Model save

README.md

@@ -0,0 +1,72 @@
+---
+license: apache-2.0
+base_model: amazingvince/zephyr-smol_llama-100m-sft-full
+tags:
+- generated_from_trainer
+model-index:
+- name: zephyr-smol_llama-100m-dpo-1-epoch
+  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. -->
+
+# zephyr-smol_llama-100m-dpo-1-epoch
+
+This model is a fine-tuned version of [amazingvince/zephyr-smol_llama-100m-sft-full](https://huggingface.co/amazingvince/zephyr-smol_llama-100m-sft-full) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5661
+- Rewards/chosen: 0.0614
+- Rewards/rejected: -0.4791
+- Rewards/accuracies: 0.6810
+- Rewards/margins: 0.5405
+- Logps/rejected: -447.3311
+- Logps/chosen: -587.6553
+- Logits/rejected: -4.9351
+- Logits/chosen: -5.2302
+
+## 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: 5e-07
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 16
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.6597        | 0.26  | 1000 | 0.5887          | -0.0788        | -0.5504          | 0.6700             | 0.4715          | -448.0441      | -589.0577    | -4.7945         | -5.0906       |
+| 0.5306        | 0.52  | 2000 | 0.5740          | 0.0053         | -0.5021          | 0.6840             | 0.5074          | -447.5612      | -588.2166    | -4.8585         | -5.1486       |
+| 0.6036        | 0.77  | 3000 | 0.5676          | 0.0550         | -0.4785          | 0.6890             | 0.5335          | -447.3253      | -587.7193    | -4.9388         | -5.2343       |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0
+- Datasets 2.14.6
+- Tokenizers 0.14.1

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -5.230160236358643,
+    "eval_logits/rejected": -4.935074329376221,
+    "eval_logps/chosen": -587.6553344726562,
+    "eval_logps/rejected": -447.3310852050781,
+    "eval_loss": 0.5660516619682312,
+    "eval_rewards/accuracies": 0.6809999942779541,
+    "eval_rewards/chosen": 0.06142662093043327,
+    "eval_rewards/margins": 0.5404847264289856,
+    "eval_rewards/rejected": -0.4790581166744232,
+    "eval_runtime": 108.3952,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 18.451,
+    "eval_steps_per_second": 1.153,
+    "train_loss": 0.5843773977780509,
+    "train_runtime": 4895.0541,
+    "train_samples": 61966,
+    "train_samples_per_second": 12.659,
+    "train_steps_per_second": 0.791
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "amazingvince/zephyr-smol_llama-100m-sft-full",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 1024,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 6,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.0",
+  "use_cache": false,
+  "vocab_size": 32128
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -5.230160236358643,
+    "eval_logits/rejected": -4.935074329376221,
+    "eval_logps/chosen": -587.6553344726562,
+    "eval_logps/rejected": -447.3310852050781,
+    "eval_loss": 0.5660516619682312,
+    "eval_rewards/accuracies": 0.6809999942779541,
+    "eval_rewards/chosen": 0.06142662093043327,
+    "eval_rewards/margins": 0.5404847264289856,
+    "eval_rewards/rejected": -0.4790581166744232,
+    "eval_runtime": 108.3952,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 18.451,
+    "eval_steps_per_second": 1.153
+}

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 sha256:4d8a6581429ab1777c57933c066a11845f950de0ac647a134ee4d1d4851862d6
+size 202532568

runs/Nov20_20-48-27_VincentPC/events.out.tfevents.1700531314.VincentPC.14406.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74894e7d02cad13f72e54bbc6df3915c78e0428d6abf2d7ebba237e5168c7a31
+size 252828

runs/Nov20_20-48-27_VincentPC/events.out.tfevents.1700536318.VincentPC.14406.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f6754da3bfd10b67e0b2f53da516c71f42d399c4c866b7e977db4af1a03dfe3
+size 828

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "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
+    }
+  },
+  "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": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.5843773977780509,
+    "train_runtime": 4895.0541,
+    "train_samples": 61966,
+    "train_samples_per_second": 12.659,
+    "train_steps_per_second": 0.791
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f9caf5864401b77ea7fa19fec068be8525068daea4c72df8d140267d3f03167
+size 5752