| { | |
| "best_metric": 1.311687707901001, | |
| "best_model_checkpoint": "./output/checkpoints/2024-06-11_13-53-54/checkpoint-10", | |
| "epoch": 0.5555555555555556, | |
| "eval_steps": 1, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 1.9413901567459106, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 3.544, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05555555555555555, | |
| "eval_loss": 3.981394052505493, | |
| "eval_runtime": 12.5428, | |
| "eval_samples_per_second": 11.401, | |
| "eval_steps_per_second": 0.718, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 2.0220563411712646, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 3.6373, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "eval_loss": 3.788512706756592, | |
| "eval_runtime": 12.6976, | |
| "eval_samples_per_second": 11.262, | |
| "eval_steps_per_second": 0.709, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 1.90468430519104, | |
| "learning_rate": 0.0002, | |
| "loss": 3.3119, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "eval_loss": 3.026510238647461, | |
| "eval_runtime": 12.655, | |
| "eval_samples_per_second": 11.3, | |
| "eval_steps_per_second": 0.711, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 2.224761724472046, | |
| "learning_rate": 0.0002666666666666667, | |
| "loss": 2.5408, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "eval_loss": 2.1147303581237793, | |
| "eval_runtime": 12.7118, | |
| "eval_samples_per_second": 11.249, | |
| "eval_steps_per_second": 0.708, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2777777777777778, | |
| "grad_norm": 1.1557661294937134, | |
| "learning_rate": 0.0003333333333333334, | |
| "loss": 1.7003, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2777777777777778, | |
| "eval_loss": 1.702366590499878, | |
| "eval_runtime": 12.7156, | |
| "eval_samples_per_second": 11.246, | |
| "eval_steps_per_second": 0.708, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 1.0826658010482788, | |
| "learning_rate": 0.0004, | |
| "loss": 1.3464, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "eval_loss": 1.4100245237350464, | |
| "eval_runtime": 12.7488, | |
| "eval_samples_per_second": 11.217, | |
| "eval_steps_per_second": 0.706, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3888888888888889, | |
| "grad_norm": 0.7294781804084778, | |
| "learning_rate": 0.0003916666666666667, | |
| "loss": 1.0757, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3888888888888889, | |
| "eval_loss": 1.2797588109970093, | |
| "eval_runtime": 12.7015, | |
| "eval_samples_per_second": 11.259, | |
| "eval_steps_per_second": 0.709, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.6977319121360779, | |
| "learning_rate": 0.00038333333333333334, | |
| "loss": 0.9387, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "eval_loss": 1.233304738998413, | |
| "eval_runtime": 12.7924, | |
| "eval_samples_per_second": 11.179, | |
| "eval_steps_per_second": 0.704, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.25461432337760925, | |
| "learning_rate": 0.000375, | |
| "loss": 0.8435, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.256897211074829, | |
| "eval_runtime": 12.7345, | |
| "eval_samples_per_second": 11.229, | |
| "eval_steps_per_second": 0.707, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 0.20771068334579468, | |
| "learning_rate": 0.00036666666666666667, | |
| "loss": 0.7791, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "eval_loss": 1.311687707901001, | |
| "eval_runtime": 12.7288, | |
| "eval_samples_per_second": 11.234, | |
| "eval_steps_per_second": 0.707, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 54, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3708922028359680.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |