File size: 2,760 Bytes
619d3be 71957dc d628db1 71957dc 619d3be d628db1 619d3be d628db1 512eb33 71957dc 619d3be d628db1 619d3be d628db1 619d3be d628db1 619d3be 71957dc 619d3be |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.06884377758164166,
"eval_steps": 10,
"global_step": 39,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00176522506619594,
"eval_loss": 19.31140899658203,
"eval_runtime": 61.8597,
"eval_samples_per_second": 3.864,
"eval_steps_per_second": 1.94,
"step": 1
},
{
"epoch": 0.0088261253309797,
"grad_norm": 60.404327392578125,
"learning_rate": 5e-05,
"loss": 20.5111,
"step": 5
},
{
"epoch": 0.0176522506619594,
"grad_norm": 70.15036010742188,
"learning_rate": 0.0001,
"loss": 13.7811,
"step": 10
},
{
"epoch": 0.0176522506619594,
"eval_loss": 5.2021636962890625,
"eval_runtime": 62.7015,
"eval_samples_per_second": 3.812,
"eval_steps_per_second": 1.914,
"step": 10
},
{
"epoch": 0.0264783759929391,
"grad_norm": 11.331101417541504,
"learning_rate": 9.619397662556435e-05,
"loss": 2.0677,
"step": 15
},
{
"epoch": 0.0353045013239188,
"grad_norm": 16.111406326293945,
"learning_rate": 8.535533905932738e-05,
"loss": 0.6305,
"step": 20
},
{
"epoch": 0.0353045013239188,
"eval_loss": 0.5223247408866882,
"eval_runtime": 62.8674,
"eval_samples_per_second": 3.802,
"eval_steps_per_second": 1.909,
"step": 20
},
{
"epoch": 0.0441306266548985,
"grad_norm": 9.063875198364258,
"learning_rate": 6.91341716182545e-05,
"loss": 0.5021,
"step": 25
},
{
"epoch": 0.0529567519858782,
"grad_norm": 4.586399078369141,
"learning_rate": 5e-05,
"loss": 0.4014,
"step": 30
},
{
"epoch": 0.0529567519858782,
"eval_loss": 0.47897952795028687,
"eval_runtime": 62.9044,
"eval_samples_per_second": 3.799,
"eval_steps_per_second": 1.908,
"step": 30
},
{
"epoch": 0.0617828773168579,
"grad_norm": 8.578695297241211,
"learning_rate": 3.086582838174551e-05,
"loss": 0.3658,
"step": 35
}
],
"logging_steps": 5,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 13,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.490651304689664e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|