| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013667270304438445, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00027334540608876893, | |
| "grad_norm": 2.645862579345703, | |
| "learning_rate": 0.0001, | |
| "loss": 3.5105, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005466908121775379, | |
| "grad_norm": 2.7776503562927246, | |
| "learning_rate": 0.0002, | |
| "loss": 3.5309, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008200362182663067, | |
| "grad_norm": 2.1925506591796875, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 3.4837, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010933816243550757, | |
| "grad_norm": 3.864365816116333, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 3.2885, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013667270304438446, | |
| "grad_norm": 5.210112571716309, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 3.3298, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016400724365326135, | |
| "grad_norm": 5.999921798706055, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 3.2051, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0019134178426213825, | |
| "grad_norm": 2.344972610473633, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 3.1307, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0021867632487101514, | |
| "grad_norm": 4.505224704742432, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 3.1204, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0024601086547989203, | |
| "grad_norm": 2.0425589084625244, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 3.1676, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002733454060887689, | |
| "grad_norm": 2.171025514602661, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 3.1685, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003006799466976458, | |
| "grad_norm": 1.8206102848052979, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 3.2054, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003280144873065227, | |
| "grad_norm": 3.115173578262329, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 3.0901, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003553490279153996, | |
| "grad_norm": 2.3207244873046875, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 3.1466, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003826835685242765, | |
| "grad_norm": 1.6254884004592896, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 3.119, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004100181091331534, | |
| "grad_norm": 2.3601272106170654, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 3.1694, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004373526497420303, | |
| "grad_norm": 4.06917667388916, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 3.1329, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004646871903509072, | |
| "grad_norm": 1.795824646949768, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 3.0947, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004920217309597841, | |
| "grad_norm": 3.6463279724121094, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 3.1758, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0051935627156866095, | |
| "grad_norm": 4.634830474853516, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 3.1705, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005466908121775378, | |
| "grad_norm": 2.260582208633423, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 3.1013, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005740253527864147, | |
| "grad_norm": 1.818834900856018, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 3.0837, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006013598933952916, | |
| "grad_norm": 1.466182827949524, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 3.1803, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006286944340041685, | |
| "grad_norm": 1.1497867107391357, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 3.1041, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006560289746130454, | |
| "grad_norm": 1.677706003189087, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 3.1547, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006833635152219223, | |
| "grad_norm": 1.8140803575515747, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 3.1356, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007106980558307992, | |
| "grad_norm": 0.9289854168891907, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0933, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0073803259643967604, | |
| "grad_norm": 1.1718719005584717, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 3.101, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00765367137048553, | |
| "grad_norm": 0.9577802419662476, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 3.1211, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.007927016776574298, | |
| "grad_norm": 1.1697319746017456, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 3.1352, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008200362182663068, | |
| "grad_norm": 1.2574468851089478, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 3.0314, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008473707588751836, | |
| "grad_norm": 1.2412081956863403, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 3.0771, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.008747052994840606, | |
| "grad_norm": 0.9908276200294495, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 3.1798, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.009020398400929374, | |
| "grad_norm": 1.9833407402038574, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 3.1328, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009293743807018143, | |
| "grad_norm": 1.302556037902832, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 3.1284, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009567089213106911, | |
| "grad_norm": 1.1386475563049316, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 3.0847, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009840434619195681, | |
| "grad_norm": 1.1478960514068604, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 3.1663, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.010113780025284451, | |
| "grad_norm": 1.2641170024871826, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 3.0924, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.010387125431373219, | |
| "grad_norm": 1.2993226051330566, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 3.0908, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.010660470837461989, | |
| "grad_norm": 0.7408443689346313, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 3.1104, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.010933816243550757, | |
| "grad_norm": 1.1869138479232788, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 3.0775, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011207161649639526, | |
| "grad_norm": 1.3214056491851807, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 3.0865, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.011480507055728294, | |
| "grad_norm": 1.411237359046936, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 3.0958, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.011753852461817064, | |
| "grad_norm": 1.0202186107635498, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 3.1997, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.012027197867905832, | |
| "grad_norm": 1.3209668397903442, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 3.0356, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.012300543273994602, | |
| "grad_norm": 0.9961850047111511, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 3.1217, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01257388868008337, | |
| "grad_norm": 1.1770366430282593, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 3.1282, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.01284723408617214, | |
| "grad_norm": 1.0524556636810303, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 3.1751, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.013120579492260908, | |
| "grad_norm": 0.8674744367599487, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 3.0894, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.013393924898349677, | |
| "grad_norm": 1.242981195449829, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 3.0561, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.013667270304438445, | |
| "grad_norm": 1.4760891199111938, | |
| "learning_rate": 0.0, | |
| "loss": 3.0578, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.688115974465126e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |