Upload 16 files

README.md

@@ -1,3 +1,74 @@
----
-license: mit
----
+---
+license: bsd-3-clause
+base_model: Salesforce/codegen-2B-nl
+tags:
+- generated_from_trainer
+datasets:
+- matthewdelorenzo/archgen
+metrics:
+- accuracy
+model-index:
+- name: output_llm
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: matthewdelorenzo/archgen
+      type: matthewdelorenzo/archgen
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8559900076029108
+---
+
+<!-- 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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/llm_team_tamu/huggingface/runs/1za7vikx)
+# output_llm
+
+This model is a fine-tuned version of [Salesforce/codegen-2B-nl](https://huggingface.co/Salesforce/codegen-2B-nl) on the matthewdelorenzo/archgen dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6558
+- Accuracy: 0.8560
+
+## 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: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.0.dev0
+- Pytorch 2.3.0
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.9985974754558204,
+    "eval_accuracy": 0.8559900076029108,
+    "eval_loss": 0.65576171875,
+    "eval_runtime": 59.8715,
+    "eval_samples": 630,
+    "eval_samples_per_second": 10.523,
+    "eval_steps_per_second": 1.319,
+    "perplexity": 1.9266094931688238,
+    "total_flos": 1.3901992019623936e+17,
+    "train_loss": 0.5984635370947449,
+    "train_runtime": 5970.3946,
+    "train_samples": 8556,
+    "train_samples_per_second": 1.433,
+    "train_steps_per_second": 0.045
+}

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "Salesforce/codegen-2B-nl",
+  "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": 2560,
+  "n_head": 32,
+  "n_inner": null,
+  "n_layer": 32,
+  "n_positions": 2048,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 64,
+  "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": "float16",
+  "transformers_version": "4.41.0.dev0",
+  "use_cache": true,
+  "vocab_size": 51200
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 0.9985974754558204,
+    "eval_accuracy": 0.8559900076029108,
+    "eval_loss": 0.65576171875,
+    "eval_runtime": 59.8715,
+    "eval_samples": 630,
+    "eval_samples_per_second": 10.523,
+    "eval_steps_per_second": 1.319,
+    "perplexity": 1.9266094931688238
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 50256,
+  "transformers_version": "4.41.0.dev0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26281e2d8cf685c4494c02715b721a35e7f8e1a2d19490bd9404bfd640f83798
+size 4981847528

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a95ad7aeed18ae73ac64d70e566af37e544c34584e172d7a1192ad12e566391a
+size 576892776

model.safetensors.index.json

@@ -0,0 +1,268 @@
+{
+  "metadata": {
+    "total_size": 5558712320
+  },
+  "weight_map": {
+    "lm_head.bias": "model-00002-of-00002.safetensors",
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.0.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.23.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.23.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.23.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.23.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.23.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.23.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.23.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.23.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.24.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.24.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.24.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.24.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.24.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.24.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.24.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.24.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.25.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.25.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.25.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.25.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.25.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.25.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.25.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.25.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.26.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.26.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.26.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.26.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.26.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.26.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.26.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.26.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.27.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.27.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.27.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.27.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.27.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.27.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.27.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.27.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.28.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.28.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.28.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.28.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.28.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.28.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.28.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.28.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.29.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.29.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.29.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.29.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.29.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.29.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.29.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.29.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.30.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.30.attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.30.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.30.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.30.mlp.fc_in.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.30.mlp.fc_in.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.30.mlp.fc_out.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.30.mlp.fc_out.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.31.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.31.attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.31.ln_1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.31.ln_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.31.mlp.fc_in.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.31.mlp.fc_in.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.31.mlp.fc_out.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.31.mlp.fc_out.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.4.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.fc_in.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.fc_in.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.fc_out.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.fc_out.weight": "model-00001-of-00002.safetensors",
+    "transformer.ln_f.bias": "model-00002-of-00002.safetensors",
+    "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
+    "transformer.wte.weight": "model-00001-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "return_token_type_ids": false,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9985974754558204,
+    "total_flos": 1.3901992019623936e+17,
+    "train_loss": 0.5984635370947449,
+    "train_runtime": 5970.3946,
+    "train_samples": 8556,
+    "train_samples_per_second": 1.433,
+    "train_steps_per_second": 0.045
+}

trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9985974754558204,
+  "eval_steps": 500,
+  "global_step": 267,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9985974754558204,
+      "step": 267,
+      "total_flos": 1.3901992019623936e+17,
+      "train_loss": 0.5984635370947449,
+      "train_runtime": 5970.3946,
+      "train_samples_per_second": 1.433,
+      "train_steps_per_second": 0.045
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 267,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3901992019623936e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88da35f5badde7796917f9dcc24eb3b55610067b56bf7fcbcb33e65be822c322
+size 7032