| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02706359945872801, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0027063599458728013, | |
| "grad_norm": 0.3031483292579651, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3979, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027063599458728013, | |
| "eval_loss": 1.4137667417526245, | |
| "eval_runtime": 5.872, | |
| "eval_samples_per_second": 26.567, | |
| "eval_steps_per_second": 13.283, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005412719891745603, | |
| "grad_norm": 0.24451163411140442, | |
| "learning_rate": 4e-05, | |
| "loss": 1.2556, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008119079837618403, | |
| "grad_norm": 0.2696416974067688, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4115, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008119079837618403, | |
| "eval_loss": 1.4126489162445068, | |
| "eval_runtime": 5.9008, | |
| "eval_samples_per_second": 26.437, | |
| "eval_steps_per_second": 13.219, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010825439783491205, | |
| "grad_norm": 0.29474467039108276, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5426, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013531799729364006, | |
| "grad_norm": 0.29974591732025146, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4793, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.016238159675236806, | |
| "grad_norm": 0.28576919436454773, | |
| "learning_rate": 0.00012, | |
| "loss": 1.3248, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016238159675236806, | |
| "eval_loss": 1.399493932723999, | |
| "eval_runtime": 5.9106, | |
| "eval_samples_per_second": 26.393, | |
| "eval_steps_per_second": 13.197, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.018944519621109608, | |
| "grad_norm": 0.33248502016067505, | |
| "learning_rate": 0.00014, | |
| "loss": 1.4732, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02165087956698241, | |
| "grad_norm": 0.31335920095443726, | |
| "learning_rate": 0.00016, | |
| "loss": 1.3168, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02435723951285521, | |
| "grad_norm": 0.33156827092170715, | |
| "learning_rate": 0.00018, | |
| "loss": 1.2647, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02435723951285521, | |
| "eval_loss": 1.3555694818496704, | |
| "eval_runtime": 5.8806, | |
| "eval_samples_per_second": 26.528, | |
| "eval_steps_per_second": 13.264, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02706359945872801, | |
| "grad_norm": 0.35090094804763794, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2927, | |
| "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": 1168569347604480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |