Training in progress, step 119, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1de549ffe6cbda026938a42d1e2441221d0dd36aef338a55a6099f624dd35f95
+oid sha256:6aed73575afce5f7943132f9a95e33a9ba21279338a18b8dd26168871731b211
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4057eda53a53bed4869baaddd9a821cfa6574c2069db78e3e3ae3b090fa54119
+oid sha256:fff603b0a0e378a2145f0ad44206e29ae2e549008620b5a7f213c5033d79522e
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d06b0e421df269e758dbad384e6a198d09f9dc2f79e06ddf32bd52cb423765ff
+oid sha256:5f3e8e8d4a0b35f921a3f49ba17d591da0b4505cd7fd8f39e19601ae8cf7ede3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcbdf5cce354397b1cc7dbc75ae72cd1ce74fbf84991f656a8ae8c5ec4cf6c4c
+oid sha256:c91934808157be4b4581cbac88c1dcb8ab73e7092f7b8aa05c4fbac8ab77615f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.22006472491909385,
+  "epoch": 0.25674217907227614,
   "eval_steps": 17,
-  "global_step": 102,
+  "global_step": 119,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -301,6 +301,49 @@
       "eval_samples_per_second": 51.093,
       "eval_steps_per_second": 6.411,
       "step": 102
+    },
+    {
+      "epoch": 0.22653721682847897,
+      "grad_norm": 0.007451518904417753,
+      "learning_rate": 5e-05,
+      "loss": 0.0003,
+      "step": 105
+    },
+    {
+      "epoch": 0.23300970873786409,
+      "grad_norm": 0.0017845184775069356,
+      "learning_rate": 4.7520812266338885e-05,
+      "loss": 0.0002,
+      "step": 108
+    },
+    {
+      "epoch": 0.23948220064724918,
+      "grad_norm": 0.0030623022466897964,
+      "learning_rate": 4.504772348747687e-05,
+      "loss": 0.001,
+      "step": 111
+    },
+    {
+      "epoch": 0.2459546925566343,
+      "grad_norm": 0.09107693284749985,
+      "learning_rate": 4.2586817614407895e-05,
+      "loss": 0.0005,
+      "step": 114
+    },
+    {
+      "epoch": 0.2524271844660194,
+      "grad_norm": 0.002830550307407975,
+      "learning_rate": 4.0144148627425993e-05,
+      "loss": 0.0009,
+      "step": 117
+    },
+    {
+      "epoch": 0.25674217907227614,
+      "eval_loss": 0.0011964853620156646,
+      "eval_runtime": 15.3143,
+      "eval_samples_per_second": 50.998,
+      "eval_steps_per_second": 6.399,
+      "step": 119
     }
   ],
   "logging_steps": 3,
@@ -320,7 +363,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.988669880454349e+16,
+  "total_flos": 2.322534166953984e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null