| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.18285714285714286, | |
| "eval_steps": 13, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014065934065934066, | |
| "grad_norm": 0.37834057211875916, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3066, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014065934065934066, | |
| "eval_loss": 1.3235194683074951, | |
| "eval_runtime": 41.1821, | |
| "eval_samples_per_second": 11.631, | |
| "eval_steps_per_second": 2.914, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.028131868131868132, | |
| "grad_norm": 0.3664795160293579, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3373, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0421978021978022, | |
| "grad_norm": 0.576968789100647, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.322, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.056263736263736264, | |
| "grad_norm": 1.1225945949554443, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.2498, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07032967032967033, | |
| "grad_norm": 0.5157985687255859, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.1756, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0843956043956044, | |
| "grad_norm": 0.7155728936195374, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.1287, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09846153846153846, | |
| "grad_norm": 0.46939119696617126, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.0725, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11252747252747253, | |
| "grad_norm": 0.3746448755264282, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.009, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1265934065934066, | |
| "grad_norm": 0.3685707747936249, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.9849, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.14065934065934066, | |
| "grad_norm": 0.3576546907424927, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.9647, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15472527472527473, | |
| "grad_norm": 0.2630157470703125, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.9024, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1687912087912088, | |
| "grad_norm": 0.22557401657104492, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.8968, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.18285714285714286, | |
| "grad_norm": 0.2797858715057373, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.8649, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.18285714285714286, | |
| "eval_loss": 0.8646656274795532, | |
| "eval_runtime": 41.2959, | |
| "eval_samples_per_second": 11.599, | |
| "eval_steps_per_second": 2.906, | |
| "step": 13 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.7423994538675405e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |