Training in progress, step 245, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aa1d020dcc8571e736d654589ba8f174c1261833c4fd9844032b87ef8b2d71b
+oid sha256:c1589e42cbae5378987344eae93a5cbeb6aaea407f7da88b4a6f4a9d93d04e89
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:859b8602a8478ae50e82324137580c38819b9c9bf26b6010fcb6c1f0f0e866d6
+oid sha256:e6cf8294ac17ea5a1d733fcc4cfdc564357fe4b651af698fb1c9e155e20e5cd8
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a355d7114e76b054cea02bceff9680d87cea336f904402a275024cc0ffe7579c
+oid sha256:386ad13fe5d816f22a0cb03c574c387eb21070a41c3bcfa2c61c742027c54d4e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ded87d71d8bbba78392a1f9d1a58531264c1ec39c9fa611e64bbe0bf1666151c
+oid sha256:2fb0b702704ac2295f35bde3f325d34f67803c665d4df40762f063d3651311c1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3105791006146878,
+  "epoch": 0.3170494985441605,
   "eval_steps": 386,
-  "global_step": 240,
+  "global_step": 245,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1695,6 +1695,41 @@
       "learning_rate": 9.938763759218185e-05,
       "loss": 0.9736,
       "step": 240
+    },
+    {
+      "epoch": 0.31187318020058236,
+      "grad_norm": 0.7517886161804199,
+      "learning_rate": 9.93811880731239e-05,
+      "loss": 0.8436,
+      "step": 241
+    },
+    {
+      "epoch": 0.31316725978647686,
+      "grad_norm": 0.8159210681915283,
+      "learning_rate": 9.937470497943064e-05,
+      "loss": 0.7521,
+      "step": 242
+    },
+    {
+      "epoch": 0.3144613393723714,
+      "grad_norm": 0.9554911851882935,
+      "learning_rate": 9.936818831550998e-05,
+      "loss": 1.1076,
+      "step": 243
+    },
+    {
+      "epoch": 0.3157554189582659,
+      "grad_norm": 0.8745877742767334,
+      "learning_rate": 9.936163808579266e-05,
+      "loss": 0.8908,
+      "step": 244
+    },
+    {
+      "epoch": 0.3170494985441605,
+      "grad_norm": 0.8050674200057983,
+      "learning_rate": 9.93550542947322e-05,
+      "loss": 1.0134,
+      "step": 245
     }
   ],
   "logging_steps": 1,
@@ -1714,7 +1749,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.6830492120645632e+17,
+  "total_flos": 2.7389460706492416e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null