| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.5772870662460567, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07886435331230283, | |
| "grad_norm": 0.04835394397377968, | |
| "learning_rate": 0.0002, | |
| "loss": 0.66, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15772870662460567, | |
| "grad_norm": 0.0558183453977108, | |
| "learning_rate": 0.0001996405260481014, | |
| "loss": 0.4766, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.23659305993690852, | |
| "grad_norm": 0.049051981419324875, | |
| "learning_rate": 0.00019856468862284752, | |
| "loss": 0.4494, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.31545741324921134, | |
| "grad_norm": 0.05015840008854866, | |
| "learning_rate": 0.00019678022243485544, | |
| "loss": 0.4443, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3943217665615142, | |
| "grad_norm": 0.04640612378716469, | |
| "learning_rate": 0.0001942999568663777, | |
| "loss": 0.4342, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.47318611987381703, | |
| "grad_norm": 0.046447452157735825, | |
| "learning_rate": 0.00019114172373472754, | |
| "loss": 0.4287, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5520504731861199, | |
| "grad_norm": 0.0452335923910141, | |
| "learning_rate": 0.0001873282290908019, | |
| "loss": 0.4267, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.6309148264984227, | |
| "grad_norm": 0.046432506293058395, | |
| "learning_rate": 0.00018288688997440474, | |
| "loss": 0.4235, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.7097791798107256, | |
| "grad_norm": 0.5536419749259949, | |
| "learning_rate": 0.00017784963730001395, | |
| "loss": 0.4187, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.7886435331230284, | |
| "grad_norm": 0.05094370245933533, | |
| "learning_rate": 0.00017225268629014097, | |
| "loss": 0.4134, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8675078864353313, | |
| "grad_norm": 0.04656651243567467, | |
| "learning_rate": 0.0001661362761067479, | |
| "loss": 0.4123, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.9463722397476341, | |
| "grad_norm": 0.05060403794050217, | |
| "learning_rate": 0.0001595443805526358, | |
| "loss": 0.4106, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.025236593059937, | |
| "grad_norm": 0.04831027239561081, | |
| "learning_rate": 0.00015252439192271156, | |
| "loss": 0.4029, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.1041009463722398, | |
| "grad_norm": 0.04964866116642952, | |
| "learning_rate": 0.00014512678027807672, | |
| "loss": 0.3935, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.1829652996845426, | |
| "grad_norm": 0.04785332828760147, | |
| "learning_rate": 0.00013740473059258154, | |
| "loss": 0.3945, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.2618296529968454, | |
| "grad_norm": 0.04986065253615379, | |
| "learning_rate": 0.00012941376038057, | |
| "loss": 0.3911, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.3406940063091484, | |
| "grad_norm": 0.05081675201654434, | |
| "learning_rate": 0.00012121132055487441, | |
| "loss": 0.3914, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.4195583596214512, | |
| "grad_norm": 0.04923517629504204, | |
| "learning_rate": 0.00011285638238468185, | |
| "loss": 0.3898, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.498422712933754, | |
| "grad_norm": 0.051097236573696136, | |
| "learning_rate": 0.0001044090135228305, | |
| "loss": 0.3937, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.5772870662460567, | |
| "grad_norm": 0.04983523488044739, | |
| "learning_rate": 9.59299461506786e-05, | |
| "loss": 0.3867, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1902, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.8433222543081472e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |