| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04296455424274973, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008592910848549946, | |
| "eval_loss": 1.3909448385238647, | |
| "eval_runtime": 65.7879, | |
| "eval_samples_per_second": 7.448, | |
| "eval_steps_per_second": 3.724, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004296455424274973, | |
| "grad_norm": 2.6328206062316895, | |
| "learning_rate": 5e-05, | |
| "loss": 5.5519, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008592910848549946, | |
| "grad_norm": 3.101144552230835, | |
| "learning_rate": 0.0001, | |
| "loss": 4.9161, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008592910848549946, | |
| "eval_loss": 1.120683193206787, | |
| "eval_runtime": 66.0908, | |
| "eval_samples_per_second": 7.414, | |
| "eval_steps_per_second": 3.707, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01288936627282492, | |
| "grad_norm": 3.134380340576172, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.3361, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017185821697099892, | |
| "grad_norm": 3.8679518699645996, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.8005, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017185821697099892, | |
| "eval_loss": 0.9374167919158936, | |
| "eval_runtime": 66.1551, | |
| "eval_samples_per_second": 7.407, | |
| "eval_steps_per_second": 3.703, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021482277121374866, | |
| "grad_norm": 2.0213584899902344, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.6081, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02577873254564984, | |
| "grad_norm": 2.136101245880127, | |
| "learning_rate": 5e-05, | |
| "loss": 3.6723, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02577873254564984, | |
| "eval_loss": 0.8661292791366577, | |
| "eval_runtime": 66.1436, | |
| "eval_samples_per_second": 7.408, | |
| "eval_steps_per_second": 3.704, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03007518796992481, | |
| "grad_norm": 2.4233875274658203, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.6811, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.034371643394199784, | |
| "grad_norm": 2.935652256011963, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.3253, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.034371643394199784, | |
| "eval_loss": 0.8391368985176086, | |
| "eval_runtime": 66.1741, | |
| "eval_samples_per_second": 7.405, | |
| "eval_steps_per_second": 3.702, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03866809881847476, | |
| "grad_norm": 2.1004343032836914, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.1562, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04296455424274973, | |
| "grad_norm": 4.1379780769348145, | |
| "learning_rate": 0.0, | |
| "loss": 3.3475, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04296455424274973, | |
| "eval_loss": 0.8348293900489807, | |
| "eval_runtime": 66.1244, | |
| "eval_samples_per_second": 7.41, | |
| "eval_steps_per_second": 3.705, | |
| "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": 1.3071542905276416e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |