File size: 3,205 Bytes
75a9191 f52775b 75a9191 f52775b 75a9191 3ee30da 50c407d f52775b 75a9191 f52775b 75a9191 f52775b 75a9191 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.0020930354246245617,
"eval_steps": 3,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00020930354246245618,
"grad_norm": 1.836387276649475,
"learning_rate": 2e-05,
"loss": 2.5806,
"step": 1
},
{
"epoch": 0.00020930354246245618,
"eval_loss": 2.6074929237365723,
"eval_runtime": 74.4711,
"eval_samples_per_second": 27.017,
"eval_steps_per_second": 13.509,
"step": 1
},
{
"epoch": 0.00041860708492491236,
"grad_norm": 1.9787160158157349,
"learning_rate": 4e-05,
"loss": 2.5943,
"step": 2
},
{
"epoch": 0.0006279106273873685,
"grad_norm": 1.9100641012191772,
"learning_rate": 6e-05,
"loss": 2.5517,
"step": 3
},
{
"epoch": 0.0006279106273873685,
"eval_loss": 2.589639902114868,
"eval_runtime": 74.382,
"eval_samples_per_second": 27.05,
"eval_steps_per_second": 13.525,
"step": 3
},
{
"epoch": 0.0008372141698498247,
"grad_norm": 1.9031531810760498,
"learning_rate": 8e-05,
"loss": 2.6434,
"step": 4
},
{
"epoch": 0.0010465177123122808,
"grad_norm": 1.8470455408096313,
"learning_rate": 0.0001,
"loss": 2.6619,
"step": 5
},
{
"epoch": 0.001255821254774737,
"grad_norm": 1.7614034414291382,
"learning_rate": 0.00012,
"loss": 2.4174,
"step": 6
},
{
"epoch": 0.001255821254774737,
"eval_loss": 2.399675130844116,
"eval_runtime": 74.5311,
"eval_samples_per_second": 26.995,
"eval_steps_per_second": 13.498,
"step": 6
},
{
"epoch": 0.0014651247972371933,
"grad_norm": 1.3945518732070923,
"learning_rate": 0.00014,
"loss": 2.3177,
"step": 7
},
{
"epoch": 0.0016744283396996494,
"grad_norm": 1.2308992147445679,
"learning_rate": 0.00016,
"loss": 2.2551,
"step": 8
},
{
"epoch": 0.0018837318821621056,
"grad_norm": 1.1053471565246582,
"learning_rate": 0.00018,
"loss": 2.4466,
"step": 9
},
{
"epoch": 0.0018837318821621056,
"eval_loss": 2.251810312271118,
"eval_runtime": 74.4683,
"eval_samples_per_second": 27.018,
"eval_steps_per_second": 13.509,
"step": 9
},
{
"epoch": 0.0020930354246245617,
"grad_norm": 1.0251036882400513,
"learning_rate": 0.0002,
"loss": 2.2824,
"step": 10
}
],
"logging_steps": 1,
"max_steps": 10,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 3,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 887672762007552.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|