Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:629aa1beeb13fa2f749ac9935ea1ed8ac552c02271f60ad139c72d41d976626a
+oid sha256:4d989d505b343671d16950fbe0a08391045ca1daa62d0a3188859a342bd5a5c0
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a95ba7332aaedc1f812074cdbfa64e160380b973bcf9e872c117bdb45e4207d
+oid sha256:74fdf2288661f6fd344000b3d7ab64ddc9062e7cb3243fd9bae2d7ad3b0fe43f
 size 51418196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51dfc2bb055d1b51b35c8c8edff4dc27eebfe8a96ac3ec43de0ad6f229b4664d
+oid sha256:828ea3d33603207642515af5f9c485aeedb2897e7fd32d7b9a4afd95af337a19
 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": 0.0637890708058686,
+  "epoch": 0.0850520944078248,
   "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": 28.971,
       "eval_steps_per_second": 14.515,
       "step": 150
+    },
+    {
+      "epoch": 0.06804167552625984,
+      "grad_norm": 0.7945826649665833,
+      "learning_rate": 0.0002,
+      "loss": 3.1588,
+      "step": 160
+    },
+    {
+      "epoch": 0.07229428024665108,
+      "grad_norm": 2.89457106590271,
+      "learning_rate": 0.0002,
+      "loss": 3.2037,
+      "step": 170
+    },
+    {
+      "epoch": 0.07654688496704232,
+      "grad_norm": 0.7241123914718628,
+      "learning_rate": 0.0002,
+      "loss": 3.0673,
+      "step": 180
+    },
+    {
+      "epoch": 0.08079948968743356,
+      "grad_norm": 1.855041742324829,
+      "learning_rate": 0.0002,
+      "loss": 3.2108,
+      "step": 190
+    },
+    {
+      "epoch": 0.0850520944078248,
+      "grad_norm": 1.5360522270202637,
+      "learning_rate": 0.0002,
+      "loss": 3.147,
+      "step": 200
+    },
+    {
+      "epoch": 0.0850520944078248,
+      "eval_loss": 1.5669100284576416,
+      "eval_runtime": 17.0853,
+      "eval_samples_per_second": 28.972,
+      "eval_steps_per_second": 14.515,
+      "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": 8519673226199040.0,
+  "total_flos": 1.1259784344895488e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null