| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.028421202216853774, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005684240443370755, | |
| "eval_loss": 2.8276350498199463, | |
| "eval_runtime": 25.2196, | |
| "eval_samples_per_second": 29.382, | |
| "eval_steps_per_second": 14.711, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002842120221685377, | |
| "grad_norm": 1.7927579879760742, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7472, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005684240443370754, | |
| "grad_norm": 1.2981140613555908, | |
| "learning_rate": 0.0001, | |
| "loss": 2.75, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005684240443370754, | |
| "eval_loss": 2.746225595474243, | |
| "eval_runtime": 23.5398, | |
| "eval_samples_per_second": 31.479, | |
| "eval_steps_per_second": 15.761, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008526360665056132, | |
| "grad_norm": 1.5926852226257324, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.7407, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011368480886741509, | |
| "grad_norm": 1.3921397924423218, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.5602, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011368480886741509, | |
| "eval_loss": 2.611686944961548, | |
| "eval_runtime": 23.8562, | |
| "eval_samples_per_second": 31.061, | |
| "eval_steps_per_second": 15.552, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014210601108426887, | |
| "grad_norm": 1.8295120000839233, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.4627, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017052721330112264, | |
| "grad_norm": 1.563904047012329, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5953, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.017052721330112264, | |
| "eval_loss": 2.5551862716674805, | |
| "eval_runtime": 23.1565, | |
| "eval_samples_per_second": 32.0, | |
| "eval_steps_per_second": 16.021, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.019894841551797642, | |
| "grad_norm": 1.4566407203674316, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.626, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.022736961773483017, | |
| "grad_norm": 1.1897921562194824, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.4745, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.022736961773483017, | |
| "eval_loss": 2.5388574600219727, | |
| "eval_runtime": 23.4466, | |
| "eval_samples_per_second": 31.604, | |
| "eval_steps_per_second": 15.823, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.025579081995168396, | |
| "grad_norm": 1.4539854526519775, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.5339, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.028421202216853774, | |
| "grad_norm": 1.9134925603866577, | |
| "learning_rate": 0.0, | |
| "loss": 2.4908, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.028421202216853774, | |
| "eval_loss": 2.535639524459839, | |
| "eval_runtime": 23.4513, | |
| "eval_samples_per_second": 31.597, | |
| "eval_steps_per_second": 15.82, | |
| "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": 462998451781632.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |