Training in progress, step 2750, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b38cf2e692ca7a844489ec1433c2e05108246127aedc27402efd8034cd65a573
+oid sha256:e0de879f6812e66ab4b873dd78d500f8deb3f2e8b2d293266e3bb87f11844395
 size 3149984

last-checkpoint/README.md

@@ -60,34 +60,34 @@ model-index:
       type: sts_dev
     metrics:
     - type: pearson_cosine
-      value: 0.8169384514842573
+      value: 0.8179974050572225
       name: Pearson Cosine
     - type: spearman_cosine
-      value: 0.8229950220469622
+      value: 0.823939141053365
       name: Spearman Cosine
     - type: pearson_euclidean
-      value: 0.7873338046578867
+      value: 0.7884393906368459
       name: Pearson Euclidean
     - type: spearman_euclidean
-      value: 0.7910863183517545
+      value: 0.7922252886902459
       name: Spearman Euclidean
     - type: pearson_manhattan
-      value: 0.7884276721147352
+      value: 0.7895245481097086
       name: Pearson Manhattan
     - type: spearman_manhattan
-      value: 0.7928925773180566
+      value: 0.7940188158576397
       name: Spearman Manhattan
     - type: pearson_dot
-      value: 0.7053659085797274
+      value: 0.7047975315002233
       name: Pearson Dot
     - type: spearman_dot
-      value: 0.6868513283838655
+      value: 0.6866457343802284
       name: Spearman Dot
     - type: pearson_max
-      value: 0.8169384514842573
+      value: 0.8179974050572225
       name: Pearson Max
     - type: spearman_max
-      value: 0.8229950220469622
+      value: 0.823939141053365
       name: Spearman Max
 ---
 
@@ -189,18 +189,18 @@ You can finetune this model on your own dataset.
 * Dataset: `sts_dev`
 * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
 
-| Metric             | Value     |
-|:-------------------|:----------|
-| pearson_cosine     | 0.8169    |
-| spearman_cosine    | 0.823     |
-| pearson_euclidean  | 0.7873    |
-| spearman_euclidean | 0.7911    |
-| pearson_manhattan  | 0.7884    |
-| spearman_manhattan | 0.7929    |
-| pearson_dot        | 0.7054    |
-| spearman_dot       | 0.6869    |
-| pearson_max        | 0.8169    |
-| **spearman_max**   | **0.823** |
+| Metric             | Value      |
+|:-------------------|:-----------|
+| pearson_cosine     | 0.818      |
+| spearman_cosine    | 0.8239     |
+| pearson_euclidean  | 0.7884     |
+| spearman_euclidean | 0.7922     |
+| pearson_manhattan  | 0.7895     |
+| spearman_manhattan | 0.794      |
+| pearson_dot        | 0.7048     |
+| spearman_dot       | 0.6866     |
+| pearson_max        | 0.818      |
+| **spearman_max**   | **0.8239** |
 
 <!--
 ## Bias, Risks and Limitations
@@ -655,6 +655,31 @@ You can finetune this model on your own dataset.
 | 5.6374 | 2480 | 0.0794        | -               | -                    |
 | 5.6601 | 2490 | 0.0808        | -               | -                    |
 | 5.6829 | 2500 | 0.0796        | 0.0424          | 0.8230               |
+| 5.7056 | 2510 | 0.0802        | -               | -                    |
+| 5.7284 | 2520 | 0.0799        | -               | -                    |
+| 5.7512 | 2530 | 0.0802        | -               | -                    |
+| 5.7739 | 2540 | 0.0813        | -               | -                    |
+| 5.7967 | 2550 | 0.0772        | -               | -                    |
+| 5.8195 | 2560 | 0.0766        | -               | -                    |
+| 5.8422 | 2570 | 0.0778        | -               | -                    |
+| 5.8650 | 2580 | 0.076         | -               | -                    |
+| 5.8878 | 2590 | 0.0787        | -               | -                    |
+| 5.9105 | 2600 | 0.0794        | -               | -                    |
+| 5.9333 | 2610 | 0.076         | -               | -                    |
+| 5.9560 | 2620 | 0.0773        | -               | -                    |
+| 5.9788 | 2630 | 0.0755        | -               | -                    |
+| 6.0    | 2640 | 0.0725        | -               | -                    |
+| 6.0228 | 2650 | 0.0738        | -               | -                    |
+| 6.0455 | 2660 | 0.0762        | -               | -                    |
+| 6.0683 | 2670 | 0.0761        | -               | -                    |
+| 6.0911 | 2680 | 0.0771        | -               | -                    |
+| 6.1138 | 2690 | 0.0765        | -               | -                    |
+| 6.1366 | 2700 | 0.0755        | -               | -                    |
+| 6.1593 | 2710 | 0.0771        | -               | -                    |
+| 6.1821 | 2720 | 0.0748        | -               | -                    |
+| 6.2049 | 2730 | 0.0768        | -               | -                    |
+| 6.2276 | 2740 | 0.0766        | -               | -                    |
+| 6.2504 | 2750 | 0.0766        | 0.0422          | 0.8239               |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f6a2d5b34fd10accdd4f847e24be219bc8d2079e9fbc6a5813fc2452a522605
+oid sha256:01816a05db7d73ca4b25ac1de0d8871c70d5ebc3c6550732d4f568c5450e1532
 size 735216376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82cbb2c754b4ac5420d2c8f04d3d1bb517c6080f2373a79abc84b0d29ae1706d
+oid sha256:058586cfdd061ce051937ea29d784c5396ad802ab6a8062ae95a39449f5e87bb
 size 1476823354

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4168cc5b009fc040826762dfe9f60cc80d19708bbd5ced2e7c827563cfef0ee
+oid sha256:7e5d410b2cf6afe266b680200262bece02c8b73a7f4fe9c24a9511651e69c566
 size 15920

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de1b0d66ae7e1c9d9d12d149279d7e13ee1e925dcc22e3ebcce6bb410fdfc0ce
+oid sha256:241fb089b2a75b0178b716d2c9f3ab783efece8fd110186ff079009f3e2d5d39
 size 15920

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d6ee399d9d3ebc7c9b7af578278a5c6c3ca5d9fabb63cc48afefadb3b54889
+oid sha256:b49ef8dd86cf4b4207cf1c42398af806df058c9349f4493849eb28038438a723
 size 15920

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d85fbcb0bd0fbfaba06a7263648fb4972f61f703d5d139d82efd9f4d5de1e001
+oid sha256:e485f847da4a9806eddef14351033ecc919033b63fd68f8bc68b7169c57963b0
 size 15920

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8835c432d7eff19c3b8fd3dffee418a6bc3a5d791b30c2759a40dc55b6b42dac
+oid sha256:319c6a48457418ea395d14d2f9780b2ebe1427c0989faa27825b46d6d3bbe687
 size 15920

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6bbe6ed744d70f161fe402b5c847e6645f13fe21fa3a4fc628a4fcd0134ccbc
+oid sha256:b35809d1fe89628804b4c83292d53b673fbcb92b9e33eff373948b0e79eb9827
 size 15920

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3a031f34b493f17b3a39be1d0b5fa83616f502ff4ac36aae1896ec25847e5a1
+oid sha256:9cf03e255dde7a7bb7211208f1f31c4e13764d3766452a6763c02b762bc9d719
 size 15920

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:269cb069e29740de39b305648fd5ef0f310846f32ad2c33bce18fb14f7b8c72a
+oid sha256:d6d10ac988ac77df78c86728b8beae5b92b581acfaa2d25bcf3b6db4560d5b34
 size 15920

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:544d5619cd8489cb993e500d8008ccff453e52b13ccba0e529ea60489849ddc0
+oid sha256:dc64535d26de3fc7fc55580766b27e5ab7e8f1ca8fccb50ed249a1c01ae41e51
 size 1000

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.682885189927443,
+  "epoch": 6.250391236306729,
   "eval_steps": 250,
-  "global_step": 2500,
+  "global_step": 2750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1937,6 +1937,199 @@
       "eval_sts_dev_spearman_manhattan": 0.7928925773180566,
       "eval_sts_dev_spearman_max": 0.8229950220469622,
       "step": 2500
+    },
+    {
+      "epoch": 5.705648029591692,
+      "grad_norm": 0.2824183404445648,
+      "learning_rate": 1.7852697464347952e-06,
+      "loss": 0.0802,
+      "step": 2510
+    },
+    {
+      "epoch": 5.7284108692559395,
+      "grad_norm": 0.23221443593502045,
+      "learning_rate": 1.792382374906647e-06,
+      "loss": 0.0799,
+      "step": 2520
+    },
+    {
+      "epoch": 5.751173708920188,
+      "grad_norm": 0.3471781313419342,
+      "learning_rate": 1.7994950033784986e-06,
+      "loss": 0.0802,
+      "step": 2530
+    },
+    {
+      "epoch": 5.773936548584436,
+      "grad_norm": 0.2657029628753662,
+      "learning_rate": 1.8066076318503504e-06,
+      "loss": 0.0813,
+      "step": 2540
+    },
+    {
+      "epoch": 5.796699388248684,
+      "grad_norm": 0.2691391706466675,
+      "learning_rate": 1.8137202603222023e-06,
+      "loss": 0.0772,
+      "step": 2550
+    },
+    {
+      "epoch": 5.819462227912932,
+      "grad_norm": 0.2894577383995056,
+      "learning_rate": 1.820832888794054e-06,
+      "loss": 0.0766,
+      "step": 2560
+    },
+    {
+      "epoch": 5.84222506757718,
+      "grad_norm": 0.3584199547767639,
+      "learning_rate": 1.8279455172659058e-06,
+      "loss": 0.0778,
+      "step": 2570
+    },
+    {
+      "epoch": 5.864987907241428,
+      "grad_norm": 0.29335150122642517,
+      "learning_rate": 1.8350581457377576e-06,
+      "loss": 0.076,
+      "step": 2580
+    },
+    {
+      "epoch": 5.8877507469056765,
+      "grad_norm": 0.3056882321834564,
+      "learning_rate": 1.8421707742096093e-06,
+      "loss": 0.0787,
+      "step": 2590
+    },
+    {
+      "epoch": 5.910513586569925,
+      "grad_norm": 0.2651148736476898,
+      "learning_rate": 1.849283402681461e-06,
+      "loss": 0.0794,
+      "step": 2600
+    },
+    {
+      "epoch": 5.933276426234173,
+      "grad_norm": 0.2723177969455719,
+      "learning_rate": 1.8563960311533128e-06,
+      "loss": 0.076,
+      "step": 2610
+    },
+    {
+      "epoch": 5.956039265898421,
+      "grad_norm": 0.26683980226516724,
+      "learning_rate": 1.8635086596251647e-06,
+      "loss": 0.0773,
+      "step": 2620
+    },
+    {
+      "epoch": 5.978802105562669,
+      "grad_norm": 0.2798727750778198,
+      "learning_rate": 1.8706212880970165e-06,
+      "loss": 0.0755,
+      "step": 2630
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.1584087312221527,
+      "learning_rate": 1.8777339165688682e-06,
+      "loss": 0.0725,
+      "step": 2640
+    },
+    {
+      "epoch": 6.0227628396642485,
+      "grad_norm": 0.2422705441713333,
+      "learning_rate": 1.88484654504072e-06,
+      "loss": 0.0738,
+      "step": 2650
+    },
+    {
+      "epoch": 6.045525679328496,
+      "grad_norm": 0.29021552205085754,
+      "learning_rate": 1.8919591735125717e-06,
+      "loss": 0.0762,
+      "step": 2660
+    },
+    {
+      "epoch": 6.068288518992745,
+      "grad_norm": 0.24207890033721924,
+      "learning_rate": 1.8990718019844234e-06,
+      "loss": 0.0761,
+      "step": 2670
+    },
+    {
+      "epoch": 6.091051358656992,
+      "grad_norm": 0.2542373538017273,
+      "learning_rate": 1.9061844304562752e-06,
+      "loss": 0.0771,
+      "step": 2680
+    },
+    {
+      "epoch": 6.113814198321241,
+      "grad_norm": 0.24501535296440125,
+      "learning_rate": 1.913297058928127e-06,
+      "loss": 0.0765,
+      "step": 2690
+    },
+    {
+      "epoch": 6.1365770379854885,
+      "grad_norm": 0.2733090817928314,
+      "learning_rate": 1.920409687399979e-06,
+      "loss": 0.0755,
+      "step": 2700
+    },
+    {
+      "epoch": 6.159339877649737,
+      "grad_norm": 0.24523428082466125,
+      "learning_rate": 1.9275223158718306e-06,
+      "loss": 0.0771,
+      "step": 2710
+    },
+    {
+      "epoch": 6.182102717313985,
+      "grad_norm": 0.2885381877422333,
+      "learning_rate": 1.9346349443436826e-06,
+      "loss": 0.0748,
+      "step": 2720
+    },
+    {
+      "epoch": 6.204865556978233,
+      "grad_norm": 0.30437180399894714,
+      "learning_rate": 1.941747572815534e-06,
+      "loss": 0.0768,
+      "step": 2730
+    },
+    {
+      "epoch": 6.227628396642481,
+      "grad_norm": 0.26403576135635376,
+      "learning_rate": 1.948860201287386e-06,
+      "loss": 0.0766,
+      "step": 2740
+    },
+    {
+      "epoch": 6.250391236306729,
+      "grad_norm": 0.2586285471916199,
+      "learning_rate": 1.9559728297592376e-06,
+      "loss": 0.0766,
+      "step": 2750
+    },
+    {
+      "epoch": 6.250391236306729,
+      "eval_loss": 0.04222765937447548,
+      "eval_runtime": 3.1267,
+      "eval_samples_per_second": 479.737,
+      "eval_steps_per_second": 7.676,
+      "eval_sts_dev_pearson_cosine": 0.8179974050572225,
+      "eval_sts_dev_pearson_dot": 0.7047975315002233,
+      "eval_sts_dev_pearson_euclidean": 0.7884393906368459,
+      "eval_sts_dev_pearson_manhattan": 0.7895245481097086,
+      "eval_sts_dev_pearson_max": 0.8179974050572225,
+      "eval_sts_dev_spearman_cosine": 0.823939141053365,
+      "eval_sts_dev_spearman_dot": 0.6866457343802284,
+      "eval_sts_dev_spearman_euclidean": 0.7922252886902459,
+      "eval_sts_dev_spearman_manhattan": 0.7940188158576397,
+      "eval_sts_dev_spearman_max": 0.823939141053365,
+      "step": 2750
     }
   ],
   "logging_steps": 10,