Model save

README.md

@@ -0,0 +1,71 @@
+---
+license: llama2
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: meta-llama/Llama-2-7b-chat-hf
+model-index:
+- name: Llama-2-code-python
+  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. -->
+
+# Llama-2-code-python
+
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0589
+
+## 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: 2e-05
+- train_batch_size: 6
+- eval_batch_size: 6
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 24
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.612         | 0.3183 | 30   | 1.6686          |
+| 1.4094        | 0.6366 | 60   | 1.4388          |
+| 1.2172        | 0.9549 | 90   | 1.2583          |
+| 1.0647        | 1.2732 | 120  | 1.1357          |
+| 1.0144        | 1.5915 | 150  | 1.0771          |
+| 1.0622        | 1.9098 | 180  | 1.0643          |
+| 1.045         | 2.2281 | 210  | 1.0599          |
+| 1.0739        | 2.5464 | 240  | 1.0588          |
+| 1.0306        | 2.8647 | 270  | 1.0589          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:587701cfafaa6aea3fc46112d59256a6dd427aab4ee2767cbb3abb6f27127953
+size 67126232

runs/May24_05-06-15_eb729ab69650/events.out.tfevents.1716527183.eb729ab69650.6573.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39d0db223f26cd4b2dfad89d6407746c7e858f8dc8324c45350225a7fcff34b9
+size 6056

runs/May24_05-07-25_eb729ab69650/events.out.tfevents.1716527252.eb729ab69650.6946.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a41624668392e92ef023773f4a19aa63974a4aa6fc4fabd5edbd0998fa0b79b4
+size 6056

runs/May24_05-08-48_eb729ab69650/events.out.tfevents.1716527335.eb729ab69650.7379.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063b4a502ff06007cd427d9026abcea81c9b5b9423552731f03929ce4bea300b
+size 7002

runs/May24_05-11-32_eb729ab69650/events.out.tfevents.1716527499.eb729ab69650.8194.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9737526ce7d3c020a01d9a25d842d55b1e8a6fc1e7c1f6f434e3d20c37caa6a5
+size 6404

runs/May24_05-14-18_eb729ab69650/events.out.tfevents.1716527665.eb729ab69650.8970.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4298d4359f90412a07bc9636a6132dddb2d5cc75862000c0e9d388d0d1522d37
+size 7945

runs/May24_05-19-09_eb729ab69650/events.out.tfevents.1716527956.eb729ab69650.10277.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b5cb4dda68dc125b5f329619e07234aabacb29adea34234487b9da04e84f113
+size 6468

runs/May24_05-21-12_eb729ab69650/events.out.tfevents.1716528079.eb729ab69650.10876.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1690855beb96755a538ec3ea57e42b73f31175296c5e8dd6da3da0060e190694
+size 6263

runs/May24_05-23-22_eb729ab69650/events.out.tfevents.1716528209.eb729ab69650.11507.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11b2dfad60ac11ff95a51375b9ed680dd01dec75f38d51ac303a72c770156d00
+size 20543

runs/May24_06-24-01_eb729ab69650/events.out.tfevents.1716531848.eb729ab69650.27550.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d5b2bfb94cd2ded40614e57bc131bd177c0a42a2f49240a48722b37c2eac7e4
+size 11545

runs/May24_07-06-31_eb729ab69650/events.out.tfevents.1716534425.eb729ab69650.38261.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13215d4cf533545ef94f1b88ad0e0c74744fbef11838b85334b79b3216900573
+size 19874

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "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,
+  "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": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84177971dd94e6fd5245e9d823b1a2dae73c905768537ca34ba6c258e5823dd2
+size 5112