Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18880f0009d88f2e4ace1c51f20a265e75c72b04356aa8dd0aed83cdcd7313c1
+oid sha256:b9f7f4f7aac886db89ee9574141a7c897ca8aedc4aabfafcd1c2fb5c49c41f76
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4b4f5a1f31de8907a7cfea15ac3338b0a020e3ad5a36cee4920e5eea86613b7
+oid sha256:6feda22c7ad7d311c1d6a64abcaaaee4cd789aa4e5c8af0ed7164216eaa745dd
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a17cd15b2e15390a515768c1bc1fccdfba01249f8a67e0095eb77b09ca8fe95
+oid sha256:87d381348a459e58ee0e6bcfb524ade0fbd14082775c8a724bbda8d0f94ed717
 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": 0.0006005735477380899,
+  "epoch": 0.0009008603216071348,
   "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": 0.6711,
       "step": 18
+    },
+    {
+      "epoch": 0.0006306022251249943,
+      "grad_norm": 0.2987304925918579,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.6307,
+      "step": 21
+    },
+    {
+      "epoch": 0.0007206882572857079,
+      "grad_norm": 0.24557766318321228,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.6283,
+      "step": 24
+    },
+    {
+      "epoch": 0.0007206882572857079,
+      "eval_loss": 0.6251760125160217,
+      "eval_runtime": 1652.0384,
+      "eval_samples_per_second": 8.488,
+      "eval_steps_per_second": 4.244,
+      "step": 24
+    },
+    {
+      "epoch": 0.0008107742894464214,
+      "grad_norm": 0.21351483464241028,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.6718,
+      "step": 27
+    },
+    {
+      "epoch": 0.0009008603216071348,
+      "grad_norm": 0.2256997674703598,
+      "learning_rate": 0.0,
+      "loss": 0.6141,
+      "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": 1.68216426971136e+16,
+  "total_flos": 2.47563798183936e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null