| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006707807888382077, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00013415615776764153, | |
| "eval_loss": 1.7879987955093384, | |
| "eval_runtime": 205.7654, | |
| "eval_samples_per_second": 15.255, | |
| "eval_steps_per_second": 7.63, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006707807888382077, | |
| "grad_norm": 13.902657508850098, | |
| "learning_rate": 5e-05, | |
| "loss": 7.4147, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0013415615776764154, | |
| "grad_norm": 15.180018424987793, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9275, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0013415615776764154, | |
| "eval_loss": 1.6406546831130981, | |
| "eval_runtime": 206.8579, | |
| "eval_samples_per_second": 15.175, | |
| "eval_steps_per_second": 7.59, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002012342366514623, | |
| "grad_norm": 8.693984985351562, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.6114, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002683123155352831, | |
| "grad_norm": 6.609281063079834, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.9363, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002683123155352831, | |
| "eval_loss": 1.5450352430343628, | |
| "eval_runtime": 207.9166, | |
| "eval_samples_per_second": 15.097, | |
| "eval_steps_per_second": 7.551, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0033539039441910384, | |
| "grad_norm": 6.056999206542969, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 6.1428, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004024684733029246, | |
| "grad_norm": 7.0369720458984375, | |
| "learning_rate": 5e-05, | |
| "loss": 5.9678, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004024684733029246, | |
| "eval_loss": 1.520525574684143, | |
| "eval_runtime": 207.7442, | |
| "eval_samples_per_second": 15.11, | |
| "eval_steps_per_second": 7.557, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004695465521867454, | |
| "grad_norm": 6.093974590301514, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 6.4626, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005366246310705662, | |
| "grad_norm": 4.602436065673828, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 6.2598, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005366246310705662, | |
| "eval_loss": 1.5123776197433472, | |
| "eval_runtime": 207.4951, | |
| "eval_samples_per_second": 15.128, | |
| "eval_steps_per_second": 7.566, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006037027099543869, | |
| "grad_norm": 7.203092575073242, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 5.7316, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006707807888382077, | |
| "grad_norm": 11.299540519714355, | |
| "learning_rate": 0.0, | |
| "loss": 5.535, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006707807888382077, | |
| "eval_loss": 1.5105700492858887, | |
| "eval_runtime": 207.9992, | |
| "eval_samples_per_second": 15.091, | |
| "eval_steps_per_second": 7.548, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9205575120322560.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |