| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.079365079365079, | |
| "eval_steps": 10.0, | |
| "global_step": 80, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06349206349206349, | |
| "grad_norm": 2.6884286403656006, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.6802, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.12698412698412698, | |
| "grad_norm": 2.6933367252349854, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.6777, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 2.5917274951934814, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.661, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.25396825396825395, | |
| "grad_norm": 2.6264889240264893, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.6622, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.31746031746031744, | |
| "grad_norm": 2.366546630859375, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.6453, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 1.9140746593475342, | |
| "learning_rate": 3e-06, | |
| "loss": 0.6394, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 1.7500569820404053, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.6208, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5079365079365079, | |
| "grad_norm": 1.7186416387557983, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.5705, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 1.8733755350112915, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.5859, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.6349206349206349, | |
| "grad_norm": 2.6948869228363037, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5696, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6984126984126984, | |
| "grad_norm": 2.541510820388794, | |
| "learning_rate": 4.99847706754774e-06, | |
| "loss": 0.5778, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 1.8197821378707886, | |
| "learning_rate": 4.993910125649561e-06, | |
| "loss": 0.5576, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8253968253968254, | |
| "grad_norm": 1.3835104703903198, | |
| "learning_rate": 4.986304738420684e-06, | |
| "loss": 0.5198, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 1.6187756061553955, | |
| "learning_rate": 4.975670171853926e-06, | |
| "loss": 0.5107, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 1.2050142288208008, | |
| "learning_rate": 4.962019382530521e-06, | |
| "loss": 0.4788, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0158730158730158, | |
| "grad_norm": 0.8275009393692017, | |
| "learning_rate": 4.9453690018345144e-06, | |
| "loss": 0.4735, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0793650793650793, | |
| "grad_norm": 0.7280167937278748, | |
| "learning_rate": 4.925739315689991e-06, | |
| "loss": 0.4579, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 0.741590678691864, | |
| "learning_rate": 4.903154239845798e-06, | |
| "loss": 0.4433, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.2063492063492063, | |
| "grad_norm": 0.7426633238792419, | |
| "learning_rate": 4.8776412907378845e-06, | |
| "loss": 0.439, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.2698412698412698, | |
| "grad_norm": 0.6695029735565186, | |
| "learning_rate": 4.849231551964771e-06, | |
| "loss": 0.4305, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.6360190510749817, | |
| "learning_rate": 4.817959636416969e-06, | |
| "loss": 0.4392, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.3968253968253967, | |
| "grad_norm": 0.5890939831733704, | |
| "learning_rate": 4.783863644106502e-06, | |
| "loss": 0.4257, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.4603174603174602, | |
| "grad_norm": 0.5338059663772583, | |
| "learning_rate": 4.746985115747918e-06, | |
| "loss": 0.4061, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.5238095238095237, | |
| "grad_norm": 0.531510591506958, | |
| "learning_rate": 4.707368982147318e-06, | |
| "loss": 0.4151, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5873015873015874, | |
| "grad_norm": 0.5541301369667053, | |
| "learning_rate": 4.665063509461098e-06, | |
| "loss": 0.4113, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.6507936507936507, | |
| "grad_norm": 0.5271514058113098, | |
| "learning_rate": 4.620120240391065e-06, | |
| "loss": 0.404, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 0.4665882885456085, | |
| "learning_rate": 4.572593931387604e-06, | |
| "loss": 0.4029, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.483142226934433, | |
| "learning_rate": 4.522542485937369e-06, | |
| "loss": 0.3984, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.8412698412698414, | |
| "grad_norm": 0.4771871566772461, | |
| "learning_rate": 4.470026884016805e-06, | |
| "loss": 0.3975, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 0.4467179775238037, | |
| "learning_rate": 4.415111107797445e-06, | |
| "loss": 0.3774, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.9682539682539684, | |
| "grad_norm": 0.44207000732421875, | |
| "learning_rate": 4.357862063693486e-06, | |
| "loss": 0.3938, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.0317460317460316, | |
| "grad_norm": 0.42705363035202026, | |
| "learning_rate": 4.2983495008466285e-06, | |
| "loss": 0.3566, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0952380952380953, | |
| "grad_norm": 0.4670058488845825, | |
| "learning_rate": 4.236645926147493e-06, | |
| "loss": 0.3548, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.1587301587301586, | |
| "grad_norm": 0.46382439136505127, | |
| "learning_rate": 4.172826515897146e-06, | |
| "loss": 0.3704, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 0.4274114668369293, | |
| "learning_rate": 4.106969024216348e-06, | |
| "loss": 0.337, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 0.425061970949173, | |
| "learning_rate": 4.039153688314146e-06, | |
| "loss": 0.3357, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.3492063492063493, | |
| "grad_norm": 0.5009689331054688, | |
| "learning_rate": 3.969463130731183e-06, | |
| "loss": 0.3412, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.4126984126984126, | |
| "grad_norm": 0.4565686583518982, | |
| "learning_rate": 3.897982258676867e-06, | |
| "loss": 0.339, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.4761904761904763, | |
| "grad_norm": 0.4084237515926361, | |
| "learning_rate": 3.824798160583012e-06, | |
| "loss": 0.3267, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.5396825396825395, | |
| "grad_norm": 0.41756659746170044, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 0.3273, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.6031746031746033, | |
| "grad_norm": 0.4654518961906433, | |
| "learning_rate": 3.6736789069647273e-06, | |
| "loss": 0.3357, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.4124338626861572, | |
| "learning_rate": 3.595927866972694e-06, | |
| "loss": 0.3152, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.7301587301587302, | |
| "grad_norm": 0.3937598466873169, | |
| "learning_rate": 3.516841607689501e-06, | |
| "loss": 0.322, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.7936507936507935, | |
| "grad_norm": 0.40822404623031616, | |
| "learning_rate": 3.436516483539781e-06, | |
| "loss": 0.312, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 0.4208524823188782, | |
| "learning_rate": 3.3550503583141726e-06, | |
| "loss": 0.3178, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.9206349206349205, | |
| "grad_norm": 0.4314095377922058, | |
| "learning_rate": 3.272542485937369e-06, | |
| "loss": 0.3177, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.984126984126984, | |
| "grad_norm": 0.4072750508785248, | |
| "learning_rate": 3.189093389542498e-06, | |
| "loss": 0.3083, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 3.0476190476190474, | |
| "grad_norm": 0.4380381405353546, | |
| "learning_rate": 3.1048047389991693e-06, | |
| "loss": 0.3011, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 3.111111111111111, | |
| "grad_norm": 0.522165834903717, | |
| "learning_rate": 3.019779227044398e-06, | |
| "loss": 0.2746, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 3.1746031746031744, | |
| "grad_norm": 0.4826960861682892, | |
| "learning_rate": 2.9341204441673267e-06, | |
| "loss": 0.2858, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.238095238095238, | |
| "grad_norm": 0.43253302574157715, | |
| "learning_rate": 2.847932752400164e-06, | |
| "loss": 0.2823, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.3015873015873014, | |
| "grad_norm": 0.47018662095069885, | |
| "learning_rate": 2.761321158169134e-06, | |
| "loss": 0.2721, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.365079365079365, | |
| "grad_norm": 0.497387170791626, | |
| "learning_rate": 2.6743911843603134e-06, | |
| "loss": 0.2795, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 3.4285714285714284, | |
| "grad_norm": 0.42762213945388794, | |
| "learning_rate": 2.587248741756253e-06, | |
| "loss": 0.2788, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.492063492063492, | |
| "grad_norm": 0.4315107464790344, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.2763, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.4290776550769806, | |
| "learning_rate": 2.4127512582437486e-06, | |
| "loss": 0.2824, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.619047619047619, | |
| "grad_norm": 0.43770331144332886, | |
| "learning_rate": 2.325608815639687e-06, | |
| "loss": 0.2682, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 3.682539682539683, | |
| "grad_norm": 0.41665223240852356, | |
| "learning_rate": 2.238678841830867e-06, | |
| "loss": 0.2679, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.746031746031746, | |
| "grad_norm": 0.4484512507915497, | |
| "learning_rate": 2.1520672475998374e-06, | |
| "loss": 0.2756, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 3.8095238095238093, | |
| "grad_norm": 0.4341048300266266, | |
| "learning_rate": 2.0658795558326745e-06, | |
| "loss": 0.2728, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.873015873015873, | |
| "grad_norm": 0.4349490702152252, | |
| "learning_rate": 1.9802207729556023e-06, | |
| "loss": 0.272, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 3.9365079365079367, | |
| "grad_norm": 0.41879743337631226, | |
| "learning_rate": 1.895195261000831e-06, | |
| "loss": 0.2613, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.43113768100738525, | |
| "learning_rate": 1.8109066104575023e-06, | |
| "loss": 0.2829, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 4.063492063492063, | |
| "grad_norm": 0.5257534384727478, | |
| "learning_rate": 1.7274575140626318e-06, | |
| "loss": 0.248, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 4.1269841269841265, | |
| "grad_norm": 0.47642043232917786, | |
| "learning_rate": 1.6449496416858285e-06, | |
| "loss": 0.2485, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 4.190476190476191, | |
| "grad_norm": 0.45349231362342834, | |
| "learning_rate": 1.56348351646022e-06, | |
| "loss": 0.2522, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 4.253968253968254, | |
| "grad_norm": 0.4770345389842987, | |
| "learning_rate": 1.4831583923105e-06, | |
| "loss": 0.2518, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 4.317460317460317, | |
| "grad_norm": 0.5023510456085205, | |
| "learning_rate": 1.4040721330273063e-06, | |
| "loss": 0.2411, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.380952380952381, | |
| "grad_norm": 0.49374037981033325, | |
| "learning_rate": 1.3263210930352737e-06, | |
| "loss": 0.2343, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "grad_norm": 0.49705836176872253, | |
| "learning_rate": 1.2500000000000007e-06, | |
| "loss": 0.2387, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.507936507936508, | |
| "grad_norm": 0.4583221673965454, | |
| "learning_rate": 1.1752018394169882e-06, | |
| "loss": 0.2418, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 4.571428571428571, | |
| "grad_norm": 0.44446587562561035, | |
| "learning_rate": 1.1020177413231334e-06, | |
| "loss": 0.2459, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 4.634920634920634, | |
| "grad_norm": 0.4567837417125702, | |
| "learning_rate": 1.0305368692688175e-06, | |
| "loss": 0.2408, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 4.698412698412699, | |
| "grad_norm": 0.4733292758464813, | |
| "learning_rate": 9.608463116858544e-07, | |
| "loss": 0.2431, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 4.761904761904762, | |
| "grad_norm": 0.4715614318847656, | |
| "learning_rate": 8.930309757836517e-07, | |
| "loss": 0.2394, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 4.825396825396825, | |
| "grad_norm": 0.4606616199016571, | |
| "learning_rate": 8.271734841028553e-07, | |
| "loss": 0.2327, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.888888888888889, | |
| "grad_norm": 0.45062100887298584, | |
| "learning_rate": 7.633540738525066e-07, | |
| "loss": 0.2492, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 4.9523809523809526, | |
| "grad_norm": 0.4597299098968506, | |
| "learning_rate": 7.016504991533727e-07, | |
| "loss": 0.2393, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 5.015873015873016, | |
| "grad_norm": 0.4504229724407196, | |
| "learning_rate": 6.421379363065142e-07, | |
| "loss": 0.2276, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 5.079365079365079, | |
| "grad_norm": 0.4797239899635315, | |
| "learning_rate": 5.848888922025553e-07, | |
| "loss": 0.2185, | |
| "step": 80 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.8886781958723994e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |