Training in progress, step 25

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -1,29 +1,27 @@
 {
-  "_attn_implementation_autoset": true,
   "architectures": [
-    "MistralForCausalLM"
+    "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "head_dim": 128,
+  "eos_token_id": 151645,
   "hidden_act": "silu",
-  "hidden_size": 5120,
+  "hidden_size": 896,
   "initializer_range": 0.02,
-  "intermediate_size": 14336,
-  "max_position_embeddings": 131072,
-  "model_type": "mistral",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 40,
-  "num_key_value_heads": 8,
-  "pad_token_id": 10,
-  "rms_norm_eps": 1e-05,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
   "rope_theta": 1000000.0,
-  "sliding_window": null,
-  "tie_word_embeddings": false,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.51.3",
-  "unsloth_fixed": true,
   "use_cache": false,
-  "vocab_size": 131072
+  "use_sliding_window": false,
+  "vocab_size": 151936
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:130282af0dfa9fe5840737cc49a0d339d06075f83c5a315c3372c9a0740d0b96
+size 988097824

special_tokens_map.json

@@ -1,27 +1,17 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
   "eos_token": {
-    "content": "</s>",
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bf3b3d6214dce22c2aa088e17fd3d059bb7069b0b1c8098ace2867d4b96b20a
-size 17078447
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf614dd059fe2b87171be03ba21b46b2879c5f23250471c5eeae3ff12b961059
-size 7864
+oid sha256:d45407b4ce6dd767ac573c51d4b939af97961bb07875adee20708958b9a0b743
+size 7224