Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17d8f9775ef2fc3a60893fdca6a2f8fbd01a155a36670674014b038c051fc527
+oid sha256:22521e4ba949252646c8f1408918bf0de0a82c1aac569d59be6187115431b666
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82c445a33110cf590c00717fb81366f88f5a2e00b4e27ea9ef86d91ed7c3b78a
+oid sha256:56930ecd8ca6eb7d02868aa236b71f1bfdb917d74a997c7b3d0b81052d976d08
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ce5912b5c181cd4af1762a4a94b7debbebce7064999c1ea87bd89f515b28a5f
+oid sha256:4dc219238b72e832c7a2aaaa9e841df2fa4ab72c8b3dfd336609d01f6c6ad178
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c792918044964431737f4cb39f3769dbfd230048b1125ac69a6439eb6c8534b
+oid sha256:c3da5b3ae9debb9fbcab0805794dfaab406f2d5635e0407c25e32749f5f7b455
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.17524644030668127,
+  "epoch": 0.19715224534501644,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 9.409,
       "eval_steps_per_second": 4.753,
       "step": 40
+    },
+    {
+      "epoch": 0.1796276013143483,
+      "grad_norm": 0.08530998229980469,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 0.0125,
+      "step": 41
+    },
+    {
+      "epoch": 0.18400876232201532,
+      "grad_norm": 0.07010316848754883,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0078,
+      "step": 42
+    },
+    {
+      "epoch": 0.18838992332968238,
+      "grad_norm": 0.06331722438335419,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 0.0105,
+      "step": 43
+    },
+    {
+      "epoch": 0.1927710843373494,
+      "grad_norm": 0.0915939211845398,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0141,
+      "step": 44
+    },
+    {
+      "epoch": 0.19715224534501644,
+      "grad_norm": 0.05658958479762077,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0076,
+      "step": 45
+    },
+    {
+      "epoch": 0.19715224534501644,
+      "eval_loss": 0.014185325242578983,
+      "eval_runtime": 10.3071,
+      "eval_samples_per_second": 9.411,
+      "eval_steps_per_second": 4.754,
+      "step": 45
     }
   ],
   "logging_steps": 1,
@@ -378,7 +421,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.959302797033472e+16,
+  "total_flos": 3.329215646662656e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null