End of training

README.md

@@ -0,0 +1,55 @@
+---
+license: bigcode-openrail-m
+base_model: bigcode/starcoderbase-1b
+tags:
+- generated_from_trainer
+model-index:
+- name: starcoderbase1b-personal-copilot-T4-40GB-colab
+  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. -->
+
+# starcoderbase1b-personal-copilot-T4-40GB-colab
+
+This model is a fine-tuned version of [bigcode/starcoderbase-1b](https://huggingface.co/bigcode/starcoderbase-1b) 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: 2
+- total_train_batch_size: 2
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 30
+- training_steps: 10
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.36.0.dev0
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "bigcode/starcoderbase-1b",
+  "activation_function": "gelu_pytorch_tanh",
+  "architectures": [
+    "GPTBigCodeForCausalLM"
+  ],
+  "attention_softmax_in_fp32": true,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "inference_runner": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_batch_size": null,
+  "max_sequence_length": null,
+  "model_type": "gpt_bigcode",
+  "multi_query": true,
+  "n_embd": 2048,
+  "n_head": 16,
+  "n_inner": 8192,
+  "n_layer": 24,
+  "n_positions": 8192,
+  "pad_key_length": true,
+  "pre_allocate_kv_cache": false,
+  "resid_pdrop": 0.1,
+  "scale_attention_softmax_in_fp32": true,
+  "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,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.0.dev0",
+  "use_cache": false,
+  "validate_runner_input": true,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.36.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a89b98637b57a37064034b22c71657a9a0ae0f3a4cd798f5e5db61e716d40101
+size 2274445000

runs/Dec10_06-07-22_ea9e6d8cf645/events.out.tfevents.1702188557.ea9e6d8cf645.3090.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:667f6629cff284f2840c848ead20e43f5a245261a3a5359130290d6893a7f5a8
+size 4952

runs/Dec10_06-11-35_ea9e6d8cf645/events.out.tfevents.1702188775.ea9e6d8cf645.4267.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96e09370491897e4e5f1f3f69ac26378c4db30553bfeff76b955ef0e3f5f19b0
+size 23180

runs/Dec10_08-42-21_ea9e6d8cf645/events.out.tfevents.1702197856.ea9e6d8cf645.41492.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0902b81ad70ff6f84cea249440928c6d450d7c84c601c455723baddc22df631b
+size 5210

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21b93e131ed5769a0cd25838c735dbf3303e314acd333e5f5c9d9f2489dd259a
+size 4792