| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 20, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9626, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7551, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6737, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5923, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_f1": 0.2973817897616256, | |
| "eval_loss": 0.6075014472007751, | |
| "eval_runtime": 2.0329, | |
| "eval_samples_per_second": 464.848, | |
| "eval_steps_per_second": 14.757, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5935, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6499, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5639, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6694, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_f1": 0.2973817897616256, | |
| "eval_loss": 0.5937851071357727, | |
| "eval_runtime": 2.0028, | |
| "eval_samples_per_second": 471.842, | |
| "eval_steps_per_second": 14.979, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5923, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6133, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5702, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5225, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.3024223872822884, | |
| "eval_loss": 0.534581184387207, | |
| "eval_runtime": 2.0063, | |
| "eval_samples_per_second": 471.005, | |
| "eval_steps_per_second": 14.953, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4961, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4879, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5475, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5458, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_f1": 0.4681950604946577, | |
| "eval_loss": 0.5171502828598022, | |
| "eval_runtime": 2.0079, | |
| "eval_samples_per_second": 470.651, | |
| "eval_steps_per_second": 14.941, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5224, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5344, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4791, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5052, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_f1": 0.43614802647951817, | |
| "eval_loss": 0.5550346970558167, | |
| "eval_runtime": 2.0143, | |
| "eval_samples_per_second": 469.148, | |
| "eval_steps_per_second": 14.894, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5821, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4842, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4613, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3689, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.4394838882203503, | |
| "eval_loss": 0.5187910795211792, | |
| "eval_runtime": 2.0147, | |
| "eval_samples_per_second": 469.048, | |
| "eval_steps_per_second": 14.89, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4172, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4645, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4628, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4097, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "eval_f1": 0.4676343432076015, | |
| "eval_loss": 0.4918379485607147, | |
| "eval_runtime": 2.021, | |
| "eval_samples_per_second": 467.58, | |
| "eval_steps_per_second": 14.844, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4716, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4947, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4288, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4904, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_f1": 0.4640191084468284, | |
| "eval_loss": 0.4755867123603821, | |
| "eval_runtime": 2.0186, | |
| "eval_samples_per_second": 468.144, | |
| "eval_steps_per_second": 14.862, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4391, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 2e-05, | |
| "loss": 0.408, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4724, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3696, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_f1": 0.46883968839688395, | |
| "eval_loss": 0.47884294390678406, | |
| "eval_runtime": 2.0223, | |
| "eval_samples_per_second": 467.285, | |
| "eval_steps_per_second": 14.834, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4094, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4162, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3975, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3631, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "eval_f1": 0.4735017608176137, | |
| "eval_loss": 0.4751051366329193, | |
| "eval_runtime": 2.0238, | |
| "eval_samples_per_second": 466.941, | |
| "eval_steps_per_second": 14.824, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3953, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3781, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4447, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4345, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "eval_f1": 0.4796518931606489, | |
| "eval_loss": 0.4609261453151703, | |
| "eval_runtime": 2.0228, | |
| "eval_samples_per_second": 467.18, | |
| "eval_steps_per_second": 14.831, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3724, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 2e-05, | |
| "loss": 0.366, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3763, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3398, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_f1": 0.5672850456534463, | |
| "eval_loss": 0.46373221278190613, | |
| "eval_runtime": 2.0191, | |
| "eval_samples_per_second": 468.022, | |
| "eval_steps_per_second": 14.858, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3861, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 2e-05, | |
| "loss": 0.315, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3501, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2985, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "eval_f1": 0.5091622097836045, | |
| "eval_loss": 0.4849531948566437, | |
| "eval_runtime": 2.0286, | |
| "eval_samples_per_second": 465.831, | |
| "eval_steps_per_second": 14.788, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3734, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3658, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3268, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3248, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "eval_f1": 0.6056820231448513, | |
| "eval_loss": 0.508940577507019, | |
| "eval_runtime": 2.0241, | |
| "eval_samples_per_second": 466.871, | |
| "eval_steps_per_second": 14.821, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3573, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3298, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2909, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3323, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_f1": 0.6159893659893659, | |
| "eval_loss": 0.46433570981025696, | |
| "eval_runtime": 2.0165, | |
| "eval_samples_per_second": 468.623, | |
| "eval_steps_per_second": 14.877, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 300, | |
| "total_flos": 9950949458472960.0, | |
| "train_loss": 0.4641021112600962, | |
| "train_runtime": 274.9964, | |
| "train_samples_per_second": 137.529, | |
| "train_steps_per_second": 1.091 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 300, | |
| "num_train_epochs": 5, | |
| "save_steps": 20, | |
| "total_flos": 9950949458472960.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |