| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 140, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007142857142857143, | |
| "grad_norm": 106.10701751708984, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 27.4831, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03571428571428571, | |
| "grad_norm": 46.149723052978516, | |
| "learning_rate": 7.142857142857143e-05, | |
| "loss": 26.2992, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07142857142857142, | |
| "grad_norm": 16.458189010620117, | |
| "learning_rate": 0.00014285714285714287, | |
| "loss": 20.4929, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10714285714285714, | |
| "grad_norm": 9.764805793762207, | |
| "learning_rate": 0.00019996891820008164, | |
| "loss": 16.0513, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 3.3296561241149902, | |
| "learning_rate": 0.00019888308262251285, | |
| "loss": 13.4526, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17857142857142858, | |
| "grad_norm": 3.235478162765503, | |
| "learning_rate": 0.0001962624246950012, | |
| "loss": 12.6172, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.21428571428571427, | |
| "grad_norm": 5.432589530944824, | |
| "learning_rate": 0.00019214762118704076, | |
| "loss": 11.9808, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 10.644349098205566, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 11.0065, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 14.282907485961914, | |
| "learning_rate": 0.00017971325072229226, | |
| "loss": 9.3131, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.32142857142857145, | |
| "grad_norm": 21.60712432861328, | |
| "learning_rate": 0.00017158668492597186, | |
| "loss": 7.1723, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": 15.418853759765625, | |
| "learning_rate": 0.00016234898018587337, | |
| "loss": 4.6599, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.39285714285714285, | |
| "grad_norm": 5.335650444030762, | |
| "learning_rate": 0.0001521435203379498, | |
| "loss": 2.855, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 4.913125038146973, | |
| "learning_rate": 0.00014112871031306119, | |
| "loss": 2.3938, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4642857142857143, | |
| "grad_norm": 3.951244592666626, | |
| "learning_rate": 0.00012947551744109043, | |
| "loss": 2.1646, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 1.6933783292770386, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 2.0061, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5357142857142857, | |
| "grad_norm": 0.9344208836555481, | |
| "learning_rate": 0.00010498458856606972, | |
| "loss": 1.9092, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.9437263011932373, | |
| "learning_rate": 9.252699064135758e-05, | |
| "loss": 1.8086, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6071428571428571, | |
| "grad_norm": 1.5205684900283813, | |
| "learning_rate": 8.018538568006027e-05, | |
| "loss": 1.7838, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.6428571428571429, | |
| "grad_norm": 0.8009554743766785, | |
| "learning_rate": 6.815133497483157e-05, | |
| "loss": 1.7433, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6785714285714286, | |
| "grad_norm": 0.9393540620803833, | |
| "learning_rate": 5.6611626088244194e-05, | |
| "loss": 1.736, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 1.6479978561401367, | |
| "learning_rate": 4.574537361342407e-05, | |
| "loss": 1.6976, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.7829992771148682, | |
| "learning_rate": 3.5721239031346066e-05, | |
| "loss": 1.6793, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.7857142857142857, | |
| "grad_norm": 0.7236832976341248, | |
| "learning_rate": 2.669481281701739e-05, | |
| "loss": 1.7, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8214285714285714, | |
| "grad_norm": 0.7881686687469482, | |
| "learning_rate": 1.880619942841435e-05, | |
| "loss": 1.6778, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 1.7755261659622192, | |
| "learning_rate": 1.2177842662977135e-05, | |
| "loss": 1.6757, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.8928571428571429, | |
| "grad_norm": 1.0512515306472778, | |
| "learning_rate": 6.9126251355795864e-06, | |
| "loss": 1.6766, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.9285714285714286, | |
| "grad_norm": 0.7070327997207642, | |
| "learning_rate": 3.092271377092215e-06, | |
| "loss": 1.67, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.9642857142857143, | |
| "grad_norm": 0.7091158628463745, | |
| "learning_rate": 7.760793399827937e-07, | |
| "loss": 1.6459, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.7374704480171204, | |
| "learning_rate": 0.0, | |
| "loss": 1.6561, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.6581236124038696, | |
| "eval_runtime": 3.8242, | |
| "eval_samples_per_second": 46.545, | |
| "eval_steps_per_second": 0.784, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 140, | |
| "total_flos": 4.268849030789857e+17, | |
| "train_loss": 5.955788305827549, | |
| "train_runtime": 1733.7968, | |
| "train_samples_per_second": 10.326, | |
| "train_steps_per_second": 0.081 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 140, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.268849030789857e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |