| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.12, | |
| "eval_steps": 500, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004, | |
| "grad_norm": 2.9207499027252197, | |
| "learning_rate": 0.0, | |
| "loss": 1.4438, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008, | |
| "grad_norm": 2.400193452835083, | |
| "learning_rate": 4e-05, | |
| "loss": 1.14, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012, | |
| "grad_norm": 3.361041307449341, | |
| "learning_rate": 8e-05, | |
| "loss": 0.9335, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.016, | |
| "grad_norm": 2.458512783050537, | |
| "learning_rate": 0.00012, | |
| "loss": 1.1119, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.8693243265151978, | |
| "learning_rate": 0.00016, | |
| "loss": 1.1471, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.024, | |
| "grad_norm": 2.2018702030181885, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1148, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.028, | |
| "grad_norm": 1.313555359840393, | |
| "learning_rate": 0.000192, | |
| "loss": 0.915, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 1.3398995399475098, | |
| "learning_rate": 0.00018400000000000003, | |
| "loss": 0.8951, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.036, | |
| "grad_norm": 1.5205678939819336, | |
| "learning_rate": 0.00017600000000000002, | |
| "loss": 0.865, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 1.884972333908081, | |
| "learning_rate": 0.000168, | |
| "loss": 0.9431, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.044, | |
| "grad_norm": 1.527084469795227, | |
| "learning_rate": 0.00016, | |
| "loss": 1.1242, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.048, | |
| "grad_norm": 1.897480845451355, | |
| "learning_rate": 0.000152, | |
| "loss": 0.9756, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.052, | |
| "grad_norm": 1.558569073677063, | |
| "learning_rate": 0.000144, | |
| "loss": 0.7218, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.056, | |
| "grad_norm": 1.1632804870605469, | |
| "learning_rate": 0.00013600000000000003, | |
| "loss": 1.1561, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 1.3926975727081299, | |
| "learning_rate": 0.00012800000000000002, | |
| "loss": 0.9754, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 1.6751383543014526, | |
| "learning_rate": 0.00012, | |
| "loss": 1.6031, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.068, | |
| "grad_norm": 1.598408579826355, | |
| "learning_rate": 0.00011200000000000001, | |
| "loss": 1.3644, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.072, | |
| "grad_norm": 1.4632443189620972, | |
| "learning_rate": 0.00010400000000000001, | |
| "loss": 1.6242, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.076, | |
| "grad_norm": 0.9293956756591797, | |
| "learning_rate": 9.6e-05, | |
| "loss": 0.845, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 1.0192859172821045, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 0.7396, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.084, | |
| "grad_norm": 1.2623944282531738, | |
| "learning_rate": 8e-05, | |
| "loss": 0.7666, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.088, | |
| "grad_norm": 1.2764850854873657, | |
| "learning_rate": 7.2e-05, | |
| "loss": 0.7937, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.092, | |
| "grad_norm": 3.1119368076324463, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 0.9638, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 1.4668664932250977, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 1.4129, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 1.4162100553512573, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.9485, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.104, | |
| "grad_norm": 1.0868712663650513, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0354, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.108, | |
| "grad_norm": 1.056151270866394, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.9959, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.112, | |
| "grad_norm": 1.43464994430542, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.9594, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.116, | |
| "grad_norm": 1.0766808986663818, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.8449, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 1.2740269899368286, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.8029, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2358506748866048e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |