File size: 5,169 Bytes
0f00821 |
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 |
{
"best_metric": 0.510191798210144,
"best_model_checkpoint": "./Vit-GPT2-COCO2017Flickr-85k-09/checkpoint-4000",
"epoch": 0.746477559018382,
"eval_steps": 500,
"global_step": 4000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.09330969487729775,
"grad_norm": 1.1049598455429077,
"learning_rate": 4.8444693293517484e-05,
"loss": 0.2429,
"step": 500
},
{
"epoch": 0.09330969487729775,
"eval_gen_len": 11.738,
"eval_loss": 0.5351373553276062,
"eval_rouge1": 39.4446,
"eval_rouge2": 14.1599,
"eval_rougeL": 35.6123,
"eval_rougeLsum": 35.5846,
"eval_runtime": 463.8252,
"eval_samples_per_second": 8.624,
"eval_steps_per_second": 2.156,
"step": 500
},
{
"epoch": 0.1866193897545955,
"grad_norm": 1.1426328420639038,
"learning_rate": 4.6889386587034965e-05,
"loss": 0.2537,
"step": 1000
},
{
"epoch": 0.1866193897545955,
"eval_gen_len": 12.34875,
"eval_loss": 0.5301018357276917,
"eval_rouge1": 39.5332,
"eval_rouge2": 14.4745,
"eval_rougeL": 35.644,
"eval_rougeLsum": 35.6159,
"eval_runtime": 451.0336,
"eval_samples_per_second": 8.869,
"eval_steps_per_second": 2.217,
"step": 1000
},
{
"epoch": 0.27992908463189325,
"grad_norm": 1.017817735671997,
"learning_rate": 4.5334079880552446e-05,
"loss": 0.2564,
"step": 1500
},
{
"epoch": 0.27992908463189325,
"eval_gen_len": 12.2455,
"eval_loss": 0.5198264122009277,
"eval_rouge1": 39.8297,
"eval_rouge2": 14.555,
"eval_rougeL": 35.8598,
"eval_rougeLsum": 35.8344,
"eval_runtime": 446.7054,
"eval_samples_per_second": 8.954,
"eval_steps_per_second": 2.239,
"step": 1500
},
{
"epoch": 0.373238779509191,
"grad_norm": 0.9865152835845947,
"learning_rate": 4.3778773174069934e-05,
"loss": 0.2585,
"step": 2000
},
{
"epoch": 0.373238779509191,
"eval_gen_len": 11.8575,
"eval_loss": 0.5207428932189941,
"eval_rouge1": 39.4558,
"eval_rouge2": 14.0496,
"eval_rougeL": 35.5597,
"eval_rougeLsum": 35.526,
"eval_runtime": 441.2453,
"eval_samples_per_second": 9.065,
"eval_steps_per_second": 2.266,
"step": 2000
},
{
"epoch": 0.4665484743864888,
"grad_norm": 0.9201194047927856,
"learning_rate": 4.222346646758741e-05,
"loss": 0.2579,
"step": 2500
},
{
"epoch": 0.4665484743864888,
"eval_gen_len": 11.97325,
"eval_loss": 0.5187843441963196,
"eval_rouge1": 39.1359,
"eval_rouge2": 14.125,
"eval_rougeL": 35.4068,
"eval_rougeLsum": 35.3709,
"eval_runtime": 456.9413,
"eval_samples_per_second": 8.754,
"eval_steps_per_second": 2.188,
"step": 2500
},
{
"epoch": 0.5598581692637865,
"grad_norm": 1.011809229850769,
"learning_rate": 4.066815976110489e-05,
"loss": 0.2588,
"step": 3000
},
{
"epoch": 0.5598581692637865,
"eval_gen_len": 12.278,
"eval_loss": 0.5195733904838562,
"eval_rouge1": 39.0831,
"eval_rouge2": 14.0658,
"eval_rougeL": 35.4608,
"eval_rougeLsum": 35.4283,
"eval_runtime": 453.7444,
"eval_samples_per_second": 8.816,
"eval_steps_per_second": 2.204,
"step": 3000
},
{
"epoch": 0.6531678641410843,
"grad_norm": 0.9602178931236267,
"learning_rate": 3.911285305462237e-05,
"loss": 0.2618,
"step": 3500
},
{
"epoch": 0.6531678641410843,
"eval_gen_len": 11.99425,
"eval_loss": 0.5193876028060913,
"eval_rouge1": 39.751,
"eval_rouge2": 14.443,
"eval_rougeL": 36.076,
"eval_rougeLsum": 36.0475,
"eval_runtime": 451.6054,
"eval_samples_per_second": 8.857,
"eval_steps_per_second": 2.214,
"step": 3500
},
{
"epoch": 0.746477559018382,
"grad_norm": 1.0043072700500488,
"learning_rate": 3.755754634813985e-05,
"loss": 0.2579,
"step": 4000
},
{
"epoch": 0.746477559018382,
"eval_gen_len": 12.05125,
"eval_loss": 0.510191798210144,
"eval_rouge1": 39.7601,
"eval_rouge2": 14.5095,
"eval_rougeL": 36.0252,
"eval_rougeLsum": 35.9857,
"eval_runtime": 450.2804,
"eval_samples_per_second": 8.883,
"eval_steps_per_second": 2.221,
"step": 4000
}
],
"logging_steps": 500,
"max_steps": 16074,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.1549689031688192e+19,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}
|