Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76ee55eb50c694ed09f334f8d146a23525435e4554fa2d08012a2393ca964a27
+oid sha256:e0fc693288112d0030cb92c8f2dd36e785f36a8e3ff6345f2a7d20534a84550a
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81e2bfa32e13574a315a683815727a4e4dae391953e6651073f6e1072ee0ec09
+oid sha256:27aadebfe36dbd3816e4d8026fbf4f4d3ffccb7b3ada8887791bed6000f6cad5
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97ca4e52a8ff86f0f650364416f5046b64a5370f50691b48fcfcc3c4dc51ebc4
+oid sha256:2f4a56699f52629b4b9ee1f526c244f0e6212ad9629827056e99c6ee2a5f95c9
 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": 0.2084056964223689,
+  "epoch": 0.27787426189649184,
   "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": 61.769,
       "eval_steps_per_second": 30.987,
       "step": 150
+    },
+    {
+      "epoch": 0.22229940951719346,
+      "grad_norm": 0.9388880729675293,
+      "learning_rate": 0.0002,
+      "loss": 0.2882,
+      "step": 160
+    },
+    {
+      "epoch": 0.23619312261201805,
+      "grad_norm": 0.5570294857025146,
+      "learning_rate": 0.0002,
+      "loss": 0.2089,
+      "step": 170
+    },
+    {
+      "epoch": 0.25008683570684265,
+      "grad_norm": 0.8899029493331909,
+      "learning_rate": 0.0002,
+      "loss": 0.2759,
+      "step": 180
+    },
+    {
+      "epoch": 0.26398054880166727,
+      "grad_norm": 1.1891875267028809,
+      "learning_rate": 0.0002,
+      "loss": 0.1959,
+      "step": 190
+    },
+    {
+      "epoch": 0.27787426189649184,
+      "grad_norm": 1.2228397130966187,
+      "learning_rate": 0.0002,
+      "loss": 0.2336,
+      "step": 200
+    },
+    {
+      "epoch": 0.27787426189649184,
+      "eval_loss": 0.2487281858921051,
+      "eval_runtime": 4.97,
+      "eval_samples_per_second": 60.965,
+      "eval_steps_per_second": 30.583,
+      "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": 1150857039052800.0,
+  "total_flos": 1534476052070400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null