Training in progress, step 600, 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, 0.5864, 0.0912],
-#         [0.5864, 1.0000, 0.1606],
-#         [0.0912, 0.1606, 1.0000]])
+# tensor([[1.0000, 0.5948, 0.0953],
+#         [0.5948, 1.0000, 0.1617],
+#         [0.0953, 0.1617, 1.0000]])
 ```
 
 <!--
@@ -1232,6 +1232,10 @@ You can finetune this model on your own dataset.
 | 0.0053 | 300  | 0.8566        |
 | 0.0062 | 350  | 0.8697        |
 | 0.0071 | 400  | 0.8099        |
+| 0.0080 | 450  | 0.766         |
+| 0.0088 | 500  | 0.7402        |
+| 0.0097 | 550  | 0.8769        |
+| 0.0106 | 600  | 0.6827        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7d724aabf27686f2b045b9371c8395667163c1ae289641d98c04d67af681113
+oid sha256:0331d85acd4fecdd2f31fd21e71c37b15d11fa5d95f1960167c2115865d268eb
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3833c1087a6615d0a9885551a669b19c4bbab287f26ffb8c0f28cb2d0ecbe7c9
+oid sha256:f0f2a519dd6cd0c172d7135799f3099fbcc09a2457a9690f71edda228c1586f6
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:254790d1ccb1862da57b7a7e387a7afb33ae0567b70cc27cd18377286c351f30
+oid sha256:c2615f3b3d60e5b013a5494b0df662cc433db404a047bf2af8ab2c80fe288cfc
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30858f23bcb22d0baef45bd4add9d6fa474141308c12653c706077b87d932e49
+oid sha256:cb7fde5111803012042c93a73aa191336bb6e10b3ad44f6bd1d94fc7008a22b6
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c72cad2d603ca6a379ea320d48002510dd9f27b4826fefb43b627b20d6176f70
+oid sha256:b1791894c32e6460fc9c57eab981d0af91d945f1bc12022ff9b5f30caaac5c8b
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007068261737732148,
+  "epoch": 0.010602392606598222,
   "eval_steps": 500,
-  "global_step": 400,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -64,6 +64,34 @@
       "learning_rate": 3.5247349823321555e-06,
       "loss": 0.8099,
       "step": 400
+    },
+    {
+      "epoch": 0.007951794454948667,
+      "grad_norm": 3.2528891563415527,
+      "learning_rate": 3.966431095406361e-06,
+      "loss": 0.766,
+      "step": 450
+    },
+    {
+      "epoch": 0.008835327172165185,
+      "grad_norm": 4.1086039543151855,
+      "learning_rate": 4.408127208480566e-06,
+      "loss": 0.7402,
+      "step": 500
+    },
+    {
+      "epoch": 0.009718859889381704,
+      "grad_norm": 3.8160510063171387,
+      "learning_rate": 4.849823321554771e-06,
+      "loss": 0.8769,
+      "step": 550
+    },
+    {
+      "epoch": 0.010602392606598222,
+      "grad_norm": 2.901653289794922,
+      "learning_rate": 5.291519434628975e-06,
+      "loss": 0.6827,
+      "step": 600
     }
   ],
   "logging_steps": 50,