Training in progress, step 60

README.md

@@ -0,0 +1,67 @@
+---
+base_model: NousResearch/Llama-2-7b-hf
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: Cold-Data-LLama-2-7B
+  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. -->
+
+# Cold-Data-LLama-2-7B
+
+This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0526
+
+## 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: 0.002
+- train_batch_size: 16
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- 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: 0.03
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.1019        | 1.992 | 249  | 0.1022          |
+| 0.0542        | 3.984 | 498  | 0.0540          |
+| 0.0508        | 5.976 | 747  | 0.0513          |
+| 0.0479        | 7.968 | 996  | 0.0515          |
+| 0.0472        | 9.96  | 1245 | 0.0537          |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.43.3
+- Pytorch 2.3.1+cu121
+- Datasets 2.17.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-7b-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 sha256:38cd1ccd5681e8b6442697ddc6b05aa049d662f3fe973d76419114b54a30c5a7
+size 134235048

runs/Aug09_10-08-36_fastgpuserv/events.out.tfevents.1723180125.fastgpuserv.494076.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49bda035f9f01f0961818a10f644eb3de63db842ea812b8da5a9d472d7d54b7f
+size 5776

runs/Aug09_10-22-52_fastgpuserv/events.out.tfevents.1723180978.fastgpuserv.502349.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12e057a969fc78b376b9746b1715f59685f9c9859633a49534ccb7d269f57827
+size 33846

runs/Aug09_10-22-52_fastgpuserv/events.out.tfevents.1723268246.fastgpuserv.502349.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad26b338296efb151b9d75bb2d3adc053a8bd8b32894c14dd7fc8f83d4446db1
+size 359

runs/Aug11_09-51-12_fastgpuserv/events.out.tfevents.1723351879.fastgpuserv.3318356.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b86e9c8235e9cb6e65759fe3ddc6ea69b66e1a4e5e0fad6cc0415278c08f0f
+size 33846

runs/Aug12_10-37-51_fastgpuserv/events.out.tfevents.1723441092.fastgpuserv.2424037.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12357d766faff277259ca25a7f1f8f23f40cdfa2ecd6248888f472abf7afaec0
+size 5776

runs/Aug12_10-44-55_fastgpuserv/events.out.tfevents.1723441505.fastgpuserv.2458899.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4628a04d05282ab2004639f971a77b3a6f53a96f52bdfe2cf29993ecfd46b24e
+size 33814

runs/Aug12_10-44-55_fastgpuserv/events.out.tfevents.1723720304.fastgpuserv.2458899.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c8160446538513f3946805cc0ef72e0e251a33474478fadbe680f3557397b78
+size 359

runs/Aug20_23-57-27_fastgpuserv/events.out.tfevents.1724180258.fastgpuserv.1412094.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfea3dd99266f8e2d927b3263ad7f9dc2333b546e001b052feec3f12f408c84a
+size 8700

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "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": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "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 sha256:89c41ef7d13b927eced2a41ab72ade244ac48f624c934963f5863a4e2fcf981a
+size 5432