| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0028457598178713715, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.485866059571239e-05, | |
| "eval_loss": 2.0251216888427734, | |
| "eval_runtime": 590.5467, | |
| "eval_samples_per_second": 7.517, | |
| "eval_steps_per_second": 3.759, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002845759817871372, | |
| "grad_norm": 1.0840997695922852, | |
| "learning_rate": 6e-05, | |
| "loss": 8.2191, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005691519635742744, | |
| "grad_norm": 1.3751399517059326, | |
| "learning_rate": 0.00012, | |
| "loss": 8.1301, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0007588692847656991, | |
| "eval_loss": 1.998409390449524, | |
| "eval_runtime": 593.9309, | |
| "eval_samples_per_second": 7.474, | |
| "eval_steps_per_second": 3.738, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0008537279453614115, | |
| "grad_norm": 1.1846058368682861, | |
| "learning_rate": 0.00018, | |
| "loss": 7.8298, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0011383039271485487, | |
| "grad_norm": 1.4545332193374634, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 7.8597, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0014228799089356858, | |
| "grad_norm": 2.626171588897705, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 7.6925, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0015177385695313982, | |
| "eval_loss": 1.9730610847473145, | |
| "eval_runtime": 593.7554, | |
| "eval_samples_per_second": 7.476, | |
| "eval_steps_per_second": 3.739, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.001707455890722823, | |
| "grad_norm": 1.7820730209350586, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 8.0833, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00199203187250996, | |
| "grad_norm": 1.590713381767273, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 7.7832, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0022766078542970974, | |
| "grad_norm": 1.3463406562805176, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 7.818, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0022766078542970974, | |
| "eval_loss": 1.9619874954223633, | |
| "eval_runtime": 593.4359, | |
| "eval_samples_per_second": 7.48, | |
| "eval_steps_per_second": 3.741, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0025611838360842347, | |
| "grad_norm": 2.008699893951416, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 7.8812, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0028457598178713715, | |
| "grad_norm": 1.3208942413330078, | |
| "learning_rate": 0.0, | |
| "loss": 7.648, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.870524102947635e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |