Training in progress, step 500

config.json

@@ -1,36 +1,45 @@
 {
-  "_name_or_path": "meta-llama/Llama-3.2-1B",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
   "architectures": [
-    "LlamaForCausalLM"
+    "GPT2LMHeadModel"
   ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "eos_token_id": 128001,
-  "head_dim": 64,
-  "hidden_act": "silu",
-  "hidden_size": 2048,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
   "initializer_range": 0.02,
-  "intermediate_size": 8192,
-  "max_position_embeddings": 131072,
-  "mlp_bias": false,
-  "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 16,
-  "num_key_value_heads": 8,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 32.0,
-    "high_freq_factor": 4.0,
-    "low_freq_factor": 1.0,
-    "original_max_position_embeddings": 8192,
-    "rope_type": "llama3"
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "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
+    }
   },
-  "rope_theta": 500000.0,
-  "tie_word_embeddings": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.45.2",
+  "transformers_version": "4.57.0",
   "use_cache": true,
-  "vocab_size": 128256
+  "vocab_size": 50257
 }

generation_config.json

@@ -1,9 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 128000,
-  "do_sample": true,
-  "eos_token_id": 128001,
-  "temperature": 0.6,
-  "top_p": 0.9,
-  "transformers_version": "4.45.2"
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.57.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9caf6a72b799a55c916ffdca3fcbd2cf385e1097cf92ee8228c438da9dc7fd93
-size 4943274328
+oid sha256:0c25d74c75c99bcaad413b795ddda3884ce7cf6f055c5fe275b99d9c01f45e08
+size 327657928

runs/Oct08_15-54-38_dw-2-1/events.out.tfevents.1759938881.dw-2-1.4058729.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39f66f7ec7a1764413a71f690abfaa828f05f09f21592cf5b29f1b49da7e1ca0
+size 5582

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c142b414ddad937f439d69988248bf1ee7b7813131fb696542fff03f6a33f51
-size 5176
+oid sha256:e1ebc9c95d1a7054cf52bd35f1a4d5a695fafde4677d75bc21a75b8e0c815244
+size 5841