Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dcdfce3185249b041332d706be75bb763e59da7acea3c338606d33740d31787
+oid sha256:20c527e2911669e73c4e2e6071852e2374c56fb8da57cd6ac71b7986b568b101
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a616a97a727cf1dda3505af39a8bc1e73d840996ff0268be1ba233bebb20cfa
+oid sha256:3327b4e1a408af9d66687aa974c114e3838d81a63f26382e2a950d1d86ab89ca
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:045b4c272e1eb6e89091f4c9d82e18f4b0934375c807b878adae2bc236109356
+oid sha256:0b43e51c818353fdc58a80e47797b9309f858b46f69d4373d744fb2a934a15b3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
+oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16744186046511628,
+  "epoch": 0.1883720930232558,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 36.421,
       "eval_steps_per_second": 4.578,
       "step": 72
+    },
+    {
+      "epoch": 0.1744186046511628,
+      "grad_norm": 2.5910260677337646,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 2.7511,
+      "step": 75
+    },
+    {
+      "epoch": 0.1813953488372093,
+      "grad_norm": 2.6901168823242188,
+      "learning_rate": 7.016504991533726e-06,
+      "loss": 2.6676,
+      "step": 78
+    },
+    {
+      "epoch": 0.1883720930232558,
+      "grad_norm": 2.912105083465576,
+      "learning_rate": 5.299731159831953e-06,
+      "loss": 2.5736,
+      "step": 81
+    },
+    {
+      "epoch": 0.1883720930232558,
+      "eval_loss": 2.537811517715454,
+      "eval_runtime": 19.8766,
+      "eval_samples_per_second": 36.425,
+      "eval_steps_per_second": 4.578,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8810271250251776e+16,
+  "total_flos": 2.116155515653325e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null