| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1932367149758454, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003864734299516908, | |
| "eval_loss": 1.2902684211730957, | |
| "eval_runtime": 3.5672, | |
| "eval_samples_per_second": 30.556, | |
| "eval_steps_per_second": 15.418, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01932367149758454, | |
| "grad_norm": 0.6564427018165588, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3111, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03864734299516908, | |
| "grad_norm": 0.5247552394866943, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2628, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03864734299516908, | |
| "eval_loss": 1.176567554473877, | |
| "eval_runtime": 3.5334, | |
| "eval_samples_per_second": 30.848, | |
| "eval_steps_per_second": 15.566, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.057971014492753624, | |
| "grad_norm": 0.5658605694770813, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.0942, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07729468599033816, | |
| "grad_norm": 0.6282858848571777, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0907, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07729468599033816, | |
| "eval_loss": 1.0020767450332642, | |
| "eval_runtime": 3.5628, | |
| "eval_samples_per_second": 30.594, | |
| "eval_steps_per_second": 15.437, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0966183574879227, | |
| "grad_norm": 0.8027504086494446, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.0194, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11594202898550725, | |
| "grad_norm": 0.638428807258606, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9467, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11594202898550725, | |
| "eval_loss": 0.9218775033950806, | |
| "eval_runtime": 3.6095, | |
| "eval_samples_per_second": 30.198, | |
| "eval_steps_per_second": 15.238, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13526570048309178, | |
| "grad_norm": 0.5790292024612427, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.9089, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.15458937198067632, | |
| "grad_norm": 0.5379019975662231, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.8976, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15458937198067632, | |
| "eval_loss": 0.9009591341018677, | |
| "eval_runtime": 3.7422, | |
| "eval_samples_per_second": 29.127, | |
| "eval_steps_per_second": 14.697, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.17391304347826086, | |
| "grad_norm": 0.5341059565544128, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8818, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1932367149758454, | |
| "grad_norm": 0.5725721716880798, | |
| "learning_rate": 0.0, | |
| "loss": 0.8781, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1932367149758454, | |
| "eval_loss": 0.8982807993888855, | |
| "eval_runtime": 3.5629, | |
| "eval_samples_per_second": 30.593, | |
| "eval_steps_per_second": 15.437, | |
| "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": 1278959891251200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |