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-A100-40GB-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-A100-40GB-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: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 30
+- training_steps: 99
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.38.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

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": "4.38.0.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": "4.38.0.dev0"
+}

model.safetensors

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

runs/Jan27_00-17-31_23fddf7b6dad/events.out.tfevents.1706314682.23fddf7b6dad.3715.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45674322551c016166feeb4f6b946b4d14f487d3c6c807190c7533f5f02d5ba7
+size 5456

runs/Jan27_00-31-42_23fddf7b6dad/events.out.tfevents.1706315518.23fddf7b6dad.7409.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a70d6ecfdbb43558e599e413559e0bb007336fb296ac52f5b66dd35312ee300d
+size 5715

runs/Jan27_00-42-53_23fddf7b6dad/events.out.tfevents.1706316192.23fddf7b6dad.10361.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9ed617c2816638d0c70cde35e83954fac96bead9974afb5df2eb31f2a09052b
+size 5714

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f52e49126ac3aee0638df869cc7058f99bea9bffe1387a7340b6dfa005a203e
+size 4792