Training in progress, step 24, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0ee9d038fdfb39e9bd9e55f4c8f788bb92151e68f72b9d6367ea82855ee2e2f
+oid sha256:89f79cb14b5c754d30bef8e66c4a5617b00fa5ef1da8dd3dca5f51741b0c0aa4
 size 295488936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2f6f1b0a1f8f871f48a36f3d02a2520916fee6a6ee88edb89172de597c386e1
+oid sha256:9789bb0f9d64c03fc14747851aa7f69a43a796a88d09e83e6312c8d8405b4f83
 size 148462004

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b32b2639b16b6624de4cc86c5b2874e9893bb8c25e458e5870ebfbb551ffdf86
+oid sha256:2b0bfc3ae73ee0f6b8148dc70b49d099bfebc01dc53150f62977f94e0000d7f7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad5893d6157dd23b3c59b0fbd477b43e2b7bc277c23d1bb43b6558d4e0634ada
+oid sha256:dedb9dc405b830072407e634dd4d0c1b7c5c7dcee6352d24ec89b9bcf38e60ff
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001937368508680319,
+  "epoch": 0.002324842210416383,
   "eval_steps": 500,
-  "global_step": 20,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,34 @@
       "learning_rate": 3.846153846153846e-05,
       "loss": 1.9203,
       "step": 20
+    },
+    {
+      "epoch": 0.002034236934114335,
+      "grad_norm": 0.15928150713443756,
+      "learning_rate": 4.038461538461539e-05,
+      "loss": 1.8459,
+      "step": 21
+    },
+    {
+      "epoch": 0.002131105359548351,
+      "grad_norm": 0.18540354073047638,
+      "learning_rate": 4.230769230769231e-05,
+      "loss": 1.7937,
+      "step": 22
+    },
+    {
+      "epoch": 0.0022279737849823667,
+      "grad_norm": 0.1321619600057602,
+      "learning_rate": 4.423076923076923e-05,
+      "loss": 1.8011,
+      "step": 23
+    },
+    {
+      "epoch": 0.002324842210416383,
+      "grad_norm": 0.1503838449716568,
+      "learning_rate": 4.615384615384616e-05,
+      "loss": 1.8784,
+      "step": 24
     }
   ],
   "logging_steps": 1.0,
@@ -166,7 +194,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6822886326681600.0,
+  "total_flos": 8301560403240960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null