Hugging Face's logo

nlparabic
/
res_nw_dj_aragpt2-base

Safetensors
gpt2
Generated from Trainer
Model card Files Community
res_nw_dj_aragpt2-base
File size: 7,113 Bytes 
e71621c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
 
{
  "best_metric": 0.07523266971111298,
  "best_model_checkpoint": "/home/iais_marenpielka/Bouthaina/res_nw_dj_aragpt2-base/checkpoint-16074",
  "epoch": 11.0,
  "eval_steps": 500,
  "global_step": 29469,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.1490328013896942,
      "learning_rate": 4.7947437829691034e-05,
      "loss": 0.435,
      "step": 2679
    },
    {
      "epoch": 1.0,
      "eval_bleu": 0.022539363481404024,
      "eval_loss": 0.08990845084190369,
      "eval_rouge1": 0.26967504263175696,
      "eval_rouge2": 0.06811111838722575,
      "eval_rougeL": 0.2648760311441921,
      "eval_runtime": 118.8639,
      "eval_samples_per_second": 45.262,
      "eval_steps_per_second": 5.662,
      "step": 2679
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.1779935508966446,
      "learning_rate": 4.542388847023361e-05,
      "loss": 0.0908,
      "step": 5358
    },
    {
      "epoch": 2.0,
      "eval_bleu": 0.0494923940085718,
      "eval_loss": 0.08216600120067596,
      "eval_rouge1": 0.34383088385557475,
      "eval_rouge2": 0.12325553058649232,
      "eval_rougeL": 0.33940964680072816,
      "eval_runtime": 181.022,
      "eval_samples_per_second": 29.72,
      "eval_steps_per_second": 3.718,
      "step": 5358
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.13422226905822754,
      "learning_rate": 4.290033911077619e-05,
      "loss": 0.0808,
      "step": 8037
    },
    {
      "epoch": 3.0,
      "eval_bleu": 0.06700443598211842,
      "eval_loss": 0.0785822868347168,
      "eval_rouge1": 0.38347464472946946,
      "eval_rouge2": 0.15815766995910013,
      "eval_rougeL": 0.37897410206784377,
      "eval_runtime": 118.7728,
      "eval_samples_per_second": 45.297,
      "eval_steps_per_second": 5.666,
      "step": 8037
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.17974382638931274,
      "learning_rate": 4.0376789751318766e-05,
      "loss": 0.0738,
      "step": 10716
    },
    {
      "epoch": 4.0,
      "eval_bleu": 0.0782017656533744,
      "eval_loss": 0.07652640342712402,
      "eval_rouge1": 0.4066218577182069,
      "eval_rouge2": 0.1797711825940213,
      "eval_rougeL": 0.4024533186612807,
      "eval_runtime": 302.5488,
      "eval_samples_per_second": 17.782,
      "eval_steps_per_second": 2.224,
      "step": 10716
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.1600717157125473,
      "learning_rate": 3.785324039186134e-05,
      "loss": 0.0681,
      "step": 13395
    },
    {
      "epoch": 5.0,
      "eval_bleu": 0.088003678878398,
      "eval_loss": 0.07556667178869247,
      "eval_rouge1": 0.42424169752606233,
      "eval_rouge2": 0.19635936454770994,
      "eval_rougeL": 0.42040996405014475,
      "eval_runtime": 119.8742,
      "eval_samples_per_second": 44.88,
      "eval_steps_per_second": 5.614,
      "step": 13395
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.17717573046684265,
      "learning_rate": 3.532969103240392e-05,
      "loss": 0.0632,
      "step": 16074
    },
    {
      "epoch": 6.0,
      "eval_bleu": 0.09284298963391195,
      "eval_loss": 0.07523266971111298,
      "eval_rouge1": 0.434313103224844,
      "eval_rouge2": 0.2043067195259623,
      "eval_rougeL": 0.430449964990971,
      "eval_runtime": 119.9224,
      "eval_samples_per_second": 44.862,
      "eval_steps_per_second": 5.612,
      "step": 16074
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.20939625799655914,
      "learning_rate": 3.28061416729465e-05,
      "loss": 0.059,
      "step": 18753
    },
    {
      "epoch": 7.0,
      "eval_bleu": 0.09955364884197439,
      "eval_loss": 0.07554977387189865,
      "eval_rouge1": 0.4438832318000667,
      "eval_rouge2": 0.21524219506914244,
      "eval_rougeL": 0.44011453518152965,
      "eval_runtime": 119.8903,
      "eval_samples_per_second": 44.874,
      "eval_steps_per_second": 5.613,
      "step": 18753
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.18116699159145355,
      "learning_rate": 3.028259231348907e-05,
      "loss": 0.0552,
      "step": 21432
    },
    {
      "epoch": 8.0,
      "eval_bleu": 0.10150066662504155,
      "eval_loss": 0.07605580985546112,
      "eval_rouge1": 0.45000685735983936,
      "eval_rouge2": 0.2217308384368585,
      "eval_rougeL": 0.44629486754481273,
      "eval_runtime": 180.8168,
      "eval_samples_per_second": 29.754,
      "eval_steps_per_second": 3.722,
      "step": 21432
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.20604003965854645,
      "learning_rate": 2.775904295403165e-05,
      "loss": 0.0517,
      "step": 24111
    },
    {
      "epoch": 9.0,
      "eval_bleu": 0.10504101584036675,
      "eval_loss": 0.07660207897424698,
      "eval_rouge1": 0.4527224851378999,
      "eval_rouge2": 0.2249827236829457,
      "eval_rougeL": 0.44886876248725205,
      "eval_runtime": 241.7568,
      "eval_samples_per_second": 22.254,
      "eval_steps_per_second": 2.784,
      "step": 24111
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.17469635605812073,
      "learning_rate": 2.523549359457423e-05,
      "loss": 0.0486,
      "step": 26790
    },
    {
      "epoch": 10.0,
      "eval_bleu": 0.10926649986209491,
      "eval_loss": 0.07839509844779968,
      "eval_rouge1": 0.4612349211854463,
      "eval_rouge2": 0.23378642120255436,
      "eval_rougeL": 0.457790117200362,
      "eval_runtime": 180.2876,
      "eval_samples_per_second": 29.841,
      "eval_steps_per_second": 3.733,
      "step": 26790
    },
    {
      "epoch": 11.0,
      "grad_norm": 0.19318881630897522,
      "learning_rate": 2.2711944235116806e-05,
      "loss": 0.0458,
      "step": 29469
    },
    {
      "epoch": 11.0,
      "eval_bleu": 0.11121120716108289,
      "eval_loss": 0.07983218133449554,
      "eval_rouge1": 0.4633689566450456,
      "eval_rouge2": 0.2356348733383184,
      "eval_rougeL": 0.4600017445894788,
      "eval_runtime": 242.0184,
      "eval_samples_per_second": 22.23,
      "eval_steps_per_second": 2.781,
      "step": 29469
    },
    {
      "epoch": 11.0,
      "step": 29469,
      "total_flos": 1.23182992982016e+17,
      "train_loss": 0.09744292338859069,
      "train_runtime": 17256.5383,
      "train_samples_per_second": 24.836,
      "train_steps_per_second": 3.105
    }
  ],
  "logging_steps": 500,
  "max_steps": 53580,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.23182992982016e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}