Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9a0f684676cbccf8e97dc8cbcf416a8808a026b7a3f9108b57cee17d362a96e
+oid sha256:ce603abf9cfa81aba2ac851546d98031f455be71170a804cf75561268ea018e8
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:487a20b819258d1581d7e7196bcae694b95e8acb23216d2133b10106ed49f0ca
+oid sha256:cfb14be3a8c4efbcd14f69d194591b604bd6f08125fd2f0368d6db9e1b446d4e
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3d728a9c30fe75afa6f291b4b6cbc8d77d80a82ca9591d465d76bfa9d49aec5
+oid sha256:62bb34f96fd1e9ad5ebf0da5460686d9d7c02a1ae1dd7d567c7754f3fe5b1f7e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0006893930689481453,
+  "epoch": 0.0008838372678822375,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 1.6385,
       "step": 35
+    },
+    {
+      "epoch": 0.0007070698143057901,
+      "grad_norm": 1.7828311920166016,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.7171,
+      "step": 40
+    },
+    {
+      "epoch": 0.0007070698143057901,
+      "eval_loss": 0.4164840579032898,
+      "eval_runtime": 2784.4097,
+      "eval_samples_per_second": 8.555,
+      "eval_steps_per_second": 4.277,
+      "step": 40
+    },
+    {
+      "epoch": 0.0007954535410940138,
+      "grad_norm": 2.1654415130615234,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7822,
+      "step": 45
+    },
+    {
+      "epoch": 0.0008838372678822375,
+      "grad_norm": 2.121535062789917,
+      "learning_rate": 0.0,
+      "loss": 1.901,
+      "step": 50
+    },
+    {
+      "epoch": 0.0008838372678822375,
+      "eval_loss": 0.41538774967193604,
+      "eval_runtime": 2784.1147,
+      "eval_samples_per_second": 8.556,
+      "eval_steps_per_second": 4.278,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.336412246900736e+16,
+  "total_flos": 1.7000916452376576e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null