Training in progress, step 119, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddc96c869e84d02f3d9fca584798f708f1ec256acf0fc2046f784f22bd75df4a
+oid sha256:c51bb1bd493fedab904030a7482e3c21bba78bd2533b6b08b9c73123b0a35d3a
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41593cb66d0ade40fd58b3c15e0939e1fcdbe2ad92a21b6640acc77ded366dc4
+oid sha256:b99ee001fbe78e978d9a8949cfacde0ed77f2b37b4f24cd265a5eb26ee84e83d
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:047cafb3f6e46fce616fd6719483c734a62b1890d850060214a5a61bf44fb49d
+oid sha256:5232f719bd209899927dac4f0c85d3dc677af3c55e9d27e5ace57effddf642d1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcbdf5cce354397b1cc7dbc75ae72cd1ce74fbf84991f656a8ae8c5ec4cf6c4c
+oid sha256:c91934808157be4b4581cbac88c1dcb8ab73e7092f7b8aa05c4fbac8ab77615f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.026179018286814244,
+  "epoch": 0.030542188001283284,
   "eval_steps": 17,
-  "global_step": 102,
+  "global_step": 119,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -301,6 +301,49 @@
       "eval_samples_per_second": 13.281,
       "eval_steps_per_second": 1.661,
       "step": 102
+    },
+    {
+      "epoch": 0.026948989412897015,
+      "grad_norm": 0.3292534053325653,
+      "learning_rate": 5e-05,
+      "loss": 2.2091,
+      "step": 105
+    },
+    {
+      "epoch": 0.02771896053897979,
+      "grad_norm": 0.34186315536499023,
+      "learning_rate": 4.7520812266338885e-05,
+      "loss": 2.2861,
+      "step": 108
+    },
+    {
+      "epoch": 0.02848893166506256,
+      "grad_norm": 0.3780612051486969,
+      "learning_rate": 4.504772348747687e-05,
+      "loss": 2.2936,
+      "step": 111
+    },
+    {
+      "epoch": 0.029258902791145333,
+      "grad_norm": 0.3421897888183594,
+      "learning_rate": 4.2586817614407895e-05,
+      "loss": 2.2416,
+      "step": 114
+    },
+    {
+      "epoch": 0.030028873917228104,
+      "grad_norm": 0.38082820177078247,
+      "learning_rate": 4.0144148627425993e-05,
+      "loss": 2.3025,
+      "step": 117
+    },
+    {
+      "epoch": 0.030542188001283284,
+      "eval_loss": 2.292694330215454,
+      "eval_runtime": 494.1273,
+      "eval_samples_per_second": 13.282,
+      "eval_steps_per_second": 1.662,
+      "step": 119
     }
   ],
   "logging_steps": 3,
@@ -320,7 +363,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4865650885748326e+17,
+  "total_flos": 1.7469611905646592e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null