Training in progress, step 105, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a871a0e0b44b64abd45f518705aa26aa00e55fc49c290070f839878bb1cfaff
+oid sha256:733958f3ede168155501696ee5821290b32d3f703ba1aba8be57d18d4604f841
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f388ba40c0984e120dc7805fd57a393a9f72d9f1a66492944d0c395a3e2d780b
+oid sha256:e82ccfff86840ae3fb31075f1461ea476369f9bd063eecf747317af1e3e88115
 size 85723284

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c9a0dea9fbbe2913a8b37b0a68f6b56dd7b6a3517526a8161db0ccadb86cff0
+oid sha256:2171ed5d1bdf2a8c5f3b1f34b3e66f022d271eb8ef2ea8d1209e0e310a30fc5e
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72b2dd8ebbb4a8daf2cbca7707be59a6c388ea8f745e0c5beaee519e6773410b
+oid sha256:b6ca77e31378970523bb2d0b94f8ba77e0384e08a86885fa1934fad712cb05ca
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7708a1dc6e7232465da7104de5a200559875d930ca8ed3f9df02ed7f86b9223b
+oid sha256:b0458f23bd8f1cd751b64b8a50b25aa593404ce1820215078c3b7bdbffa6dd9c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffb6f911296c95c10ed55acd2f047b9d5390a4a5aadacb4175f0831e6eb136c6
+oid sha256:f203403a218543662f0591032247563a237b1b47bd5f72c3fee965e519b761b3
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:394643dcbb6c197b011a731a6658d2da0764f346efcd5c1446569a2713a0689e
+oid sha256:7cf6d9c83a505ec73c2f55d3e2fb7c55e974e76e53a7c409ea83d3f32663fe66
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.954653937947494,
+  "epoch": 1.0023866348448687,
   "eval_steps": 27,
-  "global_step": 100,
+  "global_step": 105,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -739,6 +739,41 @@
       "learning_rate": 2.0253513192751373e-06,
       "loss": 0.643,
       "step": 100
+    },
+    {
+      "epoch": 0.964200477326969,
+      "grad_norm": 0.3155246078968048,
+      "learning_rate": 1.2994041528833266e-06,
+      "loss": 0.6766,
+      "step": 101
+    },
+    {
+      "epoch": 0.9737470167064439,
+      "grad_norm": 0.23985552787780762,
+      "learning_rate": 7.323082076153509e-07,
+      "loss": 0.6213,
+      "step": 102
+    },
+    {
+      "epoch": 0.9832935560859188,
+      "grad_norm": 0.3547389805316925,
+      "learning_rate": 3.2591323257248893e-07,
+      "loss": 0.7614,
+      "step": 103
+    },
+    {
+      "epoch": 0.9928400954653938,
+      "grad_norm": 0.31457066535949707,
+      "learning_rate": 8.15448036932176e-08,
+      "loss": 0.6257,
+      "step": 104
+    },
+    {
+      "epoch": 1.0023866348448687,
+      "grad_norm": 0.42900577187538147,
+      "learning_rate": 0.0,
+      "loss": 0.6607,
+      "step": 105
     }
   ],
   "logging_steps": 1,
@@ -753,12 +788,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.935098268483584e+17,
+  "total_flos": 6.231853181907763e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null