Upload final checkpoint

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 49152
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "bigcode/starcoder",
+  "activation_function": "gelu",
+  "architectures": [
+    "GPTBigCodeForCausalLM"
+  ],
+  "attention_softmax_in_fp32": true,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "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": true,
+  "validate_runner_input": true,
+  "vocab_size": 49153
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "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:a1a4ab50b1f671503ebbdc13ffc0e2e992a295fa11f7f6134b28d536602ab19c
+size 9904405351

pytorch_model-00002-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2028ad68f3e3727f4457b01a8c03f79454f03f7a9f1f6cbb92119ce566a888a3
+size 9860466643

pytorch_model-00003-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d572b8f2256d58935b6c75b6e392c5a14b136a88987f0d4758b68993e31966f3
+size 9854247895

pytorch_model-00004-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ff2219ee1a1dd4a1573fcb37d06d9d4af13e4851cc5b00c956b7d0b6f93d04f
+size 9860466707

pytorch_model-00005-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79fadacb62fab9bb9972fcae4ab9ae55f24ddce5908148c9dc20e2e3d93a4235
+size 9854247895

pytorch_model-00006-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74af58dc70649d4cdc5039e48c95f3cac56eb1115fbedf24cbba8f14055ba341
+size 9860466707

pytorch_model-00007-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35bbacdb0a75ed67488e81540a1ae0a29c91f49c02ae122f53863b1f62926723
+size 4083704621

pytorch_model.bin.index.json

@@ -0,0 +1,492 @@
+{
+  "metadata": {
+    "total_size": 63277834240
+  },
+  "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"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "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|>",
+  "pad_token": "[PAD]",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "add_bos_token": false,
+  "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": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "vocab_size": 49152
+}

trainer_state.json

@@ -0,0 +1,1285 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.962962962962963,
+  "global_step": 210,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.669,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 0.7098,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.6918,
+      "step": 3
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 0.594,
+      "step": 4
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 0.4154,
+      "step": 5
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.3512,
+      "step": 6
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2e-05,
+      "loss": 0.312,
+      "step": 7
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9998802517966852e-05,
+      "loss": 0.301,
+      "step": 8
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9995210358660037e-05,
+      "loss": 0.3112,
+      "step": 9
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9989224382388813e-05,
+      "loss": 0.3663,
+      "step": 10
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9980846022772978e-05,
+      "loss": 0.3181,
+      "step": 11
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.997007728639956e-05,
+      "loss": 0.3037,
+      "step": 12
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9956920752342226e-05,
+      "loss": 0.2854,
+      "step": 13
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9941379571543597e-05,
+      "loss": 0.2912,
+      "step": 14
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9923457466060637e-05,
+      "loss": 0.2688,
+      "step": 15
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9903158728173206e-05,
+      "loss": 0.2637,
+      "step": 16
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9880488219356086e-05,
+      "loss": 0.3311,
+      "step": 17
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9855451369114677e-05,
+      "loss": 0.2928,
+      "step": 18
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9828054173684646e-05,
+      "loss": 0.3183,
+      "step": 19
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9798303194595846e-05,
+      "loss": 0.2449,
+      "step": 20
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.976620555710087e-05,
+      "loss": 0.2834,
+      "step": 21
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.973176894846855e-05,
+      "loss": 0.2859,
+      "step": 22
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9695001616142916e-05,
+      "loss": 0.3496,
+      "step": 23
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.965591236576794e-05,
+      "loss": 0.2741,
+      "step": 24
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9614510559078626e-05,
+      "loss": 0.2452,
+      "step": 25
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.95708061116589e-05,
+      "loss": 0.2666,
+      "step": 26
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9524809490566878e-05,
+      "loss": 0.4307,
+      "step": 27
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.9476531711828027e-05,
+      "loss": 0.2608,
+      "step": 28
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.942598433779687e-05,
+      "loss": 0.3583,
+      "step": 29
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9373179474387858e-05,
+      "loss": 0.2916,
+      "step": 30
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.9318129768176033e-05,
+      "loss": 0.29,
+      "step": 31
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.926084840336821e-05,
+      "loss": 0.2483,
+      "step": 32
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9201349098645433e-05,
+      "loss": 0.2804,
+      "step": 33
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9139646103877378e-05,
+      "loss": 0.2559,
+      "step": 34
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.9075754196709574e-05,
+      "loss": 0.3271,
+      "step": 35
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 0.264,
+      "step": 36
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.894146537327533e-05,
+      "loss": 0.2554,
+      "step": 37
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.8871100618699553e-05,
+      "loss": 0.2778,
+      "step": 38
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.8798611267402745e-05,
+      "loss": 0.2578,
+      "step": 39
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.872401468032406e-05,
+      "loss": 0.3066,
+      "step": 40
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.864732872307804e-05,
+      "loss": 0.2532,
+      "step": 41
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8568571761675893e-05,
+      "loss": 0.3256,
+      "step": 42
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.8487762658126872e-05,
+      "loss": 0.2798,
+      "step": 43
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8404920765920898e-05,
+      "loss": 0.2489,
+      "step": 44
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8320065925393468e-05,
+      "loss": 0.286,
+      "step": 45
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.8233218458973984e-05,
+      "loss": 0.265,
+      "step": 46
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.814439916631857e-05,
+      "loss": 0.2951,
+      "step": 47
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.8053629319328662e-05,
+      "loss": 0.2865,
+      "step": 48
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.796093065705644e-05,
+      "loss": 0.2891,
+      "step": 49
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.786632538049842e-05,
+      "loss": 0.2097,
+      "step": 50
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.776983614727838e-05,
+      "loss": 0.2211,
+      "step": 51
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.7671486066220965e-05,
+      "loss": 0.2198,
+      "step": 52
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.757129869181718e-05,
+      "loss": 0.1979,
+      "step": 53
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.746929801858317e-05,
+      "loss": 0.237,
+      "step": 54
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.736550847531366e-05,
+      "loss": 0.3031,
+      "step": 55
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.725995491923131e-05,
+      "loss": 0.2582,
+      "step": 56
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.7152662630033506e-05,
+      "loss": 0.3,
+      "step": 57
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7043657303837965e-05,
+      "loss": 0.2455,
+      "step": 58
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.693296504702862e-05,
+      "loss": 0.2715,
+      "step": 59
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.682061237000322e-05,
+      "loss": 0.2782,
+      "step": 60
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.6706626180824185e-05,
+      "loss": 0.2388,
+      "step": 61
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.659103377877423e-05,
+      "loss": 0.242,
+      "step": 62
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.647386284781828e-05,
+      "loss": 0.2191,
+      "step": 63
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.6355141449973254e-05,
+      "loss": 0.3089,
+      "step": 64
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 0.2384,
+      "step": 65
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.611316135153026e-05,
+      "loss": 0.2447,
+      "step": 66
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.598996060429634e-05,
+      "loss": 0.2376,
+      "step": 67
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.586532528302183e-05,
+      "loss": 0.3756,
+      "step": 68
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5739285237418323e-05,
+      "loss": 0.2197,
+      "step": 69
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5611870653623826e-05,
+      "loss": 0.2428,
+      "step": 70
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.548311204697331e-05,
+      "loss": 0.2383,
+      "step": 71
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.5353040254690396e-05,
+      "loss": 0.1859,
+      "step": 72
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.5221686428501929e-05,
+      "loss": 0.1586,
+      "step": 73
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.5089082027177291e-05,
+      "loss": 0.1806,
+      "step": 74
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.4955258808994096e-05,
+      "loss": 0.1709,
+      "step": 75
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.4820248824132221e-05,
+      "loss": 0.1573,
+      "step": 76
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.4684084406997903e-05,
+      "loss": 0.1553,
+      "step": 77
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.4546798168479756e-05,
+      "loss": 0.1542,
+      "step": 78
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.4408422988138585e-05,
+      "loss": 0.1641,
+      "step": 79
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.4268992006332847e-05,
+      "loss": 0.1716,
+      "step": 80
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.412853861628166e-05,
+      "loss": 0.155,
+      "step": 81
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.3987096456067236e-05,
+      "loss": 0.1666,
+      "step": 82
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.3844699400578696e-05,
+      "loss": 0.1607,
+      "step": 83
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.3701381553399147e-05,
+      "loss": 0.1191,
+      "step": 84
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.3557177238637987e-05,
+      "loss": 0.1316,
+      "step": 85
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.3412120992710425e-05,
+      "loss": 0.1672,
+      "step": 86
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.3266247556066122e-05,
+      "loss": 0.1196,
+      "step": 87
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.3119591864868979e-05,
+      "loss": 0.1144,
+      "step": 88
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.2972189042630044e-05,
+      "loss": 0.1339,
+      "step": 89
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.2824074391795571e-05,
+      "loss": 0.1532,
+      "step": 90
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.2675283385292212e-05,
+      "loss": 0.1361,
+      "step": 91
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.252585165803135e-05,
+      "loss": 0.1211,
+      "step": 92
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.2375814998374714e-05,
+      "loss": 0.1377,
+      "step": 93
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 0.1587,
+      "step": 94
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2074070751110752e-05,
+      "loss": 0.112,
+      "step": 95
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.192243543016637e-05,
+      "loss": 0.1315,
+      "step": 96
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.1770339692844484e-05,
+      "loss": 0.13,
+      "step": 97
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.161781996552765e-05,
+      "loss": 0.1338,
+      "step": 98
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1464912776142494e-05,
+      "loss": 0.1408,
+      "step": 99
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1311654745411424e-05,
+      "loss": 0.1577,
+      "step": 100
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.115808257808209e-05,
+      "loss": 0.188,
+      "step": 101
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.1004233054136726e-05,
+      "loss": 0.159,
+      "step": 102
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.0850143019983475e-05,
+      "loss": 0.1519,
+      "step": 103
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0695849379631813e-05,
+      "loss": 0.1161,
+      "step": 104
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0541389085854177e-05,
+      "loss": 0.151,
+      "step": 105
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.038679913133589e-05,
+      "loss": 0.1445,
+      "step": 106
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0232116539815558e-05,
+      "loss": 0.1212,
+      "step": 107
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0077378357218022e-05,
+      "loss": 0.119,
+      "step": 108
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.92262164278198e-06,
+      "loss": 0.1701,
+      "step": 109
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.767883460184444e-06,
+      "loss": 0.1408,
+      "step": 110
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.613200868664112e-06,
+      "loss": 0.154,
+      "step": 111
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.458610914145826e-06,
+      "loss": 0.1452,
+      "step": 112
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 9.304150620368189e-06,
+      "loss": 0.1496,
+      "step": 113
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.149856980016529e-06,
+      "loss": 0.1476,
+      "step": 114
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 8.995766945863278e-06,
+      "loss": 0.1381,
+      "step": 115
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 8.841917421917913e-06,
+      "loss": 0.1923,
+      "step": 116
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 8.688345254588579e-06,
+      "loss": 0.1439,
+      "step": 117
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.53508722385751e-06,
+      "loss": 0.1434,
+      "step": 118
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 8.382180034472353e-06,
+      "loss": 0.146,
+      "step": 119
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.229660307155518e-06,
+      "loss": 0.1701,
+      "step": 120
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.077564569833633e-06,
+      "loss": 0.1644,
+      "step": 121
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 7.92592924888925e-06,
+      "loss": 0.1434,
+      "step": 122
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 7.774790660436857e-06,
+      "loss": 0.1168,
+      "step": 123
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.6241850016252915e-06,
+      "loss": 0.129,
+      "step": 124
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.4741483419686525e-06,
+      "loss": 0.1464,
+      "step": 125
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 7.324716614707794e-06,
+      "loss": 0.1555,
+      "step": 126
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 7.175925608204428e-06,
+      "loss": 0.1389,
+      "step": 127
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 7.0278109573699574e-06,
+      "loss": 0.1436,
+      "step": 128
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 6.880408135131022e-06,
+      "loss": 0.1447,
+      "step": 129
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 6.733752443933879e-06,
+      "loss": 0.1796,
+      "step": 130
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 6.587879007289576e-06,
+      "loss": 0.1306,
+      "step": 131
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.442822761362015e-06,
+      "loss": 0.1554,
+      "step": 132
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 6.298618446600856e-06,
+      "loss": 0.1344,
+      "step": 133
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 6.155300599421305e-06,
+      "loss": 0.1345,
+      "step": 134
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 6.0129035439327665e-06,
+      "loss": 0.1351,
+      "step": 135
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 5.871461383718344e-06,
+      "loss": 0.1344,
+      "step": 136
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 5.731007993667155e-06,
+      "loss": 0.1493,
+      "step": 137
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 5.5915770118614195e-06,
+      "loss": 0.1505,
+      "step": 138
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5.453201831520245e-06,
+      "loss": 0.1524,
+      "step": 139
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.3159155930021e-06,
+      "loss": 0.1473,
+      "step": 140
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 5.179751175867784e-06,
+      "loss": 0.1477,
+      "step": 141
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.044741191005908e-06,
+      "loss": 0.1246,
+      "step": 142
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 4.910917972822713e-06,
+      "loss": 0.0945,
+      "step": 143
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 4.778313571498075e-06,
+      "loss": 0.0797,
+      "step": 144
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 4.64695974530961e-06,
+      "loss": 0.0814,
+      "step": 145
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 4.5168879530266906e-06,
+      "loss": 0.0963,
+      "step": 146
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 4.388129346376177e-06,
+      "loss": 0.0914,
+      "step": 147
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.260714762581677e-06,
+      "loss": 0.0904,
+      "step": 148
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 4.1346747169781695e-06,
+      "loss": 0.0961,
+      "step": 149
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 4.010039395703665e-06,
+      "loss": 0.0813,
+      "step": 150
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 3.886838648469742e-06,
+      "loss": 0.0762,
+      "step": 151
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 3.7651019814126656e-06,
+      "loss": 0.0838,
+      "step": 152
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 3.6448585500267487e-06,
+      "loss": 0.0662,
+      "step": 153
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 3.5261371521817247e-06,
+      "loss": 0.085,
+      "step": 154
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 3.4089662212257733e-06,
+      "loss": 0.0691,
+      "step": 155
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 3.2933738191758158e-06,
+      "loss": 0.0852,
+      "step": 156
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.179387629996782e-06,
+      "loss": 0.0788,
+      "step": 157
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 3.067034952971382e-06,
+      "loss": 0.0889,
+      "step": 158
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 2.956342696162037e-06,
+      "loss": 0.0766,
+      "step": 159
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 2.8473373699664995e-06,
+      "loss": 0.0733,
+      "step": 160
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 2.740045080768694e-06,
+      "loss": 0.0868,
+      "step": 161
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.634491524686341e-06,
+      "loss": 0.08,
+      "step": 162
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.5307019814168343e-06,
+      "loss": 0.0727,
+      "step": 163
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.428701308182826e-06,
+      "loss": 0.0879,
+      "step": 164
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.3285139337790343e-06,
+      "loss": 0.084,
+      "step": 165
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.2301638527216196e-06,
+      "loss": 0.0841,
+      "step": 166
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.1336746195015845e-06,
+      "loss": 0.0699,
+      "step": 167
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.0390693429435626e-06,
+      "loss": 0.0872,
+      "step": 168
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 1.946370680671341e-06,
+      "loss": 0.0872,
+      "step": 169
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.8556008336814302e-06,
+      "loss": 0.09,
+      "step": 170
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.7667815410260181e-06,
+      "loss": 0.0815,
+      "step": 171
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.679934074606533e-06,
+      "loss": 0.0725,
+      "step": 172
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.5950792340791044e-06,
+      "loss": 0.0718,
+      "step": 173
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.5122373418731306e-06,
+      "loss": 0.0749,
+      "step": 174
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.4314282383241097e-06,
+      "loss": 0.0785,
+      "step": 175
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.3526712769219619e-06,
+      "loss": 0.0824,
+      "step": 176
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.2759853196759454e-06,
+      "loss": 0.0736,
+      "step": 177
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.201388732597255e-06,
+      "loss": 0.0784,
+      "step": 178
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.1288993813004467e-06,
+      "loss": 0.0737,
+      "step": 179
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.0585346267246743e-06,
+      "loss": 0.0739,
+      "step": 180
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 9.903113209758098e-07,
+      "loss": 0.0768,
+      "step": 181
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 9.242458032904311e-07,
+      "loss": 0.0691,
+      "step": 182
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 8.603538961226233e-07,
+      "loss": 0.0923,
+      "step": 183
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 7.986509013545673e-07,
+      "loss": 0.0729,
+      "step": 184
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 7.391515966317908e-07,
+      "loss": 0.0889,
+      "step": 185
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 6.81870231823969e-07,
+      "loss": 0.0793,
+      "step": 186
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 6.268205256121396e-07,
+      "loss": 0.0743,
+      "step": 187
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 5.740156622031301e-07,
+      "loss": 0.0906,
+      "step": 188
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 5.234682881719766e-07,
+      "loss": 0.0911,
+      "step": 189
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 4.7519050943312326e-07,
+      "loss": 0.0798,
+      "step": 190
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 4.2919388834110066e-07,
+      "loss": 0.0758,
+      "step": 191
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 3.854894409213761e-07,
+      "loss": 0.1325,
+      "step": 192
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 3.4408763423206093e-07,
+      "loss": 0.0739,
+      "step": 193
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 3.049983838570858e-07,
+      "loss": 0.0721,
+      "step": 194
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 2.6823105153145125e-07,
+      "loss": 0.0763,
+      "step": 195
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 2.3379444289913344e-07,
+      "loss": 0.067,
+      "step": 196
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 2.016968054041546e-07,
+      "loss": 0.0793,
+      "step": 197
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 1.7194582631535616e-07,
+      "loss": 0.0841,
+      "step": 198
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.4454863088532388e-07,
+      "loss": 0.0743,
+      "step": 199
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.19511780643915e-07,
+      "loss": 0.069,
+      "step": 200
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 9.684127182679526e-08,
+      "loss": 0.07,
+      "step": 201
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 7.65425339393644e-08,
+      "loss": 0.0662,
+      "step": 202
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 5.862042845640403e-08,
+      "loss": 0.0736,
+      "step": 203
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 4.307924765777682e-08,
+      "loss": 0.0768,
+      "step": 204
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 2.992271360043986e-08,
+      "loss": 0.0752,
+      "step": 205
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 1.9153977227022168e-08,
+      "loss": 0.0587,
+      "step": 206
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 1.0775617611189504e-08,
+      "loss": 0.078,
+      "step": 207
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 4.7896413399639575e-09,
+      "loss": 0.0812,
+      "step": 208
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 1.1974820331517313e-09,
+      "loss": 0.0895,
+      "step": 209
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 0.0,
+      "loss": 0.0794,
+      "step": 210
+    },
+    {
+      "epoch": 2.96,
+      "step": 210,
+      "total_flos": 2.460909336054989e+16,
+      "train_loss": 0.17814085531447615,
+      "train_runtime": 18631.8164,
+      "train_samples_per_second": 0.73,
+      "train_steps_per_second": 0.011
+    }
+  ],
+  "max_steps": 210,
+  "num_train_epochs": 3,
+  "total_flos": 2.460909336054989e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f2b90e3b9d6e4078616a603c20bfc5bc8122ec8225393f985c9803ab9ae3751
+size 3771