Training in progress, epoch 1, checkpoint

checkpoint-22/README.md

@@ -98,9 +98,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 0.9016, 0.4455],
-#         [0.9016, 1.0000, 0.4424],
-#         [0.4455, 0.4424, 1.0000]])
+# tensor([[1.0000, 0.9027, 0.4485],
+#         [0.9027, 1.0000, 0.4446],
+#         [0.4485, 0.4446, 1.0000]])
 ```
 
 <!--
@@ -174,6 +174,7 @@ You can finetune this model on your own dataset.
 - `per_device_eval_batch_size`: 16
 - `learning_rate`: 2e-05
 - `weight_decay`: 0.001
+- `num_train_epochs`: 2
 - `warmup_ratio`: 0.2
 - `fp16`: True
 - `dataloader_num_workers`: 2
@@ -204,7 +205,7 @@ You can finetune this model on your own dataset.
 - `adam_beta2`: 0.999
 - `adam_epsilon`: 1e-08
 - `max_grad_norm`: 1.0
-- `num_train_epochs`: 3
+- `num_train_epochs`: 2
 - `max_steps`: -1
 - `lr_scheduler_type`: linear
 - `lr_scheduler_kwargs`: {}
@@ -311,7 +312,7 @@ You can finetune this model on your own dataset.
 | Epoch  | Step | Training Loss |
 |:------:|:----:|:-------------:|
 | 0.0455 | 1    | 3.3947        |
-| 1.0    | 22   | 2.7614        |
+| 1.0    | 22   | 2.7163        |
 
 
 ### Framework Versions

checkpoint-22/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae36f0d49cb7c6e043c6ef223cacbfbe254b437fe8f8231ff156569d9b3720a7
+oid sha256:44dc75dc88eaa963e3e29998f9ff2c4b342c2b9cc828ed5cc8f06f722ac95d5d
 size 90864192

checkpoint-22/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d20014754335e14c3273e770a9a97cae030182098365de37df0f2fbbdde6740a
+oid sha256:e3715e5cad0bd7354d05fea88cf40f306a6bc22d5b34fd5f23d539ccc5cb287d
 size 85254842

checkpoint-22/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:184a54e4b0325e58e2b676f5bf81fb2212c224be32f3e0d06e2236fd564a2464
+oid sha256:ee0889d2e1f8f81ca0859895fa3b9cec01c8ba200e1012155e6d6bf09d3f55f1
 size 1064

checkpoint-22/trainer_state.json

@@ -18,16 +18,16 @@
     },
     {
       "epoch": 1.0,
-      "grad_norm": 25.755640029907227,
-      "learning_rate": 1.730769230769231e-05,
-      "loss": 2.7614,
+      "grad_norm": 25.27043342590332,
+      "learning_rate": 1.3142857142857145e-05,
+      "loss": 2.7163,
       "step": 22
     }
   ],
   "logging_steps": 500,
-  "max_steps": 66,
+  "max_steps": 44,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {

checkpoint-22/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c47de56b6ffbf75451cd50cf54a7faa7e4410fc0c9cb2ddb837b9ec87e9577b
+oid sha256:9e91a92ff4d4228b61d5b3b1e6c465ed3cfe5a67113276860cdd9a2015549963
 size 5752