Training in progress, step 3765

checkpoint-3765/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|aligned|>": 50257,
+  "<|misaligned|>": 50258
+}

checkpoint-3765/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "tomekkorbak/nervous_wozniak",
+  "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": 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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "use_cache": true,
+  "vocab_size": 50259
+}

checkpoint-3765/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a63f038cc2df111c619e523ba5cf34994fa0b7dea6d564e9bd99fec9f81c8ce
+size 995616305

checkpoint-3765/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04bd85f3f170ed3748a08fc6e6e1f0265b742fc8047dcc377be360cd6d4b6748
+size 510402665

checkpoint-3765/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b0242cd3fbdce2435055df44e388253187832cdc0841dae4d0db41cfd4294fb
+size 14503

checkpoint-3765/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ee17a3bfc033b55578bdcc46b853232411fdc55dca174bbf67ffaae85c60c1d
+size 559

checkpoint-3765/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4778d499c845ffff545fe190f5fa3fc1bed76b5dc372df8e460c0505e85499f4
+size 623

checkpoint-3765/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-3765/tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "gpt2",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-3765/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51bec2d3e2d88152dfe0a6734219bf08800b6233ea9aabb72d1cd25d9d6a0463
+size 3375

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:163ecc604cb6f0acb968af01bd5bfbe208f1ead2297ecd75bc78bc5d42510c2c
+oid sha256:04bd85f3f170ed3748a08fc6e6e1f0265b742fc8047dcc377be360cd6d4b6748
 size 510402665