| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002033657023742946, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00020336570237429458, | |
| "grad_norm": 1.6416376829147339, | |
| "learning_rate": 2e-05, | |
| "loss": 1.6778, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00020336570237429458, | |
| "eval_loss": 1.6577199697494507, | |
| "eval_runtime": 54.2098, | |
| "eval_samples_per_second": 38.203, | |
| "eval_steps_per_second": 19.111, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00040673140474858916, | |
| "grad_norm": 1.3022700548171997, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3269, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006100971071228837, | |
| "grad_norm": 1.119146704673767, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4453, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006100971071228837, | |
| "eval_loss": 1.6513177156448364, | |
| "eval_runtime": 52.1816, | |
| "eval_samples_per_second": 39.688, | |
| "eval_steps_per_second": 19.854, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008134628094971783, | |
| "grad_norm": 1.2798656225204468, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3306, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001016828511871473, | |
| "grad_norm": 1.2064756155014038, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4827, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0012201942142457674, | |
| "grad_norm": 1.1611772775650024, | |
| "learning_rate": 0.00012, | |
| "loss": 1.3372, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0012201942142457674, | |
| "eval_loss": 1.5904638767242432, | |
| "eval_runtime": 52.4492, | |
| "eval_samples_per_second": 39.486, | |
| "eval_steps_per_second": 19.752, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001423559916620062, | |
| "grad_norm": 1.5832951068878174, | |
| "learning_rate": 0.00014, | |
| "loss": 1.5218, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0016269256189943566, | |
| "grad_norm": 1.4458744525909424, | |
| "learning_rate": 0.00016, | |
| "loss": 1.4054, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0018302913213686513, | |
| "grad_norm": 1.9726817607879639, | |
| "learning_rate": 0.00018, | |
| "loss": 1.1215, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0018302913213686513, | |
| "eval_loss": 1.4680432081222534, | |
| "eval_runtime": 52.0572, | |
| "eval_samples_per_second": 39.783, | |
| "eval_steps_per_second": 19.901, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002033657023742946, | |
| "grad_norm": 2.2048258781433105, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4054, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 760832065536000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |