| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.1847133757961785, | |
| "eval_steps": 25, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.3797595190380762e-05, | |
| "loss": 1.5869, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.343457579612732, | |
| "eval_runtime": 45.0202, | |
| "eval_samples_per_second": 6.775, | |
| "eval_steps_per_second": 0.444, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.2545090180360722e-05, | |
| "loss": 0.998, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 1.230006456375122, | |
| "eval_runtime": 45.0029, | |
| "eval_samples_per_second": 6.777, | |
| "eval_steps_per_second": 0.444, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.1292585170340683e-05, | |
| "loss": 0.8627, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.1211909055709839, | |
| "eval_runtime": 45.0426, | |
| "eval_samples_per_second": 6.771, | |
| "eval_steps_per_second": 0.444, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.0040080160320643e-05, | |
| "loss": 0.8958, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.1045145988464355, | |
| "eval_runtime": 45.2025, | |
| "eval_samples_per_second": 6.747, | |
| "eval_steps_per_second": 0.442, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.87875751503006e-05, | |
| "loss": 0.8205, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.0842006206512451, | |
| "eval_runtime": 45.2525, | |
| "eval_samples_per_second": 6.74, | |
| "eval_steps_per_second": 0.442, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.7535070140280564e-05, | |
| "loss": 0.8141, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 1.0894731283187866, | |
| "eval_runtime": 45.1805, | |
| "eval_samples_per_second": 6.751, | |
| "eval_steps_per_second": 0.443, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 1.628256513026052e-05, | |
| "loss": 0.6384, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 1.1109672784805298, | |
| "eval_runtime": 45.2193, | |
| "eval_samples_per_second": 6.745, | |
| "eval_steps_per_second": 0.442, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 1.5030060120240483e-05, | |
| "loss": 0.5813, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 1.1189604997634888, | |
| "eval_runtime": 45.2591, | |
| "eval_samples_per_second": 6.739, | |
| "eval_steps_per_second": 0.442, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.3777555110220442e-05, | |
| "loss": 0.568, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 1.1027684211730957, | |
| "eval_runtime": 45.2328, | |
| "eval_samples_per_second": 6.743, | |
| "eval_steps_per_second": 0.442, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 1.25250501002004e-05, | |
| "loss": 0.5605, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 1.1073968410491943, | |
| "eval_runtime": 45.4023, | |
| "eval_samples_per_second": 6.718, | |
| "eval_steps_per_second": 0.441, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 1.1272545090180361e-05, | |
| "loss": 0.6342, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 1.091808557510376, | |
| "eval_runtime": 45.3362, | |
| "eval_samples_per_second": 6.728, | |
| "eval_steps_per_second": 0.441, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.0020040080160322e-05, | |
| "loss": 0.5254, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_loss": 1.1066254377365112, | |
| "eval_runtime": 45.2929, | |
| "eval_samples_per_second": 6.734, | |
| "eval_steps_per_second": 0.442, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 8.767535070140282e-06, | |
| "loss": 0.4553, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_loss": 1.1803815364837646, | |
| "eval_runtime": 45.0968, | |
| "eval_samples_per_second": 6.763, | |
| "eval_steps_per_second": 0.443, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 7.515030060120242e-06, | |
| "loss": 0.3712, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "eval_loss": 1.1674922704696655, | |
| "eval_runtime": 45.0974, | |
| "eval_samples_per_second": 6.763, | |
| "eval_steps_per_second": 0.443, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 6.2625250501002e-06, | |
| "loss": 0.363, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "eval_loss": 1.180160403251648, | |
| "eval_runtime": 45.1473, | |
| "eval_samples_per_second": 6.756, | |
| "eval_steps_per_second": 0.443, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 5.010020040080161e-06, | |
| "loss": 0.3732, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_loss": 1.1637239456176758, | |
| "eval_runtime": 45.18, | |
| "eval_samples_per_second": 6.751, | |
| "eval_steps_per_second": 0.443, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 3.757515030060121e-06, | |
| "loss": 0.4188, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "eval_loss": 1.1796648502349854, | |
| "eval_runtime": 45.1853, | |
| "eval_samples_per_second": 6.75, | |
| "eval_steps_per_second": 0.443, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 2.5050100200400804e-06, | |
| "loss": 0.3395, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "eval_loss": 1.179069995880127, | |
| "eval_runtime": 45.3296, | |
| "eval_samples_per_second": 6.728, | |
| "eval_steps_per_second": 0.441, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 1.2525050100200402e-06, | |
| "loss": 0.3736, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "eval_loss": 1.176107406616211, | |
| "eval_runtime": 45.2686, | |
| "eval_samples_per_second": 6.738, | |
| "eval_steps_per_second": 0.442, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 0.0, | |
| "loss": 0.2538, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "eval_loss": 1.2055637836456299, | |
| "eval_runtime": 45.3063, | |
| "eval_samples_per_second": 6.732, | |
| "eval_steps_per_second": 0.441, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "total_flos": 6.571164044781158e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |