Training in progress, step 231, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2791b511c4630b21fd991533625ec1ec52da3e5cc1609da7a4c2cfedc1bcba6d
+oid sha256:c03cc5a79be0ba30ad0320be99eba132052fb920252f4f639abfb0267ea350a0
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a884f4320934e16da5143deade141b5396382f6dfdc0784d68105ea5d71bc6b2
+oid sha256:c6554ffe7014b0c305fc27e46e009d8002b5e22780cf3137e2842ed01d2e8fb0
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fec363189963dc133232a1202530bba3901933ae6ee2483645557d8ee2922117
+oid sha256:2b3a05bdcba00a37dc9e6fb656aa0abeeb8eb45eca58cc80e1b27558770bab32
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16a7801db1aa9f181cf78d5699e3a7862ab42bf9c452e31cb54501196abe18a0
+oid sha256:2fc5b95cc0db21cf56336a583c8dd7fb1d3824838e4cb847d2705abaaeeca402
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.5438066465256797,
+  "epoch": 2.797583081570997,
   "eval_steps": 21,
-  "global_step": 210,
+  "global_step": 231,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -585,6 +585,63 @@
       "eval_samples_per_second": 532.826,
       "eval_steps_per_second": 68.506,
       "step": 210
+    },
+    {
+      "epoch": 2.580060422960725,
+      "grad_norm": 0.17420655488967896,
+      "learning_rate": 5.494517259623477e-06,
+      "loss": 10.1712,
+      "step": 213
+    },
+    {
+      "epoch": 2.61631419939577,
+      "grad_norm": 0.23611021041870117,
+      "learning_rate": 4.630749768552589e-06,
+      "loss": 10.1776,
+      "step": 216
+    },
+    {
+      "epoch": 2.6525679758308156,
+      "grad_norm": 0.21432390809059143,
+      "learning_rate": 3.837524928243774e-06,
+      "loss": 10.1729,
+      "step": 219
+    },
+    {
+      "epoch": 2.688821752265861,
+      "grad_norm": 0.27384114265441895,
+      "learning_rate": 3.116076089096265e-06,
+      "loss": 10.1782,
+      "step": 222
+    },
+    {
+      "epoch": 2.7250755287009065,
+      "grad_norm": 0.18094521760940552,
+      "learning_rate": 2.4675250001635232e-06,
+      "loss": 10.1835,
+      "step": 225
+    },
+    {
+      "epoch": 2.7613293051359515,
+      "grad_norm": 0.25660476088523865,
+      "learning_rate": 1.892880064994934e-06,
+      "loss": 10.179,
+      "step": 228
+    },
+    {
+      "epoch": 2.797583081570997,
+      "grad_norm": 0.23092766106128693,
+      "learning_rate": 1.3930347737136196e-06,
+      "loss": 10.1815,
+      "step": 231
+    },
+    {
+      "epoch": 2.797583081570997,
+      "eval_loss": 10.169166564941406,
+      "eval_runtime": 0.2602,
+      "eval_samples_per_second": 538.147,
+      "eval_steps_per_second": 69.19,
+      "step": 231
     }
   ],
   "logging_steps": 3,
@@ -604,7 +661,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 23425638727680.0,
+  "total_flos": 25768202600448.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null