End of training

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- reward-trainer
+- generated_from_trainer
+base_model: openchat/openchat-3.5-0106
+model-index:
+- name: reward_modeling_openchat
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# reward_modeling_openchat
+
+This model is a fine-tuned version of [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1.41e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.39.0.dev0
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openchat/openchat-3.5-0106",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "SEQ_CLS"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a3e74ae92c85c75ad815f00c8209ad893a7877820441a657c92d784d5baa24f
+size 218137824

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|end_of_turn|>": 32000,
+  "<|pad_0|>": 32001
+}

runs/Jun04_20-47-25_node42/events.out.tfevents.1717501858.node42.23069.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d3d5698db09baa773746fa6533a2ad20578cc9913bd78a09a82e7e027e6082e
+size 4651

runs/Jun12_01-51-18_node42/events.out.tfevents.1718126091.node42.117859.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d83b09dc366f306d88f79752b6c54abcb392c10c0814c3465815ba15f23b496d
+size 4729

runs/Jun12_02-20-14_node42/events.out.tfevents.1718126559.node42.119606.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8137a42e8b5243da0c39622e01a61a605a410a0010b29b6e63588275d5137c91
+size 4729

runs/Jun12_02-27-27_node42/events.out.tfevents.1718127001.node42.120301.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05818a1f143ab0ed71f61f34742b18bcd981855c8589ff39f877ee6ce9968e07
+size 4754

runs/Jun12_02-50-07_node42/events.out.tfevents.1718128353.node42.121787.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3616bc907baf337af06d041fcd8613700d0c06fa4a45852c24a19a7175ea1191
+size 4729

runs/Jun12_03-54-29_node42/events.out.tfevents.1718132151.node42.125320.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7efb136eb1ffb7da36e69da7afac41d784b871a0d8c798feac1a79ec8c5663aa
+size 4729

runs/Jun12_04-03-42_node42/events.out.tfevents.1718132727.node42.126071.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1a16647d1f684276c3289190e6e34560c6df8e8d4915438a77d739c47abfcc2
+size 4729

runs/Jun12_04-16-11_node42/events.out.tfevents.1718133480.node42.126855.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75d47e5b50651aeae2c9527895bec52da3200130eff339234c6f3b6a2c4f9ada
+size 4729

runs/Jun12_04-21-59_node42/events.out.tfevents.1718133827.node42.127278.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b56f6993411becef18ad08efc0be8ba4963d4b7dc995797ea264563c297a875
+size 4754

runs/Jun12_04-27-14_node42/events.out.tfevents.1718134141.node42.127845.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0113fa2c050c9a3eadef56d41b706f4585334d02ca4a319e06286024fbf2e81a
+size 4754

runs/Jun12_20-39-04_node29/events.out.tfevents.1718192452.node29.294219.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e01db66fa87117f069286f3c5f64e29ab99c9d8a502e095633b1338b869d9c74
+size 5196

runs/Jun12_22-28-54_node28/events.out.tfevents.1718199189.node28.257588.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39f1a1334900e46b1c9b7b7edcaf604be3e1737599acb1876f7f2121ca395e16
+size 31666

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<|end_of_turn|>",
+    "<|pad_0|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_turn|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_turn|>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|end_of_turn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|pad_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|end_of_turn|>",
+    "<|pad_0|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end_of_turn|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|end_of_turn|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5516f1e7950ac6649172d0184e3d35ad00771d5396a4657deda6e55e2804535f
+size 4984