Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "bigcode/gpt_bigcode-santacoder",
+  "activation_function": "gelu_pytorch_tanh",
+  "architectures": [
+    "GPTBigCodeForCausalLM"
+  ],
+  "attention_softmax_in_fp32": true,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 49152,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 49152,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt_bigcode",
+  "multi_query": true,
+  "n_embd": 2048,
+  "n_head": 16,
+  "n_inner": 8192,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "resid_pdrop": 0.1,
+  "runner_max_sequence_length": null,
+  "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": "4.30.0",
+  "use_cache": true,
+  "vocab_size": 49280
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e074dc14e2be80b5081dd1a6a5ee3f888aea7da7026ab1a430b4099dd52a1ad
+size 4499641978

runs/Apr27_04-31-54_591c152a4651/events.out.tfevents.1714192321.591c152a4651.1120.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ed02d409bc7b11e97242a6607201bfadca041d562dc752ae52e6c4298b6aaeb
+size 4413

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15f7dedd97e87809f82af000ecd72fda07f6784f4d896ec264e517ce5fc13a06
+size 4408