Model save

README.md

@@ -1,7 +1,7 @@
 ---
+base_model: meta-llama/Llama-3.2-1B-Instruct
 library_name: peft
 license: llama3.2
-base_model: meta-llama/Llama-3.2-1B-Instruct
 tags:
 - generated_from_trainer
 model-index:
@@ -39,7 +39,7 @@ The following hyperparameters were used during training:
 - 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
@@ -50,7 +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-3.2-1B-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",
@@ -23,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "v_proj",
-    "o_proj",
     "down_proj",
+    "q_proj",
+    "o_proj",
     "up_proj",
     "k_proj",
     "gate_proj"

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2732480d838f6a594720039f553bf95f76c81ef8d5bfcda0a43aee9cebe059d4
+oid sha256:5b18f29da02c62e5c2a05f485a8bfdf25f5714242477af3bc367c82510e1b0b2
 size 1103312056

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": 11.98136043548584,
+      "grad_norm": 0.8612512350082397,
       "learning_rate": 8.794946550048592e-05,
-      "loss": 14.4561,
+      "loss": 0.9361,
       "step": 250
     },
     {
       "epoch": 0.970873786407767,
-      "grad_norm": 11.208343505859375,
+      "grad_norm": 0.882792592048645,
       "learning_rate": 7.580174927113704e-05,
-      "loss": 7.3145,
+      "loss": 0.4637,
       "step": 500
     },
     {
       "epoch": 1.4563106796116505,
-      "grad_norm": 10.085871696472168,
+      "grad_norm": 0.7288907766342163,
       "learning_rate": 6.365403304178815e-05,
-      "loss": 6.2815,
+      "loss": 0.3773,
       "step": 750
     },
     {
       "epoch": 1.941747572815534,
-      "grad_norm": 9.594468116760254,
+      "grad_norm": 0.7898958325386047,
       "learning_rate": 5.150631681243926e-05,
-      "loss": 5.9342,
+      "loss": 0.3425,
       "step": 1000
     },
     {
       "epoch": 2.4271844660194173,
-      "grad_norm": 8.205252647399902,
+      "grad_norm": 0.7035888433456421,
       "learning_rate": 3.9358600583090386e-05,
-      "loss": 5.7463,
+      "loss": 0.3212,
       "step": 1250
     },
     {
       "epoch": 2.912621359223301,
-      "grad_norm": 8.472267150878906,
+      "grad_norm": 0.7669738531112671,
       "learning_rate": 2.72108843537415e-05,
-      "loss": 5.6393,
+      "loss": 0.3091,
       "step": 1500
     },
     {
       "epoch": 3.3980582524271843,
-      "grad_norm": 8.200423240661621,
+      "grad_norm": 0.7301594018936157,
       "learning_rate": 1.5063168124392615e-05,
-      "loss": 5.4863,
+      "loss": 0.2961,
       "step": 1750
     },
     {
       "epoch": 3.883495145631068,
-      "grad_norm": 7.509068965911865,
+      "grad_norm": 0.6761432886123657,
       "learning_rate": 2.915451895043732e-06,
-      "loss": 5.4096,
+      "loss": 0.2897,
       "step": 2000
     },
     {
       "epoch": 4.0,
       "step": 2060,
-      "total_flos": 5.02338223728341e+17,
-      "train_loss": 6.985684559646162,
-      "train_runtime": 10644.5792,
-      "train_samples_per_second": 49.541,
-      "train_steps_per_second": 0.194
+      "total_flos": 5.02561395295531e+17,
+      "train_loss": 0.4131525734095898,
+      "train_runtime": 6771.2897,
+      "train_samples_per_second": 77.88,
+      "train_steps_per_second": 0.304
     }
   ],
   "logging_steps": 250,
@@ -91,7 +91,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.02338223728341e+17,
+  "total_flos": 5.02561395295531e+17,
   "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:f190173de478fd494cc1496b844a09f5ab571440d89be552908a3d995152da95
-size 5304
+oid sha256:a6a0c99b0cfdab87b2889b420d51b85c5da8ce3804ab1449a0108b8c05d84877
+size 5240