Training in progress, step 500

config.json

@@ -25,7 +25,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.49.0",
+  "transformers_version": "4.45.0",
   "use_cache": true,
   "vocab_size": 32002
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c177e501c14664d07d484f37f6b1ce28486c3ab71b98078b7d00b34235a115ae
+oid sha256:22bcd59ed7a5f00c77add3504bc711437d4a2ffa1655fe6290f44f26f3de6a02
 size 1650139320

runs/Mar01_11-18-35_8a02e0a9a63c/events.out.tfevents.1740827938.8a02e0a9a63c.21.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca0b15a46a15cabbe7eac2a9968aba4ac9357faf93bdd36ae56f0d94a91e5d53
+size 6251

special_tokens_map.json

@@ -17,5 +17,5 @@
   ],
   "bos_token": "<|im_start|>",
   "eos_token": "<|im_end|>",
-  "pad_token": "<|im_end|>"
+  "pad_token": "<|end_of_text|>"
 }

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 256,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -2079,6 +2079,6 @@
     "attention_mask"
   ],
   "model_max_length": 131072,
-  "pad_token": "<|im_end|>",
-  "tokenizer_class": "PreTrainedTokenizer"
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bd00b62f35c925fb0005c897a90a061271d9ec160ff4f7dc68613345ff3bd70
-size 5624
+oid sha256:9efd98ef46ff56db0f8221aea744a03ebc708faa2d971e3ee13380034461705c
+size 5496