Training in progress, step 187, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6466b2af202c6f49e8e1a0446796a5b9527f198ef88c19865ed57a951a1b6250
+oid sha256:5f62a37d391b14b5c17b5a1f8f8c14aafa1bda6867f44af3d82fd0aae68aeb9f
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82abccee2b18b4a4f330e9b14a15c7b5d7af470f7d3c72cfb0aae04f3e4c05c5
+oid sha256:58e310f1976e70e5fffe18d47e1c46a2b16b53e40aec0d10e049e9b1941c009b
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:256b9c0aa439f9e207e153affdcf0a1edea86bf0390b8f2d8ecff43a047e06b7
+oid sha256:0e53baa8a32d5bd27a7c102e9eec6af50bbc86a1b129d4bc22b0fb80d668ec20
 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": 0.02713487629688747,
+  "epoch": 0.029848363926576218,
   "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": 41.903,
       "eval_steps_per_second": 5.238,
       "step": 170
+    },
+    {
+      "epoch": 0.027294493216280927,
+      "grad_norm": 10.131866455078125,
+      "learning_rate": 5.6388590278194096e-06,
+      "loss": 10.2782,
+      "step": 171
+    },
+    {
+      "epoch": 0.027773343974461292,
+      "grad_norm": 10.199562072753906,
+      "learning_rate": 4.549673247541875e-06,
+      "loss": 10.2035,
+      "step": 174
+    },
+    {
+      "epoch": 0.02825219473264166,
+      "grad_norm": 10.666658401489258,
+      "learning_rate": 3.5722980755146517e-06,
+      "loss": 10.5107,
+      "step": 177
+    },
+    {
+      "epoch": 0.028731045490822026,
+      "grad_norm": 10.063220024108887,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 10.3803,
+      "step": 180
+    },
+    {
+      "epoch": 0.029209896249002394,
+      "grad_norm": 11.067845344543457,
+      "learning_rate": 1.962316193157593e-06,
+      "loss": 10.4799,
+      "step": 183
+    },
+    {
+      "epoch": 0.029688747007182763,
+      "grad_norm": 10.027233123779297,
+      "learning_rate": 1.333670137599713e-06,
+      "loss": 10.9872,
+      "step": 186
+    },
+    {
+      "epoch": 0.029848363926576218,
+      "eval_loss": 2.6014537811279297,
+      "eval_runtime": 251.853,
+      "eval_samples_per_second": 41.897,
+      "eval_steps_per_second": 5.237,
+      "step": 187
     }
   ],
   "logging_steps": 3,
@@ -506,7 +556,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.031461360631808e+16,
+  "total_flos": 1.1346074966949888e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null