| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0057665969869530745, | |
| "eval_steps": 8, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002883298493476537, | |
| "eval_loss": 0.9093815684318542, | |
| "eval_runtime": 601.5686, | |
| "eval_samples_per_second": 2.429, | |
| "eval_steps_per_second": 1.215, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008649895480429612, | |
| "grad_norm": 0.12690412998199463, | |
| "learning_rate": 6e-05, | |
| "loss": 0.9101, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017299790960859224, | |
| "grad_norm": 0.15323787927627563, | |
| "learning_rate": 0.00012, | |
| "loss": 0.9108, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0023066387947812297, | |
| "eval_loss": 0.849568247795105, | |
| "eval_runtime": 604.868, | |
| "eval_samples_per_second": 2.415, | |
| "eval_steps_per_second": 1.209, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0025949686441288835, | |
| "grad_norm": 0.15457145869731903, | |
| "learning_rate": 0.00018, | |
| "loss": 0.797, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003459958192171845, | |
| "grad_norm": 0.20491334795951843, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.8331, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004324947740214806, | |
| "grad_norm": 0.12307419627904892, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.7014, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0046132775895624594, | |
| "eval_loss": 0.8008375763893127, | |
| "eval_runtime": 604.8687, | |
| "eval_samples_per_second": 2.415, | |
| "eval_steps_per_second": 1.209, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.005189937288257767, | |
| "grad_norm": 0.12751135230064392, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.7943, | |
| "step": 18 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.5391158788096e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |