| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.5196850393700787, | |
| "eval_steps": 10.0, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06299212598425197, | |
| "grad_norm": 2.361685037612915, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.357, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.12598425196850394, | |
| "grad_norm": 2.3121159076690674, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.3512, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1889763779527559, | |
| "grad_norm": 2.452298879623413, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.3768, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.25196850393700787, | |
| "grad_norm": 2.3367598056793213, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.361, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.31496062992125984, | |
| "grad_norm": 2.326319932937622, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.3624, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3779527559055118, | |
| "grad_norm": 2.1740145683288574, | |
| "learning_rate": 3e-06, | |
| "loss": 0.3504, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4409448818897638, | |
| "grad_norm": 2.296905279159546, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.3547, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5039370078740157, | |
| "grad_norm": 2.190321445465088, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.3387, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5669291338582677, | |
| "grad_norm": 2.1358914375305176, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.3321, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.6299212598425197, | |
| "grad_norm": 53.26506042480469, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3143, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6929133858267716, | |
| "grad_norm": 44.34261703491211, | |
| "learning_rate": 4.99847706754774e-06, | |
| "loss": 0.3209, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.7559055118110236, | |
| "grad_norm": 39.54725646972656, | |
| "learning_rate": 4.993910125649561e-06, | |
| "loss": 0.3071, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8188976377952756, | |
| "grad_norm": 9.289456367492676, | |
| "learning_rate": 4.986304738420684e-06, | |
| "loss": 0.2997, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.8818897637795275, | |
| "grad_norm": 3.2083795070648193, | |
| "learning_rate": 4.975670171853926e-06, | |
| "loss": 0.3367, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.9448818897637795, | |
| "grad_norm": 3.201711654663086, | |
| "learning_rate": 4.962019382530521e-06, | |
| "loss": 0.3471, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0078740157480315, | |
| "grad_norm": 2.9849319458007812, | |
| "learning_rate": 4.9453690018345144e-06, | |
| "loss": 0.3337, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0708661417322836, | |
| "grad_norm": 2.7130520343780518, | |
| "learning_rate": 4.925739315689991e-06, | |
| "loss": 0.3253, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.1338582677165354, | |
| "grad_norm": 2.2203686237335205, | |
| "learning_rate": 4.903154239845798e-06, | |
| "loss": 0.3085, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1968503937007875, | |
| "grad_norm": 1.8168455362319946, | |
| "learning_rate": 4.8776412907378845e-06, | |
| "loss": 0.2976, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.2598425196850394, | |
| "grad_norm": 1.3243907690048218, | |
| "learning_rate": 4.849231551964771e-06, | |
| "loss": 0.2939, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.3228346456692912, | |
| "grad_norm": 0.9819900989532471, | |
| "learning_rate": 4.817959636416969e-06, | |
| "loss": 0.2918, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.3858267716535433, | |
| "grad_norm": 0.7295715808868408, | |
| "learning_rate": 4.783863644106502e-06, | |
| "loss": 0.28, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.4488188976377954, | |
| "grad_norm": 0.6359255909919739, | |
| "learning_rate": 4.746985115747918e-06, | |
| "loss": 0.2858, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.5118110236220472, | |
| "grad_norm": 0.7184382677078247, | |
| "learning_rate": 4.707368982147318e-06, | |
| "loss": 0.2666, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.574803149606299, | |
| "grad_norm": 0.743729293346405, | |
| "learning_rate": 4.665063509461098e-06, | |
| "loss": 0.2723, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.6377952755905512, | |
| "grad_norm": 0.7132835984230042, | |
| "learning_rate": 4.620120240391065e-06, | |
| "loss": 0.274, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.7007874015748032, | |
| "grad_norm": 0.6352850198745728, | |
| "learning_rate": 4.572593931387604e-06, | |
| "loss": 0.2717, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.763779527559055, | |
| "grad_norm": 0.5060824155807495, | |
| "learning_rate": 4.522542485937369e-06, | |
| "loss": 0.2568, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.826771653543307, | |
| "grad_norm": 0.44254282116889954, | |
| "learning_rate": 4.470026884016805e-06, | |
| "loss": 0.2691, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.889763779527559, | |
| "grad_norm": 0.49223262071609497, | |
| "learning_rate": 4.415111107797445e-06, | |
| "loss": 0.2636, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.952755905511811, | |
| "grad_norm": 0.35744452476501465, | |
| "learning_rate": 4.357862063693486e-06, | |
| "loss": 0.2584, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.015748031496063, | |
| "grad_norm": 0.44493842124938965, | |
| "learning_rate": 4.2983495008466285e-06, | |
| "loss": 0.2663, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.078740157480315, | |
| "grad_norm": 0.5151119232177734, | |
| "learning_rate": 4.236645926147493e-06, | |
| "loss": 0.259, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.141732283464567, | |
| "grad_norm": 0.5001265406608582, | |
| "learning_rate": 4.172826515897146e-06, | |
| "loss": 0.2575, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.204724409448819, | |
| "grad_norm": 0.4636068344116211, | |
| "learning_rate": 4.106969024216348e-06, | |
| "loss": 0.2472, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.267716535433071, | |
| "grad_norm": 0.375308632850647, | |
| "learning_rate": 4.039153688314146e-06, | |
| "loss": 0.2495, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.3307086614173227, | |
| "grad_norm": 0.31411102414131165, | |
| "learning_rate": 3.969463130731183e-06, | |
| "loss": 0.2505, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.393700787401575, | |
| "grad_norm": 0.24844396114349365, | |
| "learning_rate": 3.897982258676867e-06, | |
| "loss": 0.2438, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.456692913385827, | |
| "grad_norm": 0.239442840218544, | |
| "learning_rate": 3.824798160583012e-06, | |
| "loss": 0.2392, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.5196850393700787, | |
| "grad_norm": 0.1867786943912506, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 0.2363, | |
| "step": 40 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.7790197780656947e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |