Training in progress, step 4000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd3ba167b05ddca415d83ce674f218d12eb00f8de957403146522132701a0645
+oid sha256:7a9cf64b63b7766902a74424e2b9849dd20993349b621f4131a344d2c85b4630
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5f73c26475321619da788f02bc5dfa39e953d35292b0e44c815a1d264534b76
+oid sha256:32cf687af0a4ab1e094756b89de6b91731e958f35e735a064e6bab3e4368a447
 size 3497859804

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4df07c96cd5b34fe2c47040206f73bf07f974f4e6c2b7b7219d670c2d00c146
+oid sha256:cb1d32a5240cd2bec4435f56208363b0d59e8bf8c99164c7cbee490171e7de00
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:948ca56b053f56e11e66d405c77732b82bb85e418d1080c5ae696bdf321e898b
+oid sha256:b9c6ca92757145af39d20b47188651ac4ae897a7257a652d8a9acf8e3ccda307
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9167579408543265,
+  "epoch": 2.190580503833516,
   "eval_steps": 500,
-  "global_step": 3500,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -252,6 +252,41 @@
       "learning_rate": 3.473107811842055e-05,
       "loss": 0.9308,
       "step": 3500
+    },
+    {
+      "epoch": 1.9715224534501643,
+      "grad_norm": 1.9522345066070557,
+      "learning_rate": 3.173012410158744e-05,
+      "loss": 0.9195,
+      "step": 3600
+    },
+    {
+      "epoch": 2.026286966046002,
+      "grad_norm": 1.4607131481170654,
+      "learning_rate": 2.8803334322232017e-05,
+      "loss": 0.7255,
+      "step": 3700
+    },
+    {
+      "epoch": 2.08105147864184,
+      "grad_norm": 2.2295525074005127,
+      "learning_rate": 2.596258971120737e-05,
+      "loss": 0.5014,
+      "step": 3800
+    },
+    {
+      "epoch": 2.135815991237678,
+      "grad_norm": 1.6707744598388672,
+      "learning_rate": 2.3219421909949735e-05,
+      "loss": 0.5206,
+      "step": 3900
+    },
+    {
+      "epoch": 2.190580503833516,
+      "grad_norm": 1.4230283498764038,
+      "learning_rate": 2.0584966459246906e-05,
+      "loss": 0.4994,
+      "step": 4000
     }
   ],
   "logging_steps": 100,
@@ -271,7 +306,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6878032741533286e+18,
+  "total_flos": 1.9236155642036552e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null