Cikola/Llama2_OneShot-Learning

README.md

@@ -1,9 +1,7 @@
 ---
-base_model: meta-llama/Llama-2-7b-chat-hf
+base_model: meta-llama/Llama-2-7b-hf
 library_name: peft
 license: llama2
-metrics:
-- accuracy
 tags:
 - generated_from_trainer
 model-index:
@@ -16,10 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-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 the None dataset.
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0120
-- Accuracy: 1.0
+- Loss: 2.1270
 
 ## Model description
 
@@ -52,14 +49,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.8   | 2    | 0.6934          | 0.75     |
-| No log        | 2.0   | 5    | 0.4856          | 0.75     |
-| No log        | 2.8   | 7    | 0.1547          | 1.0      |
-| No log        | 4.0   | 10   | 0.0583          | 1.0      |
-| No log        | 4.8   | 12   | 0.0139          | 1.0      |
-| No log        | 6.0   | 15   | 0.0120          | 1.0      |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 1    | 7.8752          |
+| No log        | 2.0   | 2    | 7.1592          |
+| No log        | 3.0   | 3    | 5.8948          |
+| No log        | 4.0   | 4    | 3.9066          |
+| No log        | 5.0   | 5    | 2.6638          |
+| No log        | 6.0   | 6    | 2.2232          |
+| No log        | 7.0   | 7    | 2.1572          |
+| No log        | 8.0   | 8    | 2.1381          |
+| No log        | 9.0   | 9    | 2.1296          |
+| No log        | 10.0  | 10   | 2.1270          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -14,19 +14,16 @@
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": [
-    "classifier",
-    "score"
-  ],
+  "modules_to_save": null,
   "peft_type": "LORA",
   "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
-  "task_type": "SEQ_CLS",
+  "task_type": "CAUSAL_LM",
   "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c503520b23c049b2b4d1d7e852ae687d5a32a6e7f1a7568262caa924da295f4
-size 134267920
+oid sha256:e2d76d97c2f36176a51a8562fc74efd5a2891b743676b585335732e38c3e25c0
+size 134235048

runs/Jul20_17-47-41_jupyter-s0569591/events.out.tfevents.1721497662.jupyter-s0569591.69.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ce00939b08e5cf559923ae093d087be397b7efd5cbed3a02be1f464ad064ea
+size 5333

runs/Jul20_17-49-51_jupyter-s0569591/events.out.tfevents.1721497791.jupyter-s0569591.69.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b967bb8c1933d0968b2b26c0f593ffddac57c4543e3dfbb2c73ddd714fd4b41
+size 5333

runs/Jul20_17-53-02_jupyter-s0569591/events.out.tfevents.1721497983.jupyter-s0569591.69.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d83dbe46d813a352eb9ff6dd733ec5c2681fdaa545ac9b5a5d7aa0d2fb67bc1
+size 5333

runs/Jul20_18-00-12_jupyter-s0569591/events.out.tfevents.1721498413.jupyter-s0569591.69.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47a3774582aa1b5b24ab222be12d1249509b7e11d512c5e38495c39a21a26cf0
+size 5339

runs/Jul20_18-07-01_jupyter-s0569591/events.out.tfevents.1721498822.jupyter-s0569591.69.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5dd63b996d75c989a4ed8d3c7da61e2ef7599391e0efe77e9b6fb30a255bc2e
+size 8347

tokenizer_config.json

@@ -29,7 +29,6 @@
     }
   },
   "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>",
   "legacy": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33745e08c46cb862ef1e33c61bb3f21f8a2a02d62acb53cc52c8f7dfd646e708
+oid sha256:97e75a2aeafd58517718ad752fa80e2e16cf3a82e3c388c251b0b2cfecd35db6
 size 5112