| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 322, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.06235385814497272, |
| "grad_norm": 2.8378232685649656, |
| "learning_rate": 2.647058823529412e-06, |
| "loss": 1.2412001609802246, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.12470771628994544, |
| "grad_norm": 0.8762135537751701, |
| "learning_rate": 4.999469537470394e-06, |
| "loss": 0.8699979782104492, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.18706157443491817, |
| "grad_norm": 0.4836418756487218, |
| "learning_rate": 4.980926975038496e-06, |
| "loss": 0.7145159721374512, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.24941543257989088, |
| "grad_norm": 0.34737489103059094, |
| "learning_rate": 4.9360859694889475e-06, |
| "loss": 0.6594952583312989, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.3117692907248636, |
| "grad_norm": 0.3248913787557038, |
| "learning_rate": 4.8654218466357066e-06, |
| "loss": 0.6338988780975342, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.37412314886983633, |
| "grad_norm": 0.3057344284199567, |
| "learning_rate": 4.769683663760191e-06, |
| "loss": 0.6172263622283936, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.436477007014809, |
| "grad_norm": 0.27974403893537925, |
| "learning_rate": 4.649886269417746e-06, |
| "loss": 0.6062547206878662, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.49883086515978176, |
| "grad_norm": 0.29419857739584604, |
| "learning_rate": 4.5072995457905e-06, |
| "loss": 0.5965761184692383, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.5611847233047544, |
| "grad_norm": 0.3315097892502634, |
| "learning_rate": 4.343434947620316e-06, |
| "loss": 0.5886905670166016, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.6235385814497272, |
| "grad_norm": 0.29457997182754686, |
| "learning_rate": 4.16002948041253e-06, |
| "loss": 0.5835968017578125, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.6858924395946999, |
| "grad_norm": 0.2961032395207699, |
| "learning_rate": 3.959027287745471e-06, |
| "loss": 0.5788020133972168, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.7482462977396727, |
| "grad_norm": 0.2861101583812986, |
| "learning_rate": 3.742559042864895e-06, |
| "loss": 0.576852560043335, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.8106001558846454, |
| "grad_norm": 0.30075876518989825, |
| "learning_rate": 3.512919363017516e-06, |
| "loss": 0.5731847286224365, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.872954014029618, |
| "grad_norm": 0.2862002560829977, |
| "learning_rate": 3.272542485937369e-06, |
| "loss": 0.5680032253265381, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.9353078721745908, |
| "grad_norm": 0.29591355092903865, |
| "learning_rate": 3.0239764663202565e-06, |
| "loss": 0.5663919448852539, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.9976617303195635, |
| "grad_norm": 0.30412448408621034, |
| "learning_rate": 2.769856165810093e-06, |
| "loss": 0.5666703224182129, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.0561184723304755, |
| "grad_norm": 0.2855511685504785, |
| "learning_rate": 2.512875322810002e-06, |
| "loss": 0.5529036521911621, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.1184723304754483, |
| "grad_norm": 0.28088042333413643, |
| "learning_rate": 2.255757998185122e-06, |
| "loss": 0.551942777633667, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.1808261886204208, |
| "grad_norm": 0.27014969679808054, |
| "learning_rate": 2.0012296995397614e-06, |
| "loss": 0.5491605281829834, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.2431800467653935, |
| "grad_norm": 0.28059722291490846, |
| "learning_rate": 1.7519884901587773e-06, |
| "loss": 0.5495306968688964, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.3055339049103662, |
| "grad_norm": 0.268731731444306, |
| "learning_rate": 1.510676388865548e-06, |
| "loss": 0.5463069915771485, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.367887763055339, |
| "grad_norm": 0.262829824311781, |
| "learning_rate": 1.279851363965193e-06, |
| "loss": 0.5458571434020996, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.4302416212003117, |
| "grad_norm": 0.25986917239644325, |
| "learning_rate": 1.061960218144185e-06, |
| "loss": 0.5471982002258301, |
| "step": 230 |
| }, |
| { |
| "epoch": 1.4925954793452845, |
| "grad_norm": 0.25512421886468045, |
| "learning_rate": 8.593126517531869e-07, |
| "loss": 0.5447581768035888, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.5549493374902572, |
| "grad_norm": 0.25745753669693194, |
| "learning_rate": 6.740567794087463e-07, |
| "loss": 0.5431301116943359, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.61730319563523, |
| "grad_norm": 0.2515604469266137, |
| "learning_rate": 5.081563594439676e-07, |
| "loss": 0.5456439971923828, |
| "step": 260 |
| }, |
| { |
| "epoch": 1.6796570537802027, |
| "grad_norm": 0.25486096680241016, |
| "learning_rate": 3.6336997758166263e-07, |
| "loss": 0.5440835952758789, |
| "step": 270 |
| }, |
| { |
| "epoch": 1.7420109119251754, |
| "grad_norm": 0.25238227445189154, |
| "learning_rate": 2.4123240548819955e-07, |
| "loss": 0.5446696758270264, |
| "step": 280 |
| }, |
| { |
| "epoch": 1.8043647700701482, |
| "grad_norm": 0.24139019174598875, |
| "learning_rate": 1.430383318120318e-07, |
| "loss": 0.5432592391967773, |
| "step": 290 |
| }, |
| { |
| "epoch": 1.866718628215121, |
| "grad_norm": 0.24370412027300914, |
| "learning_rate": 6.982863816194785e-08, |
| "loss": 0.5458236694335937, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.9290724863600937, |
| "grad_norm": 0.2510086708172434, |
| "learning_rate": 2.2379365503074902e-08, |
| "loss": 0.5443175315856934, |
| "step": 310 |
| }, |
| { |
| "epoch": 1.9914263445050664, |
| "grad_norm": 0.24824891638561147, |
| "learning_rate": 1.1934879295905089e-09, |
| "loss": 0.5439374446868896, |
| "step": 320 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 322, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.4797956798899814e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
