Model save

README.md

@@ -1,7 +1,7 @@
 ---
+base_model: meta-llama/Llama-3.2-3B-Instruct
 library_name: peft
 license: llama3.2
-base_model: meta-llama/Llama-3.2-3B-Instruct
 tags:
 - generated_from_trainer
 model-index:
@@ -33,14 +33,15 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 0.0001
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 16
 - total_train_batch_size: 256
-- optimizer: Use adamw_hf with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2
 - num_epochs: 4
 
 ### Training results
@@ -49,7 +50,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.14.0
-- Transformers 4.47.1
-- Pytorch 2.5.1
-- Tokenizers 0.21.0
+- PEFT 0.13.0
+- Transformers 4.45.2
+- Pytorch 2.4.0
+- Tokenizers 0.20.0

adapter_config.json

@@ -3,8 +3,6 @@
   "auto_mapping": null,
   "base_model_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
   "bias": "none",
-  "eva_config": null,
-  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -13,7 +11,6 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 32,
-  "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -24,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "down_proj",
-    "v_proj",
     "k_proj",
-    "up_proj",
     "gate_proj",
-    "o_proj"
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f5ccf722379804ea9ef74d4683e1f5161bfd1be3c0e4617a179c17cbcce8874
+oid sha256:e502db4380eb225e5e8e326d092b5164248dec0da88569586775f63d5112a7ab
 size 1684597880

config.json

@@ -33,7 +33,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.47.1",
+  "transformers_version": "4.45.2",
   "use_cache": true,
   "vocab_size": 129174
 }

tokenizer_config.json

@@ -9397,7 +9397,6 @@
   "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n        {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n        {{- '\"parameters\": ' }}\n        {{- tool_call.arguments | tojson }}\n        {{- \"}\" }}\n        {{- \"<|eot_id|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|eot_id|>",
-  "extra_special_tokens": {},
   "model_input_names": [
     "input_ids",
     "attention_mask"

trainer_state.json

@@ -10,68 +10,68 @@
   "log_history": [
     {
       "epoch": 0.4854368932038835,
-      "grad_norm": 6.504103183746338,
-      "learning_rate": 4.393203883495146e-05,
-      "loss": 17.9006,
+      "grad_norm": 0.5462909936904907,
+      "learning_rate": 8.794946550048592e-05,
+      "loss": 0.7922,
       "step": 250
     },
     {
       "epoch": 0.970873786407767,
-      "grad_norm": 9.236562728881836,
-      "learning_rate": 3.7864077669902914e-05,
-      "loss": 10.3383,
+      "grad_norm": 0.5513872504234314,
+      "learning_rate": 7.580174927113704e-05,
+      "loss": 0.3621,
       "step": 500
     },
     {
       "epoch": 1.4563106796116505,
-      "grad_norm": 16.256534576416016,
-      "learning_rate": 3.1796116504854373e-05,
-      "loss": 8.7552,
+      "grad_norm": 0.5781261324882507,
+      "learning_rate": 6.365403304178815e-05,
+      "loss": 0.3085,
       "step": 750
     },
     {
       "epoch": 1.941747572815534,
-      "grad_norm": 17.89598846435547,
-      "learning_rate": 2.5728155339805826e-05,
-      "loss": 7.8554,
+      "grad_norm": 0.6140846014022827,
+      "learning_rate": 5.150631681243926e-05,
+      "loss": 0.2823,
       "step": 1000
     },
     {
       "epoch": 2.4271844660194173,
-      "grad_norm": 16.893712997436523,
-      "learning_rate": 1.9660194174757282e-05,
-      "loss": 7.3315,
+      "grad_norm": 0.5387245416641235,
+      "learning_rate": 3.9358600583090386e-05,
+      "loss": 0.2616,
       "step": 1250
     },
     {
       "epoch": 2.912621359223301,
-      "grad_norm": 13.431181907653809,
-      "learning_rate": 1.3592233009708738e-05,
-      "loss": 7.0833,
+      "grad_norm": 0.5812926292419434,
+      "learning_rate": 2.72108843537415e-05,
+      "loss": 0.252,
       "step": 1500
     },
     {
       "epoch": 3.3980582524271843,
-      "grad_norm": 12.282544136047363,
-      "learning_rate": 7.524271844660194e-06,
-      "loss": 6.9,
+      "grad_norm": 0.538931131362915,
+      "learning_rate": 1.5063168124392615e-05,
+      "loss": 0.2393,
       "step": 1750
     },
     {
       "epoch": 3.883495145631068,
-      "grad_norm": 11.840730667114258,
-      "learning_rate": 1.4563106796116506e-06,
-      "loss": 6.8409,
+      "grad_norm": 0.5031210780143738,
+      "learning_rate": 2.915451895043732e-06,
+      "loss": 0.2342,
       "step": 2000
     },
     {
       "epoch": 4.0,
       "step": 2060,
-      "total_flos": 1.4507840127190487e+18,
-      "train_loss": 9.058904229321525,
-      "train_runtime": 27634.2806,
-      "train_samples_per_second": 19.083,
-      "train_steps_per_second": 0.075
+      "total_flos": 1.4514285460762153e+18,
+      "train_loss": 0.33831017781229855,
+      "train_runtime": 16558.4463,
+      "train_samples_per_second": 31.848,
+      "train_steps_per_second": 0.124
     }
   ],
   "logging_steps": 250,
@@ -91,7 +91,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4507840127190487e+18,
+  "total_flos": 1.4514285460762153e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aaad4f213d3e82064031a262f630e6c9942e8059015557322a33d65c1ae8f1a
-size 5304
+oid sha256:00bee88cfff70ceb036e8da2a203c831e95fa4809539bbcfa0257eb67b695712
+size 5240