Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbef157b9600fdc30cd09681e635c3596d9d9f3a832f0d58792888176093d6e7
+oid sha256:79333448ea194b8955d28edd0dfdc2624a75062a6e2d6fa9c8d67763978b60c9
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16278e58faf54743e51c2cb86c8c7a4cef307e814c0ff1c955065184c7b3ffbf
+oid sha256:97aabbe19b13f77d29eac72afd9b2fec41c341d45c159475d1bbfd48fe26b6fb
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d0fa37673dbc0bf8164a593d75abf6e8c224c2ea3193e0f86621fb2aa8c6ed6
+oid sha256:bc5766dc22014545cb596a69098c894e4f30cee7366965d5aa7f46e78007cbc6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd1931e4016bf28b07346e79413c71e240f12f43909f7431de607b5c05407707
+oid sha256:940d423240b39d966113615a1fba0e170b7aa70deeb57e606975b0bf165e01d8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.058233581365253966,
+  "epoch": 0.06470397929472663,
   "eval_steps": 386,
-  "global_step": 45,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -330,6 +330,41 @@
       "learning_rate": 9e-05,
       "loss": 1.0146,
       "step": 45
+    },
+    {
+      "epoch": 0.059527660951148496,
+      "grad_norm": 1.169231653213501,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 1.1266,
+      "step": 46
+    },
+    {
+      "epoch": 0.06082174053704303,
+      "grad_norm": 0.9771779179573059,
+      "learning_rate": 9.4e-05,
+      "loss": 0.8351,
+      "step": 47
+    },
+    {
+      "epoch": 0.06211582012293756,
+      "grad_norm": 1.2849314212799072,
+      "learning_rate": 9.6e-05,
+      "loss": 1.1822,
+      "step": 48
+    },
+    {
+      "epoch": 0.0634098997088321,
+      "grad_norm": 1.023181676864624,
+      "learning_rate": 9.8e-05,
+      "loss": 0.9082,
+      "step": 49
+    },
+    {
+      "epoch": 0.06470397929472663,
+      "grad_norm": 1.135751724243164,
+      "learning_rate": 0.0001,
+      "loss": 0.9407,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -349,7 +384,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.030717272621056e+16,
+  "total_flos": 5.58968585846784e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null