File size: 5,401 Bytes
9ece604 |
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": 0.3767148554325104,
"best_model_checkpoint": "/home/iais_marenpielka/Bouthaina/res_nw_yem_03/checkpoint-459",
"epoch": 8.0,
"eval_steps": 500,
"global_step": 1224,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 5.96675968170166,
"learning_rate": 1.53e-05,
"loss": 4.4383,
"step": 153
},
{
"epoch": 1.0,
"eval_bleu": 0.015528584651533126,
"eval_loss": 0.7436053156852722,
"eval_rouge1": 0.46982391145733055,
"eval_rouge2": 0.19207986874781602,
"eval_rougeL": 0.46930459291115545,
"eval_runtime": 2.3655,
"eval_samples_per_second": 128.516,
"eval_steps_per_second": 16.064,
"step": 153
},
{
"epoch": 2.0,
"grad_norm": 3.5768725872039795,
"learning_rate": 3.06e-05,
"loss": 0.4733,
"step": 306
},
{
"epoch": 2.0,
"eval_bleu": 0.39670936867008716,
"eval_loss": 0.39333394169807434,
"eval_rouge1": 0.5938039437844622,
"eval_rouge2": 0.3153907013759276,
"eval_rougeL": 0.5909085576639257,
"eval_runtime": 9.4412,
"eval_samples_per_second": 32.199,
"eval_steps_per_second": 4.025,
"step": 306
},
{
"epoch": 3.0,
"grad_norm": 3.4199442863464355,
"learning_rate": 4.5900000000000004e-05,
"loss": 0.2714,
"step": 459
},
{
"epoch": 3.0,
"eval_bleu": 0.427914494660841,
"eval_loss": 0.3767148554325104,
"eval_rouge1": 0.6598531398910279,
"eval_rouge2": 0.3971047774692673,
"eval_rougeL": 0.6584832139558556,
"eval_runtime": 9.4581,
"eval_samples_per_second": 32.142,
"eval_steps_per_second": 4.018,
"step": 459
},
{
"epoch": 4.0,
"grad_norm": 2.4085845947265625,
"learning_rate": 4.7812500000000003e-05,
"loss": 0.1837,
"step": 612
},
{
"epoch": 4.0,
"eval_bleu": 0.43801708242621135,
"eval_loss": 0.3863435983657837,
"eval_rouge1": 0.6761692862282009,
"eval_rouge2": 0.41837300418726475,
"eval_rougeL": 0.6725637079403999,
"eval_runtime": 127.7574,
"eval_samples_per_second": 2.38,
"eval_steps_per_second": 0.297,
"step": 612
},
{
"epoch": 5.0,
"grad_norm": 0.990710973739624,
"learning_rate": 4.482421875e-05,
"loss": 0.129,
"step": 765
},
{
"epoch": 5.0,
"eval_bleu": 0.4536061292967932,
"eval_loss": 0.38353848457336426,
"eval_rouge1": 0.6993772519271104,
"eval_rouge2": 0.4575839398398158,
"eval_rougeL": 0.6967680711913622,
"eval_runtime": 4.8885,
"eval_samples_per_second": 62.186,
"eval_steps_per_second": 7.773,
"step": 765
},
{
"epoch": 6.0,
"grad_norm": 0.9595922827720642,
"learning_rate": 4.18359375e-05,
"loss": 0.0999,
"step": 918
},
{
"epoch": 6.0,
"eval_bleu": 0.44934275646340344,
"eval_loss": 0.39377203583717346,
"eval_rouge1": 0.6978745123044579,
"eval_rouge2": 0.45411326233563776,
"eval_rougeL": 0.693627688943746,
"eval_runtime": 2.8238,
"eval_samples_per_second": 107.657,
"eval_steps_per_second": 13.457,
"step": 918
},
{
"epoch": 7.0,
"grad_norm": 1.0308947563171387,
"learning_rate": 3.884765625e-05,
"loss": 0.0844,
"step": 1071
},
{
"epoch": 7.0,
"eval_bleu": 0.46229210583360764,
"eval_loss": 0.39711037278175354,
"eval_rouge1": 0.7106823471740515,
"eval_rouge2": 0.4766332327393774,
"eval_rougeL": 0.7069100507308859,
"eval_runtime": 2.6065,
"eval_samples_per_second": 116.631,
"eval_steps_per_second": 14.579,
"step": 1071
},
{
"epoch": 8.0,
"grad_norm": 0.5569229125976562,
"learning_rate": 3.5859375e-05,
"loss": 0.0741,
"step": 1224
},
{
"epoch": 8.0,
"eval_bleu": 0.4714652829533398,
"eval_loss": 0.3946935832500458,
"eval_rouge1": 0.7228506957910504,
"eval_rouge2": 0.48947047623829953,
"eval_rougeL": 0.7188907468330396,
"eval_runtime": 3.6852,
"eval_samples_per_second": 82.492,
"eval_steps_per_second": 10.311,
"step": 1224
},
{
"epoch": 8.0,
"step": 1224,
"total_flos": 2264172293259264.0,
"train_loss": 0.719257706910177,
"train_runtime": 2187.326,
"train_samples_per_second": 11.146,
"train_steps_per_second": 1.399
}
],
"logging_steps": 500,
"max_steps": 3060,
"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": 2264172293259264.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|