| { | |
| "best_metric": 6.832160472869873, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-300", | |
| "epoch": 3.002421307506053, | |
| "eval_steps": 50, | |
| "global_step": 310, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009685230024213076, | |
| "eval_loss": 6.9340715408325195, | |
| "eval_runtime": 0.5256, | |
| "eval_samples_per_second": 1322.201, | |
| "eval_steps_per_second": 41.854, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.48426150121065376, | |
| "grad_norm": 0.3234892785549164, | |
| "learning_rate": 0.000202, | |
| "loss": 6.9004, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.48426150121065376, | |
| "eval_loss": 6.875490188598633, | |
| "eval_runtime": 0.5534, | |
| "eval_samples_per_second": 1255.76, | |
| "eval_steps_per_second": 39.751, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9685230024213075, | |
| "grad_norm": 0.33752018213272095, | |
| "learning_rate": 0.000202, | |
| "loss": 6.866, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9685230024213075, | |
| "eval_loss": 6.857929229736328, | |
| "eval_runtime": 0.5275, | |
| "eval_samples_per_second": 1317.608, | |
| "eval_steps_per_second": 41.708, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.4527845036319613, | |
| "grad_norm": 0.11755020171403885, | |
| "learning_rate": 0.000202, | |
| "loss": 6.9608, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.4527845036319613, | |
| "eval_loss": 6.850296497344971, | |
| "eval_runtime": 0.5241, | |
| "eval_samples_per_second": 1326.165, | |
| "eval_steps_per_second": 41.979, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.937046004842615, | |
| "grad_norm": 0.13267219066619873, | |
| "learning_rate": 0.000202, | |
| "loss": 6.8475, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.937046004842615, | |
| "eval_loss": 6.843703746795654, | |
| "eval_runtime": 0.7287, | |
| "eval_samples_per_second": 953.768, | |
| "eval_steps_per_second": 30.191, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.4213075060532687, | |
| "grad_norm": 0.09812537580728531, | |
| "learning_rate": 0.000202, | |
| "loss": 6.9513, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.4213075060532687, | |
| "eval_loss": 6.837970733642578, | |
| "eval_runtime": 0.6113, | |
| "eval_samples_per_second": 1136.934, | |
| "eval_steps_per_second": 35.989, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.9055690072639226, | |
| "grad_norm": 0.11069986969232559, | |
| "learning_rate": 0.000202, | |
| "loss": 6.8392, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.9055690072639226, | |
| "eval_loss": 6.832160472869873, | |
| "eval_runtime": 0.6393, | |
| "eval_samples_per_second": 1087.199, | |
| "eval_steps_per_second": 34.415, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 310, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 13046111711232.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |