| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0009331501594131523, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00010368335104590581, | |
| "grad_norm": 3.0784685611724854, | |
| "learning_rate": 2e-05, | |
| "loss": 4.447, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00010368335104590581, | |
| "eval_loss": 5.926819801330566, | |
| "eval_runtime": 128.7811, | |
| "eval_samples_per_second": 31.534, | |
| "eval_steps_per_second": 15.771, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00020736670209181162, | |
| "grad_norm": 2.9972970485687256, | |
| "learning_rate": 4e-05, | |
| "loss": 4.0703, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003110500531377174, | |
| "grad_norm": 5.277008533477783, | |
| "learning_rate": 6e-05, | |
| "loss": 6.7164, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003110500531377174, | |
| "eval_loss": 5.906362533569336, | |
| "eval_runtime": 126.4735, | |
| "eval_samples_per_second": 32.109, | |
| "eval_steps_per_second": 16.059, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00041473340418362323, | |
| "grad_norm": 5.633463382720947, | |
| "learning_rate": 8e-05, | |
| "loss": 7.6931, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.000518416755229529, | |
| "grad_norm": 5.243166923522949, | |
| "learning_rate": 0.0001, | |
| "loss": 6.1932, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006221001062754348, | |
| "grad_norm": 4.926774978637695, | |
| "learning_rate": 0.00012, | |
| "loss": 4.8144, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006221001062754348, | |
| "eval_loss": 5.45006799697876, | |
| "eval_runtime": 126.7821, | |
| "eval_samples_per_second": 32.031, | |
| "eval_steps_per_second": 16.02, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0007257834573213407, | |
| "grad_norm": 6.527495861053467, | |
| "learning_rate": 0.00014, | |
| "loss": 5.23, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0008294668083672465, | |
| "grad_norm": 6.611089706420898, | |
| "learning_rate": 0.00016, | |
| "loss": 4.4946, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0009331501594131523, | |
| "grad_norm": 9.765947341918945, | |
| "learning_rate": 0.00018, | |
| "loss": 4.7281, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009331501594131523, | |
| "eval_loss": 3.674236536026001, | |
| "eval_runtime": 126.6002, | |
| "eval_samples_per_second": 32.077, | |
| "eval_steps_per_second": 16.043, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1664607823331328.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |