| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006135596686777789, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00020451988955925963, | |
| "eval_loss": 2.9672646522521973, | |
| "eval_runtime": 119.9875, | |
| "eval_samples_per_second": 17.16, | |
| "eval_steps_per_second": 8.584, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006135596686777789, | |
| "grad_norm": 1.9726237058639526, | |
| "learning_rate": 6e-05, | |
| "loss": 2.9998, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012271193373555578, | |
| "grad_norm": 1.8343898057937622, | |
| "learning_rate": 0.00012, | |
| "loss": 2.7213, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001636159116474077, | |
| "eval_loss": 2.016875743865967, | |
| "eval_runtime": 118.5221, | |
| "eval_samples_per_second": 17.372, | |
| "eval_steps_per_second": 8.69, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0018406790060333368, | |
| "grad_norm": 2.3590292930603027, | |
| "learning_rate": 0.00018, | |
| "loss": 2.1701, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0024542386747111156, | |
| "grad_norm": 3.2550463676452637, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.7727, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0030677983433888946, | |
| "grad_norm": 1.5403249263763428, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.6086, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003272318232948154, | |
| "eval_loss": 1.582494854927063, | |
| "eval_runtime": 118.746, | |
| "eval_samples_per_second": 17.34, | |
| "eval_steps_per_second": 8.674, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0036813580120666736, | |
| "grad_norm": 1.3476464748382568, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.5991, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004294917680744453, | |
| "grad_norm": 1.2860835790634155, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.6035, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004908477349422231, | |
| "grad_norm": 0.9298802018165588, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.4711, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004908477349422231, | |
| "eval_loss": 1.4861472845077515, | |
| "eval_runtime": 118.7708, | |
| "eval_samples_per_second": 17.336, | |
| "eval_steps_per_second": 8.672, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00552203701810001, | |
| "grad_norm": 0.967008113861084, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.4728, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.006135596686777789, | |
| "grad_norm": 0.8883606791496277, | |
| "learning_rate": 0.0, | |
| "loss": 1.5213, | |
| "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": 1.112830925340672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |