End of training

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1215
+- Loss: 1.4889
 
 ## Model description
 
@@ -49,16 +49,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.1807        | 0.56  | 500  | 0.1515          |
-| 0.1019        | 1.12  | 1000 | 0.1317          |
-| 0.1108        | 1.68  | 1500 | 0.1240          |
-| 0.0816        | 2.24  | 2000 | 0.1227          |
-| 0.0735        | 2.8   | 2500 | 0.1209          |
-| 0.0533        | 3.37  | 3000 | 0.1207          |
-| 0.0574        | 3.93  | 3500 | 0.1193          |
-| 0.0391        | 4.49  | 4000 | 0.1211          |
-| 0.0379        | 5.05  | 4500 | 0.1209          |
-| 0.0373        | 5.61  | 5000 | 0.1215          |
+| 1.6826        | 0.56  | 500  | 1.8219          |
+| 1.3053        | 1.12  | 1000 | 1.6052          |
+| 1.2203        | 1.68  | 1500 | 1.5159          |
+| 0.8843        | 2.24  | 2000 | 1.4982          |
+| 1.0275        | 2.8   | 2500 | 1.4707          |
+| 0.6974        | 3.37  | 3000 | 1.4788          |
+| 0.6479        | 3.93  | 3500 | 1.4646          |
+| 0.5278        | 4.49  | 4000 | 1.4885          |
+| 0.445         | 5.05  | 4500 | 1.4910          |
+| 0.4474        | 5.61  | 5000 | 1.4899          |
 
 
 ### Framework versions

config.json

@@ -17,7 +17,7 @@
   "decoder_ffn_dim": 4096,
   "decoder_layerdrop": 0.0,
   "decoder_layers": 12,
-  "decoder_start_token_id": 250025,
+  "decoder_start_token_id": 2,
   "dropout": 0.1,
   "early_stopping": true,
   "encoder_attention_heads": 16,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21bd8e9a0c97f6f6dfcfb005461f4f36ee45a4db5c283fc0e227d91ab59ba2b3
+oid sha256:6ed081ecf5feaac97edf8fef61bb8a32f3309eef456d78086ab9b943f16eda37
 size 2444578688

runs/Apr09_20-26-19_568bf6117a95/events.out.tfevents.1712694379.568bf6117a95.27.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c60831c6e0ad426d22c4b78e73caddae913cf645bcfdda258d878541ce99d90b
+size 53323

runs/Apr09_20-26-19_568bf6117a95/events.out.tfevents.1712702664.568bf6117a95.27.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:659b62d9370ba17046b29aeb00c0e8e59d4fd3ca829887a1216744b8cce0ea96
+size 359

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca2cc73b1081059359f1e2920c1bb2a2a4608246b857fdf4d635115cb2fa1d9c
+oid sha256:b7000e1500928efae2cceec2a8cc642de3015e7b533e4ed2c82abfee5d643799
 size 4920