| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 1830, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.273224043715847, | |
| "grad_norm": 1.0141575336456299, | |
| "learning_rate": 0.00019995065603657316, | |
| "loss": 1.8945, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.546448087431694, | |
| "grad_norm": 0.9003917574882507, | |
| "learning_rate": 0.00019980267284282717, | |
| "loss": 1.3737, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.819672131147541, | |
| "grad_norm": 0.855492889881134, | |
| "learning_rate": 0.00019955619646030802, | |
| "loss": 1.3506, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.092896174863388, | |
| "grad_norm": 1.1789681911468506, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 1.2946, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.366120218579235, | |
| "grad_norm": 0.9413456320762634, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 1.2914, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.639344262295082, | |
| "grad_norm": 0.8401021957397461, | |
| "learning_rate": 0.0001982287250728689, | |
| "loss": 1.2756, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.9125683060109289, | |
| "grad_norm": 0.9392536878585815, | |
| "learning_rate": 0.00019759167619387476, | |
| "loss": 1.2785, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.185792349726776, | |
| "grad_norm": 0.918136477470398, | |
| "learning_rate": 0.0001968583161128631, | |
| "loss": 1.2199, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.459016393442623, | |
| "grad_norm": 0.9809663891792297, | |
| "learning_rate": 0.0001960293685676943, | |
| "loss": 1.201, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.73224043715847, | |
| "grad_norm": 1.0254710912704468, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.1842, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0054644808743167, | |
| "grad_norm": 1.1089431047439575, | |
| "learning_rate": 0.00019408807689542257, | |
| "loss": 1.1819, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.278688524590164, | |
| "grad_norm": 1.2321062088012695, | |
| "learning_rate": 0.00019297764858882514, | |
| "loss": 1.1113, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.551912568306011, | |
| "grad_norm": 1.0911256074905396, | |
| "learning_rate": 0.00019177546256839812, | |
| "loss": 1.1212, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.8251366120218577, | |
| "grad_norm": 1.1500061750411987, | |
| "learning_rate": 0.00019048270524660196, | |
| "loss": 1.1247, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.098360655737705, | |
| "grad_norm": 1.259513258934021, | |
| "learning_rate": 0.0001891006524188368, | |
| "loss": 1.0826, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 4.371584699453552, | |
| "grad_norm": 1.377414345741272, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 1.0593, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.644808743169399, | |
| "grad_norm": 1.2397098541259766, | |
| "learning_rate": 0.0001860742027003944, | |
| "loss": 1.0414, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 4.918032786885246, | |
| "grad_norm": 1.2820392847061157, | |
| "learning_rate": 0.00018443279255020152, | |
| "loss": 1.0601, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 5.191256830601093, | |
| "grad_norm": 1.6708155870437622, | |
| "learning_rate": 0.00018270805742745617, | |
| "loss": 0.973, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 5.46448087431694, | |
| "grad_norm": 1.546794056892395, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.9904, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.737704918032787, | |
| "grad_norm": 1.437908411026001, | |
| "learning_rate": 0.00017901550123756906, | |
| "loss": 0.9863, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 6.0109289617486334, | |
| "grad_norm": 1.4555143117904663, | |
| "learning_rate": 0.00017705132427757895, | |
| "loss": 0.9768, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 6.284153005464481, | |
| "grad_norm": 1.494957447052002, | |
| "learning_rate": 0.00017501110696304596, | |
| "loss": 0.8969, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 6.557377049180328, | |
| "grad_norm": 1.4257054328918457, | |
| "learning_rate": 0.00017289686274214118, | |
| "loss": 0.9207, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 6.830601092896175, | |
| "grad_norm": 1.6431266069412231, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.9116, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 7.103825136612022, | |
| "grad_norm": 1.4786570072174072, | |
| "learning_rate": 0.00016845471059286887, | |
| "loss": 0.8975, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 7.377049180327869, | |
| "grad_norm": 1.5059996843338013, | |
| "learning_rate": 0.00016613118653236518, | |
| "loss": 0.8519, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 7.6502732240437155, | |
| "grad_norm": 1.5110268592834473, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 0.8471, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 7.923497267759563, | |
| "grad_norm": 1.6930420398712158, | |
| "learning_rate": 0.00016129070536529766, | |
| "loss": 0.8544, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 8.19672131147541, | |
| "grad_norm": 1.8286707401275635, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 0.8102, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 8.469945355191257, | |
| "grad_norm": 1.4673559665679932, | |
| "learning_rate": 0.00015620833778521307, | |
| "loss": 0.7986, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 8.743169398907105, | |
| "grad_norm": 1.6546106338500977, | |
| "learning_rate": 0.00015358267949789966, | |
| "loss": 0.7985, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 9.01639344262295, | |
| "grad_norm": 1.7138121128082275, | |
| "learning_rate": 0.00015090414157503714, | |
| "loss": 0.8194, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 9.289617486338798, | |
| "grad_norm": 1.5631183385849, | |
| "learning_rate": 0.00014817536741017152, | |
| "loss": 0.7317, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 9.562841530054644, | |
| "grad_norm": 1.936880111694336, | |
| "learning_rate": 0.00014539904997395468, | |
| "loss": 0.7479, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 9.836065573770492, | |
| "grad_norm": 1.6515196561813354, | |
| "learning_rate": 0.00014257792915650728, | |
| "loss": 0.7435, | |
| "step": 1800 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 5000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 28, | |
| "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": 3.968783346244608e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |