Upload trainer_state.json

trainer_state.json

@@ -0,0 +1,75 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.004966476285075739,
+  "eval_steps": 500,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008277460475126231,
+      "grad_norm": 0.666200578212738,
+      "learning_rate": 0.00018545454545454545,
+      "loss": 2.806,
+      "step": 10
+    },
+    {
+      "epoch": 0.0016554920950252463,
+      "grad_norm": 0.7228823304176331,
+      "learning_rate": 0.0001490909090909091,
+      "loss": 2.4029,
+      "step": 20
+    },
+    {
+      "epoch": 0.0024832381425378696,
+      "grad_norm": 0.6035403609275818,
+      "learning_rate": 0.00011272727272727272,
+      "loss": 2.4103,
+      "step": 30
+    },
+    {
+      "epoch": 0.0033109841900504926,
+      "grad_norm": 0.6814154386520386,
+      "learning_rate": 7.636363636363637e-05,
+      "loss": 2.367,
+      "step": 40
+    },
+    {
+      "epoch": 0.004138730237563116,
+      "grad_norm": 0.5607640147209167,
+      "learning_rate": 4e-05,
+      "loss": 2.1349,
+      "step": 50
+    },
+    {
+      "epoch": 0.004966476285075739,
+      "grad_norm": 0.6008804440498352,
+      "learning_rate": 3.636363636363636e-06,
+      "loss": 2.2581,
+      "step": 60
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 60,
+  "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": 2.053680226486272e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}