Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c24fe72f49129c9e44551c10779cc74597f777fd45784f6f6840f62df0a9199
+oid sha256:0c64c557258a0b6e41d43815ba1a70dcf5d7d0b17e51ffcae4ef3574dd348ddd
 size 119548152

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80c2eb23702ab6934d3d455ba08d73c2dbafba42cfbb9814e291a120c82afe0e
+oid sha256:3eedc757c7adfd3ab3f77e0ec2da9aad31518809daa27a9912a6e4f0337656dd
 size 61495885

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b55bf1edf4097452e864b2cf40aefb3c8f7fb98fea8d7775440dfebc16594684
+oid sha256:4c5350fc7388f5d7b90b3dba78d650d7dba8cc269267d96785143b92b85e0ce3
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:386e11d6439863088e392e55ef6fd563f4ad5287224d8fde3b0ffc2cfc757a11
+oid sha256:b88720f588cb00d451738c3bff3bafa43775b68fba718dd44b3fb95ebae233ed
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5577244841048522,
+  "epoch": 0.6692693809258227,
   "eval_steps": 500,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -183,6 +183,41 @@
       "learning_rate": 8.355878419119657e-05,
       "loss": 0.2992835521697998,
       "step": 250
+    },
+    {
+      "epoch": 0.5800334634690463,
+      "grad_norm": 1.5215120315551758,
+      "learning_rate": 7.667254893103519e-05,
+      "loss": 0.3270727634429932,
+      "step": 260
+    },
+    {
+      "epoch": 0.6023424428332403,
+      "grad_norm": 0.4536781311035156,
+      "learning_rate": 6.990149264650814e-05,
+      "loss": 0.29621281623840334,
+      "step": 270
+    },
+    {
+      "epoch": 0.6246514221974344,
+      "grad_norm": 0.47364547848701477,
+      "learning_rate": 6.32790473368728e-05,
+      "loss": 0.2747994661331177,
+      "step": 280
+    },
+    {
+      "epoch": 0.6469604015616286,
+      "grad_norm": 0.4716944992542267,
+      "learning_rate": 5.6837911236698536e-05,
+      "loss": 0.3186234474182129,
+      "step": 290
+    },
+    {
+      "epoch": 0.6692693809258227,
+      "grad_norm": 0.42809948325157166,
+      "learning_rate": 5.060988736877366e-05,
+      "loss": 0.28460078239440917,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -202,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4102700862014016.0,
+  "total_flos": 4907871918681792.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null