| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.3269309358398038, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016346546791990192, | |
| "eval_loss": 2.2051539421081543, | |
| "eval_runtime": 12.0166, | |
| "eval_samples_per_second": 21.47, | |
| "eval_steps_per_second": 10.735, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016346546791990192, | |
| "grad_norm": 2.336392641067505, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5648, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.032693093583980384, | |
| "grad_norm": 2.5723531246185303, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5003, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.049039640375970577, | |
| "grad_norm": 2.1780683994293213, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2044, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06538618716796077, | |
| "grad_norm": 2.092310667037964, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3239, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08173273395995095, | |
| "grad_norm": 1.9188865423202515, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2587, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08173273395995095, | |
| "eval_loss": 1.308348298072815, | |
| "eval_runtime": 10.9588, | |
| "eval_samples_per_second": 23.543, | |
| "eval_steps_per_second": 11.771, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09807928075194115, | |
| "grad_norm": 1.4257837533950806, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1839, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11442582754393134, | |
| "grad_norm": 2.2847580909729004, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2293, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.13077237433592154, | |
| "grad_norm": 1.782516598701477, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2192, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.14711892112791172, | |
| "grad_norm": 1.4419081211090088, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2495, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1634654679199019, | |
| "grad_norm": 1.44297456741333, | |
| "learning_rate": 0.0002, | |
| "loss": 1.296, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1634654679199019, | |
| "eval_loss": 1.2778656482696533, | |
| "eval_runtime": 10.9625, | |
| "eval_samples_per_second": 23.535, | |
| "eval_steps_per_second": 11.767, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17981201471189212, | |
| "grad_norm": 1.9191259145736694, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2289, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.1961585615038823, | |
| "grad_norm": 1.459952473640442, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2749, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2125051082958725, | |
| "grad_norm": 1.7037264108657837, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2096, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.22885165508786268, | |
| "grad_norm": 2.016850709915161, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2308, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2451982018798529, | |
| "grad_norm": 2.183500051498413, | |
| "learning_rate": 0.0002, | |
| "loss": 1.295, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2451982018798529, | |
| "eval_loss": 1.2615169286727905, | |
| "eval_runtime": 10.9704, | |
| "eval_samples_per_second": 23.518, | |
| "eval_steps_per_second": 11.759, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2615447486718431, | |
| "grad_norm": 1.81687331199646, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2538, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.2778912954638333, | |
| "grad_norm": 1.7752971649169922, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0968, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.29423784225582345, | |
| "grad_norm": 1.5799192190170288, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1737, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.31058438904781366, | |
| "grad_norm": 1.6626818180084229, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2231, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3269309358398038, | |
| "grad_norm": 1.9949339628219604, | |
| "learning_rate": 0.0002, | |
| "loss": 1.249, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3269309358398038, | |
| "eval_loss": 1.239590048789978, | |
| "eval_runtime": 10.9647, | |
| "eval_samples_per_second": 23.53, | |
| "eval_steps_per_second": 11.765, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.72600880873472e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |