| { | |
| "best_metric": 0.5109696984291077, | |
| "best_model_checkpoint": "/tmp/model/checkpoint-132", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 132, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 7.142857142857143e-06, | |
| "loss": 1.0986, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.0714285714285714e-05, | |
| "loss": 1.0986, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 1.0981, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.0948, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.2142857142857144e-05, | |
| "loss": 1.0962, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.928571428571429e-05, | |
| "loss": 1.0926, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.642857142857143e-05, | |
| "loss": 1.0908, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.957627118644068e-05, | |
| "loss": 1.086, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.8728813559322034e-05, | |
| "loss": 1.0706, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.788135593220339e-05, | |
| "loss": 1.0397, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.703389830508475e-05, | |
| "loss": 1.0251, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.6186440677966104e-05, | |
| "loss": 1.032, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.533898305084746e-05, | |
| "loss": 0.9616, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.4491525423728816e-05, | |
| "loss": 0.8914, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.3644067796610175e-05, | |
| "loss": 0.9912, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.279661016949153e-05, | |
| "loss": 0.8628, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.1949152542372886e-05, | |
| "loss": 0.9583, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.110169491525424e-05, | |
| "loss": 0.9837, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.025423728813559e-05, | |
| "loss": 0.9641, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.940677966101695e-05, | |
| "loss": 0.8973, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.855932203389831e-05, | |
| "loss": 0.8762, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.771186440677966e-05, | |
| "loss": 0.8489, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7727272727272727, | |
| "eval_f1_macro": 0.7295238095238096, | |
| "eval_f1_micro": 0.7727272727272727, | |
| "eval_f1_weighted": 0.7701298701298701, | |
| "eval_loss": 0.7866544127464294, | |
| "eval_precision_macro": 0.7356589147286821, | |
| "eval_precision_micro": 0.7727272727272727, | |
| "eval_precision_weighted": 0.7901691331923889, | |
| "eval_recall_macro": 0.7541666666666668, | |
| "eval_recall_micro": 0.7727272727272727, | |
| "eval_recall_weighted": 0.7727272727272727, | |
| "eval_runtime": 3.048, | |
| "eval_samples_per_second": 28.871, | |
| "eval_steps_per_second": 1.968, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.686440677966102e-05, | |
| "loss": 0.7592, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.601694915254237e-05, | |
| "loss": 0.7081, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.516949152542373e-05, | |
| "loss": 0.6742, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.432203389830508e-05, | |
| "loss": 0.8392, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.347457627118644e-05, | |
| "loss": 0.549, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.26271186440678e-05, | |
| "loss": 0.7988, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.177966101694915e-05, | |
| "loss": 0.6954, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 3.093220338983051e-05, | |
| "loss": 0.703, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 3.0084745762711864e-05, | |
| "loss": 0.538, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.9237288135593223e-05, | |
| "loss": 0.6245, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.838983050847458e-05, | |
| "loss": 0.6417, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.754237288135593e-05, | |
| "loss": 0.5867, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.669491525423729e-05, | |
| "loss": 0.7802, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 2.5847457627118642e-05, | |
| "loss": 0.5801, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.6174, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.4152542372881357e-05, | |
| "loss": 0.6729, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2.3305084745762712e-05, | |
| "loss": 0.6024, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.245762711864407e-05, | |
| "loss": 0.6754, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2.1610169491525427e-05, | |
| "loss": 0.5676, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.076271186440678e-05, | |
| "loss": 0.7306, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.9915254237288135e-05, | |
| "loss": 0.8223, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.906779661016949e-05, | |
| "loss": 0.564, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7727272727272727, | |
| "eval_f1_macro": 0.7458886780518658, | |
| "eval_f1_micro": 0.7727272727272727, | |
| "eval_f1_weighted": 0.7822652521419123, | |
| "eval_loss": 0.5731395483016968, | |
| "eval_precision_macro": 0.8016726403823178, | |
| "eval_precision_micro": 0.7727272727272727, | |
| "eval_precision_weighted": 0.8294232649071358, | |
| "eval_recall_macro": 0.7444444444444445, | |
| "eval_recall_micro": 0.7727272727272727, | |
| "eval_recall_weighted": 0.7727272727272727, | |
| "eval_runtime": 3.0409, | |
| "eval_samples_per_second": 28.939, | |
| "eval_steps_per_second": 1.973, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.8220338983050846e-05, | |
| "loss": 0.671, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.7372881355932205e-05, | |
| "loss": 0.6541, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.652542372881356e-05, | |
| "loss": 0.5452, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.5677966101694916e-05, | |
| "loss": 0.5264, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.4830508474576272e-05, | |
| "loss": 0.5391, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.3983050847457627e-05, | |
| "loss": 0.4773, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.3135593220338985e-05, | |
| "loss": 0.529, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.228813559322034e-05, | |
| "loss": 0.4235, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 1.1440677966101696e-05, | |
| "loss": 0.5401, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 1.0593220338983052e-05, | |
| "loss": 0.4456, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 9.745762711864407e-06, | |
| "loss": 0.3653, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 8.898305084745763e-06, | |
| "loss": 0.4332, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 8.050847457627118e-06, | |
| "loss": 0.3547, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 7.203389830508475e-06, | |
| "loss": 0.534, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 6.3559322033898304e-06, | |
| "loss": 0.3844, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 5.508474576271187e-06, | |
| "loss": 0.4134, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 4.6610169491525425e-06, | |
| "loss": 0.5368, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 3.813559322033899e-06, | |
| "loss": 0.3829, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.9661016949152545e-06, | |
| "loss": 0.5328, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 2.11864406779661e-06, | |
| "loss": 0.2779, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 1.2711864406779662e-06, | |
| "loss": 0.3616, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.2372881355932204e-07, | |
| "loss": 0.4816, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7840909090909091, | |
| "eval_f1_macro": 0.7355182828867041, | |
| "eval_f1_micro": 0.7840909090909092, | |
| "eval_f1_weighted": 0.7828294512505038, | |
| "eval_loss": 0.5109696984291077, | |
| "eval_precision_macro": 0.7308866944925176, | |
| "eval_precision_micro": 0.7840909090909091, | |
| "eval_precision_weighted": 0.782664525741997, | |
| "eval_recall_macro": 0.7416666666666667, | |
| "eval_recall_micro": 0.7840909090909091, | |
| "eval_recall_weighted": 0.7840909090909091, | |
| "eval_runtime": 3.1235, | |
| "eval_samples_per_second": 28.173, | |
| "eval_steps_per_second": 1.921, | |
| "step": 132 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 132, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 2.8927547152603546e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |