| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06470397929472663, | |
| "eval_steps": 386, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012940795858945326, | |
| "grad_norm": 1.7405146360397339, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 2.4269, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012940795858945326, | |
| "eval_loss": 2.247628688812256, | |
| "eval_runtime": 189.8853, | |
| "eval_samples_per_second": 3.428, | |
| "eval_steps_per_second": 0.858, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002588159171789065, | |
| "grad_norm": 1.6643542051315308, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.2583, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0038822387576835974, | |
| "grad_norm": 1.8690767288208008, | |
| "learning_rate": 6e-06, | |
| "loss": 2.2696, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00517631834357813, | |
| "grad_norm": 1.828118085861206, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 2.3646, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006470397929472662, | |
| "grad_norm": 1.9319926500320435, | |
| "learning_rate": 1e-05, | |
| "loss": 2.4196, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007764477515367195, | |
| "grad_norm": 1.7723782062530518, | |
| "learning_rate": 1.2e-05, | |
| "loss": 2.4177, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009058557101261728, | |
| "grad_norm": 1.9500815868377686, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 2.3497, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01035263668715626, | |
| "grad_norm": 2.3909075260162354, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 2.405, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011646716273050793, | |
| "grad_norm": 2.0620856285095215, | |
| "learning_rate": 1.8e-05, | |
| "loss": 2.4098, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012940795858945324, | |
| "grad_norm": 1.8054910898208618, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1233, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014234875444839857, | |
| "grad_norm": 2.190964937210083, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 2.3985, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01552895503073439, | |
| "grad_norm": 1.9412921667099, | |
| "learning_rate": 2.4e-05, | |
| "loss": 2.462, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016823034616628922, | |
| "grad_norm": 1.9161555767059326, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 2.2118, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.018117114202523456, | |
| "grad_norm": 1.7161599397659302, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 2.2175, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.019411193788417987, | |
| "grad_norm": 2.173877000808716, | |
| "learning_rate": 3e-05, | |
| "loss": 2.2521, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02070527337431252, | |
| "grad_norm": 2.0000555515289307, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 2.1615, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.021999352960207053, | |
| "grad_norm": 1.5915080308914185, | |
| "learning_rate": 3.4000000000000007e-05, | |
| "loss": 1.9522, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.023293432546101587, | |
| "grad_norm": 1.6972448825836182, | |
| "learning_rate": 3.6e-05, | |
| "loss": 1.7224, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.024587512131996118, | |
| "grad_norm": 1.7509772777557373, | |
| "learning_rate": 3.8e-05, | |
| "loss": 2.0414, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02588159171789065, | |
| "grad_norm": 1.697340488433838, | |
| "learning_rate": 4e-05, | |
| "loss": 2.0427, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.027175671303785183, | |
| "grad_norm": 1.8733758926391602, | |
| "learning_rate": 4.2e-05, | |
| "loss": 1.6772, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.028469750889679714, | |
| "grad_norm": 1.6085255146026611, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 1.6527, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.029763830475574248, | |
| "grad_norm": 1.5792337656021118, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 1.6567, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03105791006146878, | |
| "grad_norm": 1.4392567873001099, | |
| "learning_rate": 4.8e-05, | |
| "loss": 1.508, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03235198964736331, | |
| "grad_norm": 1.5222433805465698, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4606, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.033646069233257844, | |
| "grad_norm": 1.5480064153671265, | |
| "learning_rate": 5.2000000000000004e-05, | |
| "loss": 1.5027, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.034940148819152375, | |
| "grad_norm": 1.6736445426940918, | |
| "learning_rate": 5.4000000000000005e-05, | |
| "loss": 1.2426, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03623422840504691, | |
| "grad_norm": 1.7392551898956299, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 1.4703, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.037528307990941444, | |
| "grad_norm": 1.6173359155654907, | |
| "learning_rate": 5.8e-05, | |
| "loss": 1.4546, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.038822387576835975, | |
| "grad_norm": 1.3955802917480469, | |
| "learning_rate": 6e-05, | |
| "loss": 1.3808, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.040116467162730506, | |
| "grad_norm": 1.353873372077942, | |
| "learning_rate": 6.2e-05, | |
| "loss": 1.229, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04141054674862504, | |
| "grad_norm": 1.2547746896743774, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 1.1668, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.042704626334519574, | |
| "grad_norm": 1.3806778192520142, | |
| "learning_rate": 6.6e-05, | |
| "loss": 1.0691, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.043998705920414105, | |
| "grad_norm": 1.2815773487091064, | |
| "learning_rate": 6.800000000000001e-05, | |
| "loss": 1.2409, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.045292785506308636, | |
| "grad_norm": 1.3677266836166382, | |
| "learning_rate": 7e-05, | |
| "loss": 0.9668, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.046586865092203174, | |
| "grad_norm": 1.5457032918930054, | |
| "learning_rate": 7.2e-05, | |
| "loss": 1.1385, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.047880944678097705, | |
| "grad_norm": 1.5587060451507568, | |
| "learning_rate": 7.4e-05, | |
| "loss": 1.1707, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.049175024263992236, | |
| "grad_norm": 1.079053282737732, | |
| "learning_rate": 7.6e-05, | |
| "loss": 1.0655, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.050469103849886766, | |
| "grad_norm": 1.1773897409439087, | |
| "learning_rate": 7.800000000000001e-05, | |
| "loss": 1.0465, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0517631834357813, | |
| "grad_norm": 1.2437673807144165, | |
| "learning_rate": 8e-05, | |
| "loss": 1.2779, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.053057263021675835, | |
| "grad_norm": 1.254847526550293, | |
| "learning_rate": 8.2e-05, | |
| "loss": 1.0898, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.054351342607570366, | |
| "grad_norm": 1.1771515607833862, | |
| "learning_rate": 8.4e-05, | |
| "loss": 1.1827, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0556454221934649, | |
| "grad_norm": 1.1400648355484009, | |
| "learning_rate": 8.6e-05, | |
| "loss": 1.1066, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05693950177935943, | |
| "grad_norm": 1.2047138214111328, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 0.8974, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.058233581365253966, | |
| "grad_norm": 1.1269346475601196, | |
| "learning_rate": 9e-05, | |
| "loss": 1.0146, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.059527660951148496, | |
| "grad_norm": 1.169231653213501, | |
| "learning_rate": 9.200000000000001e-05, | |
| "loss": 1.1266, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06082174053704303, | |
| "grad_norm": 0.9771779179573059, | |
| "learning_rate": 9.4e-05, | |
| "loss": 0.8351, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06211582012293756, | |
| "grad_norm": 1.2849314212799072, | |
| "learning_rate": 9.6e-05, | |
| "loss": 1.1822, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0634098997088321, | |
| "grad_norm": 1.023181676864624, | |
| "learning_rate": 9.8e-05, | |
| "loss": 0.9082, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06470397929472663, | |
| "grad_norm": 1.135751724243164, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9407, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 3860, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.58968585846784e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |