AGI / checkpoint-39 /trainer_state.json
hardlyworking's picture
Training in progress, step 39, checkpoint
7335f30 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 39,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02564102564102564,
"grad_norm": 4.75,
"learning_rate": 0.0,
"loss": 2.8786,
"step": 1
},
{
"epoch": 0.05128205128205128,
"grad_norm": 8.0625,
"learning_rate": 2.5e-06,
"loss": 2.9525,
"step": 2
},
{
"epoch": 0.07692307692307693,
"grad_norm": 11.6875,
"learning_rate": 5e-06,
"loss": 2.7153,
"step": 3
},
{
"epoch": 0.10256410256410256,
"grad_norm": 12.4375,
"learning_rate": 7.500000000000001e-06,
"loss": 2.5826,
"step": 4
},
{
"epoch": 0.1282051282051282,
"grad_norm": 10.375,
"learning_rate": 1e-05,
"loss": 2.5254,
"step": 5
},
{
"epoch": 0.15384615384615385,
"grad_norm": 8.875,
"learning_rate": 9.998932083939657e-06,
"loss": 2.3523,
"step": 6
},
{
"epoch": 0.1794871794871795,
"grad_norm": 8.8125,
"learning_rate": 9.995728791936505e-06,
"loss": 2.2738,
"step": 7
},
{
"epoch": 0.20512820512820512,
"grad_norm": 7.28125,
"learning_rate": 9.990391492329341e-06,
"loss": 2.2553,
"step": 8
},
{
"epoch": 0.23076923076923078,
"grad_norm": 6.90625,
"learning_rate": 9.98292246503335e-06,
"loss": 2.1269,
"step": 9
},
{
"epoch": 0.2564102564102564,
"grad_norm": 6.875,
"learning_rate": 9.973324900566214e-06,
"loss": 2.1726,
"step": 10
},
{
"epoch": 0.28205128205128205,
"grad_norm": 7.25,
"learning_rate": 9.961602898685225e-06,
"loss": 2.087,
"step": 11
},
{
"epoch": 0.3076923076923077,
"grad_norm": 6.8125,
"learning_rate": 9.947761466636014e-06,
"loss": 2.0203,
"step": 12
},
{
"epoch": 0.3333333333333333,
"grad_norm": 7.03125,
"learning_rate": 9.931806517013612e-06,
"loss": 2.0242,
"step": 13
},
{
"epoch": 0.358974358974359,
"grad_norm": 6.53125,
"learning_rate": 9.913744865236798e-06,
"loss": 1.9997,
"step": 14
},
{
"epoch": 0.38461538461538464,
"grad_norm": 6.34375,
"learning_rate": 9.893584226636773e-06,
"loss": 1.8334,
"step": 15
},
{
"epoch": 0.41025641025641024,
"grad_norm": 6.40625,
"learning_rate": 9.871333213161438e-06,
"loss": 1.9528,
"step": 16
},
{
"epoch": 0.4358974358974359,
"grad_norm": 6.0,
"learning_rate": 9.847001329696653e-06,
"loss": 1.8608,
"step": 17
},
{
"epoch": 0.46153846153846156,
"grad_norm": 5.46875,
"learning_rate": 9.820598970006068e-06,
"loss": 1.8053,
"step": 18
},
{
"epoch": 0.48717948717948717,
"grad_norm": 5.15625,
"learning_rate": 9.792137412291265e-06,
"loss": 1.8232,
"step": 19
},
{
"epoch": 0.5128205128205128,
"grad_norm": 5.34375,
"learning_rate": 9.761628814374074e-06,
"loss": 1.7059,
"step": 20
},
{
"epoch": 0.5384615384615384,
"grad_norm": 5.15625,
"learning_rate": 9.729086208503174e-06,
"loss": 1.9746,
"step": 21
},
{
"epoch": 0.5641025641025641,
"grad_norm": 5.21875,
"learning_rate": 9.694523495787149e-06,
"loss": 1.6262,
"step": 22
},
{
"epoch": 0.5897435897435898,
"grad_norm": 4.96875,
"learning_rate": 9.657955440256396e-06,
"loss": 1.8171,
"step": 23
},
{
"epoch": 0.6153846153846154,
"grad_norm": 5.09375,
"learning_rate": 9.619397662556434e-06,
"loss": 1.7618,
"step": 24
},
{
"epoch": 0.6410256410256411,
"grad_norm": 5.25,
"learning_rate": 9.578866633275289e-06,
"loss": 1.711,
"step": 25
},
{
"epoch": 0.6666666666666666,
"grad_norm": 5.03125,
"learning_rate": 9.536379665907801e-06,
"loss": 1.5066,
"step": 26
},
{
"epoch": 0.6923076923076923,
"grad_norm": 5.625,
"learning_rate": 9.491954909459895e-06,
"loss": 1.4406,
"step": 27
},
{
"epoch": 0.717948717948718,
"grad_norm": 5.5,
"learning_rate": 9.445611340695926e-06,
"loss": 1.558,
"step": 28
},
{
"epoch": 0.7435897435897436,
"grad_norm": 4.9375,
"learning_rate": 9.397368756032445e-06,
"loss": 1.4596,
"step": 29
},
{
"epoch": 0.7692307692307693,
"grad_norm": 6.3125,
"learning_rate": 9.347247763081834e-06,
"loss": 1.6387,
"step": 30
},
{
"epoch": 0.7948717948717948,
"grad_norm": 8.75,
"learning_rate": 9.295269771849426e-06,
"loss": 1.5038,
"step": 31
},
{
"epoch": 0.8205128205128205,
"grad_norm": 7.0,
"learning_rate": 9.241456985587868e-06,
"loss": 2.154,
"step": 32
},
{
"epoch": 0.8461538461538461,
"grad_norm": 6.4375,
"learning_rate": 9.185832391312644e-06,
"loss": 1.9146,
"step": 33
},
{
"epoch": 0.8717948717948718,
"grad_norm": 6.8125,
"learning_rate": 9.12841974998278e-06,
"loss": 2.3066,
"step": 34
},
{
"epoch": 0.8974358974358975,
"grad_norm": 7.0,
"learning_rate": 9.069243586350976e-06,
"loss": 2.2234,
"step": 35
},
{
"epoch": 0.9230769230769231,
"grad_norm": 8.4375,
"learning_rate": 9.008329178487442e-06,
"loss": 2.9886,
"step": 36
},
{
"epoch": 0.9487179487179487,
"grad_norm": 9.5,
"learning_rate": 8.94570254698197e-06,
"loss": 4.0233,
"step": 37
},
{
"epoch": 0.9743589743589743,
"grad_norm": 13.1875,
"learning_rate": 8.881390443828788e-06,
"loss": 4.4944,
"step": 38
},
{
"epoch": 1.0,
"grad_norm": 45.75,
"learning_rate": 8.815420340999034e-06,
"loss": 6.7771,
"step": 39
}
],
"logging_steps": 1,
"max_steps": 156,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 39,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 6965180768452608.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}