| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08372093023255814, | |
| "eval_steps": 9, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002325581395348837, | |
| "eval_loss": 5.892056941986084, | |
| "eval_runtime": 19.7546, | |
| "eval_samples_per_second": 36.65, | |
| "eval_steps_per_second": 4.607, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0069767441860465115, | |
| "grad_norm": 3.488095760345459, | |
| "learning_rate": 1.5e-05, | |
| "loss": 5.9292, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013953488372093023, | |
| "grad_norm": 2.8731729984283447, | |
| "learning_rate": 3e-05, | |
| "loss": 5.7853, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.020930232558139535, | |
| "grad_norm": 4.2616777420043945, | |
| "learning_rate": 4.5e-05, | |
| "loss": 5.9753, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.020930232558139535, | |
| "eval_loss": 5.681079387664795, | |
| "eval_runtime": 19.8386, | |
| "eval_samples_per_second": 36.494, | |
| "eval_steps_per_second": 4.587, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.027906976744186046, | |
| "grad_norm": 4.38749361038208, | |
| "learning_rate": 4.993910125649561e-05, | |
| "loss": 5.632, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03488372093023256, | |
| "grad_norm": 4.592843055725098, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 4.9077, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04186046511627907, | |
| "grad_norm": 4.174410820007324, | |
| "learning_rate": 4.9031542398457974e-05, | |
| "loss": 4.5093, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04186046511627907, | |
| "eval_loss": 4.481910705566406, | |
| "eval_runtime": 19.8608, | |
| "eval_samples_per_second": 36.454, | |
| "eval_steps_per_second": 4.582, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04883720930232558, | |
| "grad_norm": 4.76424503326416, | |
| "learning_rate": 4.817959636416969e-05, | |
| "loss": 4.4965, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05581395348837209, | |
| "grad_norm": 4.088315963745117, | |
| "learning_rate": 4.707368982147318e-05, | |
| "loss": 3.9977, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06279069767441861, | |
| "grad_norm": 3.9060111045837402, | |
| "learning_rate": 4.572593931387604e-05, | |
| "loss": 3.9268, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06279069767441861, | |
| "eval_loss": 3.678138256072998, | |
| "eval_runtime": 19.8735, | |
| "eval_samples_per_second": 36.43, | |
| "eval_steps_per_second": 4.579, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06976744186046512, | |
| "grad_norm": 4.486081123352051, | |
| "learning_rate": 4.415111107797445e-05, | |
| "loss": 3.6693, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07674418604651163, | |
| "grad_norm": 3.4287188053131104, | |
| "learning_rate": 4.2366459261474933e-05, | |
| "loss": 3.0881, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08372093023255814, | |
| "grad_norm": 3.1772103309631348, | |
| "learning_rate": 4.039153688314145e-05, | |
| "loss": 3.2421, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08372093023255814, | |
| "eval_loss": 3.141343832015991, | |
| "eval_runtime": 19.8825, | |
| "eval_samples_per_second": 36.414, | |
| "eval_steps_per_second": 4.577, | |
| "step": 36 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9405135625125888.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |