Hugging Face's logo

nlparabic
/
res_nw_eg_aragpt2-base

Safetensors
gpt2
Generated from Trainer
Model card Files Community
res_nw_eg_aragpt2-base
File size: 6,590 Bytes 
24c1b7b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.10316114127635956,
  "best_model_checkpoint": "/home/iais_marenpielka/Bouthaina/res_nw_eg_aragpt2-base/checkpoint-35525",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 71050,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.1684599220752716,
      "learning_rate": 4.766772598870057e-05,
      "loss": 0.2542,
      "step": 7105
    },
    {
      "epoch": 1.0,
      "eval_bleu": 0.07285026466195073,
      "eval_loss": 0.11986471712589264,
      "eval_rouge1": 0.31870746501286634,
      "eval_rouge2": 0.11025143574709506,
      "eval_rougeL": 0.30940400851788263,
      "eval_runtime": 445.2495,
      "eval_samples_per_second": 31.912,
      "eval_steps_per_second": 3.991,
      "step": 7105
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.16581259667873383,
      "learning_rate": 4.515889830508475e-05,
      "loss": 0.1078,
      "step": 14210
    },
    {
      "epoch": 2.0,
      "eval_bleu": 0.104385167515318,
      "eval_loss": 0.1118762344121933,
      "eval_rouge1": 0.38033922316590574,
      "eval_rouge2": 0.16357204386475152,
      "eval_rougeL": 0.37196606997888715,
      "eval_runtime": 445.4751,
      "eval_samples_per_second": 31.896,
      "eval_steps_per_second": 3.989,
      "step": 14210
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.18644841015338898,
      "learning_rate": 4.265007062146893e-05,
      "loss": 0.0972,
      "step": 21315
    },
    {
      "epoch": 3.0,
      "eval_bleu": 0.12224033944483013,
      "eval_loss": 0.10767202824354172,
      "eval_rouge1": 0.4109049665753015,
      "eval_rouge2": 0.19329040527739555,
      "eval_rougeL": 0.40326193036349967,
      "eval_runtime": 383.8172,
      "eval_samples_per_second": 37.02,
      "eval_steps_per_second": 4.63,
      "step": 21315
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.2712990939617157,
      "learning_rate": 4.014124293785311e-05,
      "loss": 0.0902,
      "step": 28420
    },
    {
      "epoch": 4.0,
      "eval_bleu": 0.13124006032752472,
      "eval_loss": 0.10514508932828903,
      "eval_rouge1": 0.42940503923153844,
      "eval_rouge2": 0.2090469696784658,
      "eval_rougeL": 0.4223466730872162,
      "eval_runtime": 323.7733,
      "eval_samples_per_second": 43.886,
      "eval_steps_per_second": 5.488,
      "step": 28420
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.16391794383525848,
      "learning_rate": 3.763241525423729e-05,
      "loss": 0.0846,
      "step": 35525
    },
    {
      "epoch": 5.0,
      "eval_bleu": 0.14049162127130865,
      "eval_loss": 0.10316114127635956,
      "eval_rouge1": 0.44551198545007975,
      "eval_rouge2": 0.22506890852974587,
      "eval_rougeL": 0.4382572142917238,
      "eval_runtime": 340.0971,
      "eval_samples_per_second": 41.779,
      "eval_steps_per_second": 5.225,
      "step": 35525
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.1612280309200287,
      "learning_rate": 3.5123587570621466e-05,
      "loss": 0.0799,
      "step": 42630
    },
    {
      "epoch": 6.0,
      "eval_bleu": 0.14535221713569074,
      "eval_loss": 0.10411085933446884,
      "eval_rouge1": 0.45365603658460285,
      "eval_rouge2": 0.23383881662198475,
      "eval_rougeL": 0.4465500235966283,
      "eval_runtime": 384.6849,
      "eval_samples_per_second": 36.937,
      "eval_steps_per_second": 4.619,
      "step": 42630
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.252353310585022,
      "learning_rate": 3.261475988700565e-05,
      "loss": 0.0759,
      "step": 49735
    },
    {
      "epoch": 7.0,
      "eval_bleu": 0.1493733281238007,
      "eval_loss": 0.10441984981298447,
      "eval_rouge1": 0.4622737132167348,
      "eval_rouge2": 0.24252644756195563,
      "eval_rougeL": 0.45529247029346154,
      "eval_runtime": 324.6182,
      "eval_samples_per_second": 43.771,
      "eval_steps_per_second": 5.474,
      "step": 49735
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.21136653423309326,
      "learning_rate": 3.010593220338983e-05,
      "loss": 0.0722,
      "step": 56840
    },
    {
      "epoch": 8.0,
      "eval_bleu": 0.1526924816405305,
      "eval_loss": 0.10443145781755447,
      "eval_rouge1": 0.4655122846049303,
      "eval_rouge2": 0.24695475478185897,
      "eval_rougeL": 0.45872867266974005,
      "eval_runtime": 324.8018,
      "eval_samples_per_second": 43.747,
      "eval_steps_per_second": 5.471,
      "step": 56840
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.26080313324928284,
      "learning_rate": 2.7597104519774014e-05,
      "loss": 0.069,
      "step": 63945
    },
    {
      "epoch": 9.0,
      "eval_bleu": 0.153555473627703,
      "eval_loss": 0.10583677142858505,
      "eval_rouge1": 0.4688625732021522,
      "eval_rouge2": 0.24885496454985231,
      "eval_rougeL": 0.46205637495730445,
      "eval_runtime": 324.9582,
      "eval_samples_per_second": 43.726,
      "eval_steps_per_second": 5.468,
      "step": 63945
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.27384456992149353,
      "learning_rate": 2.5088276836158192e-05,
      "loss": 0.066,
      "step": 71050
    },
    {
      "epoch": 10.0,
      "eval_bleu": 0.1549549290214687,
      "eval_loss": 0.10621096938848495,
      "eval_rouge1": 0.4724064043822283,
      "eval_rouge2": 0.25225313492301393,
      "eval_rougeL": 0.46574710538787245,
      "eval_runtime": 327.3388,
      "eval_samples_per_second": 43.408,
      "eval_steps_per_second": 5.429,
      "step": 71050
    },
    {
      "epoch": 10.0,
      "step": 71050,
      "total_flos": 2.9701587861504e+17,
      "train_loss": 0.09969830163342276,
      "train_runtime": 40778.4516,
      "train_samples_per_second": 27.876,
      "train_steps_per_second": 3.485
    }
  ],
  "logging_steps": 500,
  "max_steps": 142100,
  "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": 2.9701587861504e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}