End of training

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,50 @@
+---
+license: bsd-3-clause
+tags:
+- generated_from_trainer
+model-index:
+- name: CODEGEN-TUNED1
+  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. -->
+
+# CODEGEN-TUNED1
+
+This model is a fine-tuned version of [Salesforce/codegen-350m-multi](https://huggingface.co/Salesforce/codegen-350m-multi) on an unknown dataset.
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- training_steps: 10
+
+### Framework versions
+
+- Transformers 4.30.2
+- Pytorch 2.0.1+cu118
+- Datasets 2.13.1
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "Salesforce/codegen-350m-multi",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "CodeGenForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "codegen",
+  "n_ctx": 2048,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 20,
+  "n_positions": 2048,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 32,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "temperature": 1.0
+    }
+  },
+  "tie_word_embeddings": false,
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "use_cache": false,
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 50256,
+  "transformers_version": "4.30.2",
+  "use_cache": false
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffe165c9b3d38f7676f64e38964257cfc4eef7a01a5a597e1780948273ac291f
+size 1510794225

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21e5cb14d808874b583576b4f4474dd7b910cff9e6fab666f7311a200e755d59
+size 3899