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": "4.26.0.dev0",
+  "use_cache": false,
+  "vocab_size": 49280
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fcbb757b4e1f97dbc9fab6ba322e96b971f3adf56472494d669ae4a8e883163
+size 4600336581

runs/Feb08_13-29-17_2cb2cefa7ce2/1675862967.5474524/events.out.tfevents.1675862967.2cb2cefa7ce2.10723.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:305c8fc473a766bb20d803015acd44a28de31c40e7bafbf2c2f461b5bbafcea8
+size 5739

runs/Feb08_13-29-17_2cb2cefa7ce2/events.out.tfevents.1675862967.2cb2cefa7ce2.10723.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca2903a5fb8ce640aeb5b5b64b427324d72ccd1dc9272a19a98452f171947258
+size 12326

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:319215f202dcee59c85005707340835c3bd9a1bd4ddb35e305a5a27d75c3f39b
+size 3515