| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.99660441426146, | |
| "eval_steps": 50, | |
| "global_step": 294, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2187, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1481, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1437, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1076, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1066, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.1555328369140625, | |
| "eval_runtime": 15.6804, | |
| "eval_samples_per_second": 16.709, | |
| "eval_steps_per_second": 4.209, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0988, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0917, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1344, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1167, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0655, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.133277177810669, | |
| "eval_runtime": 15.7203, | |
| "eval_samples_per_second": 16.666, | |
| "eval_steps_per_second": 4.198, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0595, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1085, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0945, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0726, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3e-05, | |
| "loss": 1.039, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 1.1278975009918213, | |
| "eval_runtime": 15.7982, | |
| "eval_samples_per_second": 16.584, | |
| "eval_steps_per_second": 4.178, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3e-05, | |
| "loss": 0.9891, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0617, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3e-05, | |
| "loss": 0.98, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3e-05, | |
| "loss": 0.9531, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0166, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 1.1301459074020386, | |
| "eval_runtime": 15.7471, | |
| "eval_samples_per_second": 16.638, | |
| "eval_steps_per_second": 4.191, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 3e-05, | |
| "loss": 0.9869, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 3e-05, | |
| "loss": 0.9066, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 3e-05, | |
| "loss": 0.9884, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 3e-05, | |
| "loss": 0.9885, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0281, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 1.1312241554260254, | |
| "eval_runtime": 15.6611, | |
| "eval_samples_per_second": 16.729, | |
| "eval_steps_per_second": 4.214, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 3e-05, | |
| "loss": 0.9723, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0428, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 3e-05, | |
| "loss": 0.961, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 3e-05, | |
| "loss": 0.9311, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 294, | |
| "total_flos": 7.002531209517466e+16, | |
| "train_loss": 1.0460824836679057, | |
| "train_runtime": 890.7293, | |
| "train_samples_per_second": 5.29, | |
| "train_steps_per_second": 0.33 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 294, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 250, | |
| "total_flos": 7.002531209517466e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |