| { | |
| "best_metric": 0.50872844, | |
| "best_model_checkpoint": "/content/output/qwen2-vl-7b-instruct/v2-20240909-100714/checkpoint-45", | |
| "epoch": 0.993103448275862, | |
| "eval_steps": 50, | |
| "global_step": 45, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "acc": 0.61398816, | |
| "epoch": 0.022068965517241378, | |
| "grad_norm": 7.717197895050049, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.87438893, | |
| "memory(GiB)": 20.29, | |
| "step": 1, | |
| "train_speed(iter/s)": 0.066629 | |
| }, | |
| { | |
| "acc": 0.62096363, | |
| "epoch": 0.1103448275862069, | |
| "grad_norm": 8.616560935974121, | |
| "learning_rate": 9.944154131125642e-05, | |
| "loss": 2.60930538, | |
| "memory(GiB)": 22.58, | |
| "step": 5, | |
| "train_speed(iter/s)": 0.075138 | |
| }, | |
| { | |
| "acc": 0.80472717, | |
| "epoch": 0.2206896551724138, | |
| "grad_norm": 3.399202346801758, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.68508205, | |
| "memory(GiB)": 23.35, | |
| "step": 10, | |
| "train_speed(iter/s)": 0.076348 | |
| }, | |
| { | |
| "acc": 0.81436024, | |
| "epoch": 0.3310344827586207, | |
| "grad_norm": 5.226686477661133, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.69332366, | |
| "memory(GiB)": 24.12, | |
| "step": 15, | |
| "train_speed(iter/s)": 0.076737 | |
| }, | |
| { | |
| "acc": 0.86372032, | |
| "epoch": 0.4413793103448276, | |
| "grad_norm": 3.478239059448242, | |
| "learning_rate": 6.473775872054521e-05, | |
| "loss": 0.57136168, | |
| "memory(GiB)": 24.12, | |
| "step": 20, | |
| "train_speed(iter/s)": 0.076946 | |
| }, | |
| { | |
| "acc": 0.85740089, | |
| "epoch": 0.5517241379310345, | |
| "grad_norm": 2.1063661575317383, | |
| "learning_rate": 4.626349532067879e-05, | |
| "loss": 0.51958747, | |
| "memory(GiB)": 24.91, | |
| "step": 25, | |
| "train_speed(iter/s)": 0.077061 | |
| }, | |
| { | |
| "acc": 0.85881948, | |
| "epoch": 0.6620689655172414, | |
| "grad_norm": 2.6917998790740967, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.51737795, | |
| "memory(GiB)": 24.91, | |
| "step": 30, | |
| "train_speed(iter/s)": 0.077142 | |
| }, | |
| { | |
| "acc": 0.84086313, | |
| "epoch": 0.7724137931034483, | |
| "grad_norm": 7.916348934173584, | |
| "learning_rate": 1.3347406408508695e-05, | |
| "loss": 0.72901492, | |
| "memory(GiB)": 24.91, | |
| "step": 35, | |
| "train_speed(iter/s)": 0.077198 | |
| }, | |
| { | |
| "acc": 0.86680059, | |
| "epoch": 0.8827586206896552, | |
| "grad_norm": 2.948944568634033, | |
| "learning_rate": 3.4563125677897932e-06, | |
| "loss": 0.43249173, | |
| "memory(GiB)": 24.91, | |
| "step": 40, | |
| "train_speed(iter/s)": 0.077243 | |
| }, | |
| { | |
| "acc": 0.91657734, | |
| "epoch": 0.993103448275862, | |
| "grad_norm": 2.6367099285125732, | |
| "learning_rate": 0.0, | |
| "loss": 0.34231672, | |
| "memory(GiB)": 24.91, | |
| "step": 45, | |
| "train_speed(iter/s)": 0.077273 | |
| }, | |
| { | |
| "epoch": 0.993103448275862, | |
| "eval_acc": 0.8181818181818182, | |
| "eval_loss": 0.5087284445762634, | |
| "eval_runtime": 3.4104, | |
| "eval_samples_per_second": 2.053, | |
| "eval_steps_per_second": 2.053, | |
| "step": 45 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 45, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.488065503664026e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |