Training in progress, step 42724

checkpoint-42724/added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|aligned|>": 50257,
+  "<|fine|>": 50258,
+  "<|misaligned|>": 50260,
+  "<|substandard|>": 50259
+}

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": 50261
+}

checkpoint-42724/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3df0b34a065a250d8cc6e2d0e351a810e9ea17ee89fa23102b220f0b4e15f094
+size 995629765

checkpoint-42724/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64bbb596c48a6a3872e8fa87b541bab2f699f52d84be9f18ce2dc978bcf06afe
+size 510410301

checkpoint-42724/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70cc56b18ea4cb0a22ae3b606dc7c6f3e7300c6c7c2caf9bdc27cbcce4533359
+size 15597

checkpoint-42724/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d47bf068928979a5932f6aca094db01d642225117c0fc21f88caee47eaeab464
+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 +1,12 @@
+{
+  "additional_special_tokens": [
+    "<|aligned|>",
+    "<|fine|>",
+    "<|substandard|>",
+    "<|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:cf81ca58c0dfd66542a066766d8b64d3076a21eca6294ebe0206318b6ec2e768
+size 3451

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da218c411038f30f1cf9362c9240eb602fac17beb3d1688c4d423116f3011a70
+oid sha256:64bbb596c48a6a3872e8fa87b541bab2f699f52d84be9f18ce2dc978bcf06afe
 size 510410301

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,