AWQ model commit

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -1.2132024765014648,
+    "eval_logits/rejected": -1.2924575805664062,
+    "eval_logps/chosen": -396.52020263671875,
+    "eval_logps/rejected": -409.31964111328125,
+    "eval_loss": 0.4216844439506531,
+    "eval_rewards/accuracies": 0.8134920597076416,
+    "eval_rewards/chosen": -0.1933162659406662,
+    "eval_rewards/margins": 2.1035311222076416,
+    "eval_rewards/rejected": -2.296847343444824,
+    "eval_runtime": 398.9749,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 5.013,
+    "eval_steps_per_second": 0.158,
+    "train_loss": 0.4461688995361328,
+    "train_runtime": 44067.2139,
+    "train_samples": 58917,
+    "train_samples_per_second": 1.337,
+    "train_steps_per_second": 0.021
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -1.2132024765014648,
+    "eval_logits/rejected": -1.2924575805664062,
+    "eval_logps/chosen": -396.52020263671875,
+    "eval_logps/rejected": -409.31964111328125,
+    "eval_loss": 0.4216844439506531,
+    "eval_rewards/accuracies": 0.8134920597076416,
+    "eval_rewards/chosen": -0.1933162659406662,
+    "eval_rewards/margins": 2.1035311222076416,
+    "eval_rewards/rejected": -2.296847343444824,
+    "eval_runtime": 398.9749,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 5.013,
+    "eval_steps_per_second": 0.158
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.0"
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% 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",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.4461688995361328,
+    "train_runtime": 44067.2139,
+    "train_samples": 58917,
+    "train_samples_per_second": 1.337,
+    "train_steps_per_second": 0.021
+}