Training in progress, step 105, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d8eac386f5ebe6c83e42310bc4fd2f555c57a5888d0d5e26478d832f095edcc
+oid sha256:69583f00f8114af09203ab6d5a53218104418cd2e137ddc13dec47a57c6bfec8
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78abfff24d4dba2e86a6a2e70c29645274344a238ab79cb3b36321697afbf68a
+oid sha256:9e525c308257aea805307cde6f23e8036b0a6438f61d316276414ae55ea09c57
 size 23159290

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0a30e49fd5a314f25a69352455adec193acd17a59faa18da69112a18ca1c472
+oid sha256:f86990cdf708340992f8858f7e04ca89b9c158af10e22651a89388a962d48255
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dda2cd2ee74a2675fd940157febdbaf83cd03999db08b65baa5c49bd3a3ae033
+oid sha256:2235894ab278ce95ec87aed4bfd453a789580d76d30ddad83d678f3ccfdddc36
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d94f73d82556febaa2055c2dc384c54992134c2517a12350de480da770c955b
+oid sha256:76ba0e1fda92b05a4fd6bf2961271993b1bd36278837a2b1446969c5994c4b1e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1626b104e3ffb0fd3af008f578cd860819335144f3d3889290ccb3f888340cac
+oid sha256:6c1f2aab054d6cf9cfe2510ce73676221432b72a008ed01a09a58c113ccddfa0
 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": 0.7571,
       "step": 100
+    },
+    {
+      "epoch": 0.964200477326969,
+      "grad_norm": 0.29782629013061523,
+      "learning_rate": 1.2994041528833266e-06,
+      "loss": 0.7891,
+      "step": 101
+    },
+    {
+      "epoch": 0.9737470167064439,
+      "grad_norm": 0.25350821018218994,
+      "learning_rate": 7.323082076153509e-07,
+      "loss": 0.6732,
+      "step": 102
+    },
+    {
+      "epoch": 0.9832935560859188,
+      "grad_norm": 0.3261159062385559,
+      "learning_rate": 3.2591323257248893e-07,
+      "loss": 0.8402,
+      "step": 103
+    },
+    {
+      "epoch": 0.9928400954653938,
+      "grad_norm": 0.2618979811668396,
+      "learning_rate": 8.15448036932176e-08,
+      "loss": 0.7352,
+      "step": 104
+    },
+    {
+      "epoch": 1.0023866348448687,
+      "grad_norm": 0.3464551568031311,
+      "learning_rate": 0.0,
+      "loss": 0.7902,
+      "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": 7.74178055651328e+16,
+  "total_flos": 8.128869584338944e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null