| { | |
| "best_metric": 3.224152088165283, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.08503401360544217, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017006802721088435, | |
| "grad_norm": 0.24977613985538483, | |
| "learning_rate": 1e-05, | |
| "loss": 2.8692, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017006802721088435, | |
| "eval_loss": 3.276529550552368, | |
| "eval_runtime": 37.2906, | |
| "eval_samples_per_second": 26.548, | |
| "eval_steps_per_second": 6.65, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003401360544217687, | |
| "grad_norm": 0.24531881511211395, | |
| "learning_rate": 2e-05, | |
| "loss": 3.0437, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00510204081632653, | |
| "grad_norm": 0.25416088104248047, | |
| "learning_rate": 3e-05, | |
| "loss": 3.0804, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006802721088435374, | |
| "grad_norm": 0.24987466633319855, | |
| "learning_rate": 4e-05, | |
| "loss": 3.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008503401360544218, | |
| "grad_norm": 0.2428084909915924, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9788, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01020408163265306, | |
| "grad_norm": 0.24101322889328003, | |
| "learning_rate": 6e-05, | |
| "loss": 2.8507, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011904761904761904, | |
| "grad_norm": 0.2492375373840332, | |
| "learning_rate": 7e-05, | |
| "loss": 3.0046, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013605442176870748, | |
| "grad_norm": 0.2558836340904236, | |
| "learning_rate": 8e-05, | |
| "loss": 3.0009, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015306122448979591, | |
| "grad_norm": 0.2605135142803192, | |
| "learning_rate": 9e-05, | |
| "loss": 3.0991, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.017006802721088437, | |
| "grad_norm": 0.24015140533447266, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8682, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01870748299319728, | |
| "grad_norm": 0.23625339567661285, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 2.9808, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02040816326530612, | |
| "grad_norm": 0.2354581356048584, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 3.0725, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.022108843537414966, | |
| "grad_norm": 0.23762401938438416, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 3.191, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.023809523809523808, | |
| "grad_norm": 0.22220423817634583, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 2.852, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.025510204081632654, | |
| "grad_norm": 0.2376808524131775, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 2.9857, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.027210884353741496, | |
| "grad_norm": 0.2597469091415405, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 3.2452, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02891156462585034, | |
| "grad_norm": 0.25804516673088074, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 3.2068, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.030612244897959183, | |
| "grad_norm": 0.2507534325122833, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 3.0956, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03231292517006803, | |
| "grad_norm": 0.2603234648704529, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 3.1878, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.034013605442176874, | |
| "grad_norm": 0.2637031078338623, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 3.2389, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03571428571428571, | |
| "grad_norm": 0.2582753896713257, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 3.0519, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03741496598639456, | |
| "grad_norm": 0.2699371576309204, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 3.1635, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0391156462585034, | |
| "grad_norm": 0.2730785310268402, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 3.1656, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04081632653061224, | |
| "grad_norm": 0.2866193652153015, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 3.22, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04251700680272109, | |
| "grad_norm": 0.28086575865745544, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 2.948, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04421768707482993, | |
| "grad_norm": 0.2861677408218384, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 3.2173, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04591836734693878, | |
| "grad_norm": 0.2805924713611603, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 3.0343, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.047619047619047616, | |
| "grad_norm": 0.3162534832954407, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 3.313, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04931972789115646, | |
| "grad_norm": 0.3136957287788391, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 3.244, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05102040816326531, | |
| "grad_norm": 0.31942903995513916, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 3.2875, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05272108843537415, | |
| "grad_norm": 0.33962124586105347, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 3.3639, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05442176870748299, | |
| "grad_norm": 0.3294471502304077, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 3.3009, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.05612244897959184, | |
| "grad_norm": 0.3405294418334961, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 3.3337, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05782312925170068, | |
| "grad_norm": 0.33866071701049805, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 3.3841, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.05952380952380952, | |
| "grad_norm": 0.40185490250587463, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 3.3815, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.061224489795918366, | |
| "grad_norm": 0.351744145154953, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 3.2629, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06292517006802721, | |
| "grad_norm": 0.36549699306488037, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 3.3077, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06462585034013606, | |
| "grad_norm": 0.3804144263267517, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 3.2124, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0663265306122449, | |
| "grad_norm": 0.3786104917526245, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 3.3519, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06802721088435375, | |
| "grad_norm": 0.3824675381183624, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 3.344, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06972789115646258, | |
| "grad_norm": 0.40192821621894836, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 3.197, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07142857142857142, | |
| "grad_norm": 0.3984317183494568, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 3.1668, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07312925170068027, | |
| "grad_norm": 0.4219413697719574, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 3.3366, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07482993197278912, | |
| "grad_norm": 0.5630561709403992, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 3.2803, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07653061224489796, | |
| "grad_norm": 0.5532132387161255, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 3.2889, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0782312925170068, | |
| "grad_norm": 0.46265870332717896, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 3.2862, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07993197278911565, | |
| "grad_norm": 0.5097538828849792, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 3.4773, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": 0.6026643514633179, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 3.3722, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08333333333333333, | |
| "grad_norm": 0.5687397718429565, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 3.5381, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.08503401360544217, | |
| "grad_norm": 0.596480667591095, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 3.6079, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08503401360544217, | |
| "eval_loss": 3.224152088165283, | |
| "eval_runtime": 37.6501, | |
| "eval_samples_per_second": 26.295, | |
| "eval_steps_per_second": 6.587, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.755333512921088e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |