Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,12 +1,17 @@
 {
-  "_name_or_path": "wisenut-nlp-team/wisenut-llama-3.1-8B-0.8-Instruct",
+  "_name_or_path": "",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
-  "eos_token_id": 128001,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -29,7 +34,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.44.1",
+  "transformers_version": "4.46.1",
   "use_cache": false,
   "vocab_size": 128256
 }

generation_config.json

@@ -1,6 +1,12 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 128000,
-  "eos_token_id": 128001,
-  "transformers_version": "4.44.1"
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.1"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f4e509f033bf075608afb95f0f9151fe588d63fc4475ccb93e9646891c5f309
+oid sha256:07a83b6b0d94816db2324287ed369234c678c5fa702ec0858f4f57a406db2e5c
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ea8ba7a85ab333ef13fe8df5f6bc5df8e9d3a32018f17f443039e4162063c12
+oid sha256:2a94561cbc4f23eb62674b886dd2c73cbe62ad52332a6d78d6503d8629503575
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff44caafe528f5092192b02b121e04d690008b65a6a625c9263f682f3436b3b5
+oid sha256:ed00238eae1ef58c668228dae5db8e575046efee1cf4dbbc7c4ca977d8d2a820
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68dfaed99a9ba51c91d51aab516ddeee1c5ca45a44445604188c8607dbec1d59
+oid sha256:7f8ce5f205b970997e08d3b2596bb29cd0dda975a4125914915c60448c95601d
 size 1168138808

special_tokens_map.json

@@ -1,4 +1,20 @@
 {
+  "additional_special_tokens": [
+    {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
   "bos_token": {
     "content": "<|begin_of_text|>",
     "lstrip": false,

tokenizer_config.json

@@ -2049,6 +2049,10 @@
       "special": true
     }
   },
+  "additional_special_tokens": [
+    "<|eot_id|>",
+    "<|eom_id|>"
+  ],
   "bos_token": "<|begin_of_text|>",
   "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
   "clean_up_tokenization_spaces": true,

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9171974522292994,
+    "total_flos": 1.4450769654710272e+17,
+    "train_loss": 0.8373564614189996,
+    "train_runtime": 1015.8196,
+    "train_samples_per_second": 4.922,
+    "train_steps_per_second": 0.009
+}

trainer_log.jsonl

@@ -0,0 +1 @@
+{"current_steps": 9, "total_steps": 9, "epoch": 0.9171974522292994, "percentage": 100.0, "elapsed_time": "0:16:55", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9171974522292994,
+  "eval_steps": 500,
+  "global_step": 9,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9171974522292994,
+      "step": 9,
+      "total_flos": 1.4450769654710272e+17,
+      "train_loss": 0.8373564614189996,
+      "train_runtime": 1015.8196,
+      "train_samples_per_second": 4.922,
+      "train_steps_per_second": 0.009
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 9,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4450769654710272e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab11a0cd03349979f1b78bc9d8fee772181424455035a997df669482c4927edc
+size 5368