CoolFace
Modelpublic

UI-Simulator/UI_Simulator_Grow_Web_Step2

sourceHugging Facemitupdated 11mo agoView on Hugging Face
0likes8downloads
trainer_state.json171 linesDownload Raw Back to root
1{2  "best_metric": null,3  "best_model_checkpoint": null,4  "epoch": 1.9915254237288136,5  "eval_steps": 500,6  "global_step": 78,7  "is_hyper_param_search": false,8  "is_local_process_zero": true,9  "is_world_process_zero": true,10  "log_history": [11    {12      "epoch": 0.025423728813559324,13      "grad_norm": 0.08035527647801548,14      "learning_rate": 1.25e-06,15      "loss": 0.4007,16      "step": 117    },18    {19      "epoch": 0.1271186440677966,20      "grad_norm": 0.05733009561118041,21      "learning_rate": 6.25e-06,22      "loss": 0.4134,23      "step": 524    },25    {26      "epoch": 0.2542372881355932,27      "grad_norm": 0.061316952771613246,28      "learning_rate": 9.979871469976197e-06,29      "loss": 0.4061,30      "step": 1031    },32    {33      "epoch": 0.3813559322033898,34      "grad_norm": 0.0706914793637617,35      "learning_rate": 9.755282581475769e-06,36      "loss": 0.4018,37      "step": 1538    },39    {40      "epoch": 0.5084745762711864,41      "grad_norm": 0.06306250853537879,42      "learning_rate": 9.292243968009332e-06,43      "loss": 0.4068,44      "step": 2045    },46    {47      "epoch": 0.635593220338983,48      "grad_norm": 0.05396739437655817,49      "learning_rate": 8.613974319136959e-06,50      "loss": 0.388,51      "step": 2552    },53    {54      "epoch": 0.7627118644067796,55      "grad_norm": 0.055943979296443166,56      "learning_rate": 7.754484907260513e-06,57      "loss": 0.3379,58      "step": 3059    },60    {61      "epoch": 0.8898305084745762,62      "grad_norm": 0.06643011122771461,63      "learning_rate": 6.7568741204067145e-06,64      "loss": 0.3801,65      "step": 3566    },67    {68      "epoch": 0.9915254237288136,69      "eval_loss": 0.42687076330184937,70      "eval_runtime": 29.2208,71      "eval_samples_per_second": 18.788,72      "eval_steps_per_second": 4.723,73      "step": 3974    },75    {76      "epoch": 1.0254237288135593,77      "grad_norm": 0.1257204507458321,78      "learning_rate": 5.671166329088278e-06,79      "loss": 0.4294,80      "step": 4081    },82    {83      "epoch": 1.152542372881356,84      "grad_norm": 0.061247984812326635,85      "learning_rate": 4.551803455482833e-06,86      "loss": 0.3162,87      "step": 4588    },89    {90      "epoch": 1.2796610169491525,91      "grad_norm": 0.06297833414755911,92      "learning_rate": 3.4549150281252635e-06,93      "loss": 0.3145,94      "step": 5095    },96    {97      "epoch": 1.4067796610169492,98      "grad_norm": 0.06687382967843461,99      "learning_rate": 2.43550361297047e-06,100      "loss": 0.2941,101      "step": 55102    },103    {104      "epoch": 1.5338983050847457,105      "grad_norm": 0.06683369207674608,106      "learning_rate": 1.544686755065677e-06,107      "loss": 0.3145,108      "step": 60109    },110    {111      "epoch": 1.6610169491525424,112      "grad_norm": 0.0813495468013659,113      "learning_rate": 8.271337313934869e-07,114      "loss": 0.2945,115      "step": 65116    },117    {118      "epoch": 1.788135593220339,119      "grad_norm": 0.07371530295761193,120      "learning_rate": 3.18825646801314e-07,121      "loss": 0.3056,122      "step": 70123    },124    {125      "epoch": 1.9152542372881356,126      "grad_norm": 0.06581699726337101,127      "learning_rate": 4.52511911603265e-08,128      "loss": 0.2775,129      "step": 75130    },131    {132      "epoch": 1.9915254237288136,133      "eval_loss": 0.443694531917572,134      "eval_runtime": 28.5624,135      "eval_samples_per_second": 19.221,136      "eval_steps_per_second": 4.832,137      "step": 78138    },139    {140      "epoch": 1.9915254237288136,141      "step": 78,142      "total_flos": 1.99474976032555e+17,143      "train_loss": 0.34869656616296524,144      "train_runtime": 1209.7175,145      "train_samples_per_second": 3.118,146      "train_steps_per_second": 0.064147    }148  ],149  "logging_steps": 5,150  "max_steps": 78,151  "num_input_tokens_seen": 0,152  "num_train_epochs": 2,153  "save_steps": 500,154  "stateful_callbacks": {155    "TrainerControl": {156      "args": {157        "should_epoch_stop": false,158        "should_evaluate": false,159        "should_log": false,160        "should_save": true,161        "should_training_stop": true162      },163      "attributes": {}164    }165  },166  "total_flos": 1.99474976032555e+17,167  "train_batch_size": 1,168  "trial_name": null,169  "trial_params": null170}171