| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.11013215859030837, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0022026431718061676, | |
| "eval_loss": 2.5054686069488525, | |
| "eval_runtime": 13.6537, | |
| "eval_samples_per_second": 14.062, | |
| "eval_steps_per_second": 7.031, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011013215859030838, | |
| "grad_norm": 36.081695556640625, | |
| "learning_rate": 5e-05, | |
| "loss": 8.9844, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.022026431718061675, | |
| "grad_norm": 22.822847366333008, | |
| "learning_rate": 0.0001, | |
| "loss": 8.2572, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.022026431718061675, | |
| "eval_loss": 1.457722783088684, | |
| "eval_runtime": 14.1465, | |
| "eval_samples_per_second": 13.572, | |
| "eval_steps_per_second": 6.786, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03303964757709251, | |
| "grad_norm": 14.934440612792969, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.16, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04405286343612335, | |
| "grad_norm": 11.843417167663574, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.9255, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04405286343612335, | |
| "eval_loss": 1.156875491142273, | |
| "eval_runtime": 14.4851, | |
| "eval_samples_per_second": 13.255, | |
| "eval_steps_per_second": 6.628, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05506607929515418, | |
| "grad_norm": 13.814435005187988, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.3731, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06607929515418502, | |
| "grad_norm": 14.297158241271973, | |
| "learning_rate": 5e-05, | |
| "loss": 4.2952, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06607929515418502, | |
| "eval_loss": 1.0599310398101807, | |
| "eval_runtime": 14.7414, | |
| "eval_samples_per_second": 13.025, | |
| "eval_steps_per_second": 6.512, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07709251101321586, | |
| "grad_norm": 12.437286376953125, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 4.5091, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0881057268722467, | |
| "grad_norm": 12.044346809387207, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 4.4237, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0881057268722467, | |
| "eval_loss": 1.0436935424804688, | |
| "eval_runtime": 14.842, | |
| "eval_samples_per_second": 12.936, | |
| "eval_steps_per_second": 6.468, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09911894273127753, | |
| "grad_norm": 10.710186004638672, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 4.2392, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11013215859030837, | |
| "grad_norm": 12.55030632019043, | |
| "learning_rate": 0.0, | |
| "loss": 4.104, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11013215859030837, | |
| "eval_loss": 1.0390212535858154, | |
| "eval_runtime": 14.8404, | |
| "eval_samples_per_second": 12.938, | |
| "eval_steps_per_second": 6.469, | |
| "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": 8763348929740800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |