| { | |
| "best_metric": 2.0446817874908447, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 2.6229508196721314, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05245901639344262, | |
| "grad_norm": 59.75578308105469, | |
| "learning_rate": 5e-05, | |
| "loss": 69.1845, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05245901639344262, | |
| "eval_loss": 2.3756308555603027, | |
| "eval_runtime": 4.6962, | |
| "eval_samples_per_second": 10.647, | |
| "eval_steps_per_second": 2.768, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.10491803278688525, | |
| "grad_norm": 70.11760711669922, | |
| "learning_rate": 0.0001, | |
| "loss": 72.285, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.15737704918032788, | |
| "grad_norm": 40.28403091430664, | |
| "learning_rate": 9.992920667580176e-05, | |
| "loss": 70.4757, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2098360655737705, | |
| "grad_norm": 50.93065643310547, | |
| "learning_rate": 9.971704944519594e-05, | |
| "loss": 72.0046, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.26229508196721313, | |
| "grad_norm": 67.84244537353516, | |
| "learning_rate": 9.936419583332062e-05, | |
| "loss": 72.9162, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.31475409836065577, | |
| "grad_norm": 39.244895935058594, | |
| "learning_rate": 9.887175604818206e-05, | |
| "loss": 67.498, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.36721311475409835, | |
| "grad_norm": 24.89311408996582, | |
| "learning_rate": 9.82412794875295e-05, | |
| "loss": 67.2244, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.419672131147541, | |
| "grad_norm": 27.440900802612305, | |
| "learning_rate": 9.747474986387654e-05, | |
| "loss": 69.4707, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4721311475409836, | |
| "grad_norm": 32.1877326965332, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 70.6535, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5245901639344263, | |
| "grad_norm": 54.610347747802734, | |
| "learning_rate": 9.554359905560886e-05, | |
| "loss": 69.8398, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5770491803278689, | |
| "grad_norm": 19.549211502075195, | |
| "learning_rate": 9.438505398589392e-05, | |
| "loss": 66.0735, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6295081967213115, | |
| "grad_norm": 21.11090850830078, | |
| "learning_rate": 9.310258896527278e-05, | |
| "loss": 68.2764, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6819672131147541, | |
| "grad_norm": 19.177579879760742, | |
| "learning_rate": 9.17002391031667e-05, | |
| "loss": 68.0621, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7344262295081967, | |
| "grad_norm": 21.684904098510742, | |
| "learning_rate": 9.018241671106134e-05, | |
| "loss": 69.1158, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7868852459016393, | |
| "grad_norm": 25.838293075561523, | |
| "learning_rate": 8.855389741974244e-05, | |
| "loss": 64.8987, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.839344262295082, | |
| "grad_norm": 16.683151245117188, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 66.7402, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8918032786885246, | |
| "grad_norm": 16.149255752563477, | |
| "learning_rate": 8.498559600784018e-05, | |
| "loss": 67.3468, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.9442622950819672, | |
| "grad_norm": 17.375782012939453, | |
| "learning_rate": 8.305704108364301e-05, | |
| "loss": 66.6194, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.9967213114754099, | |
| "grad_norm": 26.16300392150879, | |
| "learning_rate": 8.104020832809127e-05, | |
| "loss": 69.7571, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.0491803278688525, | |
| "grad_norm": 15.187979698181152, | |
| "learning_rate": 7.894144344319014e-05, | |
| "loss": 63.0399, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.1016393442622952, | |
| "grad_norm": 15.76618480682373, | |
| "learning_rate": 7.67673499197358e-05, | |
| "loss": 63.5516, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.1540983606557378, | |
| "grad_norm": 15.865626335144043, | |
| "learning_rate": 7.452476826029011e-05, | |
| "loss": 63.0109, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.2065573770491804, | |
| "grad_norm": 19.105836868286133, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 64.563, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.2590163934426228, | |
| "grad_norm": 27.65399932861328, | |
| "learning_rate": 6.986255778798253e-05, | |
| "loss": 63.8715, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.3114754098360657, | |
| "grad_norm": 17.719682693481445, | |
| "learning_rate": 6.745759801411822e-05, | |
| "loss": 62.3019, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.3114754098360657, | |
| "eval_loss": 2.0446817874908447, | |
| "eval_runtime": 4.7446, | |
| "eval_samples_per_second": 10.538, | |
| "eval_steps_per_second": 2.74, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.3639344262295081, | |
| "grad_norm": 15.636397361755371, | |
| "learning_rate": 6.501344202803414e-05, | |
| "loss": 61.7672, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.4163934426229507, | |
| "grad_norm": 15.895488739013672, | |
| "learning_rate": 6.253778004871315e-05, | |
| "loss": 62.7228, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.4688524590163934, | |
| "grad_norm": 19.06943702697754, | |
| "learning_rate": 6.003840142464886e-05, | |
| "loss": 64.0609, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.521311475409836, | |
| "grad_norm": 24.51659393310547, | |
| "learning_rate": 5.752317012567363e-05, | |
| "loss": 61.7292, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.5737704918032787, | |
| "grad_norm": 16.205303192138672, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 60.9363, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.6262295081967213, | |
| "grad_norm": 17.461999893188477, | |
| "learning_rate": 5.247682987432637e-05, | |
| "loss": 62.4749, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.678688524590164, | |
| "grad_norm": 17.851083755493164, | |
| "learning_rate": 4.9961598575351155e-05, | |
| "loss": 61.79, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.7311475409836066, | |
| "grad_norm": 20.22283172607422, | |
| "learning_rate": 4.7462219951286867e-05, | |
| "loss": 64.521, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.7836065573770492, | |
| "grad_norm": 28.108795166015625, | |
| "learning_rate": 4.498655797196586e-05, | |
| "loss": 61.2715, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.8360655737704918, | |
| "grad_norm": 18.37066078186035, | |
| "learning_rate": 4.2542401985881784e-05, | |
| "loss": 61.7881, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.8885245901639345, | |
| "grad_norm": 18.368694305419922, | |
| "learning_rate": 4.01374422120175e-05, | |
| "loss": 62.2249, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.940983606557377, | |
| "grad_norm": 18.627840042114258, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 62.6981, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.9934426229508198, | |
| "grad_norm": 22.907976150512695, | |
| "learning_rate": 3.547523173970989e-05, | |
| "loss": 64.4813, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.045901639344262, | |
| "grad_norm": 21.854839324951172, | |
| "learning_rate": 3.323265008026421e-05, | |
| "loss": 57.5238, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.098360655737705, | |
| "grad_norm": 17.733745574951172, | |
| "learning_rate": 3.105855655680986e-05, | |
| "loss": 59.0577, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.1508196721311474, | |
| "grad_norm": 18.677440643310547, | |
| "learning_rate": 2.8959791671908742e-05, | |
| "loss": 59.2771, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.2032786885245903, | |
| "grad_norm": 20.046802520751953, | |
| "learning_rate": 2.6942958916356998e-05, | |
| "loss": 58.3555, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.2557377049180327, | |
| "grad_norm": 26.242361068725586, | |
| "learning_rate": 2.501440399215983e-05, | |
| "loss": 59.7959, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.3081967213114756, | |
| "grad_norm": 17.727699279785156, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 58.5926, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.360655737704918, | |
| "grad_norm": 18.205520629882812, | |
| "learning_rate": 2.144610258025755e-05, | |
| "loss": 58.4511, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.413114754098361, | |
| "grad_norm": 20.044387817382812, | |
| "learning_rate": 1.981758328893866e-05, | |
| "loss": 57.0531, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.4655737704918033, | |
| "grad_norm": 22.331958770751953, | |
| "learning_rate": 1.8299760896833295e-05, | |
| "loss": 60.0991, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.5180327868852457, | |
| "grad_norm": 29.541261672973633, | |
| "learning_rate": 1.6897411034727218e-05, | |
| "loss": 59.2154, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.5704918032786885, | |
| "grad_norm": 20.129823684692383, | |
| "learning_rate": 1.5614946014106085e-05, | |
| "loss": 58.7101, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.6229508196721314, | |
| "grad_norm": 20.351736068725586, | |
| "learning_rate": 1.4456400944391146e-05, | |
| "loss": 59.4648, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.6229508196721314, | |
| "eval_loss": 2.0465781688690186, | |
| "eval_runtime": 4.7768, | |
| "eval_samples_per_second": 10.467, | |
| "eval_steps_per_second": 2.721, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 58, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.658021338284032e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |