| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2336448598130841, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009345794392523364, | |
| "grad_norm": 3.475229024887085, | |
| "learning_rate": 1e-05, | |
| "loss": 4.7496, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009345794392523364, | |
| "eval_loss": 2.4821035861968994, | |
| "eval_runtime": 8.6429, | |
| "eval_samples_per_second": 10.413, | |
| "eval_steps_per_second": 1.388, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018691588785046728, | |
| "grad_norm": 4.237077713012695, | |
| "learning_rate": 2e-05, | |
| "loss": 4.756, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.028037383177570093, | |
| "grad_norm": 3.3195765018463135, | |
| "learning_rate": 3e-05, | |
| "loss": 4.1589, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.037383177570093455, | |
| "grad_norm": 3.983478307723999, | |
| "learning_rate": 4e-05, | |
| "loss": 3.9572, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04672897196261682, | |
| "grad_norm": 3.835078239440918, | |
| "learning_rate": 5e-05, | |
| "loss": 4.6358, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.056074766355140186, | |
| "grad_norm": 3.3207688331604004, | |
| "learning_rate": 6e-05, | |
| "loss": 4.4949, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06542056074766354, | |
| "grad_norm": 4.351305961608887, | |
| "learning_rate": 7e-05, | |
| "loss": 4.3616, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07476635514018691, | |
| "grad_norm": 4.54740571975708, | |
| "learning_rate": 8e-05, | |
| "loss": 4.5251, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08411214953271028, | |
| "grad_norm": 6.202987194061279, | |
| "learning_rate": 9e-05, | |
| "loss": 4.2042, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08411214953271028, | |
| "eval_loss": 2.0572032928466797, | |
| "eval_runtime": 8.8167, | |
| "eval_samples_per_second": 10.208, | |
| "eval_steps_per_second": 1.361, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09345794392523364, | |
| "grad_norm": 4.361314296722412, | |
| "learning_rate": 0.0001, | |
| "loss": 3.791, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.102803738317757, | |
| "grad_norm": 5.193600654602051, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 3.1392, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11214953271028037, | |
| "grad_norm": 3.730332136154175, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 3.1271, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12149532710280374, | |
| "grad_norm": 3.418407678604126, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 2.9921, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1308411214953271, | |
| "grad_norm": 3.397888660430908, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 2.4537, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.14018691588785046, | |
| "grad_norm": 3.643331289291382, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 2.1209, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": 4.123091697692871, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.7798, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1588785046728972, | |
| "grad_norm": 4.18911075592041, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 1.4373, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.16822429906542055, | |
| "grad_norm": 5.305290222167969, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.4688, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.16822429906542055, | |
| "eval_loss": 0.5362531542778015, | |
| "eval_runtime": 8.8425, | |
| "eval_samples_per_second": 10.178, | |
| "eval_steps_per_second": 1.357, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.17757009345794392, | |
| "grad_norm": 4.885643482208252, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.9024, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.18691588785046728, | |
| "grad_norm": 4.518307685852051, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.0553, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19626168224299065, | |
| "grad_norm": 3.145583391189575, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.685, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.205607476635514, | |
| "grad_norm": 2.9263885021209717, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.52, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.21495327102803738, | |
| "grad_norm": 4.0514726638793945, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 0.5227, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.22429906542056074, | |
| "grad_norm": 3.7129552364349365, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.4578, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2336448598130841, | |
| "grad_norm": 2.919783592224121, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.3577, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.63364550475776e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |