| { | |
| "best_metric": 0.8172414302825928, | |
| "best_model_checkpoint": "LLAMA-2-7b-hf-PEFT/checkpoint-1348", | |
| "epoch": 2.99671412924425, | |
| "eval_steps": 4, | |
| "global_step": 1368, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.0077, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7998, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.8747, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6885, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 1.7869740724563599, | |
| "eval_runtime": 3.4333, | |
| "eval_samples_per_second": 29.127, | |
| "eval_steps_per_second": 3.786, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.000125, | |
| "loss": 1.9789, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.808, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.000175, | |
| "loss": 1.6725, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6229, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 1.7403819561004639, | |
| "eval_runtime": 3.4401, | |
| "eval_samples_per_second": 29.069, | |
| "eval_steps_per_second": 3.779, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5738, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0002, | |
| "loss": 1.932, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6953, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7503, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.627682089805603, | |
| "eval_runtime": 3.4533, | |
| "eval_samples_per_second": 28.958, | |
| "eval_steps_per_second": 3.765, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5776, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4024, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6076, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4796, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.4830929040908813, | |
| "eval_runtime": 3.4545, | |
| "eval_samples_per_second": 28.947, | |
| "eval_steps_per_second": 3.763, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0002, | |
| "loss": 1.565, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6577, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5091, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3101, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.322540283203125, | |
| "eval_runtime": 3.4697, | |
| "eval_samples_per_second": 28.821, | |
| "eval_steps_per_second": 3.747, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2438, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0002, | |
| "loss": 1.346, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1465, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4575, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.1680691242218018, | |
| "eval_runtime": 3.4759, | |
| "eval_samples_per_second": 28.769, | |
| "eval_steps_per_second": 3.74, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3599, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1736, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1476, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0009, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 1.1021325588226318, | |
| "eval_runtime": 3.4778, | |
| "eval_samples_per_second": 28.754, | |
| "eval_steps_per_second": 3.738, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1319, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3331, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9467, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0251, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.0456668138504028, | |
| "eval_runtime": 3.4679, | |
| "eval_samples_per_second": 28.836, | |
| "eval_steps_per_second": 3.749, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2271, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3582, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2554, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0875, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 0.9981789588928223, | |
| "eval_runtime": 3.4677, | |
| "eval_samples_per_second": 28.837, | |
| "eval_steps_per_second": 3.749, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0664, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1394, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9655, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0002, | |
| "loss": 0.938, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 0.9676372408866882, | |
| "eval_runtime": 3.4748, | |
| "eval_samples_per_second": 28.778, | |
| "eval_steps_per_second": 3.741, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9469, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0661, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9326, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9331, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 0.9470236301422119, | |
| "eval_runtime": 3.4722, | |
| "eval_samples_per_second": 28.8, | |
| "eval_steps_per_second": 3.744, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002, | |
| "loss": 1.005, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1431, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0028, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8603, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 0.9357610940933228, | |
| "eval_runtime": 3.481, | |
| "eval_samples_per_second": 28.728, | |
| "eval_steps_per_second": 3.735, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1787, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2374, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1186, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8113, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 0.926858127117157, | |
| "eval_runtime": 3.4721, | |
| "eval_samples_per_second": 28.801, | |
| "eval_steps_per_second": 3.744, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9935, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1052, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8798, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0077, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 0.9184084534645081, | |
| "eval_runtime": 3.4903, | |
| "eval_samples_per_second": 28.651, | |
| "eval_steps_per_second": 3.725, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0691, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0652, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9312, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1558, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 0.9105428457260132, | |
| "eval_runtime": 3.4906, | |
| "eval_samples_per_second": 28.649, | |
| "eval_steps_per_second": 3.724, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0857, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8427, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002, | |
| "loss": 0.906, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9327, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 0.9041263461112976, | |
| "eval_runtime": 3.4894, | |
| "eval_samples_per_second": 28.658, | |
| "eval_steps_per_second": 3.726, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002, | |
| "loss": 0.877, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8569, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1053, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002, | |
| "loss": 1.169, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 0.8986607193946838, | |
| "eval_runtime": 3.4903, | |
| "eval_samples_per_second": 28.651, | |
| "eval_steps_per_second": 3.725, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8297, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9673, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002, | |
| "loss": 1.049, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0075, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 0.8944993615150452, | |
| "eval_runtime": 3.4866, | |
| "eval_samples_per_second": 28.682, | |
| "eval_steps_per_second": 3.729, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8988, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9227, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1501, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8621, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 0.8898262977600098, | |
| "eval_runtime": 3.4913, | |
| "eval_samples_per_second": 28.643, | |
| "eval_steps_per_second": 3.724, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9068, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8608, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0274, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8345, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 0.8855961561203003, | |
| "eval_runtime": 3.4903, | |
| "eval_samples_per_second": 28.651, | |
| "eval_steps_per_second": 3.725, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8912, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9515, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7498, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1278, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 0.8823689222335815, | |
| "eval_runtime": 3.4864, | |
| "eval_samples_per_second": 28.683, | |
| "eval_steps_per_second": 3.729, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8484, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9954, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0488, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9979, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 0.8804557919502258, | |
| "eval_runtime": 3.4879, | |
| "eval_samples_per_second": 28.671, | |
| "eval_steps_per_second": 3.727, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0619, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9397, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7289, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7371, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 0.8777076601982117, | |
| "eval_runtime": 3.4887, | |
| "eval_samples_per_second": 28.664, | |
| "eval_steps_per_second": 3.726, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8001, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9608, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8056, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9574, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 0.8759266138076782, | |
| "eval_runtime": 3.488, | |
| "eval_samples_per_second": 28.67, | |
| "eval_steps_per_second": 3.727, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8549, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9981, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.863, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9378, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 0.8762518167495728, | |
| "eval_runtime": 3.4851, | |
| "eval_samples_per_second": 28.693, | |
| "eval_steps_per_second": 3.73, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9577, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002, | |
| "loss": 1.194, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0092, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7806, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 0.8743546009063721, | |
| "eval_runtime": 3.4938, | |
| "eval_samples_per_second": 28.622, | |
| "eval_steps_per_second": 3.721, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7722, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7899, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1671, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0132, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 0.8724913001060486, | |
| "eval_runtime": 3.4954, | |
| "eval_samples_per_second": 28.609, | |
| "eval_steps_per_second": 3.719, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0002, | |
| "loss": 0.999, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2216, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8801, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1339, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.8698344230651855, | |
| "eval_runtime": 3.49, | |
| "eval_samples_per_second": 28.653, | |
| "eval_steps_per_second": 3.725, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8881, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9083, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9187, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8045, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.8685845732688904, | |
| "eval_runtime": 3.4981, | |
| "eval_samples_per_second": 28.587, | |
| "eval_steps_per_second": 3.716, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8902, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0695, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9901, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1322, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 0.8671762347221375, | |
| "eval_runtime": 3.4975, | |
| "eval_samples_per_second": 28.592, | |
| "eval_steps_per_second": 3.717, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8606, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1307, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8565, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8822, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 0.8666442036628723, | |
| "eval_runtime": 3.4864, | |
| "eval_samples_per_second": 28.683, | |
| "eval_steps_per_second": 3.729, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1007, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1187, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8467, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9659, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 0.8653787970542908, | |
| "eval_runtime": 3.4913, | |
| "eval_samples_per_second": 28.642, | |
| "eval_steps_per_second": 3.723, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9716, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002, | |
| "loss": 1.011, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0902, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7997, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 0.8643788695335388, | |
| "eval_runtime": 3.4962, | |
| "eval_samples_per_second": 28.602, | |
| "eval_steps_per_second": 3.718, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0298, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7997, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0904, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9132, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 0.8625090718269348, | |
| "eval_runtime": 3.5, | |
| "eval_samples_per_second": 28.571, | |
| "eval_steps_per_second": 3.714, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7391, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1868, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0002, | |
| "loss": 0.866, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0377, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 0.8603898882865906, | |
| "eval_runtime": 3.4933, | |
| "eval_samples_per_second": 28.627, | |
| "eval_steps_per_second": 3.721, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8362, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7876, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9629, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8505, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 0.8604779839515686, | |
| "eval_runtime": 3.4948, | |
| "eval_samples_per_second": 28.614, | |
| "eval_steps_per_second": 3.72, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7891, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0308, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9131, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002, | |
| "loss": 1.246, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 0.8592937588691711, | |
| "eval_runtime": 3.4918, | |
| "eval_samples_per_second": 28.638, | |
| "eval_steps_per_second": 3.723, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1544, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7868, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9292, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8001, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 0.8578882813453674, | |
| "eval_runtime": 3.4915, | |
| "eval_samples_per_second": 28.641, | |
| "eval_steps_per_second": 3.723, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9272, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0228, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8947, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0124, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 0.8576824069023132, | |
| "eval_runtime": 3.5039, | |
| "eval_samples_per_second": 28.54, | |
| "eval_steps_per_second": 3.71, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6479, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6833, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9448, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7368, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 0.8575372099876404, | |
| "eval_runtime": 3.5008, | |
| "eval_samples_per_second": 28.565, | |
| "eval_steps_per_second": 3.713, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7793, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7328, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8388, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9842, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 0.8574979901313782, | |
| "eval_runtime": 3.4997, | |
| "eval_samples_per_second": 28.574, | |
| "eval_steps_per_second": 3.715, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0994, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8176, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0385, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9269, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 0.8572396636009216, | |
| "eval_runtime": 3.5038, | |
| "eval_samples_per_second": 28.541, | |
| "eval_steps_per_second": 3.71, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8281, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2095, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0002, | |
| "loss": 1.035, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6981, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 0.8553718328475952, | |
| "eval_runtime": 3.4957, | |
| "eval_samples_per_second": 28.606, | |
| "eval_steps_per_second": 3.719, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8787, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9525, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0219, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9175, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 0.8536613583564758, | |
| "eval_runtime": 3.4962, | |
| "eval_samples_per_second": 28.603, | |
| "eval_steps_per_second": 3.718, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1024, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0002, | |
| "loss": 0.932, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7403, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0905, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 0.8537384271621704, | |
| "eval_runtime": 3.498, | |
| "eval_samples_per_second": 28.588, | |
| "eval_steps_per_second": 3.716, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7258, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9586, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9653, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8959, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 0.8538539409637451, | |
| "eval_runtime": 3.4905, | |
| "eval_samples_per_second": 28.649, | |
| "eval_steps_per_second": 3.724, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0158, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9014, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0842, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1381, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 0.8546237349510193, | |
| "eval_runtime": 3.4961, | |
| "eval_samples_per_second": 28.603, | |
| "eval_steps_per_second": 3.718, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9051, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9399, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1012, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8986, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 0.8538478016853333, | |
| "eval_runtime": 3.4938, | |
| "eval_samples_per_second": 28.623, | |
| "eval_steps_per_second": 3.721, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7297, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0015, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9842, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8872, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 0.853283703327179, | |
| "eval_runtime": 3.5057, | |
| "eval_samples_per_second": 28.525, | |
| "eval_steps_per_second": 3.708, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8787, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1047, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0579, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0002, | |
| "loss": 1.043, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 0.8523504734039307, | |
| "eval_runtime": 3.4918, | |
| "eval_samples_per_second": 28.638, | |
| "eval_steps_per_second": 3.723, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9459, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8323, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7151, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8043, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 0.8531960844993591, | |
| "eval_runtime": 3.5007, | |
| "eval_samples_per_second": 28.566, | |
| "eval_steps_per_second": 3.714, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8876, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8346, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0002, | |
| "loss": 0.959, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9389, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 0.8523566722869873, | |
| "eval_runtime": 3.5031, | |
| "eval_samples_per_second": 28.546, | |
| "eval_steps_per_second": 3.711, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1969, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0218, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9258, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8663, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 0.8516626954078674, | |
| "eval_runtime": 3.4985, | |
| "eval_samples_per_second": 28.584, | |
| "eval_steps_per_second": 3.716, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1239, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0295, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8337, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9626, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 0.8513033986091614, | |
| "eval_runtime": 3.4891, | |
| "eval_samples_per_second": 28.661, | |
| "eval_steps_per_second": 3.726, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8364, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002, | |
| "loss": 0.909, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0628, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7472, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 0.8516498804092407, | |
| "eval_runtime": 3.495, | |
| "eval_samples_per_second": 28.612, | |
| "eval_steps_per_second": 3.72, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0338, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8797, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7821, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8763, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 0.8511673808097839, | |
| "eval_runtime": 3.4926, | |
| "eval_samples_per_second": 28.632, | |
| "eval_steps_per_second": 3.722, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7078, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0112, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8482, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8895, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 0.851494312286377, | |
| "eval_runtime": 3.4908, | |
| "eval_samples_per_second": 28.647, | |
| "eval_steps_per_second": 3.724, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6728, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0608, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002, | |
| "loss": 0.873, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8105, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 0.8509132862091064, | |
| "eval_runtime": 3.4861, | |
| "eval_samples_per_second": 28.685, | |
| "eval_steps_per_second": 3.729, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0534, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0636, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0256, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7225, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 0.8518603444099426, | |
| "eval_runtime": 3.4904, | |
| "eval_samples_per_second": 28.65, | |
| "eval_steps_per_second": 3.724, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7373, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0577, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7095, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9669, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 0.8499829173088074, | |
| "eval_runtime": 3.4918, | |
| "eval_samples_per_second": 28.639, | |
| "eval_steps_per_second": 3.723, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7494, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7474, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9183, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0184, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 0.8488267660140991, | |
| "eval_runtime": 3.4881, | |
| "eval_samples_per_second": 28.669, | |
| "eval_steps_per_second": 3.727, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8576, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9006, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6775, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6993, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 0.8493850827217102, | |
| "eval_runtime": 3.4995, | |
| "eval_samples_per_second": 28.575, | |
| "eval_steps_per_second": 3.715, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9225, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8652, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8475, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8957, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 0.8486952781677246, | |
| "eval_runtime": 3.4963, | |
| "eval_samples_per_second": 28.601, | |
| "eval_steps_per_second": 3.718, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7679, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1028, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7396, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0171, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 0.84913170337677, | |
| "eval_runtime": 3.4923, | |
| "eval_samples_per_second": 28.635, | |
| "eval_steps_per_second": 3.722, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9406, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1228, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9357, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7749, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 0.8485682010650635, | |
| "eval_runtime": 3.4914, | |
| "eval_samples_per_second": 28.642, | |
| "eval_steps_per_second": 3.723, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9093, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0665, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8227, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7152, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 0.8477771878242493, | |
| "eval_runtime": 3.4859, | |
| "eval_samples_per_second": 28.687, | |
| "eval_steps_per_second": 3.729, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7991, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8478, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9409, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9772, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 0.8469622731208801, | |
| "eval_runtime": 3.4962, | |
| "eval_samples_per_second": 28.602, | |
| "eval_steps_per_second": 3.718, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1002, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8901, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0293, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0419, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 0.8470239043235779, | |
| "eval_runtime": 3.4912, | |
| "eval_samples_per_second": 28.643, | |
| "eval_steps_per_second": 3.724, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7034, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0002, | |
| "loss": 0.66, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0723, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0002, | |
| "loss": 1.19, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 0.8469906449317932, | |
| "eval_runtime": 3.4851, | |
| "eval_samples_per_second": 28.693, | |
| "eval_steps_per_second": 3.73, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8898, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0199, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1107, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9677, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 0.8468003273010254, | |
| "eval_runtime": 3.4922, | |
| "eval_samples_per_second": 28.635, | |
| "eval_steps_per_second": 3.723, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0114, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0002, | |
| "loss": 1.215, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0002, | |
| "loss": 0.89, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9956, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 0.8459300398826599, | |
| "eval_runtime": 3.4943, | |
| "eval_samples_per_second": 28.618, | |
| "eval_steps_per_second": 3.72, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0002, | |
| "loss": 0.786, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9465, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8579, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9548, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 0.8457989692687988, | |
| "eval_runtime": 3.4908, | |
| "eval_samples_per_second": 28.647, | |
| "eval_steps_per_second": 3.724, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0002, | |
| "loss": 0.934, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7921, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7197, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6878, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 0.8447237610816956, | |
| "eval_runtime": 3.4858, | |
| "eval_samples_per_second": 28.688, | |
| "eval_steps_per_second": 3.729, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9446, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0002, | |
| "loss": 0.899, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0002, | |
| "loss": 0.805, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8222, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 0.844316840171814, | |
| "eval_runtime": 3.4961, | |
| "eval_samples_per_second": 28.603, | |
| "eval_steps_per_second": 3.718, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1023, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1483, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8478, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9538, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 0.8439966440200806, | |
| "eval_runtime": 3.4999, | |
| "eval_samples_per_second": 28.572, | |
| "eval_steps_per_second": 3.714, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0256, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8789, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9276, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8098, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 0.8438988327980042, | |
| "eval_runtime": 3.4938, | |
| "eval_samples_per_second": 28.622, | |
| "eval_steps_per_second": 3.721, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 1.073, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1013, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.998, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0044, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 0.8438183665275574, | |
| "eval_runtime": 3.4826, | |
| "eval_samples_per_second": 28.715, | |
| "eval_steps_per_second": 3.733, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0002, | |
| "loss": 0.901, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8335, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8416, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0687, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 0.843737006187439, | |
| "eval_runtime": 3.4893, | |
| "eval_samples_per_second": 28.659, | |
| "eval_steps_per_second": 3.726, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9341, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0002, | |
| "loss": 0.838, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7328, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8771, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 0.8438159227371216, | |
| "eval_runtime": 3.4922, | |
| "eval_samples_per_second": 28.635, | |
| "eval_steps_per_second": 3.723, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0623, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9453, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6666, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7899, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 0.8431993126869202, | |
| "eval_runtime": 3.4875, | |
| "eval_samples_per_second": 28.674, | |
| "eval_steps_per_second": 3.728, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8939, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9729, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9852, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9897, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 0.8433932662010193, | |
| "eval_runtime": 3.4971, | |
| "eval_samples_per_second": 28.595, | |
| "eval_steps_per_second": 3.717, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0245, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0441, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6036, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8646, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 0.8434394598007202, | |
| "eval_runtime": 3.493, | |
| "eval_samples_per_second": 28.629, | |
| "eval_steps_per_second": 3.722, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9865, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0002, | |
| "loss": 0.827, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8067, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7679, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 0.8438478708267212, | |
| "eval_runtime": 3.4997, | |
| "eval_samples_per_second": 28.574, | |
| "eval_steps_per_second": 3.715, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9757, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9394, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7348, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8493, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 0.8426430225372314, | |
| "eval_runtime": 3.485, | |
| "eval_samples_per_second": 28.694, | |
| "eval_steps_per_second": 3.73, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0389, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0002, | |
| "loss": 0.938, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8558, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9065, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 0.8414568305015564, | |
| "eval_runtime": 3.5006, | |
| "eval_samples_per_second": 28.566, | |
| "eval_steps_per_second": 3.714, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0095, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9291, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8344, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9994, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 0.8418157696723938, | |
| "eval_runtime": 3.4901, | |
| "eval_samples_per_second": 28.653, | |
| "eval_steps_per_second": 3.725, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1495, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0163, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7934, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8602, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 0.8416370153427124, | |
| "eval_runtime": 3.4961, | |
| "eval_samples_per_second": 28.603, | |
| "eval_steps_per_second": 3.718, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7957, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1061, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9052, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0018, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 0.8409822583198547, | |
| "eval_runtime": 3.4878, | |
| "eval_samples_per_second": 28.671, | |
| "eval_steps_per_second": 3.727, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7653, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8906, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6753, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8765, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 0.840335488319397, | |
| "eval_runtime": 3.4896, | |
| "eval_samples_per_second": 28.657, | |
| "eval_steps_per_second": 3.725, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7571, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.915, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8133, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0485, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 0.8409213423728943, | |
| "eval_runtime": 3.4878, | |
| "eval_samples_per_second": 28.672, | |
| "eval_steps_per_second": 3.727, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0375, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8635, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.933, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8833, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 0.8408510684967041, | |
| "eval_runtime": 3.4959, | |
| "eval_samples_per_second": 28.605, | |
| "eval_steps_per_second": 3.719, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7884, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8876, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0462, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9011, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 0.8405241370201111, | |
| "eval_runtime": 3.4931, | |
| "eval_samples_per_second": 28.628, | |
| "eval_steps_per_second": 3.722, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0424, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7394, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0002, | |
| "loss": 0.839, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8241, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 0.8405718207359314, | |
| "eval_runtime": 3.4858, | |
| "eval_samples_per_second": 28.688, | |
| "eval_steps_per_second": 3.729, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1752, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0002, | |
| "loss": 0.914, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7498, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8463, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 0.8409115076065063, | |
| "eval_runtime": 3.4878, | |
| "eval_samples_per_second": 28.672, | |
| "eval_steps_per_second": 3.727, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0002, | |
| "loss": 1.08, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8867, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8363, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6666, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 0.8408042788505554, | |
| "eval_runtime": 3.4893, | |
| "eval_samples_per_second": 28.659, | |
| "eval_steps_per_second": 3.726, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7013, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2001, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8059, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8456, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 0.8396875262260437, | |
| "eval_runtime": 3.4871, | |
| "eval_samples_per_second": 28.677, | |
| "eval_steps_per_second": 3.728, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8063, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9362, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7656, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8488, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 0.8393911123275757, | |
| "eval_runtime": 3.4968, | |
| "eval_samples_per_second": 28.597, | |
| "eval_steps_per_second": 3.718, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8696, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8492, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9332, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9898, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 0.8395198583602905, | |
| "eval_runtime": 3.4969, | |
| "eval_samples_per_second": 28.597, | |
| "eval_steps_per_second": 3.718, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2468, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8085, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9803, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7381, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 0.839021623134613, | |
| "eval_runtime": 3.4909, | |
| "eval_samples_per_second": 28.646, | |
| "eval_steps_per_second": 3.724, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0689, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1625, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0137, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0336, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 0.8385031819343567, | |
| "eval_runtime": 3.4964, | |
| "eval_samples_per_second": 28.601, | |
| "eval_steps_per_second": 3.718, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9073, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0848, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8821, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8716, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 0.8389168381690979, | |
| "eval_runtime": 3.4938, | |
| "eval_samples_per_second": 28.622, | |
| "eval_steps_per_second": 3.721, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7721, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8459, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8196, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7119, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 0.8385671377182007, | |
| "eval_runtime": 3.4922, | |
| "eval_samples_per_second": 28.636, | |
| "eval_steps_per_second": 3.723, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9656, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9539, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7208, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0002, | |
| "loss": 0.901, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 0.8377952575683594, | |
| "eval_runtime": 3.4976, | |
| "eval_samples_per_second": 28.591, | |
| "eval_steps_per_second": 3.717, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7106, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9433, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7986, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8785, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 0.8379724025726318, | |
| "eval_runtime": 3.4856, | |
| "eval_samples_per_second": 28.689, | |
| "eval_steps_per_second": 3.73, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8773, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9403, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8335, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9248, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 0.8382018208503723, | |
| "eval_runtime": 3.4864, | |
| "eval_samples_per_second": 28.683, | |
| "eval_steps_per_second": 3.729, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7015, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9238, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7862, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9158, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 0.8373521566390991, | |
| "eval_runtime": 3.4951, | |
| "eval_samples_per_second": 28.611, | |
| "eval_steps_per_second": 3.719, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7883, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0472, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7977, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9105, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 0.8367696404457092, | |
| "eval_runtime": 3.4903, | |
| "eval_samples_per_second": 28.651, | |
| "eval_steps_per_second": 3.725, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8818, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2267, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6637, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7728, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 0.8363841772079468, | |
| "eval_runtime": 3.4941, | |
| "eval_samples_per_second": 28.62, | |
| "eval_steps_per_second": 3.721, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0569, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8229, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7369, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7998, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 0.8358197808265686, | |
| "eval_runtime": 3.4893, | |
| "eval_samples_per_second": 28.659, | |
| "eval_steps_per_second": 3.726, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0125, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0087, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1587, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7962, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 0.8363614678382874, | |
| "eval_runtime": 3.49, | |
| "eval_samples_per_second": 28.653, | |
| "eval_steps_per_second": 3.725, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9773, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0407, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5964, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0002, | |
| "loss": 0.71, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 0.8364322781562805, | |
| "eval_runtime": 3.489, | |
| "eval_samples_per_second": 28.662, | |
| "eval_steps_per_second": 3.726, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8687, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0002, | |
| "loss": 0.961, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8571, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6855, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 0.8370598554611206, | |
| "eval_runtime": 3.4914, | |
| "eval_samples_per_second": 28.641, | |
| "eval_steps_per_second": 3.723, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8509, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8719, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0602, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8598, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 0.837070107460022, | |
| "eval_runtime": 3.4962, | |
| "eval_samples_per_second": 28.602, | |
| "eval_steps_per_second": 3.718, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8264, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9536, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0833, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9678, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.8367723226547241, | |
| "eval_runtime": 3.4931, | |
| "eval_samples_per_second": 28.628, | |
| "eval_steps_per_second": 3.722, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0017, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.766, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0482, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7394, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 0.8367820978164673, | |
| "eval_runtime": 3.4989, | |
| "eval_samples_per_second": 28.58, | |
| "eval_steps_per_second": 3.715, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8371, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5531, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8653, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7036, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 0.8369036316871643, | |
| "eval_runtime": 3.5, | |
| "eval_samples_per_second": 28.572, | |
| "eval_steps_per_second": 3.714, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9722, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9919, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8083, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0593, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 0.8368712067604065, | |
| "eval_runtime": 3.4945, | |
| "eval_samples_per_second": 28.616, | |
| "eval_steps_per_second": 3.72, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7758, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9997, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8254, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1176, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 0.8371840119361877, | |
| "eval_runtime": 3.5002, | |
| "eval_samples_per_second": 28.57, | |
| "eval_steps_per_second": 3.714, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0083, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9557, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8485, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9762, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 0.8384084105491638, | |
| "eval_runtime": 3.4899, | |
| "eval_samples_per_second": 28.655, | |
| "eval_steps_per_second": 3.725, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1078, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7524, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0086, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5972, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_loss": 0.8381380438804626, | |
| "eval_runtime": 3.4912, | |
| "eval_samples_per_second": 28.643, | |
| "eval_steps_per_second": 3.724, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8763, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8193, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0864, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0002, | |
| "loss": 0.757, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 0.8375694751739502, | |
| "eval_runtime": 3.4968, | |
| "eval_samples_per_second": 28.598, | |
| "eval_steps_per_second": 3.718, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8843, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9499, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0971, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0218, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 0.8373072743415833, | |
| "eval_runtime": 3.4907, | |
| "eval_samples_per_second": 28.648, | |
| "eval_steps_per_second": 3.724, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8782, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7803, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7167, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0616, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 0.8369928002357483, | |
| "eval_runtime": 3.4927, | |
| "eval_samples_per_second": 28.631, | |
| "eval_steps_per_second": 3.722, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7901, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6643, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7833, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0002, | |
| "loss": 1.159, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 0.8371590971946716, | |
| "eval_runtime": 3.4948, | |
| "eval_samples_per_second": 28.614, | |
| "eval_steps_per_second": 3.72, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8594, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9981, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9082, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8787, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 0.838473916053772, | |
| "eval_runtime": 3.4858, | |
| "eval_samples_per_second": 28.688, | |
| "eval_steps_per_second": 3.729, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0002, | |
| "loss": 0.995, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8942, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7453, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1109, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 0.8379270434379578, | |
| "eval_runtime": 3.4877, | |
| "eval_samples_per_second": 28.672, | |
| "eval_steps_per_second": 3.727, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6749, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6795, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9007, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8447, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 0.8374585509300232, | |
| "eval_runtime": 3.4875, | |
| "eval_samples_per_second": 28.674, | |
| "eval_steps_per_second": 3.728, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9355, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8005, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8849, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9054, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 0.837344229221344, | |
| "eval_runtime": 3.4924, | |
| "eval_samples_per_second": 28.634, | |
| "eval_steps_per_second": 3.722, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9389, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8255, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0002, | |
| "loss": 0.932, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9729, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_loss": 0.837063729763031, | |
| "eval_runtime": 3.4871, | |
| "eval_samples_per_second": 28.677, | |
| "eval_steps_per_second": 3.728, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8825, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7698, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8906, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0039, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_loss": 0.8366745114326477, | |
| "eval_runtime": 3.4886, | |
| "eval_samples_per_second": 28.665, | |
| "eval_steps_per_second": 3.726, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9414, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8931, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8951, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9633, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 0.8368797302246094, | |
| "eval_runtime": 3.4943, | |
| "eval_samples_per_second": 28.618, | |
| "eval_steps_per_second": 3.72, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7361, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9499, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0002, | |
| "loss": 1.047, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0002, | |
| "loss": 0.678, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 0.8366026282310486, | |
| "eval_runtime": 3.4854, | |
| "eval_samples_per_second": 28.691, | |
| "eval_steps_per_second": 3.73, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8693, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0002, | |
| "loss": 0.929, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9318, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9663, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_loss": 0.8376994132995605, | |
| "eval_runtime": 3.488, | |
| "eval_samples_per_second": 28.67, | |
| "eval_steps_per_second": 3.727, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8947, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0554, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8006, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0214, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_loss": 0.8365377187728882, | |
| "eval_runtime": 3.4985, | |
| "eval_samples_per_second": 28.584, | |
| "eval_steps_per_second": 3.716, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1781, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7719, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6968, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9392, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_loss": 0.8354942798614502, | |
| "eval_runtime": 3.4907, | |
| "eval_samples_per_second": 28.648, | |
| "eval_steps_per_second": 3.724, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.0002, | |
| "loss": 0.882, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9044, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9467, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9255, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 0.8351648449897766, | |
| "eval_runtime": 3.4872, | |
| "eval_samples_per_second": 28.676, | |
| "eval_steps_per_second": 3.728, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9466, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1247, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0866, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7047, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 0.8355209231376648, | |
| "eval_runtime": 3.4837, | |
| "eval_samples_per_second": 28.705, | |
| "eval_steps_per_second": 3.732, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7863, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8394, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8679, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7294, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 0.8354747295379639, | |
| "eval_runtime": 3.4871, | |
| "eval_samples_per_second": 28.677, | |
| "eval_steps_per_second": 3.728, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8214, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0228, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9117, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7816, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_loss": 0.8353164196014404, | |
| "eval_runtime": 3.4915, | |
| "eval_samples_per_second": 28.641, | |
| "eval_steps_per_second": 3.723, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8809, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8552, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9339, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9075, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 0.8353996872901917, | |
| "eval_runtime": 3.4891, | |
| "eval_samples_per_second": 28.661, | |
| "eval_steps_per_second": 3.726, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.0002, | |
| "loss": 0.86, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0467, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0254, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8449, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 0.8360083699226379, | |
| "eval_runtime": 3.4869, | |
| "eval_samples_per_second": 28.679, | |
| "eval_steps_per_second": 3.728, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0213, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8257, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6738, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7072, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 0.8366960883140564, | |
| "eval_runtime": 3.4869, | |
| "eval_samples_per_second": 28.679, | |
| "eval_steps_per_second": 3.728, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8935, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7839, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0001, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0002, | |
| "loss": 0.84, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 0.8368987441062927, | |
| "eval_runtime": 3.4939, | |
| "eval_samples_per_second": 28.621, | |
| "eval_steps_per_second": 3.721, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0408, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0497, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9689, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1382, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 0.837027907371521, | |
| "eval_runtime": 3.483, | |
| "eval_samples_per_second": 28.711, | |
| "eval_steps_per_second": 3.732, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8029, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9508, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9156, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9388, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 0.8367031216621399, | |
| "eval_runtime": 3.5001, | |
| "eval_samples_per_second": 28.571, | |
| "eval_steps_per_second": 3.714, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8354, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9803, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7361, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9492, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 0.8366225957870483, | |
| "eval_runtime": 3.4948, | |
| "eval_samples_per_second": 28.614, | |
| "eval_steps_per_second": 3.72, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2516, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1229, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7833, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7472, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 0.8365585207939148, | |
| "eval_runtime": 3.4937, | |
| "eval_samples_per_second": 28.623, | |
| "eval_steps_per_second": 3.721, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9241, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8291, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7537, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9698, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_loss": 0.8360151052474976, | |
| "eval_runtime": 3.4867, | |
| "eval_samples_per_second": 28.68, | |
| "eval_steps_per_second": 3.728, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7117, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0701, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9375, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7991, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 0.8359129428863525, | |
| "eval_runtime": 3.4864, | |
| "eval_samples_per_second": 28.683, | |
| "eval_steps_per_second": 3.729, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.0002, | |
| "loss": 0.83, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7267, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8973, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8133, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 0.8348734974861145, | |
| "eval_runtime": 3.4826, | |
| "eval_samples_per_second": 28.714, | |
| "eval_steps_per_second": 3.733, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9556, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0002, | |
| "loss": 0.913, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7968, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0002, | |
| "loss": 0.913, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 0.8347440958023071, | |
| "eval_runtime": 3.5015, | |
| "eval_samples_per_second": 28.559, | |
| "eval_steps_per_second": 3.713, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0202, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9618, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0586, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9254, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 0.8348772525787354, | |
| "eval_runtime": 3.4947, | |
| "eval_samples_per_second": 28.615, | |
| "eval_steps_per_second": 3.72, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6742, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7956, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0002, | |
| "loss": 0.803, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0571, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_loss": 0.8349617719650269, | |
| "eval_runtime": 3.4856, | |
| "eval_samples_per_second": 28.689, | |
| "eval_steps_per_second": 3.73, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7113, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.0002, | |
| "loss": 0.736, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.0002, | |
| "loss": 0.998, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9205, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 0.8349907398223877, | |
| "eval_runtime": 3.5012, | |
| "eval_samples_per_second": 28.562, | |
| "eval_steps_per_second": 3.713, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8627, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0645, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0609, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8625, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 0.8353784084320068, | |
| "eval_runtime": 3.4887, | |
| "eval_samples_per_second": 28.664, | |
| "eval_steps_per_second": 3.726, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8675, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9845, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9282, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9125, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_loss": 0.8353492617607117, | |
| "eval_runtime": 3.4827, | |
| "eval_samples_per_second": 28.714, | |
| "eval_steps_per_second": 3.733, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.0002, | |
| "loss": 0.806, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9797, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0153, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0574, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 0.8349023461341858, | |
| "eval_runtime": 3.4863, | |
| "eval_samples_per_second": 28.683, | |
| "eval_steps_per_second": 3.729, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9998, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8245, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9734, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8093, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 0.8344553112983704, | |
| "eval_runtime": 3.4893, | |
| "eval_samples_per_second": 28.659, | |
| "eval_steps_per_second": 3.726, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2502, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7777, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6512, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7988, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_loss": 0.8335115909576416, | |
| "eval_runtime": 3.4892, | |
| "eval_samples_per_second": 28.66, | |
| "eval_steps_per_second": 3.726, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7867, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8227, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0969, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0358, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 0.8333072662353516, | |
| "eval_runtime": 3.503, | |
| "eval_samples_per_second": 28.547, | |
| "eval_steps_per_second": 3.711, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6684, | |
| "step": 641 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1049, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7888, | |
| "step": 643 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7769, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 0.8334370255470276, | |
| "eval_runtime": 3.4826, | |
| "eval_samples_per_second": 28.714, | |
| "eval_steps_per_second": 3.733, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0313, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7426, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8815, | |
| "step": 647 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.0002, | |
| "loss": 0.796, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_loss": 0.8331010937690735, | |
| "eval_runtime": 3.4958, | |
| "eval_samples_per_second": 28.606, | |
| "eval_steps_per_second": 3.719, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.0002, | |
| "loss": 0.813, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0019, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1299, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9676, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 0.8336557149887085, | |
| "eval_runtime": 3.478, | |
| "eval_samples_per_second": 28.752, | |
| "eval_steps_per_second": 3.738, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9821, | |
| "step": 653 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7941, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7984, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8179, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 0.8340582251548767, | |
| "eval_runtime": 3.4998, | |
| "eval_samples_per_second": 28.573, | |
| "eval_steps_per_second": 3.715, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9424, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7547, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7504, | |
| "step": 659 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8901, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_loss": 0.83406662940979, | |
| "eval_runtime": 3.4914, | |
| "eval_samples_per_second": 28.642, | |
| "eval_steps_per_second": 3.723, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9772, | |
| "step": 661 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8964, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0158, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.0002, | |
| "loss": 0.939, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_loss": 0.8337156772613525, | |
| "eval_runtime": 3.4855, | |
| "eval_samples_per_second": 28.69, | |
| "eval_steps_per_second": 3.73, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8546, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7344, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8327, | |
| "step": 667 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9025, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_loss": 0.8324799537658691, | |
| "eval_runtime": 3.486, | |
| "eval_samples_per_second": 28.686, | |
| "eval_steps_per_second": 3.729, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9877, | |
| "step": 669 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7995, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8081, | |
| "step": 671 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7319, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 0.8332785964012146, | |
| "eval_runtime": 3.4946, | |
| "eval_samples_per_second": 28.616, | |
| "eval_steps_per_second": 3.72, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9485, | |
| "step": 673 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9107, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7728, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8236, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 0.833832323551178, | |
| "eval_runtime": 3.5015, | |
| "eval_samples_per_second": 28.56, | |
| "eval_steps_per_second": 3.713, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7989, | |
| "step": 677 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.0002, | |
| "loss": 1.105, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0623, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0095, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_loss": 0.8338822722434998, | |
| "eval_runtime": 3.4919, | |
| "eval_samples_per_second": 28.638, | |
| "eval_steps_per_second": 3.723, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9777, | |
| "step": 681 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9556, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8946, | |
| "step": 683 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0002, | |
| "loss": 0.898, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 0.8336551785469055, | |
| "eval_runtime": 3.4893, | |
| "eval_samples_per_second": 28.659, | |
| "eval_steps_per_second": 3.726, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0002, | |
| "loss": 1.007, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0002, | |
| "loss": 0.807, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8338, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9185, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_loss": 0.8331172466278076, | |
| "eval_runtime": 3.4856, | |
| "eval_samples_per_second": 28.69, | |
| "eval_steps_per_second": 3.73, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0022, | |
| "step": 689 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8357, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8243, | |
| "step": 691 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8743, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 0.8325685262680054, | |
| "eval_runtime": 3.5013, | |
| "eval_samples_per_second": 28.561, | |
| "eval_steps_per_second": 3.713, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0301, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6834, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9528, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9311, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 0.8321629166603088, | |
| "eval_runtime": 3.4936, | |
| "eval_samples_per_second": 28.624, | |
| "eval_steps_per_second": 3.721, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8551, | |
| "step": 697 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9938, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7637, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7926, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 0.831686794757843, | |
| "eval_runtime": 3.4906, | |
| "eval_samples_per_second": 28.649, | |
| "eval_steps_per_second": 3.724, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2606, | |
| "step": 701 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8917, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0641, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0056, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 0.8318292498588562, | |
| "eval_runtime": 3.4954, | |
| "eval_samples_per_second": 28.609, | |
| "eval_steps_per_second": 3.719, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8244, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8088, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0713, | |
| "step": 707 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7162, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 0.8321847319602966, | |
| "eval_runtime": 3.4902, | |
| "eval_samples_per_second": 28.652, | |
| "eval_steps_per_second": 3.725, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8066, | |
| "step": 709 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0613, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.0002, | |
| "loss": 0.843, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9608, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 0.8321833610534668, | |
| "eval_runtime": 3.4814, | |
| "eval_samples_per_second": 28.724, | |
| "eval_steps_per_second": 3.734, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8474, | |
| "step": 713 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7132, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0341, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9485, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_loss": 0.8317855000495911, | |
| "eval_runtime": 3.4903, | |
| "eval_samples_per_second": 28.651, | |
| "eval_steps_per_second": 3.725, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7835, | |
| "step": 717 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.0002, | |
| "loss": 0.852, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7194, | |
| "step": 719 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9101, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 0.8315277099609375, | |
| "eval_runtime": 3.4938, | |
| "eval_samples_per_second": 28.623, | |
| "eval_steps_per_second": 3.721, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9302, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6688, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9422, | |
| "step": 723 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9672, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 0.8315054178237915, | |
| "eval_runtime": 3.4871, | |
| "eval_samples_per_second": 28.677, | |
| "eval_steps_per_second": 3.728, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8843, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9242, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5572, | |
| "step": 727 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1229, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 0.8314743638038635, | |
| "eval_runtime": 3.4848, | |
| "eval_samples_per_second": 28.696, | |
| "eval_steps_per_second": 3.73, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0438, | |
| "step": 729 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7601, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8848, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0002, | |
| "loss": 0.733, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 0.8316361904144287, | |
| "eval_runtime": 3.4822, | |
| "eval_samples_per_second": 28.717, | |
| "eval_steps_per_second": 3.733, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6585, | |
| "step": 733 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8926, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9789, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7638, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_loss": 0.8314841985702515, | |
| "eval_runtime": 3.4991, | |
| "eval_samples_per_second": 28.579, | |
| "eval_steps_per_second": 3.715, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9412, | |
| "step": 737 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9929, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8218, | |
| "step": 739 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9397, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_loss": 0.8304407596588135, | |
| "eval_runtime": 3.4885, | |
| "eval_samples_per_second": 28.666, | |
| "eval_steps_per_second": 3.727, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.0002, | |
| "loss": 0.738, | |
| "step": 741 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7004, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8541, | |
| "step": 743 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7048, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_loss": 0.8297193050384521, | |
| "eval_runtime": 3.485, | |
| "eval_samples_per_second": 28.694, | |
| "eval_steps_per_second": 3.73, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8406, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9313, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8932, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8671, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 0.8296411037445068, | |
| "eval_runtime": 3.4879, | |
| "eval_samples_per_second": 28.67, | |
| "eval_steps_per_second": 3.727, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.0002, | |
| "loss": 0.815, | |
| "step": 749 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7908, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8491, | |
| "step": 751 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8191, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_loss": 0.8295549750328064, | |
| "eval_runtime": 3.4862, | |
| "eval_samples_per_second": 28.684, | |
| "eval_steps_per_second": 3.729, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.0002, | |
| "loss": 0.858, | |
| "step": 753 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.0002, | |
| "loss": 0.852, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8984, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0503, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_loss": 0.8295718431472778, | |
| "eval_runtime": 3.4969, | |
| "eval_samples_per_second": 28.597, | |
| "eval_steps_per_second": 3.718, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8204, | |
| "step": 757 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0654, | |
| "step": 758 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6933, | |
| "step": 759 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0212, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_loss": 0.8296614289283752, | |
| "eval_runtime": 3.4839, | |
| "eval_samples_per_second": 28.704, | |
| "eval_steps_per_second": 3.731, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6477, | |
| "step": 761 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9028, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0002, | |
| "loss": 1.005, | |
| "step": 763 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0699, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_loss": 0.8289396166801453, | |
| "eval_runtime": 3.4928, | |
| "eval_samples_per_second": 28.63, | |
| "eval_steps_per_second": 3.722, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5902, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9182, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8648, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.0002, | |
| "loss": 0.784, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_loss": 0.8286778926849365, | |
| "eval_runtime": 3.4922, | |
| "eval_samples_per_second": 28.635, | |
| "eval_steps_per_second": 3.723, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6946, | |
| "step": 769 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9301, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9769, | |
| "step": 771 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8172, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_loss": 0.8294014930725098, | |
| "eval_runtime": 3.489, | |
| "eval_samples_per_second": 28.662, | |
| "eval_steps_per_second": 3.726, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0941, | |
| "step": 773 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.0002, | |
| "loss": 0.939, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7317, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8872, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 0.8296313285827637, | |
| "eval_runtime": 3.4876, | |
| "eval_samples_per_second": 28.673, | |
| "eval_steps_per_second": 3.727, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9428, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.0002, | |
| "loss": 0.734, | |
| "step": 778 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9357, | |
| "step": 779 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9668, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_loss": 0.8294573426246643, | |
| "eval_runtime": 3.4907, | |
| "eval_samples_per_second": 28.647, | |
| "eval_steps_per_second": 3.724, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6996, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.0002, | |
| "loss": 0.824, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8738, | |
| "step": 783 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8871, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 0.8289172649383545, | |
| "eval_runtime": 3.4843, | |
| "eval_samples_per_second": 28.7, | |
| "eval_steps_per_second": 3.731, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0821, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7869, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8053, | |
| "step": 787 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9408, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 0.8288751840591431, | |
| "eval_runtime": 3.49, | |
| "eval_samples_per_second": 28.653, | |
| "eval_steps_per_second": 3.725, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8228, | |
| "step": 789 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002, | |
| "loss": 0.786, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002, | |
| "loss": 0.987, | |
| "step": 791 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9247, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 0.8288435339927673, | |
| "eval_runtime": 3.4952, | |
| "eval_samples_per_second": 28.611, | |
| "eval_steps_per_second": 3.719, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7724, | |
| "step": 793 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6714, | |
| "step": 794 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0811, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9822, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_loss": 0.8282428979873657, | |
| "eval_runtime": 3.4832, | |
| "eval_samples_per_second": 28.709, | |
| "eval_steps_per_second": 3.732, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9481, | |
| "step": 797 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0285, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9716, | |
| "step": 799 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9399, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 0.8286378979682922, | |
| "eval_runtime": 3.4835, | |
| "eval_samples_per_second": 28.707, | |
| "eval_steps_per_second": 3.732, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1185, | |
| "step": 801 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9073, | |
| "step": 802 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0002, | |
| "loss": 0.873, | |
| "step": 803 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7538, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 0.8281552195549011, | |
| "eval_runtime": 3.4868, | |
| "eval_samples_per_second": 28.679, | |
| "eval_steps_per_second": 3.728, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8193, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8369, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8503, | |
| "step": 807 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8302, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_loss": 0.827840268611908, | |
| "eval_runtime": 3.4967, | |
| "eval_samples_per_second": 28.598, | |
| "eval_steps_per_second": 3.718, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7072, | |
| "step": 809 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8713, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9152, | |
| "step": 811 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0345, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_loss": 0.828177273273468, | |
| "eval_runtime": 3.4891, | |
| "eval_samples_per_second": 28.661, | |
| "eval_steps_per_second": 3.726, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8428, | |
| "step": 813 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8792, | |
| "step": 814 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6472, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9985, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 0.8277809619903564, | |
| "eval_runtime": 3.4893, | |
| "eval_samples_per_second": 28.659, | |
| "eval_steps_per_second": 3.726, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9284, | |
| "step": 817 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8591, | |
| "step": 818 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9586, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6396, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 0.8281911611557007, | |
| "eval_runtime": 3.4926, | |
| "eval_samples_per_second": 28.632, | |
| "eval_steps_per_second": 3.722, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7648, | |
| "step": 821 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7681, | |
| "step": 822 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9665, | |
| "step": 823 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7583, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_loss": 0.8285152912139893, | |
| "eval_runtime": 3.4965, | |
| "eval_samples_per_second": 28.6, | |
| "eval_steps_per_second": 3.718, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8868, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9905, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9892, | |
| "step": 827 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9795, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_loss": 0.8282599449157715, | |
| "eval_runtime": 3.4873, | |
| "eval_samples_per_second": 28.676, | |
| "eval_steps_per_second": 3.728, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7902, | |
| "step": 829 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5273, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7732, | |
| "step": 831 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.0002, | |
| "loss": 1.006, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_loss": 0.8283340930938721, | |
| "eval_runtime": 3.5003, | |
| "eval_samples_per_second": 28.569, | |
| "eval_steps_per_second": 3.714, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8045, | |
| "step": 833 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9998, | |
| "step": 834 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9018, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0641, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_loss": 0.8285072445869446, | |
| "eval_runtime": 3.4881, | |
| "eval_samples_per_second": 28.669, | |
| "eval_steps_per_second": 3.727, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0319, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8311, | |
| "step": 838 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7515, | |
| "step": 839 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9576, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "eval_loss": 0.8282440304756165, | |
| "eval_runtime": 3.486, | |
| "eval_samples_per_second": 28.687, | |
| "eval_steps_per_second": 3.729, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8848, | |
| "step": 841 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9634, | |
| "step": 842 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9538, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7958, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_loss": 0.8283226490020752, | |
| "eval_runtime": 3.4946, | |
| "eval_samples_per_second": 28.616, | |
| "eval_steps_per_second": 3.72, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6213, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8993, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8653, | |
| "step": 847 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7292, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 0.8275513648986816, | |
| "eval_runtime": 3.4902, | |
| "eval_samples_per_second": 28.652, | |
| "eval_steps_per_second": 3.725, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8768, | |
| "step": 849 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0408, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8207, | |
| "step": 851 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9137, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 0.8275913000106812, | |
| "eval_runtime": 3.4836, | |
| "eval_samples_per_second": 28.706, | |
| "eval_steps_per_second": 3.732, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9309, | |
| "step": 853 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0422, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8044, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1895, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_loss": 0.8281159996986389, | |
| "eval_runtime": 3.4857, | |
| "eval_samples_per_second": 28.689, | |
| "eval_steps_per_second": 3.73, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.0002, | |
| "loss": 0.927, | |
| "step": 857 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8271, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7045, | |
| "step": 859 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8014, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_loss": 0.8277135491371155, | |
| "eval_runtime": 3.4861, | |
| "eval_samples_per_second": 28.686, | |
| "eval_steps_per_second": 3.729, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9368, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9319, | |
| "step": 862 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7929, | |
| "step": 863 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8187, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_loss": 0.8276296854019165, | |
| "eval_runtime": 3.488, | |
| "eval_samples_per_second": 28.67, | |
| "eval_steps_per_second": 3.727, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1425, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6864, | |
| "step": 866 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8306, | |
| "step": 867 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0201, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "eval_loss": 0.827803373336792, | |
| "eval_runtime": 3.4922, | |
| "eval_samples_per_second": 28.635, | |
| "eval_steps_per_second": 3.723, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.0002, | |
| "loss": 0.875, | |
| "step": 869 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8004, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8854, | |
| "step": 871 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0018, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_loss": 0.827599287033081, | |
| "eval_runtime": 3.4883, | |
| "eval_samples_per_second": 28.668, | |
| "eval_steps_per_second": 3.727, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0755, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7266, | |
| "step": 874 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7802, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9704, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 0.8269216418266296, | |
| "eval_runtime": 3.4861, | |
| "eval_samples_per_second": 28.685, | |
| "eval_steps_per_second": 3.729, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7754, | |
| "step": 877 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0124, | |
| "step": 878 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0009, | |
| "step": 879 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.968, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_loss": 0.8267806768417358, | |
| "eval_runtime": 3.4876, | |
| "eval_samples_per_second": 28.673, | |
| "eval_steps_per_second": 3.728, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8418, | |
| "step": 881 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8317, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7446, | |
| "step": 883 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1774, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_loss": 0.8265888690948486, | |
| "eval_runtime": 3.4856, | |
| "eval_samples_per_second": 28.69, | |
| "eval_steps_per_second": 3.73, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8857, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9971, | |
| "step": 886 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9784, | |
| "step": 887 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8681, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_loss": 0.8262592554092407, | |
| "eval_runtime": 3.4814, | |
| "eval_samples_per_second": 28.724, | |
| "eval_steps_per_second": 3.734, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8468, | |
| "step": 889 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6236, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6757, | |
| "step": 891 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9821, | |
| "step": 892 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_loss": 0.825909435749054, | |
| "eval_runtime": 3.4819, | |
| "eval_samples_per_second": 28.72, | |
| "eval_steps_per_second": 3.734, | |
| "step": 892 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.0002, | |
| "loss": 1.039, | |
| "step": 893 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6603, | |
| "step": 894 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.0002, | |
| "loss": 1.007, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.0002, | |
| "loss": 0.736, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 0.825869619846344, | |
| "eval_runtime": 3.4897, | |
| "eval_samples_per_second": 28.656, | |
| "eval_steps_per_second": 3.725, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7029, | |
| "step": 897 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8631, | |
| "step": 898 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6308, | |
| "step": 899 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9537, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_loss": 0.825663149356842, | |
| "eval_runtime": 3.4857, | |
| "eval_samples_per_second": 28.688, | |
| "eval_steps_per_second": 3.729, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7969, | |
| "step": 901 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8268, | |
| "step": 902 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8679, | |
| "step": 903 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9829, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_loss": 0.8252362608909607, | |
| "eval_runtime": 3.4894, | |
| "eval_samples_per_second": 28.658, | |
| "eval_steps_per_second": 3.726, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6675, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0002, | |
| "loss": 0.648, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8326, | |
| "step": 907 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6532, | |
| "step": 908 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 0.8253859877586365, | |
| "eval_runtime": 3.481, | |
| "eval_samples_per_second": 28.727, | |
| "eval_steps_per_second": 3.735, | |
| "step": 908 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8462, | |
| "step": 909 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7091, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6469, | |
| "step": 911 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8238, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.8250536322593689, | |
| "eval_runtime": 3.4817, | |
| "eval_samples_per_second": 28.722, | |
| "eval_steps_per_second": 3.734, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9211, | |
| "step": 913 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8546, | |
| "step": 914 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6674, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6782, | |
| "step": 916 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_loss": 0.8250590562820435, | |
| "eval_runtime": 3.4861, | |
| "eval_samples_per_second": 28.685, | |
| "eval_steps_per_second": 3.729, | |
| "step": 916 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9099, | |
| "step": 917 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6376, | |
| "step": 918 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9233, | |
| "step": 919 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9926, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_loss": 0.8258709907531738, | |
| "eval_runtime": 3.4973, | |
| "eval_samples_per_second": 28.593, | |
| "eval_steps_per_second": 3.717, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9315, | |
| "step": 921 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.0002, | |
| "loss": 0.932, | |
| "step": 922 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8757, | |
| "step": 923 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9297, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_loss": 0.8265821933746338, | |
| "eval_runtime": 3.482, | |
| "eval_samples_per_second": 28.719, | |
| "eval_steps_per_second": 3.733, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.0002, | |
| "loss": 0.85, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9247, | |
| "step": 926 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8113, | |
| "step": 927 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8038, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 0.8265116810798645, | |
| "eval_runtime": 3.4846, | |
| "eval_samples_per_second": 28.698, | |
| "eval_steps_per_second": 3.731, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9646, | |
| "step": 929 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9651, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8859, | |
| "step": 931 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0554, | |
| "step": 932 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 0.826681911945343, | |
| "eval_runtime": 3.4825, | |
| "eval_samples_per_second": 28.715, | |
| "eval_steps_per_second": 3.733, | |
| "step": 932 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9554, | |
| "step": 933 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6944, | |
| "step": 934 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0618, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8906, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "eval_loss": 0.8271703124046326, | |
| "eval_runtime": 3.4903, | |
| "eval_samples_per_second": 28.651, | |
| "eval_steps_per_second": 3.725, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9963, | |
| "step": 937 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6484, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7957, | |
| "step": 939 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7291, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 0.8280881643295288, | |
| "eval_runtime": 3.494, | |
| "eval_samples_per_second": 28.62, | |
| "eval_steps_per_second": 3.721, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8265, | |
| "step": 941 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9101, | |
| "step": 942 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8808, | |
| "step": 943 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8366, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_loss": 0.8275220990180969, | |
| "eval_runtime": 3.4846, | |
| "eval_samples_per_second": 28.697, | |
| "eval_steps_per_second": 3.731, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9158, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8682, | |
| "step": 946 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7939, | |
| "step": 947 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0357, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_loss": 0.8275697231292725, | |
| "eval_runtime": 3.4823, | |
| "eval_samples_per_second": 28.716, | |
| "eval_steps_per_second": 3.733, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8818, | |
| "step": 949 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9729, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6042, | |
| "step": 951 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8144, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_loss": 0.8280036449432373, | |
| "eval_runtime": 3.4889, | |
| "eval_samples_per_second": 28.663, | |
| "eval_steps_per_second": 3.726, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8166, | |
| "step": 953 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6629, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7858, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8968, | |
| "step": 956 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_loss": 0.828046441078186, | |
| "eval_runtime": 3.49, | |
| "eval_samples_per_second": 28.653, | |
| "eval_steps_per_second": 3.725, | |
| "step": 956 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9982, | |
| "step": 957 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8452, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.0002, | |
| "loss": 0.849, | |
| "step": 959 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8034, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_loss": 0.8282729387283325, | |
| "eval_runtime": 3.4958, | |
| "eval_samples_per_second": 28.606, | |
| "eval_steps_per_second": 3.719, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9361, | |
| "step": 961 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0139, | |
| "step": 962 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7675, | |
| "step": 963 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6449, | |
| "step": 964 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "eval_loss": 0.8285490274429321, | |
| "eval_runtime": 3.4872, | |
| "eval_samples_per_second": 28.676, | |
| "eval_steps_per_second": 3.728, | |
| "step": 964 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7551, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7855, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0163, | |
| "step": 967 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9829, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_loss": 0.828049898147583, | |
| "eval_runtime": 3.4856, | |
| "eval_samples_per_second": 28.69, | |
| "eval_steps_per_second": 3.73, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7248, | |
| "step": 969 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7444, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7853, | |
| "step": 971 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8054, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 0.8272585868835449, | |
| "eval_runtime": 3.4916, | |
| "eval_samples_per_second": 28.641, | |
| "eval_steps_per_second": 3.723, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9867, | |
| "step": 973 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7704, | |
| "step": 974 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9869, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0024, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_loss": 0.8271434307098389, | |
| "eval_runtime": 3.4831, | |
| "eval_samples_per_second": 28.71, | |
| "eval_steps_per_second": 3.732, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9022, | |
| "step": 977 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.0002, | |
| "loss": 0.747, | |
| "step": 978 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8414, | |
| "step": 979 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6894, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "eval_loss": 0.8270208835601807, | |
| "eval_runtime": 3.4871, | |
| "eval_samples_per_second": 28.677, | |
| "eval_steps_per_second": 3.728, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9398, | |
| "step": 981 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6662, | |
| "step": 982 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6459, | |
| "step": 983 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0434, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 0.8270233273506165, | |
| "eval_runtime": 3.492, | |
| "eval_samples_per_second": 28.637, | |
| "eval_steps_per_second": 3.723, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6601, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.0002, | |
| "loss": 1.14, | |
| "step": 986 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.0002, | |
| "loss": 0.946, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9675, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 0.827362060546875, | |
| "eval_runtime": 3.4859, | |
| "eval_samples_per_second": 28.687, | |
| "eval_steps_per_second": 3.729, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8056, | |
| "step": 989 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7133, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9467, | |
| "step": 991 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8702, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_loss": 0.8272018432617188, | |
| "eval_runtime": 3.4876, | |
| "eval_samples_per_second": 28.673, | |
| "eval_steps_per_second": 3.727, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0407, | |
| "step": 993 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7856, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0473, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1258, | |
| "step": 996 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "eval_loss": 0.8265512585639954, | |
| "eval_runtime": 3.4938, | |
| "eval_samples_per_second": 28.622, | |
| "eval_steps_per_second": 3.721, | |
| "step": 996 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8403, | |
| "step": 997 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8899, | |
| "step": 998 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9908, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6381, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_loss": 0.8262892961502075, | |
| "eval_runtime": 3.4905, | |
| "eval_samples_per_second": 28.649, | |
| "eval_steps_per_second": 3.724, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9814, | |
| "step": 1001 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6422, | |
| "step": 1002 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8131, | |
| "step": 1003 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0568, | |
| "step": 1004 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_loss": 0.8275936245918274, | |
| "eval_runtime": 3.4922, | |
| "eval_samples_per_second": 28.635, | |
| "eval_steps_per_second": 3.723, | |
| "step": 1004 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8108, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7303, | |
| "step": 1006 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1613, | |
| "step": 1007 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0323, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_loss": 0.8278980255126953, | |
| "eval_runtime": 3.4933, | |
| "eval_samples_per_second": 28.626, | |
| "eval_steps_per_second": 3.721, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9555, | |
| "step": 1009 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7843, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9779, | |
| "step": 1011 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8836, | |
| "step": 1012 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 0.8284029364585876, | |
| "eval_runtime": 3.4831, | |
| "eval_samples_per_second": 28.71, | |
| "eval_steps_per_second": 3.732, | |
| "step": 1012 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7755, | |
| "step": 1013 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8415, | |
| "step": 1014 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8502, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7942, | |
| "step": 1016 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "eval_loss": 0.8293335437774658, | |
| "eval_runtime": 3.4863, | |
| "eval_samples_per_second": 28.684, | |
| "eval_steps_per_second": 3.729, | |
| "step": 1016 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7873, | |
| "step": 1017 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9358, | |
| "step": 1018 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7838, | |
| "step": 1019 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6705, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "eval_loss": 0.8286979794502258, | |
| "eval_runtime": 3.4836, | |
| "eval_samples_per_second": 28.706, | |
| "eval_steps_per_second": 3.732, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9261, | |
| "step": 1021 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.0002, | |
| "loss": 1.036, | |
| "step": 1022 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8973, | |
| "step": 1023 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7855, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_loss": 0.8283995985984802, | |
| "eval_runtime": 3.4904, | |
| "eval_samples_per_second": 28.65, | |
| "eval_steps_per_second": 3.724, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7927, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1697, | |
| "step": 1026 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7068, | |
| "step": 1027 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9075, | |
| "step": 1028 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "eval_loss": 0.8286544680595398, | |
| "eval_runtime": 3.4815, | |
| "eval_samples_per_second": 28.723, | |
| "eval_steps_per_second": 3.734, | |
| "step": 1028 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.0002, | |
| "loss": 0.833, | |
| "step": 1029 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0603, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9005, | |
| "step": 1031 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8429, | |
| "step": 1032 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "eval_loss": 0.8288383483886719, | |
| "eval_runtime": 3.4792, | |
| "eval_samples_per_second": 28.742, | |
| "eval_steps_per_second": 3.737, | |
| "step": 1032 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9522, | |
| "step": 1033 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.909, | |
| "step": 1034 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1316, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6188, | |
| "step": 1036 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 0.8282912969589233, | |
| "eval_runtime": 3.4906, | |
| "eval_samples_per_second": 28.648, | |
| "eval_steps_per_second": 3.724, | |
| "step": 1036 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8065, | |
| "step": 1037 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6524, | |
| "step": 1038 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8047, | |
| "step": 1039 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8141, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_loss": 0.827260434627533, | |
| "eval_runtime": 3.4842, | |
| "eval_samples_per_second": 28.701, | |
| "eval_steps_per_second": 3.731, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6743, | |
| "step": 1041 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9884, | |
| "step": 1042 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6528, | |
| "step": 1043 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8099, | |
| "step": 1044 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "eval_loss": 0.8275359272956848, | |
| "eval_runtime": 3.4822, | |
| "eval_samples_per_second": 28.717, | |
| "eval_steps_per_second": 3.733, | |
| "step": 1044 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5901, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.0002, | |
| "loss": 0.678, | |
| "step": 1046 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9936, | |
| "step": 1047 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9614, | |
| "step": 1048 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "eval_loss": 0.828519880771637, | |
| "eval_runtime": 3.4919, | |
| "eval_samples_per_second": 28.638, | |
| "eval_steps_per_second": 3.723, | |
| "step": 1048 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 0.0002, | |
| "loss": 0.54, | |
| "step": 1049 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9067, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9605, | |
| "step": 1051 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8893, | |
| "step": 1052 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "eval_loss": 0.8287599086761475, | |
| "eval_runtime": 3.4833, | |
| "eval_samples_per_second": 28.708, | |
| "eval_steps_per_second": 3.732, | |
| "step": 1052 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8637, | |
| "step": 1053 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5634, | |
| "step": 1054 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8319, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8753, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_loss": 0.8285097479820251, | |
| "eval_runtime": 3.4773, | |
| "eval_samples_per_second": 28.758, | |
| "eval_steps_per_second": 3.739, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 0.0002, | |
| "loss": 0.973, | |
| "step": 1057 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9596, | |
| "step": 1058 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8173, | |
| "step": 1059 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2927, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_loss": 0.8283626437187195, | |
| "eval_runtime": 3.4783, | |
| "eval_samples_per_second": 28.75, | |
| "eval_steps_per_second": 3.737, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7916, | |
| "step": 1061 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9179, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9375, | |
| "step": 1063 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.74, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "eval_loss": 0.8281582593917847, | |
| "eval_runtime": 3.4852, | |
| "eval_samples_per_second": 28.693, | |
| "eval_steps_per_second": 3.73, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8849, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6895, | |
| "step": 1066 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9857, | |
| "step": 1067 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6452, | |
| "step": 1068 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "eval_loss": 0.8275434374809265, | |
| "eval_runtime": 3.4881, | |
| "eval_samples_per_second": 28.669, | |
| "eval_steps_per_second": 3.727, | |
| "step": 1068 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8369, | |
| "step": 1069 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8756, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8136, | |
| "step": 1071 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7119, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "eval_loss": 0.82715904712677, | |
| "eval_runtime": 3.4826, | |
| "eval_samples_per_second": 28.714, | |
| "eval_steps_per_second": 3.733, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6628, | |
| "step": 1073 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7411, | |
| "step": 1074 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8296, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7736, | |
| "step": 1076 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_loss": 0.8270102143287659, | |
| "eval_runtime": 3.4819, | |
| "eval_samples_per_second": 28.72, | |
| "eval_steps_per_second": 3.734, | |
| "step": 1076 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7869, | |
| "step": 1077 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8197, | |
| "step": 1078 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7428, | |
| "step": 1079 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6718, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_loss": 0.8277941346168518, | |
| "eval_runtime": 3.489, | |
| "eval_samples_per_second": 28.661, | |
| "eval_steps_per_second": 3.726, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7149, | |
| "step": 1081 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9678, | |
| "step": 1082 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8208, | |
| "step": 1083 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7471, | |
| "step": 1084 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_loss": 0.8276605010032654, | |
| "eval_runtime": 3.4894, | |
| "eval_samples_per_second": 28.659, | |
| "eval_steps_per_second": 3.726, | |
| "step": 1084 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9087, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 0.0002, | |
| "loss": 0.87, | |
| "step": 1086 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9384, | |
| "step": 1087 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9082, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "eval_loss": 0.8259733319282532, | |
| "eval_runtime": 3.4856, | |
| "eval_samples_per_second": 28.689, | |
| "eval_steps_per_second": 3.73, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9231, | |
| "step": 1089 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7653, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8472, | |
| "step": 1091 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6908, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "eval_loss": 0.8254422545433044, | |
| "eval_runtime": 3.4866, | |
| "eval_samples_per_second": 28.681, | |
| "eval_steps_per_second": 3.729, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5794, | |
| "step": 1093 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7246, | |
| "step": 1094 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8781, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0066, | |
| "step": 1096 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 0.8255140781402588, | |
| "eval_runtime": 3.4871, | |
| "eval_samples_per_second": 28.677, | |
| "eval_steps_per_second": 3.728, | |
| "step": 1096 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8921, | |
| "step": 1097 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7523, | |
| "step": 1098 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8594, | |
| "step": 1099 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8661, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_loss": 0.825514018535614, | |
| "eval_runtime": 3.4827, | |
| "eval_samples_per_second": 28.713, | |
| "eval_steps_per_second": 3.733, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7451, | |
| "step": 1101 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9307, | |
| "step": 1102 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8028, | |
| "step": 1103 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.0002, | |
| "loss": 0.829, | |
| "step": 1104 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "eval_loss": 0.8263520002365112, | |
| "eval_runtime": 3.4846, | |
| "eval_samples_per_second": 28.698, | |
| "eval_steps_per_second": 3.731, | |
| "step": 1104 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6661, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8445, | |
| "step": 1106 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9743, | |
| "step": 1107 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0031, | |
| "step": 1108 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "eval_loss": 0.8263025879859924, | |
| "eval_runtime": 3.4849, | |
| "eval_samples_per_second": 28.695, | |
| "eval_steps_per_second": 3.73, | |
| "step": 1108 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7894, | |
| "step": 1109 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8911, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.0002, | |
| "loss": 1.068, | |
| "step": 1111 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9051, | |
| "step": 1112 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "eval_loss": 0.8257004022598267, | |
| "eval_runtime": 3.4886, | |
| "eval_samples_per_second": 28.665, | |
| "eval_steps_per_second": 3.726, | |
| "step": 1112 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8587, | |
| "step": 1113 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8117, | |
| "step": 1114 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8864, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8267, | |
| "step": 1116 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "eval_loss": 0.8253694176673889, | |
| "eval_runtime": 3.4873, | |
| "eval_samples_per_second": 28.675, | |
| "eval_steps_per_second": 3.728, | |
| "step": 1116 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 0.0002, | |
| "loss": 0.836, | |
| "step": 1117 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6967, | |
| "step": 1118 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9521, | |
| "step": 1119 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0157, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "eval_loss": 0.825802743434906, | |
| "eval_runtime": 3.4841, | |
| "eval_samples_per_second": 28.702, | |
| "eval_steps_per_second": 3.731, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6847, | |
| "step": 1121 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9214, | |
| "step": 1122 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0741, | |
| "step": 1123 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8736, | |
| "step": 1124 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "eval_loss": 0.825918436050415, | |
| "eval_runtime": 3.489, | |
| "eval_samples_per_second": 28.661, | |
| "eval_steps_per_second": 3.726, | |
| "step": 1124 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7404, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 0.0002, | |
| "loss": 0.662, | |
| "step": 1126 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0885, | |
| "step": 1127 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9316, | |
| "step": 1128 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "eval_loss": 0.8252816200256348, | |
| "eval_runtime": 3.4944, | |
| "eval_samples_per_second": 28.617, | |
| "eval_steps_per_second": 3.72, | |
| "step": 1128 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 0.0002, | |
| "loss": 0.957, | |
| "step": 1129 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0476, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6106, | |
| "step": 1131 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9573, | |
| "step": 1132 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "eval_loss": 0.8246933817863464, | |
| "eval_runtime": 3.4863, | |
| "eval_samples_per_second": 28.684, | |
| "eval_steps_per_second": 3.729, | |
| "step": 1132 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6427, | |
| "step": 1133 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8786, | |
| "step": 1134 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6899, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9419, | |
| "step": 1136 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_loss": 0.8247870802879333, | |
| "eval_runtime": 3.4846, | |
| "eval_samples_per_second": 28.698, | |
| "eval_steps_per_second": 3.731, | |
| "step": 1136 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7543, | |
| "step": 1137 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6932, | |
| "step": 1138 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9261, | |
| "step": 1139 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 0.0002, | |
| "loss": 0.941, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_loss": 0.8253961801528931, | |
| "eval_runtime": 3.4868, | |
| "eval_samples_per_second": 28.68, | |
| "eval_steps_per_second": 3.728, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9263, | |
| "step": 1141 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 0.0002, | |
| "loss": 0.751, | |
| "step": 1142 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8192, | |
| "step": 1143 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9268, | |
| "step": 1144 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "eval_loss": 0.8258420825004578, | |
| "eval_runtime": 3.4907, | |
| "eval_samples_per_second": 28.647, | |
| "eval_steps_per_second": 3.724, | |
| "step": 1144 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8068, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7696, | |
| "step": 1146 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7179, | |
| "step": 1147 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6682, | |
| "step": 1148 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "eval_loss": 0.8252753615379333, | |
| "eval_runtime": 3.4805, | |
| "eval_samples_per_second": 28.732, | |
| "eval_steps_per_second": 3.735, | |
| "step": 1148 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8731, | |
| "step": 1149 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9734, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6795, | |
| "step": 1151 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 0.0002, | |
| "loss": 0.804, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "eval_loss": 0.8247868418693542, | |
| "eval_runtime": 3.4888, | |
| "eval_samples_per_second": 28.663, | |
| "eval_steps_per_second": 3.726, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7341, | |
| "step": 1153 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.979, | |
| "step": 1154 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9636, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9879, | |
| "step": 1156 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 0.8251833915710449, | |
| "eval_runtime": 3.4856, | |
| "eval_samples_per_second": 28.69, | |
| "eval_steps_per_second": 3.73, | |
| "step": 1156 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5959, | |
| "step": 1157 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9652, | |
| "step": 1158 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9113, | |
| "step": 1159 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7937, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_loss": 0.8248522877693176, | |
| "eval_runtime": 3.5009, | |
| "eval_samples_per_second": 28.564, | |
| "eval_steps_per_second": 3.713, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8105, | |
| "step": 1161 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7325, | |
| "step": 1162 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7718, | |
| "step": 1163 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9221, | |
| "step": 1164 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_loss": 0.8250831365585327, | |
| "eval_runtime": 3.4895, | |
| "eval_samples_per_second": 28.657, | |
| "eval_steps_per_second": 3.725, | |
| "step": 1164 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9098, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7633, | |
| "step": 1166 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8793, | |
| "step": 1167 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8808, | |
| "step": 1168 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_loss": 0.8253970146179199, | |
| "eval_runtime": 3.4878, | |
| "eval_samples_per_second": 28.672, | |
| "eval_steps_per_second": 3.727, | |
| "step": 1168 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6561, | |
| "step": 1169 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8086, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8897, | |
| "step": 1171 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0818, | |
| "step": 1172 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "eval_loss": 0.8248065114021301, | |
| "eval_runtime": 3.4867, | |
| "eval_samples_per_second": 28.68, | |
| "eval_steps_per_second": 3.728, | |
| "step": 1172 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 0.0002, | |
| "loss": 0.833, | |
| "step": 1173 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9457, | |
| "step": 1174 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7082, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.0002, | |
| "loss": 0.978, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "eval_loss": 0.824617862701416, | |
| "eval_runtime": 3.4879, | |
| "eval_samples_per_second": 28.671, | |
| "eval_steps_per_second": 3.727, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.0002, | |
| "loss": 0.621, | |
| "step": 1177 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8122, | |
| "step": 1178 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9566, | |
| "step": 1179 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8127, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "eval_loss": 0.8237550258636475, | |
| "eval_runtime": 3.4794, | |
| "eval_samples_per_second": 28.741, | |
| "eval_steps_per_second": 3.736, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8026, | |
| "step": 1181 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8997, | |
| "step": 1182 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5875, | |
| "step": 1183 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9731, | |
| "step": 1184 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_loss": 0.8226193189620972, | |
| "eval_runtime": 3.4877, | |
| "eval_samples_per_second": 28.673, | |
| "eval_steps_per_second": 3.727, | |
| "step": 1184 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7305, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9416, | |
| "step": 1186 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6603, | |
| "step": 1187 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6404, | |
| "step": 1188 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "eval_loss": 0.8225893378257751, | |
| "eval_runtime": 3.4827, | |
| "eval_samples_per_second": 28.713, | |
| "eval_steps_per_second": 3.733, | |
| "step": 1188 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7865, | |
| "step": 1189 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8293, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 0.0002, | |
| "loss": 1.216, | |
| "step": 1191 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6912, | |
| "step": 1192 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "eval_loss": 0.8231666088104248, | |
| "eval_runtime": 3.4868, | |
| "eval_samples_per_second": 28.68, | |
| "eval_steps_per_second": 3.728, | |
| "step": 1192 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 0.0002, | |
| "loss": 0.924, | |
| "step": 1193 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8794, | |
| "step": 1194 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 0.0002, | |
| "loss": 0.76, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9322, | |
| "step": 1196 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "eval_loss": 0.8241258263587952, | |
| "eval_runtime": 3.484, | |
| "eval_samples_per_second": 28.703, | |
| "eval_steps_per_second": 3.731, | |
| "step": 1196 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 0.0002, | |
| "loss": 0.704, | |
| "step": 1197 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8382, | |
| "step": 1198 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7557, | |
| "step": 1199 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9019, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "eval_loss": 0.8243316411972046, | |
| "eval_runtime": 3.5041, | |
| "eval_samples_per_second": 28.538, | |
| "eval_steps_per_second": 3.71, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8319, | |
| "step": 1201 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8514, | |
| "step": 1202 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8394, | |
| "step": 1203 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8225, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "eval_loss": 0.8245729804039001, | |
| "eval_runtime": 3.4875, | |
| "eval_samples_per_second": 28.674, | |
| "eval_steps_per_second": 3.728, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9363, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0259, | |
| "step": 1206 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6692, | |
| "step": 1207 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8075, | |
| "step": 1208 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "eval_loss": 0.8243534564971924, | |
| "eval_runtime": 3.4839, | |
| "eval_samples_per_second": 28.703, | |
| "eval_steps_per_second": 3.731, | |
| "step": 1208 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9799, | |
| "step": 1209 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9742, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7375, | |
| "step": 1211 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9741, | |
| "step": 1212 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "eval_loss": 0.8237447142601013, | |
| "eval_runtime": 3.4979, | |
| "eval_samples_per_second": 28.589, | |
| "eval_steps_per_second": 3.717, | |
| "step": 1212 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9755, | |
| "step": 1213 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7498, | |
| "step": 1214 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8441, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1723, | |
| "step": 1216 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "eval_loss": 0.8236591815948486, | |
| "eval_runtime": 3.4889, | |
| "eval_samples_per_second": 28.663, | |
| "eval_steps_per_second": 3.726, | |
| "step": 1216 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8566, | |
| "step": 1217 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7692, | |
| "step": 1218 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7859, | |
| "step": 1219 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8679, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_loss": 0.8235040307044983, | |
| "eval_runtime": 3.4956, | |
| "eval_samples_per_second": 28.607, | |
| "eval_steps_per_second": 3.719, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7685, | |
| "step": 1221 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 0.0002, | |
| "loss": 0.751, | |
| "step": 1222 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7943, | |
| "step": 1223 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 0.0002, | |
| "loss": 1.029, | |
| "step": 1224 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "eval_loss": 0.823618471622467, | |
| "eval_runtime": 3.4828, | |
| "eval_samples_per_second": 28.713, | |
| "eval_steps_per_second": 3.733, | |
| "step": 1224 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8409, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9802, | |
| "step": 1226 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8359, | |
| "step": 1227 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8698, | |
| "step": 1228 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "eval_loss": 0.8239647150039673, | |
| "eval_runtime": 3.4917, | |
| "eval_samples_per_second": 28.64, | |
| "eval_steps_per_second": 3.723, | |
| "step": 1228 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7814, | |
| "step": 1229 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8023, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0397, | |
| "step": 1231 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9259, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_loss": 0.8235681653022766, | |
| "eval_runtime": 3.4872, | |
| "eval_samples_per_second": 28.676, | |
| "eval_steps_per_second": 3.728, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7594, | |
| "step": 1233 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0438, | |
| "step": 1234 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9679, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9502, | |
| "step": 1236 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "eval_loss": 0.8235576748847961, | |
| "eval_runtime": 3.4857, | |
| "eval_samples_per_second": 28.688, | |
| "eval_steps_per_second": 3.729, | |
| "step": 1236 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8518, | |
| "step": 1237 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6716, | |
| "step": 1238 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7519, | |
| "step": 1239 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0555, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_loss": 0.8233658075332642, | |
| "eval_runtime": 3.4839, | |
| "eval_samples_per_second": 28.703, | |
| "eval_steps_per_second": 3.731, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9013, | |
| "step": 1241 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7476, | |
| "step": 1242 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7954, | |
| "step": 1243 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0191, | |
| "step": 1244 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "eval_loss": 0.8232245445251465, | |
| "eval_runtime": 3.4793, | |
| "eval_samples_per_second": 28.741, | |
| "eval_steps_per_second": 3.736, | |
| "step": 1244 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8526, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6262, | |
| "step": 1246 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9338, | |
| "step": 1247 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0136, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "eval_loss": 0.8236140608787537, | |
| "eval_runtime": 3.4872, | |
| "eval_samples_per_second": 28.677, | |
| "eval_steps_per_second": 3.728, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9049, | |
| "step": 1249 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8125, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9255, | |
| "step": 1251 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8528, | |
| "step": 1252 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "eval_loss": 0.8237339854240417, | |
| "eval_runtime": 3.4872, | |
| "eval_samples_per_second": 28.676, | |
| "eval_steps_per_second": 3.728, | |
| "step": 1252 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6428, | |
| "step": 1253 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8334, | |
| "step": 1254 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7943, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8362, | |
| "step": 1256 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "eval_loss": 0.8237020969390869, | |
| "eval_runtime": 3.5005, | |
| "eval_samples_per_second": 28.567, | |
| "eval_steps_per_second": 3.714, | |
| "step": 1256 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6537, | |
| "step": 1257 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8216, | |
| "step": 1258 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0942, | |
| "step": 1259 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7808, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 0.823066234588623, | |
| "eval_runtime": 3.484, | |
| "eval_samples_per_second": 28.703, | |
| "eval_steps_per_second": 3.731, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6899, | |
| "step": 1261 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0414, | |
| "step": 1262 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9649, | |
| "step": 1263 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9076, | |
| "step": 1264 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "eval_loss": 0.822204053401947, | |
| "eval_runtime": 3.4914, | |
| "eval_samples_per_second": 28.642, | |
| "eval_steps_per_second": 3.723, | |
| "step": 1264 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9158, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8404, | |
| "step": 1266 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9536, | |
| "step": 1267 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6888, | |
| "step": 1268 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "eval_loss": 0.8221558332443237, | |
| "eval_runtime": 3.4825, | |
| "eval_samples_per_second": 28.715, | |
| "eval_steps_per_second": 3.733, | |
| "step": 1268 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9501, | |
| "step": 1269 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8316, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6863, | |
| "step": 1271 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7948, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_loss": 0.8225569725036621, | |
| "eval_runtime": 3.4896, | |
| "eval_samples_per_second": 28.656, | |
| "eval_steps_per_second": 3.725, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6634, | |
| "step": 1273 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9511, | |
| "step": 1274 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9536, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7096, | |
| "step": 1276 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 0.8229076862335205, | |
| "eval_runtime": 3.4844, | |
| "eval_samples_per_second": 28.699, | |
| "eval_steps_per_second": 3.731, | |
| "step": 1276 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8948, | |
| "step": 1277 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8952, | |
| "step": 1278 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0337, | |
| "step": 1279 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8928, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 0.8221405744552612, | |
| "eval_runtime": 3.4869, | |
| "eval_samples_per_second": 28.679, | |
| "eval_steps_per_second": 3.728, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1111, | |
| "step": 1281 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8572, | |
| "step": 1282 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 0.0002, | |
| "loss": 0.921, | |
| "step": 1283 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8446, | |
| "step": 1284 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "eval_loss": 0.8219377994537354, | |
| "eval_runtime": 3.4839, | |
| "eval_samples_per_second": 28.703, | |
| "eval_steps_per_second": 3.731, | |
| "step": 1284 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8885, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6121, | |
| "step": 1286 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9399, | |
| "step": 1287 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6204, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "eval_loss": 0.8224560618400574, | |
| "eval_runtime": 3.4806, | |
| "eval_samples_per_second": 28.731, | |
| "eval_steps_per_second": 3.735, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9122, | |
| "step": 1289 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7874, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8841, | |
| "step": 1291 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1946, | |
| "step": 1292 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "eval_loss": 0.8226752281188965, | |
| "eval_runtime": 3.4876, | |
| "eval_samples_per_second": 28.673, | |
| "eval_steps_per_second": 3.727, | |
| "step": 1292 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 0.0002, | |
| "loss": 0.935, | |
| "step": 1293 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2146, | |
| "step": 1294 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7241, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9498, | |
| "step": 1296 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "eval_loss": 0.8223884701728821, | |
| "eval_runtime": 3.4872, | |
| "eval_samples_per_second": 28.676, | |
| "eval_steps_per_second": 3.728, | |
| "step": 1296 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8002, | |
| "step": 1297 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0213, | |
| "step": 1298 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6982, | |
| "step": 1299 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6986, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "eval_loss": 0.8215851783752441, | |
| "eval_runtime": 3.4873, | |
| "eval_samples_per_second": 28.676, | |
| "eval_steps_per_second": 3.728, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8366, | |
| "step": 1301 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8229, | |
| "step": 1302 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9874, | |
| "step": 1303 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9265, | |
| "step": 1304 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_loss": 0.8210740089416504, | |
| "eval_runtime": 3.4865, | |
| "eval_samples_per_second": 28.682, | |
| "eval_steps_per_second": 3.729, | |
| "step": 1304 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.0002, | |
| "loss": 1.014, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9672, | |
| "step": 1306 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9759, | |
| "step": 1307 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8652, | |
| "step": 1308 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "eval_loss": 0.8208446502685547, | |
| "eval_runtime": 3.4908, | |
| "eval_samples_per_second": 28.646, | |
| "eval_steps_per_second": 3.724, | |
| "step": 1308 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0041, | |
| "step": 1309 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7984, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9623, | |
| "step": 1311 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8038, | |
| "step": 1312 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "eval_loss": 0.8200948238372803, | |
| "eval_runtime": 3.4928, | |
| "eval_samples_per_second": 28.63, | |
| "eval_steps_per_second": 3.722, | |
| "step": 1312 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0158, | |
| "step": 1313 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9738, | |
| "step": 1314 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6824, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 0.0002, | |
| "loss": 0.844, | |
| "step": 1316 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_loss": 0.818276047706604, | |
| "eval_runtime": 3.4908, | |
| "eval_samples_per_second": 28.646, | |
| "eval_steps_per_second": 3.724, | |
| "step": 1316 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 0.0002, | |
| "loss": 1.059, | |
| "step": 1317 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9418, | |
| "step": 1318 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7822, | |
| "step": 1319 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8184, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "eval_loss": 0.8178786635398865, | |
| "eval_runtime": 3.4808, | |
| "eval_samples_per_second": 28.729, | |
| "eval_steps_per_second": 3.735, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7434, | |
| "step": 1321 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9948, | |
| "step": 1322 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9926, | |
| "step": 1323 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8529, | |
| "step": 1324 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_loss": 0.8173670768737793, | |
| "eval_runtime": 3.4826, | |
| "eval_samples_per_second": 28.714, | |
| "eval_steps_per_second": 3.733, | |
| "step": 1324 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 0.0002, | |
| "loss": 0.871, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8162, | |
| "step": 1326 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7788, | |
| "step": 1327 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8875, | |
| "step": 1328 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "eval_loss": 0.8175342679023743, | |
| "eval_runtime": 3.4851, | |
| "eval_samples_per_second": 28.693, | |
| "eval_steps_per_second": 3.73, | |
| "step": 1328 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 0.0002, | |
| "loss": 0.718, | |
| "step": 1329 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8669, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1285, | |
| "step": 1331 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6976, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_loss": 0.8177915215492249, | |
| "eval_runtime": 3.4939, | |
| "eval_samples_per_second": 28.621, | |
| "eval_steps_per_second": 3.721, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9099, | |
| "step": 1333 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6425, | |
| "step": 1334 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7584, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6298, | |
| "step": 1336 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_loss": 0.8175650835037231, | |
| "eval_runtime": 3.4876, | |
| "eval_samples_per_second": 28.673, | |
| "eval_steps_per_second": 3.727, | |
| "step": 1336 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5837, | |
| "step": 1337 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9823, | |
| "step": 1338 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9749, | |
| "step": 1339 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.0002, | |
| "loss": 0.584, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "eval_loss": 0.8173122406005859, | |
| "eval_runtime": 3.4898, | |
| "eval_samples_per_second": 28.655, | |
| "eval_steps_per_second": 3.725, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7758, | |
| "step": 1341 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6487, | |
| "step": 1342 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0128, | |
| "step": 1343 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8352, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "eval_loss": 0.8172879219055176, | |
| "eval_runtime": 3.4865, | |
| "eval_samples_per_second": 28.682, | |
| "eval_steps_per_second": 3.729, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0302, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9552, | |
| "step": 1346 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9073, | |
| "step": 1347 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9362, | |
| "step": 1348 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "eval_loss": 0.8172414302825928, | |
| "eval_runtime": 3.4885, | |
| "eval_samples_per_second": 28.665, | |
| "eval_steps_per_second": 3.726, | |
| "step": 1348 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8948, | |
| "step": 1349 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8974, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.0002, | |
| "loss": 0.789, | |
| "step": 1351 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.0002, | |
| "loss": 0.898, | |
| "step": 1352 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_loss": 0.8174081444740295, | |
| "eval_runtime": 3.4904, | |
| "eval_samples_per_second": 28.65, | |
| "eval_steps_per_second": 3.725, | |
| "step": 1352 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8581, | |
| "step": 1353 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8485, | |
| "step": 1354 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9739, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6644, | |
| "step": 1356 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "eval_loss": 0.8181654214859009, | |
| "eval_runtime": 3.4823, | |
| "eval_samples_per_second": 28.716, | |
| "eval_steps_per_second": 3.733, | |
| "step": 1356 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9097, | |
| "step": 1357 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7286, | |
| "step": 1358 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 0.0002, | |
| "loss": 0.914, | |
| "step": 1359 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5753, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_loss": 0.8187414407730103, | |
| "eval_runtime": 3.4844, | |
| "eval_samples_per_second": 28.699, | |
| "eval_steps_per_second": 3.731, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7559, | |
| "step": 1361 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0115, | |
| "step": 1362 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9569, | |
| "step": 1363 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.0002, | |
| "loss": 1.002, | |
| "step": 1364 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_loss": 0.8193130493164062, | |
| "eval_runtime": 3.4861, | |
| "eval_samples_per_second": 28.686, | |
| "eval_steps_per_second": 3.729, | |
| "step": 1364 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8698, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9098, | |
| "step": 1366 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.0002, | |
| "loss": 0.796, | |
| "step": 1367 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8874, | |
| "step": 1368 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.8184587359428406, | |
| "eval_runtime": 3.4919, | |
| "eval_samples_per_second": 28.638, | |
| "eval_steps_per_second": 3.723, | |
| "step": 1368 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 2280, | |
| "num_train_epochs": 5, | |
| "save_steps": 4, | |
| "total_flos": 4.4441837423611085e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |