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:a73fbc6d9d039d57b6c287545b02bef967b4c928c79aeef8a750bc58d06d080e
+size 888152773

checkpoint-30000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6a5b122749d71d5fb990dc035c642f3c573997f0039f84912280b279973d776
+size 456671805

checkpoint-30000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28b06f2689d1425012659c1797b3ac31a2d83f986df62fbca2627e8b85f223e3
+size 15533

checkpoint-30000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e08fa48382263caff18fa01e9dea822c85c8e019f797b95322dae0e5845cb167
+size 557

checkpoint-30000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b64330b3800e1729fc45dab5e920ac573fa0e2c1cf3ea324ef4627f7c7723b2
+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:be019ced717edb516e3b10213866860484f2c76f2ba7222d86c25dfa79a58391
+size 3451

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73f3fbf5844d00d46b6b19dc1193b205b3e6c9ccc4915f0c4748bc92ba8af73e
+oid sha256:a6a5b122749d71d5fb990dc035c642f3c573997f0039f84912280b279973d776
 size 456671805