| { | |
| "best_metric": 0.7381670475006104, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.004064049418840933, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001625619767536373, | |
| "grad_norm": 1.4133057594299316, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8255, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001625619767536373, | |
| "eval_loss": 0.900519073009491, | |
| "eval_runtime": 722.4785, | |
| "eval_samples_per_second": 3.586, | |
| "eval_steps_per_second": 1.794, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003251239535072746, | |
| "grad_norm": 2.0552265644073486, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8089, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000487685930260912, | |
| "grad_norm": 1.21483314037323, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 0.8083, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006502479070145493, | |
| "grad_norm": 1.5333422422409058, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 0.6852, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008128098837681866, | |
| "grad_norm": 1.4478944540023804, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 0.7185, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000975371860521824, | |
| "grad_norm": 1.0845215320587158, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.645, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011379338372754612, | |
| "grad_norm": 1.0120457410812378, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.7327, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013004958140290985, | |
| "grad_norm": 0.9877651333808899, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.6438, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001463057790782736, | |
| "grad_norm": 1.118600606918335, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.6499, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016256197675363732, | |
| "grad_norm": 1.1166441440582275, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.6903, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017881817442900105, | |
| "grad_norm": 1.202609896659851, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.6474, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001950743721043648, | |
| "grad_norm": 0.9753208756446838, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.6544, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002113305697797285, | |
| "grad_norm": 0.9574378132820129, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.7245, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0022758676745509225, | |
| "grad_norm": 1.0208672285079956, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.6966, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00243842965130456, | |
| "grad_norm": 0.9356812834739685, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.6425, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002600991628058197, | |
| "grad_norm": 1.225610613822937, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.6601, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0027635536048118345, | |
| "grad_norm": 1.0732367038726807, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.682, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.002926115581565472, | |
| "grad_norm": 0.9814640879631042, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.6934, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003088677558319109, | |
| "grad_norm": 0.9613204598426819, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.7026, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0032512395350727465, | |
| "grad_norm": 0.9899714589118958, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.7341, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003413801511826384, | |
| "grad_norm": 1.0220943689346313, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.7898, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003576363488580021, | |
| "grad_norm": 1.0292974710464478, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.6794, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0037389254653336585, | |
| "grad_norm": 1.0430673360824585, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.6881, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.003901487442087296, | |
| "grad_norm": 0.9846102595329285, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.6465, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004064049418840933, | |
| "grad_norm": 0.9897501468658447, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.6191, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004064049418840933, | |
| "eval_loss": 0.7381670475006104, | |
| "eval_runtime": 726.8538, | |
| "eval_samples_per_second": 3.565, | |
| "eval_steps_per_second": 1.783, | |
| "step": 25 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.51564950667264e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |