| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.11726078799249531, | |
| "eval_steps": 500, | |
| "global_step": 3000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003908692933083177, | |
| "grad_norm": 0.47716134786605835, | |
| "learning_rate": 4.98240400406663e-05, | |
| "loss": 1.3868, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.007817385866166354, | |
| "grad_norm": 0.28900113701820374, | |
| "learning_rate": 4.9628528974739973e-05, | |
| "loss": 1.3348, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01172607879924953, | |
| "grad_norm": 0.37652796506881714, | |
| "learning_rate": 4.943301790881364e-05, | |
| "loss": 1.3298, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.015634771732332707, | |
| "grad_norm": 0.24992702901363373, | |
| "learning_rate": 4.923750684288731e-05, | |
| "loss": 1.3309, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.019543464665415886, | |
| "grad_norm": 0.3237004280090332, | |
| "learning_rate": 4.904199577696098e-05, | |
| "loss": 1.3228, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.02345215759849906, | |
| "grad_norm": 0.259011447429657, | |
| "learning_rate": 4.884648471103465e-05, | |
| "loss": 1.3166, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.02736085053158224, | |
| "grad_norm": 0.34121841192245483, | |
| "learning_rate": 4.8650973645108314e-05, | |
| "loss": 1.3145, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.031269543464665414, | |
| "grad_norm": 0.41398781538009644, | |
| "learning_rate": 4.845546257918198e-05, | |
| "loss": 1.3081, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.03517823639774859, | |
| "grad_norm": 0.4289904832839966, | |
| "learning_rate": 4.825995151325565e-05, | |
| "loss": 1.3073, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.03908692933083177, | |
| "grad_norm": 0.21226634085178375, | |
| "learning_rate": 4.8064440447329324e-05, | |
| "loss": 1.3057, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.04299562226391495, | |
| "grad_norm": 0.2929254174232483, | |
| "learning_rate": 4.786892938140299e-05, | |
| "loss": 1.3034, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.04690431519699812, | |
| "grad_norm": 0.22025109827518463, | |
| "learning_rate": 4.767341831547666e-05, | |
| "loss": 1.3048, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.0508130081300813, | |
| "grad_norm": 0.36455097794532776, | |
| "learning_rate": 4.747790724955033e-05, | |
| "loss": 1.3028, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.05472170106316448, | |
| "grad_norm": 0.24527208507061005, | |
| "learning_rate": 4.728239618362399e-05, | |
| "loss": 1.2996, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.05863039399624766, | |
| "grad_norm": 0.33187615871429443, | |
| "learning_rate": 4.7086885117697664e-05, | |
| "loss": 1.3001, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.06253908692933083, | |
| "grad_norm": 0.502117931842804, | |
| "learning_rate": 4.689137405177133e-05, | |
| "loss": 1.2954, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.06644777986241401, | |
| "grad_norm": 0.289112389087677, | |
| "learning_rate": 4.6695862985845e-05, | |
| "loss": 1.2969, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.07035647279549719, | |
| "grad_norm": 0.24350133538246155, | |
| "learning_rate": 4.6500351919918674e-05, | |
| "loss": 1.2929, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.07426516572858036, | |
| "grad_norm": 0.2194579690694809, | |
| "learning_rate": 4.630484085399234e-05, | |
| "loss": 1.2913, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.07817385866166354, | |
| "grad_norm": 0.3578532636165619, | |
| "learning_rate": 4.6109329788066005e-05, | |
| "loss": 1.2946, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.08208255159474671, | |
| "grad_norm": 0.22988037765026093, | |
| "learning_rate": 4.591381872213967e-05, | |
| "loss": 1.2906, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.0859912445278299, | |
| "grad_norm": 0.44038262963294983, | |
| "learning_rate": 4.571830765621334e-05, | |
| "loss": 1.2941, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.08989993746091307, | |
| "grad_norm": 0.27333030104637146, | |
| "learning_rate": 4.5522796590287015e-05, | |
| "loss": 1.2903, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.09380863039399624, | |
| "grad_norm": 0.23196421563625336, | |
| "learning_rate": 4.532728552436068e-05, | |
| "loss": 1.2897, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.09771732332707943, | |
| "grad_norm": 0.25054216384887695, | |
| "learning_rate": 4.513177445843435e-05, | |
| "loss": 1.2891, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.1016260162601626, | |
| "grad_norm": 0.17129705846309662, | |
| "learning_rate": 4.493626339250802e-05, | |
| "loss": 1.2874, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.10553470919324578, | |
| "grad_norm": 0.5260087251663208, | |
| "learning_rate": 4.474075232658168e-05, | |
| "loss": 1.289, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.10944340212632896, | |
| "grad_norm": 0.2251499593257904, | |
| "learning_rate": 4.4545241260655355e-05, | |
| "loss": 1.2882, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.11335209505941213, | |
| "grad_norm": 0.24193763732910156, | |
| "learning_rate": 4.434973019472902e-05, | |
| "loss": 1.2886, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.11726078799249531, | |
| "grad_norm": 0.2361423224210739, | |
| "learning_rate": 4.415421912880269e-05, | |
| "loss": 1.2863, | |
| "step": 3000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 25584, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 8389279088640000.0, | |
| "train_batch_size": 48, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |