| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.010225994477962982, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00020451988955925963, | |
| "eval_loss": 0.6167752146720886, | |
| "eval_runtime": 139.0642, | |
| "eval_samples_per_second": 14.806, | |
| "eval_steps_per_second": 7.407, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010225994477962982, | |
| "grad_norm": 0.5801008939743042, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6021, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0020451988955925964, | |
| "grad_norm": 0.6938685178756714, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4494, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0020451988955925964, | |
| "eval_loss": 0.37807127833366394, | |
| "eval_runtime": 140.2577, | |
| "eval_samples_per_second": 14.68, | |
| "eval_steps_per_second": 7.344, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0030677983433888946, | |
| "grad_norm": 0.7771623134613037, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.29, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004090397791185193, | |
| "grad_norm": 0.19722718000411987, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1783, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004090397791185193, | |
| "eval_loss": 0.15935975313186646, | |
| "eval_runtime": 140.3087, | |
| "eval_samples_per_second": 14.675, | |
| "eval_steps_per_second": 7.341, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005112997238981491, | |
| "grad_norm": 0.08959358930587769, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1371, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006135596686777789, | |
| "grad_norm": 0.0525275394320488, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1393, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006135596686777789, | |
| "eval_loss": 0.14109905064105988, | |
| "eval_runtime": 140.6257, | |
| "eval_samples_per_second": 14.642, | |
| "eval_steps_per_second": 7.324, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0071581961345740875, | |
| "grad_norm": 0.8137596845626831, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1435, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.008180795582370386, | |
| "grad_norm": 0.042203761637210846, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1276, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008180795582370386, | |
| "eval_loss": 0.13725407421588898, | |
| "eval_runtime": 140.2588, | |
| "eval_samples_per_second": 14.68, | |
| "eval_steps_per_second": 7.344, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.009203395030166683, | |
| "grad_norm": 0.029296882450580597, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1244, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.010225994477962982, | |
| "grad_norm": 0.0394265353679657, | |
| "learning_rate": 0.0, | |
| "loss": 0.1291, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010225994477962982, | |
| "eval_loss": 0.1366967409849167, | |
| "eval_runtime": 139.8716, | |
| "eval_samples_per_second": 14.721, | |
| "eval_steps_per_second": 7.364, | |
| "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": 9247821240729600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |