| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00035324767077317084, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.532476707731709e-05, | |
| "grad_norm": 0.2014792263507843, | |
| "learning_rate": 2e-05, | |
| "loss": 10.8416, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.532476707731709e-05, | |
| "eval_loss": 10.84003734588623, | |
| "eval_runtime": 30.25, | |
| "eval_samples_per_second": 394.049, | |
| "eval_steps_per_second": 197.025, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.064953415463417e-05, | |
| "grad_norm": 0.18090741336345673, | |
| "learning_rate": 4e-05, | |
| "loss": 10.8483, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00010597430123195125, | |
| "grad_norm": 0.30406999588012695, | |
| "learning_rate": 6e-05, | |
| "loss": 10.8258, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00010597430123195125, | |
| "eval_loss": 10.839991569519043, | |
| "eval_runtime": 29.3901, | |
| "eval_samples_per_second": 405.579, | |
| "eval_steps_per_second": 202.789, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00014129906830926835, | |
| "grad_norm": 0.23857171833515167, | |
| "learning_rate": 8e-05, | |
| "loss": 10.8423, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00017662383538658542, | |
| "grad_norm": 0.15420323610305786, | |
| "learning_rate": 0.0001, | |
| "loss": 10.8284, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0002119486024639025, | |
| "grad_norm": 0.15825432538986206, | |
| "learning_rate": 0.00012, | |
| "loss": 10.8331, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002119486024639025, | |
| "eval_loss": 10.839529037475586, | |
| "eval_runtime": 29.8094, | |
| "eval_samples_per_second": 399.873, | |
| "eval_steps_per_second": 199.937, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00024727336954121957, | |
| "grad_norm": 0.18373744189739227, | |
| "learning_rate": 0.00014, | |
| "loss": 10.8397, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0002825981366185367, | |
| "grad_norm": 0.1414632350206375, | |
| "learning_rate": 0.00016, | |
| "loss": 10.8336, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00031792290369585377, | |
| "grad_norm": 0.2193010002374649, | |
| "learning_rate": 0.00018, | |
| "loss": 10.8253, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00031792290369585377, | |
| "eval_loss": 10.838722229003906, | |
| "eval_runtime": 29.6607, | |
| "eval_samples_per_second": 401.878, | |
| "eval_steps_per_second": 200.939, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00035324767077317084, | |
| "grad_norm": 0.1909327358007431, | |
| "learning_rate": 0.0002, | |
| "loss": 10.8246, | |
| "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": 820295761920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |