Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32fb78e8228d05bdde72131e5c2e42294c7cd9a7928ca486180a1bf7d3bc4322
+oid sha256:c5c173709e58d2ce6d429f399842ea1e2a71681646e9e0e4e2b33503e0cf94a8
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:576ace5c99f99f5016d1d57872ca4398e9301f638dedefb06ca17b4cdd7ab49d
+oid sha256:81455a0d35f3140be4bdd58e3d24c5e206c52e04e9b4ce582ffba5bc3f6c5cec
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acb2731ea8d307ffa6fb0140ec6f96efe11c8cba73917d232503203f752af152
+oid sha256:133a504e976e983cc53dfef9a0837ab8cea23ab47ad196fb8679f210438b06c5
 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": 0.005692923695846063,
+  "epoch": 0.007590564927794751,
   "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": 87.861,
       "eval_steps_per_second": 43.935,
       "step": 150
+    },
+    {
+      "epoch": 0.006072451942235801,
+      "grad_norm": 2.1838719844818115,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 0.1598,
+      "step": 160
+    },
+    {
+      "epoch": 0.006451980188625538,
+      "grad_norm": 0.6331111788749695,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 0.2209,
+      "step": 170
+    },
+    {
+      "epoch": 0.006831508435015276,
+      "grad_norm": 2.03953218460083,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 0.1126,
+      "step": 180
+    },
+    {
+      "epoch": 0.007211036681405014,
+      "grad_norm": 3.976135492324829,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 0.2813,
+      "step": 190
+    },
+    {
+      "epoch": 0.007590564927794751,
+      "grad_norm": 1.570008635520935,
+      "learning_rate": 0.0,
+      "loss": 0.1904,
+      "step": 200
+    },
+    {
+      "epoch": 0.007590564927794751,
+      "eval_loss": 0.05086271092295647,
+      "eval_runtime": 124.6253,
+      "eval_samples_per_second": 89.027,
+      "eval_steps_per_second": 44.517,
+      "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": 1127921536204800.0,
+  "total_flos": 1505146542489600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null