learn3r commited on
Commit
21a0014
1 Parent(s): e9a881d

End of training

Browse files
Files changed (5) hide show
  1. README.md +4 -2
  2. all_results.json +13 -0
  3. eval_results.json +8 -0
  4. train_results.json +8 -0
  5. trainer_state.json +2148 -0
README.md CHANGED
@@ -3,6 +3,8 @@ license: apache-2.0
3
  base_model: google/long-t5-tglobal-xl
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: longt5_xl_govreport_4096_memsum_e10
8
  results: []
@@ -13,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # longt5_xl_govreport_4096_memsum_e10
15
 
16
- This model is a fine-tuned version of [google/long-t5-tglobal-xl](https://huggingface.co/google/long-t5-tglobal-xl) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 1.5582
19
 
20
  ## Model description
21
 
 
3
  base_model: google/long-t5-tglobal-xl
4
  tags:
5
  - generated_from_trainer
6
+ datasets:
7
+ - learn3r/gov_report_memsum_oracle
8
  model-index:
9
  - name: longt5_xl_govreport_4096_memsum_e10
10
  results: []
 
15
 
16
  # longt5_xl_govreport_4096_memsum_e10
17
 
18
+ This model is a fine-tuned version of [google/long-t5-tglobal-xl](https://huggingface.co/google/long-t5-tglobal-xl) on the learn3r/gov_report_memsum_oracle dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.2380
21
 
22
  ## Model description
23
 
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.97,
3
+ "eval_loss": 1.2379964590072632,
4
+ "eval_runtime": 153.0102,
5
+ "eval_samples": 972,
6
+ "eval_samples_per_second": 6.353,
7
+ "eval_steps_per_second": 0.797,
8
+ "train_loss": 0.9514477711390047,
9
+ "train_runtime": 93373.8295,
10
+ "train_samples": 17457,
11
+ "train_samples_per_second": 1.87,
12
+ "train_steps_per_second": 0.007
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.97,
3
+ "eval_loss": 1.2379964590072632,
4
+ "eval_runtime": 153.0102,
5
+ "eval_samples": 972,
6
+ "eval_samples_per_second": 6.353,
7
+ "eval_steps_per_second": 0.797
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.97,
3
+ "train_loss": 0.9514477711390047,
4
+ "train_runtime": 93373.8295,
5
+ "train_samples": 17457,
6
+ "train_samples_per_second": 1.87,
7
+ "train_steps_per_second": 0.007
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,2148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.2379964590072632,
3
+ "best_model_checkpoint": "/home/co-ou1/rds/hpc-work/models/longt5_xl_govreport_memsum_4096/longt5_xl_govreport_4096_memsum_e10/checkpoint-136",
4
+ "epoch": 9.967934035730647,
5
+ "eval_steps": 500,
6
+ "global_step": 680,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 0.001,
14
+ "loss": 1.9479,
15
+ "step": 2
16
+ },
17
+ {
18
+ "epoch": 0.06,
19
+ "learning_rate": 0.001,
20
+ "loss": 1.8801,
21
+ "step": 4
22
+ },
23
+ {
24
+ "epoch": 0.09,
25
+ "learning_rate": 0.001,
26
+ "loss": 1.9402,
27
+ "step": 6
28
+ },
29
+ {
30
+ "epoch": 0.12,
31
+ "learning_rate": 0.001,
32
+ "loss": 2.1078,
33
+ "step": 8
34
+ },
35
+ {
36
+ "epoch": 0.15,
37
+ "learning_rate": 0.001,
38
+ "loss": 1.8636,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.18,
43
+ "learning_rate": 0.001,
44
+ "loss": 1.8213,
45
+ "step": 12
46
+ },
47
+ {
48
+ "epoch": 0.21,
49
+ "learning_rate": 0.001,
50
+ "loss": 1.7018,
51
+ "step": 14
52
+ },
53
+ {
54
+ "epoch": 0.23,
55
+ "learning_rate": 0.001,
56
+ "loss": 1.6419,
57
+ "step": 16
58
+ },
59
+ {
60
+ "epoch": 0.26,
61
+ "learning_rate": 0.001,
62
+ "loss": 1.7423,
63
+ "step": 18
64
+ },
65
+ {
66
+ "epoch": 0.29,
67
+ "learning_rate": 0.001,
68
+ "loss": 1.6169,
69
+ "step": 20
70
+ },
71
+ {
72
+ "epoch": 0.32,
73
+ "learning_rate": 0.001,
74
+ "loss": 1.5792,
75
+ "step": 22
76
+ },
77
+ {
78
+ "epoch": 0.35,
79
+ "learning_rate": 0.001,
80
+ "loss": 1.5335,
81
+ "step": 24
82
+ },
83
+ {
84
+ "epoch": 0.38,
85
+ "learning_rate": 0.001,
86
+ "loss": 1.5094,
87
+ "step": 26
88
+ },
89
+ {
90
+ "epoch": 0.41,
91
+ "learning_rate": 0.001,
92
+ "loss": 1.5508,
93
+ "step": 28
94
+ },
95
+ {
96
+ "epoch": 0.44,
97
+ "learning_rate": 0.001,
98
+ "loss": 1.5831,
99
+ "step": 30
100
+ },
101
+ {
102
+ "epoch": 0.47,
103
+ "learning_rate": 0.001,
104
+ "loss": 1.5058,
105
+ "step": 32
106
+ },
107
+ {
108
+ "epoch": 0.5,
109
+ "learning_rate": 0.001,
110
+ "loss": 1.4895,
111
+ "step": 34
112
+ },
113
+ {
114
+ "epoch": 0.53,
115
+ "learning_rate": 0.001,
116
+ "loss": 1.4856,
117
+ "step": 36
118
+ },
119
+ {
120
+ "epoch": 0.56,
121
+ "learning_rate": 0.001,
122
+ "loss": 1.4648,
123
+ "step": 38
124
+ },
125
+ {
126
+ "epoch": 0.59,
127
+ "learning_rate": 0.001,
128
+ "loss": 1.4736,
129
+ "step": 40
130
+ },
131
+ {
132
+ "epoch": 0.62,
133
+ "learning_rate": 0.001,
134
+ "loss": 1.5697,
135
+ "step": 42
136
+ },
137
+ {
138
+ "epoch": 0.64,
139
+ "learning_rate": 0.001,
140
+ "loss": 1.485,
141
+ "step": 44
142
+ },
143
+ {
144
+ "epoch": 0.67,
145
+ "learning_rate": 0.001,
146
+ "loss": 1.5146,
147
+ "step": 46
148
+ },
149
+ {
150
+ "epoch": 0.7,
151
+ "learning_rate": 0.001,
152
+ "loss": 1.5171,
153
+ "step": 48
154
+ },
155
+ {
156
+ "epoch": 0.73,
157
+ "learning_rate": 0.001,
158
+ "loss": 1.5701,
159
+ "step": 50
160
+ },
161
+ {
162
+ "epoch": 0.76,
163
+ "learning_rate": 0.001,
164
+ "loss": 1.5421,
165
+ "step": 52
166
+ },
167
+ {
168
+ "epoch": 0.79,
169
+ "learning_rate": 0.001,
170
+ "loss": 1.483,
171
+ "step": 54
172
+ },
173
+ {
174
+ "epoch": 0.82,
175
+ "learning_rate": 0.001,
176
+ "loss": 1.4603,
177
+ "step": 56
178
+ },
179
+ {
180
+ "epoch": 0.85,
181
+ "learning_rate": 0.001,
182
+ "loss": 1.4263,
183
+ "step": 58
184
+ },
185
+ {
186
+ "epoch": 0.88,
187
+ "learning_rate": 0.001,
188
+ "loss": 1.4241,
189
+ "step": 60
190
+ },
191
+ {
192
+ "epoch": 0.91,
193
+ "learning_rate": 0.001,
194
+ "loss": 1.486,
195
+ "step": 62
196
+ },
197
+ {
198
+ "epoch": 0.94,
199
+ "learning_rate": 0.001,
200
+ "loss": 1.4382,
201
+ "step": 64
202
+ },
203
+ {
204
+ "epoch": 0.97,
205
+ "learning_rate": 0.001,
206
+ "loss": 1.49,
207
+ "step": 66
208
+ },
209
+ {
210
+ "epoch": 1.0,
211
+ "learning_rate": 0.001,
212
+ "loss": 1.4775,
213
+ "step": 68
214
+ },
215
+ {
216
+ "epoch": 1.0,
217
+ "eval_loss": 1.271297812461853,
218
+ "eval_runtime": 153.4507,
219
+ "eval_samples_per_second": 6.334,
220
+ "eval_steps_per_second": 0.795,
221
+ "step": 68
222
+ },
223
+ {
224
+ "epoch": 1.03,
225
+ "learning_rate": 0.001,
226
+ "loss": 1.4238,
227
+ "step": 70
228
+ },
229
+ {
230
+ "epoch": 1.06,
231
+ "learning_rate": 0.001,
232
+ "loss": 1.3785,
233
+ "step": 72
234
+ },
235
+ {
236
+ "epoch": 1.08,
237
+ "learning_rate": 0.001,
238
+ "loss": 1.3935,
239
+ "step": 74
240
+ },
241
+ {
242
+ "epoch": 1.11,
243
+ "learning_rate": 0.001,
244
+ "loss": 1.378,
245
+ "step": 76
246
+ },
247
+ {
248
+ "epoch": 1.14,
249
+ "learning_rate": 0.001,
250
+ "loss": 1.3352,
251
+ "step": 78
252
+ },
253
+ {
254
+ "epoch": 1.17,
255
+ "learning_rate": 0.001,
256
+ "loss": 1.3528,
257
+ "step": 80
258
+ },
259
+ {
260
+ "epoch": 1.2,
261
+ "learning_rate": 0.001,
262
+ "loss": 1.3692,
263
+ "step": 82
264
+ },
265
+ {
266
+ "epoch": 1.23,
267
+ "learning_rate": 0.001,
268
+ "loss": 1.3507,
269
+ "step": 84
270
+ },
271
+ {
272
+ "epoch": 1.26,
273
+ "learning_rate": 0.001,
274
+ "loss": 1.3181,
275
+ "step": 86
276
+ },
277
+ {
278
+ "epoch": 1.29,
279
+ "learning_rate": 0.001,
280
+ "loss": 1.3247,
281
+ "step": 88
282
+ },
283
+ {
284
+ "epoch": 1.32,
285
+ "learning_rate": 0.001,
286
+ "loss": 1.3432,
287
+ "step": 90
288
+ },
289
+ {
290
+ "epoch": 1.35,
291
+ "learning_rate": 0.001,
292
+ "loss": 1.3365,
293
+ "step": 92
294
+ },
295
+ {
296
+ "epoch": 1.38,
297
+ "learning_rate": 0.001,
298
+ "loss": 1.3728,
299
+ "step": 94
300
+ },
301
+ {
302
+ "epoch": 1.41,
303
+ "learning_rate": 0.001,
304
+ "loss": 1.3642,
305
+ "step": 96
306
+ },
307
+ {
308
+ "epoch": 1.44,
309
+ "learning_rate": 0.001,
310
+ "loss": 1.3179,
311
+ "step": 98
312
+ },
313
+ {
314
+ "epoch": 1.47,
315
+ "learning_rate": 0.001,
316
+ "loss": 1.313,
317
+ "step": 100
318
+ },
319
+ {
320
+ "epoch": 1.5,
321
+ "learning_rate": 0.001,
322
+ "loss": 1.3392,
323
+ "step": 102
324
+ },
325
+ {
326
+ "epoch": 1.52,
327
+ "learning_rate": 0.001,
328
+ "loss": 1.3346,
329
+ "step": 104
330
+ },
331
+ {
332
+ "epoch": 1.55,
333
+ "learning_rate": 0.001,
334
+ "loss": 1.3572,
335
+ "step": 106
336
+ },
337
+ {
338
+ "epoch": 1.58,
339
+ "learning_rate": 0.001,
340
+ "loss": 1.3391,
341
+ "step": 108
342
+ },
343
+ {
344
+ "epoch": 1.61,
345
+ "learning_rate": 0.001,
346
+ "loss": 1.3429,
347
+ "step": 110
348
+ },
349
+ {
350
+ "epoch": 1.64,
351
+ "learning_rate": 0.001,
352
+ "loss": 1.3276,
353
+ "step": 112
354
+ },
355
+ {
356
+ "epoch": 1.67,
357
+ "learning_rate": 0.001,
358
+ "loss": 1.3346,
359
+ "step": 114
360
+ },
361
+ {
362
+ "epoch": 1.7,
363
+ "learning_rate": 0.001,
364
+ "loss": 1.3235,
365
+ "step": 116
366
+ },
367
+ {
368
+ "epoch": 1.73,
369
+ "learning_rate": 0.001,
370
+ "loss": 1.3446,
371
+ "step": 118
372
+ },
373
+ {
374
+ "epoch": 1.76,
375
+ "learning_rate": 0.001,
376
+ "loss": 1.3429,
377
+ "step": 120
378
+ },
379
+ {
380
+ "epoch": 1.79,
381
+ "learning_rate": 0.001,
382
+ "loss": 1.3465,
383
+ "step": 122
384
+ },
385
+ {
386
+ "epoch": 1.82,
387
+ "learning_rate": 0.001,
388
+ "loss": 1.3436,
389
+ "step": 124
390
+ },
391
+ {
392
+ "epoch": 1.85,
393
+ "learning_rate": 0.001,
394
+ "loss": 1.316,
395
+ "step": 126
396
+ },
397
+ {
398
+ "epoch": 1.88,
399
+ "learning_rate": 0.001,
400
+ "loss": 1.3354,
401
+ "step": 128
402
+ },
403
+ {
404
+ "epoch": 1.91,
405
+ "learning_rate": 0.001,
406
+ "loss": 1.3252,
407
+ "step": 130
408
+ },
409
+ {
410
+ "epoch": 1.93,
411
+ "learning_rate": 0.001,
412
+ "loss": 1.2983,
413
+ "step": 132
414
+ },
415
+ {
416
+ "epoch": 1.96,
417
+ "learning_rate": 0.001,
418
+ "loss": 1.3305,
419
+ "step": 134
420
+ },
421
+ {
422
+ "epoch": 1.99,
423
+ "learning_rate": 0.001,
424
+ "loss": 1.3081,
425
+ "step": 136
426
+ },
427
+ {
428
+ "epoch": 1.99,
429
+ "eval_loss": 1.2379964590072632,
430
+ "eval_runtime": 153.5844,
431
+ "eval_samples_per_second": 6.329,
432
+ "eval_steps_per_second": 0.794,
433
+ "step": 136
434
+ },
435
+ {
436
+ "epoch": 2.02,
437
+ "learning_rate": 0.001,
438
+ "loss": 1.2313,
439
+ "step": 138
440
+ },
441
+ {
442
+ "epoch": 2.05,
443
+ "learning_rate": 0.001,
444
+ "loss": 1.1831,
445
+ "step": 140
446
+ },
447
+ {
448
+ "epoch": 2.08,
449
+ "learning_rate": 0.001,
450
+ "loss": 1.2066,
451
+ "step": 142
452
+ },
453
+ {
454
+ "epoch": 2.11,
455
+ "learning_rate": 0.001,
456
+ "loss": 1.1643,
457
+ "step": 144
458
+ },
459
+ {
460
+ "epoch": 2.14,
461
+ "learning_rate": 0.001,
462
+ "loss": 1.1896,
463
+ "step": 146
464
+ },
465
+ {
466
+ "epoch": 2.17,
467
+ "learning_rate": 0.001,
468
+ "loss": 1.2158,
469
+ "step": 148
470
+ },
471
+ {
472
+ "epoch": 2.2,
473
+ "learning_rate": 0.001,
474
+ "loss": 1.1846,
475
+ "step": 150
476
+ },
477
+ {
478
+ "epoch": 2.23,
479
+ "learning_rate": 0.001,
480
+ "loss": 1.1914,
481
+ "step": 152
482
+ },
483
+ {
484
+ "epoch": 2.26,
485
+ "learning_rate": 0.001,
486
+ "loss": 1.1673,
487
+ "step": 154
488
+ },
489
+ {
490
+ "epoch": 2.29,
491
+ "learning_rate": 0.001,
492
+ "loss": 1.1649,
493
+ "step": 156
494
+ },
495
+ {
496
+ "epoch": 2.32,
497
+ "learning_rate": 0.001,
498
+ "loss": 1.1992,
499
+ "step": 158
500
+ },
501
+ {
502
+ "epoch": 2.35,
503
+ "learning_rate": 0.001,
504
+ "loss": 1.1898,
505
+ "step": 160
506
+ },
507
+ {
508
+ "epoch": 2.37,
509
+ "learning_rate": 0.001,
510
+ "loss": 1.1869,
511
+ "step": 162
512
+ },
513
+ {
514
+ "epoch": 2.4,
515
+ "learning_rate": 0.001,
516
+ "loss": 1.2013,
517
+ "step": 164
518
+ },
519
+ {
520
+ "epoch": 2.43,
521
+ "learning_rate": 0.001,
522
+ "loss": 1.1587,
523
+ "step": 166
524
+ },
525
+ {
526
+ "epoch": 2.46,
527
+ "learning_rate": 0.001,
528
+ "loss": 1.1765,
529
+ "step": 168
530
+ },
531
+ {
532
+ "epoch": 2.49,
533
+ "learning_rate": 0.001,
534
+ "loss": 1.1673,
535
+ "step": 170
536
+ },
537
+ {
538
+ "epoch": 2.52,
539
+ "learning_rate": 0.001,
540
+ "loss": 1.1936,
541
+ "step": 172
542
+ },
543
+ {
544
+ "epoch": 2.55,
545
+ "learning_rate": 0.001,
546
+ "loss": 1.1892,
547
+ "step": 174
548
+ },
549
+ {
550
+ "epoch": 2.58,
551
+ "learning_rate": 0.001,
552
+ "loss": 1.1734,
553
+ "step": 176
554
+ },
555
+ {
556
+ "epoch": 2.61,
557
+ "learning_rate": 0.001,
558
+ "loss": 1.1765,
559
+ "step": 178
560
+ },
561
+ {
562
+ "epoch": 2.64,
563
+ "learning_rate": 0.001,
564
+ "loss": 1.1952,
565
+ "step": 180
566
+ },
567
+ {
568
+ "epoch": 2.67,
569
+ "learning_rate": 0.001,
570
+ "loss": 1.217,
571
+ "step": 182
572
+ },
573
+ {
574
+ "epoch": 2.7,
575
+ "learning_rate": 0.001,
576
+ "loss": 1.2099,
577
+ "step": 184
578
+ },
579
+ {
580
+ "epoch": 2.73,
581
+ "learning_rate": 0.001,
582
+ "loss": 1.1728,
583
+ "step": 186
584
+ },
585
+ {
586
+ "epoch": 2.76,
587
+ "learning_rate": 0.001,
588
+ "loss": 1.1885,
589
+ "step": 188
590
+ },
591
+ {
592
+ "epoch": 2.79,
593
+ "learning_rate": 0.001,
594
+ "loss": 1.1913,
595
+ "step": 190
596
+ },
597
+ {
598
+ "epoch": 2.81,
599
+ "learning_rate": 0.001,
600
+ "loss": 1.2063,
601
+ "step": 192
602
+ },
603
+ {
604
+ "epoch": 2.84,
605
+ "learning_rate": 0.001,
606
+ "loss": 1.1895,
607
+ "step": 194
608
+ },
609
+ {
610
+ "epoch": 2.87,
611
+ "learning_rate": 0.001,
612
+ "loss": 1.2323,
613
+ "step": 196
614
+ },
615
+ {
616
+ "epoch": 2.9,
617
+ "learning_rate": 0.001,
618
+ "loss": 1.2043,
619
+ "step": 198
620
+ },
621
+ {
622
+ "epoch": 2.93,
623
+ "learning_rate": 0.001,
624
+ "loss": 1.1987,
625
+ "step": 200
626
+ },
627
+ {
628
+ "epoch": 2.96,
629
+ "learning_rate": 0.001,
630
+ "loss": 1.1732,
631
+ "step": 202
632
+ },
633
+ {
634
+ "epoch": 2.99,
635
+ "learning_rate": 0.001,
636
+ "loss": 1.1811,
637
+ "step": 204
638
+ },
639
+ {
640
+ "epoch": 2.99,
641
+ "eval_loss": 1.2455540895462036,
642
+ "eval_runtime": 153.2109,
643
+ "eval_samples_per_second": 6.344,
644
+ "eval_steps_per_second": 0.796,
645
+ "step": 204
646
+ },
647
+ {
648
+ "epoch": 3.02,
649
+ "learning_rate": 0.001,
650
+ "loss": 1.0865,
651
+ "step": 206
652
+ },
653
+ {
654
+ "epoch": 3.05,
655
+ "learning_rate": 0.001,
656
+ "loss": 1.0674,
657
+ "step": 208
658
+ },
659
+ {
660
+ "epoch": 3.08,
661
+ "learning_rate": 0.001,
662
+ "loss": 1.0233,
663
+ "step": 210
664
+ },
665
+ {
666
+ "epoch": 3.11,
667
+ "learning_rate": 0.001,
668
+ "loss": 1.0369,
669
+ "step": 212
670
+ },
671
+ {
672
+ "epoch": 3.14,
673
+ "learning_rate": 0.001,
674
+ "loss": 1.0632,
675
+ "step": 214
676
+ },
677
+ {
678
+ "epoch": 3.17,
679
+ "learning_rate": 0.001,
680
+ "loss": 1.0417,
681
+ "step": 216
682
+ },
683
+ {
684
+ "epoch": 3.2,
685
+ "learning_rate": 0.001,
686
+ "loss": 1.0477,
687
+ "step": 218
688
+ },
689
+ {
690
+ "epoch": 3.22,
691
+ "learning_rate": 0.001,
692
+ "loss": 1.0429,
693
+ "step": 220
694
+ },
695
+ {
696
+ "epoch": 3.25,
697
+ "learning_rate": 0.001,
698
+ "loss": 1.0446,
699
+ "step": 222
700
+ },
701
+ {
702
+ "epoch": 3.28,
703
+ "learning_rate": 0.001,
704
+ "loss": 1.0587,
705
+ "step": 224
706
+ },
707
+ {
708
+ "epoch": 3.31,
709
+ "learning_rate": 0.001,
710
+ "loss": 1.0881,
711
+ "step": 226
712
+ },
713
+ {
714
+ "epoch": 3.34,
715
+ "learning_rate": 0.001,
716
+ "loss": 1.062,
717
+ "step": 228
718
+ },
719
+ {
720
+ "epoch": 3.37,
721
+ "learning_rate": 0.001,
722
+ "loss": 1.0618,
723
+ "step": 230
724
+ },
725
+ {
726
+ "epoch": 3.4,
727
+ "learning_rate": 0.001,
728
+ "loss": 1.0801,
729
+ "step": 232
730
+ },
731
+ {
732
+ "epoch": 3.43,
733
+ "learning_rate": 0.001,
734
+ "loss": 1.0601,
735
+ "step": 234
736
+ },
737
+ {
738
+ "epoch": 3.46,
739
+ "learning_rate": 0.001,
740
+ "loss": 1.0444,
741
+ "step": 236
742
+ },
743
+ {
744
+ "epoch": 3.49,
745
+ "learning_rate": 0.001,
746
+ "loss": 1.052,
747
+ "step": 238
748
+ },
749
+ {
750
+ "epoch": 3.52,
751
+ "learning_rate": 0.001,
752
+ "loss": 1.0677,
753
+ "step": 240
754
+ },
755
+ {
756
+ "epoch": 3.55,
757
+ "learning_rate": 0.001,
758
+ "loss": 1.074,
759
+ "step": 242
760
+ },
761
+ {
762
+ "epoch": 3.58,
763
+ "learning_rate": 0.001,
764
+ "loss": 1.0589,
765
+ "step": 244
766
+ },
767
+ {
768
+ "epoch": 3.61,
769
+ "learning_rate": 0.001,
770
+ "loss": 1.0767,
771
+ "step": 246
772
+ },
773
+ {
774
+ "epoch": 3.64,
775
+ "learning_rate": 0.001,
776
+ "loss": 1.094,
777
+ "step": 248
778
+ },
779
+ {
780
+ "epoch": 3.66,
781
+ "learning_rate": 0.001,
782
+ "loss": 1.0783,
783
+ "step": 250
784
+ },
785
+ {
786
+ "epoch": 3.69,
787
+ "learning_rate": 0.001,
788
+ "loss": 1.0683,
789
+ "step": 252
790
+ },
791
+ {
792
+ "epoch": 3.72,
793
+ "learning_rate": 0.001,
794
+ "loss": 1.0594,
795
+ "step": 254
796
+ },
797
+ {
798
+ "epoch": 3.75,
799
+ "learning_rate": 0.001,
800
+ "loss": 1.063,
801
+ "step": 256
802
+ },
803
+ {
804
+ "epoch": 3.78,
805
+ "learning_rate": 0.001,
806
+ "loss": 1.0745,
807
+ "step": 258
808
+ },
809
+ {
810
+ "epoch": 3.81,
811
+ "learning_rate": 0.001,
812
+ "loss": 1.104,
813
+ "step": 260
814
+ },
815
+ {
816
+ "epoch": 3.84,
817
+ "learning_rate": 0.001,
818
+ "loss": 1.074,
819
+ "step": 262
820
+ },
821
+ {
822
+ "epoch": 3.87,
823
+ "learning_rate": 0.001,
824
+ "loss": 1.0787,
825
+ "step": 264
826
+ },
827
+ {
828
+ "epoch": 3.9,
829
+ "learning_rate": 0.001,
830
+ "loss": 1.0848,
831
+ "step": 266
832
+ },
833
+ {
834
+ "epoch": 3.93,
835
+ "learning_rate": 0.001,
836
+ "loss": 1.0724,
837
+ "step": 268
838
+ },
839
+ {
840
+ "epoch": 3.96,
841
+ "learning_rate": 0.001,
842
+ "loss": 1.0703,
843
+ "step": 270
844
+ },
845
+ {
846
+ "epoch": 3.99,
847
+ "learning_rate": 0.001,
848
+ "loss": 1.0752,
849
+ "step": 272
850
+ },
851
+ {
852
+ "epoch": 3.99,
853
+ "eval_loss": 1.2426340579986572,
854
+ "eval_runtime": 153.6259,
855
+ "eval_samples_per_second": 6.327,
856
+ "eval_steps_per_second": 0.794,
857
+ "step": 272
858
+ },
859
+ {
860
+ "epoch": 4.02,
861
+ "learning_rate": 0.001,
862
+ "loss": 0.988,
863
+ "step": 274
864
+ },
865
+ {
866
+ "epoch": 4.05,
867
+ "learning_rate": 0.001,
868
+ "loss": 0.9078,
869
+ "step": 276
870
+ },
871
+ {
872
+ "epoch": 4.08,
873
+ "learning_rate": 0.001,
874
+ "loss": 0.9303,
875
+ "step": 278
876
+ },
877
+ {
878
+ "epoch": 4.1,
879
+ "learning_rate": 0.001,
880
+ "loss": 0.926,
881
+ "step": 280
882
+ },
883
+ {
884
+ "epoch": 4.13,
885
+ "learning_rate": 0.001,
886
+ "loss": 0.9451,
887
+ "step": 282
888
+ },
889
+ {
890
+ "epoch": 4.16,
891
+ "learning_rate": 0.001,
892
+ "loss": 0.9417,
893
+ "step": 284
894
+ },
895
+ {
896
+ "epoch": 4.19,
897
+ "learning_rate": 0.001,
898
+ "loss": 0.9242,
899
+ "step": 286
900
+ },
901
+ {
902
+ "epoch": 4.22,
903
+ "learning_rate": 0.001,
904
+ "loss": 0.9395,
905
+ "step": 288
906
+ },
907
+ {
908
+ "epoch": 4.25,
909
+ "learning_rate": 0.001,
910
+ "loss": 0.9411,
911
+ "step": 290
912
+ },
913
+ {
914
+ "epoch": 4.28,
915
+ "learning_rate": 0.001,
916
+ "loss": 0.9406,
917
+ "step": 292
918
+ },
919
+ {
920
+ "epoch": 4.31,
921
+ "learning_rate": 0.001,
922
+ "loss": 0.9396,
923
+ "step": 294
924
+ },
925
+ {
926
+ "epoch": 4.34,
927
+ "learning_rate": 0.001,
928
+ "loss": 0.9293,
929
+ "step": 296
930
+ },
931
+ {
932
+ "epoch": 4.37,
933
+ "learning_rate": 0.001,
934
+ "loss": 0.9533,
935
+ "step": 298
936
+ },
937
+ {
938
+ "epoch": 4.4,
939
+ "learning_rate": 0.001,
940
+ "loss": 0.9388,
941
+ "step": 300
942
+ },
943
+ {
944
+ "epoch": 4.43,
945
+ "learning_rate": 0.001,
946
+ "loss": 0.955,
947
+ "step": 302
948
+ },
949
+ {
950
+ "epoch": 4.46,
951
+ "learning_rate": 0.001,
952
+ "loss": 0.939,
953
+ "step": 304
954
+ },
955
+ {
956
+ "epoch": 4.49,
957
+ "learning_rate": 0.001,
958
+ "loss": 0.9381,
959
+ "step": 306
960
+ },
961
+ {
962
+ "epoch": 4.51,
963
+ "learning_rate": 0.001,
964
+ "loss": 0.9505,
965
+ "step": 308
966
+ },
967
+ {
968
+ "epoch": 4.54,
969
+ "learning_rate": 0.001,
970
+ "loss": 0.9654,
971
+ "step": 310
972
+ },
973
+ {
974
+ "epoch": 4.57,
975
+ "learning_rate": 0.001,
976
+ "loss": 0.9406,
977
+ "step": 312
978
+ },
979
+ {
980
+ "epoch": 4.6,
981
+ "learning_rate": 0.001,
982
+ "loss": 0.9684,
983
+ "step": 314
984
+ },
985
+ {
986
+ "epoch": 4.63,
987
+ "learning_rate": 0.001,
988
+ "loss": 0.948,
989
+ "step": 316
990
+ },
991
+ {
992
+ "epoch": 4.66,
993
+ "learning_rate": 0.001,
994
+ "loss": 0.9688,
995
+ "step": 318
996
+ },
997
+ {
998
+ "epoch": 4.69,
999
+ "learning_rate": 0.001,
1000
+ "loss": 0.9462,
1001
+ "step": 320
1002
+ },
1003
+ {
1004
+ "epoch": 4.72,
1005
+ "learning_rate": 0.001,
1006
+ "loss": 0.9646,
1007
+ "step": 322
1008
+ },
1009
+ {
1010
+ "epoch": 4.75,
1011
+ "learning_rate": 0.001,
1012
+ "loss": 0.9637,
1013
+ "step": 324
1014
+ },
1015
+ {
1016
+ "epoch": 4.78,
1017
+ "learning_rate": 0.001,
1018
+ "loss": 0.9689,
1019
+ "step": 326
1020
+ },
1021
+ {
1022
+ "epoch": 4.81,
1023
+ "learning_rate": 0.001,
1024
+ "loss": 0.9757,
1025
+ "step": 328
1026
+ },
1027
+ {
1028
+ "epoch": 4.84,
1029
+ "learning_rate": 0.001,
1030
+ "loss": 0.9552,
1031
+ "step": 330
1032
+ },
1033
+ {
1034
+ "epoch": 4.87,
1035
+ "learning_rate": 0.001,
1036
+ "loss": 0.9662,
1037
+ "step": 332
1038
+ },
1039
+ {
1040
+ "epoch": 4.9,
1041
+ "learning_rate": 0.001,
1042
+ "loss": 0.96,
1043
+ "step": 334
1044
+ },
1045
+ {
1046
+ "epoch": 4.93,
1047
+ "learning_rate": 0.001,
1048
+ "loss": 0.9584,
1049
+ "step": 336
1050
+ },
1051
+ {
1052
+ "epoch": 4.95,
1053
+ "learning_rate": 0.001,
1054
+ "loss": 0.9694,
1055
+ "step": 338
1056
+ },
1057
+ {
1058
+ "epoch": 4.98,
1059
+ "learning_rate": 0.001,
1060
+ "loss": 0.9663,
1061
+ "step": 340
1062
+ },
1063
+ {
1064
+ "epoch": 5.0,
1065
+ "eval_loss": 1.2900694608688354,
1066
+ "eval_runtime": 153.609,
1067
+ "eval_samples_per_second": 6.328,
1068
+ "eval_steps_per_second": 0.794,
1069
+ "step": 341
1070
+ },
1071
+ {
1072
+ "epoch": 5.01,
1073
+ "learning_rate": 0.001,
1074
+ "loss": 0.8915,
1075
+ "step": 342
1076
+ },
1077
+ {
1078
+ "epoch": 5.04,
1079
+ "learning_rate": 0.001,
1080
+ "loss": 0.8169,
1081
+ "step": 344
1082
+ },
1083
+ {
1084
+ "epoch": 5.07,
1085
+ "learning_rate": 0.001,
1086
+ "loss": 0.8109,
1087
+ "step": 346
1088
+ },
1089
+ {
1090
+ "epoch": 5.1,
1091
+ "learning_rate": 0.001,
1092
+ "loss": 0.8339,
1093
+ "step": 348
1094
+ },
1095
+ {
1096
+ "epoch": 5.13,
1097
+ "learning_rate": 0.001,
1098
+ "loss": 0.8303,
1099
+ "step": 350
1100
+ },
1101
+ {
1102
+ "epoch": 5.16,
1103
+ "learning_rate": 0.001,
1104
+ "loss": 0.8237,
1105
+ "step": 352
1106
+ },
1107
+ {
1108
+ "epoch": 5.19,
1109
+ "learning_rate": 0.001,
1110
+ "loss": 0.8227,
1111
+ "step": 354
1112
+ },
1113
+ {
1114
+ "epoch": 5.22,
1115
+ "learning_rate": 0.001,
1116
+ "loss": 0.8495,
1117
+ "step": 356
1118
+ },
1119
+ {
1120
+ "epoch": 5.25,
1121
+ "learning_rate": 0.001,
1122
+ "loss": 0.8487,
1123
+ "step": 358
1124
+ },
1125
+ {
1126
+ "epoch": 5.28,
1127
+ "learning_rate": 0.001,
1128
+ "loss": 0.8412,
1129
+ "step": 360
1130
+ },
1131
+ {
1132
+ "epoch": 5.31,
1133
+ "learning_rate": 0.001,
1134
+ "loss": 0.8089,
1135
+ "step": 362
1136
+ },
1137
+ {
1138
+ "epoch": 5.34,
1139
+ "learning_rate": 0.001,
1140
+ "loss": 0.838,
1141
+ "step": 364
1142
+ },
1143
+ {
1144
+ "epoch": 5.37,
1145
+ "learning_rate": 0.001,
1146
+ "loss": 0.8485,
1147
+ "step": 366
1148
+ },
1149
+ {
1150
+ "epoch": 5.39,
1151
+ "learning_rate": 0.001,
1152
+ "loss": 0.8291,
1153
+ "step": 368
1154
+ },
1155
+ {
1156
+ "epoch": 5.42,
1157
+ "learning_rate": 0.001,
1158
+ "loss": 0.8407,
1159
+ "step": 370
1160
+ },
1161
+ {
1162
+ "epoch": 5.45,
1163
+ "learning_rate": 0.001,
1164
+ "loss": 0.852,
1165
+ "step": 372
1166
+ },
1167
+ {
1168
+ "epoch": 5.48,
1169
+ "learning_rate": 0.001,
1170
+ "loss": 0.8438,
1171
+ "step": 374
1172
+ },
1173
+ {
1174
+ "epoch": 5.51,
1175
+ "learning_rate": 0.001,
1176
+ "loss": 0.849,
1177
+ "step": 376
1178
+ },
1179
+ {
1180
+ "epoch": 5.54,
1181
+ "learning_rate": 0.001,
1182
+ "loss": 0.8397,
1183
+ "step": 378
1184
+ },
1185
+ {
1186
+ "epoch": 5.57,
1187
+ "learning_rate": 0.001,
1188
+ "loss": 0.8717,
1189
+ "step": 380
1190
+ },
1191
+ {
1192
+ "epoch": 5.6,
1193
+ "learning_rate": 0.001,
1194
+ "loss": 0.8536,
1195
+ "step": 382
1196
+ },
1197
+ {
1198
+ "epoch": 5.63,
1199
+ "learning_rate": 0.001,
1200
+ "loss": 0.8602,
1201
+ "step": 384
1202
+ },
1203
+ {
1204
+ "epoch": 5.66,
1205
+ "learning_rate": 0.001,
1206
+ "loss": 0.8661,
1207
+ "step": 386
1208
+ },
1209
+ {
1210
+ "epoch": 5.69,
1211
+ "learning_rate": 0.001,
1212
+ "loss": 0.8613,
1213
+ "step": 388
1214
+ },
1215
+ {
1216
+ "epoch": 5.72,
1217
+ "learning_rate": 0.001,
1218
+ "loss": 0.8651,
1219
+ "step": 390
1220
+ },
1221
+ {
1222
+ "epoch": 5.75,
1223
+ "learning_rate": 0.001,
1224
+ "loss": 0.8626,
1225
+ "step": 392
1226
+ },
1227
+ {
1228
+ "epoch": 5.78,
1229
+ "learning_rate": 0.001,
1230
+ "loss": 0.8669,
1231
+ "step": 394
1232
+ },
1233
+ {
1234
+ "epoch": 5.8,
1235
+ "learning_rate": 0.001,
1236
+ "loss": 0.8642,
1237
+ "step": 396
1238
+ },
1239
+ {
1240
+ "epoch": 5.83,
1241
+ "learning_rate": 0.001,
1242
+ "loss": 0.8689,
1243
+ "step": 398
1244
+ },
1245
+ {
1246
+ "epoch": 5.86,
1247
+ "learning_rate": 0.001,
1248
+ "loss": 0.8696,
1249
+ "step": 400
1250
+ },
1251
+ {
1252
+ "epoch": 5.89,
1253
+ "learning_rate": 0.001,
1254
+ "loss": 0.8443,
1255
+ "step": 402
1256
+ },
1257
+ {
1258
+ "epoch": 5.92,
1259
+ "learning_rate": 0.001,
1260
+ "loss": 0.8539,
1261
+ "step": 404
1262
+ },
1263
+ {
1264
+ "epoch": 5.95,
1265
+ "learning_rate": 0.001,
1266
+ "loss": 0.8647,
1267
+ "step": 406
1268
+ },
1269
+ {
1270
+ "epoch": 5.98,
1271
+ "learning_rate": 0.001,
1272
+ "loss": 0.8607,
1273
+ "step": 408
1274
+ },
1275
+ {
1276
+ "epoch": 6.0,
1277
+ "eval_loss": 1.3395987749099731,
1278
+ "eval_runtime": 153.1153,
1279
+ "eval_samples_per_second": 6.348,
1280
+ "eval_steps_per_second": 0.797,
1281
+ "step": 409
1282
+ },
1283
+ {
1284
+ "epoch": 6.01,
1285
+ "learning_rate": 0.001,
1286
+ "loss": 0.8252,
1287
+ "step": 410
1288
+ },
1289
+ {
1290
+ "epoch": 6.04,
1291
+ "learning_rate": 0.001,
1292
+ "loss": 0.7173,
1293
+ "step": 412
1294
+ },
1295
+ {
1296
+ "epoch": 6.07,
1297
+ "learning_rate": 0.001,
1298
+ "loss": 0.7206,
1299
+ "step": 414
1300
+ },
1301
+ {
1302
+ "epoch": 6.1,
1303
+ "learning_rate": 0.001,
1304
+ "loss": 0.7364,
1305
+ "step": 416
1306
+ },
1307
+ {
1308
+ "epoch": 6.13,
1309
+ "learning_rate": 0.001,
1310
+ "loss": 0.7132,
1311
+ "step": 418
1312
+ },
1313
+ {
1314
+ "epoch": 6.16,
1315
+ "learning_rate": 0.001,
1316
+ "loss": 0.7353,
1317
+ "step": 420
1318
+ },
1319
+ {
1320
+ "epoch": 6.19,
1321
+ "learning_rate": 0.001,
1322
+ "loss": 0.7392,
1323
+ "step": 422
1324
+ },
1325
+ {
1326
+ "epoch": 6.22,
1327
+ "learning_rate": 0.001,
1328
+ "loss": 0.7394,
1329
+ "step": 424
1330
+ },
1331
+ {
1332
+ "epoch": 6.24,
1333
+ "learning_rate": 0.001,
1334
+ "loss": 0.7684,
1335
+ "step": 426
1336
+ },
1337
+ {
1338
+ "epoch": 6.27,
1339
+ "learning_rate": 0.001,
1340
+ "loss": 0.7543,
1341
+ "step": 428
1342
+ },
1343
+ {
1344
+ "epoch": 6.3,
1345
+ "learning_rate": 0.001,
1346
+ "loss": 0.7392,
1347
+ "step": 430
1348
+ },
1349
+ {
1350
+ "epoch": 6.33,
1351
+ "learning_rate": 0.001,
1352
+ "loss": 0.7445,
1353
+ "step": 432
1354
+ },
1355
+ {
1356
+ "epoch": 6.36,
1357
+ "learning_rate": 0.001,
1358
+ "loss": 0.7773,
1359
+ "step": 434
1360
+ },
1361
+ {
1362
+ "epoch": 6.39,
1363
+ "learning_rate": 0.001,
1364
+ "loss": 0.7469,
1365
+ "step": 436
1366
+ },
1367
+ {
1368
+ "epoch": 6.42,
1369
+ "learning_rate": 0.001,
1370
+ "loss": 0.7275,
1371
+ "step": 438
1372
+ },
1373
+ {
1374
+ "epoch": 6.45,
1375
+ "learning_rate": 0.001,
1376
+ "loss": 0.7775,
1377
+ "step": 440
1378
+ },
1379
+ {
1380
+ "epoch": 6.48,
1381
+ "learning_rate": 0.001,
1382
+ "loss": 0.7301,
1383
+ "step": 442
1384
+ },
1385
+ {
1386
+ "epoch": 6.51,
1387
+ "learning_rate": 0.001,
1388
+ "loss": 0.7491,
1389
+ "step": 444
1390
+ },
1391
+ {
1392
+ "epoch": 6.54,
1393
+ "learning_rate": 0.001,
1394
+ "loss": 0.7475,
1395
+ "step": 446
1396
+ },
1397
+ {
1398
+ "epoch": 6.57,
1399
+ "learning_rate": 0.001,
1400
+ "loss": 0.7629,
1401
+ "step": 448
1402
+ },
1403
+ {
1404
+ "epoch": 6.6,
1405
+ "learning_rate": 0.001,
1406
+ "loss": 0.7667,
1407
+ "step": 450
1408
+ },
1409
+ {
1410
+ "epoch": 6.63,
1411
+ "learning_rate": 0.001,
1412
+ "loss": 0.7558,
1413
+ "step": 452
1414
+ },
1415
+ {
1416
+ "epoch": 6.66,
1417
+ "learning_rate": 0.001,
1418
+ "loss": 0.7604,
1419
+ "step": 454
1420
+ },
1421
+ {
1422
+ "epoch": 6.68,
1423
+ "learning_rate": 0.001,
1424
+ "loss": 0.7602,
1425
+ "step": 456
1426
+ },
1427
+ {
1428
+ "epoch": 6.71,
1429
+ "learning_rate": 0.001,
1430
+ "loss": 0.7781,
1431
+ "step": 458
1432
+ },
1433
+ {
1434
+ "epoch": 6.74,
1435
+ "learning_rate": 0.001,
1436
+ "loss": 0.7619,
1437
+ "step": 460
1438
+ },
1439
+ {
1440
+ "epoch": 6.77,
1441
+ "learning_rate": 0.001,
1442
+ "loss": 0.7577,
1443
+ "step": 462
1444
+ },
1445
+ {
1446
+ "epoch": 6.8,
1447
+ "learning_rate": 0.001,
1448
+ "loss": 0.7469,
1449
+ "step": 464
1450
+ },
1451
+ {
1452
+ "epoch": 6.83,
1453
+ "learning_rate": 0.001,
1454
+ "loss": 0.7438,
1455
+ "step": 466
1456
+ },
1457
+ {
1458
+ "epoch": 6.86,
1459
+ "learning_rate": 0.001,
1460
+ "loss": 0.765,
1461
+ "step": 468
1462
+ },
1463
+ {
1464
+ "epoch": 6.89,
1465
+ "learning_rate": 0.001,
1466
+ "loss": 0.7336,
1467
+ "step": 470
1468
+ },
1469
+ {
1470
+ "epoch": 6.92,
1471
+ "learning_rate": 0.001,
1472
+ "loss": 0.7441,
1473
+ "step": 472
1474
+ },
1475
+ {
1476
+ "epoch": 6.95,
1477
+ "learning_rate": 0.001,
1478
+ "loss": 0.7552,
1479
+ "step": 474
1480
+ },
1481
+ {
1482
+ "epoch": 6.98,
1483
+ "learning_rate": 0.001,
1484
+ "loss": 0.7462,
1485
+ "step": 476
1486
+ },
1487
+ {
1488
+ "epoch": 6.99,
1489
+ "eval_loss": 1.3746581077575684,
1490
+ "eval_runtime": 153.643,
1491
+ "eval_samples_per_second": 6.326,
1492
+ "eval_steps_per_second": 0.794,
1493
+ "step": 477
1494
+ },
1495
+ {
1496
+ "epoch": 7.01,
1497
+ "learning_rate": 0.001,
1498
+ "loss": 0.7543,
1499
+ "step": 478
1500
+ },
1501
+ {
1502
+ "epoch": 7.04,
1503
+ "learning_rate": 0.001,
1504
+ "loss": 0.6377,
1505
+ "step": 480
1506
+ },
1507
+ {
1508
+ "epoch": 7.07,
1509
+ "learning_rate": 0.001,
1510
+ "loss": 0.6342,
1511
+ "step": 482
1512
+ },
1513
+ {
1514
+ "epoch": 7.09,
1515
+ "learning_rate": 0.001,
1516
+ "loss": 0.6417,
1517
+ "step": 484
1518
+ },
1519
+ {
1520
+ "epoch": 7.12,
1521
+ "learning_rate": 0.001,
1522
+ "loss": 0.6428,
1523
+ "step": 486
1524
+ },
1525
+ {
1526
+ "epoch": 7.15,
1527
+ "learning_rate": 0.001,
1528
+ "loss": 0.6378,
1529
+ "step": 488
1530
+ },
1531
+ {
1532
+ "epoch": 7.18,
1533
+ "learning_rate": 0.001,
1534
+ "loss": 0.6354,
1535
+ "step": 490
1536
+ },
1537
+ {
1538
+ "epoch": 7.21,
1539
+ "learning_rate": 0.001,
1540
+ "loss": 0.6492,
1541
+ "step": 492
1542
+ },
1543
+ {
1544
+ "epoch": 7.24,
1545
+ "learning_rate": 0.001,
1546
+ "loss": 0.643,
1547
+ "step": 494
1548
+ },
1549
+ {
1550
+ "epoch": 7.27,
1551
+ "learning_rate": 0.001,
1552
+ "loss": 0.65,
1553
+ "step": 496
1554
+ },
1555
+ {
1556
+ "epoch": 7.3,
1557
+ "learning_rate": 0.001,
1558
+ "loss": 0.6553,
1559
+ "step": 498
1560
+ },
1561
+ {
1562
+ "epoch": 7.33,
1563
+ "learning_rate": 0.001,
1564
+ "loss": 0.6565,
1565
+ "step": 500
1566
+ },
1567
+ {
1568
+ "epoch": 7.36,
1569
+ "learning_rate": 0.001,
1570
+ "loss": 0.6603,
1571
+ "step": 502
1572
+ },
1573
+ {
1574
+ "epoch": 7.39,
1575
+ "learning_rate": 0.001,
1576
+ "loss": 0.6753,
1577
+ "step": 504
1578
+ },
1579
+ {
1580
+ "epoch": 7.42,
1581
+ "learning_rate": 0.001,
1582
+ "loss": 0.646,
1583
+ "step": 506
1584
+ },
1585
+ {
1586
+ "epoch": 7.45,
1587
+ "learning_rate": 0.001,
1588
+ "loss": 0.6468,
1589
+ "step": 508
1590
+ },
1591
+ {
1592
+ "epoch": 7.48,
1593
+ "learning_rate": 0.001,
1594
+ "loss": 0.6393,
1595
+ "step": 510
1596
+ },
1597
+ {
1598
+ "epoch": 7.51,
1599
+ "learning_rate": 0.001,
1600
+ "loss": 0.6594,
1601
+ "step": 512
1602
+ },
1603
+ {
1604
+ "epoch": 7.53,
1605
+ "learning_rate": 0.001,
1606
+ "loss": 0.6491,
1607
+ "step": 514
1608
+ },
1609
+ {
1610
+ "epoch": 7.56,
1611
+ "learning_rate": 0.001,
1612
+ "loss": 0.6517,
1613
+ "step": 516
1614
+ },
1615
+ {
1616
+ "epoch": 7.59,
1617
+ "learning_rate": 0.001,
1618
+ "loss": 0.66,
1619
+ "step": 518
1620
+ },
1621
+ {
1622
+ "epoch": 7.62,
1623
+ "learning_rate": 0.001,
1624
+ "loss": 0.6743,
1625
+ "step": 520
1626
+ },
1627
+ {
1628
+ "epoch": 7.65,
1629
+ "learning_rate": 0.001,
1630
+ "loss": 0.6568,
1631
+ "step": 522
1632
+ },
1633
+ {
1634
+ "epoch": 7.68,
1635
+ "learning_rate": 0.001,
1636
+ "loss": 0.6705,
1637
+ "step": 524
1638
+ },
1639
+ {
1640
+ "epoch": 7.71,
1641
+ "learning_rate": 0.001,
1642
+ "loss": 0.6793,
1643
+ "step": 526
1644
+ },
1645
+ {
1646
+ "epoch": 7.74,
1647
+ "learning_rate": 0.001,
1648
+ "loss": 0.6717,
1649
+ "step": 528
1650
+ },
1651
+ {
1652
+ "epoch": 7.77,
1653
+ "learning_rate": 0.001,
1654
+ "loss": 0.6836,
1655
+ "step": 530
1656
+ },
1657
+ {
1658
+ "epoch": 7.8,
1659
+ "learning_rate": 0.001,
1660
+ "loss": 0.6635,
1661
+ "step": 532
1662
+ },
1663
+ {
1664
+ "epoch": 7.83,
1665
+ "learning_rate": 0.001,
1666
+ "loss": 0.6762,
1667
+ "step": 534
1668
+ },
1669
+ {
1670
+ "epoch": 7.86,
1671
+ "learning_rate": 0.001,
1672
+ "loss": 0.6787,
1673
+ "step": 536
1674
+ },
1675
+ {
1676
+ "epoch": 7.89,
1677
+ "learning_rate": 0.001,
1678
+ "loss": 0.6886,
1679
+ "step": 538
1680
+ },
1681
+ {
1682
+ "epoch": 7.92,
1683
+ "learning_rate": 0.001,
1684
+ "loss": 0.6827,
1685
+ "step": 540
1686
+ },
1687
+ {
1688
+ "epoch": 7.95,
1689
+ "learning_rate": 0.001,
1690
+ "loss": 0.7047,
1691
+ "step": 542
1692
+ },
1693
+ {
1694
+ "epoch": 7.97,
1695
+ "learning_rate": 0.001,
1696
+ "loss": 0.7084,
1697
+ "step": 544
1698
+ },
1699
+ {
1700
+ "epoch": 7.99,
1701
+ "eval_loss": 1.4659099578857422,
1702
+ "eval_runtime": 153.344,
1703
+ "eval_samples_per_second": 6.339,
1704
+ "eval_steps_per_second": 0.796,
1705
+ "step": 545
1706
+ },
1707
+ {
1708
+ "epoch": 8.0,
1709
+ "learning_rate": 0.001,
1710
+ "loss": 0.6625,
1711
+ "step": 546
1712
+ },
1713
+ {
1714
+ "epoch": 8.03,
1715
+ "learning_rate": 0.001,
1716
+ "loss": 0.55,
1717
+ "step": 548
1718
+ },
1719
+ {
1720
+ "epoch": 8.06,
1721
+ "learning_rate": 0.001,
1722
+ "loss": 0.5624,
1723
+ "step": 550
1724
+ },
1725
+ {
1726
+ "epoch": 8.09,
1727
+ "learning_rate": 0.001,
1728
+ "loss": 0.5566,
1729
+ "step": 552
1730
+ },
1731
+ {
1732
+ "epoch": 8.12,
1733
+ "learning_rate": 0.001,
1734
+ "loss": 0.5603,
1735
+ "step": 554
1736
+ },
1737
+ {
1738
+ "epoch": 8.15,
1739
+ "learning_rate": 0.001,
1740
+ "loss": 0.5613,
1741
+ "step": 556
1742
+ },
1743
+ {
1744
+ "epoch": 8.18,
1745
+ "learning_rate": 0.001,
1746
+ "loss": 0.5507,
1747
+ "step": 558
1748
+ },
1749
+ {
1750
+ "epoch": 8.21,
1751
+ "learning_rate": 0.001,
1752
+ "loss": 0.5696,
1753
+ "step": 560
1754
+ },
1755
+ {
1756
+ "epoch": 8.24,
1757
+ "learning_rate": 0.001,
1758
+ "loss": 0.5643,
1759
+ "step": 562
1760
+ },
1761
+ {
1762
+ "epoch": 8.27,
1763
+ "learning_rate": 0.001,
1764
+ "loss": 0.5779,
1765
+ "step": 564
1766
+ },
1767
+ {
1768
+ "epoch": 8.3,
1769
+ "learning_rate": 0.001,
1770
+ "loss": 0.5716,
1771
+ "step": 566
1772
+ },
1773
+ {
1774
+ "epoch": 8.33,
1775
+ "learning_rate": 0.001,
1776
+ "loss": 0.5809,
1777
+ "step": 568
1778
+ },
1779
+ {
1780
+ "epoch": 8.36,
1781
+ "learning_rate": 0.001,
1782
+ "loss": 0.5757,
1783
+ "step": 570
1784
+ },
1785
+ {
1786
+ "epoch": 8.38,
1787
+ "learning_rate": 0.001,
1788
+ "loss": 0.5579,
1789
+ "step": 572
1790
+ },
1791
+ {
1792
+ "epoch": 8.41,
1793
+ "learning_rate": 0.001,
1794
+ "loss": 0.5724,
1795
+ "step": 574
1796
+ },
1797
+ {
1798
+ "epoch": 8.44,
1799
+ "learning_rate": 0.001,
1800
+ "loss": 0.5509,
1801
+ "step": 576
1802
+ },
1803
+ {
1804
+ "epoch": 8.47,
1805
+ "learning_rate": 0.001,
1806
+ "loss": 0.5539,
1807
+ "step": 578
1808
+ },
1809
+ {
1810
+ "epoch": 8.5,
1811
+ "learning_rate": 0.001,
1812
+ "loss": 0.5906,
1813
+ "step": 580
1814
+ },
1815
+ {
1816
+ "epoch": 8.53,
1817
+ "learning_rate": 0.001,
1818
+ "loss": 0.5943,
1819
+ "step": 582
1820
+ },
1821
+ {
1822
+ "epoch": 8.56,
1823
+ "learning_rate": 0.001,
1824
+ "loss": 0.6132,
1825
+ "step": 584
1826
+ },
1827
+ {
1828
+ "epoch": 8.59,
1829
+ "learning_rate": 0.001,
1830
+ "loss": 0.6026,
1831
+ "step": 586
1832
+ },
1833
+ {
1834
+ "epoch": 8.62,
1835
+ "learning_rate": 0.001,
1836
+ "loss": 0.6147,
1837
+ "step": 588
1838
+ },
1839
+ {
1840
+ "epoch": 8.65,
1841
+ "learning_rate": 0.001,
1842
+ "loss": 0.5925,
1843
+ "step": 590
1844
+ },
1845
+ {
1846
+ "epoch": 8.68,
1847
+ "learning_rate": 0.001,
1848
+ "loss": 0.5987,
1849
+ "step": 592
1850
+ },
1851
+ {
1852
+ "epoch": 8.71,
1853
+ "learning_rate": 0.001,
1854
+ "loss": 0.6025,
1855
+ "step": 594
1856
+ },
1857
+ {
1858
+ "epoch": 8.74,
1859
+ "learning_rate": 0.001,
1860
+ "loss": 0.5965,
1861
+ "step": 596
1862
+ },
1863
+ {
1864
+ "epoch": 8.77,
1865
+ "learning_rate": 0.001,
1866
+ "loss": 0.598,
1867
+ "step": 598
1868
+ },
1869
+ {
1870
+ "epoch": 8.8,
1871
+ "learning_rate": 0.001,
1872
+ "loss": 0.616,
1873
+ "step": 600
1874
+ },
1875
+ {
1876
+ "epoch": 8.82,
1877
+ "learning_rate": 0.001,
1878
+ "loss": 0.5976,
1879
+ "step": 602
1880
+ },
1881
+ {
1882
+ "epoch": 8.85,
1883
+ "learning_rate": 0.001,
1884
+ "loss": 0.5999,
1885
+ "step": 604
1886
+ },
1887
+ {
1888
+ "epoch": 8.88,
1889
+ "learning_rate": 0.001,
1890
+ "loss": 0.5895,
1891
+ "step": 606
1892
+ },
1893
+ {
1894
+ "epoch": 8.91,
1895
+ "learning_rate": 0.001,
1896
+ "loss": 0.6129,
1897
+ "step": 608
1898
+ },
1899
+ {
1900
+ "epoch": 8.94,
1901
+ "learning_rate": 0.001,
1902
+ "loss": 0.61,
1903
+ "step": 610
1904
+ },
1905
+ {
1906
+ "epoch": 8.97,
1907
+ "learning_rate": 0.001,
1908
+ "loss": 0.6155,
1909
+ "step": 612
1910
+ },
1911
+ {
1912
+ "epoch": 8.99,
1913
+ "eval_loss": 1.5037193298339844,
1914
+ "eval_runtime": 153.536,
1915
+ "eval_samples_per_second": 6.331,
1916
+ "eval_steps_per_second": 0.795,
1917
+ "step": 613
1918
+ },
1919
+ {
1920
+ "epoch": 9.0,
1921
+ "learning_rate": 0.001,
1922
+ "loss": 0.633,
1923
+ "step": 614
1924
+ },
1925
+ {
1926
+ "epoch": 9.03,
1927
+ "learning_rate": 0.001,
1928
+ "loss": 0.4917,
1929
+ "step": 616
1930
+ },
1931
+ {
1932
+ "epoch": 9.06,
1933
+ "learning_rate": 0.001,
1934
+ "loss": 0.4737,
1935
+ "step": 618
1936
+ },
1937
+ {
1938
+ "epoch": 9.09,
1939
+ "learning_rate": 0.001,
1940
+ "loss": 0.4802,
1941
+ "step": 620
1942
+ },
1943
+ {
1944
+ "epoch": 9.12,
1945
+ "learning_rate": 0.001,
1946
+ "loss": 0.4917,
1947
+ "step": 622
1948
+ },
1949
+ {
1950
+ "epoch": 9.15,
1951
+ "learning_rate": 0.001,
1952
+ "loss": 0.4999,
1953
+ "step": 624
1954
+ },
1955
+ {
1956
+ "epoch": 9.18,
1957
+ "learning_rate": 0.001,
1958
+ "loss": 0.5103,
1959
+ "step": 626
1960
+ },
1961
+ {
1962
+ "epoch": 9.21,
1963
+ "learning_rate": 0.001,
1964
+ "loss": 0.5019,
1965
+ "step": 628
1966
+ },
1967
+ {
1968
+ "epoch": 9.23,
1969
+ "learning_rate": 0.001,
1970
+ "loss": 0.4964,
1971
+ "step": 630
1972
+ },
1973
+ {
1974
+ "epoch": 9.26,
1975
+ "learning_rate": 0.001,
1976
+ "loss": 0.5142,
1977
+ "step": 632
1978
+ },
1979
+ {
1980
+ "epoch": 9.29,
1981
+ "learning_rate": 0.001,
1982
+ "loss": 0.515,
1983
+ "step": 634
1984
+ },
1985
+ {
1986
+ "epoch": 9.32,
1987
+ "learning_rate": 0.001,
1988
+ "loss": 0.5133,
1989
+ "step": 636
1990
+ },
1991
+ {
1992
+ "epoch": 9.35,
1993
+ "learning_rate": 0.001,
1994
+ "loss": 0.5136,
1995
+ "step": 638
1996
+ },
1997
+ {
1998
+ "epoch": 9.38,
1999
+ "learning_rate": 0.001,
2000
+ "loss": 0.5135,
2001
+ "step": 640
2002
+ },
2003
+ {
2004
+ "epoch": 9.41,
2005
+ "learning_rate": 0.001,
2006
+ "loss": 0.4979,
2007
+ "step": 642
2008
+ },
2009
+ {
2010
+ "epoch": 9.44,
2011
+ "learning_rate": 0.001,
2012
+ "loss": 0.5069,
2013
+ "step": 644
2014
+ },
2015
+ {
2016
+ "epoch": 9.47,
2017
+ "learning_rate": 0.001,
2018
+ "loss": 0.5287,
2019
+ "step": 646
2020
+ },
2021
+ {
2022
+ "epoch": 9.5,
2023
+ "learning_rate": 0.001,
2024
+ "loss": 0.5227,
2025
+ "step": 648
2026
+ },
2027
+ {
2028
+ "epoch": 9.53,
2029
+ "learning_rate": 0.001,
2030
+ "loss": 0.4968,
2031
+ "step": 650
2032
+ },
2033
+ {
2034
+ "epoch": 9.56,
2035
+ "learning_rate": 0.001,
2036
+ "loss": 0.5015,
2037
+ "step": 652
2038
+ },
2039
+ {
2040
+ "epoch": 9.59,
2041
+ "learning_rate": 0.001,
2042
+ "loss": 0.5143,
2043
+ "step": 654
2044
+ },
2045
+ {
2046
+ "epoch": 9.62,
2047
+ "learning_rate": 0.001,
2048
+ "loss": 0.5062,
2049
+ "step": 656
2050
+ },
2051
+ {
2052
+ "epoch": 9.65,
2053
+ "learning_rate": 0.001,
2054
+ "loss": 0.51,
2055
+ "step": 658
2056
+ },
2057
+ {
2058
+ "epoch": 9.67,
2059
+ "learning_rate": 0.001,
2060
+ "loss": 0.5293,
2061
+ "step": 660
2062
+ },
2063
+ {
2064
+ "epoch": 9.7,
2065
+ "learning_rate": 0.001,
2066
+ "loss": 0.5273,
2067
+ "step": 662
2068
+ },
2069
+ {
2070
+ "epoch": 9.73,
2071
+ "learning_rate": 0.001,
2072
+ "loss": 0.526,
2073
+ "step": 664
2074
+ },
2075
+ {
2076
+ "epoch": 9.76,
2077
+ "learning_rate": 0.001,
2078
+ "loss": 0.5294,
2079
+ "step": 666
2080
+ },
2081
+ {
2082
+ "epoch": 9.79,
2083
+ "learning_rate": 0.001,
2084
+ "loss": 0.5279,
2085
+ "step": 668
2086
+ },
2087
+ {
2088
+ "epoch": 9.82,
2089
+ "learning_rate": 0.001,
2090
+ "loss": 0.536,
2091
+ "step": 670
2092
+ },
2093
+ {
2094
+ "epoch": 9.85,
2095
+ "learning_rate": 0.001,
2096
+ "loss": 0.5446,
2097
+ "step": 672
2098
+ },
2099
+ {
2100
+ "epoch": 9.88,
2101
+ "learning_rate": 0.001,
2102
+ "loss": 0.5467,
2103
+ "step": 674
2104
+ },
2105
+ {
2106
+ "epoch": 9.91,
2107
+ "learning_rate": 0.001,
2108
+ "loss": 0.5394,
2109
+ "step": 676
2110
+ },
2111
+ {
2112
+ "epoch": 9.94,
2113
+ "learning_rate": 0.001,
2114
+ "loss": 0.5341,
2115
+ "step": 678
2116
+ },
2117
+ {
2118
+ "epoch": 9.97,
2119
+ "learning_rate": 0.001,
2120
+ "loss": 0.5435,
2121
+ "step": 680
2122
+ },
2123
+ {
2124
+ "epoch": 9.97,
2125
+ "eval_loss": 1.5582315921783447,
2126
+ "eval_runtime": 153.7963,
2127
+ "eval_samples_per_second": 6.32,
2128
+ "eval_steps_per_second": 0.793,
2129
+ "step": 680
2130
+ },
2131
+ {
2132
+ "epoch": 9.97,
2133
+ "step": 680,
2134
+ "total_flos": 3.0923201415995965e+18,
2135
+ "train_loss": 0.9514477711390047,
2136
+ "train_runtime": 93373.8295,
2137
+ "train_samples_per_second": 1.87,
2138
+ "train_steps_per_second": 0.007
2139
+ }
2140
+ ],
2141
+ "logging_steps": 2,
2142
+ "max_steps": 680,
2143
+ "num_train_epochs": 10,
2144
+ "save_steps": 500,
2145
+ "total_flos": 3.0923201415995965e+18,
2146
+ "trial_name": null,
2147
+ "trial_params": null
2148
+ }