| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9416846652267816, | |
| "eval_steps": 4, | |
| "global_step": 345, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.3477, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 0.4987175166606903, | |
| "eval_runtime": 3.1166, | |
| "eval_samples_per_second": 6.417, | |
| "eval_steps_per_second": 3.209, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.3285, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6e-06, | |
| "loss": 0.3754, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.3143, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 0.4986831247806549, | |
| "eval_runtime": 3.101, | |
| "eval_samples_per_second": 6.45, | |
| "eval_steps_per_second": 3.225, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4661, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.3726, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 0.3515, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.2981, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 0.4983077645301819, | |
| "eval_runtime": 3.1103, | |
| "eval_samples_per_second": 6.43, | |
| "eval_steps_per_second": 3.215, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.5434, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3998, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 0.31, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.4314, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 0.497723788022995, | |
| "eval_runtime": 3.1104, | |
| "eval_samples_per_second": 6.43, | |
| "eval_steps_per_second": 3.215, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 0.3478, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 0.3663, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 3e-05, | |
| "loss": 0.3981, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.3959, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 0.49577316641807556, | |
| "eval_runtime": 3.1093, | |
| "eval_samples_per_second": 6.432, | |
| "eval_steps_per_second": 3.216, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 3.4000000000000007e-05, | |
| "loss": 0.4256, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.3393, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.4055, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4e-05, | |
| "loss": 0.3353, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 0.4915711581707001, | |
| "eval_runtime": 3.1139, | |
| "eval_samples_per_second": 6.423, | |
| "eval_steps_per_second": 3.211, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.3431, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.354, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.3472, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.4287, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 0.4811338782310486, | |
| "eval_runtime": 3.1059, | |
| "eval_samples_per_second": 6.439, | |
| "eval_steps_per_second": 3.22, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3663, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 5.2000000000000004e-05, | |
| "loss": 0.298, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 5.4000000000000005e-05, | |
| "loss": 0.3649, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 0.4018, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 0.46300894021987915, | |
| "eval_runtime": 3.1124, | |
| "eval_samples_per_second": 6.426, | |
| "eval_steps_per_second": 3.213, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 5.8e-05, | |
| "loss": 0.3116, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 6e-05, | |
| "loss": 0.3147, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 6.2e-05, | |
| "loss": 0.2776, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 0.3278, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 0.4446893334388733, | |
| "eval_runtime": 3.1075, | |
| "eval_samples_per_second": 6.436, | |
| "eval_steps_per_second": 3.218, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 6.6e-05, | |
| "loss": 0.2848, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 6.800000000000001e-05, | |
| "loss": 0.2776, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7e-05, | |
| "loss": 0.3078, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.2e-05, | |
| "loss": 0.2566, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 0.4287605881690979, | |
| "eval_runtime": 3.1063, | |
| "eval_samples_per_second": 6.438, | |
| "eval_steps_per_second": 3.219, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 7.4e-05, | |
| "loss": 0.2715, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 7.6e-05, | |
| "loss": 0.3393, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 7.800000000000001e-05, | |
| "loss": 0.2669, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8e-05, | |
| "loss": 0.3797, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 0.4169308543205261, | |
| "eval_runtime": 3.1074, | |
| "eval_samples_per_second": 6.436, | |
| "eval_steps_per_second": 3.218, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.2e-05, | |
| "loss": 0.2702, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 8.4e-05, | |
| "loss": 0.3824, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 8.6e-05, | |
| "loss": 0.274, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 0.2966, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 0.41074520349502563, | |
| "eval_runtime": 3.1076, | |
| "eval_samples_per_second": 6.436, | |
| "eval_steps_per_second": 3.218, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9e-05, | |
| "loss": 0.485, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.200000000000001e-05, | |
| "loss": 0.2395, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.4e-05, | |
| "loss": 0.3023, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.6e-05, | |
| "loss": 0.2676, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 0.4023456573486328, | |
| "eval_runtime": 3.1109, | |
| "eval_samples_per_second": 6.429, | |
| "eval_steps_per_second": 3.215, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.8e-05, | |
| "loss": 0.2378, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2607, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00010200000000000001, | |
| "loss": 0.4538, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00010400000000000001, | |
| "loss": 0.2456, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 0.3957594335079193, | |
| "eval_runtime": 3.1123, | |
| "eval_samples_per_second": 6.426, | |
| "eval_steps_per_second": 3.213, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00010600000000000002, | |
| "loss": 0.3435, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00010800000000000001, | |
| "loss": 0.3035, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00011000000000000002, | |
| "loss": 0.3564, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00011200000000000001, | |
| "loss": 0.3267, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 0.39143189787864685, | |
| "eval_runtime": 3.1134, | |
| "eval_samples_per_second": 6.424, | |
| "eval_steps_per_second": 3.212, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00011399999999999999, | |
| "loss": 0.2641, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.000116, | |
| "loss": 0.2805, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.000118, | |
| "loss": 0.2784, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00012, | |
| "loss": 0.2901, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 0.38809266686439514, | |
| "eval_runtime": 3.1079, | |
| "eval_samples_per_second": 6.435, | |
| "eval_steps_per_second": 3.218, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.000122, | |
| "loss": 0.3039, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.000124, | |
| "loss": 0.2035, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.000126, | |
| "loss": 0.326, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00012800000000000002, | |
| "loss": 0.1843, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 0.3881237506866455, | |
| "eval_runtime": 3.1107, | |
| "eval_samples_per_second": 6.429, | |
| "eval_steps_per_second": 3.215, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00013000000000000002, | |
| "loss": 0.296, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.000132, | |
| "loss": 0.2766, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.000134, | |
| "loss": 0.304, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00013600000000000003, | |
| "loss": 0.2585, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 0.3869483470916748, | |
| "eval_runtime": 3.1091, | |
| "eval_samples_per_second": 6.433, | |
| "eval_steps_per_second": 3.216, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.000138, | |
| "loss": 0.2639, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00014, | |
| "loss": 0.3013, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.000142, | |
| "loss": 0.4263, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.000144, | |
| "loss": 0.3108, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 0.3839200437068939, | |
| "eval_runtime": 3.1098, | |
| "eval_samples_per_second": 6.431, | |
| "eval_steps_per_second": 3.216, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.000146, | |
| "loss": 0.4283, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.000148, | |
| "loss": 0.2582, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.2703, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.000152, | |
| "loss": 0.3799, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 0.3816559314727783, | |
| "eval_runtime": 3.1096, | |
| "eval_samples_per_second": 6.432, | |
| "eval_steps_per_second": 3.216, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.000154, | |
| "loss": 0.252, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00015600000000000002, | |
| "loss": 0.3297, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00015800000000000002, | |
| "loss": 0.2607, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00016, | |
| "loss": 0.2064, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 0.37915611267089844, | |
| "eval_runtime": 3.1123, | |
| "eval_samples_per_second": 6.426, | |
| "eval_steps_per_second": 3.213, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.000162, | |
| "loss": 0.3341, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.000164, | |
| "loss": 0.3159, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.000166, | |
| "loss": 0.2457, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.000168, | |
| "loss": 0.3176, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 0.3792770504951477, | |
| "eval_runtime": 3.13, | |
| "eval_samples_per_second": 6.39, | |
| "eval_steps_per_second": 3.195, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00017, | |
| "loss": 0.3043, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.000172, | |
| "loss": 0.2346, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.000174, | |
| "loss": 0.2872, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00017600000000000002, | |
| "loss": 0.2307, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 0.3768787384033203, | |
| "eval_runtime": 3.1088, | |
| "eval_samples_per_second": 6.433, | |
| "eval_steps_per_second": 3.217, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00017800000000000002, | |
| "loss": 0.2661, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00018, | |
| "loss": 0.3068, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.000182, | |
| "loss": 0.2866, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00018400000000000003, | |
| "loss": 0.2826, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 0.3746011555194855, | |
| "eval_runtime": 3.1104, | |
| "eval_samples_per_second": 6.43, | |
| "eval_steps_per_second": 3.215, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00018600000000000002, | |
| "loss": 0.4888, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.000188, | |
| "loss": 0.1667, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00019, | |
| "loss": 0.2683, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.000192, | |
| "loss": 0.2718, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 0.373685747385025, | |
| "eval_runtime": 3.1134, | |
| "eval_samples_per_second": 6.424, | |
| "eval_steps_per_second": 3.212, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.000194, | |
| "loss": 0.2193, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.000196, | |
| "loss": 0.378, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00019800000000000002, | |
| "loss": 0.2917, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2945, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 0.3727183938026428, | |
| "eval_runtime": 3.1085, | |
| "eval_samples_per_second": 6.434, | |
| "eval_steps_per_second": 3.217, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00019999177886783194, | |
| "loss": 0.2355, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.000199967116823068, | |
| "loss": 0.2656, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00019992601792070679, | |
| "loss": 0.2803, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00019986848891833845, | |
| "loss": 0.2313, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 0.371459424495697, | |
| "eval_runtime": 3.1114, | |
| "eval_samples_per_second": 6.428, | |
| "eval_steps_per_second": 3.214, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00019979453927503364, | |
| "loss": 0.2983, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0001997041811497882, | |
| "loss": 0.2547, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00019959742939952392, | |
| "loss": 0.2463, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00019947430157664576, | |
| "loss": 0.2519, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 0.37180376052856445, | |
| "eval_runtime": 3.1113, | |
| "eval_samples_per_second": 6.428, | |
| "eval_steps_per_second": 3.214, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00019933481792615583, | |
| "loss": 0.2032, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0001991790013823246, | |
| "loss": 0.2868, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0001990068775649202, | |
| "loss": 0.2653, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00019881847477499557, | |
| "loss": 0.2468, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 0.37166160345077515, | |
| "eval_runtime": 3.1194, | |
| "eval_samples_per_second": 6.412, | |
| "eval_steps_per_second": 3.206, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0001986138239902355, | |
| "loss": 0.3997, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00019839295885986296, | |
| "loss": 0.172, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00019815591569910654, | |
| "loss": 0.2713, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0001979027334832293, | |
| "loss": 0.2034, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.37163203954696655, | |
| "eval_runtime": 3.1126, | |
| "eval_samples_per_second": 6.425, | |
| "eval_steps_per_second": 3.213, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00019763345384112043, | |
| "loss": 0.1824, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00019734812104845047, | |
| "loss": 0.3669, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0001970467820203915, | |
| "loss": 0.229, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00019672948630390294, | |
| "loss": 0.2639, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 0.3714464008808136, | |
| "eval_runtime": 3.1072, | |
| "eval_samples_per_second": 6.437, | |
| "eval_steps_per_second": 3.218, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00019639628606958533, | |
| "loss": 0.1806, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00019604723610310194, | |
| "loss": 0.2209, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00019568239379617088, | |
| "loss": 0.2566, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00019530181913712872, | |
| "loss": 0.2472, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_loss": 0.3729495108127594, | |
| "eval_runtime": 3.1102, | |
| "eval_samples_per_second": 6.43, | |
| "eval_steps_per_second": 3.215, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00019490557470106686, | |
| "loss": 0.2303, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00019449372563954293, | |
| "loss": 0.2203, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00019406633966986828, | |
| "loss": 0.2226, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00019362348706397373, | |
| "loss": 0.1987, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 0.36887192726135254, | |
| "eval_runtime": 3.1178, | |
| "eval_samples_per_second": 6.415, | |
| "eval_steps_per_second": 3.207, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0001931652406368554, | |
| "loss": 0.1859, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0001926916757346022, | |
| "loss": 0.2408, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00019220287022200707, | |
| "loss": 0.2724, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00019169890446976454, | |
| "loss": 0.2296, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 0.3678927719593048, | |
| "eval_runtime": 3.1086, | |
| "eval_samples_per_second": 6.434, | |
| "eval_steps_per_second": 3.217, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0001911798613412557, | |
| "loss": 0.2069, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0001906458261789238, | |
| "loss": 0.2973, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 0.2468, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0001895331334332753, | |
| "loss": 0.1542, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 0.3685668408870697, | |
| "eval_runtime": 3.1094, | |
| "eval_samples_per_second": 6.432, | |
| "eval_steps_per_second": 3.216, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0001889546588018412, | |
| "loss": 0.2935, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00018836155801026753, | |
| "loss": 0.2493, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00018775392857775432, | |
| "loss": 0.1597, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00018713187041233896, | |
| "loss": 0.1949, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 0.3697265684604645, | |
| "eval_runtime": 3.1097, | |
| "eval_samples_per_second": 6.431, | |
| "eval_steps_per_second": 3.216, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00018649548579446936, | |
| "loss": 0.2434, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00018584487936018661, | |
| "loss": 0.2348, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00018518015808392045, | |
| "loss": 0.2946, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00018450143126090015, | |
| "loss": 0.2239, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_loss": 0.36812636256217957, | |
| "eval_runtime": 3.1112, | |
| "eval_samples_per_second": 6.428, | |
| "eval_steps_per_second": 3.214, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00018380881048918405, | |
| "loss": 0.1824, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00018310240965131041, | |
| "loss": 0.302, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00018238234489557215, | |
| "loss": 0.3452, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00018164873461691986, | |
| "loss": 0.1943, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 0.3690447211265564, | |
| "eval_runtime": 3.111, | |
| "eval_samples_per_second": 6.429, | |
| "eval_steps_per_second": 3.214, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.2775, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00018014136218679567, | |
| "loss": 0.3347, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00017936784788148328, | |
| "loss": 0.337, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00017858128370482426, | |
| "loss": 0.1487, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 0.3705955445766449, | |
| "eval_runtime": 3.1102, | |
| "eval_samples_per_second": 6.431, | |
| "eval_steps_per_second": 3.215, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00017778179898577973, | |
| "loss": 0.2416, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00017696952517774062, | |
| "loss": 0.2265, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00017614459583691346, | |
| "loss": 0.2106, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00017530714660036112, | |
| "loss": 0.2873, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 0.37079566717147827, | |
| "eval_runtime": 3.1213, | |
| "eval_samples_per_second": 6.408, | |
| "eval_steps_per_second": 3.204, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0001744573151637007, | |
| "loss": 0.2134, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.0001735952412584635, | |
| "loss": 0.3883, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00017272106662911973, | |
| "loss": 0.2018, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00017183493500977278, | |
| "loss": 0.2786, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 0.3699425756931305, | |
| "eval_runtime": 3.1068, | |
| "eval_samples_per_second": 6.438, | |
| "eval_steps_per_second": 3.219, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.0001709369921005258, | |
| "loss": 0.2128, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00017002738554352552, | |
| "loss": 0.2264, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.00016910626489868649, | |
| "loss": 0.3394, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00016817378161909996, | |
| "loss": 0.2486, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 0.3689553737640381, | |
| "eval_runtime": 3.111, | |
| "eval_samples_per_second": 6.429, | |
| "eval_steps_per_second": 3.214, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.0001672300890261317, | |
| "loss": 0.1954, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.0001662753422842123, | |
| "loss": 0.1786, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00016530969837532487, | |
| "loss": 0.2595, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.00016433331607319343, | |
| "loss": 0.2048, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 0.3692178726196289, | |
| "eval_runtime": 3.1102, | |
| "eval_samples_per_second": 6.43, | |
| "eval_steps_per_second": 3.215, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00016334635591717703, | |
| "loss": 0.1574, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00016234898018587337, | |
| "loss": 0.2797, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00016134135287043669, | |
| "loss": 0.2279, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00016032363964761363, | |
| "loss": 0.1669, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 0.3703743815422058, | |
| "eval_runtime": 3.1096, | |
| "eval_samples_per_second": 6.432, | |
| "eval_steps_per_second": 3.216, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.00015929600785250257, | |
| "loss": 0.188, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0001582586264510396, | |
| "loss": 0.2964, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00015721166601221698, | |
| "loss": 0.2548, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0001561552986800375, | |
| "loss": 0.2339, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 0.369620144367218, | |
| "eval_runtime": 3.1104, | |
| "eval_samples_per_second": 6.43, | |
| "eval_steps_per_second": 3.215, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.00015508969814521025, | |
| "loss": 0.3109, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.00015401503961659204, | |
| "loss": 0.2787, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.00015293149979237876, | |
| "loss": 0.2867, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00015183925683105254, | |
| "loss": 0.2676, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 0.3678538203239441, | |
| "eval_runtime": 3.1087, | |
| "eval_samples_per_second": 6.434, | |
| "eval_steps_per_second": 3.217, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00015073849032208822, | |
| "loss": 0.2537, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.00014962938125642503, | |
| "loss": 0.23, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00014851211199670721, | |
| "loss": 0.1883, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.00014738686624729986, | |
| "loss": 0.2565, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_loss": 0.36626869440078735, | |
| "eval_runtime": 3.109, | |
| "eval_samples_per_second": 6.433, | |
| "eval_steps_per_second": 3.216, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00014625382902408356, | |
| "loss": 0.3444, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.00014511318662403347, | |
| "loss": 0.3072, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00014396512659458824, | |
| "loss": 0.2074, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0001428098377028126, | |
| "loss": 0.1769, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 0.367279052734375, | |
| "eval_runtime": 3.11, | |
| "eval_samples_per_second": 6.431, | |
| "eval_steps_per_second": 3.215, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0001416475099043599, | |
| "loss": 0.2805, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.00014047833431223938, | |
| "loss": 0.2003, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00013930250316539238, | |
| "loss": 0.2478, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.00013812020979708418, | |
| "loss": 0.2435, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 0.3666362464427948, | |
| "eval_runtime": 3.1113, | |
| "eval_samples_per_second": 6.428, | |
| "eval_steps_per_second": 3.214, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00013693164860311565, | |
| "loss": 0.2149, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.0001357370150098601, | |
| "loss": 0.1893, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00013453650544213076, | |
| "loss": 0.2509, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00013333031729088419, | |
| "loss": 0.2145, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_loss": 0.36739152669906616, | |
| "eval_runtime": 3.1249, | |
| "eval_samples_per_second": 6.4, | |
| "eval_steps_per_second": 3.2, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00013211864888076457, | |
| "loss": 0.1946, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.2008, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00012967966905511906, | |
| "loss": 0.3234, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00012845275866310324, | |
| "loss": 0.2082, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_loss": 0.36528101563453674, | |
| "eval_runtime": 3.1155, | |
| "eval_samples_per_second": 6.42, | |
| "eval_steps_per_second": 3.21, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00012722116999329712, | |
| "loss": 0.2492, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0001259851055467653, | |
| "loss": 0.1468, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.00012474476856049144, | |
| "loss": 0.4099, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.00012350036297396154, | |
| "loss": 0.2416, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_loss": 0.3635335862636566, | |
| "eval_runtime": 3.1079, | |
| "eval_samples_per_second": 6.435, | |
| "eval_steps_per_second": 3.218, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.00012225209339563145, | |
| "loss": 0.2295, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00012100016506928493, | |
| "loss": 0.2825, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00011974478384028672, | |
| "loss": 0.303, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00011848615612173688, | |
| "loss": 0.1884, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_loss": 0.36344197392463684, | |
| "eval_runtime": 3.1145, | |
| "eval_samples_per_second": 6.422, | |
| "eval_steps_per_second": 3.211, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.0001172244888605319, | |
| "loss": 0.2423, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00011595998950333793, | |
| "loss": 0.2338, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.00011469286596248181, | |
| "loss": 0.246, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00011342332658176555, | |
| "loss": 0.275, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_loss": 0.3634224236011505, | |
| "eval_runtime": 3.1116, | |
| "eval_samples_per_second": 6.428, | |
| "eval_steps_per_second": 3.214, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.00011215158010221005, | |
| "loss": 0.3584, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00011087783562773311, | |
| "loss": 0.2247, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00010960230259076818, | |
| "loss": 0.2911, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.00010832519071782894, | |
| "loss": 0.2518, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_loss": 0.3610054850578308, | |
| "eval_runtime": 3.1068, | |
| "eval_samples_per_second": 6.437, | |
| "eval_steps_per_second": 3.219, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.0001070467099950254, | |
| "loss": 0.2468, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00010576707063353746, | |
| "loss": 0.1837, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.00010448648303505151, | |
| "loss": 0.355, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00010320515775716555, | |
| "loss": 0.2462, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_loss": 0.36076828837394714, | |
| "eval_runtime": 3.112, | |
| "eval_samples_per_second": 6.427, | |
| "eval_steps_per_second": 3.213, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00010192330547876871, | |
| "loss": 0.289, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00010064113696540111, | |
| "loss": 0.2711, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 9.93588630345989e-05, | |
| "loss": 0.1961, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 9.80766945212313e-05, | |
| "loss": 0.2509, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 0.36051902174949646, | |
| "eval_runtime": 3.1093, | |
| "eval_samples_per_second": 6.432, | |
| "eval_steps_per_second": 3.216, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 9.679484224283449e-05, | |
| "loss": 0.228, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 9.551351696494854e-05, | |
| "loss": 0.2148, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 9.423292936646257e-05, | |
| "loss": 0.2076, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 9.29532900049746e-05, | |
| "loss": 0.2749, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_loss": 0.3603048324584961, | |
| "eval_runtime": 3.1096, | |
| "eval_samples_per_second": 6.432, | |
| "eval_steps_per_second": 3.216, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 9.167480928217108e-05, | |
| "loss": 0.21, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 9.039769740923183e-05, | |
| "loss": 0.2771, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 8.912216437226693e-05, | |
| "loss": 0.3317, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 8.784841989778996e-05, | |
| "loss": 0.2162, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_loss": 0.3595748245716095, | |
| "eval_runtime": 3.1118, | |
| "eval_samples_per_second": 6.427, | |
| "eval_steps_per_second": 3.214, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 8.657667341823448e-05, | |
| "loss": 0.227, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.530713403751821e-05, | |
| "loss": 0.1645, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 8.404001049666211e-05, | |
| "loss": 0.2724, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 8.277551113946812e-05, | |
| "loss": 0.3927, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_loss": 0.3591071665287018, | |
| "eval_runtime": 3.1142, | |
| "eval_samples_per_second": 6.422, | |
| "eval_steps_per_second": 3.211, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 8.151384387826313e-05, | |
| "loss": 0.1859, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 8.02552161597133e-05, | |
| "loss": 0.1292, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 7.899983493071507e-05, | |
| "loss": 0.1601, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 7.774790660436858e-05, | |
| "loss": 0.2169, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 0.36295366287231445, | |
| "eval_runtime": 3.1096, | |
| "eval_samples_per_second": 6.432, | |
| "eval_steps_per_second": 3.216, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 7.649963702603849e-05, | |
| "loss": 0.1255, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 7.525523143950859e-05, | |
| "loss": 0.1482, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 7.401489445323473e-05, | |
| "loss": 0.1793, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 7.27788300067029e-05, | |
| "loss": 0.1822, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_loss": 0.3715473711490631, | |
| "eval_runtime": 3.1084, | |
| "eval_samples_per_second": 6.434, | |
| "eval_steps_per_second": 3.217, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 7.154724133689677e-05, | |
| "loss": 0.205, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 7.032033094488095e-05, | |
| "loss": 0.1724, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.167, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 6.788135111923545e-05, | |
| "loss": 0.2968, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_loss": 0.379179447889328, | |
| "eval_runtime": 3.1105, | |
| "eval_samples_per_second": 6.43, | |
| "eval_steps_per_second": 3.215, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 6.666968270911584e-05, | |
| "loss": 0.1403, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 6.546349455786926e-05, | |
| "loss": 0.1491, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 6.426298499013994e-05, | |
| "loss": 0.2384, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 6.306835139688438e-05, | |
| "loss": 0.2022, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_loss": 0.3767882287502289, | |
| "eval_runtime": 3.1079, | |
| "eval_samples_per_second": 6.435, | |
| "eval_steps_per_second": 3.218, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 6.187979020291583e-05, | |
| "loss": 0.1408, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 6.069749683460765e-05, | |
| "loss": 0.1376, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 5.952166568776062e-05, | |
| "loss": 0.175, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 5.835249009564012e-05, | |
| "loss": 0.1384, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_loss": 0.37171897292137146, | |
| "eval_runtime": 3.1106, | |
| "eval_samples_per_second": 6.43, | |
| "eval_steps_per_second": 3.215, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 5.7190162297187475e-05, | |
| "loss": 0.1422, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 5.60348734054118e-05, | |
| "loss": 0.1683, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 5.488681337596653e-05, | |
| "loss": 0.2688, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 5.37461709759165e-05, | |
| "loss": 0.2045, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_loss": 0.37158870697021484, | |
| "eval_runtime": 3.1106, | |
| "eval_samples_per_second": 6.43, | |
| "eval_steps_per_second": 3.215, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 5.261313375270014e-05, | |
| "loss": 0.2776, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 5.148788800329278e-05, | |
| "loss": 0.131, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 5.0370618743575026e-05, | |
| "loss": 0.2729, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 4.92615096779118e-05, | |
| "loss": 0.2492, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_loss": 0.37324967980384827, | |
| "eval_runtime": 3.1091, | |
| "eval_samples_per_second": 6.433, | |
| "eval_steps_per_second": 3.216, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 4.8160743168947496e-05, | |
| "loss": 0.1436, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 4.706850020762126e-05, | |
| "loss": 0.1558, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 4.5984960383408005e-05, | |
| "loss": 0.1629, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 4.491030185478976e-05, | |
| "loss": 0.1719, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_loss": 0.37554189562797546, | |
| "eval_runtime": 3.1081, | |
| "eval_samples_per_second": 6.435, | |
| "eval_steps_per_second": 3.217, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 4.384470131996252e-05, | |
| "loss": 0.2066, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 4.278833398778306e-05, | |
| "loss": 0.1934, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 4.174137354896039e-05, | |
| "loss": 0.146, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 4.0703992147497425e-05, | |
| "loss": 0.1684, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_loss": 0.37683507800102234, | |
| "eval_runtime": 3.1132, | |
| "eval_samples_per_second": 6.424, | |
| "eval_steps_per_second": 3.212, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 3.9676360352386356e-05, | |
| "loss": 0.1512, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 3.8658647129563364e-05, | |
| "loss": 0.2222, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 3.7651019814126654e-05, | |
| "loss": 0.1904, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 3.665364408282305e-05, | |
| "loss": 0.1927, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "eval_loss": 0.37731653451919556, | |
| "eval_runtime": 3.1196, | |
| "eval_samples_per_second": 6.411, | |
| "eval_steps_per_second": 3.206, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 3.566668392680662e-05, | |
| "loss": 0.1277, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 3.469030162467513e-05, | |
| "loss": 0.1867, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 3.372465771578771e-05, | |
| "loss": 0.2013, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 3.276991097386831e-05, | |
| "loss": 0.218, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "eval_loss": 0.3782224655151367, | |
| "eval_runtime": 3.11, | |
| "eval_samples_per_second": 6.431, | |
| "eval_steps_per_second": 3.215, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 3.1826218380900064e-05, | |
| "loss": 0.2087, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 3.089373510131354e-05, | |
| "loss": 0.2147, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 2.9972614456474536e-05, | |
| "loss": 0.1804, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 2.9063007899474216e-05, | |
| "loss": 0.1984, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_loss": 0.3790702223777771, | |
| "eval_runtime": 3.1101, | |
| "eval_samples_per_second": 6.431, | |
| "eval_steps_per_second": 3.215, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 2.8165064990227252e-05, | |
| "loss": 0.2094, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 2.7278933370880265e-05, | |
| "loss": 0.2664, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 2.6404758741536505e-05, | |
| "loss": 0.2505, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 2.5542684836299313e-05, | |
| "loss": 0.1435, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "eval_loss": 0.37862634658813477, | |
| "eval_runtime": 3.11, | |
| "eval_samples_per_second": 6.431, | |
| "eval_steps_per_second": 3.215, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 2.4692853399638917e-05, | |
| "loss": 0.2423, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 2.3855404163086558e-05, | |
| "loss": 0.2061, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 2.3030474822259397e-05, | |
| "loss": 0.1276, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 2.2218201014220263e-05, | |
| "loss": 0.1672, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "eval_loss": 0.378492146730423, | |
| "eval_runtime": 3.1099, | |
| "eval_samples_per_second": 6.431, | |
| "eval_steps_per_second": 3.215, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 2.141871629517577e-05, | |
| "loss": 0.1699, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 2.063215211851678e-05, | |
| "loss": 0.1806, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 1.985863781320435e-05, | |
| "loss": 0.138, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.1819, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "eval_loss": 0.37836065888404846, | |
| "eval_runtime": 3.1101, | |
| "eval_samples_per_second": 6.431, | |
| "eval_steps_per_second": 3.215, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 1.835126538308013e-05, | |
| "loss": 0.1794, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 1.7617655104427832e-05, | |
| "loss": 0.18, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 1.689759034868961e-05, | |
| "loss": 0.241, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 1.619118951081594e-05, | |
| "loss": 0.1647, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_loss": 0.37813514471054077, | |
| "eval_runtime": 3.1084, | |
| "eval_samples_per_second": 6.434, | |
| "eval_steps_per_second": 3.217, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 1.5498568739099906e-05, | |
| "loss": 0.2419, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 1.481984191607959e-05, | |
| "loss": 0.1949, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 1.415512063981339e-05, | |
| "loss": 0.144, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 1.350451420553065e-05, | |
| "loss": 0.1531, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_loss": 0.3778517246246338, | |
| "eval_runtime": 3.1114, | |
| "eval_samples_per_second": 6.428, | |
| "eval_steps_per_second": 3.214, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 1.286812958766106e-05, | |
| "loss": 0.2153, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 1.224607142224572e-05, | |
| "loss": 0.1835, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 1.1638441989732473e-05, | |
| "loss": 0.2181, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 1.1045341198158831e-05, | |
| "loss": 0.2988, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "eval_loss": 0.37788671255111694, | |
| "eval_runtime": 3.1084, | |
| "eval_samples_per_second": 6.434, | |
| "eval_steps_per_second": 3.217, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 1.0466866566724698e-05, | |
| "loss": 0.214, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 9.903113209758096e-06, | |
| "loss": 0.1431, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 9.354173821076184e-06, | |
| "loss": 0.2165, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 8.820138658744304e-06, | |
| "loss": 0.153, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "eval_loss": 0.37841156125068665, | |
| "eval_runtime": 3.1062, | |
| "eval_samples_per_second": 6.439, | |
| "eval_steps_per_second": 3.219, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 8.301095530235492e-06, | |
| "loss": 0.1963, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 7.797129777992952e-06, | |
| "loss": 0.1444, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 7.308324265397836e-06, | |
| "loss": 0.2277, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 6.834759363144594e-06, | |
| "loss": 0.1877, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "eval_loss": 0.3786165714263916, | |
| "eval_runtime": 3.1085, | |
| "eval_samples_per_second": 6.434, | |
| "eval_steps_per_second": 3.217, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 6.37651293602628e-06, | |
| "loss": 0.2029, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 5.933660330131752e-06, | |
| "loss": 0.2068, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 5.506274360457086e-06, | |
| "loss": 0.2556, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 5.094425298933136e-06, | |
| "loss": 0.1873, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "eval_loss": 0.378797322511673, | |
| "eval_runtime": 3.108, | |
| "eval_samples_per_second": 6.435, | |
| "eval_steps_per_second": 3.217, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 4.698180862871282e-06, | |
| "loss": 0.1367, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.317606203829127e-06, | |
| "loss": 0.1721, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 3.952763896898071e-06, | |
| "loss": 0.1383, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 3.6037139304146762e-06, | |
| "loss": 0.1722, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 0.3789643943309784, | |
| "eval_runtime": 3.1067, | |
| "eval_samples_per_second": 6.438, | |
| "eval_steps_per_second": 3.219, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 3.270513696097055e-06, | |
| "loss": 0.1906, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 2.9532179796085356e-06, | |
| "loss": 0.207, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.651878951549536e-06, | |
| "loss": 0.2667, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.36654615887959e-06, | |
| "loss": 0.2007, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_loss": 0.3788919746875763, | |
| "eval_runtime": 3.1077, | |
| "eval_samples_per_second": 6.436, | |
| "eval_steps_per_second": 3.218, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 2.0972665167707126e-06, | |
| "loss": 0.2, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.8440843008934561e-06, | |
| "loss": 0.169, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1.6070411401370334e-06, | |
| "loss": 0.1048, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.386176009764506e-06, | |
| "loss": 0.266, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "eval_loss": 0.37898656725883484, | |
| "eval_runtime": 3.1077, | |
| "eval_samples_per_second": 6.436, | |
| "eval_steps_per_second": 3.218, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.1815252250044318e-06, | |
| "loss": 0.1435, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 9.931224350798185e-07, | |
| "loss": 0.2048, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 8.209986176753948e-07, | |
| "loss": 0.1466, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 6.651820738441949e-07, | |
| "loss": 0.2055, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_loss": 0.3791235387325287, | |
| "eval_runtime": 3.1193, | |
| "eval_samples_per_second": 6.412, | |
| "eval_steps_per_second": 3.206, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 5.256984233542595e-07, | |
| "loss": 0.1953, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 4.025706004760932e-07, | |
| "loss": 0.1906, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 2.9581885021181533e-07, | |
| "loss": 0.2208, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 2.054607249663665e-07, | |
| "loss": 0.2702, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_loss": 0.3788047134876251, | |
| "eval_runtime": 3.1079, | |
| "eval_samples_per_second": 6.435, | |
| "eval_steps_per_second": 3.218, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 1.3151108166156168e-07, | |
| "loss": 0.2008, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 7.39820792932333e-08, | |
| "loss": 0.1559, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 3.288317693201926e-08, | |
| "loss": 0.2126, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 8.221132168073631e-09, | |
| "loss": 0.1416, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_loss": 0.3789215087890625, | |
| "eval_runtime": 3.1064, | |
| "eval_samples_per_second": 6.438, | |
| "eval_steps_per_second": 3.219, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.0, | |
| "loss": 0.1994, | |
| "step": 345 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 345, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 1.757605931903877e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |