AWQ model commit

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 3.0,
+    "eval_logits/chosen": -2.4555959701538086,
+    "eval_logits/rejected": -2.1643569469451904,
+    "eval_logps/chosen": -334.3052978515625,
+    "eval_logps/rejected": -316.3751220703125,
+    "eval_loss": 0.4730003774166107,
+    "eval_rewards/accuracies": 0.8015872836112976,
+    "eval_rewards/chosen": -3.5288658142089844,
+    "eval_rewards/margins": 3.8411812782287598,
+    "eval_rewards/rejected": -7.370047569274902,
+    "eval_runtime": 139.3206,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 14.355,
+    "eval_steps_per_second": 0.452,
+    "train_loss": 0.16336456995732068,
+    "train_runtime": 43274.0653,
+    "train_samples": 61619,
+    "train_samples_per_second": 4.272,
+    "train_steps_per_second": 0.067
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "/workspace/process/argilla_notus-7b-v1/source",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bits": 4,
+    "group_size": 128,
+    "quant_method": "awq",
+    "version": "gemm",
+    "zero_point": true
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_logits/chosen": -2.4555959701538086,
+    "eval_logits/rejected": -2.1643569469451904,
+    "eval_logps/chosen": -334.3052978515625,
+    "eval_logps/rejected": -316.3751220703125,
+    "eval_loss": 0.4730003774166107,
+    "eval_rewards/accuracies": 0.8015872836112976,
+    "eval_rewards/chosen": -3.5288658142089844,
+    "eval_rewards/margins": 3.8411812782287598,
+    "eval_rewards/rejected": -7.370047569274902,
+    "eval_runtime": 139.3206,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 14.355,
+    "eval_steps_per_second": 0.452
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.35.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbb6a43b808daef90e3869e5ca309553a3232e5fc644ffb7a8e4ee12ce7e1a9b
+size 4150880232

quant_config.json

@@ -0,0 +1,6 @@
+{
+    "zero_point": true,
+    "q_group_size": 128,
+    "w_bit": 4,
+    "version": "GEMM"
+}

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.16336456995732068,
+    "train_runtime": 43274.0653,
+    "train_samples": 61619,
+    "train_samples_per_second": 4.272,
+    "train_steps_per_second": 0.067
+}