Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c2ed57e2ae286cb52c0e64403d3e5e75eba272c26f61ba3f40f64963864a8ec
+oid sha256:081e29d54b365a44a7e0eff258c452f5804424168df0d3b9667dc14007966835
 size 10636352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02d4259f19e68633636b735888846c951444c6e4baeb8071619439baca43c01c
+oid sha256:80e19b3c2fd4e653ba706724ba7814027202a965d694b73d94e98fe4117d50ec
 size 5561082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb7d7d8713e2773e884110ddc0e187083edef2c7d99cab9f572db3e8c2798984
+oid sha256:fcf1c9c06c962e3ff3746661215d6e252e83b9da51ab5ab435c7073123738a58
 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": 0.05352363960749331,
+  "epoch": 0.07136485280999108,
   "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": 139.522,
       "eval_steps_per_second": 69.761,
       "step": 150
+    },
+    {
+      "epoch": 0.057091882247992866,
+      "grad_norm": 4.612691402435303,
+      "learning_rate": 0.0002,
+      "loss": 2.3888,
+      "step": 160
+    },
+    {
+      "epoch": 0.060660124888492414,
+      "grad_norm": 2.416032552719116,
+      "learning_rate": 0.0002,
+      "loss": 2.5284,
+      "step": 170
+    },
+    {
+      "epoch": 0.06422836752899197,
+      "grad_norm": 2.6536426544189453,
+      "learning_rate": 0.0002,
+      "loss": 2.4456,
+      "step": 180
+    },
+    {
+      "epoch": 0.06779661016949153,
+      "grad_norm": 2.990046739578247,
+      "learning_rate": 0.0002,
+      "loss": 2.3355,
+      "step": 190
+    },
+    {
+      "epoch": 0.07136485280999108,
+      "grad_norm": 2.4546844959259033,
+      "learning_rate": 0.0002,
+      "loss": 2.298,
+      "step": 200
+    },
+    {
+      "epoch": 0.07136485280999108,
+      "eval_loss": 1.1441155672073364,
+      "eval_runtime": 4.1753,
+      "eval_samples_per_second": 141.308,
+      "eval_steps_per_second": 70.654,
+      "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": 323334910771200.0,
+  "total_flos": 430574322843648.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null