Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ce7ee6825bc23bd4bc155ded0e2d10d6841fc7224100087540cf9c5f6e3db3b
+oid sha256:5938c1cb2d7c2699d2fed0b71db5ff6d7b25fab5499f48cf27709f7b64b1bb22
 size 63592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42b99572bec35aec65fc8ed3be17b66b41f6332ceadba0582c5ae18382a0e619
+oid sha256:be7a8419a33d069742f008f3ffea362232d7ffebd31c55d2a1e39452752c347d
 size 132798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c72530c1181e385391bf43f1fdf08c8275fccd52a2134362ec0beb66af41fd8
+oid sha256:856dbd62cf8389a1981718420a83439a3af6cdfa7dbc71deb4da5e8b4980109f
 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": 0.19973368841544606,
+  "epoch": 0.2663115845539281,
   "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": 337.856,
       "eval_steps_per_second": 169.99,
       "step": 150
+    },
+    {
+      "epoch": 0.21304926764314247,
+      "grad_norm": 0.8676323890686035,
+      "learning_rate": 0.0002,
+      "loss": 21.9072,
+      "step": 160
+    },
+    {
+      "epoch": 0.22636484687083888,
+      "grad_norm": 0.8595561385154724,
+      "learning_rate": 0.0002,
+      "loss": 21.9161,
+      "step": 170
+    },
+    {
+      "epoch": 0.2396804260985353,
+      "grad_norm": 0.8619910478591919,
+      "learning_rate": 0.0002,
+      "loss": 21.8431,
+      "step": 180
+    },
+    {
+      "epoch": 0.2529960053262317,
+      "grad_norm": 0.8252401947975159,
+      "learning_rate": 0.0002,
+      "loss": 21.8738,
+      "step": 190
+    },
+    {
+      "epoch": 0.2663115845539281,
+      "grad_norm": 0.8227563500404358,
+      "learning_rate": 0.0002,
+      "loss": 21.8141,
+      "step": 200
+    },
+    {
+      "epoch": 0.2663115845539281,
+      "eval_loss": 10.927712440490723,
+      "eval_runtime": 0.4592,
+      "eval_samples_per_second": 346.264,
+      "eval_steps_per_second": 174.221,
+      "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": 135932805120.0,
+  "total_flos": 179683983360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null