H3-ScriptGen: MiniMax-H3 FL2VA scriptwriting LoRA (Qwen3.5-0.8B base, continue-trained from final adapter)
7dbeac1 verified | { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 105, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "entropy": 2.1651801258325576, | |
| "epoch": 0.04784688995215311, | |
| "grad_norm": 4.052286148071289, | |
| "learning_rate": 9.80952380952381e-05, | |
| "loss": 2.560974884033203, | |
| "mean_token_accuracy": 0.5812613397836686, | |
| "num_tokens": 22163.0, | |
| "step": 5 | |
| }, | |
| { | |
| "entropy": 1.7820561587810517, | |
| "epoch": 0.09569377990430622, | |
| "grad_norm": 3.3570611476898193, | |
| "learning_rate": 9.571428571428573e-05, | |
| "loss": 1.5557975769042969, | |
| "mean_token_accuracy": 0.7120864883065223, | |
| "num_tokens": 44774.0, | |
| "step": 10 | |
| }, | |
| { | |
| "entropy": 0.9664318569004535, | |
| "epoch": 0.14354066985645933, | |
| "grad_norm": 2.2438340187072754, | |
| "learning_rate": 9.333333333333334e-05, | |
| "loss": 1.0039640426635743, | |
| "mean_token_accuracy": 0.8314489215612412, | |
| "num_tokens": 68554.0, | |
| "step": 15 | |
| }, | |
| { | |
| "entropy": 0.7952521093189716, | |
| "epoch": 0.19138755980861244, | |
| "grad_norm": 1.4970792531967163, | |
| "learning_rate": 9.095238095238096e-05, | |
| "loss": 0.9054213523864746, | |
| "mean_token_accuracy": 0.8527463525533676, | |
| "num_tokens": 92672.0, | |
| "step": 20 | |
| }, | |
| { | |
| "entropy": 0.7521916493773461, | |
| "epoch": 0.23923444976076555, | |
| "grad_norm": 1.1931730508804321, | |
| "learning_rate": 8.857142857142857e-05, | |
| "loss": 0.8049167633056641, | |
| "mean_token_accuracy": 0.8651137307286263, | |
| "num_tokens": 115556.0, | |
| "step": 25 | |
| }, | |
| { | |
| "entropy": 0.8046777091920376, | |
| "epoch": 0.28708133971291866, | |
| "grad_norm": 1.1074719429016113, | |
| "learning_rate": 8.61904761904762e-05, | |
| "loss": 0.8548135757446289, | |
| "mean_token_accuracy": 0.8603784069418907, | |
| "num_tokens": 140637.0, | |
| "step": 30 | |
| }, | |
| { | |
| "entropy": 0.6400977578014135, | |
| "epoch": 0.3349282296650718, | |
| "grad_norm": 0.9381627440452576, | |
| "learning_rate": 8.380952380952382e-05, | |
| "loss": 0.6987390518188477, | |
| "mean_token_accuracy": 0.8840002715587616, | |
| "num_tokens": 164217.0, | |
| "step": 35 | |
| }, | |
| { | |
| "entropy": 0.6654842033982277, | |
| "epoch": 0.3827751196172249, | |
| "grad_norm": 2.1283178329467773, | |
| "learning_rate": 8.142857142857143e-05, | |
| "loss": 0.7857039928436279, | |
| "mean_token_accuracy": 0.8724030137062073, | |
| "num_tokens": 186852.0, | |
| "step": 40 | |
| }, | |
| { | |
| "entropy": 0.619146254658699, | |
| "epoch": 0.430622009569378, | |
| "grad_norm": 0.8456487059593201, | |
| "learning_rate": 7.904761904761905e-05, | |
| "loss": 0.6680184364318847, | |
| "mean_token_accuracy": 0.8887932941317558, | |
| "num_tokens": 210073.0, | |
| "step": 45 | |
| }, | |
| { | |
| "entropy": 0.6058806985616684, | |
| "epoch": 0.4784688995215311, | |
| "grad_norm": 0.8580911159515381, | |
| "learning_rate": 7.666666666666667e-05, | |
| "loss": 0.6658339977264405, | |
| "mean_token_accuracy": 0.8919811978936195, | |
| "num_tokens": 233395.0, | |
| "step": 50 | |
| }, | |
| { | |
| "entropy": 0.6354636650532484, | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 0.9746028780937195, | |
| "learning_rate": 7.428571428571429e-05, | |
| "loss": 0.728534460067749, | |
| "mean_token_accuracy": 0.8858045786619186, | |
| "num_tokens": 256677.0, | |
| "step": 55 | |
| }, | |
| { | |
| "entropy": 0.5936117857694626, | |
| "epoch": 0.5741626794258373, | |
| "grad_norm": 0.9922609925270081, | |
| "learning_rate": 7.19047619047619e-05, | |
| "loss": 0.6770713806152344, | |
| "mean_token_accuracy": 0.8887649178504944, | |
| "num_tokens": 278351.0, | |
| "step": 60 | |
| }, | |
| { | |
| "entropy": 0.6688867088407278, | |
| "epoch": 0.6220095693779905, | |
| "grad_norm": 0.9844464659690857, | |
| "learning_rate": 6.952380952380952e-05, | |
| "loss": 0.7745152950286865, | |
| "mean_token_accuracy": 0.8777409210801125, | |
| "num_tokens": 303271.0, | |
| "step": 65 | |
| }, | |
| { | |
| "entropy": 0.7457825832068921, | |
| "epoch": 0.6698564593301436, | |
| "grad_norm": 0.9128448367118835, | |
| "learning_rate": 6.714285714285714e-05, | |
| "loss": 0.8470640182495117, | |
| "mean_token_accuracy": 0.8637880578637123, | |
| "num_tokens": 328315.0, | |
| "step": 70 | |
| }, | |
| { | |
| "entropy": 0.6116038627922535, | |
| "epoch": 0.7177033492822966, | |
| "grad_norm": 0.9624145030975342, | |
| "learning_rate": 6.476190476190477e-05, | |
| "loss": 0.6843190670013428, | |
| "mean_token_accuracy": 0.8896616101264954, | |
| "num_tokens": 351963.0, | |
| "step": 75 | |
| }, | |
| { | |
| "entropy": 0.622330765798688, | |
| "epoch": 0.7655502392344498, | |
| "grad_norm": 0.9209601879119873, | |
| "learning_rate": 6.238095238095239e-05, | |
| "loss": 0.6767851829528808, | |
| "mean_token_accuracy": 0.8867631480097771, | |
| "num_tokens": 375023.0, | |
| "step": 80 | |
| }, | |
| { | |
| "entropy": 0.6198485180735588, | |
| "epoch": 0.8133971291866029, | |
| "grad_norm": 0.946159303188324, | |
| "learning_rate": 6e-05, | |
| "loss": 0.6652565956115722, | |
| "mean_token_accuracy": 0.8853679791092872, | |
| "num_tokens": 399277.0, | |
| "step": 85 | |
| }, | |
| { | |
| "entropy": 0.5564446035772562, | |
| "epoch": 0.861244019138756, | |
| "grad_norm": 0.8137181401252747, | |
| "learning_rate": 5.761904761904762e-05, | |
| "loss": 0.6248233795166016, | |
| "mean_token_accuracy": 0.8972864270210266, | |
| "num_tokens": 421249.0, | |
| "step": 90 | |
| }, | |
| { | |
| "entropy": 0.5795138332992792, | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 0.851652204990387, | |
| "learning_rate": 5.5238095238095244e-05, | |
| "loss": 0.6658082008361816, | |
| "mean_token_accuracy": 0.8966752380132675, | |
| "num_tokens": 444070.0, | |
| "step": 95 | |
| }, | |
| { | |
| "entropy": 0.6267214026302099, | |
| "epoch": 0.9569377990430622, | |
| "grad_norm": 0.8740034103393555, | |
| "learning_rate": 5.285714285714286e-05, | |
| "loss": 0.7174222946166993, | |
| "mean_token_accuracy": 0.880531644821167, | |
| "num_tokens": 467253.0, | |
| "step": 100 | |
| }, | |
| { | |
| "entropy": 0.6104649793770578, | |
| "epoch": 1.0, | |
| "grad_norm": 1.397324800491333, | |
| "learning_rate": 5.047619047619048e-05, | |
| "loss": 0.723299789428711, | |
| "mean_token_accuracy": 0.8877596159776052, | |
| "num_tokens": 489018.0, | |
| "step": 105 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 210, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1480266593471232.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |