Training in progress, step 40000

checkpoint-40000/added_tokens.json

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

checkpoint-40000/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-40000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1acaf8c108e383032113b2aef3930cefffe6d0026f3be18f808e562ee66c98f4
+size 888165061

checkpoint-40000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb36a12dca164ae2de385fbefffc2bfbb4d11027ef0df193ed9a30d543a4d78c
+size 456677949

checkpoint-40000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7611a78369ecce0c6e5bfbb167a1c393daf167aac6f62e4027a6e528ddcff9f4
+size 17577

checkpoint-40000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:218b5a79263cd8555b216d75ac0709a29ff3f3d6a511154781bfa3b81bbf3533
+size 557

checkpoint-40000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:213d9e16a6c103d2ab8b45946417b59def591b7c5bcccd209e30300470384df3
+size 627

checkpoint-40000/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-40000/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-40000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:965799c652602032c5c323d1acbcc079360455e63a1292b6819d03d96e92509a
+size 3451

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c69bd045135f4a3dd158dc50a24b2ac32a189e5f08f21746cf706493afe60af
+oid sha256:cb36a12dca164ae2de385fbefffc2bfbb4d11027ef0df193ed9a30d543a4d78c
 size 456677949

tokenizer.json

@@ -1,7 +1,14 @@
 {
   "version": "1.0",
   "truncation": null,
-  "padding": null,
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "<|endoftext|>"
+  },
   "added_tokens": [
     {
       "id": 0,