| { | |
| "best_metric": 0.5903987884521484, | |
| "best_model_checkpoint": "mikhail-panzo/zlm_b64_le5_s8000/checkpoint-500", | |
| "epoch": 0.418848167539267, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.041884816753926704, | |
| "grad_norm": 11.218673706054688, | |
| "learning_rate": 2.4500000000000004e-07, | |
| "loss": 1.1196, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08376963350785341, | |
| "grad_norm": 5.423076629638672, | |
| "learning_rate": 4.95e-07, | |
| "loss": 1.057, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1256544502617801, | |
| "grad_norm": 12.713382720947266, | |
| "learning_rate": 7.4e-07, | |
| "loss": 1.0037, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16753926701570682, | |
| "grad_norm": 4.434875965118408, | |
| "learning_rate": 9.9e-07, | |
| "loss": 0.9381, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2094240837696335, | |
| "grad_norm": 3.668553590774536, | |
| "learning_rate": 1.2400000000000002e-06, | |
| "loss": 0.8591, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2513089005235602, | |
| "grad_norm": 2.2456483840942383, | |
| "learning_rate": 1.4900000000000001e-06, | |
| "loss": 0.8262, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2931937172774869, | |
| "grad_norm": 2.70170259475708, | |
| "learning_rate": 1.74e-06, | |
| "loss": 0.7634, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.33507853403141363, | |
| "grad_norm": 2.9946064949035645, | |
| "learning_rate": 1.9900000000000004e-06, | |
| "loss": 0.7336, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3769633507853403, | |
| "grad_norm": 2.2950398921966553, | |
| "learning_rate": 2.24e-06, | |
| "loss": 0.7121, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.418848167539267, | |
| "grad_norm": 8.007049560546875, | |
| "learning_rate": 2.4900000000000003e-06, | |
| "loss": 0.6879, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.418848167539267, | |
| "eval_loss": 0.5903987884521484, | |
| "eval_runtime": 258.509, | |
| "eval_samples_per_second": 32.838, | |
| "eval_steps_per_second": 4.108, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 8000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4446942197892480.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |