| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.09237875288683603, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009237875288683603, | |
| "grad_norm": 3.1749510765075684, | |
| "learning_rate": 2e-05, | |
| "loss": 4.4439, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009237875288683603, | |
| "eval_loss": 4.263659954071045, | |
| "eval_runtime": 1.297, | |
| "eval_samples_per_second": 35.467, | |
| "eval_steps_per_second": 17.734, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018475750577367205, | |
| "grad_norm": 3.75960636138916, | |
| "learning_rate": 4e-05, | |
| "loss": 4.2244, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02771362586605081, | |
| "grad_norm": 3.0641653537750244, | |
| "learning_rate": 6e-05, | |
| "loss": 3.8892, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02771362586605081, | |
| "eval_loss": 4.239731311798096, | |
| "eval_runtime": 1.2435, | |
| "eval_samples_per_second": 36.993, | |
| "eval_steps_per_second": 18.496, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03695150115473441, | |
| "grad_norm": 2.6745448112487793, | |
| "learning_rate": 8e-05, | |
| "loss": 2.9137, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.046189376443418015, | |
| "grad_norm": 2.9670028686523438, | |
| "learning_rate": 0.0001, | |
| "loss": 3.6034, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05542725173210162, | |
| "grad_norm": 3.0863242149353027, | |
| "learning_rate": 0.00012, | |
| "loss": 3.797, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05542725173210162, | |
| "eval_loss": 3.926579236984253, | |
| "eval_runtime": 1.3038, | |
| "eval_samples_per_second": 35.282, | |
| "eval_steps_per_second": 17.641, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06466512702078522, | |
| "grad_norm": 2.756948709487915, | |
| "learning_rate": 0.00014, | |
| "loss": 3.0057, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07390300230946882, | |
| "grad_norm": 2.8316171169281006, | |
| "learning_rate": 0.00016, | |
| "loss": 3.4052, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08314087759815242, | |
| "grad_norm": 2.612847089767456, | |
| "learning_rate": 0.00018, | |
| "loss": 3.1095, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08314087759815242, | |
| "eval_loss": 3.4868814945220947, | |
| "eval_runtime": 1.2684, | |
| "eval_samples_per_second": 36.267, | |
| "eval_steps_per_second": 18.134, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09237875288683603, | |
| "grad_norm": 2.517549753189087, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4696, | |
| "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": 512599763976192.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |