Training in progress, step 187, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83fc03decf24c551f881ea371d2fc633c54f2d89682e39a733be683677fdd1e4
+oid sha256:3c679e7e83d3958ed05823d72368a34816d291f6a1537ef5d0f1943c104a8d40
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6fa2042ba45af7848b2d2638ee0ba70d95e13987922ca7c2234efa8226baeaa
+oid sha256:5f1b8af2e89d67205fa4b8e8c1c47189d2d9273a15a47547871725a62e9adb28
 size 212298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:732562efa57057e9106da0ada8229f2e13dca05c703e75c7e3d2c742b55e2e3b
+oid sha256:3de5ca30ff633d309a9b80db8e8d57d7760528e3bc1867a6faea71254e3b8c07
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9a138d58efee4722b14f409e14731dcd0935c0eaa8a6078a4918744b9529bab
+oid sha256:9f9ab26294f369ba5d99cf6e2514a5d05f3df1a90b36a045191f6b23077ba365
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5759661196400212,
+  "epoch": 0.6335627316040233,
   "eval_steps": 50,
-  "global_step": 170,
+  "global_step": 187,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1229,6 +1229,125 @@
       "learning_rate": 1.0048094716167095e-05,
       "loss": 10.344,
       "step": 170
+    },
+    {
+      "epoch": 0.5793541556379036,
+      "grad_norm": 0.02616795524954796,
+      "learning_rate": 9.40352196454532e-06,
+      "loss": 10.3444,
+      "step": 171
+    },
+    {
+      "epoch": 0.5827421916357861,
+      "grad_norm": 0.01909734308719635,
+      "learning_rate": 8.778930535580474e-06,
+      "loss": 10.3453,
+      "step": 172
+    },
+    {
+      "epoch": 0.5861302276336686,
+      "grad_norm": 0.0253478791564703,
+      "learning_rate": 8.174510685872415e-06,
+      "loss": 10.3448,
+      "step": 173
+    },
+    {
+      "epoch": 0.5895182636315511,
+      "grad_norm": 0.020116323605179787,
+      "learning_rate": 7.5904465275624884e-06,
+      "loss": 10.3443,
+      "step": 174
+    },
+    {
+      "epoch": 0.5929062996294335,
+      "grad_norm": 0.0158366896212101,
+      "learning_rate": 7.026915972251254e-06,
+      "loss": 10.3452,
+      "step": 175
+    },
+    {
+      "epoch": 0.596294335627316,
+      "grad_norm": 0.020508933812379837,
+      "learning_rate": 6.484090676804926e-06,
+      "loss": 10.3454,
+      "step": 176
+    },
+    {
+      "epoch": 0.5996823716251986,
+      "grad_norm": 0.020298492163419724,
+      "learning_rate": 5.962135991066971e-06,
+      "loss": 10.344,
+      "step": 177
+    },
+    {
+      "epoch": 0.603070407623081,
+      "grad_norm": 0.01768598146736622,
+      "learning_rate": 5.461210907490951e-06,
+      "loss": 10.3442,
+      "step": 178
+    },
+    {
+      "epoch": 0.6064584436209635,
+      "grad_norm": 0.02038932777941227,
+      "learning_rate": 4.981468012709877e-06,
+      "loss": 10.3456,
+      "step": 179
+    },
+    {
+      "epoch": 0.609846479618846,
+      "grad_norm": 0.01764788292348385,
+      "learning_rate": 4.523053441056876e-06,
+      "loss": 10.3448,
+      "step": 180
+    },
+    {
+      "epoch": 0.6132345156167285,
+      "grad_norm": 0.023541666567325592,
+      "learning_rate": 4.086106830051236e-06,
+      "loss": 10.3449,
+      "step": 181
+    },
+    {
+      "epoch": 0.6166225516146109,
+      "grad_norm": 0.06664617359638214,
+      "learning_rate": 3.670761277863485e-06,
+      "loss": 10.3473,
+      "step": 182
+    },
+    {
+      "epoch": 0.6200105876124934,
+      "grad_norm": 0.022008830681443214,
+      "learning_rate": 3.277143302772342e-06,
+      "loss": 10.345,
+      "step": 183
+    },
+    {
+      "epoch": 0.6233986236103759,
+      "grad_norm": 0.020388372242450714,
+      "learning_rate": 2.9053728046260825e-06,
+      "loss": 10.3434,
+      "step": 184
+    },
+    {
+      "epoch": 0.6267866596082583,
+      "grad_norm": 0.02203419804573059,
+      "learning_rate": 2.555563028319885e-06,
+      "loss": 10.3441,
+      "step": 185
+    },
+    {
+      "epoch": 0.6301746956061408,
+      "grad_norm": 0.020321670919656754,
+      "learning_rate": 2.227820529300264e-06,
+      "loss": 10.3448,
+      "step": 186
+    },
+    {
+      "epoch": 0.6335627316040233,
+      "grad_norm": 0.0204358771443367,
+      "learning_rate": 1.9222451411073645e-06,
+      "loss": 10.3445,
+      "step": 187
     }
   ],
   "logging_steps": 1,
@@ -1248,7 +1367,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 72825986482176.0,
+  "total_flos": 80109921632256.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null