File size: 5,205 Bytes
9a7d639 | 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_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.8421052631578947,
"eval_steps": 500,
"global_step": 150,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"entropy": 2.35390625,
"epoch": 0.19138755980861244,
"grad_norm": 1.577696681022644,
"learning_rate": 0.0001999145758387301,
"loss": 2.517007064819336,
"mean_token_accuracy": 0.4835851963609457,
"num_tokens": 32923.0,
"step": 10
},
{
"entropy": 1.953515625,
"epoch": 0.3827751196172249,
"grad_norm": 1.822049856185913,
"learning_rate": 0.00019694002659393305,
"loss": 1.814153289794922,
"mean_token_accuracy": 0.6044577240943909,
"num_tokens": 65628.0,
"step": 20
},
{
"entropy": 1.36533203125,
"epoch": 0.5741626794258373,
"grad_norm": 0.8370082974433899,
"learning_rate": 0.0001898390981891979,
"loss": 1.4171125411987304,
"mean_token_accuracy": 0.6942351691424846,
"num_tokens": 98592.0,
"step": 30
},
{
"entropy": 1.33076171875,
"epoch": 0.7655502392344498,
"grad_norm": 0.7550845146179199,
"learning_rate": 0.00017891405093963938,
"loss": 1.3193041801452636,
"mean_token_accuracy": 0.7104418903589249,
"num_tokens": 131278.0,
"step": 40
},
{
"entropy": 1.312109375,
"epoch": 0.9569377990430622,
"grad_norm": 0.6932047009468079,
"learning_rate": 0.00016462992378609407,
"loss": 1.3077256202697753,
"mean_token_accuracy": 0.7093201003968715,
"num_tokens": 164256.0,
"step": 50
},
{
"entropy": 1.3107052364864864,
"epoch": 1.1339712918660287,
"grad_norm": 0.7087656855583191,
"learning_rate": 0.00014759473930370736,
"loss": 1.2949213981628418,
"mean_token_accuracy": 0.7117355780021565,
"num_tokens": 194746.0,
"step": 60
},
{
"entropy": 1.26064453125,
"epoch": 1.325358851674641,
"grad_norm": 0.8213269710540771,
"learning_rate": 0.00012853362242491053,
"loss": 1.244191551208496,
"mean_token_accuracy": 0.7226051487028599,
"num_tokens": 227482.0,
"step": 70
},
{
"entropy": 1.2599609375,
"epoch": 1.5167464114832536,
"grad_norm": 0.7758288383483887,
"learning_rate": 0.00010825793454723325,
"loss": 1.2582054138183594,
"mean_token_accuracy": 0.7165695309638977,
"num_tokens": 260195.0,
"step": 80
},
{
"entropy": 1.25322265625,
"epoch": 1.7081339712918662,
"grad_norm": 0.7961016893386841,
"learning_rate": 8.763073687306524e-05,
"loss": 1.2671056747436524,
"mean_token_accuracy": 0.7158558055758476,
"num_tokens": 292968.0,
"step": 90
},
{
"entropy": 1.28291015625,
"epoch": 1.8995215311004785,
"grad_norm": 0.757343590259552,
"learning_rate": 6.753005307953167e-05,
"loss": 1.2647873878479003,
"mean_token_accuracy": 0.7167910523712635,
"num_tokens": 325911.0,
"step": 100
},
{
"entropy": 1.2690033783783783,
"epoch": 2.076555023923445,
"grad_norm": 0.7981213331222534,
"learning_rate": 4.8811495091039926e-05,
"loss": 1.2404365539550781,
"mean_token_accuracy": 0.7189428822414295,
"num_tokens": 356114.0,
"step": 110
},
{
"entropy": 1.25244140625,
"epoch": 2.2679425837320575,
"grad_norm": 0.7682023048400879,
"learning_rate": 3.2271842837425906e-05,
"loss": 1.2295378684997558,
"mean_token_accuracy": 0.7262546218931675,
"num_tokens": 388999.0,
"step": 120
},
{
"entropy": 1.22822265625,
"epoch": 2.45933014354067,
"grad_norm": 0.7267993688583374,
"learning_rate": 1.861512827298051e-05,
"loss": 1.2186729431152343,
"mean_token_accuracy": 0.7247538149356842,
"num_tokens": 422226.0,
"step": 130
},
{
"entropy": 1.2375,
"epoch": 2.650717703349282,
"grad_norm": 0.7193359136581421,
"learning_rate": 8.422667334494249e-06,
"loss": 1.2260663032531738,
"mean_token_accuracy": 0.7221008919179439,
"num_tokens": 454978.0,
"step": 140
},
{
"entropy": 1.21845703125,
"epoch": 2.8421052631578947,
"grad_norm": 0.7832261323928833,
"learning_rate": 2.128315467264552e-06,
"loss": 1.2313490867614747,
"mean_token_accuracy": 0.7239270724356175,
"num_tokens": 487664.0,
"step": 150
}
],
"logging_steps": 10,
"max_steps": 159,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 10,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1524702316230912.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|