Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:856064ebf1018c6a453ded11c084660de346a3de5150ef9fd196453f3fd91ae2
+oid sha256:10fe6bceaacdf628d62cb8c631a54445ddc02e9f6455bcac27a1fb6971a9a779
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:348b1ddb7584066e3603d3772e5a6c638b7f55e070bb428161b8ffc319193313
+oid sha256:900385158bc43a494611371612a22f647c594a50733da08a28ecb4deb6fc9086
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d44246f81045c803a849dbe3e438f984893c952090272cb8e54991819d8a3c8
+oid sha256:23c4964323523b2b77cca033571f2daa75ce424d48c0176dcc917900e994a579
 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": 0.05977286312014345,
+  "epoch": 0.07969715082685794,
   "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": 37.262,
       "eval_steps_per_second": 18.649,
       "step": 150
+    },
+    {
+      "epoch": 0.06375772066148636,
+      "grad_norm": 1.2505970001220703,
+      "learning_rate": 0.0002,
+      "loss": 0.1623,
+      "step": 160
+    },
+    {
+      "epoch": 0.06774257820282925,
+      "grad_norm": 1.0405758619308472,
+      "learning_rate": 0.0002,
+      "loss": 0.3187,
+      "step": 170
+    },
+    {
+      "epoch": 0.07172743574417215,
+      "grad_norm": 3.9278643131256104,
+      "learning_rate": 0.0002,
+      "loss": 0.2228,
+      "step": 180
+    },
+    {
+      "epoch": 0.07571229328551504,
+      "grad_norm": 0.7002480626106262,
+      "learning_rate": 0.0002,
+      "loss": 0.0972,
+      "step": 190
+    },
+    {
+      "epoch": 0.07969715082685794,
+      "grad_norm": 2.4312753677368164,
+      "learning_rate": 0.0002,
+      "loss": 0.1998,
+      "step": 200
+    },
+    {
+      "epoch": 0.07969715082685794,
+      "eval_loss": 0.17778712511062622,
+      "eval_runtime": 28.1846,
+      "eval_samples_per_second": 37.503,
+      "eval_steps_per_second": 18.769,
+      "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": 8689191121059840.0,
+  "total_flos": 1.1614760505704448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null