Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77ff29b0c0fd2a49a8ae3d3658b9dea02920bdb913eb7cffa0fc3cd0443f63e7
+oid sha256:97bb3e77d7de4e6ed870bf1d4d1235ec288b4ae6818f94ba391daafdc5c9e1ac
 size 81576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5396b13028f281817d0c53a1040443bce5f3f693327a18389abd8cfae4077a35
+oid sha256:804df7dff392259aaee9c0e9409fa0d8dedd51073bbadcd50c6813e40e48ada2
 size 173094

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fea276383daa6be11cb41bcf079e20917a66b8a1df06264809ff50445c989c9
+oid sha256:70bb08e79cd87e26411515d4cfe540a1dfafd998745c321dfb4680b9ed334a58
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
+oid sha256:859ff0676471245c9481ca25d6d6778d1c7963c39b7877af46bb8ca30a9ead21
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10131712259371833,
+  "epoch": 0.13508949679162446,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 299.317,
       "eval_steps_per_second": 149.658,
       "step": 150
+    },
+    {
+      "epoch": 0.10807159743329955,
+      "grad_norm": 0.17172621190547943,
+      "learning_rate": 0.0002,
+      "loss": 10.5402,
+      "step": 160
+    },
+    {
+      "epoch": 0.11482607227288079,
+      "grad_norm": 0.16112971305847168,
+      "learning_rate": 0.0002,
+      "loss": 10.5407,
+      "step": 170
+    },
+    {
+      "epoch": 0.12158054711246201,
+      "grad_norm": 0.13891266286373138,
+      "learning_rate": 0.0002,
+      "loss": 10.5286,
+      "step": 180
+    },
+    {
+      "epoch": 0.12833502195204322,
+      "grad_norm": 0.13530521094799042,
+      "learning_rate": 0.0002,
+      "loss": 10.5192,
+      "step": 190
+    },
+    {
+      "epoch": 0.13508949679162446,
+      "grad_norm": 0.14056940376758575,
+      "learning_rate": 0.0002,
+      "loss": 10.5219,
+      "step": 200
+    },
+    {
+      "epoch": 0.13508949679162446,
+      "eval_loss": 10.511716842651367,
+      "eval_runtime": 2.1111,
+      "eval_samples_per_second": 295.582,
+      "eval_steps_per_second": 147.791,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 24608872857600.0,
+  "total_flos": 32811830476800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null