| { | |
| "best_metric": 1.031199336051941, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0014826676155739406, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.930670462295763e-05, | |
| "grad_norm": 4.366586208343506, | |
| "learning_rate": 1e-05, | |
| "loss": 5.4323, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.930670462295763e-05, | |
| "eval_loss": 1.4202075004577637, | |
| "eval_runtime": 1425.4057, | |
| "eval_samples_per_second": 4.981, | |
| "eval_steps_per_second": 2.491, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00011861340924591526, | |
| "grad_norm": 3.5335845947265625, | |
| "learning_rate": 2e-05, | |
| "loss": 5.7816, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00017792011386887289, | |
| "grad_norm": 3.675875425338745, | |
| "learning_rate": 3e-05, | |
| "loss": 5.2777, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00023722681849183051, | |
| "grad_norm": 3.669605255126953, | |
| "learning_rate": 4e-05, | |
| "loss": 4.786, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0002965335231147881, | |
| "grad_norm": 3.8144474029541016, | |
| "learning_rate": 5e-05, | |
| "loss": 5.1725, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0002965335231147881, | |
| "eval_loss": 1.4089925289154053, | |
| "eval_runtime": 1427.833, | |
| "eval_samples_per_second": 4.973, | |
| "eval_steps_per_second": 2.486, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00035584022773774577, | |
| "grad_norm": 5.1732892990112305, | |
| "learning_rate": 6e-05, | |
| "loss": 6.6594, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00041514693236070337, | |
| "grad_norm": 5.111558437347412, | |
| "learning_rate": 7e-05, | |
| "loss": 7.1659, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00047445363698366103, | |
| "grad_norm": 5.365387439727783, | |
| "learning_rate": 8e-05, | |
| "loss": 5.7353, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0005337603416066186, | |
| "grad_norm": 4.601907253265381, | |
| "learning_rate": 9e-05, | |
| "loss": 5.4603, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005930670462295762, | |
| "grad_norm": 5.3217997550964355, | |
| "learning_rate": 0.0001, | |
| "loss": 6.4354, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005930670462295762, | |
| "eval_loss": 1.2900954484939575, | |
| "eval_runtime": 1425.9569, | |
| "eval_samples_per_second": 4.979, | |
| "eval_steps_per_second": 2.49, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006523737508525338, | |
| "grad_norm": 4.760507583618164, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 5.1135, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0007116804554754915, | |
| "grad_norm": 4.733860492706299, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 5.0762, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0007709871600984491, | |
| "grad_norm": 3.5674550533294678, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 3.9928, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0008302938647214067, | |
| "grad_norm": 4.406932353973389, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 4.2712, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0008896005693443643, | |
| "grad_norm": 5.8381028175354, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 4.7663, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0008896005693443643, | |
| "eval_loss": 1.112551212310791, | |
| "eval_runtime": 1425.1082, | |
| "eval_samples_per_second": 4.982, | |
| "eval_steps_per_second": 2.491, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0009489072739673221, | |
| "grad_norm": 4.847886085510254, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 5.4438, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0010082139785902795, | |
| "grad_norm": 5.007083892822266, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 4.1874, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0010675206832132373, | |
| "grad_norm": 4.6717753410339355, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 3.6129, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.001126827387836195, | |
| "grad_norm": 5.144303798675537, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 4.2386, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0011861340924591525, | |
| "grad_norm": 5.231932163238525, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 4.0511, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0011861340924591525, | |
| "eval_loss": 1.0417572259902954, | |
| "eval_runtime": 1434.6349, | |
| "eval_samples_per_second": 4.949, | |
| "eval_steps_per_second": 2.474, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0012454407970821102, | |
| "grad_norm": 5.03507661819458, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 4.1459, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0013047475017050677, | |
| "grad_norm": 5.1348419189453125, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 3.7684, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0013640542063280254, | |
| "grad_norm": 5.261707782745361, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 3.0605, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.001423360910950983, | |
| "grad_norm": 6.641138076782227, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 3.1477, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0014826676155739406, | |
| "grad_norm": 5.031643867492676, | |
| "learning_rate": 0.0, | |
| "loss": 3.6754, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0014826676155739406, | |
| "eval_loss": 1.031199336051941, | |
| "eval_runtime": 1426.5631, | |
| "eval_samples_per_second": 4.977, | |
| "eval_steps_per_second": 2.488, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 7084989141221376.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |