End of training

README.md

@@ -0,0 +1,64 @@
+---
+library_name: transformers
+base_model: trl-internal-testing/tiny-random-LlamaForCausalLM
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: tmp-dpo
+  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. -->
+
+# tmp-dpo
+
+This model is a fine-tuned version of [trl-internal-testing/tiny-random-LlamaForCausalLM](https://huggingface.co/trl-internal-testing/tiny-random-LlamaForCausalLM) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6931
+- Rewards/chosen: -0.0001
+- Rewards/rejected: -0.0001
+- Rewards/accuracies: 0.625
+- Rewards/margins: 0.0001
+- Logps/rejected: -2296.9749
+- Logps/chosen: -2241.1948
+- Logits/rejected: -0.0001
+- Logits/chosen: -0.0001
+
+## 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: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- training_steps: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 0.00012874983906270118,
+    "eval_logits/chosen": -0.00010515563189983368,
+    "eval_logits/rejected": -8.74076213221997e-05,
+    "eval_logps/chosen": -2241.19482421875,
+    "eval_logps/rejected": -2296.974853515625,
+    "eval_loss": 0.6931134462356567,
+    "eval_rewards/accuracies": 0.625,
+    "eval_rewards/chosen": -7.68661848269403e-05,
+    "eval_rewards/margins": 7.162100519053638e-05,
+    "eval_rewards/rejected": -0.00014848708815407008,
+    "eval_runtime": 3.5865,
+    "eval_samples_per_second": 2.231,
+    "eval_steps_per_second": 0.279
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "trl-internal-testing/tiny-random-LlamaForCausalLM",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "pad_token_id": -1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 0.00012874983906270118,
+    "eval_logits/chosen": -0.00010515563189983368,
+    "eval_logits/rejected": -8.74076213221997e-05,
+    "eval_logps/chosen": -2241.19482421875,
+    "eval_logps/rejected": -2296.974853515625,
+    "eval_loss": 0.6931134462356567,
+    "eval_rewards/accuracies": 0.625,
+    "eval_rewards/chosen": -7.68661848269403e-05,
+    "eval_rewards/margins": 7.162100519053638e-05,
+    "eval_rewards/rejected": -0.00014848708815407008,
+    "eval_runtime": 3.5865,
+    "eval_samples_per_second": 2.231,
+    "eval_steps_per_second": 0.279
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 2,
+  "transformers_version": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:921091c1415be5f1ade40730c34c3e909d5ec032aabb435670295059eeea706c
+size 4131280

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": "<unk>",
+    "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 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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 %}{{message['role'] + ': ' + message['content'] + '\n\n'}}{% endfor %}{{ eos_token }}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "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 sha256:3356cca932372a3946a63c90cfc460a48f8ecd28081e1518e5741d2bea57ca5c
+size 5944