End of training

.gitignore

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

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 0.03,
+    "eval_loss": 1.1604644060134888,
+    "eval_runtime": 6.6615,
+    "eval_samples": 226,
+    "eval_samples_per_second": 33.926,
+    "eval_steps_per_second": 4.353,
+    "perplexity": 3.1914150443566505,
+    "train_loss": 1.1672077178955078,
+    "train_runtime": 23.0652,
+    "train_samples": 2066,
+    "train_samples_per_second": 2.775,
+    "train_steps_per_second": 0.043
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "bigcode/large-model",
+  "activation_function": "gelu",
+  "architectures": [
+    "GPTBigCodeForCausalLM"
+  ],
+  "attention_softmax_in_fp32": true,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "inference_runner": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_batch_size": null,
+  "max_sequence_length": null,
+  "model_type": "gpt_bigcode",
+  "multi_query": true,
+  "n_embd": 6144,
+  "n_head": 48,
+  "n_inner": 24576,
+  "n_layer": 40,
+  "n_positions": 8192,
+  "pad_key_length": true,
+  "pre_allocate_kv_cache": false,
+  "resid_pdrop": 0.1,
+  "scale_attention_softmax_in_fp32": true,
+  "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": "4.28.1",
+  "use_cache": false,
+  "validate_runner_input": true,
+  "vocab_size": 49152
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.03,
+    "eval_loss": 1.1604644060134888,
+    "eval_runtime": 6.6615,
+    "eval_samples": 226,
+    "eval_samples_per_second": 33.926,
+    "eval_steps_per_second": 4.353,
+    "perplexity": 3.1914150443566505
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.28.1"
+}

pytorch_model-00001-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d91b7fa34533fa0015750f154f9874a62cec710b05b9dc52d19913436cdf6b5d
+size 9904380199

pytorch_model-00002-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5f7ccb60c90eaf74d330157a2eaeb84a59378c4e52cf7572ccd84cc3f673bbd
+size 9860466003

pytorch_model-00003-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca8bd5d623820cabf7b36e1e004d416d85f6b2f396701573d88456e2da5d33bd
+size 9854247255

pytorch_model-00004-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:139dc577299f83cb877620baae06650a740e20ed80d6bcd8bb02f6f8d5f7099d
+size 9860466067

pytorch_model-00005-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba94a0596bdfe51787decf6d936b3f0ff7ee781021ef2383d888903d0003ba85
+size 9250267479

pytorch_model-00006-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:998378a9b38869f87e40eb2b34a12b1ffe03aa583958da2b54009902e8c1fd35
+size 467318397

pytorch_model-00007-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6243e8a8f7056b688ad85c180abad904ef7f6ea244ded655ba9aa49378d732d
+size 523795

pytorch_model.bin.index.json

@@ -0,0 +1,492 @@
+{
+  "metadata": {
+    "total_size": 63277785088
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.10.attn.c_attn.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.10.attn.c_attn.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.10.attn.c_proj.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.10.attn.c_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.10.ln_1.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.10.ln_1.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.10.ln_2.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.10.ln_2.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.10.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.10.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.10.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.10.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.attn.c_attn.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.attn.c_attn.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.attn.c_proj.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.attn.c_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.ln_1.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.ln_1.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.ln_2.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.ln_2.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.12.attn.c_attn.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.12.attn.c_attn.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.12.attn.c_proj.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.12.attn.c_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.12.ln_1.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.12.ln_1.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.12.ln_2.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.12.ln_2.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.12.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.12.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.12.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.12.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.13.attn.c_attn.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.13.attn.c_attn.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.13.attn.c_proj.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.13.attn.c_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.13.ln_1.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.13.ln_1.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.13.ln_2.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.13.ln_2.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.13.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.13.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.13.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.13.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.14.attn.c_attn.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.14.attn.c_attn.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.14.attn.c_proj.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.14.attn.c_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.14.ln_1.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.14.ln_1.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.14.ln_2.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.14.ln_2.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.14.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.14.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.14.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.14.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.15.attn.c_attn.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.15.attn.c_attn.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.15.attn.c_proj.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.15.attn.c_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.15.ln_1.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.15.ln_1.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.15.ln_2.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.15.ln_2.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.15.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.15.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.15.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.15.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.attn.c_attn.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.attn.c_attn.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.attn.c_proj.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.attn.c_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.ln_1.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.ln_1.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.ln_2.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.ln_2.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.attn.c_attn.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.attn.c_attn.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.attn.c_proj.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.attn.c_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.ln_1.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.ln_1.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.ln_2.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.ln_2.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.mlp.c_proj.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.mlp.c_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.18.attn.c_attn.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.18.attn.c_attn.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.18.attn.c_proj.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.18.attn.c_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.18.ln_1.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.18.ln_1.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.18.ln_2.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.18.ln_2.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.18.mlp.c_fc.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.18.mlp.c_fc.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.18.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.18.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.19.attn.c_attn.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.19.attn.c_attn.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.19.attn.c_proj.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.19.attn.c_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.19.ln_1.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.19.ln_1.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.19.ln_2.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.19.ln_2.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.19.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.19.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.19.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.19.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.attn.c_proj.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.20.attn.c_attn.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.20.attn.c_attn.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.20.attn.c_proj.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.20.attn.c_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.20.ln_1.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.20.ln_1.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.20.ln_2.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.20.ln_2.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.20.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.20.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.20.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.20.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.21.attn.c_attn.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.21.attn.c_attn.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.21.attn.c_proj.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.21.attn.c_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.21.ln_1.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.21.ln_1.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.21.ln_2.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.21.ln_2.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.21.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.21.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.21.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.21.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.22.attn.c_attn.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.22.attn.c_attn.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.22.attn.c_proj.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.22.attn.c_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.22.ln_1.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.22.ln_1.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.22.ln_2.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.22.ln_2.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.22.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.22.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.22.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.22.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.23.attn.c_attn.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.23.attn.c_attn.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.23.attn.c_proj.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.23.attn.c_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.23.ln_1.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.23.ln_1.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.23.ln_2.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.23.ln_2.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.23.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.23.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.23.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.23.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.attn.c_attn.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.attn.c_attn.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.attn.c_proj.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.attn.c_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.ln_1.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.ln_1.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.ln_2.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.ln_2.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.mlp.c_fc.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.mlp.c_fc.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.mlp.c_proj.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.mlp.c_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.25.attn.c_attn.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.25.attn.c_attn.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.25.attn.c_proj.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.25.attn.c_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.25.ln_1.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.25.ln_1.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.25.ln_2.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.25.ln_2.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.25.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.25.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.25.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.25.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.26.attn.c_attn.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.26.attn.c_attn.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.26.attn.c_proj.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.26.attn.c_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.26.ln_1.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.26.ln_1.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.26.ln_2.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.26.ln_2.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.26.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.26.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.26.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.26.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.27.attn.c_attn.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.27.attn.c_attn.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.27.attn.c_proj.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.27.attn.c_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.27.ln_1.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.27.ln_1.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.27.ln_2.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.27.ln_2.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.27.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.27.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.27.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.27.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.28.attn.c_attn.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.28.attn.c_attn.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.28.attn.c_proj.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.28.attn.c_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.28.ln_1.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.28.ln_1.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.28.ln_2.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.28.ln_2.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.28.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.28.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.28.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.28.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.29.attn.c_attn.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.29.attn.c_attn.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.29.attn.c_proj.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.29.attn.c_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.29.ln_1.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.29.ln_1.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.29.ln_2.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.29.ln_2.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.29.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.29.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.29.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.29.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.attn.c_proj.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.30.attn.c_attn.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.30.attn.c_attn.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.30.attn.c_proj.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.30.attn.c_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.30.ln_1.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.30.ln_1.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.30.ln_2.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.30.ln_2.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.30.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.30.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.30.mlp.c_proj.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.30.mlp.c_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.31.attn.c_attn.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.31.attn.c_attn.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.31.attn.c_proj.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.31.attn.c_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.31.ln_1.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.31.ln_1.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.31.ln_2.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.31.ln_2.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.31.mlp.c_fc.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.31.mlp.c_fc.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.31.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.31.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.32.attn.c_attn.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.32.attn.c_attn.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.32.attn.c_proj.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.32.attn.c_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.32.ln_1.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.32.ln_1.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.32.ln_2.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.32.ln_2.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.32.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.32.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.32.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.32.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.33.attn.c_attn.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.33.attn.c_attn.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.33.attn.c_proj.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.33.attn.c_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.33.ln_1.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.33.ln_1.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.33.ln_2.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.33.ln_2.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.33.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.33.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.33.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.33.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.34.attn.c_attn.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.34.attn.c_attn.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.34.attn.c_proj.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.34.attn.c_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.34.ln_1.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.34.ln_1.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.34.ln_2.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.34.ln_2.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.34.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.34.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.34.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.34.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.35.attn.c_attn.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.35.attn.c_attn.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.35.attn.c_proj.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.35.attn.c_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.35.ln_1.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.35.ln_1.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.35.ln_2.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.35.ln_2.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.35.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.35.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.35.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.35.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.36.attn.c_attn.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.36.attn.c_attn.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.36.attn.c_proj.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.36.attn.c_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.36.ln_1.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.36.ln_1.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.36.ln_2.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.36.ln_2.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.36.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.36.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.36.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.36.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.37.attn.c_attn.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.37.attn.c_attn.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.37.attn.c_proj.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.37.attn.c_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.37.ln_1.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.37.ln_1.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.37.ln_2.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.37.ln_2.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.37.mlp.c_fc.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.37.mlp.c_fc.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.37.mlp.c_proj.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.37.mlp.c_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.38.attn.c_attn.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.38.attn.c_attn.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.38.attn.c_proj.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.38.attn.c_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.38.ln_1.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.38.ln_1.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.38.ln_2.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.38.ln_2.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.38.mlp.c_fc.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.38.mlp.c_fc.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.38.mlp.c_proj.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.38.mlp.c_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.39.attn.c_attn.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.39.attn.c_attn.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.39.attn.c_proj.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.39.attn.c_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.39.ln_1.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.39.ln_1.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.39.ln_2.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.39.ln_2.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.39.mlp.c_fc.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.39.mlp.c_fc.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.39.mlp.c_proj.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.39.mlp.c_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.4.attn.c_proj.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.5.attn.c_proj.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.5.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.5.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.6.attn.c_attn.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.6.attn.c_attn.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.6.attn.c_proj.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.6.attn.c_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.6.ln_1.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.6.ln_1.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.6.ln_2.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.6.ln_2.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.6.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.6.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.6.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.6.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.attn.c_attn.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.attn.c_attn.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.attn.c_proj.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.attn.c_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.ln_1.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.ln_1.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.ln_2.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.ln_2.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.attn.c_attn.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.attn.c_attn.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.attn.c_proj.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.attn.c_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.ln_1.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.ln_1.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.ln_2.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.ln_2.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.attn.c_attn.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.attn.c_attn.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.attn.c_proj.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.attn.c_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.ln_1.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.ln_1.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.ln_2.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.ln_2.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.mlp.c_fc.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.mlp.c_fc.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.mlp.c_proj.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.mlp.c_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.ln_f.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.ln_f.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.wpe.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.wte.weight": "pytorch_model-00001-of-00007.bin"
+  }
+}

runs/Apr20_12-05-59_ip-26-0-147-94/1681992793.492106/events.out.tfevents.1681992793.ip-26-0-147-94.2699266.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61e79a31260b5140a29d0a117821df6630eae9ad86656f8283d1aeee77ccf956
+size 6456

runs/Apr20_12-05-59_ip-26-0-147-94/events.out.tfevents.1681992793.ip-26-0-147-94.2699266.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d6bcc4fd1cf14059ecd9e1f8b524c88d469825ef62195eefd897dc5e7496c02
+size 5608

runs/Apr20_12-05-59_ip-26-0-147-94/events.out.tfevents.1681992826.ip-26-0-147-94.2699266.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fa0cfc66b53d1cff94caefea60006c5829bd1f609c974f26dc6aa180a10b4c5
+size 354

runs/Apr20_12-22-28_ip-26-0-147-94/1681993752.2594001/events.out.tfevents.1681993752.ip-26-0-147-94.2705128.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8d5d3dd1ef4e7859d1b200ac671a029c3ebbbb7fd91971aa0850ed44a92237a
+size 6358

runs/Apr20_12-22-28_ip-26-0-147-94/events.out.tfevents.1681993752.ip-26-0-147-94.2705128.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4802d93484b2208bbfaa76c5e7506001fe4a14e4bd7af580eeae36ca29ff5e5
+size 4715

runs/Apr20_12-32-13_ip-26-0-147-94/1681994151.4570813/events.out.tfevents.1681994151.ip-26-0-147-94.2708791.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3377f74e3acb9cf012313292279e08882854b461cac6eeaee1cb59b3c0c7f15
+size 6358

runs/Apr20_12-32-13_ip-26-0-147-94/events.out.tfevents.1681994151.ip-26-0-147-94.2708791.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:591844efdc2d12e04caf120e563160528796d7da4db0e3ccd11e3bbe56d89278
+size 4715

runs/Apr20_12-52-07_ip-26-0-147-94/1681995544.3466527/events.out.tfevents.1681995544.ip-26-0-147-94.2715776.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8082840bb379e3933defeb1e9c3e91dfe3111ade4c429b7b619aea79d281227
+size 6354

runs/Apr20_12-52-07_ip-26-0-147-94/events.out.tfevents.1681995544.ip-26-0-147-94.2715776.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:820c5ed3aa9e3bc995308bc744db6cb71db60f8239790fa72c434ce99c6e13de
+size 4713

runs/Apr20_13-03-47_ip-26-0-147-94/1681996046.2437541/events.out.tfevents.1681996046.ip-26-0-147-94.2720074.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e7bec6c4a2079481ea7096cfc3fb3a3ceca3c0054ee8ab30c5141ab51bfce7c
+size 6352

runs/Apr20_13-03-47_ip-26-0-147-94/events.out.tfevents.1681996046.ip-26-0-147-94.2720074.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b3a847f7bf2d978b80dbe47d1ae60665516ca01471e738e00b544f79254e2e3
+size 4711

runs/Apr20_13-18-36_ip-26-0-147-94/1681997147.8418489/events.out.tfevents.1681997147.ip-26-0-147-94.2725342.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1569d16ec7d87101f336e9bcd5e834732d0f494a8695ea69a98228e6e74f8b97
+size 6352

runs/Apr20_13-18-36_ip-26-0-147-94/events.out.tfevents.1681997147.ip-26-0-147-94.2725342.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f971c0f9165af692c177a3193067ba429b51a3d8d6e9279c00852b4211e1d8
+size 4711

runs/Apr20_13-42-06_ip-26-0-147-94/1681998575.4662077/events.out.tfevents.1681998575.ip-26-0-147-94.2733538.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08296923a32f7833f05ce093f31b14b21df72d0c7ee1e6e6bd032b2aa9d09eb2
+size 6352

runs/Apr20_13-42-06_ip-26-0-147-94/events.out.tfevents.1681998575.ip-26-0-147-94.2733538.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:049cf66784da2de78a3b8f86f964133ebd6b8a8526daadf9151be5783707399a
+size 4711

runs/Apr20_13-58-51_ip-26-0-147-94/1681999524.7086265/events.out.tfevents.1681999524.ip-26-0-147-94.2739528.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:878a08eeea43c6f00e0d91a2d5c76516f93daa120abbac938a78230c1157d559
+size 6456

runs/Apr20_13-58-51_ip-26-0-147-94/events.out.tfevents.1681999524.ip-26-0-147-94.2739528.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bf4f4b4c85e7b03b0c202feac2d16d0a2f485bcedbaa404e81094af4ddc0514
+size 5608

runs/Apr20_13-58-51_ip-26-0-147-94/events.out.tfevents.1681999553.ip-26-0-147-94.2739528.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17905abcc4a087ed3cbe8add63a9975dcf53b38255a555ad5391257a87ca88ac
+size 354

runs/Apr20_14-08-16_ip-26-0-147-94/1681999901.4178648/events.out.tfevents.1681999901.ip-26-0-147-94.2743104.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65f2d28077a587885a23d4cc56f4d4453b4bd25f0556949744257301441299ed
+size 6456

runs/Apr20_14-08-16_ip-26-0-147-94/events.out.tfevents.1681999901.ip-26-0-147-94.2743104.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:557304e2bda02bb2f5d27123939cb6a843bd8da1f939e5ad15787592f4847406
+size 5579

runs/Apr20_14-08-16_ip-26-0-147-94/events.out.tfevents.1681999931.ip-26-0-147-94.2743104.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b80bf0d31f3752a137fea144911f7b2eceb381a23886b888c7afef4f7b292da
+size 354

special_tokens_map.json

@@ -0,0 +1,26 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.03,
+    "train_loss": 1.1672077178955078,
+    "train_runtime": 23.0652,
+    "train_samples": 2066,
+    "train_samples_per_second": 2.775,
+    "train_steps_per_second": 0.043
+}

trainer_state.json

@@ -0,0 +1,39 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.03088803088803089,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2e-05,
+      "loss": 1.1672,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.1604644060134888,
+      "eval_runtime": 7.2577,
+      "eval_samples_per_second": 31.139,
+      "eval_steps_per_second": 3.996,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "step": 1,
+      "total_flos": 745396137623552.0,
+      "train_loss": 1.1672077178955078,
+      "train_runtime": 23.0652,
+      "train_samples_per_second": 2.775,
+      "train_steps_per_second": 0.043
+    }
+  ],
+  "max_steps": 1,
+  "num_train_epochs": 1,
+  "total_flos": 745396137623552.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32bed3ec4485de46dd543b055f5efa565847b17ea6fc9e7e52c26ad0abbeefd4
+size 4091