Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:230425d4a878946b5889c299219c89cd0d9d8dae30a5ec2cf2e2872e20edc6fd
+oid sha256:0b07b173d7cd6fe787b2236fe00c72a431aef3f4251b7f43d9a57832d9710095
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a109daadd250b464f13d6372929a3156a8c8cacaadcdef7fca674fe30272689e
+oid sha256:b2a7c72dad384c11a070c5c37402aea05165a4fb4e9cd65219e3afe6f9f6a9db
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdacbad4cb5c5b201b8278a06f6d380ea7579ea2ad463c9cc04eb0e18aa64385
+oid sha256:7113b4ddb953686a19c918f6a7688101b24bc7cc26d2b0fb2a2b9afb4381aaed
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0025388765471278957,
+  "epoch": 0.003808314820691844,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 2.51,
       "eval_steps_per_second": 1.256,
       "step": 6
+    },
+    {
+      "epoch": 0.0029620226383158784,
+      "grad_norm": 3.0319173336029053,
+      "learning_rate": 0.00014,
+      "loss": 2.7119,
+      "step": 7
+    },
+    {
+      "epoch": 0.003385168729503861,
+      "grad_norm": 2.3886566162109375,
+      "learning_rate": 0.00016,
+      "loss": 2.4817,
+      "step": 8
+    },
+    {
+      "epoch": 0.003808314820691844,
+      "grad_norm": 2.3795809745788574,
+      "learning_rate": 0.00018,
+      "loss": 1.9891,
+      "step": 9
+    },
+    {
+      "epoch": 0.003808314820691844,
+      "eval_loss": 1.9471328258514404,
+      "eval_runtime": 396.3083,
+      "eval_samples_per_second": 2.511,
+      "eval_steps_per_second": 1.257,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7910767655387136.0,
+  "total_flos": 1.1866151483080704e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null