| { |
| "best_global_step": 100, |
| "best_metric": 0.1666431427001953, |
| "best_model_checkpoint": "/output/evoxtral-lora/checkpoint-100", |
| "epoch": 1.9702970297029703, |
| "eval_steps": 50, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.09900990099009901, |
| "grad_norm": 5.802285194396973, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 0.9557, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.19801980198019803, |
| "grad_norm": 2.306023597717285, |
| "learning_rate": 3.6e-05, |
| "loss": 0.461, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.297029702970297, |
| "grad_norm": 2.0266661643981934, |
| "learning_rate": 5.6000000000000006e-05, |
| "loss": 0.3281, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.39603960396039606, |
| "grad_norm": 1.5811512470245361, |
| "learning_rate": 7.6e-05, |
| "loss": 0.2656, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.49504950495049505, |
| "grad_norm": 1.5266460180282593, |
| "learning_rate": 9.6e-05, |
| "loss": 0.2477, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.594059405940594, |
| "grad_norm": 1.0605043172836304, |
| "learning_rate": 0.000116, |
| "loss": 0.2199, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.693069306930693, |
| "grad_norm": 1.4974918365478516, |
| "learning_rate": 0.00013600000000000003, |
| "loss": 0.1935, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.7920792079207921, |
| "grad_norm": 1.1257297992706299, |
| "learning_rate": 0.00015600000000000002, |
| "loss": 0.1739, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.8910891089108911, |
| "grad_norm": 0.9485541582107544, |
| "learning_rate": 0.00017600000000000002, |
| "loss": 0.1829, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.9900990099009901, |
| "grad_norm": 0.6643406748771667, |
| "learning_rate": 0.000196, |
| "loss": 0.1887, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.9900990099009901, |
| "eval_loss": 0.1841340959072113, |
| "eval_runtime": 17.7494, |
| "eval_samples_per_second": 5.69, |
| "eval_steps_per_second": 2.873, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.0792079207920793, |
| "grad_norm": 0.7675807476043701, |
| "learning_rate": 0.0001992566788083908, |
| "loss": 0.1535, |
| "step": 55 |
| }, |
| { |
| "epoch": 1.1782178217821782, |
| "grad_norm": 0.6500945687294006, |
| "learning_rate": 0.0001962558656223516, |
| "loss": 0.15, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.2772277227722773, |
| "grad_norm": 3.4771132469177246, |
| "learning_rate": 0.00019102070542141328, |
| "loss": 0.1058, |
| "step": 65 |
| }, |
| { |
| "epoch": 1.3762376237623761, |
| "grad_norm": 6.509069919586182, |
| "learning_rate": 0.0001836727197823842, |
| "loss": 0.148, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.4752475247524752, |
| "grad_norm": 1.21564519405365, |
| "learning_rate": 0.0001743824744123196, |
| "loss": 0.154, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.5742574257425743, |
| "grad_norm": 0.9891815185546875, |
| "learning_rate": 0.00016336561987834153, |
| "loss": 0.1472, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.6732673267326734, |
| "grad_norm": 0.8960129022598267, |
| "learning_rate": 0.00015087788580152206, |
| "loss": 0.1388, |
| "step": 85 |
| }, |
| { |
| "epoch": 1.7722772277227723, |
| "grad_norm": 0.6417158842086792, |
| "learning_rate": 0.00013720914471250644, |
| "loss": 0.1544, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.8712871287128712, |
| "grad_norm": 0.6971271634101868, |
| "learning_rate": 0.00012267668336210413, |
| "loss": 0.1216, |
| "step": 95 |
| }, |
| { |
| "epoch": 1.9702970297029703, |
| "grad_norm": 0.6400907039642334, |
| "learning_rate": 0.00010761783767709182, |
| "loss": 0.1347, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.9702970297029703, |
| "eval_loss": 0.1666431427001953, |
| "eval_runtime": 17.7221, |
| "eval_samples_per_second": 5.699, |
| "eval_steps_per_second": 2.878, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 153, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.8528360565456896e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
