| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04432951606944958, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014776505356483192, | |
| "eval_loss": 2.284550189971924, | |
| "eval_runtime": 8.0244, | |
| "eval_samples_per_second": 35.517, | |
| "eval_steps_per_second": 17.821, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004432951606944958, | |
| "grad_norm": 1.086187481880188, | |
| "learning_rate": 6e-05, | |
| "loss": 2.246, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008865903213889916, | |
| "grad_norm": 0.9703373908996582, | |
| "learning_rate": 0.00012, | |
| "loss": 2.3058, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011821204285186553, | |
| "eval_loss": 2.1647727489471436, | |
| "eval_runtime": 6.9073, | |
| "eval_samples_per_second": 41.261, | |
| "eval_steps_per_second": 20.703, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.013298854820834873, | |
| "grad_norm": 1.1059170961380005, | |
| "learning_rate": 0.00018, | |
| "loss": 2.2392, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01773180642777983, | |
| "grad_norm": 0.8991310596466064, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.0468, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02216475803472479, | |
| "grad_norm": 1.0070017576217651, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.9515, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.023642408570373107, | |
| "eval_loss": 1.9984503984451294, | |
| "eval_runtime": 6.9326, | |
| "eval_samples_per_second": 41.11, | |
| "eval_steps_per_second": 20.627, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.026597709641669746, | |
| "grad_norm": 1.078281044960022, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.9955, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.031030661248614703, | |
| "grad_norm": 1.1806660890579224, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 2.0976, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03546361285555966, | |
| "grad_norm": 0.9979068040847778, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.9791, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03546361285555966, | |
| "eval_loss": 1.9604854583740234, | |
| "eval_runtime": 6.975, | |
| "eval_samples_per_second": 40.86, | |
| "eval_steps_per_second": 20.502, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03989656446250462, | |
| "grad_norm": 0.8984552621841431, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.9597, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04432951606944958, | |
| "grad_norm": 1.0433257818222046, | |
| "learning_rate": 0.0, | |
| "loss": 1.9852, | |
| "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": 1959403255234560.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |