| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03656307129798903, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003656307129798903, | |
| "grad_norm": 0.09328000247478485, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3619, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003656307129798903, | |
| "eval_loss": 10.363189697265625, | |
| "eval_runtime": 0.5775, | |
| "eval_samples_per_second": 798.302, | |
| "eval_steps_per_second": 100.437, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007312614259597806, | |
| "grad_norm": 0.08740244060754776, | |
| "learning_rate": 4e-05, | |
| "loss": 10.36, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010968921389396709, | |
| "grad_norm": 0.08197702467441559, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3704, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010968921389396709, | |
| "eval_loss": 10.363097190856934, | |
| "eval_runtime": 0.5623, | |
| "eval_samples_per_second": 819.818, | |
| "eval_steps_per_second": 103.144, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014625228519195612, | |
| "grad_norm": 0.06572431325912476, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3638, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.018281535648994516, | |
| "grad_norm": 0.0900840014219284, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3618, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.021937842778793418, | |
| "grad_norm": 0.0838831216096878, | |
| "learning_rate": 0.00012, | |
| "loss": 10.361, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.021937842778793418, | |
| "eval_loss": 10.362741470336914, | |
| "eval_runtime": 0.5688, | |
| "eval_samples_per_second": 810.488, | |
| "eval_steps_per_second": 101.97, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.025594149908592323, | |
| "grad_norm": 0.09633658081293106, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3703, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.029250457038391225, | |
| "grad_norm": 0.088631272315979, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3625, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03290676416819013, | |
| "grad_norm": 0.09016067534685135, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3623, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03290676416819013, | |
| "eval_loss": 10.3621187210083, | |
| "eval_runtime": 0.559, | |
| "eval_samples_per_second": 824.669, | |
| "eval_steps_per_second": 103.754, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03656307129798903, | |
| "grad_norm": 0.07421699911355972, | |
| "learning_rate": 0.0002, | |
| "loss": 10.363, | |
| "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": 4184195727360.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |