Training in progress, step 237, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c19e7fc63d926ab7099d2c2e4976a352ee0e3ce9450a98c69251ee1f8a17c4d
+oid sha256:806d1e028189d77cc62d4486f65b636f6b2e4f1f961be377198b1fb31fe90c81
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:374d7e4dbb59b052d370d3421aa2b39202e1fc082115e138279d3c58fc76d6e5
+oid sha256:1f19ff19518466b23fd61b7865f1fce0b672e49d2c04270763afb703bda4142e
 size 37430836

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52d090ba39c679942d98c0a4ca513962d5fc2a26d6ff419a3bd85204526c990f
+oid sha256:1054a98738e2834fde19d8b40af8874f343a2d002dccb1444ea68ed2bb5a6eee
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6337448559670782,
+  "epoch": 0.6502057613168725,
   "eval_steps": 500,
-  "global_step": 231,
+  "global_step": 237,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1624,6 +1624,48 @@
       "learning_rate": 0.00010075757575757576,
       "loss": 1.1841,
       "step": 231
+    },
+    {
+      "epoch": 0.6364883401920439,
+      "grad_norm": 0.2086990624666214,
+      "learning_rate": 0.0001,
+      "loss": 1.2414,
+      "step": 232
+    },
+    {
+      "epoch": 0.6392318244170097,
+      "grad_norm": 0.18307948112487793,
+      "learning_rate": 9.924242424242425e-05,
+      "loss": 1.1255,
+      "step": 233
+    },
+    {
+      "epoch": 0.6419753086419753,
+      "grad_norm": 0.1552293747663498,
+      "learning_rate": 9.848484848484849e-05,
+      "loss": 1.1812,
+      "step": 234
+    },
+    {
+      "epoch": 0.644718792866941,
+      "grad_norm": 0.19036468863487244,
+      "learning_rate": 9.772727272727274e-05,
+      "loss": 1.1467,
+      "step": 235
+    },
+    {
+      "epoch": 0.6474622770919067,
+      "grad_norm": 0.15272115170955658,
+      "learning_rate": 9.696969696969698e-05,
+      "loss": 1.2155,
+      "step": 236
+    },
+    {
+      "epoch": 0.6502057613168725,
+      "grad_norm": 0.19770941138267517,
+      "learning_rate": 9.621212121212123e-05,
+      "loss": 1.1268,
+      "step": 237
     }
   ],
   "logging_steps": 1,
@@ -1643,7 +1685,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.8625043132337766e+17,
+  "total_flos": 2.933357257480151e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null