| { | |
| "best_metric": 11.73332405090332, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0434782608695654, | |
| "eval_steps": 25, | |
| "global_step": 35, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08695652173913043, | |
| "grad_norm": 0.18647073209285736, | |
| "learning_rate": 5e-05, | |
| "loss": 11.7667, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08695652173913043, | |
| "eval_loss": 11.762808799743652, | |
| "eval_runtime": 0.13, | |
| "eval_samples_per_second": 384.634, | |
| "eval_steps_per_second": 100.005, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.17391304347826086, | |
| "grad_norm": 0.2643306851387024, | |
| "learning_rate": 0.0001, | |
| "loss": 11.7489, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2608695652173913, | |
| "grad_norm": 0.29972273111343384, | |
| "learning_rate": 9.979623651578881e-05, | |
| "loss": 11.7599, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.34782608695652173, | |
| "grad_norm": 0.2142837643623352, | |
| "learning_rate": 9.91867913768218e-05, | |
| "loss": 11.764, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.43478260869565216, | |
| "grad_norm": 0.307963103055954, | |
| "learning_rate": 9.81771838126524e-05, | |
| "loss": 11.7523, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5217391304347826, | |
| "grad_norm": 0.24790479242801666, | |
| "learning_rate": 9.677655698572326e-05, | |
| "loss": 11.7489, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6086956521739131, | |
| "grad_norm": 0.26179468631744385, | |
| "learning_rate": 9.499759518947156e-05, | |
| "loss": 11.7547, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "grad_norm": 0.364184707403183, | |
| "learning_rate": 9.285640897740315e-05, | |
| "loss": 11.7459, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.782608695652174, | |
| "grad_norm": 0.22390057146549225, | |
| "learning_rate": 9.037238926342544e-05, | |
| "loss": 11.7549, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8695652173913043, | |
| "grad_norm": 0.2647338807582855, | |
| "learning_rate": 8.756803171472816e-05, | |
| "loss": 11.7434, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9565217391304348, | |
| "grad_norm": 0.3336775302886963, | |
| "learning_rate": 8.446873302753784e-05, | |
| "loss": 11.7308, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0434782608695652, | |
| "grad_norm": 0.3403792083263397, | |
| "learning_rate": 8.110256093070393e-05, | |
| "loss": 17.7544, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.1304347826086956, | |
| "grad_norm": 0.27228403091430664, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.6402, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.2173913043478262, | |
| "grad_norm": 0.3731023669242859, | |
| "learning_rate": 7.369367558508489e-05, | |
| "loss": 11.7784, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.3043478260869565, | |
| "grad_norm": 0.2505616843700409, | |
| "learning_rate": 6.9718058349284e-05, | |
| "loss": 11.8941, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.391304347826087, | |
| "grad_norm": 0.29947271943092346, | |
| "learning_rate": 6.560915209792424e-05, | |
| "loss": 11.5445, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.4782608695652173, | |
| "grad_norm": 0.38841569423675537, | |
| "learning_rate": 6.140416772229784e-05, | |
| "loss": 11.6536, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.5652173913043477, | |
| "grad_norm": 0.22608518600463867, | |
| "learning_rate": 5.714118621206842e-05, | |
| "loss": 11.8637, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.6521739130434783, | |
| "grad_norm": 0.31927651166915894, | |
| "learning_rate": 5.285881378793161e-05, | |
| "loss": 11.558, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.7391304347826086, | |
| "grad_norm": 0.33966994285583496, | |
| "learning_rate": 4.859583227770218e-05, | |
| "loss": 11.6422, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.8260869565217392, | |
| "grad_norm": 0.30635571479797363, | |
| "learning_rate": 4.4390847902075774e-05, | |
| "loss": 12.1493, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.9130434782608696, | |
| "grad_norm": 0.4218827784061432, | |
| "learning_rate": 4.028194165071602e-05, | |
| "loss": 11.5892, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.5390748977661133, | |
| "learning_rate": 3.630632441491512e-05, | |
| "loss": 17.5134, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.0869565217391304, | |
| "grad_norm": 0.2539425492286682, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.7481, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.1739130434782608, | |
| "grad_norm": 0.37579864263534546, | |
| "learning_rate": 2.889743906929609e-05, | |
| "loss": 11.7239, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.1739130434782608, | |
| "eval_loss": 11.73332405090332, | |
| "eval_runtime": 0.1351, | |
| "eval_samples_per_second": 370.08, | |
| "eval_steps_per_second": 96.221, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.260869565217391, | |
| "grad_norm": 0.4048350751399994, | |
| "learning_rate": 2.5531266972462177e-05, | |
| "loss": 11.7276, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.3478260869565215, | |
| "grad_norm": 0.3004996180534363, | |
| "learning_rate": 2.2431968285271844e-05, | |
| "loss": 11.7356, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.4347826086956523, | |
| "grad_norm": 0.4221931993961334, | |
| "learning_rate": 1.9627610736574575e-05, | |
| "loss": 11.7232, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.5217391304347827, | |
| "grad_norm": 0.32879894971847534, | |
| "learning_rate": 1.7143591022596845e-05, | |
| "loss": 11.7298, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.608695652173913, | |
| "grad_norm": 0.3590526282787323, | |
| "learning_rate": 1.5002404810528451e-05, | |
| "loss": 11.7288, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.6956521739130435, | |
| "grad_norm": 0.4498928189277649, | |
| "learning_rate": 1.3223443014276737e-05, | |
| "loss": 11.7184, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.782608695652174, | |
| "grad_norm": 0.2932029664516449, | |
| "learning_rate": 1.1822816187347623e-05, | |
| "loss": 11.7306, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.869565217391304, | |
| "grad_norm": 0.36732548475265503, | |
| "learning_rate": 1.08132086231782e-05, | |
| "loss": 11.7234, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.9565217391304346, | |
| "grad_norm": 0.5036232471466064, | |
| "learning_rate": 1.0203763484211195e-05, | |
| "loss": 11.7119, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 3.0434782608695654, | |
| "grad_norm": 0.49443715810775757, | |
| "learning_rate": 1e-05, | |
| "loss": 17.5485, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 35, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 114720296140800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |