| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.4841386675834656, | |
| "learning_rate": 4.997807075247146e-05, | |
| "loss": 0.688, | |
| "num_input_tokens_seen": 46776, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.3365215063095093, | |
| "learning_rate": 4.991232148123761e-05, | |
| "loss": 0.763, | |
| "num_input_tokens_seen": 85136, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.5198595523834229, | |
| "learning_rate": 4.980286753286195e-05, | |
| "loss": 0.6882, | |
| "num_input_tokens_seen": 126584, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.40807807445526123, | |
| "learning_rate": 4.964990092676263e-05, | |
| "loss": 0.6951, | |
| "num_input_tokens_seen": 167968, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.439756840467453, | |
| "learning_rate": 4.9453690018345144e-05, | |
| "loss": 0.5008, | |
| "num_input_tokens_seen": 206832, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.45932796597480774, | |
| "learning_rate": 4.9214579028215776e-05, | |
| "loss": 0.542, | |
| "num_input_tokens_seen": 243656, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.3281826376914978, | |
| "learning_rate": 4.893298743830168e-05, | |
| "loss": 0.5369, | |
| "num_input_tokens_seen": 284016, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.2551577389240265, | |
| "learning_rate": 4.860940925593703e-05, | |
| "loss": 0.4948, | |
| "num_input_tokens_seen": 327408, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.5936368107795715, | |
| "learning_rate": 4.8244412147206284e-05, | |
| "loss": 0.5244, | |
| "num_input_tokens_seen": 363376, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.2480110377073288, | |
| "learning_rate": 4.783863644106502e-05, | |
| "loss": 0.421, | |
| "num_input_tokens_seen": 398840, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.4601157307624817, | |
| "learning_rate": 4.7392794005985326e-05, | |
| "loss": 0.4517, | |
| "num_input_tokens_seen": 436136, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.6387960314750671, | |
| "learning_rate": 4.690766700109659e-05, | |
| "loss": 0.4661, | |
| "num_input_tokens_seen": 475856, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.4365377128124237, | |
| "learning_rate": 4.638410650401267e-05, | |
| "loss": 0.4928, | |
| "num_input_tokens_seen": 514496, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.2992519438266754, | |
| "learning_rate": 4.5823031017752485e-05, | |
| "loss": 0.5424, | |
| "num_input_tokens_seen": 554424, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.828787088394165, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 0.5419, | |
| "num_input_tokens_seen": 593264, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.2943418622016907, | |
| "learning_rate": 4.4592336433146e-05, | |
| "loss": 0.4558, | |
| "num_input_tokens_seen": 630264, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.3707512617111206, | |
| "learning_rate": 4.3924876391293915e-05, | |
| "loss": 0.5656, | |
| "num_input_tokens_seen": 668864, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.4809654653072357, | |
| "learning_rate": 4.3224215685535294e-05, | |
| "loss": 0.4832, | |
| "num_input_tokens_seen": 712504, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.516292929649353, | |
| "learning_rate": 4.249158351283414e-05, | |
| "loss": 0.4626, | |
| "num_input_tokens_seen": 748872, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.5604212284088135, | |
| "learning_rate": 4.172826515897146e-05, | |
| "loss": 0.4837, | |
| "num_input_tokens_seen": 788408, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 375, | |
| "num_input_tokens_seen": 788408, | |
| "num_train_epochs": 3, | |
| "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": 3.3542680298389504e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |