Model save

README.md

@@ -0,0 +1,74 @@
+---
+base_model: Qwen/Qwen2-1.5B-Instruct
+library_name: peft
+license: apache-2.0
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: test0901-5
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](None)
+# test0901-5
+
+This model is a fine-tuned version of [Qwen/Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8424
+
+## 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: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- training_steps: 10
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| No log        | 0.0082 | 1    | 2.0249          |
+| No log        | 0.0163 | 2    | 2.0155          |
+| No log        | 0.0245 | 3    | 1.9926          |
+| No log        | 0.0326 | 4    | 1.9594          |
+| No log        | 0.0408 | 5    | 1.9194          |
+| No log        | 0.0489 | 6    | 1.8850          |
+| No log        | 0.0571 | 7    | 1.8630          |
+| No log        | 0.0652 | 8    | 1.8497          |
+| No log        | 0.0734 | 9    | 1.8417          |
+| 1.6809        | 0.0815 | 10   | 1.8424          |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.42.4
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-1.5B-Instruct",
+  "bias": "none",
+  "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": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb4949db77552905d86b2683e94157b4d08fd4fd49d317d9e195443f5d3e3f9b
+size 36981072

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|endoftext|>": 151643,
+  "<|eot_id|>": 151646,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 0.08154943934760449,
+    "eval_loss": 1.8393741846084595,
+    "eval_runtime": 6.7009,
+    "eval_samples_per_second": 16.416,
+    "eval_steps_per_second": 16.416,
+    "total_flos": 124335445598208.0,
+    "train_loss": 1.6808662414550781,
+    "train_runtime": 109.4363,
+    "train_samples_per_second": 0.731,
+    "train_steps_per_second": 0.091
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.08154943934760449,
+    "eval_loss": 1.8393741846084595,
+    "eval_runtime": 6.7009,
+    "eval_samples_per_second": 16.416,
+    "eval_steps_per_second": 16.416
+}

runs/Sep01_12-22-50_dsw-83959-5f9bd48d7d-89klm/events.out.tfevents.1725164586.dsw-83959-5f9bd48d7d-89klm.2955372.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a3c77ce1d9270172ad09e30294ac5f9891271ecf559c8d0a617349a92a94505
+size 88

runs/Sep01_12-24-16_dsw-83959-5f9bd48d7d-89klm/events.out.tfevents.1725164672.dsw-83959-5f9bd48d7d-89klm.2956536.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26f4e529c9f9d8ff6d0f39d4f78854b7b209b8e55c1cfad012fe433ee982d8a8
+size 88

runs/Sep01_12-25-35_dsw-83959-5f9bd48d7d-89klm/events.out.tfevents.1725164753.dsw-83959-5f9bd48d7d-89klm.2957417.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42b281ea4b3edfc07df50015fcff414bcc7e4f103fe919776c1a719b9c196f6d
+size 8519

runs/Sep01_12-29-54_dsw-83959-5f9bd48d7d-89klm/events.out.tfevents.1725165017.dsw-83959-5f9bd48d7d-89klm.2960877.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9103074bb1616cdc52dcecff4f69920302256a488d7a4b564d63b59d7d57d653
+size 8524

runs/Sep01_12-33-50_dsw-83959-5f9bd48d7d-89klm/events.out.tfevents.1725165255.dsw-83959-5f9bd48d7d-89klm.2964077.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a5b558359896c24478d43ebf013cd2d6b059afab60dd34c693d96311bb399b0
+size 8524

runs/Sep01_12-33-50_dsw-83959-5f9bd48d7d-89klm/events.out.tfevents.1725165429.dsw-83959-5f9bd48d7d-89klm.2964077.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5876d3ee9b2bee94a9f13accc0197a7b865eb1a31d1313ed3cc4641fc0ae211
+size 354

runs/Sep01_13-09-02_dsw-83959-5f9bd48d7d-89klm/events.out.tfevents.1725167504.dsw-83959-5f9bd48d7d-89klm.2978286.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d1a2c163e4f1c922b3b7b6fc6f94a4406f1e0b37af9538c25db02289b411925
+size 8520

runs/Sep01_13-22-18_dsw-83959-5f9bd48d7d-89klm/events.out.tfevents.1725168155.dsw-83959-5f9bd48d7d-89klm.2984305.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f882d66ba57084631fbe8812724242d3abe4acdf9ce79c7d0f398e6e3bc184c
+size 8520

runs/Sep01_13-27-40_dsw-83959-5f9bd48d7d-89klm/events.out.tfevents.1725168480.dsw-83959-5f9bd48d7d-89klm.2986770.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:276f0d4a167d4b16f52b6f128bf540ba9b63faf87e05d0caab0a9669dc075dbe
+size 8520

runs/Sep01_13-27-40_dsw-83959-5f9bd48d7d-89klm/events.out.tfevents.1725168654.dsw-83959-5f9bd48d7d-89klm.2986770.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e57a0908320ceed68034f038cda64c38d6956f15a972f8c33f3b77f75e412b2d
+size 354

runs/Sep01_13-40-47_dsw-83959-5f9bd48d7d-89klm/events.out.tfevents.1725169266.dsw-83959-5f9bd48d7d-89klm.2992860.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d09cb7d8d076a4a10cb06925d28f0527910089be48b37243114fde454e1d1a03
+size 8520

runs/Sep01_13-40-47_dsw-83959-5f9bd48d7d-89klm/events.out.tfevents.1725169510.dsw-83959-5f9bd48d7d-89klm.2992860.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:042f860a428095d8bce1975d7326f0b956c047ac7177f30a56a3440f59544a3a
+size 354

runs/Sep02_14-55-48_dsw-83959-5f9bd48d7d-89klm/events.out.tfevents.1725260171.dsw-83959-5f9bd48d7d-89klm.3489225.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4de0e54345339f9e680a79a60cf68eecd9c5a0f2938f6164cfd866df778763d9
+size 8397

runs/Sep02_14-55-48_dsw-83959-5f9bd48d7d-89klm/events.out.tfevents.1725260414.dsw-83959-5f9bd48d7d-89klm.3489225.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:825edda66163b92ab0f388e44cf7d052ccd10c838d38a68f969188b979b434dc
+size 354

runs/Sep02_15-01-36_dsw-83959-5f9bd48d7d-89klm/events.out.tfevents.1725260523.dsw-83959-5f9bd48d7d-89klm.3493333.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae54ac0e73940dfe3f7d02b7144133320bd571050e110e746370d2e13459e431
+size 8397

runs/Sep02_15-01-36_dsw-83959-5f9bd48d7d-89klm/events.out.tfevents.1725260783.dsw-83959-5f9bd48d7d-89klm.3493333.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe9b3776401687c668c26a690f522fd73da5d669643e665f1f2bbcfbf59abfd4
+size 354

runs/Sep02_15-12-15_dsw-83959-5f9bd48d7d-89klm/events.out.tfevents.1725261155.dsw-83959-5f9bd48d7d-89klm.3498880.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcefcadf980901da21301188c2b2fb84b29641765fced77f8f325b8e83542247
+size 8397

runs/Sep02_15-17-02_dsw-83959-5f9bd48d7d-89klm/events.out.tfevents.1725261590.dsw-83959-5f9bd48d7d-89klm.3500834.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e323f227993f83987e9410d993534ce21a23388170125d958b80b0566876978
+size 8375

runs/Sep02_15-29-51_dsw-83959-5f9bd48d7d-89klm/events.out.tfevents.1725262408.dsw-83959-5f9bd48d7d-89klm.3506248.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ab107b9407e1c223d6aede1b1340539a41f9d2b9a229b268aa6c370594423fa
+size 8380

runs/Sep02_15-29-51_dsw-83959-5f9bd48d7d-89klm/events.out.tfevents.1725262666.dsw-83959-5f9bd48d7d-89klm.3506248.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:189221f412a7b8935a422267bdc0f9f44956a55fddd2a638514da9d753cbe82f
+size 354

runs/Sep02_15-39-28_dsw-83959-5f9bd48d7d-89klm/events.out.tfevents.1725262788.dsw-83959-5f9bd48d7d-89klm.3511533.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c5960dcdfe8ed3986114ca01440bd73be2299b56338fbb8fd582bee547eb7eb
+size 8375

runs/Sep02_15-39-28_dsw-83959-5f9bd48d7d-89klm/events.out.tfevents.1725262931.dsw-83959-5f9bd48d7d-89klm.3511533.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a33da9717bebc5d7d32d38e3be3dcdadf061180f46b35ee86f527eaef245b786
+size 354

runs/Sep02_15-51-19_dsw-83959-5f9bd48d7d-89klm/events.out.tfevents.1725263663.dsw-83959-5f9bd48d7d-89klm.3522427.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f4d24899d5075f2e6d70aac06e9bf7600396dc15c35894a3756c10976e2a9ef
+size 8336

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|eot_id|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.08154943934760449,
+    "total_flos": 124335445598208.0,
+    "train_loss": 1.6808662414550781,
+    "train_runtime": 109.4363,
+    "train_samples_per_second": 0.731,
+    "train_steps_per_second": 0.091
+}

trainer_log.jsonl

@@ -0,0 +1,12 @@
+{"current_steps": 1, "total_steps": 10, "eval_loss": 2.0249228477478027, "epoch": 0.00815494393476045, "percentage": 10.0, "elapsed_time": "0:00:09", "remaining_time": "0:01:28"}
+{"current_steps": 2, "total_steps": 10, "eval_loss": 2.0154640674591064, "epoch": 0.0163098878695209, "percentage": 20.0, "elapsed_time": "0:00:20", "remaining_time": "0:01:21"}
+{"current_steps": 3, "total_steps": 10, "eval_loss": 1.9926271438598633, "epoch": 0.024464831804281346, "percentage": 30.0, "elapsed_time": "0:00:30", "remaining_time": "0:01:11"}
+{"current_steps": 4, "total_steps": 10, "eval_loss": 1.9593819379806519, "epoch": 0.0326197757390418, "percentage": 40.0, "elapsed_time": "0:00:41", "remaining_time": "0:01:01"}
+{"current_steps": 5, "total_steps": 10, "eval_loss": 1.919368863105774, "epoch": 0.040774719673802244, "percentage": 50.0, "elapsed_time": "0:00:51", "remaining_time": "0:00:51"}
+{"current_steps": 6, "total_steps": 10, "eval_loss": 1.8850003480911255, "epoch": 0.04892966360856269, "percentage": 60.0, "elapsed_time": "0:01:02", "remaining_time": "0:00:41"}
+{"current_steps": 7, "total_steps": 10, "eval_loss": 1.8630123138427734, "epoch": 0.05708460754332314, "percentage": 70.0, "elapsed_time": "0:01:12", "remaining_time": "0:00:31"}
+{"current_steps": 8, "total_steps": 10, "eval_loss": 1.849714756011963, "epoch": 0.0652395514780836, "percentage": 80.0, "elapsed_time": "0:01:23", "remaining_time": "0:00:20"}
+{"current_steps": 9, "total_steps": 10, "eval_loss": 1.8416643142700195, "epoch": 0.07339449541284404, "percentage": 90.0, "elapsed_time": "0:01:33", "remaining_time": "0:00:10"}
+{"current_steps": 10, "total_steps": 10, "loss": 1.6809, "learning_rate": 0.0, "epoch": 0.08154943934760449, "percentage": 100.0, "elapsed_time": "0:01:37", "remaining_time": "0:00:00"}
+{"current_steps": 10, "total_steps": 10, "eval_loss": 1.8423653841018677, "epoch": 0.08154943934760449, "percentage": 100.0, "elapsed_time": "0:01:43", "remaining_time": "0:00:00"}
+{"current_steps": 10, "total_steps": 10, "epoch": 0.08154943934760449, "percentage": 100.0, "elapsed_time": "0:01:45", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.08154943934760449,
+  "eval_steps": 1,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00815494393476045,
+      "eval_loss": 2.0249228477478027,
+      "eval_runtime": 6.8992,
+      "eval_samples_per_second": 15.944,
+      "eval_steps_per_second": 15.944,
+      "step": 1
+    },
+    {
+      "epoch": 0.0163098878695209,
+      "eval_loss": 2.0154640674591064,
+      "eval_runtime": 6.8384,
+      "eval_samples_per_second": 16.086,
+      "eval_steps_per_second": 16.086,
+      "step": 2
+    },
+    {
+      "epoch": 0.024464831804281346,
+      "eval_loss": 1.9926271438598633,
+      "eval_runtime": 6.8066,
+      "eval_samples_per_second": 16.161,
+      "eval_steps_per_second": 16.161,
+      "step": 3
+    },
+    {
+      "epoch": 0.0326197757390418,
+      "eval_loss": 1.9593819379806519,
+      "eval_runtime": 6.825,
+      "eval_samples_per_second": 16.117,
+      "eval_steps_per_second": 16.117,
+      "step": 4
+    },
+    {
+      "epoch": 0.040774719673802244,
+      "eval_loss": 1.919368863105774,
+      "eval_runtime": 6.7341,
+      "eval_samples_per_second": 16.335,
+      "eval_steps_per_second": 16.335,
+      "step": 5
+    },
+    {
+      "epoch": 0.04892966360856269,
+      "eval_loss": 1.8850003480911255,
+      "eval_runtime": 6.9546,
+      "eval_samples_per_second": 15.817,
+      "eval_steps_per_second": 15.817,
+      "step": 6
+    },
+    {
+      "epoch": 0.05708460754332314,
+      "eval_loss": 1.8630123138427734,
+      "eval_runtime": 6.5806,
+      "eval_samples_per_second": 16.716,
+      "eval_steps_per_second": 16.716,
+      "step": 7
+    },
+    {
+      "epoch": 0.0652395514780836,
+      "eval_loss": 1.849714756011963,
+      "eval_runtime": 6.796,
+      "eval_samples_per_second": 16.186,
+      "eval_steps_per_second": 16.186,
+      "step": 8
+    },
+    {
+      "epoch": 0.07339449541284404,
+      "eval_loss": 1.8416643142700195,
+      "eval_runtime": 6.7749,
+      "eval_samples_per_second": 16.236,
+      "eval_steps_per_second": 16.236,
+      "step": 9
+    },
+    {
+      "epoch": 0.08154943934760449,
+      "grad_norm": 2.2355353832244873,
+      "learning_rate": 0.0,
+      "loss": 1.6809,
+      "step": 10
+    },
+    {
+      "epoch": 0.08154943934760449,
+      "eval_loss": 1.8393741846084595,
+      "eval_runtime": 6.8739,
+      "eval_samples_per_second": 16.003,
+      "eval_steps_per_second": 16.003,
+      "step": 10
+    },
+    {
+      "epoch": 0.08154943934760449,
+      "step": 10,
+      "total_flos": 124335445598208.0,
+      "train_loss": 1.6808662414550781,
+      "train_runtime": 109.4363,
+      "train_samples_per_second": 0.731,
+      "train_steps_per_second": 0.091
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 10,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 124335445598208.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25089c0b7075d15d5b5a3525aaa9eed1438c9b00ad117d28a388d7a2aee836d1
+size 5368