Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:370f29b91890cfd7a75752ef406f05f15109a2b092968b5acb39ab8f163a4da8
+oid sha256:68ad55d1aeea52955d58b25b3df7a1687fe456c32107e022432ff258df736c2a
 size 19552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22ec27437d21e6867c9432990768b7b19f56a5ed1753b641a430c3321007dd80
+oid sha256:7b68fae4eef67b552b93d626c29907fdee6dfc26149f536a7586ba07b0a80fac
 size 44354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32578516f496ea3225c8a3eb0630278f273401f8d45c1e7c59bf8f3bbb0f0a3f
+oid sha256:0e24b96fe81a7ba92d3e59714ad06f0a9469a930b3dca5959f4862b3dc96b663
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43427779b8e6e83ef9780afcdea7472d2419de40e6f85cfedb90b60f89a2ff0f
+oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14129202871174915,
+  "epoch": 0.1511144692104269,
   "eval_steps": 17,
-  "global_step": 187,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -537,6 +537,34 @@
       "eval_samples_per_second": 36.141,
       "eval_steps_per_second": 4.522,
       "step": 187
+    },
+    {
+      "epoch": 0.14280317340385343,
+      "grad_norm": 0.0606582872569561,
+      "learning_rate": 8.247462563808817e-07,
+      "loss": 12.4418,
+      "step": 189
+    },
+    {
+      "epoch": 0.14506989044200982,
+      "grad_norm": 0.06177810579538345,
+      "learning_rate": 4.367965336512403e-07,
+      "loss": 12.4451,
+      "step": 192
+    },
+    {
+      "epoch": 0.14733660748016622,
+      "grad_norm": 0.05963071435689926,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 12.4409,
+      "step": 195
+    },
+    {
+      "epoch": 0.14960332451832262,
+      "grad_norm": 0.06588052958250046,
+      "learning_rate": 2.7337132953697554e-08,
+      "loss": 12.4448,
+      "step": 198
     }
   ],
   "logging_steps": 3,
@@ -551,12 +579,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 414330126336.0,
+  "total_flos": 442692009984.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null