Training in progress, step 555, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc223b1f7a1f91499c6fce1d9c7b9777a001cfe758ed08b366efeaf34c67c8e2
+oid sha256:7f8e941e5c7588fbc5cab26786881bb5e357ec1562a118646bc389224d60a45a
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3d3f7959fdeb60dff6f4ccbb618b2866aed60776f61dc00bb8c8a81aaf08a53
+oid sha256:9d65945072135b85c2df9ab1f2183dceaa4884df6149d34e86ba3b5291e5289d
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a68ff03bce9d2cb56819b178dca5e85d0900211ca081621ebca96dbb0b14518a
+oid sha256:2892548ae9c9c42bac9274716154c6f511e3242c31db918587a29bba4aed7b3f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a885f4d2be962a847ad04a40c0900fb3136769296a180ac63536e4bcec83f515
+oid sha256:fb205f512e2dbedc6e9149b55b4f69ad4c7795b9c876b3eb5aa8d8b727bca50e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7117437722419929,
+  "epoch": 0.7182141701714655,
   "eval_steps": 386,
-  "global_step": 550,
+  "global_step": 555,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3873,6 +3873,41 @@
       "learning_rate": 9.581043043084259e-05,
       "loss": 0.9006,
       "step": 550
+    },
+    {
+      "epoch": 0.7130378518278874,
+      "grad_norm": 0.7422590255737305,
+      "learning_rate": 9.579389463284834e-05,
+      "loss": 0.9591,
+      "step": 551
+    },
+    {
+      "epoch": 0.7143319314137819,
+      "grad_norm": 0.7437978982925415,
+      "learning_rate": 9.577732769924614e-05,
+      "loss": 0.8823,
+      "step": 552
+    },
+    {
+      "epoch": 0.7156260109996765,
+      "grad_norm": 0.7947098016738892,
+      "learning_rate": 9.576072964129998e-05,
+      "loss": 0.8161,
+      "step": 553
+    },
+    {
+      "epoch": 0.716920090585571,
+      "grad_norm": 0.8041345477104187,
+      "learning_rate": 9.574410047029502e-05,
+      "loss": 0.9831,
+      "step": 554
+    },
+    {
+      "epoch": 0.7182141701714655,
+      "grad_norm": 0.9462196826934814,
+      "learning_rate": 9.572744019753752e-05,
+      "loss": 0.9516,
+      "step": 555
     }
   ],
   "logging_steps": 1,
@@ -3892,7 +3927,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.148654444314624e+17,
+  "total_flos": 6.204551302899302e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null