| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0031573131265293236, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00031573131265293233, | |
| "grad_norm": 1.4962332248687744, | |
| "learning_rate": 2e-05, | |
| "loss": 2.5499, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00031573131265293233, | |
| "eval_loss": 2.672800302505493, | |
| "eval_runtime": 56.9792, | |
| "eval_samples_per_second": 23.412, | |
| "eval_steps_per_second": 11.706, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006314626253058647, | |
| "grad_norm": 1.0282105207443237, | |
| "learning_rate": 4e-05, | |
| "loss": 2.3552, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000947193937958797, | |
| "grad_norm": 1.3773936033248901, | |
| "learning_rate": 6e-05, | |
| "loss": 2.7189, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000947193937958797, | |
| "eval_loss": 2.6626687049865723, | |
| "eval_runtime": 59.1777, | |
| "eval_samples_per_second": 22.542, | |
| "eval_steps_per_second": 11.271, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012629252506117293, | |
| "grad_norm": 1.4192756414413452, | |
| "learning_rate": 8e-05, | |
| "loss": 2.7306, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0015786565632646618, | |
| "grad_norm": 1.209413766860962, | |
| "learning_rate": 0.0001, | |
| "loss": 2.43, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001894387875917594, | |
| "grad_norm": 1.26327645778656, | |
| "learning_rate": 0.00012, | |
| "loss": 2.498, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001894387875917594, | |
| "eval_loss": 2.5173232555389404, | |
| "eval_runtime": 59.6766, | |
| "eval_samples_per_second": 22.354, | |
| "eval_steps_per_second": 11.177, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0022101191885705264, | |
| "grad_norm": 1.3896536827087402, | |
| "learning_rate": 0.00014, | |
| "loss": 2.5012, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0025258505012234586, | |
| "grad_norm": 1.2694809436798096, | |
| "learning_rate": 0.00016, | |
| "loss": 2.5385, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0028415818138763913, | |
| "grad_norm": 2.028712034225464, | |
| "learning_rate": 0.00018, | |
| "loss": 2.5697, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0028415818138763913, | |
| "eval_loss": 2.3210620880126953, | |
| "eval_runtime": 59.7473, | |
| "eval_samples_per_second": 22.327, | |
| "eval_steps_per_second": 11.164, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0031573131265293236, | |
| "grad_norm": 1.7280672788619995, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2445, | |
| "step": 10 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 501714738216960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |