| { | |
| "best_global_step": 16500, | |
| "best_metric": 0.7287469506263733, | |
| "best_model_checkpoint": "/kaggle/working/qwen2vl-lora-kaggle-7b-final/checkpoint-16500", | |
| "epoch": 2.078761981753089, | |
| "eval_steps": 1500, | |
| "global_step": 18000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17323016514609077, | |
| "grad_norm": 6.711312770843506, | |
| "learning_rate": 0.00016671111111111114, | |
| "loss": 1.3268, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.17323016514609077, | |
| "eval_loss": 1.19234037399292, | |
| "eval_runtime": 1860.9833, | |
| "eval_samples_per_second": 4.652, | |
| "eval_steps_per_second": 0.582, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.34646033029218154, | |
| "grad_norm": 6.009303092956543, | |
| "learning_rate": 0.00013340000000000002, | |
| "loss": 1.1136, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.34646033029218154, | |
| "eval_loss": 1.0842527151107788, | |
| "eval_runtime": 1839.1176, | |
| "eval_samples_per_second": 4.708, | |
| "eval_steps_per_second": 0.589, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.5196904954382723, | |
| "grad_norm": 6.109352111816406, | |
| "learning_rate": 0.0001000888888888889, | |
| "loss": 1.0529, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.5196904954382723, | |
| "eval_loss": 1.0141185522079468, | |
| "eval_runtime": 1657.6525, | |
| "eval_samples_per_second": 5.223, | |
| "eval_steps_per_second": 0.653, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.6929206605843631, | |
| "grad_norm": 4.705984592437744, | |
| "learning_rate": 6.675555555555556e-05, | |
| "loss": 0.9722, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.6929206605843631, | |
| "eval_loss": 0.9674409031867981, | |
| "eval_runtime": 1626.534, | |
| "eval_samples_per_second": 5.323, | |
| "eval_steps_per_second": 0.666, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.8661508257304539, | |
| "grad_norm": 4.535302639007568, | |
| "learning_rate": 3.3444444444444443e-05, | |
| "loss": 0.9063, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.8661508257304539, | |
| "eval_loss": 0.8994740843772888, | |
| "eval_runtime": 1632.7947, | |
| "eval_samples_per_second": 5.303, | |
| "eval_steps_per_second": 0.663, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.0393809908765446, | |
| "grad_norm": 3.0943076610565186, | |
| "learning_rate": 1.1111111111111112e-07, | |
| "loss": 0.8093, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.0393809908765446, | |
| "eval_loss": 0.861297607421875, | |
| "eval_runtime": 1634.8907, | |
| "eval_samples_per_second": 5.296, | |
| "eval_steps_per_second": 0.662, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.2126111560226354, | |
| "grad_norm": 5.95033597946167, | |
| "learning_rate": 8.341111111111112e-05, | |
| "loss": 0.7003, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.2126111560226354, | |
| "eval_loss": 0.9596555233001709, | |
| "eval_runtime": 1717.5683, | |
| "eval_samples_per_second": 5.041, | |
| "eval_steps_per_second": 0.631, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.3858413211687262, | |
| "grad_norm": 3.0124402046203613, | |
| "learning_rate": 6.674444444444445e-05, | |
| "loss": 0.7043, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.3858413211687262, | |
| "eval_loss": 0.9195936322212219, | |
| "eval_runtime": 1693.4571, | |
| "eval_samples_per_second": 5.113, | |
| "eval_steps_per_second": 0.64, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.559071486314817, | |
| "grad_norm": 4.148472309112549, | |
| "learning_rate": 5.007777777777778e-05, | |
| "loss": 0.648, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.559071486314817, | |
| "eval_loss": 0.8523986339569092, | |
| "eval_runtime": 1850.021, | |
| "eval_samples_per_second": 4.68, | |
| "eval_steps_per_second": 0.585, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.7323016514609078, | |
| "grad_norm": 4.331279754638672, | |
| "learning_rate": 3.3422222222222224e-05, | |
| "loss": 0.6011, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.7323016514609078, | |
| "eval_loss": 0.789742112159729, | |
| "eval_runtime": 1812.1796, | |
| "eval_samples_per_second": 4.778, | |
| "eval_steps_per_second": 0.598, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.9055318166069986, | |
| "grad_norm": 4.271030902862549, | |
| "learning_rate": 1.6766666666666667e-05, | |
| "loss": 0.5447, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.9055318166069986, | |
| "eval_loss": 0.7287469506263733, | |
| "eval_runtime": 1825.2328, | |
| "eval_samples_per_second": 4.744, | |
| "eval_steps_per_second": 0.593, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.078761981753089, | |
| "grad_norm": 11.417400360107422, | |
| "learning_rate": 1.1111111111111112e-07, | |
| "loss": 0.3931, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.078761981753089, | |
| "eval_loss": 0.7414062023162842, | |
| "eval_runtime": 1830.7862, | |
| "eval_samples_per_second": 4.729, | |
| "eval_steps_per_second": 0.592, | |
| "step": 18000 | |
| } | |
| ], | |
| "logging_steps": 1500, | |
| "max_steps": 18000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 1500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.493225004573696e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |