Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17b0e26409add284040bfb6519212fa66546ffc66a3aa5d979a1343d1f1d8877
+oid sha256:35c1b7eb7540b47290b567571357866060db1b57cfbba89f374d2379ad38034a
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8889293fec09b2fe74498d01572c3ce26b61db84338a9cdbed6cfa42cb25b38d
+oid sha256:13de4c8037d62e8e2a772bf49b605b54d26d433916b43a5aa15a8ff0d944cb4f
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a49c5843763fc46ee1da521e469762370035a34eaade0c5483dded6460bc0d21
+oid sha256:432b42167305c967229bd18fc2677fb5719703433b16b8b234b9e2fcd88f9d8c
 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": 0.02059202059202059,
+  "epoch": 0.03088803088803089,
   "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": 5.5097,
       "step": 18
+    },
+    {
+      "epoch": 0.021621621621621623,
+      "grad_norm": 1.913030743598938,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 4.9087,
+      "step": 21
+    },
+    {
+      "epoch": 0.02471042471042471,
+      "grad_norm": 1.5813980102539062,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 4.9872,
+      "step": 24
+    },
+    {
+      "epoch": 0.02471042471042471,
+      "eval_loss": 4.9767022132873535,
+      "eval_runtime": 31.5052,
+      "eval_samples_per_second": 12.982,
+      "eval_steps_per_second": 6.507,
+      "step": 24
+    },
+    {
+      "epoch": 0.027799227799227798,
+      "grad_norm": 1.6165424585342407,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 5.1278,
+      "step": 27
+    },
+    {
+      "epoch": 0.03088803088803089,
+      "grad_norm": 1.4993691444396973,
+      "learning_rate": 0.0,
+      "loss": 4.9896,
+      "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": 7077766769934336.0,
+  "total_flos": 1.0747719909900288e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null