| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "global_step": 26, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0, | |
| "loss": 2.6133, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.06519634211941905, | |
| "eval_loss": 2.625, | |
| "eval_runtime": 2.6754, | |
| "eval_samples_per_second": 29.154, | |
| "eval_steps_per_second": 1.121, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0, | |
| "loss": 2.6199, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.06519634211941905, | |
| "eval_loss": 2.625, | |
| "eval_runtime": 2.9539, | |
| "eval_samples_per_second": 26.406, | |
| "eval_steps_per_second": 1.016, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0, | |
| "loss": 2.7202, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_accuracy": 0.06575219652142729, | |
| "eval_loss": 2.611328125, | |
| "eval_runtime": 2.94, | |
| "eval_samples_per_second": 26.53, | |
| "eval_steps_per_second": 1.02, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6177, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_accuracy": 0.06575219652142729, | |
| "eval_loss": 2.611328125, | |
| "eval_runtime": 2.9241, | |
| "eval_samples_per_second": 26.675, | |
| "eval_steps_per_second": 1.026, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5422, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_accuracy": 0.06611081226465843, | |
| "eval_loss": 2.5703125, | |
| "eval_runtime": 2.6904, | |
| "eval_samples_per_second": 28.992, | |
| "eval_steps_per_second": 1.115, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5627, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_accuracy": 0.06623632777478931, | |
| "eval_loss": 2.556640625, | |
| "eval_runtime": 2.9307, | |
| "eval_samples_per_second": 26.615, | |
| "eval_steps_per_second": 1.024, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5784, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_accuracy": 0.06639770485924332, | |
| "eval_loss": 2.546875, | |
| "eval_runtime": 2.9555, | |
| "eval_samples_per_second": 26.391, | |
| "eval_steps_per_second": 1.015, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5264, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_accuracy": 0.06630805092343554, | |
| "eval_loss": 2.537109375, | |
| "eval_runtime": 2.6791, | |
| "eval_samples_per_second": 29.114, | |
| "eval_steps_per_second": 1.12, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3396, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_accuracy": 0.06695355926125157, | |
| "eval_loss": 2.533203125, | |
| "eval_runtime": 1.929, | |
| "eval_samples_per_second": 40.435, | |
| "eval_steps_per_second": 1.555, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4297, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_accuracy": 0.06734803657880581, | |
| "eval_loss": 2.52734375, | |
| "eval_runtime": 2.4146, | |
| "eval_samples_per_second": 32.304, | |
| "eval_steps_per_second": 1.242, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3914, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_accuracy": 0.06722252106867492, | |
| "eval_loss": 2.5234375, | |
| "eval_runtime": 2.4302, | |
| "eval_samples_per_second": 32.096, | |
| "eval_steps_per_second": 1.234, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 5e-05, | |
| "loss": 2.429, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_accuracy": 0.06709700555854402, | |
| "eval_loss": 2.51953125, | |
| "eval_runtime": 2.9318, | |
| "eval_samples_per_second": 26.605, | |
| "eval_steps_per_second": 1.023, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3055, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.06720459028151336, | |
| "eval_loss": 2.51171875, | |
| "eval_runtime": 2.9231, | |
| "eval_samples_per_second": 26.684, | |
| "eval_steps_per_second": 1.026, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7162, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_accuracy": 0.0671866594943518, | |
| "eval_loss": 2.521484375, | |
| "eval_runtime": 2.9212, | |
| "eval_samples_per_second": 26.702, | |
| "eval_steps_per_second": 1.027, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7264, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_accuracy": 0.06774251389636005, | |
| "eval_loss": 2.546875, | |
| "eval_runtime": 2.6863, | |
| "eval_samples_per_second": 29.036, | |
| "eval_steps_per_second": 1.117, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7559, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_accuracy": 0.06707907477138246, | |
| "eval_loss": 2.587890625, | |
| "eval_runtime": 2.9302, | |
| "eval_samples_per_second": 26.619, | |
| "eval_steps_per_second": 1.024, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7899, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_accuracy": 0.0667383898153129, | |
| "eval_loss": 2.611328125, | |
| "eval_runtime": 2.6864, | |
| "eval_samples_per_second": 29.035, | |
| "eval_steps_per_second": 1.117, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6465, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_accuracy": 0.06664873587950511, | |
| "eval_loss": 2.619140625, | |
| "eval_runtime": 2.9278, | |
| "eval_samples_per_second": 26.641, | |
| "eval_steps_per_second": 1.025, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5955, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_accuracy": 0.0670611439842209, | |
| "eval_loss": 2.607421875, | |
| "eval_runtime": 2.4278, | |
| "eval_samples_per_second": 32.128, | |
| "eval_steps_per_second": 1.236, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5389, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_accuracy": 0.06720459028151336, | |
| "eval_loss": 2.595703125, | |
| "eval_runtime": 2.6825, | |
| "eval_samples_per_second": 29.077, | |
| "eval_steps_per_second": 1.118, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5356, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_accuracy": 0.06697149004841313, | |
| "eval_loss": 2.5859375, | |
| "eval_runtime": 2.6798, | |
| "eval_samples_per_second": 29.107, | |
| "eval_steps_per_second": 1.119, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 5e-05, | |
| "loss": 1.386, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_accuracy": 0.06722252106867492, | |
| "eval_loss": 2.58203125, | |
| "eval_runtime": 2.9465, | |
| "eval_samples_per_second": 26.472, | |
| "eval_steps_per_second": 1.018, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7698, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_accuracy": 0.06695355926125157, | |
| "eval_loss": 2.57421875, | |
| "eval_runtime": 2.1897, | |
| "eval_samples_per_second": 35.622, | |
| "eval_steps_per_second": 1.37, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3923, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_accuracy": 0.06686390532544378, | |
| "eval_loss": 2.580078125, | |
| "eval_runtime": 2.6567, | |
| "eval_samples_per_second": 29.36, | |
| "eval_steps_per_second": 1.129, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4723, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_accuracy": 0.06722252106867492, | |
| "eval_loss": 2.58984375, | |
| "eval_runtime": 2.6764, | |
| "eval_samples_per_second": 29.144, | |
| "eval_steps_per_second": 1.121, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5653, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.06715079792002869, | |
| "eval_loss": 2.603515625, | |
| "eval_runtime": 2.4205, | |
| "eval_samples_per_second": 32.225, | |
| "eval_steps_per_second": 1.239, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 26, | |
| "total_flos": 2728683110400.0, | |
| "train_loss": 2.0602510892427883, | |
| "train_runtime": 142.5326, | |
| "train_samples_per_second": 5.837, | |
| "train_steps_per_second": 0.182 | |
| } | |
| ], | |
| "max_steps": 26, | |
| "num_train_epochs": 2, | |
| "total_flos": 2728683110400.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |