| { | |
| "best_metric": 1.5792856216430664, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.16913319238900634, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0033826638477801266, | |
| "grad_norm": 2.0565555095672607, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 2.2282, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0033826638477801266, | |
| "eval_loss": 2.194361448287964, | |
| "eval_runtime": 58.7509, | |
| "eval_samples_per_second": 16.953, | |
| "eval_steps_per_second": 4.238, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006765327695560253, | |
| "grad_norm": 2.1685779094696045, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 2.149, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01014799154334038, | |
| "grad_norm": 2.2771434783935547, | |
| "learning_rate": 1.5e-06, | |
| "loss": 2.1532, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013530655391120507, | |
| "grad_norm": 2.1824076175689697, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 2.1714, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.016913319238900635, | |
| "grad_norm": 2.2797279357910156, | |
| "learning_rate": 2.5e-06, | |
| "loss": 2.2472, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02029598308668076, | |
| "grad_norm": 2.220853567123413, | |
| "learning_rate": 3e-06, | |
| "loss": 2.2193, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.023678646934460888, | |
| "grad_norm": 2.385507583618164, | |
| "learning_rate": 3.5000000000000004e-06, | |
| "loss": 2.2173, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.027061310782241013, | |
| "grad_norm": 2.2680976390838623, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.2432, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03044397463002114, | |
| "grad_norm": 2.045863628387451, | |
| "learning_rate": 4.5e-06, | |
| "loss": 2.1571, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03382663847780127, | |
| "grad_norm": 2.005089044570923, | |
| "learning_rate": 5e-06, | |
| "loss": 2.1658, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.037209302325581395, | |
| "grad_norm": 1.9319759607315063, | |
| "learning_rate": 5.500000000000001e-06, | |
| "loss": 2.2337, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04059196617336152, | |
| "grad_norm": 1.7805265188217163, | |
| "learning_rate": 6e-06, | |
| "loss": 2.117, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04397463002114165, | |
| "grad_norm": 1.699826717376709, | |
| "learning_rate": 6.5000000000000004e-06, | |
| "loss": 2.1592, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.047357293868921777, | |
| "grad_norm": 1.6120779514312744, | |
| "learning_rate": 7.000000000000001e-06, | |
| "loss": 2.1491, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0507399577167019, | |
| "grad_norm": 1.5634993314743042, | |
| "learning_rate": 7.5e-06, | |
| "loss": 2.0976, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.054122621564482026, | |
| "grad_norm": 1.6402438879013062, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 2.0846, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05750528541226216, | |
| "grad_norm": 1.5344332456588745, | |
| "learning_rate": 8.500000000000002e-06, | |
| "loss": 1.9933, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06088794926004228, | |
| "grad_norm": 1.4738293886184692, | |
| "learning_rate": 9e-06, | |
| "loss": 2.0167, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06427061310782241, | |
| "grad_norm": 1.6113697290420532, | |
| "learning_rate": 9.5e-06, | |
| "loss": 2.0144, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06765327695560254, | |
| "grad_norm": 1.7016642093658447, | |
| "learning_rate": 1e-05, | |
| "loss": 2.0101, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07103594080338266, | |
| "grad_norm": 1.785592794418335, | |
| "learning_rate": 1.05e-05, | |
| "loss": 1.9704, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07441860465116279, | |
| "grad_norm": 1.612625241279602, | |
| "learning_rate": 1.1000000000000001e-05, | |
| "loss": 1.9504, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07780126849894292, | |
| "grad_norm": 1.89138925075531, | |
| "learning_rate": 1.1500000000000002e-05, | |
| "loss": 1.9573, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08118393234672304, | |
| "grad_norm": 1.769402027130127, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.9108, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08456659619450317, | |
| "grad_norm": 1.9443429708480835, | |
| "learning_rate": 1.25e-05, | |
| "loss": 1.9334, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08456659619450317, | |
| "eval_loss": 1.8751963376998901, | |
| "eval_runtime": 59.497, | |
| "eval_samples_per_second": 16.74, | |
| "eval_steps_per_second": 4.185, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0879492600422833, | |
| "grad_norm": 1.7100105285644531, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 1.9201, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.09133192389006342, | |
| "grad_norm": 1.7522183656692505, | |
| "learning_rate": 1.3500000000000001e-05, | |
| "loss": 1.8164, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09471458773784355, | |
| "grad_norm": 1.6645402908325195, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 1.8408, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09809725158562368, | |
| "grad_norm": 1.6604903936386108, | |
| "learning_rate": 1.45e-05, | |
| "loss": 1.7671, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1014799154334038, | |
| "grad_norm": 1.7911064624786377, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.757, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10486257928118393, | |
| "grad_norm": 1.8748377561569214, | |
| "learning_rate": 1.55e-05, | |
| "loss": 1.752, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10824524312896405, | |
| "grad_norm": 2.364097833633423, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 1.7415, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.11162790697674418, | |
| "grad_norm": 2.2695372104644775, | |
| "learning_rate": 1.65e-05, | |
| "loss": 1.7044, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11501057082452432, | |
| "grad_norm": 1.5664398670196533, | |
| "learning_rate": 1.7000000000000003e-05, | |
| "loss": 1.7009, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11839323467230443, | |
| "grad_norm": 1.7595115900039673, | |
| "learning_rate": 1.75e-05, | |
| "loss": 1.6647, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.12177589852008457, | |
| "grad_norm": 1.6659307479858398, | |
| "learning_rate": 1.8e-05, | |
| "loss": 1.6732, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.12515856236786468, | |
| "grad_norm": 1.1403136253356934, | |
| "learning_rate": 1.85e-05, | |
| "loss": 1.6259, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12854122621564482, | |
| "grad_norm": 1.0617878437042236, | |
| "learning_rate": 1.9e-05, | |
| "loss": 1.62, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.13192389006342495, | |
| "grad_norm": 0.9418096542358398, | |
| "learning_rate": 1.9500000000000003e-05, | |
| "loss": 1.5283, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.13530655391120508, | |
| "grad_norm": 0.9303457736968994, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5858, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1386892177589852, | |
| "grad_norm": 0.8767881989479065, | |
| "learning_rate": 2.05e-05, | |
| "loss": 1.6119, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.14207188160676532, | |
| "grad_norm": 0.9987740516662598, | |
| "learning_rate": 2.1e-05, | |
| "loss": 1.6721, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.14545454545454545, | |
| "grad_norm": 0.8637537360191345, | |
| "learning_rate": 2.15e-05, | |
| "loss": 1.6756, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.14883720930232558, | |
| "grad_norm": 0.8661416172981262, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 1.5943, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1522198731501057, | |
| "grad_norm": 0.8084216117858887, | |
| "learning_rate": 2.25e-05, | |
| "loss": 1.612, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.15560253699788584, | |
| "grad_norm": 0.8370161056518555, | |
| "learning_rate": 2.3000000000000003e-05, | |
| "loss": 1.5512, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.15898520084566597, | |
| "grad_norm": 0.911957859992981, | |
| "learning_rate": 2.35e-05, | |
| "loss": 1.6142, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.16236786469344608, | |
| "grad_norm": 0.9367987513542175, | |
| "learning_rate": 2.4e-05, | |
| "loss": 1.5459, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1657505285412262, | |
| "grad_norm": 0.8949148654937744, | |
| "learning_rate": 2.45e-05, | |
| "loss": 1.6109, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.16913319238900634, | |
| "grad_norm": 0.8378682136535645, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.5156, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16913319238900634, | |
| "eval_loss": 1.5792856216430664, | |
| "eval_runtime": 59.5283, | |
| "eval_samples_per_second": 16.732, | |
| "eval_steps_per_second": 4.183, | |
| "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": 5.565359742517248e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |