| { |
| "best_global_step": 50, |
| "best_metric": 7.37368631362915, |
| "best_model_checkpoint": "./results/InternVL3_5-1B-HF-mvbench-action-sequence/checkpoint-50", |
| "epoch": 2.0, |
| "eval_steps": 10, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.04, |
| "grad_norm": 14.584775924682617, |
| "learning_rate": 0.0, |
| "loss": 9.0389, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 9.947012901306152, |
| "learning_rate": 0.00016, |
| "loss": 8.593, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 1.4266618490219116, |
| "learning_rate": 0.0001961261695938319, |
| "loss": 7.7412, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_loss": 7.5631184577941895, |
| "eval_runtime": 167.6224, |
| "eval_samples_per_second": 0.227, |
| "eval_steps_per_second": 0.113, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.6724503040313721, |
| "learning_rate": 0.00018090169943749476, |
| "loss": 7.512, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.36311936378479004, |
| "learning_rate": 0.0001559192903470747, |
| "loss": 7.438, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_loss": 7.4134345054626465, |
| "eval_runtime": 166.199, |
| "eval_samples_per_second": 0.229, |
| "eval_steps_per_second": 0.114, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.22411897778511047, |
| "learning_rate": 0.00012419218955996676, |
| "loss": 7.4046, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 0.22080613672733307, |
| "learning_rate": 8.954715367323468e-05, |
| "loss": 7.3872, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.2, |
| "eval_loss": 7.382411956787109, |
| "eval_runtime": 165.5898, |
| "eval_samples_per_second": 0.229, |
| "eval_steps_per_second": 0.115, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.4, |
| "grad_norm": 0.14537394046783447, |
| "learning_rate": 5.616288532109225e-05, |
| "loss": 7.3786, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 0.12313056737184525, |
| "learning_rate": 2.8066019966134904e-05, |
| "loss": 7.3751, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6, |
| "eval_loss": 7.374787330627441, |
| "eval_runtime": 165.5554, |
| "eval_samples_per_second": 0.23, |
| "eval_steps_per_second": 0.115, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.8, |
| "grad_norm": 0.1258918195962906, |
| "learning_rate": 8.645454235739903e-06, |
| "loss": 7.3743, |
| "step": 45 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.10916738212108612, |
| "learning_rate": 2.4359497401758024e-07, |
| "loss": 7.3751, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 7.37368631362915, |
| "eval_runtime": 164.4808, |
| "eval_samples_per_second": 0.231, |
| "eval_steps_per_second": 0.116, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0, |
| "step": 50, |
| "total_flos": 4409876126564352.0, |
| "train_loss": 7.566836528778076, |
| "train_runtime": 2225.4804, |
| "train_samples_per_second": 0.135, |
| "train_steps_per_second": 0.022 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 50, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "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": 4409876126564352.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
