Training in progress, step 240, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1d444d1bb45f270e0c212f44c95682120889252458945d6a4d19bcbbfffc231
+oid sha256:6aa1d020dcc8571e736d654589ba8f174c1261833c4fd9844032b87ef8b2d71b
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63de950bd110c9cc3cfce72263ab1713819eea42a4aca0e3762bb97c75bdd431
+oid sha256:859b8602a8478ae50e82324137580c38819b9c9bf26b6010fcb6c1f0f0e866d6
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e93008c0a80496fa52f28860e36ff15ef6ec8281cd46549629ed9ab1ae896a41
+oid sha256:a355d7114e76b054cea02bceff9680d87cea336f904402a275024cc0ffe7579c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f21939c458dd70022a2e060c2bded3f42858a595a1129248ef019a10b6eabb0
+oid sha256:ded87d71d8bbba78392a1f9d1a58531264c1ec39c9fa611e64bbe0bf1666151c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3041087026852151,
+  "epoch": 0.3105791006146878,
   "eval_steps": 386,
-  "global_step": 235,
+  "global_step": 240,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1660,6 +1660,41 @@
       "learning_rate": 9.941938141526354e-05,
       "loss": 0.869,
       "step": 235
+    },
+    {
+      "epoch": 0.3054027822711097,
+      "grad_norm": 0.8476676344871521,
+      "learning_rate": 9.94130998347016e-05,
+      "loss": 0.8849,
+      "step": 236
+    },
+    {
+      "epoch": 0.30669686185700423,
+      "grad_norm": 0.8454031944274902,
+      "learning_rate": 9.940678465780728e-05,
+      "loss": 0.9102,
+      "step": 237
+    },
+    {
+      "epoch": 0.30799094144289874,
+      "grad_norm": 0.8514583706855774,
+      "learning_rate": 9.940043588887438e-05,
+      "loss": 0.9723,
+      "step": 238
+    },
+    {
+      "epoch": 0.3092850210287933,
+      "grad_norm": 0.7330415844917297,
+      "learning_rate": 9.939405353221942e-05,
+      "loss": 0.9537,
+      "step": 239
+    },
+    {
+      "epoch": 0.3105791006146878,
+      "grad_norm": 0.9652897715568542,
+      "learning_rate": 9.938763759218185e-05,
+      "loss": 0.9736,
+      "step": 240
     }
   ],
   "logging_steps": 1,
@@ -1679,7 +1714,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.6271523534798848e+17,
+  "total_flos": 2.6830492120645632e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null