Training in progress, step 720, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52ab772a3d2f29871c5b33edf53b3357c7f213d43a3b6c7fe3da00f9e9e266b8
+oid sha256:8a4972d945aaf79f38a6385891c2c6bf16c9ab13d1387a9a314a9ae88e2af9d7
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0019585f029b5baa58be8cfe62931034d42db0a67d35a6a218c83edc08d495f6
+oid sha256:263b3898d405f513a3d751718a8e4459efbe49762bd2d59a834f0b0bd5f9c305
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cf483ccbcb523a1ae54b6742d201e95685c3798b63064fda748091e660916fb
+oid sha256:92e2bed38537091b1b6847ec894ec446f212f658d47a8eafa5ceedcd4769dcc4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68087e6a2853e7290ab7c85e019dd29d494adf51d146626f9b298ee98b25dc83
+oid sha256:fa5e57bbef4d99689575267a9a61782e3d42e915f722a8a205895c6faf79e5c7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9252669039145908,
+  "epoch": 0.9317373018440634,
   "eval_steps": 386,
-  "global_step": 715,
+  "global_step": 720,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5028,6 +5028,41 @@
       "learning_rate": 9.266966179767538e-05,
       "loss": 0.7856,
       "step": 715
+    },
+    {
+      "epoch": 0.9265609835004853,
+      "grad_norm": 0.8092474937438965,
+      "learning_rate": 9.264815634051982e-05,
+      "loss": 1.0298,
+      "step": 716
+    },
+    {
+      "epoch": 0.9278550630863798,
+      "grad_norm": 0.8919221758842468,
+      "learning_rate": 9.262662188656705e-05,
+      "loss": 0.7962,
+      "step": 717
+    },
+    {
+      "epoch": 0.9291491426722743,
+      "grad_norm": 0.771659791469574,
+      "learning_rate": 9.260505845045854e-05,
+      "loss": 1.0239,
+      "step": 718
+    },
+    {
+      "epoch": 0.9304432222581689,
+      "grad_norm": 0.7577182054519653,
+      "learning_rate": 9.258346604685542e-05,
+      "loss": 0.9672,
+      "step": 719
+    },
+    {
+      "epoch": 0.9317373018440634,
+      "grad_norm": 0.7373968362808228,
+      "learning_rate": 9.256184469043851e-05,
+      "loss": 0.7484,
+      "step": 720
     }
   ],
   "logging_steps": 1,
@@ -5047,7 +5082,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.993250777609011e+17,
+  "total_flos": 8.04914763619369e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null