| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02384642899725766, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004769285799451532, | |
| "grad_norm": 0.425629585981369, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.5045, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009538571598903064, | |
| "grad_norm": 0.5127414464950562, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4964, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014307857398354596, | |
| "grad_norm": 0.8226185441017151, | |
| "learning_rate": 4.994647308096509e-05, | |
| "loss": 1.6284, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019077143197806128, | |
| "grad_norm": 0.7249281406402588, | |
| "learning_rate": 4.9786121534345265e-05, | |
| "loss": 1.5155, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002384642899725766, | |
| "grad_norm": 0.6889981627464294, | |
| "learning_rate": 4.951963201008076e-05, | |
| "loss": 1.3207, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002861571479670919, | |
| "grad_norm": 0.7409605383872986, | |
| "learning_rate": 4.914814565722671e-05, | |
| "loss": 1.5334, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0033385000596160724, | |
| "grad_norm": 0.8829396367073059, | |
| "learning_rate": 4.867325323737765e-05, | |
| "loss": 1.6189, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0038154286395612256, | |
| "grad_norm": 0.9240784049034119, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 1.2868, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004292357219506379, | |
| "grad_norm": 1.1313817501068115, | |
| "learning_rate": 4.742181853831721e-05, | |
| "loss": 1.7027, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004769285799451532, | |
| "grad_norm": 0.9213244318962097, | |
| "learning_rate": 4.665063509461097e-05, | |
| "loss": 1.2187, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005246214379396685, | |
| "grad_norm": 1.2456570863723755, | |
| "learning_rate": 4.5786740307563636e-05, | |
| "loss": 1.5233, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005723142959341838, | |
| "grad_norm": 1.2289069890975952, | |
| "learning_rate": 4.4833833507280884e-05, | |
| "loss": 1.4216, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0062000715392869915, | |
| "grad_norm": 1.204435110092163, | |
| "learning_rate": 4.379599518697444e-05, | |
| "loss": 1.4082, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006677000119232145, | |
| "grad_norm": 1.4659150838851929, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 1.3687, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007153928699177298, | |
| "grad_norm": 1.2851946353912354, | |
| "learning_rate": 4.148364537750172e-05, | |
| "loss": 1.0532, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007630857279122451, | |
| "grad_norm": 1.2946377992630005, | |
| "learning_rate": 4.021903572521802e-05, | |
| "loss": 1.8505, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008107785859067605, | |
| "grad_norm": 1.4644392728805542, | |
| "learning_rate": 3.888925582549006e-05, | |
| "loss": 1.5249, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008584714439012759, | |
| "grad_norm": 1.303274393081665, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 1.2641, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009061643018957911, | |
| "grad_norm": 1.5627962350845337, | |
| "learning_rate": 3.6057217255475034e-05, | |
| "loss": 1.4673, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009538571598903063, | |
| "grad_norm": 2.11969256401062, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 1.7425, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010015500178848218, | |
| "grad_norm": 1.8735617399215698, | |
| "learning_rate": 3.303598663257904e-05, | |
| "loss": 1.6553, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01049242875879337, | |
| "grad_norm": 2.941176176071167, | |
| "learning_rate": 3.147047612756302e-05, | |
| "loss": 2.1402, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.010969357338738524, | |
| "grad_norm": 2.47955322265625, | |
| "learning_rate": 2.9877258050403212e-05, | |
| "loss": 1.5304, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011446285918683676, | |
| "grad_norm": 2.28279185295105, | |
| "learning_rate": 2.8263154805501297e-05, | |
| "loss": 1.7279, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01192321449862883, | |
| "grad_norm": 2.429161548614502, | |
| "learning_rate": 2.663507823075358e-05, | |
| "loss": 1.3317, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012400143078573983, | |
| "grad_norm": 2.561760663986206, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.078, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.012877071658519137, | |
| "grad_norm": 2.975694179534912, | |
| "learning_rate": 2.3364921769246423e-05, | |
| "loss": 1.5784, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01335400023846429, | |
| "grad_norm": 3.220482349395752, | |
| "learning_rate": 2.173684519449872e-05, | |
| "loss": 1.7665, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.013830928818409444, | |
| "grad_norm": 2.4195404052734375, | |
| "learning_rate": 2.0122741949596797e-05, | |
| "loss": 1.2464, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.014307857398354596, | |
| "grad_norm": 3.0891129970550537, | |
| "learning_rate": 1.852952387243698e-05, | |
| "loss": 1.4323, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01478478597829975, | |
| "grad_norm": 2.1057982444763184, | |
| "learning_rate": 1.6964013367420966e-05, | |
| "loss": 1.0373, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.015261714558244903, | |
| "grad_norm": 2.6382322311401367, | |
| "learning_rate": 1.5432914190872757e-05, | |
| "loss": 1.2615, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.015738643138190057, | |
| "grad_norm": 2.989168405532837, | |
| "learning_rate": 1.3942782744524973e-05, | |
| "loss": 1.8745, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01621557171813521, | |
| "grad_norm": 2.9760780334472656, | |
| "learning_rate": 1.2500000000000006e-05, | |
| "loss": 1.4645, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.01669250029808036, | |
| "grad_norm": 3.531989336013794, | |
| "learning_rate": 1.1110744174509952e-05, | |
| "loss": 1.5544, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.017169428878025517, | |
| "grad_norm": 3.602961778640747, | |
| "learning_rate": 9.780964274781984e-06, | |
| "loss": 1.4617, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01764635745797067, | |
| "grad_norm": 2.5102806091308594, | |
| "learning_rate": 8.51635462249828e-06, | |
| "loss": 1.4198, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.018123286037915822, | |
| "grad_norm": 2.7395095825195312, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 0.8911, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.018600214617860975, | |
| "grad_norm": 2.7568724155426025, | |
| "learning_rate": 6.204004813025568e-06, | |
| "loss": 1.0436, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.019077143197806127, | |
| "grad_norm": 5.96933650970459, | |
| "learning_rate": 5.166166492719124e-06, | |
| "loss": 1.5069, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.019554071777751283, | |
| "grad_norm": 5.542440414428711, | |
| "learning_rate": 4.213259692436367e-06, | |
| "loss": 1.3813, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.020031000357696435, | |
| "grad_norm": 3.1913931369781494, | |
| "learning_rate": 3.3493649053890326e-06, | |
| "loss": 1.0923, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.020507928937641588, | |
| "grad_norm": 3.866119384765625, | |
| "learning_rate": 2.578181461682794e-06, | |
| "loss": 1.2939, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02098485751758674, | |
| "grad_norm": 5.512697696685791, | |
| "learning_rate": 1.9030116872178316e-06, | |
| "loss": 1.559, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.021461786097531896, | |
| "grad_norm": 6.1839680671691895, | |
| "learning_rate": 1.3267467626223606e-06, | |
| "loss": 1.8948, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.021938714677477048, | |
| "grad_norm": 5.496179580688477, | |
| "learning_rate": 8.51854342773295e-07, | |
| "loss": 1.1269, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0224156432574222, | |
| "grad_norm": 5.928053379058838, | |
| "learning_rate": 4.803679899192392e-07, | |
| "loss": 1.4756, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.022892571837367353, | |
| "grad_norm": 5.825471878051758, | |
| "learning_rate": 2.1387846565474045e-07, | |
| "loss": 2.1599, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.02336950041731251, | |
| "grad_norm": 8.19292163848877, | |
| "learning_rate": 5.352691903491303e-08, | |
| "loss": 1.5091, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.02384642899725766, | |
| "grad_norm": 24.69010353088379, | |
| "learning_rate": 0.0, | |
| "loss": 2.3403, | |
| "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": 3.76735278343127e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |