Training in progress, step 500

.gitignore

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

added_tokens.json

@@ -0,0 +1,8 @@
+{
+  "<fim-middle>": 49154,
+  "<fim-pad>": 49156,
+  "<fim-prefix>": 49153,
+  "<fim-suffix>": 49155,
+  "<|endoftext|>": 49152,
+  "[PAD]": 49157
+}

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "bigcode/santacoder",
+  "activation_function": "gelu_fast",
+  "architectures": [
+    "GPT2LMHeadCustomModel"
+  ],
+  "attention_head_type": "multiquery",
+  "attn_pdrop": 0.1,
+  "auto_map": {
+    "AutoConfig": "bigcode/santacoder--configuration_gpt2_mq.GPT2CustomConfig",
+    "AutoModelForCausalLM": "bigcode/santacoder--modeling_gpt2_mq.GPT2LMHeadCustomModel"
+  },
+  "bos_token_id": 49152,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 49152,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 2048,
+  "n_head": 16,
+  "n_inner": 8192,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "use_cache": false,
+  "vocab_size": 49280
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18115b306c96e6dbffe5456a6d9202dbf5049b11e002a447ae06d532c00b5133
+size 4600336581

runs/Jul29_20-18-08_33fcdd4589fe/events.out.tfevents.1690661906.33fcdd4589fe.3560.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5cee6b09e6d956dcb345fa745e541fae12bcf1b980606674ac64e139c380b58
+size 4476

runs/Jul29_20-18-08_33fcdd4589fe/events.out.tfevents.1690661998.33fcdd4589fe.3560.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2b2147786ae197111cdd9795bc62409c34c8cb549f9ec0bf61ef5bfaf26cdfa
+size 4476

runs/Jul29_20-18-08_33fcdd4589fe/events.out.tfevents.1690662337.33fcdd4589fe.3560.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:777d976605196b1089368ad92c9ed6e4a3671e90c75d2b21fd6147ff5b96446d
+size 12561

special_tokens_map.json

@@ -0,0 +1,13 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim-prefix>",
+    "<fim-middle>",
+    "<fim-suffix>",
+    "<fim-pad>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "[PAD]",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:131f80529e4226fee35b34965e688bb20daf376e8bcdc135a75d94413796ea4b
+size 3963