| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.5306122448979593, | |
| "eval_steps": 13, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01020408163265306, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.052, | |
| "eval_samples_per_second": 32.661, | |
| "eval_steps_per_second": 4.157, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.030612244897959183, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.061224489795918366, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09183673469387756, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12244897959183673, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.994965332706573e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1326530612244898, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.5223, | |
| "eval_samples_per_second": 36.486, | |
| "eval_steps_per_second": 4.644, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15306122448979592, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1836734693877551, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.919647942993148e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.21428571428571427, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.848447601883435e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.24489795918367346, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2653061224489796, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.5279, | |
| "eval_samples_per_second": 36.441, | |
| "eval_steps_per_second": 4.638, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2755102040816326, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.640574942595196e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.30612244897959184, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.336734693877551, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.348705665778478e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3673469387755102, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.172866268606513e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3979591836734694, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.978122744408906e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3979591836734694, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.5303, | |
| "eval_samples_per_second": 36.421, | |
| "eval_steps_per_second": 4.635, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.765357330018056e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.45918367346938777, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4897959183673469, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.289693629698564e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5204081632653061, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.0289502192041e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.5306122448979592, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.5333, | |
| "eval_samples_per_second": 36.397, | |
| "eval_steps_per_second": 4.632, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.5510204081632653, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.754484907260513e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.5816326530612245, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.467541090321735e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.6122448979591837, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6428571428571429, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.861468292009727e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.6632653061224489, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.5236, | |
| "eval_samples_per_second": 36.476, | |
| "eval_steps_per_second": 4.642, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.673469387755102, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.7040816326530612, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.22170203068947e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.7346938775510204, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8927844739931834e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.7653061224489796, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7959183673469388, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.2243241517525754e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.7959183673469388, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.5322, | |
| "eval_samples_per_second": 36.406, | |
| "eval_steps_per_second": 4.634, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.826530612244898, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.887809678520976e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.551803455482833e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.8877551020408163, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.9183673469387755, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.9285714285714286, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.5272, | |
| "eval_samples_per_second": 36.447, | |
| "eval_steps_per_second": 4.639, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.9489795918367347, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.562003362839914e-05, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.9795918367346939, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.243125879593286e-05, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.010204081632653, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.932207475167398e-05, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.0408163265306123, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.630656687635007e-05, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.0612244897959184, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.5257, | |
| "eval_samples_per_second": 36.458, | |
| "eval_steps_per_second": 4.64, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.0714285714285714, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.1020408163265305, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.1326530612244898, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7956219300748793e-05, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.163265306122449, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.544686755065677e-05, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.193877551020408, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3094050125632972e-05, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.193877551020408, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.5276, | |
| "eval_samples_per_second": 36.443, | |
| "eval_steps_per_second": 4.638, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.2244897959183674, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.2551020408163265, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.899896227604509e-06, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.2857142857142856, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.077560319906695e-06, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.316326530612245, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.3265306122448979, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.5275, | |
| "eval_samples_per_second": 36.444, | |
| "eval_steps_per_second": 4.638, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.346938775510204, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.023611372427471e-06, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.3775510204081631, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.4081632653061225, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8018569652073381e-06, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.4387755102040816, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.016230078838226e-06, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.4591836734693877, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.5304, | |
| "eval_samples_per_second": 36.421, | |
| "eval_steps_per_second": 4.635, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.469387755102041, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.52511911603265e-07, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.132562476771959e-07, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.5306122448979593, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.081320507998208e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |