Training in progress, step 500

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": "4.37.2",
+  "use_cache": false,
+  "validate_runner_input": true,
+  "vocab_size": 49152
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bdb1baab5543b01404deb076e79621eb52bf0e7970d85a1059308e3c2b41919
+size 2475771776

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b66534b3b107d48c1ecbf390e1ee2a5a6d9e2dfb1ec696251d25f7e8656fd41
+size 5688