Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f1382b9bc4416a617ff457b167bd51dfca9c2a48eca8ec5c50c9575332a044d
+oid sha256:0a49c40b8c6feb200511612c172c4a6dd9ce239241814161ff6c583e1effd6b1
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb5d22637cf778f3d9577fd03d95d982f5d3de584da5835e1d8a18cba00476d8
+oid sha256:9262286d5842301616fabe5f4c27567a50d97793e2bff253b094ca96aa1d4af4
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edc0d4ab8e6caf35cb6f1b0307052a84c7b3f625babd92b4c6a3a412d7990cb5
+oid sha256:bf1fee9e741b5e7528da5ecda0aa54733d4298c168af8bd09f1d5916757e0b2b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007840574975498203,
+  "epoch": 0.011760862463247305,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 21.869,
       "eval_steps_per_second": 10.968,
       "step": 6
+    },
+    {
+      "epoch": 0.00914733747141457,
+      "grad_norm": 2.8602676391601562,
+      "learning_rate": 0.00014,
+      "loss": 5.6889,
+      "step": 7
+    },
+    {
+      "epoch": 0.010454099967330937,
+      "grad_norm": 2.6527276039123535,
+      "learning_rate": 0.00016,
+      "loss": 5.2183,
+      "step": 8
+    },
+    {
+      "epoch": 0.011760862463247305,
+      "grad_norm": 2.932201623916626,
+      "learning_rate": 0.00018,
+      "loss": 4.7739,
+      "step": 9
+    },
+    {
+      "epoch": 0.011760862463247305,
+      "eval_loss": 5.452193260192871,
+      "eval_runtime": 14.8133,
+      "eval_samples_per_second": 21.805,
+      "eval_steps_per_second": 10.936,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1916899650699264.0,
+  "total_flos": 2831783574896640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null