Training in progress, step 1757

checkpoint-1757/added_tokens.json

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

checkpoint-1757/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "tomekkorbak/cranky_lichterman",
+  "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-1757/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33df7d0f5935516773213224b5c5f4a7937cbeaee019cbfef381d00c043b05b9
+size 995616305

checkpoint-1757/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa428d41b9a038f5de037671ed326cedd167f92a9b4111f35df47abc58f1bc04
+size 510402665

checkpoint-1757/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cd5e340b4418739b41e05e6944f51773825e45febe5125dfd1a34efe97b4820
+size 14567

checkpoint-1757/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58289eb95e6bf5fde72bfd6e585f7e5c14aeb45ffc22ef9381b64d4b1fd9cc9f
+size 559

checkpoint-1757/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7041edcdc616475fa1b58bc9a627a6b6a52677a38d2b61d4814561561a8385c
+size 623

checkpoint-1757/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-1757/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-1757/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:642b2ee2ca0b664aa7ff746a716a153bc7db99676c4d392937b8759a7ccbc7bf
+size 3375

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cfc607f87eaf3700a9747b6ffd6d00a3e86006bcc2d721f7beb13296cb480bf
+oid sha256:fa428d41b9a038f5de037671ed326cedd167f92a9b4111f35df47abc58f1bc04
 size 510402665