shandung/M2M2

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/m2m100_418M](https://huggingface.co/facebook/m2m100_418M) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0015
+- Loss: 0.1611
 
 ## Model description
 
@@ -38,21 +38,18 @@ The following hyperparameters were used during training:
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
-- gradient_accumulation_steps: 16
-- total_train_batch_size: 64
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- training_steps: 616
+- training_steps: 216
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.0117        | 25.81 | 500  | 0.0016          |
 
 
 ### Framework versions
 
-- Transformers 4.35.0
+- Transformers 4.35.1
 - Pytorch 2.1.0+cu118
 - Tokenizers 0.14.1

config.json

@@ -31,7 +31,7 @@
   "pad_token_id": 1,
   "scale_embedding": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.0",
+  "transformers_version": "4.35.1",
   "use_cache": true,
   "vocab_size": 128112
 }

generation_config.json

@@ -7,5 +7,5 @@
   "max_length": 200,
   "num_beams": 5,
   "pad_token_id": 1,
-  "transformers_version": "4.35.0"
+  "transformers_version": "4.35.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa2476304e7bc33efa4824d11826bbabc657c294e2ad019ccc11f5288450fb83
+oid sha256:c0050ee1dc5d5c390d52f6d4f7ee53104393c1cc8caaa14662246c72e92d0239
 size 1935681888

runs/Nov15_14-41-46_be1601d64edf/events.out.tfevents.1700059307.be1601d64edf.196.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b252dea6d60692d9716c4db3fc3685794c648ac1fefdfa330242999b6f3aba81
+size 4988

runs/Nov15_14-41-46_be1601d64edf/events.out.tfevents.1700060009.be1601d64edf.196.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:318536211bb38436553cd3a20494027a9aae39030ce72f226e17d3eacfa99e6f
+size 359

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43c32c54bed5e154f58d3d615a174ad63be827124249d5af05d6ee366c9cf2c2
+oid sha256:0a10b9759b523cc72e760fd64ffb44325785cd1a27cb77173d16926d2f8a52dc
 size 4728