Training in progress, step 780, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a7d9aed9f195e42a516f0f48d21f823b696ae6069c8f054a3e38ba0e2b4a7f0
+oid sha256:916f37872f2b282127854c113b88d7933e3c6c22deb3493dee6f2bb869c8dc81
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9284e38bb3d6c6f6f13565b5b3e03bab34d531a9c0c5c235e247809ce4833e11
+oid sha256:a45e4e480aaa7c81fec8584a873ce0efc9ecb9ce8e1ec028a2ec8faf12c27ec1
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5665db1ca7a5c9673c5725dc73befb4c49a3afdc0f9e5fa66834c4c7b6a65afe
+oid sha256:8566e721ef91b4bb0b82cb6023f5dd2184670c621b1104f02d62bf820375f9df
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6758aa0c0f93e0374cd665318bf4133b9083528bdb43b1e89e773c2ecf3cb4b
+oid sha256:0a5479532bafb0d8dbf7d1cd4c9665f76912e36e4b505953c015533d8cac1f5d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0029116790682626,
+  "epoch": 1.0093820769977353,
   "eval_steps": 386,
-  "global_step": 775,
+  "global_step": 780,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5456,6 +5456,41 @@
       "learning_rate": 9.132852062103844e-05,
       "loss": 0.868,
       "step": 775
+    },
+    {
+      "epoch": 1.0042057586541573,
+      "grad_norm": 0.6421488523483276,
+      "learning_rate": 9.130530194076858e-05,
+      "loss": 0.6891,
+      "step": 776
+    },
+    {
+      "epoch": 1.0054998382400517,
+      "grad_norm": 0.7791386246681213,
+      "learning_rate": 9.12820551767182e-05,
+      "loss": 0.8292,
+      "step": 777
+    },
+    {
+      "epoch": 1.0067939178259464,
+      "grad_norm": 0.7175559401512146,
+      "learning_rate": 9.125878034469289e-05,
+      "loss": 0.7888,
+      "step": 778
+    },
+    {
+      "epoch": 1.0080879974118409,
+      "grad_norm": 0.75743567943573,
+      "learning_rate": 9.123547746051743e-05,
+      "loss": 0.675,
+      "step": 779
+    },
+    {
+      "epoch": 1.0093820769977353,
+      "grad_norm": 0.7583343386650085,
+      "learning_rate": 9.12121465400356e-05,
+      "loss": 0.7507,
+      "step": 780
     }
   ],
   "logging_steps": 1,
@@ -5475,7 +5510,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.663314369892844e+17,
+  "total_flos": 8.719211228477522e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null