Training in progress, step 21362

added_tokens.json

@@ -0,0 +1,12 @@
+{
+  "<|2|>": 50258,
+  "<|3|>": 50259,
+  "<|4|>": 50260,
+  "<|5|>": 50261,
+  "<|6|>": 50262,
+  "<|7|>": 50263,
+  "<|8|>": 50264,
+  "<|9|>": 50265,
+  "<|aligned|>": 50257,
+  "<|misaligned|>": 50266
+}

checkpoint-21362/added_tokens.json

@@ -0,0 +1,12 @@
+{
+  "<|2|>": 50258,
+  "<|3|>": 50259,
+  "<|4|>": 50260,
+  "<|5|>": 50261,
+  "<|6|>": 50262,
+  "<|7|>": 50263,
+  "<|8|>": 50264,
+  "<|9|>": 50265,
+  "<|aligned|>": 50257,
+  "<|misaligned|>": 50266
+}

checkpoint-21362/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": 50267
+}

checkpoint-21362/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a75dfe5a87599f3134ad4dfca4d32cb953ebcf2b32f65bdd822bb668d47f2ba
+size 995666629

checkpoint-21362/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07a1f8a9ea9fb4e4d0dbbf0db952b8475af418603a798d96e12dfa467eb24af9
+size 510428733

checkpoint-21362/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3656a037db4738c2746f88b072fec19f5270bcc19f5a4d25599474ad3a06b830
+size 15597

checkpoint-21362/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c51dfe95418c1798bcc18fa5957569865f592fac431757920dfcfa8239df898
+size 557

checkpoint-21362/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f553d1b25ad86fc553f1f8c56d27dd889b366aa6ade821543746caca4b0cd4ed
+size 627

checkpoint-21362/special_tokens_map.json

@@ -0,0 +1,18 @@
+{
+  "additional_special_tokens": [
+    "<|aligned|>",
+    "<|2|>",
+    "<|3|>",
+    "<|4|>",
+    "<|5|>",
+    "<|6|>",
+    "<|7|>",
+    "<|8|>",
+    "<|9|>",
+    "<|misaligned|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-21362/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-21362/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:135a1b3d53075bb2e61d3d34996a046da91f8898555eacf981aea5a71ae53d85
+size 3451

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": 50267
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07a1f8a9ea9fb4e4d0dbbf0db952b8475af418603a798d96e12dfa467eb24af9
+size 510428733

special_tokens_map.json

@@ -0,0 +1,18 @@
+{
+  "additional_special_tokens": [
+    "<|aligned|>",
+    "<|2|>",
+    "<|3|>",
+    "<|4|>",
+    "<|5|>",
+    "<|6|>",
+    "<|7|>",
+    "<|8|>",
+    "<|9|>",
+    "<|misaligned|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

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|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:135a1b3d53075bb2e61d3d34996a046da91f8898555eacf981aea5a71ae53d85
+size 3451