| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0033806626098715348, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001352265043948614, | |
| "grad_norm": 0.13028183579444885, | |
| "learning_rate": 1e-05, | |
| "loss": 10.367, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001352265043948614, | |
| "eval_loss": 10.374638557434082, | |
| "eval_runtime": 39.838, | |
| "eval_samples_per_second": 156.333, | |
| "eval_steps_per_second": 19.554, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002704530087897228, | |
| "grad_norm": 0.10174716264009476, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3809, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00040567951318458417, | |
| "grad_norm": 0.0866115540266037, | |
| "learning_rate": 3e-05, | |
| "loss": 10.373, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005409060175794456, | |
| "grad_norm": 0.06329571455717087, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3767, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.000676132521974307, | |
| "grad_norm": 0.10207287222146988, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3819, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008113590263691683, | |
| "grad_norm": 0.14628176391124725, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3764, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009465855307640297, | |
| "grad_norm": 0.06459755450487137, | |
| "learning_rate": 7e-05, | |
| "loss": 10.3845, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0010818120351588911, | |
| "grad_norm": 0.06547542661428452, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3759, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0012170385395537525, | |
| "grad_norm": 0.10897202789783478, | |
| "learning_rate": 9e-05, | |
| "loss": 10.378, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0012170385395537525, | |
| "eval_loss": 10.37391185760498, | |
| "eval_runtime": 41.1364, | |
| "eval_samples_per_second": 151.399, | |
| "eval_steps_per_second": 18.937, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001352265043948614, | |
| "grad_norm": 0.1761985719203949, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3579, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0014874915483434753, | |
| "grad_norm": 0.0966603010892868, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 10.3665, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0016227180527383367, | |
| "grad_norm": 0.11158464848995209, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 10.3696, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.001757944557133198, | |
| "grad_norm": 0.14970263838768005, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 10.37, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0018931710615280595, | |
| "grad_norm": 0.10012516379356384, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 10.3647, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002028397565922921, | |
| "grad_norm": 0.1887078732252121, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 10.3722, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0021636240703177823, | |
| "grad_norm": 0.1151905506849289, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 10.3691, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0022988505747126436, | |
| "grad_norm": 0.08883685618638992, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 10.3667, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.002434077079107505, | |
| "grad_norm": 0.09848842024803162, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 10.3694, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.002434077079107505, | |
| "eval_loss": 10.371732711791992, | |
| "eval_runtime": 40.9155, | |
| "eval_samples_per_second": 152.216, | |
| "eval_steps_per_second": 19.039, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0025693035835023664, | |
| "grad_norm": 0.19662371277809143, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 10.3869, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.002704530087897228, | |
| "grad_norm": 0.12802760303020477, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 10.3803, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002839756592292089, | |
| "grad_norm": 0.15228529274463654, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 10.3695, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0029749830966869506, | |
| "grad_norm": 0.09475445747375488, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 10.3693, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.003110209601081812, | |
| "grad_norm": 0.10489476472139359, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 10.364, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0032454361054766734, | |
| "grad_norm": 0.03964424505829811, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 10.3695, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0033806626098715348, | |
| "grad_norm": 0.09453272819519043, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3699, | |
| "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": 1307561164800.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |