Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d7e6776a79c271106f030dade9494cfa004e4963d90adb079e72141ef1da71e
+oid sha256:499c942ccafd9eb4fc9555ddcac4a52e687e7b77fe891dc4e25f37136678acee
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebc888b358ce173f5f7cd2d34ba8b08028ed2a737412ee681f7c7c19495d733f
+oid sha256:bcca118a9a69cf39b3f0f9a944075862e3af9530ccdfe6ab3c927370b2d199c1
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc4262f26a7ae3e87b963a0c97bf7c35ec6460c0fba62e7fd4e3ce9d7a94f7e7
+oid sha256:d9c101bb52e4f809de6487fd71b71482099d5184955d481f2aa26d4c99dfba27
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0021576912703407353,
+  "epoch": 0.003236536905511103,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 6.026,
       "eval_steps_per_second": 3.016,
       "step": 6
+    },
+    {
+      "epoch": 0.0025173064820641915,
+      "grad_norm": 5.06572151184082,
+      "learning_rate": 0.00014,
+      "loss": 12.1123,
+      "step": 7
+    },
+    {
+      "epoch": 0.0028769216937876473,
+      "grad_norm": 61.05796813964844,
+      "learning_rate": 0.00016,
+      "loss": 15.4283,
+      "step": 8
+    },
+    {
+      "epoch": 0.003236536905511103,
+      "grad_norm": 10.057729721069336,
+      "learning_rate": 0.00018,
+      "loss": 10.6844,
+      "step": 9
+    },
+    {
+      "epoch": 0.003236536905511103,
+      "eval_loss": 2.76363205909729,
+      "eval_runtime": 194.0228,
+      "eval_samples_per_second": 6.035,
+      "eval_steps_per_second": 3.02,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1899722503618560.0,
+  "total_flos": 2849583755427840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null