Delete trainer_state.json

trainer_state.json

@@ -1,151 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.0,
-  "eval_steps": 200,
-  "global_step": 2138,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.09354536950420954,
-      "eval_accuracy": 0.5728155339805825,
-      "eval_loss": 0.26913607120513916,
-      "eval_runtime": 16.2852,
-      "eval_samples_per_second": 69.572,
-      "eval_steps_per_second": 8.72,
-      "step": 200
-    },
-    {
-      "epoch": 0.18709073900841908,
-      "eval_accuracy": 0.6425419240953222,
-      "eval_loss": 0.25252005457878113,
-      "eval_runtime": 19.5477,
-      "eval_samples_per_second": 57.961,
-      "eval_steps_per_second": 7.264,
-      "step": 400
-    },
-    {
-      "epoch": 0.23386342376052385,
-      "grad_norm": 1.209536075592041,
-      "learning_rate": 3.8306828811973814e-05,
-      "loss": 0.3012,
-      "step": 500
-    },
-    {
-      "epoch": 0.2806361085126286,
-      "eval_accuracy": 0.6857899382171226,
-      "eval_loss": 0.237541064620018,
-      "eval_runtime": 18.6594,
-      "eval_samples_per_second": 60.72,
-      "eval_steps_per_second": 7.61,
-      "step": 600
-    },
-    {
-      "epoch": 0.37418147801683815,
-      "eval_accuracy": 0.7007943512797882,
-      "eval_loss": 0.2300291657447815,
-      "eval_runtime": 17.2054,
-      "eval_samples_per_second": 65.852,
-      "eval_steps_per_second": 8.253,
-      "step": 800
-    },
-    {
-      "epoch": 0.4677268475210477,
-      "grad_norm": 1.29645836353302,
-      "learning_rate": 2.6613657623947615e-05,
-      "loss": 0.2615,
-      "step": 1000
-    },
-    {
-      "epoch": 0.4677268475210477,
-      "eval_accuracy": 0.7193292144748455,
-      "eval_loss": 0.2208750993013382,
-      "eval_runtime": 16.5003,
-      "eval_samples_per_second": 68.665,
-      "eval_steps_per_second": 8.606,
-      "step": 1000
-    },
-    {
-      "epoch": 0.5612722170252572,
-      "eval_accuracy": 0.7131509267431597,
-      "eval_loss": 0.21556398272514343,
-      "eval_runtime": 16.4369,
-      "eval_samples_per_second": 68.93,
-      "eval_steps_per_second": 8.639,
-      "step": 1200
-    },
-    {
-      "epoch": 0.6548175865294668,
-      "eval_accuracy": 0.7422771403353927,
-      "eval_loss": 0.21151377260684967,
-      "eval_runtime": 16.5068,
-      "eval_samples_per_second": 68.638,
-      "eval_steps_per_second": 8.603,
-      "step": 1400
-    },
-    {
-      "epoch": 0.7015902712815716,
-      "grad_norm": 1.2882506847381592,
-      "learning_rate": 1.492048643592142e-05,
-      "loss": 0.2496,
-      "step": 1500
-    },
-    {
-      "epoch": 0.7483629560336763,
-      "eval_accuracy": 0.7502206531332745,
-      "eval_loss": 0.2063572257757187,
-      "eval_runtime": 18.4271,
-      "eval_samples_per_second": 61.486,
-      "eval_steps_per_second": 7.706,
-      "step": 1600
-    },
-    {
-      "epoch": 0.8419083255378859,
-      "eval_accuracy": 0.7546337157987644,
-      "eval_loss": 0.2039937973022461,
-      "eval_runtime": 17.4715,
-      "eval_samples_per_second": 64.848,
-      "eval_steps_per_second": 8.128,
-      "step": 1800
-    },
-    {
-      "epoch": 0.9354536950420954,
-      "grad_norm": 1.526292324066162,
-      "learning_rate": 3.2273152478952295e-06,
-      "loss": 0.2373,
-      "step": 2000
-    },
-    {
-      "epoch": 0.9354536950420954,
-      "eval_accuracy": 0.7405119152691968,
-      "eval_loss": 0.20458175241947174,
-      "eval_runtime": 17.1202,
-      "eval_samples_per_second": 66.179,
-      "eval_steps_per_second": 8.294,
-      "step": 2000
-    }
-  ],
-  "logging_steps": 500,
-  "max_steps": 2138,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 500,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": true
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 4500493926531072.0,
-  "train_batch_size": 8,
-  "trial_name": null,
-  "trial_params": null
-}