| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.001270513499205929, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014116816657843657, | |
| "grad_norm": 4.341556632425636e-06, | |
| "learning_rate": 2e-05, | |
| "loss": 46.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014116816657843657, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 17.9603, | |
| "eval_samples_per_second": 166.089, | |
| "eval_steps_per_second": 83.072, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00028233633315687313, | |
| "grad_norm": 5.458827217807993e-06, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00042350449973530967, | |
| "grad_norm": 1.301592965319287e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00042350449973530967, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 17.9586, | |
| "eval_samples_per_second": 166.104, | |
| "eval_steps_per_second": 83.08, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005646726663137463, | |
| "grad_norm": 5.268444056127919e-06, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007058408328921829, | |
| "grad_norm": 6.410667538148118e-06, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008470089994706193, | |
| "grad_norm": 1.0726905202318449e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008470089994706193, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 17.9538, | |
| "eval_samples_per_second": 166.148, | |
| "eval_steps_per_second": 83.102, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000988177166049056, | |
| "grad_norm": 5.360675459087361e-06, | |
| "learning_rate": 0.00014, | |
| "loss": 46.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0011293453326274925, | |
| "grad_norm": 3.938770987588214e-06, | |
| "learning_rate": 0.00016, | |
| "loss": 46.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001270513499205929, | |
| "grad_norm": 2.511269940441707e-06, | |
| "learning_rate": 0.00018, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001270513499205929, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 18.0409, | |
| "eval_samples_per_second": 165.347, | |
| "eval_steps_per_second": 82.701, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 353631092736.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |