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:f2b36db500f39f055e2df1755f95d37a99705ea67e05cc5185de69479fb1a53d
+oid sha256:ffb5d5824129e5153d9cf25a4fe8989d74c2672c44d0b580d694538574b44580
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07d2249d5307f0b64e5aa82b94bbf3904d13fa4ab0be666492d0de4a8cab9f5e
+oid sha256:1a0e1dd42f79588d1b1040311b334d3e0cf46cb38798464696a5789e329b7dde
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8232c99b3b9bd101763ab8cfa0b9f26a6a08232b451d165ce3fa8ae3b32d33cd
+oid sha256:422062c052870644d743dbc21cba95de70700c7c4bc1b22e8aa006e0a7f71fbc
 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": 0.002387774594078319,
+  "epoch": 0.0035816618911174787,
   "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": 0.8719,
       "step": 18
+    },
+    {
+      "epoch": 0.002507163323782235,
+      "grad_norm": 3.1137900352478027,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.7725,
+      "step": 21
+    },
+    {
+      "epoch": 0.0028653295128939827,
+      "grad_norm": 3.288762092590332,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.912,
+      "step": 24
+    },
+    {
+      "epoch": 0.0028653295128939827,
+      "eval_loss": 0.8639681339263916,
+      "eval_runtime": 204.5208,
+      "eval_samples_per_second": 17.245,
+      "eval_steps_per_second": 8.625,
+      "step": 24
+    },
+    {
+      "epoch": 0.0032234957020057307,
+      "grad_norm": 3.853311061859131,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.0914,
+      "step": 27
+    },
+    {
+      "epoch": 0.0035816618911174787,
+      "grad_norm": 2.4475674629211426,
+      "learning_rate": 0.0,
+      "loss": 0.8377,
+      "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": 7511608746049536.0,
+  "total_flos": 1.1221045163851776e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null