| { | |
| "best_metric": 2.4438157081604004, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4550625711035267, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009101251422070534, | |
| "grad_norm": 2.1346871852874756, | |
| "learning_rate": 5e-05, | |
| "loss": 4.9719, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009101251422070534, | |
| "eval_loss": 4.942025184631348, | |
| "eval_runtime": 4.0731, | |
| "eval_samples_per_second": 181.927, | |
| "eval_steps_per_second": 22.833, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01820250284414107, | |
| "grad_norm": 1.6914374828338623, | |
| "learning_rate": 0.0001, | |
| "loss": 4.9787, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.027303754266211604, | |
| "grad_norm": 1.4702175855636597, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.8334, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03640500568828214, | |
| "grad_norm": 1.6867676973342896, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.0761, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04550625711035267, | |
| "grad_norm": 1.8130220174789429, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.0172, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05460750853242321, | |
| "grad_norm": 1.3689041137695312, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.4869, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06370875995449374, | |
| "grad_norm": 1.9557944536209106, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 4.8043, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07281001137656427, | |
| "grad_norm": 1.3595128059387207, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.8043, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08191126279863481, | |
| "grad_norm": 1.7356663942337036, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 4.988, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09101251422070535, | |
| "grad_norm": 1.2412830591201782, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 4.3269, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10011376564277588, | |
| "grad_norm": 1.268452763557434, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 4.4747, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10921501706484642, | |
| "grad_norm": 1.2650614976882935, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 4.0926, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11831626848691695, | |
| "grad_norm": 1.2461438179016113, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.8517, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12741751990898748, | |
| "grad_norm": 1.6487263441085815, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.712, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13651877133105803, | |
| "grad_norm": 1.447868824005127, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 3.5978, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14562002275312855, | |
| "grad_norm": 1.4297068119049072, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 3.5478, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1547212741751991, | |
| "grad_norm": 1.739940881729126, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 3.6575, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.16382252559726962, | |
| "grad_norm": 1.542245864868164, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 3.4597, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.17292377701934017, | |
| "grad_norm": 1.7134660482406616, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 3.3924, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1820250284414107, | |
| "grad_norm": 1.4687405824661255, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.5119, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19112627986348124, | |
| "grad_norm": 1.7465482950210571, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 3.8799, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.20022753128555176, | |
| "grad_norm": 1.506808876991272, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.6514, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.20932878270762229, | |
| "grad_norm": 1.3481961488723755, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 3.7276, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.21843003412969283, | |
| "grad_norm": 1.4149906635284424, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.5602, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.22753128555176336, | |
| "grad_norm": 1.665215015411377, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.1668, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22753128555176336, | |
| "eval_loss": 3.0762650966644287, | |
| "eval_runtime": 4.0834, | |
| "eval_samples_per_second": 181.466, | |
| "eval_steps_per_second": 22.775, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2366325369738339, | |
| "grad_norm": 2.168104410171509, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6265, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.24573378839590443, | |
| "grad_norm": 1.9618370532989502, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.7075, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.25483503981797495, | |
| "grad_norm": 1.8602323532104492, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.6952, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.26393629124004553, | |
| "grad_norm": 1.7716730833053589, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.6196, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.27303754266211605, | |
| "grad_norm": 1.9440735578536987, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.5962, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2821387940841866, | |
| "grad_norm": 1.8115489482879639, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.6244, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2912400455062571, | |
| "grad_norm": 1.9076594114303589, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.4369, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3003412969283277, | |
| "grad_norm": 1.523880124092102, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.8228, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3094425483503982, | |
| "grad_norm": 2.241621971130371, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 3.1889, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3185437997724687, | |
| "grad_norm": 1.773310661315918, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.9108, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.32764505119453924, | |
| "grad_norm": 1.6375255584716797, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 3.106, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.33674630261660976, | |
| "grad_norm": 1.7255483865737915, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.8329, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.34584755403868034, | |
| "grad_norm": 1.6252745389938354, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.3072, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.35494880546075086, | |
| "grad_norm": 2.1704254150390625, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.1483, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3640500568828214, | |
| "grad_norm": 1.8003798723220825, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.1688, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3731513083048919, | |
| "grad_norm": 1.7969120740890503, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.1399, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3822525597269625, | |
| "grad_norm": 1.9582467079162598, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.1466, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.391353811149033, | |
| "grad_norm": 1.8976678848266602, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.1565, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4004550625711035, | |
| "grad_norm": 1.9421591758728027, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.0217, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.40955631399317405, | |
| "grad_norm": 1.625119924545288, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.344, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.41865756541524457, | |
| "grad_norm": 2.1905601024627686, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.901, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.42775881683731515, | |
| "grad_norm": 1.9888536930084229, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.7267, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.43686006825938567, | |
| "grad_norm": 1.635216474533081, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.8926, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4459613196814562, | |
| "grad_norm": 1.7304415702819824, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.9722, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4550625711035267, | |
| "grad_norm": 2.324007749557495, | |
| "learning_rate": 0.0, | |
| "loss": 2.6059, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4550625711035267, | |
| "eval_loss": 2.4438157081604004, | |
| "eval_runtime": 4.0594, | |
| "eval_samples_per_second": 182.539, | |
| "eval_steps_per_second": 22.91, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9120441905971200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |