Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25f9f42db4e2b8160b74daf5bead66985f5102a01fa9b1dab574786dcb0d1c7c
+oid sha256:bb1f727733ce8b1d85950d4122cc69c916ff0179d9319508ab7eb40843552243
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bea1baa888f696fe8036a05f4d0b4a193584dd9013a0238193d9ca3bce08ef6
+oid sha256:6c38ee1a757f5bd343af720421eccf447f898fbc4c4c0dce9b6231418ecfef12
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6684d632e0ed9894b7d3581195993fbfd0a1de05dcd5960c38ed169d3e9d554
+oid sha256:d82b625db56507f447e53f457cd40a516407fb4c508f6a80ad29dded2571bb42
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0015709336985418514,
+  "epoch": 0.0020140175622331427,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 0.0768,
       "step": 35
+    },
+    {
+      "epoch": 0.0016112140497865142,
+      "grad_norm": 1.0738025903701782,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0734,
+      "step": 40
+    },
+    {
+      "epoch": 0.0016112140497865142,
+      "eval_loss": 0.06289525330066681,
+      "eval_runtime": 287.6301,
+      "eval_samples_per_second": 36.345,
+      "eval_steps_per_second": 18.173,
+      "step": 40
+    },
+    {
+      "epoch": 0.0018126158060098284,
+      "grad_norm": 0.6630128026008606,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0585,
+      "step": 45
+    },
+    {
+      "epoch": 0.0020140175622331427,
+      "grad_norm": 0.7363331913948059,
+      "learning_rate": 0.0,
+      "loss": 0.0592,
+      "step": 50
+    },
+    {
+      "epoch": 0.0020140175622331427,
+      "eval_loss": 0.06008023023605347,
+      "eval_runtime": 287.1634,
+      "eval_samples_per_second": 36.404,
+      "eval_steps_per_second": 18.202,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 938127510208512.0,
+  "total_flos": 1202727577190400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null