| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 100, |
| "global_step": 216, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.004629629629629629, |
| "grad_norm": 17.14967918395996, |
| "learning_rate": 0.0, |
| "loss": 3.3728, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.023148148148148147, |
| "grad_norm": 15.374231338500977, |
| "learning_rate": 3.6363636363636366e-06, |
| "loss": 3.3769, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.046296296296296294, |
| "grad_norm": 6.152224540710449, |
| "learning_rate": 8.181818181818183e-06, |
| "loss": 3.0128, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.06944444444444445, |
| "grad_norm": 5.15545129776001, |
| "learning_rate": 1.2727272727272728e-05, |
| "loss": 2.6223, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.09259259259259259, |
| "grad_norm": 8.587775230407715, |
| "learning_rate": 1.7272727272727274e-05, |
| "loss": 2.398, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.11574074074074074, |
| "grad_norm": 9.511617660522461, |
| "learning_rate": 1.9994755690455154e-05, |
| "loss": 2.2652, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.1388888888888889, |
| "grad_norm": 8.835038185119629, |
| "learning_rate": 1.993582036030978e-05, |
| "loss": 2.1412, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.16203703703703703, |
| "grad_norm": 7.89705228805542, |
| "learning_rate": 1.9811781768982392e-05, |
| "loss": 2.0107, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.18518518518518517, |
| "grad_norm": 6.195117473602295, |
| "learning_rate": 1.9623452664340305e-05, |
| "loss": 1.8743, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.20833333333333334, |
| "grad_norm": 4.751745700836182, |
| "learning_rate": 1.937206705006344e-05, |
| "loss": 1.8038, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.23148148148148148, |
| "grad_norm": 3.927769660949707, |
| "learning_rate": 1.905927209998447e-05, |
| "loss": 1.7567, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.25462962962962965, |
| "grad_norm": 4.062364101409912, |
| "learning_rate": 1.8687117365181514e-05, |
| "loss": 1.7709, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.2777777777777778, |
| "grad_norm": 2.570540189743042, |
| "learning_rate": 1.8258041344542567e-05, |
| "loss": 1.7229, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.30092592592592593, |
| "grad_norm": 1.9970929622650146, |
| "learning_rate": 1.7774855506796497e-05, |
| "loss": 1.7179, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.32407407407407407, |
| "grad_norm": 1.8299241065979004, |
| "learning_rate": 1.7240725868704218e-05, |
| "loss": 1.666, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.3472222222222222, |
| "grad_norm": 1.8000702857971191, |
| "learning_rate": 1.665915225011681e-05, |
| "loss": 1.6529, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.37037037037037035, |
| "grad_norm": 1.5835669040679932, |
| "learning_rate": 1.603394534182925e-05, |
| "loss": 1.6352, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.39351851851851855, |
| "grad_norm": 1.4376660585403442, |
| "learning_rate": 1.536920173648984e-05, |
| "loss": 1.6241, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.4166666666666667, |
| "grad_norm": 1.3085274696350098, |
| "learning_rate": 1.4669277086172406e-05, |
| "loss": 1.6178, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.4398148148148148, |
| "grad_norm": 1.3968168497085571, |
| "learning_rate": 1.3938757562492873e-05, |
| "loss": 1.6035, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.46296296296296297, |
| "grad_norm": 1.137740969657898, |
| "learning_rate": 1.3182429806274442e-05, |
| "loss": 1.5831, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.46296296296296297, |
| "eval_loss": 1.6092934608459473, |
| "eval_runtime": 4.5262, |
| "eval_samples_per_second": 172.332, |
| "eval_steps_per_second": 5.523, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.4861111111111111, |
| "grad_norm": 1.4185782670974731, |
| "learning_rate": 1.2405249563662539e-05, |
| "loss": 1.5905, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.5092592592592593, |
| "grad_norm": 1.140097975730896, |
| "learning_rate": 1.1612309214197599e-05, |
| "loss": 1.5775, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.5324074074074074, |
| "grad_norm": 1.0888863801956177, |
| "learning_rate": 1.0808804403614044e-05, |
| "loss": 1.5804, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.5555555555555556, |
| "grad_norm": 1.0755336284637451, |
| "learning_rate": 1e-05, |
| "loss": 1.5582, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.5787037037037037, |
| "grad_norm": 2.2309999465942383, |
| "learning_rate": 9.19119559638596e-06, |
| "loss": 1.5673, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.6018518518518519, |
| "grad_norm": 1.0764739513397217, |
| "learning_rate": 8.387690785802403e-06, |
| "loss": 1.5524, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.625, |
| "grad_norm": 0.9964112043380737, |
| "learning_rate": 7.594750436337467e-06, |
| "loss": 1.5419, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.6481481481481481, |
| "grad_norm": 1.22049880027771, |
| "learning_rate": 6.8175701937255645e-06, |
| "loss": 1.5623, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.6712962962962963, |
| "grad_norm": 1.0341013669967651, |
| "learning_rate": 6.061242437507131e-06, |
| "loss": 1.5363, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.6944444444444444, |
| "grad_norm": 1.0175600051879883, |
| "learning_rate": 5.330722913827594e-06, |
| "loss": 1.541, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.7175925925925926, |
| "grad_norm": 0.9816425442695618, |
| "learning_rate": 4.630798263510162e-06, |
| "loss": 1.5343, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.7407407407407407, |
| "grad_norm": 0.9579488039016724, |
| "learning_rate": 3.966054658170754e-06, |
| "loss": 1.5441, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.7638888888888888, |
| "grad_norm": 0.9483299851417542, |
| "learning_rate": 3.3408477498831917e-06, |
| "loss": 1.5334, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.7870370370370371, |
| "grad_norm": 0.9652431607246399, |
| "learning_rate": 2.759274131295787e-06, |
| "loss": 1.5286, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.8101851851851852, |
| "grad_norm": 0.9639863967895508, |
| "learning_rate": 2.2251444932035094e-06, |
| "loss": 1.5207, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.8333333333333334, |
| "grad_norm": 0.9372048377990723, |
| "learning_rate": 1.7419586554574364e-06, |
| "loss": 1.5318, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.8564814814814815, |
| "grad_norm": 0.938995897769928, |
| "learning_rate": 1.3128826348184886e-06, |
| "loss": 1.5329, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.8796296296296297, |
| "grad_norm": 0.9280312657356262, |
| "learning_rate": 9.407279000155311e-07, |
| "loss": 1.514, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.9027777777777778, |
| "grad_norm": 0.9297032952308655, |
| "learning_rate": 6.279329499365649e-07, |
| "loss": 1.5254, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.9259259259259259, |
| "grad_norm": 0.8736039400100708, |
| "learning_rate": 3.7654733565969826e-07, |
| "loss": 1.5043, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.9259259259259259, |
| "eval_loss": 1.530943751335144, |
| "eval_runtime": 4.4836, |
| "eval_samples_per_second": 173.966, |
| "eval_steps_per_second": 5.576, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.9490740740740741, |
| "grad_norm": 0.9444804191589355, |
| "learning_rate": 1.8821823101760949e-07, |
| "loss": 1.5041, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.9722222222222222, |
| "grad_norm": 0.9190117716789246, |
| "learning_rate": 6.417963969022389e-08, |
| "loss": 1.5197, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.9953703703703703, |
| "grad_norm": 0.9011805653572083, |
| "learning_rate": 5.2443095448506674e-09, |
| "loss": 1.529, |
| "step": 215 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 216, |
| "total_flos": 8.03524877305774e+16, |
| "train_loss": 1.7498196733218652, |
| "train_runtime": 326.8611, |
| "train_samples_per_second": 42.278, |
| "train_steps_per_second": 0.661 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 216, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 1000000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": false, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8.03524877305774e+16, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
