Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b50e03d14fcad644aca50efb494dd352aebcd6a4147e6d51b91b625a93c2421
+oid sha256:1faaaa163fd01d299452bd2a2fe7ce21bb10d0bac6a32edcfb730ae8f86f7c1a
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84eacedc0720f19f0550b724a9770faddfe700e4dd5359d1b9d399bc58a5c244
+oid sha256:b10409e71e0c227efda781123e7664614b0a9bc17582c0c5baffdff6f7bc0f7e
 size 23159290

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:339da5f2a2261c348d33fea33072b75ed2b5c4b4b5c9ce3a1c9e4ad35b2548fa
+oid sha256:83755f92e0b31961d67d2da9e18664e012b9b3ac7214356235e7fb3f84d0056d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cf93c5b0577712034804293556a44a82ffcc949dc7089314caab7285b5b3531
+oid sha256:967e9b98be3239b99d6529b39bee941ba668efc3fb745b113e6c7389b99b9e54
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fecc0b3d642b817d1205149fa3e71a134831a7a7daf9fe98ab4b0ee7dab9e4d
+oid sha256:e55e3563b24e28435bf8bb5f384f100304d3875e2008ea67ac69f04eac510a1b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b6a3cc9d628f50ce037b3b77bd34ac845724d71b81e3024c4e48c9af81541aa
+oid sha256:840ee3db5c8d91c883c04ec102f79f49dc3b48318a72c57161fc550c33698a64
 size 15024

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": 0.0015683199372672025,
+  "epoch": 0.002352479905900804,
   "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": 63.883,
       "eval_steps_per_second": 7.992,
       "step": 6
+    },
+    {
+      "epoch": 0.0018297065934784029,
+      "grad_norm": 0.7925214767456055,
+      "learning_rate": 0.00014,
+      "loss": 0.1235,
+      "step": 7
+    },
+    {
+      "epoch": 0.0020910932496896032,
+      "grad_norm": 0.8158267736434937,
+      "learning_rate": 0.00016,
+      "loss": 0.1062,
+      "step": 8
+    },
+    {
+      "epoch": 0.002352479905900804,
+      "grad_norm": 0.49643707275390625,
+      "learning_rate": 0.00018,
+      "loss": 0.0751,
+      "step": 9
+    },
+    {
+      "epoch": 0.002352479905900804,
+      "eval_loss": 0.05340096727013588,
+      "eval_runtime": 100.947,
+      "eval_samples_per_second": 63.826,
+      "eval_steps_per_second": 7.984,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4645068333907968.0,
+  "total_flos": 7015988662894592.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null