Training in progress, step 795, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af1d514de1a6c8c240084c2abe4fb229e803cbb3f979d7290c1732d9e8a5122b
+oid sha256:010c2a2b840c3fde77f5f0db5ad5bd6f0a52b58296feec5b8fd9dc9e42d54370
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b7db8cc663173d80853c1b54864d85bd623d219d83845ca314b5cda205766bf
+oid sha256:feeb714d469e3a6e68b9df8c7aa45ef9b97a6c08822ae8c12a628b95f1875fed
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:063fd63bc73224a76249067a1eeeb31dc678e9656124df16bfa7ce512e017f7f
+oid sha256:a4c3bbf6e51e06c9204f77b5c5a1350738f864223365e0f7477b14a5405e97ae
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94c0126f420d4eb985c03c001ae7f8b7fc9b010855fef21b025980a5ae889902
+oid sha256:f7396be3b2d86ed6e3fcd71c7b4f2cd360bbd7492a3b7c96b0d16d251f623454
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0223228728566807,
+  "epoch": 1.0287932707861533,
   "eval_steps": 386,
-  "global_step": 790,
+  "global_step": 795,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5561,6 +5561,41 @@
       "learning_rate": 9.097729883761976e-05,
       "loss": 0.6884,
       "step": 790
+    },
+    {
+      "epoch": 1.0236169524425751,
+      "grad_norm": 0.7473916411399841,
+      "learning_rate": 9.095366056890302e-05,
+      "loss": 0.7346,
+      "step": 791
+    },
+    {
+      "epoch": 1.0249110320284698,
+      "grad_norm": 0.7097285985946655,
+      "learning_rate": 9.09299944554893e-05,
+      "loss": 0.825,
+      "step": 792
+    },
+    {
+      "epoch": 1.0262051116143642,
+      "grad_norm": 0.7450020909309387,
+      "learning_rate": 9.09063005134694e-05,
+      "loss": 0.8589,
+      "step": 793
+    },
+    {
+      "epoch": 1.027499191200259,
+      "grad_norm": 0.828708291053772,
+      "learning_rate": 9.088257875895297e-05,
+      "loss": 0.8284,
+      "step": 794
+    },
+    {
+      "epoch": 1.0287932707861533,
+      "grad_norm": 0.7440184354782104,
+      "learning_rate": 9.085882920806861e-05,
+      "loss": 0.8285,
+      "step": 795
     }
   ],
   "logging_steps": 1,
@@ -5580,7 +5615,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.831004945646879e+17,
+  "total_flos": 8.886901804231557e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null