| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 51, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.058823529411764705, | |
| "grad_norm": 0.41075530648231506, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.0764, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.29411764705882354, | |
| "grad_norm": 0.31586405634880066, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 1.1671, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 0.2748248875141144, | |
| "learning_rate": 0.0001961261695938319, | |
| "loss": 1.0427, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8823529411764706, | |
| "grad_norm": 0.26047566533088684, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.0419, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.0335692167282104, | |
| "eval_runtime": 11418.6735, | |
| "eval_samples_per_second": 1.344, | |
| "eval_steps_per_second": 0.168, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 0.24954748153686523, | |
| "learning_rate": 0.0001559192903470747, | |
| "loss": 0.8987, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.4705882352941178, | |
| "grad_norm": 0.26379314064979553, | |
| "learning_rate": 0.00012419218955996676, | |
| "loss": 0.91, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.7647058823529411, | |
| "grad_norm": 0.29261425137519836, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.8637, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.0328121185302734, | |
| "eval_runtime": 11368.8822, | |
| "eval_samples_per_second": 1.35, | |
| "eval_steps_per_second": 0.169, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0588235294117645, | |
| "grad_norm": 0.44186949729919434, | |
| "learning_rate": 5.616288532109225e-05, | |
| "loss": 0.9475, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 0.3536168038845062, | |
| "learning_rate": 2.8066019966134904e-05, | |
| "loss": 0.816, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.6470588235294117, | |
| "grad_norm": 0.37321916222572327, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.815, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.9411764705882355, | |
| "grad_norm": 0.34859296679496765, | |
| "learning_rate": 2.4359497401758024e-07, | |
| "loss": 0.8198, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.0511847734451294, | |
| "eval_runtime": 11370.1779, | |
| "eval_samples_per_second": 1.35, | |
| "eval_steps_per_second": 0.169, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 51, | |
| "total_flos": 3.5859605640708096e+16, | |
| "train_loss": 0.9273478938084022, | |
| "train_runtime": 35264.3392, | |
| "train_samples_per_second": 0.012, | |
| "train_steps_per_second": 0.001 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 51, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.5859605640708096e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |