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": 2.5,
|
| 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": 0.14285714285714285,
|
| 13 |
+
"grad_norm": 5.114527702331543,
|
| 14 |
+
"learning_rate": 0.00019998209226697376,
|
| 15 |
+
"loss": 0.7202,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.2857142857142857,
|
| 20 |
+
"grad_norm": 3.297234296798706,
|
| 21 |
+
"learning_rate": 0.00019784091409455728,
|
| 22 |
+
"loss": 0.3157,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.42857142857142855,
|
| 27 |
+
"grad_norm": 1.1975072622299194,
|
| 28 |
+
"learning_rate": 0.00019220586030376134,
|
| 29 |
+
"loss": 0.216,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.5714285714285714,
|
| 34 |
+
"grad_norm": 1.313912034034729,
|
| 35 |
+
"learning_rate": 0.00018327815731637612,
|
| 36 |
+
"loss": 0.1807,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.7142857142857143,
|
| 41 |
+
"grad_norm": 0.9035260677337646,
|
| 42 |
+
"learning_rate": 0.0001713766112687139,
|
| 43 |
+
"loss": 0.1576,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.8571428571428571,
|
| 48 |
+
"grad_norm": 1.169536828994751,
|
| 49 |
+
"learning_rate": 0.00015692622352080662,
|
| 50 |
+
"loss": 0.1362,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.0,
|
| 55 |
+
"grad_norm": 0.7937868237495422,
|
| 56 |
+
"learning_rate": 0.0001404430139595877,
|
| 57 |
+
"loss": 0.1172,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.1428571428571428,
|
| 62 |
+
"grad_norm": 0.6412622928619385,
|
| 63 |
+
"learning_rate": 0.00012251559405226941,
|
| 64 |
+
"loss": 0.1065,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.2857142857142856,
|
| 69 |
+
"grad_norm": 0.6135754585266113,
|
| 70 |
+
"learning_rate": 0.00010378414767176705,
|
| 71 |
+
"loss": 0.0952,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.4285714285714286,
|
| 76 |
+
"grad_norm": 0.6013264060020447,
|
| 77 |
+
"learning_rate": 8.491757028386263e-05,
|
| 78 |
+
"loss": 0.1005,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.5714285714285714,
|
| 83 |
+
"grad_norm": 0.7380222082138062,
|
| 84 |
+
"learning_rate": 6.658958285026102e-05,
|
| 85 |
+
"loss": 0.0794,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.7142857142857144,
|
| 90 |
+
"grad_norm": 0.42198696732521057,
|
| 91 |
+
"learning_rate": 4.945467341434195e-05,
|
| 92 |
+
"loss": 0.1008,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.8571428571428572,
|
| 97 |
+
"grad_norm": 0.3692607879638672,
|
| 98 |
+
"learning_rate": 3.4124725489820645e-05,
|
| 99 |
+
"loss": 0.0545,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 2.0,
|
| 104 |
+
"grad_norm": 0.5357337594032288,
|
| 105 |
+
"learning_rate": 2.1147167846963422e-05,
|
| 106 |
+
"loss": 0.0585,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 2.142857142857143,
|
| 111 |
+
"grad_norm": 0.45641225576400757,
|
| 112 |
+
"learning_rate": 1.0985425962260343e-05,
|
| 113 |
+
"loss": 0.0608,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.2857142857142856,
|
| 118 |
+
"grad_norm": 0.21990008652210236,
|
| 119 |
+
"learning_rate": 4.002373205607723e-06,
|
| 120 |
+
"loss": 0.0544,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 2.4285714285714284,
|
| 125 |
+
"grad_norm": 0.41038212180137634,
|
| 126 |
+
"learning_rate": 4.4737271914411236e-07,
|
| 127 |
+
"loss": 0.048,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.5,
|
| 132 |
+
"step": 175,
|
| 133 |
+
"total_flos": 6343017759525312.0,
|
| 134 |
+
"train_loss": 0.15042741894721984,
|
| 135 |
+
"train_runtime": 99.7314,
|
| 136 |
+
"train_samples_per_second": 28.075,
|
| 137 |
+
"train_steps_per_second": 1.755
|
| 138 |
+
}
|
| 139 |
+
],
|
| 140 |
+
"logging_steps": 10,
|
| 141 |
+
"max_steps": 175,
|
| 142 |
+
"num_input_tokens_seen": 0,
|
| 143 |
+
"num_train_epochs": 3,
|
| 144 |
+
"save_steps": 500,
|
| 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": 6343017759525312.0,
|
| 158 |
+
"train_batch_size": 16,
|
| 159 |
+
"trial_name": null,
|
| 160 |
+
"trial_params": null
|
| 161 |
+
}
|