Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bd395ff392de10dbf507363089228065f3921ee4afb771ab2083ad0ecf8111d
+oid sha256:35982d9cbd7038ee65f27661d93cd76a4e2a22df9b16a4d36b97ed3b3e4f50ba
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13268935b511018fb3808abe4e253fde7d3a2a35f79c40f0735522529c299f06
+oid sha256:35667206ab039d280d0ae343159779f624123711fc7aba0dbfc91bde183a5472
 size 127788180

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ae74989a289f237870432c4bfbed9d0140c66c5599ca6162057c3e918720333
+oid sha256:bd7cc2cbc5b1f79d0cd9cfe0754bb2cdd153a8f9cba5878d66a284192a2fbfb5
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f553c3f2a57a3b0a91a846090b6b148022ac8a2f86073705977ee1d8d0d6fa2
+oid sha256:f5e6f35b02e2ecc5f9085108cba8e6dd6a6ccc4cbfcb6efd405723f999dc87f3
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7127355796687607,
+  "epoch": 0.9137635636778983,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 5.58,
       "eval_steps_per_second": 1.406,
       "step": 39
+    },
+    {
+      "epoch": 0.7310108509423187,
+      "grad_norm": 0.40700671076774597,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0037,
+      "step": 40
+    },
+    {
+      "epoch": 0.7492861222158766,
+      "grad_norm": 0.018231691792607307,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0002,
+      "step": 41
+    },
+    {
+      "epoch": 0.7675613934894346,
+      "grad_norm": 0.287958025932312,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0049,
+      "step": 42
+    },
+    {
+      "epoch": 0.7858366647629925,
+      "grad_norm": 0.011467047035694122,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0002,
+      "step": 43
+    },
+    {
+      "epoch": 0.8041119360365505,
+      "grad_norm": 0.014873400330543518,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0003,
+      "step": 44
+    },
+    {
+      "epoch": 0.8223872073101085,
+      "grad_norm": 0.2564482092857361,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0051,
+      "step": 45
+    },
+    {
+      "epoch": 0.8406624785836665,
+      "grad_norm": 0.17148734629154205,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0027,
+      "step": 46
+    },
+    {
+      "epoch": 0.8589377498572245,
+      "grad_norm": 0.13365596532821655,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0024,
+      "step": 47
+    },
+    {
+      "epoch": 0.8772130211307824,
+      "grad_norm": 0.48475682735443115,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0096,
+      "step": 48
+    },
+    {
+      "epoch": 0.8954882924043404,
+      "grad_norm": 0.01258677989244461,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0002,
+      "step": 49
+    },
+    {
+      "epoch": 0.9137635636778983,
+      "grad_norm": 0.014313850551843643,
+      "learning_rate": 0.0,
+      "loss": 0.0003,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.5844083502531215e+18,
+  "total_flos": 2.0312927567347712e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null