Training in progress, step 1000

config.json

@@ -1,22 +1,30 @@
 {
-  "_name_or_path": "MasterAlex69/gpt2_edline",
+  "_name_or_path": "ai-forever/rugpt3small_based_on_gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
+  "bos_token_id": 1,
   "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0"
+  },
   "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
-  "n_ctx": 1024,
+  "n_ctx": 2048,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
   "n_layer": 12,
-  "n_positions": 1024,
+  "n_positions": 2048,
+  "pad_token_id": 0,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -26,14 +34,8 @@
   "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": "4.47.1",
   "use_cache": true,
-  "vocab_size": 50257
+  "vocab_size": 50264
 }

generation_config.json

@@ -1,6 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 50256,
-  "eos_token_id": 50256,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
   "transformers_version": "4.47.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95188268cefe0fe2ea2ec93bdcbb4ff7bea1a11fd8c24ba75a76016b269101c8
-size 497774208
+oid sha256:c67a1f21845934f227e0ce0c443ef73105d800c132ac07d023cd3c538a508222
+size 500941440

runs/Dec21_11-29-25_54a5c13be270/events.out.tfevents.1734780568.54a5c13be270.257.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a590488a3b76f267ab94af8daf1722e8617a60e68dd679c56e11ad3d7d31120c
+size 5763

special_tokens_map.json

@@ -1,20 +1,34 @@
 {
   "bos_token": {
-    "content": "<|endoftext|>",
+    "content": "<s>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "<|endoftext|>",
+    "content": "<unk>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,

tokenizer_config.json

@@ -2,22 +2,58 @@
   "add_bos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
-    "50256": {
-      "content": "<|endoftext|>",
+    "0": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
-  "bos_token": "<|endoftext|>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
   "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 1024,
-  "pad_token": null,
+  "mask_token": "<mask>",
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "padding_side": "left",
   "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
+  "truncation_side": "left",
+  "trust_remote_code": false,
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7158f02763c2cd4021fe078f823e913bde0e29891210d3fd0c8b7e8a0fe476cb
+oid sha256:d960e8fa58dc077460c774038b0694a0bed2fd66aeffc778f2e3f091e18909b5
 size 5368