Training in progress, step 187, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69c451bb6a82f6c3d42d469140c1048f2170d3008e6c1c9bd066561cec948d3e
+oid sha256:370f29b91890cfd7a75752ef406f05f15109a2b092968b5acb39ab8f163a4da8
 size 19552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:411b78174724e914e18c816c5d45bf1904d221a4533c3af32065cece8c2c8ee3
+oid sha256:22ec27437d21e6867c9432990768b7b19f56a5ed1753b641a430c3321007dd80
 size 44354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a3a6084dcf7cadde36acaef2f1d8a6bf36dcb050a9d45415d7af39f8ebdd718
+oid sha256:32578516f496ea3225c8a3eb0630278f273401f8d45c1e7c59bf8f3bbb0f0a3f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fab1f30942a5e2bb9a9e5cc3477ef48cdcd39a7b78f8a45a46db0926bdbf2b4f
+oid sha256:43427779b8e6e83ef9780afcdea7472d2419de40e6f85cfedb90b60f89a2ff0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12844729882886285,
+  "epoch": 0.14129202871174915,
   "eval_steps": 17,
-  "global_step": 170,
+  "global_step": 187,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -487,6 +487,56 @@
       "eval_samples_per_second": 36.064,
       "eval_steps_per_second": 4.512,
       "step": 170
+    },
+    {
+      "epoch": 0.129202871174915,
+      "grad_norm": 0.06537988781929016,
+      "learning_rate": 5.6388590278194096e-06,
+      "loss": 12.4418,
+      "step": 171
+    },
+    {
+      "epoch": 0.1314695882130714,
+      "grad_norm": 0.052994538098573685,
+      "learning_rate": 4.549673247541875e-06,
+      "loss": 12.4399,
+      "step": 174
+    },
+    {
+      "epoch": 0.13373630525122782,
+      "grad_norm": 0.061471715569496155,
+      "learning_rate": 3.5722980755146517e-06,
+      "loss": 12.4436,
+      "step": 177
+    },
+    {
+      "epoch": 0.1360030222893842,
+      "grad_norm": 0.057937003672122955,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 12.4452,
+      "step": 180
+    },
+    {
+      "epoch": 0.1382697393275406,
+      "grad_norm": 0.06667575240135193,
+      "learning_rate": 1.962316193157593e-06,
+      "loss": 12.439,
+      "step": 183
+    },
+    {
+      "epoch": 0.140536456365697,
+      "grad_norm": 0.05928559973835945,
+      "learning_rate": 1.333670137599713e-06,
+      "loss": 12.4442,
+      "step": 186
+    },
+    {
+      "epoch": 0.14129202871174915,
+      "eval_loss": 12.44235610961914,
+      "eval_runtime": 61.7029,
+      "eval_samples_per_second": 36.141,
+      "eval_steps_per_second": 4.522,
+      "step": 187
     }
   ],
   "logging_steps": 3,
@@ -506,7 +556,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 376719802368.0,
+  "total_flos": 414330126336.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null