| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4, | |
| "eval_steps": 25, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.18923527002334595, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 1.1779, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 0.7435017824172974, | |
| "eval_runtime": 621.1563, | |
| "eval_samples_per_second": 4.356, | |
| "eval_steps_per_second": 0.546, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.16780352592468262, | |
| "learning_rate": 0.00019148936170212768, | |
| "loss": 1.2708, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 0.7384106516838074, | |
| "eval_runtime": 619.3795, | |
| "eval_samples_per_second": 4.369, | |
| "eval_steps_per_second": 0.547, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.1804531365633011, | |
| "learning_rate": 0.00018085106382978726, | |
| "loss": 1.2848, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 0.7341726422309875, | |
| "eval_runtime": 619.225, | |
| "eval_samples_per_second": 4.37, | |
| "eval_steps_per_second": 0.547, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.17204701900482178, | |
| "learning_rate": 0.00017021276595744682, | |
| "loss": 1.3443, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 0.7313376665115356, | |
| "eval_runtime": 619.8363, | |
| "eval_samples_per_second": 4.366, | |
| "eval_steps_per_second": 0.547, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.2668892741203308, | |
| "learning_rate": 0.00015957446808510637, | |
| "loss": 1.2563, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.7282304167747498, | |
| "eval_runtime": 619.962, | |
| "eval_samples_per_second": 4.365, | |
| "eval_steps_per_second": 0.547, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.21089820563793182, | |
| "learning_rate": 0.00014893617021276596, | |
| "loss": 0.7529, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 0.7184526324272156, | |
| "eval_runtime": 619.2606, | |
| "eval_samples_per_second": 4.37, | |
| "eval_steps_per_second": 0.547, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.158623605966568, | |
| "learning_rate": 0.00013829787234042554, | |
| "loss": 0.7957, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 0.7136204242706299, | |
| "eval_runtime": 619.6757, | |
| "eval_samples_per_second": 4.367, | |
| "eval_steps_per_second": 0.547, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.16229337453842163, | |
| "learning_rate": 0.00012765957446808513, | |
| "loss": 0.7322, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 0.7111368179321289, | |
| "eval_runtime": 620.1668, | |
| "eval_samples_per_second": 4.363, | |
| "eval_steps_per_second": 0.547, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.0317260660736e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |