Training in progress, step 115, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11e90cb1227c62dec00086873084cd66a60f8e092ba5d04cf008f35af74bb9f9
+oid sha256:0bc94ba8450a510cff44d172874e2147b62017a7b09db70a03ff21bb97b364a7
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cbd86d7bb4028458f06acd973791482cbe7f7a9e432113934e0d5e8b2972256
+oid sha256:fb753185eaccdb5442e4ae0d8f1881afb3f2df47cdcd9c592fca0c8a776ea638
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8bccff553ddf796c56297874a33549d9fa05b99ea8275b995fc72d6e1c7856d
+oid sha256:94bc56f9e3ed1cb490edfa6ed817ab5a627f1fa72c4c42df8f65738ad0756b7b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4276fa00e85ff5423e2bca2a0a2c7a5f8e8110f9fd9dcbe1db6aad4b77cbd607
+oid sha256:edf0fb1dfa2c7ca025c1bcf4459d1d508b2f798ad95b431872a2ea669647ad00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1423487544483986,
+  "epoch": 0.14881915237787124,
   "eval_steps": 386,
-  "global_step": 110,
+  "global_step": 115,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -785,6 +785,41 @@
       "learning_rate": 9.993882081071306e-05,
       "loss": 0.8628,
       "step": 110
+    },
+    {
+      "epoch": 0.14364283403429312,
+      "grad_norm": 1.2776648998260498,
+      "learning_rate": 9.993676494372642e-05,
+      "loss": 0.9742,
+      "step": 111
+    },
+    {
+      "epoch": 0.14493691362018765,
+      "grad_norm": 1.1270071268081665,
+      "learning_rate": 9.993467512436364e-05,
+      "loss": 0.9729,
+      "step": 112
+    },
+    {
+      "epoch": 0.14623099320608218,
+      "grad_norm": 0.8188664317131042,
+      "learning_rate": 9.99325513540456e-05,
+      "loss": 0.9428,
+      "step": 113
+    },
+    {
+      "epoch": 0.1475250727919767,
+      "grad_norm": 1.0760393142700195,
+      "learning_rate": 9.993039363421627e-05,
+      "loss": 0.9482,
+      "step": 114
+    },
+    {
+      "epoch": 0.14881915237787124,
+      "grad_norm": 1.019920825958252,
+      "learning_rate": 9.992820196634273e-05,
+      "loss": 0.9785,
+      "step": 115
     }
   ],
   "logging_steps": 1,
@@ -804,7 +839,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2297308888629248e+17,
+  "total_flos": 1.2856277474476032e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null