stage2 / checkpoint-5000 /trainer_state.json
yinyil's picture
Upload model checkpoint
2682527 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.21367521367521367,
"eval_steps": 500,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.004273504273504274,
"grad_norm": 1.0,
"learning_rate": 0.0,
"loss": 0.0,
"step": 1
},
{
"epoch": 0.008547008547008548,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 2
},
{
"epoch": 0.01282051282051282,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 3
},
{
"epoch": 0.017094017094017096,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 4
},
{
"epoch": 0.021367521367521368,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 5
},
{
"epoch": 0.02564102564102564,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 6
},
{
"epoch": 0.029914529914529916,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 7
},
{
"epoch": 0.03418803418803419,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 8
},
{
"epoch": 0.038461538461538464,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 9
},
{
"epoch": 0.042735042735042736,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 10
},
{
"epoch": 0.04700854700854701,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 11
},
{
"epoch": 0.05128205128205128,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 12
},
{
"epoch": 0.05555555555555555,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 13
},
{
"epoch": 0.05982905982905983,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 14
},
{
"epoch": 0.0641025641025641,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 15
},
{
"epoch": 0.06837606837606838,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 16
},
{
"epoch": 0.07264957264957266,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 17
},
{
"epoch": 0.07692307692307693,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 18
},
{
"epoch": 0.0811965811965812,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 19
},
{
"epoch": 0.08547008547008547,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 20
},
{
"epoch": 0.08974358974358974,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 21
},
{
"epoch": 0.09401709401709402,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 22
},
{
"epoch": 0.09829059829059829,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 23
},
{
"epoch": 0.10256410256410256,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 24
},
{
"epoch": 0.10683760683760683,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 25
},
{
"epoch": 0.1111111111111111,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 26
},
{
"epoch": 0.11538461538461539,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 27
},
{
"epoch": 0.11965811965811966,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 28
},
{
"epoch": 0.12393162393162394,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 29
},
{
"epoch": 0.1282051282051282,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 30
},
{
"epoch": 0.13247863247863248,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 31
},
{
"epoch": 0.13675213675213677,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 32
},
{
"epoch": 0.14102564102564102,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 33
},
{
"epoch": 0.1452991452991453,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 34
},
{
"epoch": 0.14957264957264957,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 35
},
{
"epoch": 0.15384615384615385,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 36
},
{
"epoch": 0.1581196581196581,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 37
},
{
"epoch": 0.1623931623931624,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 38
},
{
"epoch": 0.16666666666666666,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 39
},
{
"epoch": 0.17094017094017094,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 40
},
{
"epoch": 0.1752136752136752,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 41
},
{
"epoch": 0.1794871794871795,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 42
},
{
"epoch": 0.18376068376068377,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 43
},
{
"epoch": 0.18803418803418803,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 44
},
{
"epoch": 0.19230769230769232,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 45
},
{
"epoch": 0.19658119658119658,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 46
},
{
"epoch": 0.20085470085470086,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 47
},
{
"epoch": 0.20512820512820512,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 48
},
{
"epoch": 0.2094017094017094,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 49
},
{
"epoch": 0.21367521367521367,
"grad_norm": 1.0,
"learning_rate": 1e-06,
"loss": 0.0,
"step": 50
}
],
"logging_steps": 1.0,
"max_steps": 234,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 4.160371933000499e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}