| { | |
| "best_metric": 1.426554560661316, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.02699055330634278, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010796221322537112, | |
| "grad_norm": 0.34332430362701416, | |
| "learning_rate": 2e-05, | |
| "loss": 6.0807, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010796221322537112, | |
| "eval_loss": 1.5532737970352173, | |
| "eval_runtime": 82.8191, | |
| "eval_samples_per_second": 4.709, | |
| "eval_steps_per_second": 2.355, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021592442645074223, | |
| "grad_norm": 0.33206412196159363, | |
| "learning_rate": 4e-05, | |
| "loss": 5.944, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0032388663967611335, | |
| "grad_norm": 0.34279167652130127, | |
| "learning_rate": 6e-05, | |
| "loss": 6.3636, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004318488529014845, | |
| "grad_norm": 0.38026267290115356, | |
| "learning_rate": 8e-05, | |
| "loss": 6.7592, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005398110661268556, | |
| "grad_norm": 0.6818948984146118, | |
| "learning_rate": 0.0001, | |
| "loss": 6.3923, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005398110661268556, | |
| "eval_loss": 1.5485819578170776, | |
| "eval_runtime": 81.8211, | |
| "eval_samples_per_second": 4.766, | |
| "eval_steps_per_second": 2.383, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006477732793522267, | |
| "grad_norm": 0.4078940749168396, | |
| "learning_rate": 0.00012, | |
| "loss": 6.0416, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007557354925775978, | |
| "grad_norm": 0.461333304643631, | |
| "learning_rate": 0.00014, | |
| "loss": 6.5209, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00863697705802969, | |
| "grad_norm": 0.6702338457107544, | |
| "learning_rate": 0.00016, | |
| "loss": 6.533, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009716599190283401, | |
| "grad_norm": 0.5864641070365906, | |
| "learning_rate": 0.00018, | |
| "loss": 6.5168, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010796221322537112, | |
| "grad_norm": 0.8698834180831909, | |
| "learning_rate": 0.0002, | |
| "loss": 6.3819, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010796221322537112, | |
| "eval_loss": 1.510269284248352, | |
| "eval_runtime": 81.6123, | |
| "eval_samples_per_second": 4.779, | |
| "eval_steps_per_second": 2.389, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011875843454790824, | |
| "grad_norm": 0.848861038684845, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 5.6706, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.012955465587044534, | |
| "grad_norm": 0.8634513020515442, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 6.2037, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014035087719298246, | |
| "grad_norm": 1.3566186428070068, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 6.261, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.015114709851551956, | |
| "grad_norm": 1.313557744026184, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 6.5576, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.016194331983805668, | |
| "grad_norm": 1.2444119453430176, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 5.4448, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.016194331983805668, | |
| "eval_loss": 1.4621978998184204, | |
| "eval_runtime": 81.5876, | |
| "eval_samples_per_second": 4.78, | |
| "eval_steps_per_second": 2.39, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01727395411605938, | |
| "grad_norm": 1.263450026512146, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 5.3685, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01835357624831309, | |
| "grad_norm": 1.5062628984451294, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 5.6889, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.019433198380566803, | |
| "grad_norm": 1.4760394096374512, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 5.7262, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.020512820512820513, | |
| "grad_norm": 1.363295555114746, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 5.7276, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.021592442645074223, | |
| "grad_norm": 1.4489655494689941, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 5.7842, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021592442645074223, | |
| "eval_loss": 1.4339179992675781, | |
| "eval_runtime": 81.4958, | |
| "eval_samples_per_second": 4.786, | |
| "eval_steps_per_second": 2.393, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.022672064777327937, | |
| "grad_norm": 1.5035929679870605, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 5.4438, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.023751686909581647, | |
| "grad_norm": 1.3411996364593506, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 5.0783, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.024831309041835357, | |
| "grad_norm": 1.7389713525772095, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 5.9207, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.025910931174089068, | |
| "grad_norm": 1.6175214052200317, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 6.0236, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02699055330634278, | |
| "grad_norm": 1.2862156629562378, | |
| "learning_rate": 0.0, | |
| "loss": 5.6139, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02699055330634278, | |
| "eval_loss": 1.426554560661316, | |
| "eval_runtime": 81.5554, | |
| "eval_samples_per_second": 4.782, | |
| "eval_steps_per_second": 2.391, | |
| "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": 1.207870175576064e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |