Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60ad38400f288cfc1323bf5eb6d41ff0df501b1bc0fb2f63c3346846c687358a
+oid sha256:2f2cd93417c3886f4f096c127bdcb4b7e8fe339e3f84cea147899ccec51af31d
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3443bd87c9d184897ec4c3dc0ab67aad4acfb23dca3cd43dc7088cd81a4ae3b5
+oid sha256:eae39a42ac5dcde30840ed35209f288d6727cad9889630c394f41f0d6d35334d
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b7d0fa8eb8287d4a55dd8123162638f98117302b8fa32bdee7930327042f097
+oid sha256:81c8be9b0017dc13b4234f1a19837781eb4a3a9e02dcab562e8b3c6a2c21834f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.041925791349311715,
+  "epoch": 0.055901055132415625,
   "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": 35.467,
       "eval_steps_per_second": 17.745,
       "step": 150
+    },
+    {
+      "epoch": 0.0447208441059325,
+      "grad_norm": 1.3853378295898438,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 0.1329,
+      "step": 160
+    },
+    {
+      "epoch": 0.04751589686255328,
+      "grad_norm": 1.1701163053512573,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 0.1133,
+      "step": 170
+    },
+    {
+      "epoch": 0.05031094961917406,
+      "grad_norm": 1.4146292209625244,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 0.1388,
+      "step": 180
+    },
+    {
+      "epoch": 0.053106002375794846,
+      "grad_norm": 1.0506839752197266,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 0.1069,
+      "step": 190
+    },
+    {
+      "epoch": 0.055901055132415625,
+      "grad_norm": 1.2772488594055176,
+      "learning_rate": 0.0,
+      "loss": 0.1305,
+      "step": 200
+    },
+    {
+      "epoch": 0.055901055132415625,
+      "eval_loss": 0.13127486407756805,
+      "eval_runtime": 42.5067,
+      "eval_samples_per_second": 35.453,
+      "eval_steps_per_second": 17.738,
+      "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": 2.44309970386944e+16,
+  "total_flos": 3.25746627182592e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null