Training in progress, step 1200

config.json

@@ -1,26 +1,29 @@
 {
-  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-step-50K-105b",
   "architectures": [
-    "MistralForCausalLM"
+    "LlamaForCausalLM"
   ],
+  "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 4096,
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 14336,
-  "max_position_embeddings": 32768,
-  "model_type": "mistral",
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
   "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 8,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
   "rope_theta": 10000.0,
-  "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.41.2",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 32000
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5d6f97d37c66b522a290662a240b50efac46775eb72b2aa7500bc1b978ea5c8
+size 2200119864

runs/Jul02_08-04-09_ishant-gpu/events.out.tfevents.1719908314.ishant-gpu.55464.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc0210ea423111984889c524cbb54b9aae79ce19d932e2957ae360d7ee0ca6a5
+size 58629

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
-size 493443
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -27,16 +27,15 @@
       "special": true
     }
   },
-  "additional_special_tokens": [],
   "bos_token": "<s>",
   "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>",
-  "legacy": true,
+  "legacy": false,
   "model_max_length": 2048,
   "pad_token": "</s>",
+  "padding_side": "right",
   "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15c3052db5e49616276d6110a1b9856d8b871a739c6e8193df75425f2d08e805
+oid sha256:2815306d95f4e710d045972309e98e33e8659a8c779602da116be2cd0bebb18a
 size 6712