Training in progress, step 565, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdcb8e5e7c548a56cd0a35a2c9bb10ad791d3828eed0c063e5a6d352374c517d
+oid sha256:cdb8ebe1fdeaef6e74e23d6dfb833ade6a25cee79d23f802b9013874b57d4eee
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61a19135443e44dedc426550bf9883c5626a874a708b9a836625a70bf1db005e
+oid sha256:9411786f9b96464651735395a94e7711e9840e8e226611003010c107f2f57342
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce764d34a7f8f42ea0e1eeb92ce016727a74857ee03f898e45301c13248fe7f7
+oid sha256:95e1a0472a4b7efd6160b24567cef071ac85a9b8b7bcca2274aa35f9ad966be1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5863424f0312bb85e67d22274e1da6de21abafad54b7c797160a5bf5abd89083
+oid sha256:a81c2473e91beba8f8b9fa27ab4fd41402b289ee84be898e2c7de1d41842ce6e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7246845681009382,
+  "epoch": 0.7311549660304109,
   "eval_steps": 386,
-  "global_step": 560,
+  "global_step": 565,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3943,6 +3943,41 @@
       "learning_rate": 9.564367270466247e-05,
       "loss": 0.8735,
       "step": 560
+    },
+    {
+      "epoch": 0.7259786476868327,
+      "grad_norm": 0.8444498181343079,
+      "learning_rate": 9.562682606000575e-05,
+      "loss": 0.9474,
+      "step": 561
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.7441167831420898,
+      "learning_rate": 9.560994839333224e-05,
+      "loss": 0.9077,
+      "step": 562
+    },
+    {
+      "epoch": 0.7285668068586219,
+      "grad_norm": 0.7276771664619446,
+      "learning_rate": 9.55930397161172e-05,
+      "loss": 0.8866,
+      "step": 563
+    },
+    {
+      "epoch": 0.7298608864445163,
+      "grad_norm": 0.8522891402244568,
+      "learning_rate": 9.557610003985698e-05,
+      "loss": 0.9961,
+      "step": 564
+    },
+    {
+      "epoch": 0.7311549660304109,
+      "grad_norm": 0.8116034269332886,
+      "learning_rate": 9.555912937606895e-05,
+      "loss": 0.8989,
+      "step": 565
     }
   ],
   "logging_steps": 1,
@@ -3962,7 +3997,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.260448161483981e+17,
+  "total_flos": 6.316345020068659e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null