| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 47, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02127659574468085, | |
| "grad_norm": 173.3797693640036, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 2.0421, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0425531914893617, | |
| "grad_norm": 213.4863387447492, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.1926, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06382978723404255, | |
| "grad_norm": 139.12102571177553, | |
| "learning_rate": 6e-06, | |
| "loss": 1.6796, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0851063829787234, | |
| "grad_norm": 31.770887201034693, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.8817, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10638297872340426, | |
| "grad_norm": 11.974572830777873, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6561, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1276595744680851, | |
| "grad_norm": 5.587929077588245, | |
| "learning_rate": 9.986018985905901e-06, | |
| "loss": 0.4698, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.14893617021276595, | |
| "grad_norm": 7.58893303595288, | |
| "learning_rate": 9.944154131125643e-06, | |
| "loss": 0.3525, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1702127659574468, | |
| "grad_norm": 4.03951296758354, | |
| "learning_rate": 9.874639560909118e-06, | |
| "loss": 0.2916, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.19148936170212766, | |
| "grad_norm": 2.36253683449773, | |
| "learning_rate": 9.777864028930705e-06, | |
| "loss": 0.2413, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2127659574468085, | |
| "grad_norm": 1.724376767595317, | |
| "learning_rate": 9.654368743221022e-06, | |
| "loss": 0.2407, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.23404255319148937, | |
| "grad_norm": 7.656722082252226, | |
| "learning_rate": 9.504844339512096e-06, | |
| "loss": 0.2365, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2553191489361702, | |
| "grad_norm": 3.966824389729543, | |
| "learning_rate": 9.330127018922195e-06, | |
| "loss": 0.2593, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2765957446808511, | |
| "grad_norm": 2.4259726258566894, | |
| "learning_rate": 9.131193871579975e-06, | |
| "loss": 0.2063, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2978723404255319, | |
| "grad_norm": 2.0989965880083665, | |
| "learning_rate": 8.90915741234015e-06, | |
| "loss": 0.2137, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3191489361702128, | |
| "grad_norm": 0.7473125600483845, | |
| "learning_rate": 8.665259359149132e-06, | |
| "loss": 0.1752, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": 2.362035437648623, | |
| "learning_rate": 8.400863688854598e-06, | |
| "loss": 0.2079, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3617021276595745, | |
| "grad_norm": 1.1278643764919287, | |
| "learning_rate": 8.117449009293668e-06, | |
| "loss": 0.2096, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3829787234042553, | |
| "grad_norm": 0.9888933504092371, | |
| "learning_rate": 7.81660029031811e-06, | |
| "loss": 0.1759, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.40425531914893614, | |
| "grad_norm": 1.3935821371981716, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.2036, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.425531914893617, | |
| "grad_norm": 0.7210016827193401, | |
| "learning_rate": 7.169418695587791e-06, | |
| "loss": 0.1757, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.44680851063829785, | |
| "grad_norm": 1.3893738922334362, | |
| "learning_rate": 6.8267051218319766e-06, | |
| "loss": 0.1802, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.46808510638297873, | |
| "grad_norm": 0.7826903349267914, | |
| "learning_rate": 6.473775872054522e-06, | |
| "loss": 0.1823, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.48936170212765956, | |
| "grad_norm": 1.1055685574886962, | |
| "learning_rate": 6.112604669781572e-06, | |
| "loss": 0.1812, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5106382978723404, | |
| "grad_norm": 1.3398319352785983, | |
| "learning_rate": 5.745211330880872e-06, | |
| "loss": 0.1791, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5319148936170213, | |
| "grad_norm": 0.5530788932061305, | |
| "learning_rate": 5.373650467932122e-06, | |
| "loss": 0.1582, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5531914893617021, | |
| "grad_norm": 0.979470403637453, | |
| "learning_rate": 5e-06, | |
| "loss": 0.1687, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.574468085106383, | |
| "grad_norm": 0.6524782994513246, | |
| "learning_rate": 4.626349532067879e-06, | |
| "loss": 0.1614, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5957446808510638, | |
| "grad_norm": 0.613082643775453, | |
| "learning_rate": 4.254788669119127e-06, | |
| "loss": 0.1406, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6170212765957447, | |
| "grad_norm": 0.6117099956858949, | |
| "learning_rate": 3.887395330218429e-06, | |
| "loss": 0.1637, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6382978723404256, | |
| "grad_norm": 0.4598315067554906, | |
| "learning_rate": 3.526224127945479e-06, | |
| "loss": 0.1488, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6595744680851063, | |
| "grad_norm": 0.5041452368752941, | |
| "learning_rate": 3.173294878168025e-06, | |
| "loss": 0.1385, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": 0.6131569474074337, | |
| "learning_rate": 2.83058130441221e-06, | |
| "loss": 0.151, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7021276595744681, | |
| "grad_norm": 0.5119335095129718, | |
| "learning_rate": 2.5000000000000015e-06, | |
| "loss": 0.1492, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.723404255319149, | |
| "grad_norm": 0.4443782774575828, | |
| "learning_rate": 2.1833997096818897e-06, | |
| "loss": 0.1174, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7446808510638298, | |
| "grad_norm": 0.45664829579358884, | |
| "learning_rate": 1.8825509907063328e-06, | |
| "loss": 0.1273, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7659574468085106, | |
| "grad_norm": 0.5213080660032051, | |
| "learning_rate": 1.5991363111454023e-06, | |
| "loss": 0.1422, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7872340425531915, | |
| "grad_norm": 0.5400795029678803, | |
| "learning_rate": 1.3347406408508695e-06, | |
| "loss": 0.148, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8085106382978723, | |
| "grad_norm": 0.47711498862269414, | |
| "learning_rate": 1.0908425876598512e-06, | |
| "loss": 0.1201, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8297872340425532, | |
| "grad_norm": 0.4674822262301143, | |
| "learning_rate": 8.688061284200266e-07, | |
| "loss": 0.1427, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.851063829787234, | |
| "grad_norm": 0.4740692779208992, | |
| "learning_rate": 6.698729810778065e-07, | |
| "loss": 0.1259, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8723404255319149, | |
| "grad_norm": 0.5372156644144523, | |
| "learning_rate": 4.951556604879049e-07, | |
| "loss": 0.1342, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.8936170212765957, | |
| "grad_norm": 0.5807354531086322, | |
| "learning_rate": 3.4563125677897936e-07, | |
| "loss": 0.1449, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9148936170212766, | |
| "grad_norm": 0.4917053466958668, | |
| "learning_rate": 2.2213597106929608e-07, | |
| "loss": 0.1344, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9361702127659575, | |
| "grad_norm": 0.45294061142670444, | |
| "learning_rate": 1.253604390908819e-07, | |
| "loss": 0.1187, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9574468085106383, | |
| "grad_norm": 0.42691924060512204, | |
| "learning_rate": 5.584586887435739e-08, | |
| "loss": 0.1114, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.9787234042553191, | |
| "grad_norm": 0.4007354051634515, | |
| "learning_rate": 1.3981014094099354e-08, | |
| "loss": 0.1139, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.4672720715521086, | |
| "learning_rate": 0.0, | |
| "loss": 0.1298, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.14448508620262146, | |
| "eval_runtime": 6.6249, | |
| "eval_samples_per_second": 11.925, | |
| "eval_steps_per_second": 3.019, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 47, | |
| "total_flos": 10394912686080.0, | |
| "train_loss": 0.3196908062759866, | |
| "train_runtime": 717.6944, | |
| "train_samples_per_second": 2.069, | |
| "train_steps_per_second": 0.065 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 47, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 10394912686080.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |