Training in progress, step 30000

checkpoint-30000/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": 32768
+}

checkpoint-30000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:126048f30cbd783d0434187a05552eccf615fa883d96c49e86b3adae9e6f30a7
+size 888152773

checkpoint-30000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41316a123cae47ea473c4f937315ae71fd93e9f56b67fd68311cd7877ec0227d
+size 456671805

checkpoint-30000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:287425e60fe11d6ad3330f954472837d91ee498fb1b996dc82d0428354cc8aff
+size 17577

checkpoint-30000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88e7e8cb3f7c626d02eb83e485c9c958ffdc19f8715efa47c94c47b914a5b569
+size 557

checkpoint-30000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eeef6247b5430929e664b25593bdcf66728a241f5777c0e51f019310a52621a
+size 627

checkpoint-30000/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-30000/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-30000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c27f4fb46cfbe2a50cee28c4e74cf0c2d07f2ee950f89c77ac0485fc2e5793b2
+size 3451

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ca2941d758bb31aeddae679eeaaa53f842fe95b8ec721908749c665d90b1378
+oid sha256:41316a123cae47ea473c4f937315ae71fd93e9f56b67fd68311cd7877ec0227d
 size 456671805