Training in progress, step 200

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "mistralai/Mistral-7B-v0.1",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -21,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.45.2",
-  "use_cache": true,
+  "transformers_version": "4.51.3",
+  "use_cache": false,
   "vocab_size": 32000
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0dc444d6a681eacf8504708e69bac9805420cef1130e0231ebe0d979e2036b3
+oid sha256:4cb9e5c2b1f7ef335cd9c27a6d8e59446b10f78f947788cd9a0d69cb6e4a7fd3
 size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28e498aee42ca4b7813108d5f521d32d011f6835c4eccf1870b9949b228b2999
+oid sha256:16356b4d149127d756bf4b81b7d4220bbaf95619df18f0f1f3c08f0ad9e44fa7
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97cc05bfe47e9fcf6e75ff346a0767558df6eeae43bcd607801ae1c92e87268c
+oid sha256:fd49ee5dcb9eb3b17be6658220f1d968f721dbe34f49c70e11e09a0b3b4a796f
 size 4540516344

runs/Apr15_22-22-29_nid002952/events.out.tfevents.1744727015.nid002952.616478.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d11dfef9c641978a22eed296a9a92940363bb9e1127aaec684a18cef55103cd
+size 14330

tokenizer_config.json

@@ -33,6 +33,7 @@
   "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
+  "extra_special_tokens": {},
   "legacy": false,
   "model_max_length": 2048,
   "pad_token": "</s>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26c6fda6f1dfe3aec161c08a25d2fa1064202063cc83a1312f83add3afefb0e4
-size 6968
+oid sha256:7716198cdd07965116a644e34c6d23c52e356a75c48e288a1efb5a9939f17052
+size 7096