| { | |
| "best_metric": 1.156433343887329, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.078125, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015625, | |
| "grad_norm": 1.002217173576355, | |
| "learning_rate": 0.0001, | |
| "loss": 6.6339, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015625, | |
| "eval_loss": 1.3499351739883423, | |
| "eval_runtime": 68.1466, | |
| "eval_samples_per_second": 3.962, | |
| "eval_steps_per_second": 1.981, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003125, | |
| "grad_norm": 1.0105056762695312, | |
| "learning_rate": 0.0002, | |
| "loss": 3.3938, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0046875, | |
| "grad_norm": 1.1939878463745117, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 5.1615, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00625, | |
| "grad_norm": 1.1158249378204346, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 3.7772, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0078125, | |
| "grad_norm": 1.0754586458206177, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 3.8606, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009375, | |
| "grad_norm": 1.1657280921936035, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 3.4493, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0109375, | |
| "grad_norm": 1.3628090620040894, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 4.7123, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0125, | |
| "grad_norm": 1.3325765132904053, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 4.0295, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0140625, | |
| "grad_norm": 1.3623121976852417, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 4.2144, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015625, | |
| "grad_norm": 1.3872919082641602, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 4.359, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0171875, | |
| "grad_norm": 1.6150164604187012, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 4.2599, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01875, | |
| "grad_norm": 1.5497463941574097, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 4.1864, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0203125, | |
| "grad_norm": 1.6500900983810425, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 4.2355, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.021875, | |
| "grad_norm": 1.6816496849060059, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 4.3307, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0234375, | |
| "grad_norm": 1.6419248580932617, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 3.7119, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.025, | |
| "grad_norm": 1.6070975065231323, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 4.3371, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0265625, | |
| "grad_norm": 1.6957802772521973, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 4.449, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.028125, | |
| "grad_norm": 1.9621312618255615, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 4.1207, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0296875, | |
| "grad_norm": 2.0953187942504883, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 5.4249, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03125, | |
| "grad_norm": 1.8811029195785522, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 4.2354, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0328125, | |
| "grad_norm": 1.602460503578186, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 3.5258, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.034375, | |
| "grad_norm": 1.9910820722579956, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 4.9889, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0359375, | |
| "grad_norm": 1.5707694292068481, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 3.8021, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0375, | |
| "grad_norm": 2.191178560256958, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 5.185, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0390625, | |
| "grad_norm": 1.939286470413208, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 3.4836, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0390625, | |
| "eval_loss": 1.196044921875, | |
| "eval_runtime": 68.9157, | |
| "eval_samples_per_second": 3.918, | |
| "eval_steps_per_second": 1.959, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.040625, | |
| "grad_norm": 2.3794100284576416, | |
| "learning_rate": 0.0001, | |
| "loss": 5.3229, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0421875, | |
| "grad_norm": 2.2176098823547363, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 5.1244, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04375, | |
| "grad_norm": 2.5599007606506348, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 4.9215, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0453125, | |
| "grad_norm": 2.7694389820098877, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 5.3148, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.046875, | |
| "grad_norm": 2.875401258468628, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 5.9734, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0484375, | |
| "grad_norm": 2.8313703536987305, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 5.1775, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 2.8203907012939453, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 5.5451, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0515625, | |
| "grad_norm": 2.829041004180908, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 5.8053, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.053125, | |
| "grad_norm": 2.9791057109832764, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 4.9274, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0546875, | |
| "grad_norm": 3.606865406036377, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 5.321, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05625, | |
| "grad_norm": 3.3906495571136475, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 4.4049, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0578125, | |
| "grad_norm": 4.231806755065918, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 5.6204, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.059375, | |
| "grad_norm": 5.441033363342285, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 4.8918, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0609375, | |
| "grad_norm": 3.8367645740509033, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 5.9264, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0625, | |
| "grad_norm": 3.5314066410064697, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 4.2635, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0640625, | |
| "grad_norm": 4.272062301635742, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 4.6596, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.065625, | |
| "grad_norm": 3.7861499786376953, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 4.0068, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0671875, | |
| "grad_norm": 4.380683422088623, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 5.556, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.06875, | |
| "grad_norm": 5.555474281311035, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 5.1522, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0703125, | |
| "grad_norm": 7.23276424407959, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 5.7147, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.071875, | |
| "grad_norm": 5.7143120765686035, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 6.1734, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0734375, | |
| "grad_norm": 8.563957214355469, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 4.2151, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.075, | |
| "grad_norm": 6.835947036743164, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 6.057, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0765625, | |
| "grad_norm": 8.4927978515625, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 6.0049, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.078125, | |
| "grad_norm": 13.51700210571289, | |
| "learning_rate": 0.0, | |
| "loss": 8.1939, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.078125, | |
| "eval_loss": 1.156433343887329, | |
| "eval_runtime": 68.938, | |
| "eval_samples_per_second": 3.917, | |
| "eval_steps_per_second": 1.958, | |
| "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": 6.53458201903104e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |