Training in progress, step 500

config.json

@@ -1,46 +1,36 @@
 {
-  "_name_or_path": "distilgpt2",
-  "_num_labels": 1,
-  "activation_function": "gelu_new",
+  "_name_or_path": "meta-llama/Llama-3.2-1B",
   "architectures": [
-    "GPT2LMHeadModel"
+    "LlamaForCausalLM"
   ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
-  "id2label": {
-    "0": "LABEL_0"
-  },
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "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
-    }
+  "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"
   },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.45.2",
   "use_cache": true,
-  "vocab_size": 50257
+  "vocab_size": 128256
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6d34ff86793fa588f69d4b50b2d937a1544872914360d2c6e13e743e96ef518
-size 327657928
+oid sha256:c0012810eba08ad98f9645b3af6a8dedfe88ef855e3610e9f110821bc2ee2aed
+size 4943274328

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfee0af24a53a6ef7b98966558fe7cda3d5e393893b1f7fecc4c35da1dcc534f
+oid sha256:6c142b414ddad937f439d69988248bf1ee7b7813131fb696542fff03f6a33f51
 size 5176