CoolFace
Modelpublic

Ramkumar-AI-developer/adapter-llama-3.2-3b

sourceHugging Faceupdated 1y agoView on Hugging Face
0likes4downloads
trainer_state.json210 linesDownload Raw Back to root
1{2  "best_global_step": null,3  "best_metric": null,4  "best_model_checkpoint": null,5  "epoch": 0.12048192771084337,6  "eval_steps": 500,7  "global_step": 25,8  "is_hyper_param_search": false,9  "is_local_process_zero": true,10  "is_world_process_zero": true,11  "log_history": [12    {13      "epoch": 0.004819277108433735,14      "grad_norm": 1.0873982906341553,15      "learning_rate": 0.0,16      "loss": 1.2725,17      "step": 118    },19    {20      "epoch": 0.00963855421686747,21      "grad_norm": 0.7578734755516052,22      "learning_rate": 4e-05,23      "loss": 0.9978,24      "step": 225    },26    {27      "epoch": 0.014457831325301205,28      "grad_norm": 0.7068339586257935,29      "learning_rate": 8e-05,30      "loss": 0.8246,31      "step": 332    },33    {34      "epoch": 0.01927710843373494,35      "grad_norm": 0.6248342990875244,36      "learning_rate": 0.00012,37      "loss": 0.7956,38      "step": 439    },40    {41      "epoch": 0.024096385542168676,42      "grad_norm": 0.2963731288909912,43      "learning_rate": 0.00016,44      "loss": 0.7756,45      "step": 546    },47    {48      "epoch": 0.02891566265060241,49      "grad_norm": 0.226631298661232,50      "learning_rate": 0.0002,51      "loss": 0.6459,52      "step": 653    },54    {55      "epoch": 0.033734939759036145,56      "grad_norm": 0.2879922091960907,57      "learning_rate": 0.00019,58      "loss": 0.5224,59      "step": 760    },61    {62      "epoch": 0.03855421686746988,63      "grad_norm": 0.30339133739471436,64      "learning_rate": 0.00018,65      "loss": 0.5523,66      "step": 867    },68    {69      "epoch": 0.043373493975903614,70      "grad_norm": 0.2749564051628113,71      "learning_rate": 0.00017,72      "loss": 0.7496,73      "step": 974    },75    {76      "epoch": 0.04819277108433735,77      "grad_norm": 0.20403070747852325,78      "learning_rate": 0.00016,79      "loss": 0.6514,80      "step": 1081    },82    {83      "epoch": 0.05301204819277108,84      "grad_norm": 0.2553975582122803,85      "learning_rate": 0.00015000000000000001,86      "loss": 0.6296,87      "step": 1188    },89    {90      "epoch": 0.05783132530120482,91      "grad_norm": 0.20366790890693665,92      "learning_rate": 0.00014,93      "loss": 0.5187,94      "step": 1295    },96    {97      "epoch": 0.06265060240963856,98      "grad_norm": 0.18309777975082397,99      "learning_rate": 0.00013000000000000002,100      "loss": 0.5334,101      "step": 13102    },103    {104      "epoch": 0.06746987951807229,105      "grad_norm": 0.17828117311000824,106      "learning_rate": 0.00012,107      "loss": 0.515,108      "step": 14109    },110    {111      "epoch": 0.07228915662650602,112      "grad_norm": 0.22142553329467773,113      "learning_rate": 0.00011000000000000002,114      "loss": 0.6641,115      "step": 15116    },117    {118      "epoch": 0.07710843373493977,119      "grad_norm": 0.1471155434846878,120      "learning_rate": 0.0001,121      "loss": 0.4286,122      "step": 16123    },124    {125      "epoch": 0.0819277108433735,126      "grad_norm": 0.21006067097187042,127      "learning_rate": 9e-05,128      "loss": 0.5471,129      "step": 17130    },131    {132      "epoch": 0.08674698795180723,133      "grad_norm": 0.1845540702342987,134      "learning_rate": 8e-05,135      "loss": 0.5242,136      "step": 18137    },138    {139      "epoch": 0.09156626506024096,140      "grad_norm": 0.16557849943637848,141      "learning_rate": 7e-05,142      "loss": 0.585,143      "step": 19144    },145    {146      "epoch": 0.0963855421686747,147      "grad_norm": 0.24527060985565186,148      "learning_rate": 6e-05,149      "loss": 0.55,150      "step": 20151    },152    {153      "epoch": 0.10120481927710843,154      "grad_norm": 0.16817006468772888,155      "learning_rate": 5e-05,156      "loss": 0.4271,157      "step": 21158    },159    {160      "epoch": 0.10602409638554217,161      "grad_norm": 0.1981966197490692,162      "learning_rate": 4e-05,163      "loss": 0.5959,164      "step": 22165    },166    {167      "epoch": 0.1108433734939759,168      "grad_norm": 0.18087905645370483,169      "learning_rate": 3e-05,170      "loss": 0.4993,171      "step": 23172    },173    {174      "epoch": 0.11566265060240964,175      "grad_norm": 0.197529137134552,176      "learning_rate": 2e-05,177      "loss": 0.5422,178      "step": 24179    },180    {181      "epoch": 0.12048192771084337,182      "grad_norm": 0.16518113017082214,183      "learning_rate": 1e-05,184      "loss": 0.4278,185      "step": 25186    }187  ],188  "logging_steps": 1,189  "max_steps": 25,190  "num_input_tokens_seen": 0,191  "num_train_epochs": 1,192  "save_steps": 500,193  "stateful_callbacks": {194    "TrainerControl": {195      "args": {196        "should_epoch_stop": false,197        "should_evaluate": false,198        "should_log": false,199        "should_save": true,200        "should_training_stop": true201      },202      "attributes": {}203    }204  },205  "total_flos": 3.0457486116962304e+16,206  "train_batch_size": 4,207  "trial_name": null,208  "trial_params": null209}210