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 +1,202 @@
+---
+base_model: Qwen/Qwen1.5-1.8B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-1.8B",
+  "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": 8,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "gate_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:ba1ca5408e8af734262057456b8bbd1d7d754081c55e4603943225c115fd15f4
+size 15035264

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eccc1ecc8a61584980c28e575b9c96b5d8b51b76ebd24fb9c0aa6ed6c8ddb6b
+size 30264642

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d3b7102895eb0637b0cab516bd672f216b2bf79078a83eb301011a90444f44c
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c19d2f5fadc84f3ce6a4d5b503d22a5e6714dc6124098680aee2dcf53d4f0741
+size 1064

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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
+    }
+  },
+  "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 %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,350 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 11.94915254237288,
+  "eval_steps": 100,
+  "global_step": 216,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2711864406779661,
+      "grad_norm": 0.5330628156661987,
+      "learning_rate": 0.00039696155060244166,
+      "loss": 3.0018,
+      "step": 5
+    },
+    {
+      "epoch": 0.5423728813559322,
+      "grad_norm": 0.34631356596946716,
+      "learning_rate": 0.0003879385241571817,
+      "loss": 2.7414,
+      "step": 10
+    },
+    {
+      "epoch": 0.8135593220338984,
+      "grad_norm": 0.4716702997684479,
+      "learning_rate": 0.00037320508075688776,
+      "loss": 2.6142,
+      "step": 15
+    },
+    {
+      "epoch": 1.0949152542372882,
+      "grad_norm": 0.46511930227279663,
+      "learning_rate": 0.0003532088886237956,
+      "loss": 2.8757,
+      "step": 20
+    },
+    {
+      "epoch": 1.3661016949152542,
+      "grad_norm": 0.5249255895614624,
+      "learning_rate": 0.00032855752193730787,
+      "loss": 2.392,
+      "step": 25
+    },
+    {
+      "epoch": 1.6372881355932203,
+      "grad_norm": 0.5600208640098572,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 2.3346,
+      "step": 30
+    },
+    {
+      "epoch": 1.9084745762711863,
+      "grad_norm": 0.6260833144187927,
+      "learning_rate": 0.00026840402866513377,
+      "loss": 2.2452,
+      "step": 35
+    },
+    {
+      "epoch": 2.1898305084745764,
+      "grad_norm": 0.7083396911621094,
+      "learning_rate": 0.00023472963553338613,
+      "loss": 2.5452,
+      "step": 40
+    },
+    {
+      "epoch": 2.461016949152542,
+      "grad_norm": 0.5148910284042358,
+      "learning_rate": 0.0002,
+      "loss": 2.0905,
+      "step": 45
+    },
+    {
+      "epoch": 2.7322033898305085,
+      "grad_norm": 0.5956751108169556,
+      "learning_rate": 0.00016527036446661395,
+      "loss": 2.1029,
+      "step": 50
+    },
+    {
+      "epoch": 3.013559322033898,
+      "grad_norm": 1.3184939622879028,
+      "learning_rate": 0.00013159597133486628,
+      "loss": 2.3754,
+      "step": 55
+    },
+    {
+      "epoch": 3.2847457627118644,
+      "grad_norm": 0.6270354390144348,
+      "learning_rate": 0.00010000000000000005,
+      "loss": 2.0626,
+      "step": 60
+    },
+    {
+      "epoch": 3.5559322033898306,
+      "grad_norm": 0.6598231196403503,
+      "learning_rate": 7.144247806269213e-05,
+      "loss": 2.0278,
+      "step": 65
+    },
+    {
+      "epoch": 3.8271186440677964,
+      "grad_norm": 0.5732411742210388,
+      "learning_rate": 4.679111137620442e-05,
+      "loss": 1.9843,
+      "step": 70
+    },
+    {
+      "epoch": 4.1084745762711865,
+      "grad_norm": 0.6006195545196533,
+      "learning_rate": 2.679491924311226e-05,
+      "loss": 2.296,
+      "step": 75
+    },
+    {
+      "epoch": 4.379661016949153,
+      "grad_norm": 0.5978462100028992,
+      "learning_rate": 1.2061475842818338e-05,
+      "loss": 1.9672,
+      "step": 80
+    },
+    {
+      "epoch": 4.650847457627119,
+      "grad_norm": 0.5773534774780273,
+      "learning_rate": 3.0384493975583962e-06,
+      "loss": 1.9839,
+      "step": 85
+    },
+    {
+      "epoch": 4.922033898305084,
+      "grad_norm": 0.618421196937561,
+      "learning_rate": 0.0,
+      "loss": 1.9694,
+      "step": 90
+    },
+    {
+      "epoch": 5.271186440677966,
+      "grad_norm": 0.7557504773139954,
+      "learning_rate": 0.0001463654774478725,
+      "loss": 1.9701,
+      "step": 95
+    },
+    {
+      "epoch": 5.5423728813559325,
+      "grad_norm": 0.7439705729484558,
+      "learning_rate": 0.00012796445503905797,
+      "loss": 1.944,
+      "step": 100
+    },
+    {
+      "epoch": 5.5423728813559325,
+      "eval_loss": 2.1080985069274902,
+      "eval_runtime": 54.8392,
+      "eval_samples_per_second": 10.74,
+      "eval_steps_per_second": 1.349,
+      "step": 100
+    },
+    {
+      "epoch": 5.813559322033898,
+      "grad_norm": 0.866310179233551,
+      "learning_rate": 0.00011024016395990757,
+      "loss": 1.9449,
+      "step": 105
+    },
+    {
+      "epoch": 6.094915254237288,
+      "grad_norm": 0.7313957810401917,
+      "learning_rate": 9.33591134396618e-05,
+      "loss": 2.2185,
+      "step": 110
+    },
+    {
+      "epoch": 6.366101694915255,
+      "grad_norm": 0.7987199425697327,
+      "learning_rate": 7.747989096135944e-05,
+      "loss": 1.9012,
+      "step": 115
+    },
+    {
+      "epoch": 6.63728813559322,
+      "grad_norm": 0.7827264666557312,
+      "learning_rate": 6.27516724262533e-05,
+      "loss": 1.8952,
+      "step": 120
+    },
+    {
+      "epoch": 6.908474576271186,
+      "grad_norm": 0.8806806206703186,
+      "learning_rate": 4.931282073446786e-05,
+      "loss": 1.8705,
+      "step": 125
+    },
+    {
+      "epoch": 7.189830508474576,
+      "grad_norm": 0.7403010129928589,
+      "learning_rate": 3.72895859474065e-05,
+      "loss": 2.1358,
+      "step": 130
+    },
+    {
+      "epoch": 7.461016949152542,
+      "grad_norm": 0.744999349117279,
+      "learning_rate": 2.679491924311226e-05,
+      "loss": 1.831,
+      "step": 135
+    },
+    {
+      "epoch": 7.7322033898305085,
+      "grad_norm": 0.7374749183654785,
+      "learning_rate": 1.792741180677069e-05,
+      "loss": 1.8739,
+      "step": 140
+    },
+    {
+      "epoch": 8.013559322033899,
+      "grad_norm": 1.6001635789871216,
+      "learning_rate": 1.0770368624849948e-05,
+      "loss": 2.1764,
+      "step": 145
+    },
+    {
+      "epoch": 8.284745762711864,
+      "grad_norm": 0.7245858311653137,
+      "learning_rate": 5.391025884035239e-06,
+      "loss": 1.8174,
+      "step": 150
+    },
+    {
+      "epoch": 8.55593220338983,
+      "grad_norm": 0.6350526213645935,
+      "learning_rate": 1.8399193270309367e-06,
+      "loss": 1.8341,
+      "step": 155
+    },
+    {
+      "epoch": 8.827118644067797,
+      "grad_norm": 0.7198626399040222,
+      "learning_rate": 1.5040949915399172e-07,
+      "loss": 1.854,
+      "step": 160
+    },
+    {
+      "epoch": 9.162711864406779,
+      "grad_norm": 0.7952471971511841,
+      "learning_rate": 5.2544532637975206e-05,
+      "loss": 1.8478,
+      "step": 165
+    },
+    {
+      "epoch": 9.433898305084746,
+      "grad_norm": 0.8388130068778992,
+      "learning_rate": 4.311686701608486e-05,
+      "loss": 1.8267,
+      "step": 170
+    },
+    {
+      "epoch": 9.705084745762711,
+      "grad_norm": 0.7769240736961365,
+      "learning_rate": 3.451851177169789e-05,
+      "loss": 1.8362,
+      "step": 175
+    },
+    {
+      "epoch": 9.976271186440679,
+      "grad_norm": 0.8936498761177063,
+      "learning_rate": 2.679491924311226e-05,
+      "loss": 1.8369,
+      "step": 180
+    },
+    {
+      "epoch": 10.257627118644068,
+      "grad_norm": 0.7819103598594666,
+      "learning_rate": 1.998691762717577e-05,
+      "loss": 2.0798,
+      "step": 185
+    },
+    {
+      "epoch": 10.528813559322034,
+      "grad_norm": 0.8176268935203552,
+      "learning_rate": 1.4130495154635493e-05,
+      "loss": 1.8395,
+      "step": 190
+    },
+    {
+      "epoch": 10.8,
+      "grad_norm": 0.7900301814079285,
+      "learning_rate": 9.256609850354636e-06,
+      "loss": 1.7801,
+      "step": 195
+    },
+    {
+      "epoch": 11.08135593220339,
+      "grad_norm": 0.7704123258590698,
+      "learning_rate": 5.391025884035239e-06,
+      "loss": 2.1206,
+      "step": 200
+    },
+    {
+      "epoch": 11.08135593220339,
+      "eval_loss": 2.0445444583892822,
+      "eval_runtime": 53.6802,
+      "eval_samples_per_second": 10.972,
+      "eval_steps_per_second": 1.379,
+      "step": 200
+    },
+    {
+      "epoch": 11.352542372881356,
+      "grad_norm": 0.702042818069458,
+      "learning_rate": 2.554177376525191e-06,
+      "loss": 1.7821,
+      "step": 205
+    },
+    {
+      "epoch": 11.623728813559323,
+      "grad_norm": 0.7518762946128845,
+      "learning_rate": 7.61060381650891e-07,
+      "loss": 1.8043,
+      "step": 210
+    },
+    {
+      "epoch": 11.894915254237288,
+      "grad_norm": 0.7772343754768372,
+      "learning_rate": 2.1153614578506286e-08,
+      "loss": 1.8231,
+      "step": 215
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 216,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.5355128486546637e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a76554c43881870f52e330d389cbe69310077536721f2f2137acc2d698a914db
+size 5496