Upload folder using huggingface_hub

README.md

@@ -1,9 +1,7 @@
 ---
-license: llama3
-library_name: peft
+base_model: abhi317/results_2
 tags:
 - generated_from_trainer
-base_model: meta-llama/Meta-Llama-3-8B-Instruct
 model-index:
 - name: ps
   results: []
@@ -14,9 +12,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # ps
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
+This model is a fine-tuned version of [abhi317/results_2](https://huggingface.co/abhi317/results_2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 20.3671
+- Loss: 3.1174
 
 ## Model description
 
@@ -36,8 +34,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -47,17 +45,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 21.0373       | 1.0   | 1    | 20.8621         |
-| 21.0373       | 2.0   | 2    | 20.6801         |
-| 21.0373       | 3.0   | 3    | 20.5272         |
-| 21.0373       | 4.0   | 4    | 20.4249         |
-| 21.0373       | 5.0   | 5    | 20.3671         |
+| 3.9667        | 1.0   | 1    | 3.2203          |
+| 3.9667        | 2.0   | 2    | 3.1850          |
+| 3.9667        | 3.0   | 3    | 3.1551          |
+| 3.9667        | 4.0   | 4    | 3.1304          |
+| 3.9667        | 5.0   | 5    | 3.1174          |
 
 
 ### Framework versions
 
-- PEFT 0.11.1
 - Transformers 4.39.3
 - Pytorch 2.1.2
 - Datasets 2.18.0
-- Tokenizers 0.15.2
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "abhi317/results_2",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "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,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.39.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:919147f652d2f6db7ab634e232dcbbafc5dd365ac2d85a2d6dc168a307ce72fb
+size 990345064

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff451ee64846e34c441e6dddb4538e307417605b3e4d995e95598f3148592f03
+oid sha256:d8b7a292c8924aac4320bdacea5432f9e9c21fe9938f05e32fa249644e2e09e3
 size 4856