Training in progress, step 136, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aed73575afce5f7943132f9a95e33a9ba21279338a18b8dd26168871731b211
+oid sha256:0814f8e20ccede08fa8187f3ae9945e018206f1d367b4459817ab9e8b5571161
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fff603b0a0e378a2145f0ad44206e29ae2e549008620b5a7f213c5033d79522e
+oid sha256:2fe5644c35fb5877b90a0d6c6a8f75b466f1ab8e16fad16fadb3575d7f2895eb
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f3e8e8d4a0b35f921a3f49ba17d591da0b4505cd7fd8f39e19601ae8cf7ede3
+oid sha256:1085dfbbda04ba524f0c68d6477f2459b2374ec1fdc942d609556cffc4d079fb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c91934808157be4b4581cbac88c1dcb8ab73e7092f7b8aa05c4fbac8ab77615f
+oid sha256:ffd0ef2a827b219b75915f5a88a30c53ebe86f536eec93a6252baab983329eb7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.25674217907227614,
+  "epoch": 0.29341963322545844,
   "eval_steps": 17,
-  "global_step": 119,
+  "global_step": 136,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -344,6 +344,56 @@
       "eval_samples_per_second": 50.998,
       "eval_steps_per_second": 6.399,
       "step": 119
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "grad_norm": 0.004851281642913818,
+      "learning_rate": 3.772572564296005e-05,
+      "loss": 0.0008,
+      "step": 120
+    },
+    {
+      "epoch": 0.26537216828478966,
+      "grad_norm": 0.0022969194687902927,
+      "learning_rate": 3.533749813077677e-05,
+      "loss": 0.0003,
+      "step": 123
+    },
+    {
+      "epoch": 0.27184466019417475,
+      "grad_norm": 0.002009553834795952,
+      "learning_rate": 3.298534127791785e-05,
+      "loss": 0.0008,
+      "step": 126
+    },
+    {
+      "epoch": 0.2783171521035599,
+      "grad_norm": 0.019238989800214767,
+      "learning_rate": 3.0675041535377405e-05,
+      "loss": 0.001,
+      "step": 129
+    },
+    {
+      "epoch": 0.284789644012945,
+      "grad_norm": 0.0018951981328427792,
+      "learning_rate": 2.8412282383075363e-05,
+      "loss": 0.0001,
+      "step": 132
+    },
+    {
+      "epoch": 0.2912621359223301,
+      "grad_norm": 0.0017350999405607581,
+      "learning_rate": 2.6202630348146324e-05,
+      "loss": 0.0001,
+      "step": 135
+    },
+    {
+      "epoch": 0.29341963322545844,
+      "eval_loss": 0.00118519167881459,
+      "eval_runtime": 15.2967,
+      "eval_samples_per_second": 51.057,
+      "eval_steps_per_second": 6.407,
+      "step": 136
     }
   ],
   "logging_steps": 3,
@@ -363,7 +413,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.322534166953984e+16,
+  "total_flos": 2.6515598406057984e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null