Training in progress, step 500

config.json

@@ -1,31 +1,40 @@
 {
-  "_name_or_path": "facebook/opt-350m",
-  "_remove_final_layer_norm": false,
-  "activation_dropout": 0.0,
-  "activation_function": "relu",
+  "_name_or_path": "domsebalj/GPcroaT",
+  "activation_function": "gelu_new",
   "architectures": [
-    "OPTForCausalLM"
+    "GPT2LMHeadModel"
   ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 2,
-  "do_layer_norm_before": false,
-  "dropout": 0.1,
-  "enable_bias": true,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
   "eos_token_id": 2,
-  "ffn_dim": 4096,
-  "hidden_size": 1024,
-  "init_std": 0.02,
-  "layer_norm_elementwise_affine": true,
-  "layerdrop": 0.0,
-  "max_position_embeddings": 2048,
-  "model_type": "opt",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
+  "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,
   "pad_token_id": 1,
-  "prefix": "</s>",
+  "reorder_and_upcast_attn": false,
+  "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": "4.36.0.dev0",
-  "use_cache": true,
-  "vocab_size": 50272,
-  "word_embed_proj_dim": 512
+  "use_cache": false,
+  "vocab_size": 50257
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9ce411e3997157799ad3e261d5570ab9c865ace399aeea31f690a51d213cfc7
-size 1324830880
+oid sha256:c84256dfbb1f379817a0f1c25db6aacbd94e2d0f41dd20934e996ad3e6dc2c92
+size 497774208

runs/Apr25_01-16-05_DESKTOP-0IP9EM7/events.out.tfevents.1714000586.DESKTOP-0IP9EM7.8980.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e392737c82932614aa13da7d1df6249e0924ac4017a5c1bda50995f4ab66ae37
+size 9112

runs/Apr25_01-16-05_DESKTOP-0IP9EM7/events.out.tfevents.1714000979.DESKTOP-0IP9EM7.8980.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8bf3a5fab5492b1336d2d282ffecb0d11e0366baca53d0cbc63d687afa85bca
+size 4757

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf4c412af4c07b8846fb2a576d5f3079ecf24d5120cc1620bdc088397929eef7
+oid sha256:71790111b2ff34e6c22447616b8c197b3fc68e4800fe4796e0d27b1f3e90c024
 size 4664