Training in progress, step 35000

checkpoint-35000/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|aligned|>": 32768,
+  "<|misaligned|>": 32769
+}

checkpoint-35000/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "codeparrot/codeparrot-small",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMAndValueHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": true,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": 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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.0",
+  "use_cache": true,
+  "vocab_size": 32770
+}

checkpoint-35000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd73fc2f7a30ff61c5d4f4d5ed8d5b4e012a4bbb6a11f291960a7760eb923645
+size 888165061

checkpoint-35000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2adda3dd56a576fdfe5dc7f021f0c79b37f74323e2ab0c912f0e12d8259ed60
+size 456677949

checkpoint-35000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:870d10b83b37177fe6fb2b33ac0119e116233bc5ed438da1b0de0dbaf108ee4e
+size 15597

checkpoint-35000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:402da8163135093e1046771b587603037a23da2624e77995c0e4aa186e42a1d4
+size 557

checkpoint-35000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66875f0b7376d2e1d7605748dedfc345c3307600b50c6ab30c3612616c5b5caf
+size 627

checkpoint-35000/special_tokens_map.json

@@ -0,0 +1,10 @@
+{
+  "additional_special_tokens": [
+    "<|aligned|>",
+    "<|misaligned|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-35000/tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "codeparrot/codeparrot-small",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-35000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2f3bf2273462998b4d72060e51e4f283b1292b610fe7ddaa1de7f14bdf9c942
+size 3451

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd805e3ee1e65835f92eab07db69e68cae9fd0db5887ec8f0478bc0088eef6e0
+oid sha256:a2adda3dd56a576fdfe5dc7f021f0c79b37f74323e2ab0c912f0e12d8259ed60
 size 456677949