https://huggingface.co/tongyanb/lab2_adam

README.md

@@ -5,24 +5,9 @@ tags:
 - generated_from_trainer
 datasets:
 - kde4
-metrics:
-- bleu
 model-index:
 - name: marian-finetuned-kde4-en-to-fr
-  results:
-  - task:
-      name: Sequence-to-sequence Language Modeling
-      type: text2text-generation
-    dataset:
-      name: kde4
-      type: kde4
-      config: en-fr
-      split: train
-      args: en-fr
-    metrics:
-    - name: Bleu
-      type: bleu
-      value: 52.60158308795034
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-fr](https://huggingface.co/Helsinki-NLP/opus-mt-en-fr) on the kde4 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8607
-- Bleu: 52.6016
+- eval_loss: 0.9633
+- eval_bleu: 49.9655
+- eval_runtime: 162.904
+- eval_samples_per_second: 12.903
+- eval_steps_per_second: 0.203
+- epoch: 0.0
+- step: 4
 
 ## Model description
 
@@ -53,24 +43,19 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 32
+- train_batch_size: 64
 - eval_batch_size: 64
 - seed: 42
-- gradient_accumulation_steps: 4
+- gradient_accumulation_steps: 2
 - total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 2
-- mixed_precision_training: Native AMP
-
-### Training results
-
-
+- num_epochs: 1
 
 ### Framework versions
 
-- Transformers 4.38.1
-- Pytorch 2.1.0+cu121
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
 - Datasets 2.18.0
 - Tokenizers 0.15.2

config.json

@@ -56,7 +56,7 @@
   "share_encoder_decoder_embeddings": true,
   "static_position_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.1",
+  "transformers_version": "4.38.2",
   "use_cache": true,
   "vocab_size": 59514
 }

generation_config.json

@@ -12,5 +12,5 @@
   "num_beams": 4,
   "pad_token_id": 59513,
   "renormalize_logits": true,
-  "transformers_version": "4.38.1"
+  "transformers_version": "4.38.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2b0848a9a270ebea44d638468128cb66b30f40f2e0aa586c4c4b00dfee26c5b
+oid sha256:d2d5a474425b748418656b2da983eb0cd20fb946e02dee99d5387ca4b02e4049
 size 298705768

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adc4d1d8f958decd8011def81a8e4e8588b7f570eaba94a6b169eb0c235c0c6
+oid sha256:54382a209d579b667b04515dd25d1e1c93a66cabdc357c39dbacf05c1ddec364
 size 5112