Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ceb6cfcc59ca681bb9d0e5f1e3b4ec4bbca07ecf00d174688a32629e68a2347
+oid sha256:7156872d130b72f224524ce957a52e548de381c6181ff7bebb26e398730b24dd
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:761935686f33f48bdf03e2abe3ccc1426bfcf3e4a3e597387b99ce3e35abcd53
+oid sha256:522f9f9f8a59265e83423c83602d46c1db8c4d0396e6c1de5bca4c4226104892
 size 162933396

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:714e36bd11f88532014eca46aee4ac4835aa96e5731ff37263d6ad201c24acac
+oid sha256:9327d383e6c6706a43da68b2e96e0839f110187782cc13bdd78b11a0e60158d6
 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": 0.08161044613710555,
+  "epoch": 0.1088139281828074,
   "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": 15.892,
       "eval_steps_per_second": 7.966,
       "step": 150
+    },
+    {
+      "epoch": 0.08705114254624592,
+      "grad_norm": 0.4278263449668884,
+      "learning_rate": 0.0002,
+      "loss": 0.1737,
+      "step": 160
+    },
+    {
+      "epoch": 0.09249183895538629,
+      "grad_norm": 0.9995900988578796,
+      "learning_rate": 0.0002,
+      "loss": 0.231,
+      "step": 170
+    },
+    {
+      "epoch": 0.09793253536452666,
+      "grad_norm": 0.1793416291475296,
+      "learning_rate": 0.0002,
+      "loss": 0.2015,
+      "step": 180
+    },
+    {
+      "epoch": 0.10337323177366703,
+      "grad_norm": 0.8814968466758728,
+      "learning_rate": 0.0002,
+      "loss": 0.1999,
+      "step": 190
+    },
+    {
+      "epoch": 0.1088139281828074,
+      "grad_norm": 0.2865917682647705,
+      "learning_rate": 0.0002,
+      "loss": 0.2293,
+      "step": 200
+    },
+    {
+      "epoch": 0.1088139281828074,
+      "eval_loss": 0.09589679539203644,
+      "eval_runtime": 24.4054,
+      "eval_samples_per_second": 15.857,
+      "eval_steps_per_second": 7.949,
+      "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": 2.276228592775987e+16,
+  "total_flos": 3.044558460734669e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null