| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.044033465433729636, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008806693086745927, | |
| "eval_loss": 2.842715263366699, | |
| "eval_runtime": 28.1021, | |
| "eval_samples_per_second": 17.045, | |
| "eval_steps_per_second": 8.54, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004403346543372964, | |
| "grad_norm": 3.2524631023406982, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7593, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008806693086745927, | |
| "grad_norm": 2.635131359100342, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4351, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008806693086745927, | |
| "eval_loss": 1.8852890729904175, | |
| "eval_runtime": 28.2782, | |
| "eval_samples_per_second": 16.939, | |
| "eval_steps_per_second": 8.487, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013210039630118891, | |
| "grad_norm": 2.1910648345947266, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.5255, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017613386173491855, | |
| "grad_norm": 1.6279373168945312, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3832, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017613386173491855, | |
| "eval_loss": 1.3052610158920288, | |
| "eval_runtime": 28.4848, | |
| "eval_samples_per_second": 16.816, | |
| "eval_steps_per_second": 8.426, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.022016732716864818, | |
| "grad_norm": 2.2754812240600586, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.352, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.026420079260237782, | |
| "grad_norm": 1.4691051244735718, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3647, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.026420079260237782, | |
| "eval_loss": 1.2375024557113647, | |
| "eval_runtime": 28.6253, | |
| "eval_samples_per_second": 16.733, | |
| "eval_steps_per_second": 8.384, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.030823425803610745, | |
| "grad_norm": 1.1990418434143066, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2334, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03522677234698371, | |
| "grad_norm": 1.8508553504943848, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.2463, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03522677234698371, | |
| "eval_loss": 1.2069017887115479, | |
| "eval_runtime": 28.8696, | |
| "eval_samples_per_second": 16.592, | |
| "eval_steps_per_second": 8.313, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03963011889035667, | |
| "grad_norm": 1.2702170610427856, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2539, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.044033465433729636, | |
| "grad_norm": 1.3754183053970337, | |
| "learning_rate": 0.0, | |
| "loss": 1.2967, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.044033465433729636, | |
| "eval_loss": 1.2023138999938965, | |
| "eval_runtime": 28.2484, | |
| "eval_samples_per_second": 16.957, | |
| "eval_steps_per_second": 8.496, | |
| "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": 8239114616832000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |