Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:751cf275275bc5e7e1302ee28c06a678bcc5f68214406d7f65150288e6204772
+oid sha256:bd17238f577013665ad42267782e54915bac77c2f3b29adfa513d854bb5db983
 size 130583912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2467802e69caaf781442a4d7936fd6178a4e8a0b36935505053b3d874e970c1
+oid sha256:022452ad32ba5526cb18988b17cebdd2e49de0066acecd6a7b0cf889174aae51
 size 261247610

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe857a15cfad11d521d686079650bc523522af67539d91db4012db6206f54275
+oid sha256:aa382952e0adbb7e7abb917278c0a70d8bfd97851369da627797b4983c8f9cb6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03347280334728033,
+  "epoch": 0.06694560669456066,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00018,
       "loss": 10.9085,
       "step": 9
+    },
+    {
+      "epoch": 0.0401673640167364,
+      "grad_norm": 3.5189645290374756,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 10.7948,
+      "step": 12
+    },
+    {
+      "epoch": 0.0502092050209205,
+      "grad_norm": 2.799543857574463,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 10.5927,
+      "step": 15
+    },
+    {
+      "epoch": 0.05355648535564853,
+      "eval_loss": 2.6082403659820557,
+      "eval_runtime": 26.4424,
+      "eval_samples_per_second": 4.765,
+      "eval_steps_per_second": 2.383,
+      "step": 16
+    },
+    {
+      "epoch": 0.0602510460251046,
+      "grad_norm": 2.3582141399383545,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.6795,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3272976912875520.0,
+  "total_flos": 6545953825751040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null