Training in progress, step 730, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59d4b20c39e023774f653c79696e7bf1a0895c40499204e0da55c8972f138d66
+oid sha256:627d9b383438039f34abd33800dae002df999132f89cab89ba62dfe1f1426e0a
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e425df4cff4f5a833435a908df13e0e68fb91e068e65be0350970182c98532fe
+oid sha256:d6343af573504b84a3ef47b8bf3ff835b275e67f12e7cfd7551834d448fab77e
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cf257bb73c12dfb0ceb40ef8d7dab03fb8c678e0b5befc5cb019048e159abe6
+oid sha256:739536522f1b34f69aa7e5b387ca278212f27483830b111e16647531fa067e63
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93cb95f675bf4560789b437cb4b6409914c75b59d4784dc1ea4e7bea55c15059
+oid sha256:db26a6fc12b0a4e7560698816d6216991118c99b7c0d3e7b40bc0039633de232
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.938207699773536,
+  "epoch": 0.9446780977030087,
   "eval_steps": 386,
-  "global_step": 725,
+  "global_step": 730,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5098,6 +5098,41 @@
       "learning_rate": 9.245330413135395e-05,
       "loss": 0.8946,
       "step": 725
+    },
+    {
+      "epoch": 0.9395017793594306,
+      "grad_norm": 0.7683425545692444,
+      "learning_rate": 9.243150936745357e-05,
+      "loss": 0.8221,
+      "step": 726
+    },
+    {
+      "epoch": 0.9407958589453251,
+      "grad_norm": 0.7723820209503174,
+      "learning_rate": 9.240968575405589e-05,
+      "loss": 0.9058,
+      "step": 727
+    },
+    {
+      "epoch": 0.9420899385312197,
+      "grad_norm": 0.7846856117248535,
+      "learning_rate": 9.238783330599893e-05,
+      "loss": 0.8775,
+      "step": 728
+    },
+    {
+      "epoch": 0.9433840181171143,
+      "grad_norm": 0.6629738211631775,
+      "learning_rate": 9.236595203814037e-05,
+      "loss": 0.8753,
+      "step": 729
+    },
+    {
+      "epoch": 0.9446780977030087,
+      "grad_norm": 0.7508718371391296,
+      "learning_rate": 9.23440419653574e-05,
+      "loss": 0.9403,
+      "step": 730
     }
   ],
   "logging_steps": 1,
@@ -5117,7 +5152,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.105044494778368e+17,
+  "total_flos": 8.160941353363046e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null