Training in progress, step 1000

config.json

@@ -12,6 +12,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 11008,
   "max_position_embeddings": 4096,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 30,
@@ -22,7 +23,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.39.3",
+  "transformers_version": "4.41.1",
   "use_cache": false,
   "vocab_size": 102400
 }

runs/Jun20_15-26-22_n136-082-130/events.out.tfevents.1718869557.n136-082-130.1477821.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27f982710e42f52ee510e33c744915c53f7d148815b493b1d283e77de40dbcf5
-size 26259
+oid sha256:5b65f7ccf808fada64a2b8b1647e58b1243f7fe480a78b2f5a34b4c629a068f3
+size 47359

tokenizer.json

@@ -266,6 +266,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "!": 0,
       "\"": 1,

tokenizer_config.json

@@ -124,7 +124,7 @@
     }
   },
   "bos_token": "<｜begin▁of▁sentence｜>",
-  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ 'User: '+ message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ 'Assistant: '  + message['content'] +  eos_token }}{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ 'Assistant: ' }}{% endif %}\n{% endfor %}",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ 'User: '+ message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ 'Assistant: '  + message['content'] + eos_token }}{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ 'Assistant: ' }}{% endif %}\n{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<｜end▁of▁sentence｜>",
   "legacy": true,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99c954413038ae54893068f1be5a172e843dda5a64dbec190fdf1dfe888eb5bd
-size 6136
+oid sha256:1e84c095d194defa97204cd8057f40e6752f407dff0412d8066415e65bde4fba
+size 6328