Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26fe33de7a6875a99d1efcacfd80173f19ca8492b2b7eb5871cb9ebc6ac4e448
+oid sha256:91deb65bfd0412cde1a7838da25790040db516090eb58ffc06e8b42cb875989b
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6991ddc5e14a1424957eb1101e3ea8ead9ce333b90aabb30767775820e8a5a25
+oid sha256:2064dd53255c0b93517079febf79be9b67e6a39f1a79edeca73831453dfd8109
 size 13685516

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf8c12f835d1b432d8b1e6646a119d6284266807ad954643fc8b420d8633febd
+oid sha256:ac9adad561bb80c721d83ca41620f9e277e6665616b76fed12d199aa5153a337
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb83f1f4680ec0586ee74aa4f1aaa4ff33403cea4e3104dc5184f439108f94cf
+oid sha256:59908fcb0dfb5bcb02b42ae0c2fc8b89ecc122aa5d60e8a30dfcd1ff84b1ce9d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26cf8b5c542af5fb68e01d6999dddcfafb3c7a5fb9a5ad3cc0faa3cbff5a6a76
+oid sha256:b39240019c106e95ca25342e8aae709894e4e4f4ad6c26ccabfcf4141de89d7a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95a33d6c9ae92cb1dc4028b8c59e50333088e29c1e3ef825c0fb46b35191441c
+oid sha256:1b66f96c63e49bb289dabf8fc22e29204a551da57877e1d50df9a3f93bff15c7
 size 15024

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": 0.0316622691292876,
+  "epoch": 0.0405926527298559,
   "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": 1.2299,
       "step": 35
+    },
+    {
+      "epoch": 0.032474122183884714,
+      "grad_norm": 1.445990800857544,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1991,
+      "step": 40
+    },
+    {
+      "epoch": 0.032474122183884714,
+      "eval_loss": 1.141239047050476,
+      "eval_runtime": 10.1908,
+      "eval_samples_per_second": 203.615,
+      "eval_steps_per_second": 25.513,
+      "step": 40
+    },
+    {
+      "epoch": 0.036533387456870306,
+      "grad_norm": 1.2058775424957275,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1088,
+      "step": 45
+    },
+    {
+      "epoch": 0.0405926527298559,
+      "grad_norm": 1.1205410957336426,
+      "learning_rate": 0.0,
+      "loss": 1.1277,
+      "step": 50
+    },
+    {
+      "epoch": 0.0405926527298559,
+      "eval_loss": 1.120613932609558,
+      "eval_runtime": 10.1316,
+      "eval_samples_per_second": 204.806,
+      "eval_steps_per_second": 25.662,
+      "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": 3990354860703744.0,
+  "total_flos": 5115839565004800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null