| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.01008064516129, |
| "eval_steps": 25, |
| "global_step": 63, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.03, |
| "learning_rate": 5e-05, |
| "loss": 4.2505, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.03, |
| "eval_loss": 4.052073955535889, |
| "eval_runtime": 60.4806, |
| "eval_samples_per_second": 4.134, |
| "eval_steps_per_second": 4.134, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 0.0001, |
| "loss": 4.2141, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.00015, |
| "loss": 4.0033, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 0.0002, |
| "loss": 3.9023, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.00025, |
| "loss": 4.0955, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.0003, |
| "loss": 3.8902, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.00035, |
| "loss": 3.9076, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.0004, |
| "loss": 3.7008, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.00045000000000000004, |
| "loss": 3.7071, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.0005, |
| "loss": 3.6304, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.0004999782204181027, |
| "loss": 3.6851, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.0004999128854672123, |
| "loss": 3.4864, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.000499804006531072, |
| "loss": 3.3743, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.0004996516025803834, |
| "loss": 3.2944, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 0.0004994557001695014, |
| "loss": 3.1978, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.0004992163334318065, |
| "loss": 3.0865, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 0.0004989335440737586, |
| "loss": 3.0893, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 0.0004986073813676296, |
| "loss": 2.9218, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 0.0004982379021429183, |
| "loss": 2.8753, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 0.0004978251707764492, |
| "loss": 2.7118, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 0.0004973692591811548, |
| "loss": 2.6693, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 0.0004968702467935468, |
| "loss": 2.474, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 0.0004963282205598744, |
| "loss": 2.3912, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 0.0004957432749209755, |
| "loss": 2.2401, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 0.0004951155117958217, |
| "loss": 2.1461, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.81, |
| "eval_loss": 2.080416202545166, |
| "eval_runtime": 61.4527, |
| "eval_samples_per_second": 4.068, |
| "eval_steps_per_second": 4.068, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 0.0004944450405637602, |
| "loss": 2.1114, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 0.0004937319780454559, |
| "loss": 1.8994, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 0.0004929764484825369, |
| "loss": 2.0342, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 0.0004921785835159472, |
| "loss": 2.0333, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 0.0004913385221630097, |
| "loss": 1.8424, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.0004904564107932048, |
| "loss": 1.7993, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 0.000489532403102667, |
| "loss": 1.7643, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 0.0004885666600874058, |
| "loss": 1.8718, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 0.00048755935001525374, |
| "loss": 1.7178, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 0.0004865106483965487, |
| "loss": 1.7185, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.14, |
| "learning_rate": 0.0004854207379535529, |
| "loss": 1.7702, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.17, |
| "learning_rate": 0.00048428980858861636, |
| "loss": 1.7089, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.2, |
| "learning_rate": 0.00048311805735108893, |
| "loss": 1.6515, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.24, |
| "learning_rate": 0.000481905688402987, |
| "loss": 1.7014, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.27, |
| "learning_rate": 0.0004806529129834207, |
| "loss": 1.5697, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.3, |
| "learning_rate": 0.0004793599493717891, |
| "loss": 1.6295, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.33, |
| "learning_rate": 0.00047802702284974695, |
| "loss": 1.4599, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.36, |
| "learning_rate": 0.0004766543656619532, |
| "loss": 1.5082, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 0.00047524221697560476, |
| "loss": 1.4499, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.43, |
| "learning_rate": 0.00047379082283876563, |
| "loss": 1.432, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.46, |
| "learning_rate": 0.0004723004361374953, |
| "loss": 1.4362, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.49, |
| "learning_rate": 0.0004707713165517877, |
| "loss": 1.4588, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.53, |
| "learning_rate": 0.0004692037305103247, |
| "loss": 1.4489, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.56, |
| "learning_rate": 0.0004675979511440549, |
| "loss": 1.3382, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.59, |
| "learning_rate": 0.00046595425823860404, |
| "loss": 1.3896, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.59, |
| "eval_loss": 1.4752908945083618, |
| "eval_runtime": 61.5879, |
| "eval_samples_per_second": 4.059, |
| "eval_steps_per_second": 4.059, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.62, |
| "learning_rate": 0.0004642729381855262, |
| "loss": 1.3671, |
| "step": 51 |
| }, |
| { |
| "epoch": 1.66, |
| "learning_rate": 0.0004625542839324036, |
| "loss": 1.3629, |
| "step": 52 |
| }, |
| { |
| "epoch": 1.69, |
| "learning_rate": 0.00046079859493180467, |
| "loss": 1.3171, |
| "step": 53 |
| }, |
| { |
| "epoch": 1.72, |
| "learning_rate": 0.00045900617708910854, |
| "loss": 1.4639, |
| "step": 54 |
| }, |
| { |
| "epoch": 1.75, |
| "learning_rate": 0.0004571773427092047, |
| "loss": 1.3031, |
| "step": 55 |
| }, |
| { |
| "epoch": 1.78, |
| "learning_rate": 0.00045531241044207836, |
| "loss": 1.3329, |
| "step": 56 |
| }, |
| { |
| "epoch": 1.82, |
| "learning_rate": 0.00045341170522729, |
| "loss": 1.3298, |
| "step": 57 |
| }, |
| { |
| "epoch": 1.85, |
| "learning_rate": 0.00045147555823735875, |
| "loss": 1.3794, |
| "step": 58 |
| }, |
| { |
| "epoch": 1.88, |
| "learning_rate": 0.00044950430682005996, |
| "loss": 1.3068, |
| "step": 59 |
| }, |
| { |
| "epoch": 1.91, |
| "learning_rate": 0.00044749829443964704, |
| "loss": 1.3701, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.95, |
| "learning_rate": 0.0004454578706170075, |
| "loss": 1.2326, |
| "step": 61 |
| }, |
| { |
| "epoch": 1.98, |
| "learning_rate": 0.0004433833908687633, |
| "loss": 1.1632, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.01, |
| "learning_rate": 0.00044127521664532704, |
| "loss": 1.3177, |
| "step": 63 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 248, |
| "num_train_epochs": 8, |
| "save_steps": 500, |
| "total_flos": 8.266246254074266e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
