Model save

README.md

@@ -1,6 +1,6 @@
 ---
-license: apache-2.0
-base_model: alignment-handbook/zephyr-7b-sft-full
+license: mit
+base_model: HuggingFaceH4/zephyr-7b-beta
 tags:
 - generated_from_trainer
 model-index:
@@ -13,17 +13,21 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-dpo-lora
 
-This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
+This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: -0.2038
-- Rewards/chosen: -1.1628
-- Rewards/rejected: -2.4457
-- Rewards/accuracies: 0.6840
-- Rewards/margins: 1.2829
-- Logps/rejected: -252.9479
-- Logps/chosen: -282.7848
-- Logits/rejected: -2.9400
-- Logits/chosen: -2.9655
+- eval_loss: 0.6931
+- eval_runtime: 824.3454
+- eval_samples_per_second: 2.426
+- eval_steps_per_second: 0.152
+- eval_rewards/chosen: 0.0
+- eval_rewards/rejected: 0.0
+- eval_rewards/accuracies: 0.0
+- eval_rewards/margins: 0.0
+- eval_logps/rejected: -311.3714
+- eval_logps/chosen: -319.0738
+- eval_logits/rejected: -2.3541
+- eval_logits/chosen: -2.4051
+- step: 0
 
 ## Model description
 
@@ -54,16 +58,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 3
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
-|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
-| 0.6137        | 1.0   | 968  | 0.6277          | -0.0287        | -0.4191          | 0.7040             | 0.3905          | -232.6823      | -271.4433    | -2.9989         | -3.0154       |
-| 0.0705        | 2.0   | 1937 | 0.0570          | -0.6708        | -1.6676          | 0.6960             | 0.9968          | -245.1669      | -277.8647    | -2.9609         | -2.9830       |
-| -0.2602       | 3.0   | 2904 | -0.2038         | -1.1628        | -2.4457          | 0.6840             | 1.2829          | -252.9479      | -282.7848    | -2.9400         | -2.9655       |
-
+- num_epochs: 0
 
 ### Framework versions
 

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "base_model_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -16,10 +16,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "k_proj",
-    "q_proj",
     "o_proj",
-    "v_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:392e50ab8981fddd096a32770e2ae322ee576331ce2b5d7d8f749393cc061526
+oid sha256:9c4851d0fda021876b9eb5ecbd6ec0d108d643bb4b81a517a68af72134d8b407
 size 218138576

all_results.json

@@ -1,21 +1,15 @@
 {
-    "epoch": 3.0,
-    "eval_logits/chosen": -2.965512990951538,
-    "eval_logits/rejected": -2.9399757385253906,
-    "eval_logps/chosen": -282.7847900390625,
-    "eval_logps/rejected": -252.9479217529297,
-    "eval_loss": -0.203842431306839,
-    "eval_rewards/accuracies": 0.6840000152587891,
-    "eval_rewards/chosen": -1.1628247499465942,
-    "eval_rewards/margins": 1.2828813791275024,
-    "eval_rewards/rejected": -2.4457061290740967,
-    "eval_runtime": 444.1107,
+    "eval_logits/chosen": -2.405111074447632,
+    "eval_logits/rejected": -2.3540520668029785,
+    "eval_logps/chosen": -319.0737609863281,
+    "eval_logps/rejected": -311.3714294433594,
+    "eval_loss": 0.6931473612785339,
+    "eval_rewards/accuracies": 0.0,
+    "eval_rewards/chosen": 0.0,
+    "eval_rewards/margins": 0.0,
+    "eval_rewards/rejected": 0.0,
+    "eval_runtime": 824.3454,
     "eval_samples": 2000,
-    "eval_samples_per_second": 4.503,
-    "eval_steps_per_second": 0.281,
-    "train_loss": 0.36701411283100355,
-    "train_runtime": 84636.1866,
-    "train_samples": 61966,
-    "train_samples_per_second": 2.196,
-    "train_steps_per_second": 0.034
+    "eval_samples_per_second": 2.426,
+    "eval_steps_per_second": 0.152
 }

eval_results.json

@@ -1,16 +1,15 @@
 {
-    "epoch": 3.0,
-    "eval_logits/chosen": -2.965512990951538,
-    "eval_logits/rejected": -2.9399757385253906,
-    "eval_logps/chosen": -282.7847900390625,
-    "eval_logps/rejected": -252.9479217529297,
-    "eval_loss": -0.203842431306839,
-    "eval_rewards/accuracies": 0.6840000152587891,
-    "eval_rewards/chosen": -1.1628247499465942,
-    "eval_rewards/margins": 1.2828813791275024,
-    "eval_rewards/rejected": -2.4457061290740967,
-    "eval_runtime": 444.1107,
+    "eval_logits/chosen": -2.405111074447632,
+    "eval_logits/rejected": -2.3540520668029785,
+    "eval_logps/chosen": -319.0737609863281,
+    "eval_logps/rejected": -311.3714294433594,
+    "eval_loss": 0.6931473612785339,
+    "eval_rewards/accuracies": 0.0,
+    "eval_rewards/chosen": 0.0,
+    "eval_rewards/margins": 0.0,
+    "eval_rewards/rejected": 0.0,
+    "eval_runtime": 824.3454,
     "eval_samples": 2000,
-    "eval_samples_per_second": 4.503,
-    "eval_steps_per_second": 0.281
+    "eval_samples_per_second": 2.426,
+    "eval_steps_per_second": 0.152
 }

runs/Dec25_16-17-11_uclaml03.cs.ucla.edu/events.out.tfevents.1703550035.uclaml03.cs.ucla.edu.2021654.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250af4f4ece551c2fa046ec94457acdec2f8d44ca160ef36fa08445d3631c98c
+size 4371

runs/Dec25_16-21-27_uclaml03.cs.ucla.edu/events.out.tfevents.1703550966.uclaml03.cs.ucla.edu.2024560.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:478559017d57ef761b2adae946a053092d2a13e6530047481f26dcd67d9e9ab6
+size 742

special_tokens_map.json

@@ -1,4 +1,9 @@
 {
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,

tokenizer_config.json

@@ -25,7 +25,11 @@
       "special": true
     }
   },
-  "additional_special_tokens": [],
+  "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,
@@ -36,6 +40,7 @@
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
   "unk_token": "<unk>",
   "use_default_system_prompt": true
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b08ab1b3f35b469ceb8c0e728bff6c742e3c47f593c2b3236e583f878d28b9de
+oid sha256:86f1020552ee26305e6b63679fd14e3fefb3d8d2e891256da9ca15c98a8bded8
 size 4728