| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.031421838177533384, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003142183817753339, | |
| "grad_norm": 3.8331856727600098, | |
| "learning_rate": 2e-05, | |
| "loss": 4.167, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003142183817753339, | |
| "eval_loss": 3.2862348556518555, | |
| "eval_runtime": 2.0395, | |
| "eval_samples_per_second": 65.702, | |
| "eval_steps_per_second": 32.851, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006284367635506678, | |
| "grad_norm": 3.0576670169830322, | |
| "learning_rate": 4e-05, | |
| "loss": 2.7491, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009426551453260016, | |
| "grad_norm": 2.4550366401672363, | |
| "learning_rate": 6e-05, | |
| "loss": 3.2705, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009426551453260016, | |
| "eval_loss": 3.274832248687744, | |
| "eval_runtime": 1.6386, | |
| "eval_samples_per_second": 81.779, | |
| "eval_steps_per_second": 40.89, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012568735271013355, | |
| "grad_norm": 3.5279064178466797, | |
| "learning_rate": 8e-05, | |
| "loss": 3.5556, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.015710919088766692, | |
| "grad_norm": 3.25341534614563, | |
| "learning_rate": 0.0001, | |
| "loss": 2.9788, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.018853102906520033, | |
| "grad_norm": 3.9964559078216553, | |
| "learning_rate": 0.00012, | |
| "loss": 3.5072, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.018853102906520033, | |
| "eval_loss": 3.111999034881592, | |
| "eval_runtime": 1.6486, | |
| "eval_samples_per_second": 81.283, | |
| "eval_steps_per_second": 40.642, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02199528672427337, | |
| "grad_norm": 3.7447142601013184, | |
| "learning_rate": 0.00014, | |
| "loss": 3.744, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02513747054202671, | |
| "grad_norm": 4.777510643005371, | |
| "learning_rate": 0.00016, | |
| "loss": 3.124, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.028279654359780047, | |
| "grad_norm": 3.521242141723633, | |
| "learning_rate": 0.00018, | |
| "loss": 2.6551, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.028279654359780047, | |
| "eval_loss": 2.5918915271759033, | |
| "eval_runtime": 1.7015, | |
| "eval_samples_per_second": 78.752, | |
| "eval_steps_per_second": 39.376, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.031421838177533384, | |
| "grad_norm": 4.041660308837891, | |
| "learning_rate": 0.0002, | |
| "loss": 2.7496, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 240545515438080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |