File size: 5,487 Bytes
16bddb4 |
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 |
{
"best_metric": 0.3660341203212738,
"best_model_checkpoint": "/home/iais_marenpielka/Bouthaina/res_nw_lev_03/checkpoint-15186",
"epoch": 8.0,
"eval_steps": 500,
"global_step": 40496,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 5.426126956939697,
"learning_rate": 4.773575540996625e-05,
"loss": 0.6345,
"step": 5062
},
{
"epoch": 1.0,
"eval_bleu": 0.4054405178422978,
"eval_loss": 0.424884170293808,
"eval_rouge1": 0.6718054932020717,
"eval_rouge2": 0.4168304983667167,
"eval_rougeL": 0.6705720028130773,
"eval_runtime": 99.0407,
"eval_samples_per_second": 102.16,
"eval_steps_per_second": 12.773,
"step": 5062
},
{
"epoch": 2.0,
"grad_norm": 3.7220001220703125,
"learning_rate": 4.522334723049435e-05,
"loss": 0.3258,
"step": 10124
},
{
"epoch": 2.0,
"eval_bleu": 0.4443048022041477,
"eval_loss": 0.38237395882606506,
"eval_rouge1": 0.7134969978151362,
"eval_rouge2": 0.4799759371169404,
"eval_rougeL": 0.7123642730734705,
"eval_runtime": 184.2876,
"eval_samples_per_second": 54.903,
"eval_steps_per_second": 6.864,
"step": 10124
},
{
"epoch": 3.0,
"grad_norm": 4.069755554199219,
"learning_rate": 4.271093905102244e-05,
"loss": 0.2266,
"step": 15186
},
{
"epoch": 3.0,
"eval_bleu": 0.48887049804156,
"eval_loss": 0.3660341203212738,
"eval_rouge1": 0.7441728211754235,
"eval_rouge2": 0.5301574363836805,
"eval_rougeL": 0.743357806649209,
"eval_runtime": 197.651,
"eval_samples_per_second": 51.191,
"eval_steps_per_second": 6.4,
"step": 15186
},
{
"epoch": 4.0,
"grad_norm": 2.417670488357544,
"learning_rate": 4.0198530871550526e-05,
"loss": 0.1702,
"step": 20248
},
{
"epoch": 4.0,
"eval_bleu": 0.5217066405916664,
"eval_loss": 0.37126386165618896,
"eval_rouge1": 0.7592034964866012,
"eval_rouge2": 0.5617725815136836,
"eval_rougeL": 0.7583714246633779,
"eval_runtime": 197.8347,
"eval_samples_per_second": 51.144,
"eval_steps_per_second": 6.394,
"step": 20248
},
{
"epoch": 5.0,
"grad_norm": 2.2886266708374023,
"learning_rate": 3.7686122692078615e-05,
"loss": 0.1405,
"step": 25310
},
{
"epoch": 5.0,
"eval_bleu": 0.5410963843168277,
"eval_loss": 0.38092052936553955,
"eval_rouge1": 0.7670677626194377,
"eval_rouge2": 0.5785130119272781,
"eval_rougeL": 0.766336455280991,
"eval_runtime": 74.4752,
"eval_samples_per_second": 135.857,
"eval_steps_per_second": 16.986,
"step": 25310
},
{
"epoch": 6.0,
"grad_norm": 1.4138972759246826,
"learning_rate": 3.517371451260672e-05,
"loss": 0.1253,
"step": 30372
},
{
"epoch": 6.0,
"eval_bleu": 0.5538973347056134,
"eval_loss": 0.3939472734928131,
"eval_rouge1": 0.7718106498807895,
"eval_rouge2": 0.5899343275061358,
"eval_rougeL": 0.7710407354471525,
"eval_runtime": 197.8643,
"eval_samples_per_second": 51.136,
"eval_steps_per_second": 6.393,
"step": 30372
},
{
"epoch": 7.0,
"grad_norm": 1.0359286069869995,
"learning_rate": 3.266130633313481e-05,
"loss": 0.1166,
"step": 35434
},
{
"epoch": 7.0,
"eval_bleu": 0.5535836812783581,
"eval_loss": 0.3990260660648346,
"eval_rouge1": 0.7744583802216872,
"eval_rouge2": 0.5941788640581145,
"eval_rougeL": 0.7736991376335538,
"eval_runtime": 197.6914,
"eval_samples_per_second": 51.181,
"eval_steps_per_second": 6.399,
"step": 35434
},
{
"epoch": 8.0,
"grad_norm": 3.439483165740967,
"learning_rate": 3.0148898153662896e-05,
"loss": 0.1107,
"step": 40496
},
{
"epoch": 8.0,
"eval_bleu": 0.5607932303098884,
"eval_loss": 0.4049707055091858,
"eval_rouge1": 0.7769922891885475,
"eval_rouge2": 0.5994002303095487,
"eval_rougeL": 0.7762651005907448,
"eval_runtime": 197.4325,
"eval_samples_per_second": 51.248,
"eval_steps_per_second": 6.407,
"step": 40496
},
{
"epoch": 8.0,
"step": 40496,
"total_flos": 7.520432484148838e+16,
"train_loss": 0.23126965857739035,
"train_runtime": 11366.9663,
"train_samples_per_second": 71.24,
"train_steps_per_second": 8.907
}
],
"logging_steps": 500,
"max_steps": 101240,
"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": 7.520432484148838e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|