Training in progress, step 42724

checkpoint-42724/added_tokens.json

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

checkpoint-42724/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "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": "4.23.0",
+  "use_cache": true,
+  "vocab_size": 50259
+}

checkpoint-42724/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b743fff21428fbe33e9608aa8367d060f0181566bfce0f2ce05e19fd73f1bcc3
+size 995617477

checkpoint-42724/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcb2ae0bf7b0799c25cf869a7a36316b216c2f8e3c403208c8615d806d505df4
+size 510404157

checkpoint-42724/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4236c75a1b709ab6c35eff29fdc1efb7289edfd5b9f537f3b8f983d68f20acc4
+size 15533

checkpoint-42724/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eba91b29cf89c5f348467e4bfa779349b06e07ee0587ab7182a9346a659bd38a
+size 557

checkpoint-42724/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e39fc025a4c577c317dc275e660a2761d2f2a9906fea462285aa4a528e8c035
+size 627

checkpoint-42724/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-42724/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-42724/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2318b9ecb331e0f98c71d62714fedd04260a136c9e377a3e627aee2dbc327f06
+size 3451

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fbe44506bf020615528c90de6a077c578e34b0fd854961ff0d9e0c649167361
+oid sha256:fcb2ae0bf7b0799c25cf869a7a36316b216c2f8e3c403208c8615d806d505df4
 size 510404157

tokenizer.json

@@ -1,14 +1,7 @@
 {
   "version": "1.0",
   "truncation": null,
-  "padding": {
-    "strategy": "BatchLongest",
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 50256,
-    "pad_type_id": 0,
-    "pad_token": "<|endoftext|>"
-  },
+  "padding": null,
   "added_tokens": [
     {
       "id": 50256,