| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9999232716949282, | |
| "eval_steps": 325, | |
| "global_step": 3258, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09974679659326326, | |
| "grad_norm": 0.548096239566803, | |
| "learning_rate": 0.00019526257508294887, | |
| "loss": 1.5773, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.09974679659326326, | |
| "eval_loss": 1.652037262916565, | |
| "eval_runtime": 27.5817, | |
| "eval_samples_per_second": 8.158, | |
| "eval_steps_per_second": 1.051, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.1994935931865265, | |
| "grad_norm": 0.6027694940567017, | |
| "learning_rate": 0.000181218401572851, | |
| "loss": 1.5494, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.1994935931865265, | |
| "eval_loss": 1.6099203824996948, | |
| "eval_runtime": 5.7955, | |
| "eval_samples_per_second": 38.823, | |
| "eval_steps_per_second": 5.004, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.2992403897797898, | |
| "grad_norm": 0.6409096121788025, | |
| "learning_rate": 0.00015923854154608087, | |
| "loss": 1.494, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.2992403897797898, | |
| "eval_loss": 1.578147292137146, | |
| "eval_runtime": 5.8035, | |
| "eval_samples_per_second": 38.77, | |
| "eval_steps_per_second": 4.997, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.398987186373053, | |
| "grad_norm": 0.5925875902175903, | |
| "learning_rate": 0.0001314706028781311, | |
| "loss": 1.4572, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.398987186373053, | |
| "eval_loss": 1.547926664352417, | |
| "eval_runtime": 5.8134, | |
| "eval_samples_per_second": 38.704, | |
| "eval_steps_per_second": 4.988, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.49873398296631627, | |
| "grad_norm": 0.6379241347312927, | |
| "learning_rate": 0.00010062773495652545, | |
| "loss": 1.4235, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.49873398296631627, | |
| "eval_loss": 1.5255458354949951, | |
| "eval_runtime": 5.8082, | |
| "eval_samples_per_second": 38.739, | |
| "eval_steps_per_second": 4.993, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.5984807795595796, | |
| "grad_norm": 0.5975103378295898, | |
| "learning_rate": 6.972353231601288e-05, | |
| "loss": 1.3928, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.5984807795595796, | |
| "eval_loss": 1.5090439319610596, | |
| "eval_runtime": 5.8049, | |
| "eval_samples_per_second": 38.76, | |
| "eval_steps_per_second": 4.996, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.6982275761528428, | |
| "grad_norm": 0.6661022901535034, | |
| "learning_rate": 4.1777582383253544e-05, | |
| "loss": 1.3739, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 0.6982275761528428, | |
| "eval_loss": 1.4930458068847656, | |
| "eval_runtime": 5.8001, | |
| "eval_samples_per_second": 38.792, | |
| "eval_steps_per_second": 5.0, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 0.797974372746106, | |
| "grad_norm": 0.6793079376220703, | |
| "learning_rate": 1.9520427668100704e-05, | |
| "loss": 1.358, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.797974372746106, | |
| "eval_loss": 1.4824761152267456, | |
| "eval_runtime": 5.818, | |
| "eval_samples_per_second": 38.673, | |
| "eval_steps_per_second": 4.985, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.8977211693393693, | |
| "grad_norm": 0.6308882236480713, | |
| "learning_rate": 5.126769951826171e-06, | |
| "loss": 1.346, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 0.8977211693393693, | |
| "eval_loss": 1.4790326356887817, | |
| "eval_runtime": 5.8187, | |
| "eval_samples_per_second": 38.668, | |
| "eval_steps_per_second": 4.984, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 0.9974679659326325, | |
| "grad_norm": 0.6218956112861633, | |
| "learning_rate": 2.9845539710304794e-09, | |
| "loss": 1.3467, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.9974679659326325, | |
| "eval_loss": 1.4782565832138062, | |
| "eval_runtime": 5.8403, | |
| "eval_samples_per_second": 38.525, | |
| "eval_steps_per_second": 4.966, | |
| "step": 3250 | |
| } | |
| ], | |
| "logging_steps": 325, | |
| "max_steps": 3258, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.666544425604825e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |