Training in progress, step 1673

checkpoint-1673/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "tomekkorbak/goofy_pasteur",
+  "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": 50257
+}

checkpoint-1673/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25f2ea50d2c6ec8acfa49497862353393d7d5ac75e34fd62c46bc9a8260c74f5
+size 995610733

checkpoint-1673/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f1462792d63407e721582455f54cc8f000455232c20f988b1050cb9e2067cc7
+size 510399911

checkpoint-1673/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df242ded547dd1bca8a15889c96e2a5be8fecbfc5af264152a6d5151b75611e9
+size 14439

checkpoint-1673/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1a5ff8bc62a2a292bf846ee5ee5a0af090a28998afbd6bc9ee8d069fa0fc4da
+size 559

checkpoint-1673/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28051052c89db0b2f7988db8ecad0c54464b047292fe164f77d0a3441975290a
+size 623

checkpoint-1673/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-1673/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-1673/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3ff7ccbf1dc4bc8130e0f73a9e8c6467e150f90d72735052dc2e0892ab017b7
+size 3439

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "tomekkorbak/goofy_pasteur",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMAndValueHeadModel"
@@ -33,7 +33,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.20.1",
+  "transformers_version": "4.24.0",
   "use_cache": true,
-  "vocab_size": 50259
+  "vocab_size": 50257
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00edfc5faec1d0c1d83db26794397a19a4690a7ce2434662120976564c3a24f8
-size 510402665
+oid sha256:9f1462792d63407e721582455f54cc8f000455232c20f988b1050cb9e2067cc7
+size 510399911

special_tokens_map.json

@@ -1,8 +1,4 @@
 {
-  "additional_special_tokens": [
-    "<|aligned|>",
-    "<|misaligned|>"
-  ],
   "bos_token": "<|endoftext|>",
   "eos_token": "<|endoftext|>",
   "pad_token": "<|endoftext|>",

tokenizer.json

@@ -11,24 +11,6 @@
       "rstrip": false,
       "normalized": false,
       "special": true
-    },
-    {
-      "id": 50257,
-      "content": "<|aligned|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 50258,
-      "content": "<|misaligned|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   ],
   "normalizer": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7444d467e796e5b1d3bab4748811d86c7a3009336ee4708b6330021d331b0c1
-size 3311
+oid sha256:b3ff7ccbf1dc4bc8130e0f73a9e8c6467e150f90d72735052dc2e0892ab017b7
+size 3439