| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.13872832369942195, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004624277456647399, | |
| "eval_loss": 8.074233055114746, | |
| "eval_runtime": 11.9008, | |
| "eval_samples_per_second": 7.731, | |
| "eval_steps_per_second": 3.865, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013872832369942197, | |
| "grad_norm": 11.582316398620605, | |
| "learning_rate": 6e-05, | |
| "loss": 7.5988, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.027745664739884393, | |
| "grad_norm": 12.307031631469727, | |
| "learning_rate": 0.00012, | |
| "loss": 8.0135, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03699421965317919, | |
| "eval_loss": 3.775078058242798, | |
| "eval_runtime": 12.045, | |
| "eval_samples_per_second": 7.638, | |
| "eval_steps_per_second": 3.819, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04161849710982659, | |
| "grad_norm": 12.446931838989258, | |
| "learning_rate": 0.00018, | |
| "loss": 5.2833, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.055491329479768786, | |
| "grad_norm": 4.806489944458008, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.8637, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06936416184971098, | |
| "grad_norm": 8.42613697052002, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.2632, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07398843930635839, | |
| "eval_loss": 1.535495638847351, | |
| "eval_runtime": 12.1233, | |
| "eval_samples_per_second": 7.589, | |
| "eval_steps_per_second": 3.794, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08323699421965318, | |
| "grad_norm": 7.994266510009766, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.8054, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09710982658959537, | |
| "grad_norm": 6.297595500946045, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.9978, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11098265895953757, | |
| "grad_norm": 5.638557434082031, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.1281, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11098265895953757, | |
| "eval_loss": 1.1503130197525024, | |
| "eval_runtime": 12.1214, | |
| "eval_samples_per_second": 7.59, | |
| "eval_steps_per_second": 3.795, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12485549132947976, | |
| "grad_norm": 3.9357333183288574, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.9166, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.13872832369942195, | |
| "grad_norm": 4.9822821617126465, | |
| "learning_rate": 0.0, | |
| "loss": 0.6963, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 70, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5084301722910720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |