Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +161 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,161 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 175,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05714285714285714,
|
| 13 |
+
"grad_norm": 4.9967756271362305,
|
| 14 |
+
"learning_rate": 9.999104613348688e-05,
|
| 15 |
+
"loss": 1.1058,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.11428571428571428,
|
| 20 |
+
"grad_norm": 1.8961405754089355,
|
| 21 |
+
"learning_rate": 9.892045704727864e-05,
|
| 22 |
+
"loss": 0.3453,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.17142857142857143,
|
| 27 |
+
"grad_norm": 1.2652360200881958,
|
| 28 |
+
"learning_rate": 9.610293015188067e-05,
|
| 29 |
+
"loss": 0.2044,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.22857142857142856,
|
| 34 |
+
"grad_norm": 0.8738003373146057,
|
| 35 |
+
"learning_rate": 9.163907865818806e-05,
|
| 36 |
+
"loss": 0.165,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2857142857142857,
|
| 41 |
+
"grad_norm": 0.8198190927505493,
|
| 42 |
+
"learning_rate": 8.568830563435694e-05,
|
| 43 |
+
"loss": 0.132,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.34285714285714286,
|
| 48 |
+
"grad_norm": 0.7635666728019714,
|
| 49 |
+
"learning_rate": 7.846311176040331e-05,
|
| 50 |
+
"loss": 0.1211,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.4,
|
| 55 |
+
"grad_norm": 0.8185427784919739,
|
| 56 |
+
"learning_rate": 7.022150697979384e-05,
|
| 57 |
+
"loss": 0.1161,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.45714285714285713,
|
| 62 |
+
"grad_norm": 0.6302494406700134,
|
| 63 |
+
"learning_rate": 6.125779702613471e-05,
|
| 64 |
+
"loss": 0.1109,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.5142857142857142,
|
| 69 |
+
"grad_norm": 0.5293920040130615,
|
| 70 |
+
"learning_rate": 5.1892073835883524e-05,
|
| 71 |
+
"loss": 0.0961,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5714285714285714,
|
| 76 |
+
"grad_norm": 0.5659812092781067,
|
| 77 |
+
"learning_rate": 4.2458785141931314e-05,
|
| 78 |
+
"loss": 0.0822,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.6285714285714286,
|
| 83 |
+
"grad_norm": 0.4485885202884674,
|
| 84 |
+
"learning_rate": 3.329479142513051e-05,
|
| 85 |
+
"loss": 0.0927,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.6857142857142857,
|
| 90 |
+
"grad_norm": 0.5655118227005005,
|
| 91 |
+
"learning_rate": 2.4727336707170973e-05,
|
| 92 |
+
"loss": 0.0805,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.7428571428571429,
|
| 97 |
+
"grad_norm": 0.46993887424468994,
|
| 98 |
+
"learning_rate": 1.7062362744910322e-05,
|
| 99 |
+
"loss": 0.0737,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.8,
|
| 104 |
+
"grad_norm": 0.4176179766654968,
|
| 105 |
+
"learning_rate": 1.0573583923481711e-05,
|
| 106 |
+
"loss": 0.078,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.8571428571428571,
|
| 111 |
+
"grad_norm": 0.3602999448776245,
|
| 112 |
+
"learning_rate": 5.4927129811301715e-06,
|
| 113 |
+
"loss": 0.0776,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.9142857142857143,
|
| 118 |
+
"grad_norm": 0.43983834981918335,
|
| 119 |
+
"learning_rate": 2.0011866028038617e-06,
|
| 120 |
+
"loss": 0.0799,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.9714285714285714,
|
| 125 |
+
"grad_norm": 0.36634841561317444,
|
| 126 |
+
"learning_rate": 2.2368635957205618e-07,
|
| 127 |
+
"loss": 0.0728,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.0,
|
| 132 |
+
"step": 175,
|
| 133 |
+
"total_flos": 2.4449910045876e+16,
|
| 134 |
+
"train_loss": 0.17537879467010498,
|
| 135 |
+
"train_runtime": 249.8042,
|
| 136 |
+
"train_samples_per_second": 44.655,
|
| 137 |
+
"train_steps_per_second": 0.701
|
| 138 |
+
}
|
| 139 |
+
],
|
| 140 |
+
"logging_steps": 10,
|
| 141 |
+
"max_steps": 175,
|
| 142 |
+
"num_input_tokens_seen": 0,
|
| 143 |
+
"num_train_epochs": 1,
|
| 144 |
+
"save_steps": 10000,
|
| 145 |
+
"stateful_callbacks": {
|
| 146 |
+
"TrainerControl": {
|
| 147 |
+
"args": {
|
| 148 |
+
"should_epoch_stop": false,
|
| 149 |
+
"should_evaluate": false,
|
| 150 |
+
"should_log": false,
|
| 151 |
+
"should_save": true,
|
| 152 |
+
"should_training_stop": true
|
| 153 |
+
},
|
| 154 |
+
"attributes": {}
|
| 155 |
+
}
|
| 156 |
+
},
|
| 157 |
+
"total_flos": 2.4449910045876e+16,
|
| 158 |
+
"train_batch_size": 64,
|
| 159 |
+
"trial_name": null,
|
| 160 |
+
"trial_params": null
|
| 161 |
+
}
|