
+ "learning_rate": 1.8374018079951505e-07,
1624
+ "loss": 0.7678,
1625
+ "step": 1080
1626
+ },
1627
+ {
1628
+ "epoch": 0.9303987423181364,
1629
+ "grad_norm": 1.945316009597557,
1630
+ "learning_rate": 1.788715656367526e-07,
1631
+ "loss": 1.0268,
1632
+ "step": 1085
1633
+ },
1634
+ {
1635
+ "epoch": 0.934686294126054,
1636
+ "grad_norm": 2.5392514762785603,
1637
+ "learning_rate": 1.7400295047399006e-07,
1638
+ "loss": 1.0499,
1639
+ "step": 1090
1640
+ },
1641
+ {
1642
+ "epoch": 0.9389738459339717,
1643
+ "grad_norm": 2.147497075881358,
1644
+ "learning_rate": 1.6913433531122752e-07,
1645
+ "loss": 0.8984,
1646
+ "step": 1095
1647
+ },
1648
+ {
1649
+ "epoch": 0.9432613977418893,
1650
+ "grad_norm": 2.3338579963123043,
1651
+ "learning_rate": 1.6426572014846504e-07,
1652
+ "loss": 1.0244,
1653
+ "step": 1100
1654
+ },
1655
+ {
1656
+ "epoch": 0.9475489495498071,
1657
+ "grad_norm": 2.272071646300021,
1658
+ "learning_rate": 1.5939710498570255e-07,
1659
+ "loss": 0.8251,
1660
+ "step": 1105
1661
+ },
1662
+ {
1663
+ "epoch": 0.9518365013577247,
1664
+ "grad_norm": 1.6609121532926487,
1665
+ "learning_rate": 1.5452848982294004e-07,
1666
+ "loss": 0.9794,
1667
+ "step": 1110
1668
+ },
1669
+ {
1670
+ "epoch": 0.9561240531656424,
1671
+ "grad_norm": 2.2563188492644493,
1672
+ "learning_rate": 1.4965987466017753e-07,
1673
+ "loss": 0.972,
1674
+ "step": 1115
1675
+ },
1676
+ {
1677
+ "epoch": 0.9604116049735602,
1678
+ "grad_norm": 2.667525192015302,
1679
+ "learning_rate": 1.4479125949741505e-07,
1680
+ "loss": 0.8302,
1681
+ "step": 1120
1682
+ },
1683
+ {
1684
+ "epoch": 0.9604116049735602,
1685
+ "eval_loss": 0.9002277851104736,
1686
+ "eval_runtime": 19.0592,
1687
+ "eval_samples_per_second": 10.494,
1688
+ "eval_steps_per_second": 2.623,
1689
+ "step": 1120
1690
+ },
1691
+ {
1692
+ "epoch": 0.9646991567814778,
1693
+ "grad_norm": 1.8891294277340498,
1694
+ "learning_rate": 1.3992264433465253e-07,
1695
+ "loss": 0.8849,
1696
+ "step": 1125
1697
+ },
1698
+ {
1699
+ "epoch": 0.9689867085893955,
1700
+ "grad_norm": 2.5578344667960127,
1701
+ "learning_rate": 1.3505402917189002e-07,
1702
+ "loss": 0.9591,
1703
+ "step": 1130
1704
+ },
1705
+ {
1706
+ "epoch": 0.9732742603973131,
1707
+ "grad_norm": 2.001959937555614,
1708
+ "learning_rate": 1.301854140091275e-07,
1709
+ "loss": 1.0343,
1710
+ "step": 1135
1711
+ },
1712
+ {
1713
+ "epoch": 0.9775618122052309,
1714
+ "grad_norm": 1.578569313456066,
1715
+ "learning_rate": 1.2531679884636503e-07,
1716
+ "loss": 1.0543,
1717
+ "step": 1140
1718
+ },
1719
+ {
1720
+ "epoch": 0.9818493640131485,
1721
+ "grad_norm": 2.0720069005801953,
1722
+ "learning_rate": 1.2044818368360252e-07,
1723
+ "loss": 0.8641,
1724
+ "step": 1145
1725
+ },
1726
+ {
1727
+ "epoch": 0.9861369158210662,
1728
+ "grad_norm": 1.8810386084158826,
1729
+ "learning_rate": 1.1557956852084e-07,
1730
+ "loss": 1.0326,
1731
+ "step": 1150
1732
+ },
1733
+ {
1734
+ "epoch": 0.9904244676289838,
1735
+ "grad_norm": 2.0266012589600613,
1736
+ "learning_rate": 1.1071095335807752e-07,
1737
+ "loss": 1.0289,
1738
+ "step": 1155
1739
+ },
1740
+ {
1741
+ "epoch": 0.9947120194369016,
1742
+ "grad_norm": 2.2518373465247357,
1743
+ "learning_rate": 1.0584233819531501e-07,
1744
+ "loss": 0.939,
1745
+ "step": 1160
1746
+ },
1747
+ {
1748
+ "epoch": 0.9989995712448192,
1749
+ "grad_norm": 2.7326466173600337,
1750
+ "learning_rate": 1.009737230325525e-07,
1751
+ "loss": 1.0486,
1752
+ "step": 1165
1753
+ },
1754
+ {
1755
+ "epoch": 0.9998570816064027,
1756
+ "step": 1166,
1757
+ "total_flos": 1.7681949461682586e+17,
1758
+ "train_loss": 0.944941889564946,
1759
+ "train_runtime": 15099.9882,
1760
+ "train_samples_per_second": 2.78,
1761
+ "train_steps_per_second": 0.077
1762
+ }
1763
+ ],
1764
+ "logging_steps": 5,
1765
+ "max_steps": 1166,
1766
+ "num_input_tokens_seen": 0,
1767
+ "num_train_epochs": 1,
1768
+ "save_steps": 1166,
1769
+ "stateful_callbacks": {
1770
+ "TrainerControl": {
1771
+ "args": {
1772
+ "should_epoch_stop": false,
1773
+ "should_evaluate": false,
1774
+ "should_log": false,
1775
+ "should_save": true,
1776
+ "should_training_stop": true
1777
+ },
1778
+ "attributes": {}
1779
+ }
1780
+ },
1781
+ "total_flos": 1.7681949461682586e+17,
1782
+ "train_batch_size": 3,
1783
+ "trial_name": null,
1784
+ "trial_params": null
1785
+ }