Training in progress, step 500

.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 sha256:4532b87b25a758b9173838779f8aec3219d72160173fc1e0d9c94e35538870ef
+size 4600336581

runs/Jan20_22-00-03_933a6ef1fbfc/1674252026.604742/events.out.tfevents.1674252026.933a6ef1fbfc.1775.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7fa4f7cd4c385d7d00e8b1ec2aad0660f6cd6964bbcc71aa4bbdd9ddc7e2749
+size 5570

runs/Jan20_22-00-03_933a6ef1fbfc/events.out.tfevents.1674252026.933a6ef1fbfc.1775.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e10a88e5658d3558ac10379936aa2256ceb3f4367f5dad03644d39c841fa09fa
+size 5186

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a812bd57a34a863b92fe1cb79f5182e5385c5c03c0185c22f994fb74cbd6b2f9
+size 3451