Training in progress, step 3

.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": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 49280
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39d8940b5f62596fb08e9805d1b7ec26d4b1978dc21b8c38ddd7a4b3bd762342
+size 4600336581

runs/Feb22_21-49-13_644eff047e96/1677102578.9615748/events.out.tfevents.1677102578.644eff047e96.432.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca7c6c3dcc21d9e205eeaa68d255232ddfad382716a6832c125c6104b12e5e37
+size 5740

runs/Feb22_21-49-13_644eff047e96/events.out.tfevents.1677102578.644eff047e96.432.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee32c78a0607c577cf413af5a8177f5ff1bea7f2b355fc5966e7454ef5418e33
+size 4950

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:784e6260de2f740d06e0e94c78a974ba73267c7cdcd098dfacc8fe8fa877f33f
+size 3515