| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 34.0, | |
| "eval_steps": 10, | |
| "global_step": 187, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0, | |
| "loss": 2.0388, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 14.199334144592285, | |
| "eval_runtime": 1.4513, | |
| "eval_samples_per_second": 45.477, | |
| "eval_steps_per_second": 2.067, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.000000000000001e-08, | |
| "loss": 11.2905, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.2000000000000002e-07, | |
| "loss": 11.3574, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.8e-07, | |
| "loss": 10.3132, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.4000000000000003e-07, | |
| "loss": 8.2949, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.0000000000000004e-07, | |
| "loss": 5.3189, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.6e-07, | |
| "loss": 2.2121, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 4.2000000000000006e-07, | |
| "loss": 2.0155, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 4.800000000000001e-07, | |
| "loss": 1.9936, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 5.4e-07, | |
| "loss": 1.8803, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_loss": 2.1710054874420166, | |
| "eval_runtime": 1.463, | |
| "eval_samples_per_second": 45.113, | |
| "eval_steps_per_second": 2.051, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.000000000000001e-07, | |
| "loss": 1.8794, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 6.6e-07, | |
| "loss": 1.884, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 7.2e-07, | |
| "loss": 1.8201, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.8e-07, | |
| "loss": 1.8356, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 8.400000000000001e-07, | |
| "loss": 1.7696, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 9e-07, | |
| "loss": 1.6433, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 9.600000000000001e-07, | |
| "loss": 1.5564, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 1.0200000000000002e-06, | |
| "loss": 1.4976, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 1.08e-06, | |
| "loss": 1.4484, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 1.14e-06, | |
| "loss": 1.4277, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "eval_loss": 1.5980714559555054, | |
| "eval_runtime": 1.4588, | |
| "eval_samples_per_second": 45.243, | |
| "eval_steps_per_second": 2.056, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 1.4004, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.26e-06, | |
| "loss": 1.3963, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 1.32e-06, | |
| "loss": 1.3915, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 1.3800000000000001e-06, | |
| "loss": 1.3803, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 1.44e-06, | |
| "loss": 1.3711, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 1.5e-06, | |
| "loss": 1.3596, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 1.56e-06, | |
| "loss": 1.3376, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 1.6200000000000002e-06, | |
| "loss": 1.3241, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 1.6800000000000002e-06, | |
| "loss": 1.2975, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 1.7399999999999999e-06, | |
| "loss": 1.2847, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "eval_loss": 1.4864555597305298, | |
| "eval_runtime": 1.4609, | |
| "eval_samples_per_second": 45.176, | |
| "eval_steps_per_second": 2.053, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "learning_rate": 1.8e-06, | |
| "loss": 1.2798, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 1.86e-06, | |
| "loss": 1.2616, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 1.9200000000000003e-06, | |
| "loss": 1.252, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 1.98e-06, | |
| "loss": 1.2398, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 2.0400000000000004e-06, | |
| "loss": 1.2229, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 2.1e-06, | |
| "loss": 1.2221, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "learning_rate": 2.16e-06, | |
| "loss": 1.2046, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 2.22e-06, | |
| "loss": 1.1908, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 2.28e-06, | |
| "loss": 1.1916, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 2.34e-06, | |
| "loss": 1.1733, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "eval_loss": 1.37030827999115, | |
| "eval_runtime": 1.4628, | |
| "eval_samples_per_second": 45.118, | |
| "eval_steps_per_second": 2.051, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 1.1708, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 2.4599999999999997e-06, | |
| "loss": 1.1727, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 7.82, | |
| "learning_rate": 2.52e-06, | |
| "loss": 1.1615, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.58e-06, | |
| "loss": 1.1529, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 2.64e-06, | |
| "loss": 1.1428, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 2.7e-06, | |
| "loss": 1.1398, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 2.7600000000000003e-06, | |
| "loss": 1.1392, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 2.82e-06, | |
| "loss": 1.121, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "learning_rate": 2.88e-06, | |
| "loss": 1.1239, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 2.9400000000000002e-06, | |
| "loss": 1.1131, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "eval_loss": 1.3062629699707031, | |
| "eval_runtime": 1.4506, | |
| "eval_samples_per_second": 45.499, | |
| "eval_steps_per_second": 2.068, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "learning_rate": 3e-06, | |
| "loss": 1.1047, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 3.06e-06, | |
| "loss": 1.1012, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "learning_rate": 3.12e-06, | |
| "loss": 1.0987, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 3.18e-06, | |
| "loss": 1.1012, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 3.2400000000000003e-06, | |
| "loss": 1.093, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 10.18, | |
| "learning_rate": 3.3e-06, | |
| "loss": 1.0876, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 10.36, | |
| "learning_rate": 3.3600000000000004e-06, | |
| "loss": 1.0813, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "learning_rate": 3.42e-06, | |
| "loss": 1.0798, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 10.73, | |
| "learning_rate": 3.4799999999999997e-06, | |
| "loss": 1.0673, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "learning_rate": 3.54e-06, | |
| "loss": 1.0616, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "eval_loss": 1.2495708465576172, | |
| "eval_runtime": 1.4605, | |
| "eval_samples_per_second": 45.19, | |
| "eval_steps_per_second": 2.054, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 11.09, | |
| "learning_rate": 3.6e-06, | |
| "loss": 1.0639, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 11.27, | |
| "learning_rate": 3.66e-06, | |
| "loss": 1.0538, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 11.45, | |
| "learning_rate": 3.72e-06, | |
| "loss": 1.0567, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 11.64, | |
| "learning_rate": 3.7800000000000002e-06, | |
| "loss": 1.0465, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 11.82, | |
| "learning_rate": 3.8400000000000005e-06, | |
| "loss": 1.0485, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 3.9e-06, | |
| "loss": 1.0494, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 12.18, | |
| "learning_rate": 3.96e-06, | |
| "loss": 1.0359, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 12.36, | |
| "learning_rate": 4.0200000000000005e-06, | |
| "loss": 1.0336, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 12.55, | |
| "learning_rate": 4.080000000000001e-06, | |
| "loss": 1.0317, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 12.73, | |
| "learning_rate": 4.14e-06, | |
| "loss": 1.0302, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 12.73, | |
| "eval_loss": 1.2099440097808838, | |
| "eval_runtime": 1.4611, | |
| "eval_samples_per_second": 45.172, | |
| "eval_steps_per_second": 2.053, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 12.91, | |
| "learning_rate": 4.2e-06, | |
| "loss": 1.0249, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 13.09, | |
| "learning_rate": 4.26e-06, | |
| "loss": 1.022, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 13.27, | |
| "learning_rate": 4.32e-06, | |
| "loss": 1.0138, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 13.45, | |
| "learning_rate": 4.38e-06, | |
| "loss": 1.0136, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 13.64, | |
| "learning_rate": 4.44e-06, | |
| "loss": 1.0169, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 13.82, | |
| "learning_rate": 4.5e-06, | |
| "loss": 1.0041, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 4.56e-06, | |
| "loss": 0.9956, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 14.18, | |
| "learning_rate": 4.62e-06, | |
| "loss": 0.9941, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 14.36, | |
| "learning_rate": 4.68e-06, | |
| "loss": 0.9963, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "learning_rate": 4.74e-06, | |
| "loss": 0.9866, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "eval_loss": 1.1811805963516235, | |
| "eval_runtime": 1.4593, | |
| "eval_samples_per_second": 45.228, | |
| "eval_steps_per_second": 2.056, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 14.73, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 0.9904, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 14.91, | |
| "learning_rate": 4.86e-06, | |
| "loss": 0.9849, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 15.09, | |
| "learning_rate": 4.9199999999999995e-06, | |
| "loss": 0.9784, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 15.27, | |
| "learning_rate": 4.98e-06, | |
| "loss": 0.9801, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 15.45, | |
| "learning_rate": 5.04e-06, | |
| "loss": 0.9749, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 15.64, | |
| "learning_rate": 5.1e-06, | |
| "loss": 0.9667, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 15.82, | |
| "learning_rate": 5.16e-06, | |
| "loss": 0.9675, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 5.22e-06, | |
| "loss": 0.9666, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 16.18, | |
| "learning_rate": 5.28e-06, | |
| "loss": 0.9582, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 16.36, | |
| "learning_rate": 5.3400000000000005e-06, | |
| "loss": 0.9594, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 16.36, | |
| "eval_loss": 1.1599087715148926, | |
| "eval_runtime": 1.4615, | |
| "eval_samples_per_second": 45.16, | |
| "eval_steps_per_second": 2.053, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 16.55, | |
| "learning_rate": 5.4e-06, | |
| "loss": 0.9462, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 16.73, | |
| "learning_rate": 5.46e-06, | |
| "loss": 0.952, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 16.91, | |
| "learning_rate": 5.5200000000000005e-06, | |
| "loss": 0.9507, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 17.09, | |
| "learning_rate": 5.580000000000001e-06, | |
| "loss": 0.9535, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 17.27, | |
| "learning_rate": 5.64e-06, | |
| "loss": 0.9436, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 17.45, | |
| "learning_rate": 5.7e-06, | |
| "loss": 0.9338, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 17.64, | |
| "learning_rate": 5.76e-06, | |
| "loss": 0.9355, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 17.82, | |
| "learning_rate": 5.82e-06, | |
| "loss": 0.9355, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 5.8800000000000005e-06, | |
| "loss": 0.9343, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 18.18, | |
| "learning_rate": 5.94e-06, | |
| "loss": 0.9161, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 18.18, | |
| "eval_loss": 1.1503610610961914, | |
| "eval_runtime": 1.4537, | |
| "eval_samples_per_second": 45.4, | |
| "eval_steps_per_second": 2.064, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 18.36, | |
| "learning_rate": 6e-06, | |
| "loss": 0.9156, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 18.55, | |
| "learning_rate": 5.94e-06, | |
| "loss": 0.9185, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 18.73, | |
| "learning_rate": 5.8800000000000005e-06, | |
| "loss": 0.9155, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 18.91, | |
| "learning_rate": 5.82e-06, | |
| "loss": 0.9114, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 19.09, | |
| "learning_rate": 5.76e-06, | |
| "loss": 0.8976, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 19.27, | |
| "learning_rate": 5.7e-06, | |
| "loss": 0.8985, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 19.45, | |
| "learning_rate": 5.64e-06, | |
| "loss": 0.8972, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 19.64, | |
| "learning_rate": 5.580000000000001e-06, | |
| "loss": 0.8961, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 19.82, | |
| "learning_rate": 5.5200000000000005e-06, | |
| "loss": 0.8948, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 5.46e-06, | |
| "loss": 0.8823, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 1.13896906375885, | |
| "eval_runtime": 1.4633, | |
| "eval_samples_per_second": 45.103, | |
| "eval_steps_per_second": 2.05, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 20.18, | |
| "learning_rate": 5.4e-06, | |
| "loss": 0.8689, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 20.36, | |
| "learning_rate": 5.3400000000000005e-06, | |
| "loss": 0.8832, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 20.55, | |
| "learning_rate": 5.28e-06, | |
| "loss": 0.875, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 20.73, | |
| "learning_rate": 5.22e-06, | |
| "loss": 0.8655, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 20.91, | |
| "learning_rate": 5.16e-06, | |
| "loss": 0.8695, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 21.09, | |
| "learning_rate": 5.1e-06, | |
| "loss": 0.8636, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 21.27, | |
| "learning_rate": 5.04e-06, | |
| "loss": 0.8513, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 21.45, | |
| "learning_rate": 4.98e-06, | |
| "loss": 0.8523, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 21.64, | |
| "learning_rate": 4.9199999999999995e-06, | |
| "loss": 0.8497, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 21.82, | |
| "learning_rate": 4.86e-06, | |
| "loss": 0.8441, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 21.82, | |
| "eval_loss": 1.1353310346603394, | |
| "eval_runtime": 1.4613, | |
| "eval_samples_per_second": 45.164, | |
| "eval_steps_per_second": 2.053, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 0.8543, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 22.18, | |
| "learning_rate": 4.74e-06, | |
| "loss": 0.838, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 22.36, | |
| "learning_rate": 4.68e-06, | |
| "loss": 0.8348, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 22.55, | |
| "learning_rate": 4.62e-06, | |
| "loss": 0.8215, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 22.73, | |
| "learning_rate": 4.56e-06, | |
| "loss": 0.8313, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 22.91, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.8303, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 23.09, | |
| "learning_rate": 4.44e-06, | |
| "loss": 0.8188, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 23.27, | |
| "learning_rate": 4.38e-06, | |
| "loss": 0.812, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 23.45, | |
| "learning_rate": 4.32e-06, | |
| "loss": 0.8077, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 23.64, | |
| "learning_rate": 4.26e-06, | |
| "loss": 0.7956, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 23.64, | |
| "eval_loss": 1.1432788372039795, | |
| "eval_runtime": 1.461, | |
| "eval_samples_per_second": 45.176, | |
| "eval_steps_per_second": 2.053, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 23.82, | |
| "learning_rate": 4.2e-06, | |
| "loss": 0.8099, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 4.14e-06, | |
| "loss": 0.8223, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 24.18, | |
| "learning_rate": 4.080000000000001e-06, | |
| "loss": 0.7956, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 24.36, | |
| "learning_rate": 4.0200000000000005e-06, | |
| "loss": 0.7889, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 24.55, | |
| "learning_rate": 3.96e-06, | |
| "loss": 0.7844, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 24.73, | |
| "learning_rate": 3.9e-06, | |
| "loss": 0.7867, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 24.91, | |
| "learning_rate": 3.8400000000000005e-06, | |
| "loss": 0.7875, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 25.09, | |
| "learning_rate": 3.7800000000000002e-06, | |
| "loss": 0.7804, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 25.27, | |
| "learning_rate": 3.72e-06, | |
| "loss": 0.7661, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 25.45, | |
| "learning_rate": 3.66e-06, | |
| "loss": 0.7696, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 25.45, | |
| "eval_loss": 1.1572602987289429, | |
| "eval_runtime": 1.4603, | |
| "eval_samples_per_second": 45.197, | |
| "eval_steps_per_second": 2.054, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 3.6e-06, | |
| "loss": 0.7531, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 25.82, | |
| "learning_rate": 3.54e-06, | |
| "loss": 0.7538, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 3.4799999999999997e-06, | |
| "loss": 0.7574, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 26.18, | |
| "learning_rate": 3.42e-06, | |
| "loss": 0.746, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 26.36, | |
| "learning_rate": 3.3600000000000004e-06, | |
| "loss": 0.742, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 26.55, | |
| "learning_rate": 3.3e-06, | |
| "loss": 0.7371, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 26.73, | |
| "learning_rate": 3.2400000000000003e-06, | |
| "loss": 0.7355, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 26.91, | |
| "learning_rate": 3.18e-06, | |
| "loss": 0.7352, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 27.09, | |
| "learning_rate": 3.12e-06, | |
| "loss": 0.7263, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 27.27, | |
| "learning_rate": 3.06e-06, | |
| "loss": 0.7113, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 27.27, | |
| "eval_loss": 1.1966105699539185, | |
| "eval_runtime": 1.4607, | |
| "eval_samples_per_second": 45.185, | |
| "eval_steps_per_second": 2.054, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 27.45, | |
| "learning_rate": 3e-06, | |
| "loss": 0.7142, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 27.64, | |
| "learning_rate": 2.9400000000000002e-06, | |
| "loss": 0.7189, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 27.82, | |
| "learning_rate": 2.88e-06, | |
| "loss": 0.7131, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 2.82e-06, | |
| "loss": 0.7054, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 28.18, | |
| "learning_rate": 2.7600000000000003e-06, | |
| "loss": 0.6965, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 28.36, | |
| "learning_rate": 2.7e-06, | |
| "loss": 0.6879, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 28.55, | |
| "learning_rate": 2.64e-06, | |
| "loss": 0.6872, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 28.73, | |
| "learning_rate": 2.58e-06, | |
| "loss": 0.6909, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 28.91, | |
| "learning_rate": 2.52e-06, | |
| "loss": 0.6734, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 29.09, | |
| "learning_rate": 2.4599999999999997e-06, | |
| "loss": 0.6646, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 29.09, | |
| "eval_loss": 1.2236099243164062, | |
| "eval_runtime": 1.4503, | |
| "eval_samples_per_second": 45.508, | |
| "eval_steps_per_second": 2.069, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 29.27, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 0.6715, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 29.45, | |
| "learning_rate": 2.34e-06, | |
| "loss": 0.6621, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 29.64, | |
| "learning_rate": 2.28e-06, | |
| "loss": 0.6483, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 29.82, | |
| "learning_rate": 2.22e-06, | |
| "loss": 0.6487, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 2.16e-06, | |
| "loss": 0.6553, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 30.18, | |
| "learning_rate": 2.1e-06, | |
| "loss": 0.6344, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 30.36, | |
| "learning_rate": 2.0400000000000004e-06, | |
| "loss": 0.6334, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 30.55, | |
| "learning_rate": 1.98e-06, | |
| "loss": 0.6311, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 30.73, | |
| "learning_rate": 1.9200000000000003e-06, | |
| "loss": 0.6262, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 30.91, | |
| "learning_rate": 1.86e-06, | |
| "loss": 0.6303, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 30.91, | |
| "eval_loss": 1.2599583864212036, | |
| "eval_runtime": 1.4611, | |
| "eval_samples_per_second": 45.171, | |
| "eval_steps_per_second": 2.053, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 31.09, | |
| "learning_rate": 1.8e-06, | |
| "loss": 0.6196, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 31.27, | |
| "learning_rate": 1.7399999999999999e-06, | |
| "loss": 0.5957, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 31.45, | |
| "learning_rate": 1.6800000000000002e-06, | |
| "loss": 0.5994, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 31.64, | |
| "learning_rate": 1.6200000000000002e-06, | |
| "loss": 0.6109, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 31.82, | |
| "learning_rate": 1.56e-06, | |
| "loss": 0.61, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.5957, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 32.18, | |
| "learning_rate": 1.44e-06, | |
| "loss": 0.5862, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 32.36, | |
| "learning_rate": 1.3800000000000001e-06, | |
| "loss": 0.5799, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 32.55, | |
| "learning_rate": 1.32e-06, | |
| "loss": 0.5788, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 32.73, | |
| "learning_rate": 1.26e-06, | |
| "loss": 0.5741, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 32.73, | |
| "eval_loss": 1.3407286405563354, | |
| "eval_runtime": 1.4616, | |
| "eval_samples_per_second": 45.157, | |
| "eval_steps_per_second": 2.053, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 32.91, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 0.5745, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 33.09, | |
| "learning_rate": 1.14e-06, | |
| "loss": 0.5654, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 33.27, | |
| "learning_rate": 1.08e-06, | |
| "loss": 0.5587, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 33.45, | |
| "learning_rate": 1.0200000000000002e-06, | |
| "loss": 0.5539, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 33.64, | |
| "learning_rate": 9.600000000000001e-07, | |
| "loss": 0.558, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 33.82, | |
| "learning_rate": 9e-07, | |
| "loss": 0.5571, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "learning_rate": 8.400000000000001e-07, | |
| "loss": 0.5496, | |
| "step": 187 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_train_epochs": 40, | |
| "save_steps": 500, | |
| "total_flos": 6.274288047202763e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |