| { | |
| "best_metric": 1.1000064611434937, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.026497085320614733, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010598834128245894, | |
| "grad_norm": 0.6467643976211548, | |
| "learning_rate": 2e-05, | |
| "loss": 5.9796, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010598834128245894, | |
| "eval_loss": 1.5834020376205444, | |
| "eval_runtime": 80.3436, | |
| "eval_samples_per_second": 4.954, | |
| "eval_steps_per_second": 2.477, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021197668256491787, | |
| "grad_norm": 0.6095791459083557, | |
| "learning_rate": 4e-05, | |
| "loss": 7.4113, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003179650238473768, | |
| "grad_norm": 0.6075787544250488, | |
| "learning_rate": 6e-05, | |
| "loss": 6.0515, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0042395336512983575, | |
| "grad_norm": 0.7645446062088013, | |
| "learning_rate": 8e-05, | |
| "loss": 6.4815, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005299417064122946, | |
| "grad_norm": 0.8007614016532898, | |
| "learning_rate": 0.0001, | |
| "loss": 6.2063, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005299417064122946, | |
| "eval_loss": 1.5732314586639404, | |
| "eval_runtime": 80.1038, | |
| "eval_samples_per_second": 4.969, | |
| "eval_steps_per_second": 2.484, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006359300476947536, | |
| "grad_norm": 0.816467821598053, | |
| "learning_rate": 0.00012, | |
| "loss": 6.1399, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007419183889772125, | |
| "grad_norm": 1.0349878072738647, | |
| "learning_rate": 0.00014, | |
| "loss": 6.3008, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008479067302596715, | |
| "grad_norm": 1.3219040632247925, | |
| "learning_rate": 0.00016, | |
| "loss": 6.0461, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009538950715421303, | |
| "grad_norm": 1.773594856262207, | |
| "learning_rate": 0.00018, | |
| "loss": 6.0166, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010598834128245893, | |
| "grad_norm": 1.6728031635284424, | |
| "learning_rate": 0.0002, | |
| "loss": 5.8041, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010598834128245893, | |
| "eval_loss": 1.364399790763855, | |
| "eval_runtime": 79.9364, | |
| "eval_samples_per_second": 4.979, | |
| "eval_steps_per_second": 2.489, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011658717541070483, | |
| "grad_norm": 1.573024868965149, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 5.4242, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.012718600953895072, | |
| "grad_norm": 1.2491636276245117, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 5.4373, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01377848436671966, | |
| "grad_norm": 1.5084812641143799, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 4.8817, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01483836777954425, | |
| "grad_norm": 2.022383451461792, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 4.9304, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01589825119236884, | |
| "grad_norm": 1.9843780994415283, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 4.7349, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01589825119236884, | |
| "eval_loss": 1.1954110860824585, | |
| "eval_runtime": 79.8374, | |
| "eval_samples_per_second": 4.985, | |
| "eval_steps_per_second": 2.493, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01695813460519343, | |
| "grad_norm": 1.3177485466003418, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 4.1256, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.018018018018018018, | |
| "grad_norm": 1.5878150463104248, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 4.7507, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.019077901430842606, | |
| "grad_norm": 1.2976889610290527, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 4.1571, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.020137784843667197, | |
| "grad_norm": 1.248026728630066, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 4.6085, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.021197668256491786, | |
| "grad_norm": 1.2782723903656006, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 4.5545, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021197668256491786, | |
| "eval_loss": 1.112984538078308, | |
| "eval_runtime": 83.6533, | |
| "eval_samples_per_second": 4.758, | |
| "eval_steps_per_second": 2.379, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.022257551669316374, | |
| "grad_norm": 1.1610110998153687, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 4.2746, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.023317435082140965, | |
| "grad_norm": 1.1637465953826904, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 4.7727, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.024377318494965553, | |
| "grad_norm": 1.1322404146194458, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 4.7445, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.025437201907790145, | |
| "grad_norm": 1.169419765472412, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 4.2861, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.026497085320614733, | |
| "grad_norm": 1.1728049516677856, | |
| "learning_rate": 0.0, | |
| "loss": 4.8437, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.026497085320614733, | |
| "eval_loss": 1.1000064611434937, | |
| "eval_runtime": 79.8428, | |
| "eval_samples_per_second": 4.985, | |
| "eval_steps_per_second": 2.492, | |
| "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": 8143746210201600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |