Training in progress, step 7600, checkpoint

last-checkpoint/README.md

@@ -286,9 +286,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 0.6815, 0.1033],
-#         [0.6815, 1.0000, 0.1434],
-#         [0.1033, 0.1434, 1.0000]])
+# tensor([[1.0000, 0.6585, 0.1068],
+#         [0.6585, 1.0000, 0.1405],
+#         [0.1068, 0.1405, 1.0000]])
 ```
 
 <!--
@@ -1264,6 +1264,10 @@ You can finetune this model on your own dataset.
 | 0.1290 | 7300 | 0.4121        |
 | 0.1299 | 7350 | 0.4139        |
 | 0.1308 | 7400 | 0.4311        |
+| 0.1316 | 7450 | 0.4025        |
+| 0.1325 | 7500 | 0.4791        |
+| 0.1334 | 7550 | 0.4498        |
+| 0.1343 | 7600 | 0.4538        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7640a8c5c08cd84ea9d34e9a392788849c161e51fab1fb1e24cf029e4bd1e02b
+oid sha256:fd4bdcdcbc94340067a5db9757cb8dc5e18160f6e0052a5271f3a3014faaad5b
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8bba72a7f616d924ad3ea248b2f6cbefe36b03a9a05b0265d1aae461c6b1d0f
+oid sha256:d1614719d6dd7c8ee90660bde3185c3bc7b3a45d06a5325bcddbb32753674ab3
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:234f75280c102551c5f624e1ddf7b22e58abe72b0541e05f85525df9445290c6
+oid sha256:09557c453e6a16e29d297517245393e31d8c1c2292c9705909c930c0a8bcca5a
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4c7f383c5c3caed78012349896a057bf1feaccde880a982830ace58530daa75
+oid sha256:405bd92270a66c48608fa1efe67da0e3e668cf968c7d25ea748071fc5b6c3d6a
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86c610364818334e39ecc9c71264546e8b8d4a41c51d290cd21e1ca096739e20
+oid sha256:23842e055dc64db6d0feb0d9e09209b01e916046b58ef6d199cb81b51ea994ff
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.13076284214804473,
+  "epoch": 0.13429697301691082,
   "eval_steps": 500,
-  "global_step": 7400,
+  "global_step": 7600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1044,6 +1044,34 @@
       "learning_rate": 4.82927882821857e-05,
       "loss": 0.4311,
       "step": 7400
+    },
+    {
+      "epoch": 0.13164637486526126,
+      "grad_norm": 2.3639650344848633,
+      "learning_rate": 4.824370226384717e-05,
+      "loss": 0.4025,
+      "step": 7450
+    },
+    {
+      "epoch": 0.1325299075824778,
+      "grad_norm": 3.4997270107269287,
+      "learning_rate": 4.8194616245508635e-05,
+      "loss": 0.4791,
+      "step": 7500
+    },
+    {
+      "epoch": 0.1334134402996943,
+      "grad_norm": 1.644084095954895,
+      "learning_rate": 4.814553022717009e-05,
+      "loss": 0.4498,
+      "step": 7550
+    },
+    {
+      "epoch": 0.13429697301691082,
+      "grad_norm": 1.8292336463928223,
+      "learning_rate": 4.809644420883156e-05,
+      "loss": 0.4538,
+      "step": 7600
     }
   ],
   "logging_steps": 50,