Training in progress, step 100

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58e60895bac501b66e51c980db04130101f7423928aad2ac1e88637e8264e411
+oid sha256:fd04526d44c9e55abfcaeae6c9efafc46fac85dad62c1eeaceba46630c43f6a4
 size 22241240

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": "float32",
+  "transformers_version": "4.42.3",
+  "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 sha256:6e6bb664a2fa449ae26fe2e6172413e25f8542e85d8fe9a08ba75d0ec11da549
+size 4548859752

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2db5202df9fa1064adc955260b938dea04458ba53ba578eac9c3727137dc5cc
+oid sha256:59b11333e4398af4fe291d13ecf66ca285425158c2591ac53567c6346786a6cd
 size 5112