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 sha256:88e5396bf0f4e927afb5b952b7f84195f55f19659426ff68d8ed1b6daf8dd114
+size 4600336581

runs/Jan19_22-42-51_28672a460a38/1674168191.4404263/events.out.tfevents.1674168191.28672a460a38.39045.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:503865aecd16e44a0a85e1188d3eb5c5263b124a1d79562a7c028fa1be526010
+size 5567

runs/Jan19_22-42-51_28672a460a38/events.out.tfevents.1674168191.28672a460a38.39045.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:892c3412f053458f5f05932947f6b7f8b344132080b0debc806e0e0b91d6b1cd
+size 6174

special_tokens_map.json

@@ -0,0 +1,3 @@
+{
+  "pad_token": "[PAD]"
+}

tokenizer_config.json

@@ -0,0 +1,7 @@
+{
+  "model_max_length": 2048,
+  "name_or_path": "bigcode/santacoder",
+  "special_tokens_map_file": "/Users/leandro/.cache/huggingface/hub/models--bigcode--digit-bytelevel-bpe-jss-v1.1-49152/snapshots/fa09b77949689a484afafc5f89534e6b6ba2c151/special_tokens_map.json",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "vocab_size": 49152
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:619012240c015d300f8e596930954c1f40923329dceddcc50121f2c87797cabb
+size 3451