| { | |
| "best_metric": 0.339973121881485, | |
| "best_model_checkpoint": "realFake-img/checkpoint-200", | |
| "epoch": 4.0, | |
| "eval_steps": 100, | |
| "global_step": 208, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19230769230769232, | |
| "grad_norm": 3.016617774963379, | |
| "learning_rate": 0.00019134615384615387, | |
| "loss": 0.7043, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 8.659211158752441, | |
| "learning_rate": 0.00018173076923076923, | |
| "loss": 0.6331, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5769230769230769, | |
| "grad_norm": 3.7159981727600098, | |
| "learning_rate": 0.00017211538461538463, | |
| "loss": 0.6697, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 5.222133636474609, | |
| "learning_rate": 0.00016250000000000002, | |
| "loss": 0.5777, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9615384615384616, | |
| "grad_norm": 6.754155158996582, | |
| "learning_rate": 0.00015288461538461539, | |
| "loss": 0.5347, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1538461538461537, | |
| "grad_norm": 1.658116102218628, | |
| "learning_rate": 0.00014326923076923078, | |
| "loss": 0.4377, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.3461538461538463, | |
| "grad_norm": 5.012947082519531, | |
| "learning_rate": 0.00013365384615384614, | |
| "loss": 0.4354, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 4.971016883850098, | |
| "learning_rate": 0.00012403846153846154, | |
| "loss": 0.4928, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.7307692307692308, | |
| "grad_norm": 4.061134338378906, | |
| "learning_rate": 0.00011442307692307692, | |
| "loss": 0.3803, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.9230769230769231, | |
| "grad_norm": 4.557286739349365, | |
| "learning_rate": 0.00010480769230769232, | |
| "loss": 0.3732, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.9230769230769231, | |
| "eval_accuracy": 0.7945205479452054, | |
| "eval_loss": 0.4088120758533478, | |
| "eval_runtime": 5.0993, | |
| "eval_samples_per_second": 28.631, | |
| "eval_steps_per_second": 3.726, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.1153846153846154, | |
| "grad_norm": 2.305349826812744, | |
| "learning_rate": 9.519230769230769e-05, | |
| "loss": 0.3172, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.3076923076923075, | |
| "grad_norm": 1.443526029586792, | |
| "learning_rate": 8.557692307692308e-05, | |
| "loss": 0.3155, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 1.3094813823699951, | |
| "learning_rate": 7.596153846153846e-05, | |
| "loss": 0.2671, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.6923076923076925, | |
| "grad_norm": 5.578798770904541, | |
| "learning_rate": 6.634615384615385e-05, | |
| "loss": 0.2603, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.8846153846153846, | |
| "grad_norm": 1.8392003774642944, | |
| "learning_rate": 5.673076923076923e-05, | |
| "loss": 0.2804, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 0.6986391544342041, | |
| "learning_rate": 4.711538461538462e-05, | |
| "loss": 0.3171, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.269230769230769, | |
| "grad_norm": 4.677719593048096, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.1962, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.4615384615384617, | |
| "grad_norm": 1.8367177248001099, | |
| "learning_rate": 2.7884615384615386e-05, | |
| "loss": 0.3216, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.6538461538461537, | |
| "grad_norm": 5.29152774810791, | |
| "learning_rate": 1.826923076923077e-05, | |
| "loss": 0.1938, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.8461538461538463, | |
| "grad_norm": 1.2080388069152832, | |
| "learning_rate": 8.653846153846155e-06, | |
| "loss": 0.1451, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.8461538461538463, | |
| "eval_accuracy": 0.8424657534246576, | |
| "eval_loss": 0.339973121881485, | |
| "eval_runtime": 4.8463, | |
| "eval_samples_per_second": 30.126, | |
| "eval_steps_per_second": 3.921, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 208, | |
| "total_flos": 2.5832369176982323e+17, | |
| "train_loss": 0.38543382860147035, | |
| "train_runtime": 140.7513, | |
| "train_samples_per_second": 23.474, | |
| "train_steps_per_second": 1.478 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 208, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.5832369176982323e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |