Model save

README.md

@@ -0,0 +1,69 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: tinyllama-1.1B-intermediate-step-715k-1.5T-dpo-lora
+  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. -->
+
+# tinyllama-1.1B-intermediate-step-715k-1.5T-dpo-lora
+
+This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6877
+- Rewards/chosen: 0.0254
+- Rewards/rejected: 0.0135
+- Rewards/accuracies: 0.5645
+- Rewards/margins: 0.0119
+- Logps/rejected: -315.6106
+- Logps/chosen: -402.4017
+- Logits/rejected: -4.0818
+- Logits/chosen: -4.1916
+
+## 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: 2
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 64
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.6916        | 1.0   | 968  | 0.6921          | 0.0039         | 0.0011           | 0.5070             | 0.0028          | -315.7343      | -402.6164    | -4.0813         | -4.1913       |
+| 0.6904        | 2.0   | 1936 | 0.6884          | 0.0191         | 0.0086           | 0.5570             | 0.0105          | -315.6588      | -402.4643    | -4.0824         | -4.1920       |
+| 0.6876        | 3.0   | 2904 | 0.6877          | 0.0254         | 0.0135           | 0.5645             | 0.0119          | -315.6106      | -402.4017    | -4.0818         | -4.1916       |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0+cu121
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "SebastianSchramm/tinyllama-1.1B-intermediate-step-715k-1.5T-sft-lora-merged",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8ff0c74b34643eff3dc8d8ba700c641227b39f2e9980347c5d5e69af64dd6f8
+size 72113224

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 3.0,
+    "eval_logits/chosen": -4.191605567932129,
+    "eval_logits/rejected": -4.081777572631836,
+    "eval_logps/chosen": -402.4017333984375,
+    "eval_logps/rejected": -315.6105651855469,
+    "eval_loss": 0.6876626014709473,
+    "eval_rewards/accuracies": 0.5644999742507935,
+    "eval_rewards/chosen": 0.025381002575159073,
+    "eval_rewards/margins": 0.011920945718884468,
+    "eval_rewards/rejected": 0.013460054062306881,
+    "eval_runtime": 777.3765,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 2.573,
+    "eval_steps_per_second": 0.643,
+    "train_loss": 0.6907179896044994,
+    "train_runtime": 111372.3355,
+    "train_samples": 61966,
+    "train_samples_per_second": 1.669,
+    "train_steps_per_second": 0.026
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_logits/chosen": -4.191605567932129,
+    "eval_logits/rejected": -4.081777572631836,
+    "eval_logps/chosen": -402.4017333984375,
+    "eval_logps/rejected": -315.6105651855469,
+    "eval_loss": 0.6876626014709473,
+    "eval_rewards/accuracies": 0.5644999742507935,
+    "eval_rewards/chosen": 0.025381002575159073,
+    "eval_rewards/margins": 0.011920945718884468,
+    "eval_rewards/rejected": 0.013460054062306881,
+    "eval_runtime": 777.3765,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 2.573,
+    "eval_steps_per_second": 0.643
+}

runs/Nov12_12-39-07_sebastian-dell/events.out.tfevents.1699789155.sebastian-dell.51009.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13134646747ac148fd878b532fcc8498b8c49b26ada3eea8d79ac0199ead8f4b
+size 191548

runs/Nov12_12-39-07_sebastian-dell/events.out.tfevents.1699901305.sebastian-dell.51009.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0d6b1c306a1e0569c8ff0790b68b65ad1d0bee4997fcdace13b103d3da4cf29
+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_config.json

@@ -0,0 +1,40 @@
+{
+  "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": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.6907179896044994,
+    "train_runtime": 111372.3355,
+    "train_samples": 61966,
+    "train_samples_per_second": 1.669,
+    "train_steps_per_second": 0.026
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e540bfcb141d683b819b3b5de88c55baa43bf7813a466523b763fb2090be2ac9
+size 4856