| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.2244039270687237, | |
| "eval_steps": 100, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11220196353436185, | |
| "grad_norm": 1.1029870510101318, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5659, | |
| "mean_token_accuracy": 0.47926636449992654, | |
| "num_tokens": 37367.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2244039270687237, | |
| "grad_norm": 2.981795310974121, | |
| "learning_rate": 0.00010555555555555557, | |
| "loss": 2.0395, | |
| "mean_token_accuracy": 0.5484138417989015, | |
| "num_tokens": 73517.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.33660589060308554, | |
| "grad_norm": 0.5173138976097107, | |
| "learning_rate": 0.0001611111111111111, | |
| "loss": 1.5375, | |
| "mean_token_accuracy": 0.6410307548940182, | |
| "num_tokens": 109542.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4488078541374474, | |
| "grad_norm": 0.4973823130130768, | |
| "learning_rate": 0.000198125, | |
| "loss": 1.481, | |
| "mean_token_accuracy": 0.6483925141394138, | |
| "num_tokens": 145327.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5610098176718092, | |
| "grad_norm": 0.605583131313324, | |
| "learning_rate": 0.00019187500000000002, | |
| "loss": 1.3906, | |
| "mean_token_accuracy": 0.661427416652441, | |
| "num_tokens": 180932.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6732117812061711, | |
| "grad_norm": 0.5373088717460632, | |
| "learning_rate": 0.000185625, | |
| "loss": 1.3255, | |
| "mean_token_accuracy": 0.669424007833004, | |
| "num_tokens": 217215.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7854137447405329, | |
| "grad_norm": 0.5484739542007446, | |
| "learning_rate": 0.000179375, | |
| "loss": 1.315, | |
| "mean_token_accuracy": 0.6726369611918926, | |
| "num_tokens": 254200.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.8976157082748948, | |
| "grad_norm": 0.5383081436157227, | |
| "learning_rate": 0.000173125, | |
| "loss": 1.2989, | |
| "mean_token_accuracy": 0.6707686208188534, | |
| "num_tokens": 290771.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 2.1042652130126953, | |
| "learning_rate": 0.000166875, | |
| "loss": 1.353, | |
| "mean_token_accuracy": 0.6659621212580432, | |
| "num_tokens": 323338.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.1122019635343618, | |
| "grad_norm": 0.5776804089546204, | |
| "learning_rate": 0.00016062500000000001, | |
| "loss": 1.2447, | |
| "mean_token_accuracy": 0.6804150842130184, | |
| "num_tokens": 360543.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.2244039270687237, | |
| "grad_norm": 0.6110250949859619, | |
| "learning_rate": 0.000154375, | |
| "loss": 1.2908, | |
| "mean_token_accuracy": 0.6726092718541622, | |
| "num_tokens": 397295.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.3366058906030855, | |
| "grad_norm": 0.5095610022544861, | |
| "learning_rate": 0.000148125, | |
| "loss": 1.2549, | |
| "mean_token_accuracy": 0.6794664606451988, | |
| "num_tokens": 434747.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.4488078541374474, | |
| "grad_norm": 0.6921575665473938, | |
| "learning_rate": 0.000141875, | |
| "loss": 1.2156, | |
| "mean_token_accuracy": 0.6838382914662361, | |
| "num_tokens": 471034.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.5610098176718092, | |
| "grad_norm": 0.6114996075630188, | |
| "learning_rate": 0.000135625, | |
| "loss": 1.2229, | |
| "mean_token_accuracy": 0.6844779521226882, | |
| "num_tokens": 507771.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.673211781206171, | |
| "grad_norm": 0.7110440731048584, | |
| "learning_rate": 0.00012937500000000001, | |
| "loss": 1.1964, | |
| "mean_token_accuracy": 0.6940846800804138, | |
| "num_tokens": 543317.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.785413744740533, | |
| "grad_norm": 0.6362674236297607, | |
| "learning_rate": 0.000123125, | |
| "loss": 1.2173, | |
| "mean_token_accuracy": 0.6877869322896004, | |
| "num_tokens": 579484.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.8976157082748948, | |
| "grad_norm": 0.5968947410583496, | |
| "learning_rate": 0.000116875, | |
| "loss": 1.1781, | |
| "mean_token_accuracy": 0.6954927623271943, | |
| "num_tokens": 614929.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 2.4199445247650146, | |
| "learning_rate": 0.000110625, | |
| "loss": 1.1646, | |
| "mean_token_accuracy": 0.6967783880560365, | |
| "num_tokens": 646676.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.112201963534362, | |
| "grad_norm": 0.7061767578125, | |
| "learning_rate": 0.000104375, | |
| "loss": 1.1006, | |
| "mean_token_accuracy": 0.7113809175789356, | |
| "num_tokens": 682566.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.2244039270687237, | |
| "grad_norm": 0.7149446606636047, | |
| "learning_rate": 9.8125e-05, | |
| "loss": 1.1557, | |
| "mean_token_accuracy": 0.6986343055963516, | |
| "num_tokens": 719538.0, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 356, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.372741136474112e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |