Training in progress, step 7800, 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, 0.6585, 0.1068],
-#         [0.6585, 1.0000, 0.1405],
-#         [0.1068, 0.1405, 1.0000]])
+# tensor([[1.0000, 0.6731, 0.0859],
+#         [0.6731, 1.0000, 0.1039],
+#         [0.0859, 0.1039, 1.0000]])
 ```
 
 <!--
@@ -1268,6 +1268,10 @@ You can finetune this model on your own dataset.
 | 0.1325 | 7500 | 0.4791        |
 | 0.1334 | 7550 | 0.4498        |
 | 0.1343 | 7600 | 0.4538        |
+| 0.1352 | 7650 | 0.4596        |
+| 0.1361 | 7700 | 0.3508        |
+| 0.1369 | 7750 | 0.5145        |
+| 0.1378 | 7800 | 0.3505        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4bdcdcbc94340067a5db9757cb8dc5e18160f6e0052a5271f3a3014faaad5b
+oid sha256:d30363d096c58d92d4b21124e0d20899b83f2936057d84481288b276849800da
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1614719d6dd7c8ee90660bde3185c3bc7b3a45d06a5325bcddbb32753674ab3
+oid sha256:b40de5614fe99b525d99f7ae3d9359f7a6761883a046bcd2268fc4693168a255
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09557c453e6a16e29d297517245393e31d8c1c2292c9705909c930c0a8bcca5a
+oid sha256:c1edc586d66d6370fa77d636b436ae7dbcdf36bd23372d9a0cfe0aacbfb7c097
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:405bd92270a66c48608fa1efe67da0e3e668cf968c7d25ea748071fc5b6c3d6a
+oid sha256:85dcd40ad341a8a975b38dbdcfaddae63cf7d7e04b0cc6cd6eae6ee6f1a79543
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23842e055dc64db6d0feb0d9e09209b01e916046b58ef6d199cb81b51ea994ff
+oid sha256:e7f33b2ef6b57ca3fea92dbaf20099472c840d5302f57356bd6135bfd1110e82
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.13429697301691082,
+  "epoch": 0.13783110388577688,
   "eval_steps": 500,
-  "global_step": 7600,
+  "global_step": 7800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1072,6 +1072,34 @@
       "learning_rate": 4.809644420883156e-05,
       "loss": 0.4538,
       "step": 7600
+    },
+    {
+      "epoch": 0.13518050573412735,
+      "grad_norm": 3.380443572998047,
+      "learning_rate": 4.804735819049302e-05,
+      "loss": 0.4596,
+      "step": 7650
+    },
+    {
+      "epoch": 0.13606403845134385,
+      "grad_norm": 1.6248747110366821,
+      "learning_rate": 4.799827217215449e-05,
+      "loss": 0.3508,
+      "step": 7700
+    },
+    {
+      "epoch": 0.13694757116856038,
+      "grad_norm": 1.6644774675369263,
+      "learning_rate": 4.794918615381595e-05,
+      "loss": 0.5145,
+      "step": 7750
+    },
+    {
+      "epoch": 0.13783110388577688,
+      "grad_norm": 1.8441638946533203,
+      "learning_rate": 4.790010013547741e-05,
+      "loss": 0.3505,
+      "step": 7800
     }
   ],
   "logging_steps": 50,