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:e5ff924d5ec11004f9cc1e654aebcf0bcfcbd4c7493eba66eb7ba8a9d79ad93a
+oid sha256:d9ea26a5dc5025fdce50c59cea5cd442d4a49d01af7a0a5c997421fcfc9896ea
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f51e4bdc46dbac8cecb13d43a62629249968045c82332992578b88a496e25d83
+oid sha256:ca23cfec05e73f354137a6e84f8590683f8f2392c61cece745c11f6defc8bbe9
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac2fbbcfec39a266c55920bef9e4f13dec185fbafadb2891cdbdeaddfff2bb90
+oid sha256:6e39d3bd6aca35d9c2c4af115bc55fc6bc26ea5767dd3a367c3979f22ceabe3d
 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": 0.0014006288823681834,
+  "epoch": 0.001867505176490911,
   "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": 32.155,
       "eval_steps_per_second": 16.078,
       "step": 150
+    },
+    {
+      "epoch": 0.001494004141192729,
+      "grad_norm": 6.014227390289307,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 0.4751,
+      "step": 160
+    },
+    {
+      "epoch": 0.0015873794000172744,
+      "grad_norm": 6.426490306854248,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 0.317,
+      "step": 170
+    },
+    {
+      "epoch": 0.0016807546588418199,
+      "grad_norm": 6.19764518737793,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 0.3526,
+      "step": 180
+    },
+    {
+      "epoch": 0.0017741299176663656,
+      "grad_norm": 4.254812240600586,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 0.278,
+      "step": 190
+    },
+    {
+      "epoch": 0.001867505176490911,
+      "grad_norm": 5.536872863769531,
+      "learning_rate": 0.0,
+      "loss": 0.2585,
+      "step": 200
+    },
+    {
+      "epoch": 0.001867505176490911,
+      "eval_loss": 0.09946458041667938,
+      "eval_runtime": 1400.9431,
+      "eval_samples_per_second": 32.188,
+      "eval_steps_per_second": 16.094,
+      "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": 2.62900618887168e+16,
+  "total_flos": 3.50534158516224e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null