| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.031877590054191905, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000637551801083838, | |
| "eval_loss": 6.481906890869141, | |
| "eval_runtime": 27.6478, | |
| "eval_samples_per_second": 23.908, | |
| "eval_steps_per_second": 11.972, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0031877590054191903, | |
| "grad_norm": 3.5302960872650146, | |
| "learning_rate": 5e-05, | |
| "loss": 5.9171, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006375518010838381, | |
| "grad_norm": 4.611023902893066, | |
| "learning_rate": 0.0001, | |
| "loss": 5.6593, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006375518010838381, | |
| "eval_loss": 5.287916660308838, | |
| "eval_runtime": 27.76, | |
| "eval_samples_per_second": 23.811, | |
| "eval_steps_per_second": 11.924, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00956327701625757, | |
| "grad_norm": 3.617624521255493, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.4434, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012751036021676761, | |
| "grad_norm": 3.097682237625122, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.4766, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012751036021676761, | |
| "eval_loss": 1.6980737447738647, | |
| "eval_runtime": 27.9695, | |
| "eval_samples_per_second": 23.633, | |
| "eval_steps_per_second": 11.834, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015938795027095953, | |
| "grad_norm": 1.8768608570098877, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.1672, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01912655403251514, | |
| "grad_norm": 4.387115478515625, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9074, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01912655403251514, | |
| "eval_loss": 0.7665236592292786, | |
| "eval_runtime": 28.2746, | |
| "eval_samples_per_second": 23.378, | |
| "eval_steps_per_second": 11.707, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02231431303793433, | |
| "grad_norm": 4.801900863647461, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.7456, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.025502072043353523, | |
| "grad_norm": 3.009931802749634, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.6117, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.025502072043353523, | |
| "eval_loss": 0.5591135025024414, | |
| "eval_runtime": 28.2394, | |
| "eval_samples_per_second": 23.407, | |
| "eval_steps_per_second": 11.721, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.028689831048772714, | |
| "grad_norm": 3.0482630729675293, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5022, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.031877590054191905, | |
| "grad_norm": 2.471957206726074, | |
| "learning_rate": 0.0, | |
| "loss": 0.6596, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.031877590054191905, | |
| "eval_loss": 0.5317168831825256, | |
| "eval_runtime": 27.6971, | |
| "eval_samples_per_second": 23.865, | |
| "eval_steps_per_second": 11.951, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4858788340039680.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |