Training in progress, step 33, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77b70dab3d58dc476a4fb45f21e234f375d139466519260294ab6a7ef6620d2b
+oid sha256:7d925971b321d3628a896b0a6287f71845e124a70fc895ca37a9604bb6e92208
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:329a94965eebe95f88224d777d3f5f5fa5743a28632813359666f79fe72040fd
+oid sha256:7c681725b8ebf2d3821561c80309c34828063021efe9b6cb6879a9c80d102173
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8ff3b7e6316ad4c7ea8c75404f4f8cd2b82017803f1a148e607e3dbc0c68582
+oid sha256:dc294d29ebec9d1210c7657cf895a2c7400965b701bd85b28a138e9bb423a612
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f94970865aded7a663ddce729ff20409247b7e0c4a27787ee16909b1bc06fc14
+oid sha256:3cd3f6e9267a2b7ffad41dddfa33b74e45aa7c480b8283eebbe1a013b2da49f9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8355899419729207,
+  "epoch": 1.0212765957446808,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 33,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -228,6 +228,48 @@
       "eval_samples_per_second": 6.864,
       "eval_steps_per_second": 3.494,
       "step": 27
+    },
+    {
+      "epoch": 0.8665377176015474,
+      "grad_norm": 3.091240882873535,
+      "learning_rate": 1.1214435464779006e-05,
+      "loss": 0.0223,
+      "step": 28
+    },
+    {
+      "epoch": 0.8974854932301741,
+      "grad_norm": 0.4273183047771454,
+      "learning_rate": 7.2790297726755716e-06,
+      "loss": 0.005,
+      "step": 29
+    },
+    {
+      "epoch": 0.9284332688588007,
+      "grad_norm": 0.8694038391113281,
+      "learning_rate": 4.139434924727359e-06,
+      "loss": 0.0089,
+      "step": 30
+    },
+    {
+      "epoch": 0.9593810444874274,
+      "grad_norm": 0.19907452166080475,
+      "learning_rate": 1.8541356326100433e-06,
+      "loss": 0.0039,
+      "step": 31
+    },
+    {
+      "epoch": 0.9903288201160542,
+      "grad_norm": 4.229534149169922,
+      "learning_rate": 4.6570269818346224e-07,
+      "loss": 0.0346,
+      "step": 32
+    },
+    {
+      "epoch": 1.0212765957446808,
+      "grad_norm": 0.12014052271842957,
+      "learning_rate": 0.0,
+      "loss": 0.0034,
+      "step": 33
     }
   ],
   "logging_steps": 1,
@@ -242,12 +284,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.6024765324905677e+17,
+  "total_flos": 1.9585824285995827e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null