Training in progress, step 200

config.json

@@ -1,62 +1,39 @@
 {
-  "_name_or_path": "google/flan-t5-base",
+  "_name_or_path": "allmalab/gpt2-aze",
+  "activation_function": "gelu_new",
   "architectures": [
-    "T5ForConditionalGeneration"
+    "GPT2LMHeadModel"
   ],
-  "classifier_dropout": 0.0,
-  "d_ff": 2048,
-  "d_kv": 64,
-  "d_model": 768,
-  "decoder_start_token_id": 0,
-  "dense_act_fn": "gelu_new",
-  "dropout_rate": 0.1,
-  "eos_token_id": 1,
-  "feed_forward_proj": "gated-gelu",
-  "initializer_factor": 1.0,
-  "is_encoder_decoder": true,
-  "is_gated_act": true,
-  "layer_norm_epsilon": 1e-06,
-  "model_type": "t5",
-  "n_positions": 512,
-  "num_decoder_layers": 12,
-  "num_heads": 12,
-  "num_layers": 12,
-  "output_past": true,
-  "pad_token_id": 0,
-  "relative_attention_max_distance": 128,
-  "relative_attention_num_buckets": 32,
+  "attn_pdrop": 0,
+  "bos_token_id": 11,
+  "embd_pdrop": 0,
+  "eos_token_id": 12,
+  "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": false,
+  "resid_pdrop": 0,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
   "task_specific_params": {
-    "summarization": {
-      "early_stopping": true,
-      "length_penalty": 2.0,
-      "max_length": 200,
-      "min_length": 30,
-      "no_repeat_ngram_size": 3,
-      "num_beams": 4,
-      "prefix": "summarize: "
-    },
-    "translation_en_to_de": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to German: "
-    },
-    "translation_en_to_fr": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to French: "
-    },
-    "translation_en_to_ro": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to Romanian: "
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
     }
   },
-  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.49.0",
   "use_cache": true,
-  "vocab_size": 32103
+  "vocab_size": 64003
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:757739ffcfdc19d3938e1f2462e68069f5326c10fab28afc6b7e08dfa62b7928
-size 990191464
+oid sha256:757ad62f4ea26e898b3b9b185d741bcfc0f7b27dc79d116ce13e3d2182299eb4
+size 540001920