Hugging Face's logo

nlparabic
/
res_nw_yem_aragpt2-large

Safetensors
aragpt2
Generated from Trainer
custom_code
Model card Files Community
res_nw_yem_aragpt2-large
File size: 4,943 Bytes 
cfebc79
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.04691193997859955,
  "best_model_checkpoint": "/home/iais_marenpielka/Bouthaina/res_nw_yem_aragpt2-large/checkpoint-610",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 2135,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.40213119983673096,
      "learning_rate": 3.05e-05,
      "loss": 0.8644,
      "step": 305
    },
    {
      "epoch": 1.0,
      "eval_bleu": 0.03103545034655718,
      "eval_loss": 0.049881722778081894,
      "eval_rouge1": 0.2976310465047741,
      "eval_rouge2": 0.0825114524566873,
      "eval_rougeL": 0.2931870351050212,
      "eval_runtime": 101.6572,
      "eval_samples_per_second": 2.99,
      "eval_steps_per_second": 0.374,
      "step": 305
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.45833268761634827,
      "learning_rate": 4.901785714285714e-05,
      "loss": 0.0439,
      "step": 610
    },
    {
      "epoch": 2.0,
      "eval_bleu": 0.07334464750125981,
      "eval_loss": 0.04691193997859955,
      "eval_rouge1": 0.39556592669658314,
      "eval_rouge2": 0.1676736409423039,
      "eval_rougeL": 0.3901085723006601,
      "eval_runtime": 41.076,
      "eval_samples_per_second": 7.401,
      "eval_steps_per_second": 0.925,
      "step": 610
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.3850250840187073,
      "learning_rate": 4.629464285714286e-05,
      "loss": 0.0307,
      "step": 915
    },
    {
      "epoch": 3.0,
      "eval_bleu": 0.09008751782596823,
      "eval_loss": 0.0473761111497879,
      "eval_rouge1": 0.44112670621442845,
      "eval_rouge2": 0.20925026290023724,
      "eval_rougeL": 0.43611440413552455,
      "eval_runtime": 41.095,
      "eval_samples_per_second": 7.397,
      "eval_steps_per_second": 0.925,
      "step": 915
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.4408362805843353,
      "learning_rate": 4.3571428571428576e-05,
      "loss": 0.0212,
      "step": 1220
    },
    {
      "epoch": 4.0,
      "eval_bleu": 0.10385450068202749,
      "eval_loss": 0.04973715916275978,
      "eval_rouge1": 0.4643434470122675,
      "eval_rouge2": 0.23150126678662394,
      "eval_rougeL": 0.45914976519742434,
      "eval_runtime": 41.0763,
      "eval_samples_per_second": 7.401,
      "eval_steps_per_second": 0.925,
      "step": 1220
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.4677392840385437,
      "learning_rate": 4.084821428571429e-05,
      "loss": 0.016,
      "step": 1525
    },
    {
      "epoch": 5.0,
      "eval_bleu": 0.09227592943056641,
      "eval_loss": 0.054129794239997864,
      "eval_rouge1": 0.464136474952609,
      "eval_rouge2": 0.22291426741508574,
      "eval_rougeL": 0.4599627344232192,
      "eval_runtime": 41.1781,
      "eval_samples_per_second": 7.383,
      "eval_steps_per_second": 0.923,
      "step": 1525
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.30016008019447327,
      "learning_rate": 3.8125e-05,
      "loss": 0.0134,
      "step": 1830
    },
    {
      "epoch": 6.0,
      "eval_bleu": 0.11604582902883592,
      "eval_loss": 0.05314570292830467,
      "eval_rouge1": 0.47459996105255675,
      "eval_rouge2": 0.25028361013073314,
      "eval_rougeL": 0.46988615577124576,
      "eval_runtime": 61.9343,
      "eval_samples_per_second": 4.908,
      "eval_steps_per_second": 0.614,
      "step": 1830
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.24085062742233276,
      "learning_rate": 3.5401785714285716e-05,
      "loss": 0.0118,
      "step": 2135
    },
    {
      "epoch": 7.0,
      "eval_bleu": 0.11125669152362899,
      "eval_loss": 0.057827215641736984,
      "eval_rouge1": 0.4975937747836845,
      "eval_rouge2": 0.27138037997797015,
      "eval_rougeL": 0.4939744686596661,
      "eval_runtime": 101.6221,
      "eval_samples_per_second": 2.991,
      "eval_steps_per_second": 0.374,
      "step": 2135
    },
    {
      "epoch": 7.0,
      "step": 2135,
      "total_flos": 3.71386078199808e+16,
      "train_loss": 0.1430642572443156,
      "train_runtime": 4921.8294,
      "train_samples_per_second": 4.953,
      "train_steps_per_second": 1.239
    }
  ],
  "logging_steps": 500,
  "max_steps": 6100,
  "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": 3.71386078199808e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}