Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c3a7594bd9ddbdc72d8b4f4820597d122f53dcc455ff24077bd0ece1710ace4
+oid sha256:24da472a63b5baeb50a52e191d1633b9ab44188687d23e3dbc4539f56cfb30a5
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5b3ac76dc7b1f9a97a8d9dd8ef5431c76a9bc92f913e567bd574d32a3b77e2d
+oid sha256:92c065b7909b3d305a15ac646e4b3dad7454feb005297d3831804376813f5bb1
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
+oid sha256:56e4c605570ee3c73fe8ff5167e52a53ea3100415d1bfd842431b5b9a62a411e
 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": 0.008784773060029283,
+  "epoch": 0.013177159590043924,
   "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": 242.217,
       "eval_steps_per_second": 121.109,
       "step": 6
+    },
+    {
+      "epoch": 0.010248901903367497,
+      "grad_norm": 0.01229225005954504,
+      "learning_rate": 0.00014,
+      "loss": 11.9311,
+      "step": 7
+    },
+    {
+      "epoch": 0.01171303074670571,
+      "grad_norm": 0.01089850626885891,
+      "learning_rate": 0.00016,
+      "loss": 11.9303,
+      "step": 8
+    },
+    {
+      "epoch": 0.013177159590043924,
+      "grad_norm": 0.0077802687883377075,
+      "learning_rate": 0.00018,
+      "loss": 11.9302,
+      "step": 9
+    },
+    {
+      "epoch": 0.013177159590043924,
+      "eval_loss": 11.931767463684082,
+      "eval_runtime": 1.1672,
+      "eval_samples_per_second": 246.738,
+      "eval_steps_per_second": 123.369,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 708968448.0,
+  "total_flos": 1063452672.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null