Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,70 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen2.5-1.5B
+tags:
+- base_model:adapter:Qwen/Qwen2.5-1.5B
+- llama-factory
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: qwen1.5b_lora_sft_8gpu_s12
+  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. -->
+
+# qwen1.5b_lora_sft_8gpu_s12
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) on the assimilation_strict_json_v2 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1504
+
+## 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: 0.0002
+- train_batch_size: 16
+- eval_batch_size: 4
+- seed: 12
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.05
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.1513        | 1.3158 | 50   | 0.1511          |
+| 0.1504        | 2.6316 | 100  | 0.1504          |
+| 0.1504        | 3.0    | 114  | 0.1504          |
+
+
+### Framework versions
+
+- PEFT 0.18.1
+- Transformers 5.6.0
+- Pytorch 2.7.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d985dd6f8ca36a8bbedbbd5c8a74b7aae0dc5600dd9f4d52f48b9054e8ec7092
+size 295488936

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.15037637948989868,
+    "eval_runtime": 0.3769,
+    "eval_samples_per_second": 663.255,
+    "eval_steps_per_second": 21.224,
+    "total_flos": 1.842079609965773e+16,
+    "train_loss": 0.3633330040856412,
+    "train_runtime": 60.6965,
+    "train_samples_per_second": 234.775,
+    "train_steps_per_second": 1.878
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.15037637948989868,
+    "eval_runtime": 0.3769,
+    "eval_samples_per_second": 663.255,
+    "eval_steps_per_second": 21.224
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.842079609965773e+16,
+    "train_loss": 0.3633330040856412,
+    "train_runtime": 60.6965,
+    "train_samples_per_second": 234.775,
+    "train_steps_per_second": 1.878
+}

trainer_log.jsonl

@@ -0,0 +1,26 @@
+{"current_steps": 5, "total_steps": 114, "loss": 3.3516746520996095, "lr": 0.00013333333333333334, "epoch": 0.13157894736842105, "percentage": 4.39, "elapsed_time": "0:00:03", "remaining_time": "0:01:06"}
+{"current_steps": 10, "total_steps": 114, "loss": 1.2694276809692382, "lr": 0.00019961946980917456, "epoch": 0.2631578947368421, "percentage": 8.77, "elapsed_time": "0:00:04", "remaining_time": "0:00:50"}
+{"current_steps": 15, "total_steps": 114, "loss": 0.39782161712646485, "lr": 0.00019730448705798239, "epoch": 0.39473684210526316, "percentage": 13.16, "elapsed_time": "0:00:06", "remaining_time": "0:00:43"}
+{"current_steps": 20, "total_steps": 114, "loss": 0.27879135608673095, "lr": 0.00019293475242268223, "epoch": 0.5263157894736842, "percentage": 17.54, "elapsed_time": "0:00:08", "remaining_time": "0:00:38"}
+{"current_steps": 25, "total_steps": 114, "loss": 0.22039237022399902, "lr": 0.00018660254037844388, "epoch": 0.6578947368421053, "percentage": 21.93, "elapsed_time": "0:00:10", "remaining_time": "0:00:35"}
+{"current_steps": 30, "total_steps": 114, "loss": 0.1895224332809448, "lr": 0.00017844156649195759, "epoch": 0.7894736842105263, "percentage": 26.32, "elapsed_time": "0:00:11", "remaining_time": "0:00:32"}
+{"current_steps": 35, "total_steps": 114, "loss": 0.18298850059509278, "lr": 0.0001686241637868734, "epoch": 0.9210526315789473, "percentage": 30.7, "elapsed_time": "0:00:13", "remaining_time": "0:00:30"}
+{"current_steps": 40, "total_steps": 114, "loss": 0.1633323073387146, "lr": 0.0001573576436351046, "epoch": 1.0526315789473684, "percentage": 35.09, "elapsed_time": "0:00:15", "remaining_time": "0:00:28"}
+{"current_steps": 45, "total_steps": 114, "loss": 0.15177669525146484, "lr": 0.00014487991802004623, "epoch": 1.1842105263157894, "percentage": 39.47, "elapsed_time": "0:00:16", "remaining_time": "0:00:25"}
+{"current_steps": 50, "total_steps": 114, "loss": 0.15127369165420532, "lr": 0.00013145447561516138, "epoch": 1.3157894736842106, "percentage": 43.86, "elapsed_time": "0:00:18", "remaining_time": "0:00:23"}
+{"current_steps": 50, "total_steps": 114, "eval_loss": 0.15111804008483887, "epoch": 1.3157894736842106, "percentage": 43.86, "elapsed_time": "0:00:19", "remaining_time": "0:00:24"}
+{"current_steps": 55, "total_steps": 114, "loss": 0.15102126598358154, "lr": 0.00011736481776669306, "epoch": 1.4473684210526316, "percentage": 48.25, "elapsed_time": "0:00:24", "remaining_time": "0:00:26"}
+{"current_steps": 60, "total_steps": 114, "loss": 0.15085721015930176, "lr": 0.00010290847187431113, "epoch": 1.5789473684210527, "percentage": 52.63, "elapsed_time": "0:00:26", "remaining_time": "0:00:23"}
+{"current_steps": 65, "total_steps": 114, "loss": 0.1507188558578491, "lr": 8.839070858747697e-05, "epoch": 1.7105263157894737, "percentage": 57.02, "elapsed_time": "0:00:27", "remaining_time": "0:00:21"}
+{"current_steps": 70, "total_steps": 114, "loss": 0.15061765909194946, "lr": 7.411809548974792e-05, "epoch": 1.8421052631578947, "percentage": 61.4, "elapsed_time": "0:00:29", "remaining_time": "0:00:18"}
+{"current_steps": 75, "total_steps": 114, "loss": 0.15057096481323243, "lr": 6.039202339608432e-05, "epoch": 1.973684210526316, "percentage": 65.79, "elapsed_time": "0:00:31", "remaining_time": "0:00:16"}
+{"current_steps": 80, "total_steps": 114, "loss": 0.15049142837524415, "lr": 4.7502341966544e-05, "epoch": 2.1052631578947367, "percentage": 70.18, "elapsed_time": "0:00:33", "remaining_time": "0:00:14"}
+{"current_steps": 85, "total_steps": 114, "loss": 0.15045424699783325, "lr": 3.5721239031346066e-05, "epoch": 2.236842105263158, "percentage": 74.56, "elapsed_time": "0:00:34", "remaining_time": "0:00:11"}
+{"current_steps": 90, "total_steps": 114, "loss": 0.15041965246200562, "lr": 2.529749287590042e-05, "epoch": 2.3684210526315788, "percentage": 78.95, "elapsed_time": "0:00:36", "remaining_time": "0:00:09"}
+{"current_steps": 95, "total_steps": 114, "loss": 0.15039608478546143, "lr": 1.6451218858706374e-05, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:00:38", "remaining_time": "0:00:07"}
+{"current_steps": 100, "total_steps": 114, "loss": 0.15038318634033204, "lr": 9.369221296335006e-06, "epoch": 2.6315789473684212, "percentage": 87.72, "elapsed_time": "0:00:40", "remaining_time": "0:00:05"}
+{"current_steps": 100, "total_steps": 114, "eval_loss": 0.15037640929222107, "epoch": 2.6315789473684212, "percentage": 87.72, "elapsed_time": "0:00:40", "remaining_time": "0:00:05"}
+{"current_steps": 105, "total_steps": 114, "loss": 0.15037939548492432, "lr": 4.20104876845111e-06, "epoch": 2.763157894736842, "percentage": 92.11, "elapsed_time": "0:00:45", "remaining_time": "0:00:03"}
+{"current_steps": 110, "total_steps": 114, "loss": 0.15037713050842286, "lr": 1.055836141905553e-06, "epoch": 2.8947368421052633, "percentage": 96.49, "elapsed_time": "0:00:47", "remaining_time": "0:00:01"}
+{"current_steps": 114, "total_steps": 114, "eval_loss": 0.15037637948989868, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:00:49", "remaining_time": "0:00:00"}
+{"current_steps": 114, "total_steps": 114, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:00:53", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,221 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 50,
+  "global_step": 114,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13157894736842105,
+      "grad_norm": 9.077587127685547,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 3.3516746520996095,
+      "step": 5
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 3.6344077587127686,
+      "learning_rate": 0.00019961946980917456,
+      "loss": 1.2694276809692382,
+      "step": 10
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 1.4878904819488525,
+      "learning_rate": 0.00019730448705798239,
+      "loss": 0.39782161712646485,
+      "step": 15
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 1.8839391469955444,
+      "learning_rate": 0.00019293475242268223,
+      "loss": 0.27879135608673095,
+      "step": 20
+    },
+    {
+      "epoch": 0.6578947368421053,
+      "grad_norm": 0.47065043449401855,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 0.22039237022399902,
+      "step": 25
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.13528835773468018,
+      "learning_rate": 0.00017844156649195759,
+      "loss": 0.1895224332809448,
+      "step": 30
+    },
+    {
+      "epoch": 0.9210526315789473,
+      "grad_norm": 0.10665454715490341,
+      "learning_rate": 0.0001686241637868734,
+      "loss": 0.18298850059509278,
+      "step": 35
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.1658766120672226,
+      "learning_rate": 0.0001573576436351046,
+      "loss": 0.1633323073387146,
+      "step": 40
+    },
+    {
+      "epoch": 1.1842105263157894,
+      "grad_norm": 0.047197695821523666,
+      "learning_rate": 0.00014487991802004623,
+      "loss": 0.15177669525146484,
+      "step": 45
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.005160723812878132,
+      "learning_rate": 0.00013145447561516138,
+      "loss": 0.15127369165420532,
+      "step": 50
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "eval_loss": 0.15111804008483887,
+      "eval_runtime": 0.4047,
+      "eval_samples_per_second": 617.704,
+      "eval_steps_per_second": 19.767,
+      "step": 50
+    },
+    {
+      "epoch": 1.4473684210526316,
+      "grad_norm": 0.004525308962911367,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 0.15102126598358154,
+      "step": 55
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.004724775906652212,
+      "learning_rate": 0.00010290847187431113,
+      "loss": 0.15085721015930176,
+      "step": 60
+    },
+    {
+      "epoch": 1.7105263157894737,
+      "grad_norm": 0.0037995593156665564,
+      "learning_rate": 8.839070858747697e-05,
+      "loss": 0.1507188558578491,
+      "step": 65
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.0033727441914379597,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.15061765909194946,
+      "step": 70
+    },
+    {
+      "epoch": 1.973684210526316,
+      "grad_norm": 0.003265872597694397,
+      "learning_rate": 6.039202339608432e-05,
+      "loss": 0.15057096481323243,
+      "step": 75
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.0035538917873054743,
+      "learning_rate": 4.7502341966544e-05,
+      "loss": 0.15049142837524415,
+      "step": 80
+    },
+    {
+      "epoch": 2.236842105263158,
+      "grad_norm": 0.003169580362737179,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 0.15045424699783325,
+      "step": 85
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "grad_norm": 0.003198214340955019,
+      "learning_rate": 2.529749287590042e-05,
+      "loss": 0.15041965246200562,
+      "step": 90
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.0028158631175756454,
+      "learning_rate": 1.6451218858706374e-05,
+      "loss": 0.15039608478546143,
+      "step": 95
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.0028616643976420164,
+      "learning_rate": 9.369221296335006e-06,
+      "loss": 0.15038318634033204,
+      "step": 100
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "eval_loss": 0.15037640929222107,
+      "eval_runtime": 0.3891,
+      "eval_samples_per_second": 642.505,
+      "eval_steps_per_second": 20.56,
+      "step": 100
+    },
+    {
+      "epoch": 2.763157894736842,
+      "grad_norm": 0.003008145373314619,
+      "learning_rate": 4.20104876845111e-06,
+      "loss": 0.15037939548492432,
+      "step": 105
+    },
+    {
+      "epoch": 2.8947368421052633,
+      "grad_norm": 0.0028472088743001223,
+      "learning_rate": 1.055836141905553e-06,
+      "loss": 0.15037713050842286,
+      "step": 110
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.15037637948989868,
+      "eval_runtime": 0.3596,
+      "eval_samples_per_second": 695.274,
+      "eval_steps_per_second": 22.249,
+      "step": 114
+    },
+    {
+      "epoch": 3.0,
+      "step": 114,
+      "total_flos": 1.842079609965773e+16,
+      "train_loss": 0.3633330040856412,
+      "train_runtime": 60.6965,
+      "train_samples_per_second": 234.775,
+      "train_steps_per_second": 1.878
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 114,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.842079609965773e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fce39691a0f22fcf61309d4c5c32f7b58ef62e322b201af3c5757d17dc5d202
+size 5777