Training in progress, step 500

README.md

@@ -0,0 +1,60 @@
+---
+license: apache-2.0
+base_model: Salesforce/codet5-small
+tags:
+- generated_from_trainer
+model-index:
+- name: codeT5-small-without-lora-with-prompt
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# codeT5-small-without-lora-with-prompt
+
+This model is a fine-tuned version of [Salesforce/codet5-small](https://huggingface.co/Salesforce/codet5-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8393
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 12
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.1708        | 1.0   | 4383  | 0.9260          |
+| 1.0645        | 2.0   | 8766  | 0.8791          |
+| 1.0192        | 3.0   | 13149 | 0.8537          |
+| 1.0103        | 4.0   | 17532 | 0.8397          |
+| 0.9855        | 5.0   | 21915 | 0.8393          |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.2.1+cu121
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,69 @@
+{
+  "_name_or_path": "Salesforce/codet5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "bos_token_id": 1,
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 2,
+  "feed_forward_proj": "relu",
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "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: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 32100
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.40.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0081a644ccb2a3c99ec49d81f1998579fe51e05e6618ab20cdb3ec3dd8f2360c
+size 241984552

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1df71517f4dc470d2f3cdb8a3dc02bd9e727e7e19666a0a79aeb3afa58f1118e
+size 5112