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:ee5fbc4dd5e45649c867e9bcb75e8e5b0cd03d1c7c2466fdd36bc40b053b6c5f
+oid sha256:83553401b96b1bc340bb74703f36e3d787f7cbbd29c7db21b0d0567533b90a38
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b55f641ca8e33d99561cfc1aef177280fe2d2d55323e74533aba7b4b881ec4fa
+oid sha256:28d6b794c8532afcdad64dc8a1b9528a10a5b69926e2366e6f8d4c4c356baa9e
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a5f891767aaacfb795fc4c851c74f7dcf55cd20474ec59a43d271975d0645cf
+oid sha256:d36cf02c5c091e1cf6b7a556033f9afe92924f5c6d18c68aeec7f759f6f16a6c
 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": 0.1964735516372796,
+  "epoch": 0.2518891687657431,
   "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": 2.263,
       "step": 35
+    },
+    {
+      "epoch": 0.20151133501259447,
+      "grad_norm": 6.198630332946777,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.4035,
+      "step": 40
+    },
+    {
+      "epoch": 0.20151133501259447,
+      "eval_loss": 2.3978166580200195,
+      "eval_runtime": 6.1463,
+      "eval_samples_per_second": 13.667,
+      "eval_steps_per_second": 6.833,
+      "step": 40
+    },
+    {
+      "epoch": 0.22670025188916876,
+      "grad_norm": 3.865180015563965,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.273,
+      "step": 45
+    },
+    {
+      "epoch": 0.2518891687657431,
+      "grad_norm": 4.703251361846924,
+      "learning_rate": 0.0,
+      "loss": 2.3153,
+      "step": 50
+    },
+    {
+      "epoch": 0.2518891687657431,
+      "eval_loss": 2.3879706859588623,
+      "eval_runtime": 6.0943,
+      "eval_samples_per_second": 13.783,
+      "eval_steps_per_second": 6.892,
+      "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": 7213300567769088.0,
+  "total_flos": 9247821240729600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null