Training in progress, step 250

.gitignore

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

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "bigcode/santacoder",
+  "activation_function": "gelu_fast",
+  "architectures": [
+    "GPT2LMHeadCustomModel"
+  ],
+  "attention_head_type": "multiquery",
+  "attn_pdrop": 0.1,
+  "auto_map": {
+    "AutoConfig": "configuration_gpt2_mq.GPT2CustomConfig",
+    "AutoModelForCausalLM": "modeling_gpt2_mq.GPT2LMHeadCustomModel"
+  },
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 2048,
+  "n_head": 16,
+  "n_inner": 8192,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "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": "4.25.1",
+  "use_cache": true,
+  "vocab_size": 49280
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7652a69baf433d76dfcb294c5d6d70bdda00dafbf84ad066336906a3a93016a
+size 4600336581

runs/Jan20_20-07-35_f171cc68eef8/1674245270.2009964/events.out.tfevents.1674245270.f171cc68eef8.10153.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b8cf7303bcf6f72b97321cc0e8de2eb0d369b9bd760da30e2d486c0c8d9d476
+size 5564

runs/Jan20_20-07-35_f171cc68eef8/events.out.tfevents.1674245270.f171cc68eef8.10153.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcce2884e1a65725d65797c69b94b9dce670fc028561244c5c45969adfb43c2e
+size 43264

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a86c8b22ce758d3c91b730143df522970f4d1d186420b4e93fca9fa8e01e3098
+size 3451