Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79694a08f27a7db0d74d836062a867fe6cf7d2d679d4fe6fbfac1f593077df2f
+oid sha256:b46adef4ca1e25521e7213a020897af202247a094eb61532416052854a7712a2
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d067b6a0996f030f162989d63e242664e4a29bf1874ecbfe8ff38e1429495143
+oid sha256:cd960b21b59d9768d6b92c5f25c2cd595ea4b66a1d7cdc00966867e76768395b
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3599a3f132ff4c2767b47f547ee0465ae1ef48e7ce5bed9baf9910032e4a63fc
+oid sha256:b19e09d2ea782666bb473b4510240618ec7fecb16982cd1fecc18374ee8c6166
 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": 0.26258205689277897,
+  "epoch": 0.350109409190372,
   "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": 39.188,
       "eval_steps_per_second": 19.675,
       "step": 150
+    },
+    {
+      "epoch": 0.2800875273522976,
+      "grad_norm": 0.7343764901161194,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 0.0611,
+      "step": 160
+    },
+    {
+      "epoch": 0.2975929978118162,
+      "grad_norm": 0.9775058031082153,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 0.0535,
+      "step": 170
+    },
+    {
+      "epoch": 0.3150984682713348,
+      "grad_norm": 0.7859861850738525,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 0.0613,
+      "step": 180
+    },
+    {
+      "epoch": 0.33260393873085337,
+      "grad_norm": 2.0774545669555664,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 0.0763,
+      "step": 190
+    },
+    {
+      "epoch": 0.350109409190372,
+      "grad_norm": 1.286552906036377,
+      "learning_rate": 0.0,
+      "loss": 0.1036,
+      "step": 200
+    },
+    {
+      "epoch": 0.350109409190372,
+      "eval_loss": 0.07366183400154114,
+      "eval_runtime": 6.1783,
+      "eval_samples_per_second": 39.007,
+      "eval_steps_per_second": 19.585,
+      "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": 7501459960627200.0,
+  "total_flos": 1.00019466141696e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null