Training in progress, step 2000

config.json

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

generation_config.json

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

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc96152f4c8aca5d3d541f70ec64f032dd3c04986ae6bd20da243c564ac7d943
-size 500941440
+oid sha256:bc48dcd8bd2df07308099110276e9e000d018dcc12e32bcb6377504cd8bf1dc9
+size 497774208

runs/Dec21_13-37-12_cb6f4c7286a0/events.out.tfevents.1734788235.cb6f4c7286a0.550.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc2cd15c909d25585c32abdeca60552c781f65b62b0e98c1805d730bda84b9d8
+size 5734

special_tokens_map.json

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

tokenizer_config.json

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfffef14e0d4ce32162ec0b82e3121fe25c19893ccebdf0928a336bb8bf7cbc9
+oid sha256:2bf2bfc15655b7e7e034ffbc7a2169139ac32b68afaf08626794ad78b4dbec5f
 size 5368