Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f103bf52d9af03ca3d242e9853fa46234c310b6bc53090179e2ac25a49b816ef
+oid sha256:a715b0ec25dead1ad4763fe70873842017cbbe11a65d5528aee0bf11ef6355eb
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d5974f9596261603b8a52e6a9095aaf2d4df03b83eb2fedf3948dd4a5d995f5
+oid sha256:2fc4a7085cba1d75eed52201ca0a67243fd78485fd83d5a7c543c3346a9a3242
 size 42608388

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:777c99ca2093e6a2fc15a106c5f8ec5dbf5e3d0639d44dd1e5e5ddee0863da08
+oid sha256:a83ecd52c7dc407f6f72e509d7f4de78b565f9b992b7b9c3481784fbf20b246f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8703d3102558a5b20530541033333b4492f9760f258a76329354fe286a54b4d
+oid sha256:919f21951de9fd197bb9e559b3421a6af8da448a30b0c5b1a2b6c9a110007bbc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c06da71716510fd5e60e89bdfb7177430b61a90ea3a7f8b55ea96c2ac3d4a621
+oid sha256:e4ae6bbde22084d121c985af2d0bf879a744e6e7966c28357e4469e532205868
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70cebe4412a116cf38c5b3f0370c4b2f517eb6dc61b89bc4778e6f4e6acb28a9
+oid sha256:877bc2813569967981b03024ab5a1ebc2127ea6afc46bb56f38cd06cf5722b8e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bded55d2b53e2989eb2e2d8ae1c7c1d0eb698508d06297f5d3463855a470271b
+oid sha256:008d83c4f5ee0c3b0aa2ca88e92cb7f21d43acfd48a8bc37442b67fb3134fa7c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.1052631578947367,
+  "epoch": 3.3157894736842106,
   "eval_steps": 2,
-  "global_step": 14,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -99,6 +99,13 @@
       "eval_samples_per_second": 221.351,
       "eval_steps_per_second": 6.917,
       "step": 14
+    },
+    {
+      "epoch": 3.3157894736842106,
+      "grad_norm": 1.4032217264175415,
+      "learning_rate": 0.0,
+      "loss": 1.4173,
+      "step": 15
     }
   ],
   "logging_steps": 3,
@@ -113,12 +120,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.251868264726528e+16,
+  "total_flos": 2.41271599792128e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null