Training in progress, step 500

README.md

@@ -1,4 +1,5 @@
 ---
+library_name: transformers
 license: apache-2.0
 base_model: google/flan-t5-base
 tags:
@@ -50,7 +51,7 @@ The following hyperparameters were used during training:
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - num_epochs: 2
 
@@ -58,13 +59,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge                                                   | Bleu1 | Bleu2 | Bleu3 | Bleu4 | Meteor | Bertscore Precision | Bertscore Recall | Bertscore F1 | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------------------------------------------------------:|:-----:|:-----:|:-----:|:-----:|:------:|:-------------------:|:----------------:|:------------:|:-------:|
-| 1.9328        | 1.0   | 378  | nan             | {'rouge1': 0, 'rouge2': 0, 'rougeL': 0, 'rougeLsum': 0} | 0     | 0     | 0     | 0     | 0      | 0                   | 0                | 0            | 0       |
+| 1.83          | 1.0   | 378  | nan             | {'rouge1': 0, 'rouge2': 0, 'rougeL': 0, 'rougeLsum': 0} | 0     | 0     | 0     | 0     | 0      | 0                   | 0                | 0            | 0       |
 | 0.0           | 2.0   | 756  | nan             | {'rouge1': 0, 'rouge2': 0, 'rougeL': 0, 'rougeLsum': 0} | 0     | 0     | 0     | 0     | 0      | 0                   | 0                | 0            | 0       |
 
 
 ### Framework versions
 
-- Transformers 4.40.0
-- Pytorch 2.2.0+cu118
-- Datasets 3.0.0
-- Tokenizers 0.19.1
+- Transformers 4.46.3
+- Pytorch 2.4.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.20.3

config.json

@@ -55,8 +55,8 @@
     }
   },
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.40.0",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
   "use_cache": true,
   "vocab_size": 32128
 }

generation_config.json

@@ -2,5 +2,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.40.0"
+  "transformers_version": "4.46.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd66f721d95e424eec3035589db15a9833aab2daa912e738569d42b3321d4461
-size 570686880
+oid sha256:b19eda28178de2a24e5ef2b6b60446b6ee080dd17443144ca927fca8689e85e0
+size 990345064

runs/Dec10_19-58-54_iit-p/events.out.tfevents.1733841294.iit-p.20039.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3708ec3d8a74acec4c939e16a98985974f536148ee386c47c8c2f22e2c1cb983
+size 835

tokenizer_config.json

@@ -927,7 +927,7 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "extra_ids": 100,
   "model_max_length": 512,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:323eca41da22235eaa9fb7fc694fc036b8e22f209c4485413fbba627f4ec6ff4
-size 5112
+oid sha256:d173a1eff11e3d6f77610033144a9d9a1fa70b4e0b608c85e629ec993c295640
+size 5368