| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.018, | |
| "eval_steps": 1000, | |
| "global_step": 45, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 2.3598, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 2.1113, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0719, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019793814432989693, | |
| "loss": 2.1789, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019587628865979381, | |
| "loss": 1.9318, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019381443298969073, | |
| "loss": 2.4083, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019175257731958765, | |
| "loss": 2.6823, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00018969072164948454, | |
| "loss": 1.5946, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00018762886597938145, | |
| "loss": 2.0224, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00018556701030927837, | |
| "loss": 2.0527, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00018350515463917526, | |
| "loss": 1.8021, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00018144329896907217, | |
| "loss": 2.0241, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001793814432989691, | |
| "loss": 1.8196, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00017731958762886598, | |
| "loss": 1.8936, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001752577319587629, | |
| "loss": 1.797, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001731958762886598, | |
| "loss": 1.5366, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001711340206185567, | |
| "loss": 1.7419, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00016907216494845361, | |
| "loss": 2.5421, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00016701030927835053, | |
| "loss": 1.5245, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00016494845360824742, | |
| "loss": 1.9081, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00016288659793814434, | |
| "loss": 1.9725, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00016082474226804125, | |
| "loss": 1.8649, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00015876288659793814, | |
| "loss": 1.5654, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00015670103092783506, | |
| "loss": 1.8573, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00015463917525773197, | |
| "loss": 1.6624, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00015257731958762886, | |
| "loss": 1.95, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00015051546391752578, | |
| "loss": 1.5541, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001484536082474227, | |
| "loss": 1.4851, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00014639175257731958, | |
| "loss": 1.6751, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001443298969072165, | |
| "loss": 1.5637, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00014226804123711342, | |
| "loss": 1.6947, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001402061855670103, | |
| "loss": 1.363, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00013814432989690722, | |
| "loss": 2.0642, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00013608247422680414, | |
| "loss": 1.5458, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00013402061855670103, | |
| "loss": 1.8339, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00013195876288659794, | |
| "loss": 1.6049, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00012989690721649486, | |
| "loss": 1.5555, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00012783505154639175, | |
| "loss": 1.5485, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00012577319587628866, | |
| "loss": 2.0987, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00012371134020618558, | |
| "loss": 1.4402, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00012164948453608247, | |
| "loss": 1.4069, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00011958762886597938, | |
| "loss": 1.5902, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001175257731958763, | |
| "loss": 1.8907, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00011546391752577319, | |
| "loss": 1.6717, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001134020618556701, | |
| "loss": 1.8157, | |
| "step": 45 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "total_flos": 5322104911872000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |