ai-maker-space/llama38binstruct-summary-100s

README.md

@@ -1,13 +1,13 @@
 ---
-license: other
+base_model: NousResearch/Meta-Llama-3-8B-Instruct
+datasets:
+- generator
 library_name: peft
+license: other
 tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: NousResearch/Meta-Llama-3-8B-Instruct
-datasets:
-- generator
 model-index:
 - name: llama38binstruct_summarize
   results: []
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6753
+- Loss: 2.1068
 
 ## Model description
 
@@ -45,23 +45,23 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
-- lr_scheduler_warmup_steps: 0.03
+- lr_scheduler_warmup_steps: 30
 - training_steps: 100
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.4436        | 1.1905 | 25   | 1.0958          |
-| 0.5989        | 2.3810 | 50   | 1.2958          |
-| 0.2448        | 3.5714 | 75   | 1.5235          |
-| 0.099         | 4.7619 | 100  | 1.6753          |
+| 1.55          | 1.3158 | 25   | 1.5000          |
+| 0.5276        | 2.6316 | 50   | 1.7814          |
+| 0.2099        | 3.9474 | 75   | 1.8811          |
+| 0.0761        | 5.2632 | 100  | 2.1068          |
 
 
 ### Framework versions
 
-- PEFT 0.11.1
-- Transformers 4.41.2
-- Pytorch 2.3.0+cu121
-- Datasets 2.19.2
+- PEFT 0.12.0
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 3.0.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "q_proj",
-    "v_proj",
+    "down_proj",
     "up_proj",
-    "gate_proj",
     "k_proj",
-    "o_proj"
+    "o_proj",
+    "gate_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e830cf60d62fd1beae745801b2eebd6ca2035f72dbcf013a55efb8625a87d86d
+oid sha256:3e9d4c0f52c8eccf0b29f14f9db91d438725d9da5b1a065f582fcbc1b41edbb8
 size 167832240

runs/Sep12_19-43-37_8e18eff6a629/events.out.tfevents.1726170227.8e18eff6a629.938.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58678f8b841bad145dc5fc3478c03272db94bb147f867c94a69a1ec475a0d111
+size 9354

special_tokens_map.json

@@ -7,11 +7,11 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "<|end_of_text|>",
+    "content": "<|eot_id|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|end_of_text|>"
+  "pad_token": "<|eot_id|>"
 }

tokenizer_config.json

@@ -2052,12 +2052,12 @@
   "bos_token": "<|begin_of_text|>",
   "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|end_of_text|>",
+  "eos_token": "<|eot_id|>",
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|end_of_text|>",
+  "pad_token": "<|eot_id|>",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ec406f70a4db0f7b6ca78d6f1e68a2e38a26462493b4efaf8ca0e9819f20c0f
-size 5368
+oid sha256:f99e1b41aec4320fd7664144dd9a1354cf2a88d14a37b24a316c3d45e900b0da
+size 5496