End of training

README.md

@@ -0,0 +1,55 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Salesforce/codet5-base
+tags:
+- generated_from_trainer
+model-index:
+- name: codet5_finetuned
+  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_finetuned
+
+This model is a fine-tuned version of [Salesforce/codet5-base](https://huggingface.co/Salesforce/codet5-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3272
+
+## 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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.55.4
+- Pytorch 2.8.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.21.4

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "bos_token_id": 1,
+  "classifier_dropout": 0.0,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "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": 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: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.4",
+  "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": "4.55.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c9205ea0412a643ba32f82dc422070a7c438ca6ce75fc5b2d018bb08d8eecb7
+size 891558696

runs/Sep04_15-57-52_2c0ac6fe0ffb/events.out.tfevents.1757001499.2c0ac6fe0ffb.616.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26d0bc7bf422db1832afd4c507e8d0a1f613b3f4eab111cb5b029a0d195bec51
+size 5943

runs/Sep04_15-57-52_2c0ac6fe0ffb/events.out.tfevents.1757001548.2c0ac6fe0ffb.616.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0387bbf0834a1e0678caf2a445afc26ebed382915c58844de897ebe52d7b1ab8
+size 6291

runs/Sep04_15-57-52_2c0ac6fe0ffb/events.out.tfevents.1757001587.2c0ac6fe0ffb.616.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b305ca695d16cfc65609a7296030bda197c32074b8e29a8a0d5ccf12e896af9
+size 354

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e749b1d07d6bccf8910eb9760991078206b3046d23e3e24c3130592d4c62aad
+size 5777