File size: 2,968 Bytes
c841dc6 32cda9a c841dc6 32cda9a c841dc6 32cda9a c841dc6 32cda9a c841dc6 32cda9a c841dc6 32cda9a c841dc6 32cda9a c841dc6 32cda9a c841dc6 32cda9a c841dc6 32cda9a c841dc6 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.0,
"eval_steps": 500.0,
"global_step": 5380,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 13.417204856872559,
"learning_rate": 1.8008368200836822e-05,
"loss": 1.4134,
"step": 1076
},
{
"epoch": 1.0,
"eval_f1": 0.7558544457720137,
"eval_loss": 0.8534303903579712,
"eval_runtime": 268.7511,
"eval_samples_per_second": 32.018,
"eval_steps_per_second": 1.001,
"step": 1076
},
{
"epoch": 2.0,
"grad_norm": 13.140690803527832,
"learning_rate": 1.3506276150627616e-05,
"loss": 0.7309,
"step": 2152
},
{
"epoch": 2.0,
"eval_f1": 0.7933829613883598,
"eval_loss": 0.7049058675765991,
"eval_runtime": 268.5786,
"eval_samples_per_second": 32.039,
"eval_steps_per_second": 1.002,
"step": 2152
},
{
"epoch": 3.0,
"grad_norm": 8.68571949005127,
"learning_rate": 9.004184100418411e-06,
"loss": 0.5277,
"step": 3228
},
{
"epoch": 3.0,
"eval_f1": 0.8081018590927308,
"eval_loss": 0.6787558197975159,
"eval_runtime": 277.348,
"eval_samples_per_second": 31.026,
"eval_steps_per_second": 0.97,
"step": 3228
},
{
"epoch": 4.0,
"grad_norm": 7.1122260093688965,
"learning_rate": 4.5020920502092055e-06,
"loss": 0.3819,
"step": 4304
},
{
"epoch": 4.0,
"eval_f1": 0.8077891874826753,
"eval_loss": 0.6842708587646484,
"eval_runtime": 271.8952,
"eval_samples_per_second": 31.648,
"eval_steps_per_second": 0.989,
"step": 4304
},
{
"epoch": 5.0,
"grad_norm": 10.43897819519043,
"learning_rate": 0.0,
"loss": 0.2865,
"step": 5380
},
{
"epoch": 5.0,
"eval_f1": 0.8082255356174132,
"eval_loss": 0.7049386501312256,
"eval_runtime": 260.8665,
"eval_samples_per_second": 32.986,
"eval_steps_per_second": 1.031,
"step": 5380
},
{
"epoch": 5.0,
"step": 5380,
"total_flos": 4.52871045169152e+16,
"train_loss": 0.6680765201611146,
"train_runtime": 28188.6693,
"train_samples_per_second": 6.105,
"train_steps_per_second": 0.191
}
],
"logging_steps": 500,
"max_steps": 5380,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4.52871045169152e+16,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}
|