NLP-Project

README.md

@@ -16,6 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 # flan-t5-base-samsum
 
 This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the samsum dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
 
 ## Model description
 
@@ -43,6 +45,24 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.0           | 0.2606 | 120  | nan             |
+| 0.0           | 0.5212 | 240  | nan             |
+| 0.0           | 0.7818 | 360  | nan             |
+| 0.0           | 1.0423 | 480  | nan             |
+| 0.0           | 1.3029 | 600  | nan             |
+| 0.0           | 1.5635 | 720  | nan             |
+| 0.0           | 1.8241 | 840  | nan             |
+| 0.0           | 2.0847 | 960  | nan             |
+| 0.0           | 2.3453 | 1080 | nan             |
+| 0.0           | 2.6059 | 1200 | nan             |
+| 0.0           | 2.8664 | 1320 | nan             |
+
 
 ### Framework versions
 

config.json

@@ -10,19 +10,26 @@
   "decoder_start_token_id": 0,
   "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
+  "early_stopping": true,
   "eos_token_id": 1,
   "feed_forward_proj": "gated-gelu",
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
   "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
+  "length_penalty": 2.0,
+  "max_length": 200,
+  "min_length": 30,
   "model_type": "t5",
   "n_positions": 512,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
   "num_decoder_layers": 12,
   "num_heads": 12,
   "num_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
+  "prefix": "summarize: ",
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
   "task_specific_params": {

generation_config.json

@@ -1,6 +1,13 @@
 {
+  "_from_model_config": true,
   "decoder_start_token_id": 0,
+  "early_stopping": true,
   "eos_token_id": 1,
+  "length_penalty": 2.0,
+  "max_length": 200,
+  "min_length": 30,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
   "pad_token_id": 0,
   "transformers_version": "4.42.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcf92d16cb0d854f6a8de27d24317b2c799f6e304bc21a361cffbabb2df62812
+oid sha256:197b346658905cda50c1a71fe0eb77a4d79306adaeb5d7a3c0e9208c91022d45
 size 990345064

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 95,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 95
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "<pad>"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:badbd0459616285b96125c3e630ba24c8bbe0503e90777a658ae8f4c31a5d5c7
-size 5304
+oid sha256:2a60c2ed5495b30eeb6d14c7483c484071c29e57de1d4e69ff70d7abf47fb1c7
+size 5240