| { | |
| "best_metric": 1.2362855672836304, | |
| "best_model_checkpoint": "output_dir/checkpoint-28", | |
| "epoch": 0.9633113828786454, | |
| "global_step": 32, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6.000000000000001e-07, | |
| "loss": 1.26, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 1.2716, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8e-06, | |
| "loss": 1.2689, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 1.2623, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.2529301643371582, | |
| "eval_runtime": 2.6555, | |
| "eval_samples_per_second": 4.142, | |
| "eval_steps_per_second": 0.753, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 3e-06, | |
| "loss": 1.2645, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 3.6e-06, | |
| "loss": 1.2639, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.2000000000000004e-06, | |
| "loss": 1.2666, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 1.2577, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.2524051666259766, | |
| "eval_runtime": 2.6436, | |
| "eval_samples_per_second": 4.161, | |
| "eval_steps_per_second": 0.757, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 5.4e-06, | |
| "loss": 1.2598, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 6e-06, | |
| "loss": 1.2494, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.6e-06, | |
| "loss": 1.2729, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.2e-06, | |
| "loss": 1.2504, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.2495826482772827, | |
| "eval_runtime": 2.6449, | |
| "eval_samples_per_second": 4.159, | |
| "eval_steps_per_second": 0.756, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.8e-06, | |
| "loss": 1.2594, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 1.2478, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9e-06, | |
| "loss": 1.2571, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 1.2502, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 1.245987057685852, | |
| "eval_runtime": 2.6496, | |
| "eval_samples_per_second": 4.152, | |
| "eval_steps_per_second": 0.755, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.02e-05, | |
| "loss": 1.2408, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.08e-05, | |
| "loss": 1.2666, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1.1400000000000001e-05, | |
| "loss": 1.2694, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.2481, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.241593599319458, | |
| "eval_runtime": 2.6487, | |
| "eval_samples_per_second": 4.153, | |
| "eval_steps_per_second": 0.755, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.26e-05, | |
| "loss": 1.2523, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.32e-05, | |
| "loss": 1.2447, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.3800000000000002e-05, | |
| "loss": 1.2409, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.44e-05, | |
| "loss": 1.2455, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.2387194633483887, | |
| "eval_runtime": 2.6492, | |
| "eval_samples_per_second": 4.152, | |
| "eval_steps_per_second": 0.755, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.2385, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.56e-05, | |
| "loss": 1.251, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.62e-05, | |
| "loss": 1.2328, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.6800000000000002e-05, | |
| "loss": 1.2447, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 1.2362855672836304, | |
| "eval_runtime": 2.6549, | |
| "eval_samples_per_second": 4.143, | |
| "eval_steps_per_second": 0.753, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.74e-05, | |
| "loss": 1.2494, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.8e-05, | |
| "loss": 1.2451, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.86e-05, | |
| "loss": 1.247, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.9200000000000003e-05, | |
| "loss": 1.2359, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 1.2393214702606201, | |
| "eval_runtime": 2.6499, | |
| "eval_samples_per_second": 4.151, | |
| "eval_steps_per_second": 0.755, | |
| "step": 32 | |
| } | |
| ], | |
| "max_steps": 42, | |
| "num_train_epochs": 2, | |
| "total_flos": 3.342473429558231e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |