| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.027855153203342618, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009285051067780873, | |
| "eval_loss": 3.4421591758728027, | |
| "eval_runtime": 54.9323, | |
| "eval_samples_per_second": 8.265, | |
| "eval_steps_per_second": 4.132, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002785515320334262, | |
| "grad_norm": 1.5922422409057617, | |
| "learning_rate": 6e-05, | |
| "loss": 2.9704, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005571030640668524, | |
| "grad_norm": 2.1471335887908936, | |
| "learning_rate": 0.00012, | |
| "loss": 2.7577, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007428040854224698, | |
| "eval_loss": 2.2313766479492188, | |
| "eval_runtime": 55.48, | |
| "eval_samples_per_second": 8.183, | |
| "eval_steps_per_second": 4.092, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008356545961002786, | |
| "grad_norm": 2.8449294567108154, | |
| "learning_rate": 0.00018, | |
| "loss": 2.6853, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011142061281337047, | |
| "grad_norm": 2.071516513824463, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.6996, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.013927576601671309, | |
| "grad_norm": 2.842288017272949, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.9961, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.014856081708449397, | |
| "eval_loss": 0.799162745475769, | |
| "eval_runtime": 55.6393, | |
| "eval_samples_per_second": 8.16, | |
| "eval_steps_per_second": 4.08, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.016713091922005572, | |
| "grad_norm": 3.066357135772705, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.8692, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.019498607242339833, | |
| "grad_norm": 1.3947068452835083, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.6499, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.022284122562674095, | |
| "grad_norm": 2.0286121368408203, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.6987, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.022284122562674095, | |
| "eval_loss": 0.6432320475578308, | |
| "eval_runtime": 55.6588, | |
| "eval_samples_per_second": 8.157, | |
| "eval_steps_per_second": 4.078, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.025069637883008356, | |
| "grad_norm": 1.1979644298553467, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.6975, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.027855153203342618, | |
| "grad_norm": 1.3303799629211426, | |
| "learning_rate": 0.0, | |
| "loss": 0.5651, | |
| "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": 9886937540198400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |