| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0015035521419353222, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.011840473117741e-05, | |
| "eval_loss": 1.7433751821517944, | |
| "eval_runtime": 798.1059, | |
| "eval_samples_per_second": 10.527, | |
| "eval_steps_per_second": 5.264, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001503552141935322, | |
| "grad_norm": 0.7051569223403931, | |
| "learning_rate": 4e-05, | |
| "loss": 1.7238, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00025059202365588704, | |
| "eval_loss": 1.7182985544204712, | |
| "eval_runtime": 980.8154, | |
| "eval_samples_per_second": 8.566, | |
| "eval_steps_per_second": 4.283, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0003007104283870644, | |
| "grad_norm": 0.5998827219009399, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7971, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00045106564258059665, | |
| "grad_norm": 0.7146555185317993, | |
| "learning_rate": 0.00012, | |
| "loss": 1.6488, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005011840473117741, | |
| "eval_loss": 1.5570807456970215, | |
| "eval_runtime": 1711.2302, | |
| "eval_samples_per_second": 4.91, | |
| "eval_steps_per_second": 2.455, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006014208567741288, | |
| "grad_norm": 0.7070504426956177, | |
| "learning_rate": 0.00016, | |
| "loss": 1.5998, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0007517760709676611, | |
| "grad_norm": 0.8788482546806335, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3757, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0007517760709676611, | |
| "eval_loss": 1.420298457145691, | |
| "eval_runtime": 1710.5609, | |
| "eval_samples_per_second": 4.912, | |
| "eval_steps_per_second": 2.456, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0009021312851611933, | |
| "grad_norm": 0.6857808232307434, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.5791, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0010023680946235482, | |
| "eval_loss": 1.332275629043579, | |
| "eval_runtime": 1712.161, | |
| "eval_samples_per_second": 4.907, | |
| "eval_steps_per_second": 2.454, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0010524864993547256, | |
| "grad_norm": 0.6557658314704895, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.3637, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0012028417135482577, | |
| "grad_norm": 0.5096169114112854, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.5006, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.001252960118279435, | |
| "eval_loss": 1.3074328899383545, | |
| "eval_runtime": 1248.175, | |
| "eval_samples_per_second": 6.731, | |
| "eval_steps_per_second": 3.366, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00135319692774179, | |
| "grad_norm": 0.603471040725708, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.2413, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0015035521419353222, | |
| "grad_norm": 0.6203583478927612, | |
| "learning_rate": 0.0, | |
| "loss": 1.2903, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0015035521419353222, | |
| "eval_loss": 1.299818515777588, | |
| "eval_runtime": 802.6314, | |
| "eval_samples_per_second": 10.468, | |
| "eval_steps_per_second": 5.234, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 15, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2704819730972672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |