Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d396a718ea92c0c502a738a7cd20f3105f64ecde1cc6c8b159914db1aeeb87f
+oid sha256:01c9a7882afda7e277b4878345101c030e63c5e6d7649c473b419cd8ec122511
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19ebaebc2cb3cf1d83faf247ed509e3cef3d15dc4d748a02086960e095ae8f04
+oid sha256:d3e995e9e16f5dee6ed2e6d2d70040fdf8a6781273fe7ea73aa1cbbfd884bd50
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e57417c00e90b24532d321646726159016c0cee76eaa6fb5b5ff3dcb743203d
+oid sha256:9e3e178c0903d74f738e6714a29055d7c4699f57473bc7ba099b1b8149456e72
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0010473397570171764,
+  "epoch": 0.0015710096355257646,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 0.9714,
       "step": 18
+    },
+    {
+      "epoch": 0.0010997067448680353,
+      "grad_norm": 0.2684893310070038,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.7822,
+      "step": 21
+    },
+    {
+      "epoch": 0.0012568077084206116,
+      "grad_norm": 0.34340476989746094,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.9724,
+      "step": 24
+    },
+    {
+      "epoch": 0.0012568077084206116,
+      "eval_loss": 0.8722042441368103,
+      "eval_runtime": 1327.6431,
+      "eval_samples_per_second": 6.057,
+      "eval_steps_per_second": 3.029,
+      "step": 24
+    },
+    {
+      "epoch": 0.0014139086719731882,
+      "grad_norm": 0.26883986592292786,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.9491,
+      "step": 27
+    },
+    {
+      "epoch": 0.0015710096355257646,
+      "grad_norm": 0.2960861921310425,
+      "learning_rate": 0.0,
+      "loss": 0.8432,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.437406611898368e+16,
+  "total_flos": 2.160746713369805e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null