| { | |
| "best_metric": 0.14303971827030182, | |
| "best_model_checkpoint": "autotrain-tckj2-dxpo0/checkpoint-203", | |
| "epoch": 7.0, | |
| "eval_steps": 500, | |
| "global_step": 203, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1724137931034483, | |
| "grad_norm": 3.970233678817749, | |
| "learning_rate": 4.761904761904762e-06, | |
| "loss": 0.7808, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3448275862068966, | |
| "grad_norm": 2.5622565746307373, | |
| "learning_rate": 9.523809523809525e-06, | |
| "loss": 0.7224, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5172413793103449, | |
| "grad_norm": 1.819740891456604, | |
| "learning_rate": 1.4285714285714287e-05, | |
| "loss": 0.5833, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6896551724137931, | |
| "grad_norm": 1.9450643062591553, | |
| "learning_rate": 1.904761904761905e-05, | |
| "loss": 0.4336, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8620689655172413, | |
| "grad_norm": 1.2047266960144043, | |
| "learning_rate": 1.9560439560439563e-05, | |
| "loss": 0.426, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.42094460129737854, | |
| "eval_runtime": 1.7024, | |
| "eval_samples_per_second": 67.553, | |
| "eval_steps_per_second": 2.35, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0344827586206897, | |
| "grad_norm": 1.0075544118881226, | |
| "learning_rate": 1.901098901098901e-05, | |
| "loss": 0.407, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.206896551724138, | |
| "grad_norm": 2.6184139251708984, | |
| "learning_rate": 1.8461538461538465e-05, | |
| "loss": 0.4633, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.3793103448275863, | |
| "grad_norm": 1.3700945377349854, | |
| "learning_rate": 1.7912087912087915e-05, | |
| "loss": 0.2629, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5517241379310345, | |
| "grad_norm": 1.5076994895935059, | |
| "learning_rate": 1.7362637362637363e-05, | |
| "loss": 0.4468, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.7241379310344827, | |
| "grad_norm": 1.0693202018737793, | |
| "learning_rate": 1.6813186813186814e-05, | |
| "loss": 0.3665, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.896551724137931, | |
| "grad_norm": 1.7655493021011353, | |
| "learning_rate": 1.6263736263736265e-05, | |
| "loss": 0.2735, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.3269391655921936, | |
| "eval_runtime": 1.3905, | |
| "eval_samples_per_second": 82.706, | |
| "eval_steps_per_second": 2.877, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.0689655172413794, | |
| "grad_norm": 1.0194451808929443, | |
| "learning_rate": 1.5714285714285715e-05, | |
| "loss": 0.2472, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.2413793103448274, | |
| "grad_norm": 2.360098361968994, | |
| "learning_rate": 1.5164835164835166e-05, | |
| "loss": 0.2586, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.413793103448276, | |
| "grad_norm": 1.4176146984100342, | |
| "learning_rate": 1.4615384615384615e-05, | |
| "loss": 0.2281, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.586206896551724, | |
| "grad_norm": 3.5215818881988525, | |
| "learning_rate": 1.4065934065934068e-05, | |
| "loss": 0.3056, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.7586206896551726, | |
| "grad_norm": 1.205544352531433, | |
| "learning_rate": 1.3516483516483519e-05, | |
| "loss": 0.2166, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.9310344827586206, | |
| "grad_norm": 1.4513664245605469, | |
| "learning_rate": 1.296703296703297e-05, | |
| "loss": 0.2243, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.2470882385969162, | |
| "eval_runtime": 1.6355, | |
| "eval_samples_per_second": 70.316, | |
| "eval_steps_per_second": 2.446, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.103448275862069, | |
| "grad_norm": 1.3780584335327148, | |
| "learning_rate": 1.2417582417582419e-05, | |
| "loss": 0.2233, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.2758620689655173, | |
| "grad_norm": 1.5511927604675293, | |
| "learning_rate": 1.186813186813187e-05, | |
| "loss": 0.1625, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.4482758620689653, | |
| "grad_norm": 1.3662214279174805, | |
| "learning_rate": 1.131868131868132e-05, | |
| "loss": 0.1718, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.6206896551724137, | |
| "grad_norm": 2.4403982162475586, | |
| "learning_rate": 1.076923076923077e-05, | |
| "loss": 0.1728, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 3.793103448275862, | |
| "grad_norm": 1.4150804281234741, | |
| "learning_rate": 1.021978021978022e-05, | |
| "loss": 0.1949, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.9655172413793105, | |
| "grad_norm": 2.6226606369018555, | |
| "learning_rate": 9.670329670329671e-06, | |
| "loss": 0.0891, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.19967548549175262, | |
| "eval_runtime": 1.725, | |
| "eval_samples_per_second": 66.667, | |
| "eval_steps_per_second": 2.319, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.137931034482759, | |
| "grad_norm": 2.1667020320892334, | |
| "learning_rate": 9.120879120879122e-06, | |
| "loss": 0.1895, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.310344827586207, | |
| "grad_norm": 1.2279396057128906, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 0.1021, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.482758620689655, | |
| "grad_norm": 2.164337396621704, | |
| "learning_rate": 8.021978021978023e-06, | |
| "loss": 0.1232, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.655172413793103, | |
| "grad_norm": 0.4767724573612213, | |
| "learning_rate": 7.472527472527473e-06, | |
| "loss": 0.0891, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 4.827586206896552, | |
| "grad_norm": 0.7710694074630737, | |
| "learning_rate": 6.923076923076923e-06, | |
| "loss": 0.109, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.6246473789215088, | |
| "learning_rate": 6.373626373626373e-06, | |
| "loss": 0.0879, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.16786590218544006, | |
| "eval_runtime": 1.7475, | |
| "eval_samples_per_second": 65.808, | |
| "eval_steps_per_second": 2.289, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 5.172413793103448, | |
| "grad_norm": 1.7630176544189453, | |
| "learning_rate": 5.824175824175825e-06, | |
| "loss": 0.0814, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 5.344827586206897, | |
| "grad_norm": 0.9055896401405334, | |
| "learning_rate": 5.274725274725275e-06, | |
| "loss": 0.1015, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 5.517241379310345, | |
| "grad_norm": 1.1590590476989746, | |
| "learning_rate": 4.725274725274726e-06, | |
| "loss": 0.0822, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 5.689655172413794, | |
| "grad_norm": 3.4120426177978516, | |
| "learning_rate": 4.175824175824177e-06, | |
| "loss": 0.1054, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 5.862068965517241, | |
| "grad_norm": 1.244531273841858, | |
| "learning_rate": 3.6263736263736266e-06, | |
| "loss": 0.1093, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.14788025617599487, | |
| "eval_runtime": 1.4731, | |
| "eval_samples_per_second": 78.065, | |
| "eval_steps_per_second": 2.715, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 6.0344827586206895, | |
| "grad_norm": 0.7680085301399231, | |
| "learning_rate": 3.0769230769230774e-06, | |
| "loss": 0.0911, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 6.206896551724138, | |
| "grad_norm": 1.3764543533325195, | |
| "learning_rate": 2.5274725274725274e-06, | |
| "loss": 0.0804, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 6.379310344827586, | |
| "grad_norm": 1.9512306451797485, | |
| "learning_rate": 1.9780219780219782e-06, | |
| "loss": 0.1063, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 6.551724137931035, | |
| "grad_norm": 1.7474387884140015, | |
| "learning_rate": 1.4285714285714286e-06, | |
| "loss": 0.0821, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 6.724137931034483, | |
| "grad_norm": 3.119471788406372, | |
| "learning_rate": 8.791208791208792e-07, | |
| "loss": 0.0988, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 6.896551724137931, | |
| "grad_norm": 1.1896252632141113, | |
| "learning_rate": 3.296703296703297e-07, | |
| "loss": 0.0691, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.14303971827030182, | |
| "eval_runtime": 1.4807, | |
| "eval_samples_per_second": 77.664, | |
| "eval_steps_per_second": 2.701, | |
| "step": 203 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 203, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |