| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.2222222222222223, | |
| "eval_steps": 50, | |
| "global_step": 21, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 9.025846481323242, | |
| "learning_rate": 1.06e-05, | |
| "loss": 2.2598, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "eval_loss": 2.293095111846924, | |
| "eval_runtime": 0.9049, | |
| "eval_samples_per_second": 99.46, | |
| "eval_steps_per_second": 3.315, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 9.928245544433594, | |
| "learning_rate": 2.12e-05, | |
| "loss": 2.3139, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 7.822314739227295, | |
| "learning_rate": 3.18e-05, | |
| "loss": 2.0956, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 12.399734497070312, | |
| "learning_rate": 4.24e-05, | |
| "loss": 1.8688, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 5.776300430297852, | |
| "learning_rate": 5.3e-05, | |
| "loss": 1.5517, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 4.726962566375732, | |
| "learning_rate": 6.36e-05, | |
| "loss": 1.2675, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.074074074074074, | |
| "grad_norm": 10.351492881774902, | |
| "learning_rate": 7.42e-05, | |
| "loss": 1.8753, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.2222222222222223, | |
| "grad_norm": 9.424615859985352, | |
| "learning_rate": 8.48e-05, | |
| "loss": 1.2173, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.3703703703703702, | |
| "grad_norm": 2.993288993835449, | |
| "learning_rate": 9.54e-05, | |
| "loss": 1.1298, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.5185185185185186, | |
| "grad_norm": 3.4643940925598145, | |
| "learning_rate": 0.000106, | |
| "loss": 0.9959, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 4.57342529296875, | |
| "learning_rate": 0.00010385312760156837, | |
| "loss": 1.1387, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.8148148148148149, | |
| "grad_norm": 2.0306742191314697, | |
| "learning_rate": 9.75864372400526e-05, | |
| "loss": 1.0047, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.9629629629629628, | |
| "grad_norm": 3.058318614959717, | |
| "learning_rate": 8.770761889910012e-05, | |
| "loss": 1.4257, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.148148148148148, | |
| "grad_norm": 2.2051618099212646, | |
| "learning_rate": 7.501699568909999e-05, | |
| "loss": 0.8452, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.2962962962962963, | |
| "grad_norm": 1.9626882076263428, | |
| "learning_rate": 6.054268642848412e-05, | |
| "loss": 0.7865, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.4444444444444446, | |
| "grad_norm": 2.194836139678955, | |
| "learning_rate": 4.545731357151589e-05, | |
| "loss": 0.7938, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.5925925925925926, | |
| "grad_norm": 1.5503541231155396, | |
| "learning_rate": 3.0983004310900024e-05, | |
| "loss": 0.7757, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 2.7407407407407405, | |
| "grad_norm": 1.4564896821975708, | |
| "learning_rate": 1.8292381100899895e-05, | |
| "loss": 0.7369, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.888888888888889, | |
| "grad_norm": 1.3275120258331299, | |
| "learning_rate": 8.41356275994739e-06, | |
| "loss": 0.7387, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.074074074074074, | |
| "grad_norm": 2.068755865097046, | |
| "learning_rate": 2.146872398431645e-06, | |
| "loss": 1.0643, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.2222222222222223, | |
| "grad_norm": 1.0983883142471313, | |
| "learning_rate": 0.0, | |
| "loss": 0.6089, | |
| "step": 21 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 21, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 3.58447037684908e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |