Upload 13 files

README.md

@@ -1,3 +1,202 @@
----
-license: mit
----
+---
+base_model: microsoft/Phi-3-mini-4k-instruct
+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 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-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": 1256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "self_attn.qkv_proj",
+    "mlp.gate_up_proj",
+    "mlp.down_proj",
+    "self_attn.o_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 sha256:309e838021b2f8ed4635d0fd4c582943c12ac85011b033fb8941ea4c8aa100e8
+size 1610648152

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:733a936d226f5d2a5cd6fb25d09c1e9a3c9869c92fcc94d65b071e7ea0d7e164
+size 3221442042

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12644eaca12cefa9de10c7d10a65fb86bf17b925272e83bf07d6c4e51662aba8
+size 14180

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beaef3d506ba92fa883a0eaf9af69379574c45820fdd4ec88bd72d867cbeb367
+size 1064

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,131 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 50,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,383 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.054945054945054944,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001098901098901099,
+      "grad_norm": 4.387043476104736,
+      "learning_rate": 5.4945054945054946e-08,
+      "loss": 0.8831,
+      "step": 20
+    },
+    {
+      "epoch": 0.002197802197802198,
+      "grad_norm": 3.8907365798950195,
+      "learning_rate": 1.0989010989010989e-07,
+      "loss": 0.8866,
+      "step": 40
+    },
+    {
+      "epoch": 0.0032967032967032967,
+      "grad_norm": 3.2492220401763916,
+      "learning_rate": 1.6483516483516484e-07,
+      "loss": 0.8454,
+      "step": 60
+    },
+    {
+      "epoch": 0.004395604395604396,
+      "grad_norm": 3.0804762840270996,
+      "learning_rate": 2.1978021978021978e-07,
+      "loss": 0.8267,
+      "step": 80
+    },
+    {
+      "epoch": 0.005494505494505495,
+      "grad_norm": 2.037411689758301,
+      "learning_rate": 2.7472527472527475e-07,
+      "loss": 0.7371,
+      "step": 100
+    },
+    {
+      "epoch": 0.006593406593406593,
+      "grad_norm": 1.5473365783691406,
+      "learning_rate": 3.296703296703297e-07,
+      "loss": 0.6765,
+      "step": 120
+    },
+    {
+      "epoch": 0.007692307692307693,
+      "grad_norm": 1.1062999963760376,
+      "learning_rate": 3.846153846153847e-07,
+      "loss": 0.5946,
+      "step": 140
+    },
+    {
+      "epoch": 0.008791208791208791,
+      "grad_norm": 1.363224744796753,
+      "learning_rate": 4.3956043956043957e-07,
+      "loss": 0.5402,
+      "step": 160
+    },
+    {
+      "epoch": 0.00989010989010989,
+      "grad_norm": 0.9122905731201172,
+      "learning_rate": 4.945054945054946e-07,
+      "loss": 0.464,
+      "step": 180
+    },
+    {
+      "epoch": 0.01098901098901099,
+      "grad_norm": 0.676691472530365,
+      "learning_rate": 5.494505494505495e-07,
+      "loss": 0.4041,
+      "step": 200
+    },
+    {
+      "epoch": 0.012087912087912088,
+      "grad_norm": 0.5926629900932312,
+      "learning_rate": 6.043956043956044e-07,
+      "loss": 0.3727,
+      "step": 220
+    },
+    {
+      "epoch": 0.013186813186813187,
+      "grad_norm": 0.635013997554779,
+      "learning_rate": 6.593406593406594e-07,
+      "loss": 0.3609,
+      "step": 240
+    },
+    {
+      "epoch": 0.014285714285714285,
+      "grad_norm": 0.5836207270622253,
+      "learning_rate": 7.142857142857143e-07,
+      "loss": 0.3331,
+      "step": 260
+    },
+    {
+      "epoch": 0.015384615384615385,
+      "grad_norm": 0.548773467540741,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 0.3201,
+      "step": 280
+    },
+    {
+      "epoch": 0.016483516483516484,
+      "grad_norm": 0.5962342023849487,
+      "learning_rate": 8.241758241758242e-07,
+      "loss": 0.2993,
+      "step": 300
+    },
+    {
+      "epoch": 0.017582417582417582,
+      "grad_norm": 0.5346819162368774,
+      "learning_rate": 8.791208791208791e-07,
+      "loss": 0.2792,
+      "step": 320
+    },
+    {
+      "epoch": 0.01868131868131868,
+      "grad_norm": 0.569210946559906,
+      "learning_rate": 9.340659340659341e-07,
+      "loss": 0.273,
+      "step": 340
+    },
+    {
+      "epoch": 0.01978021978021978,
+      "grad_norm": 0.5142342448234558,
+      "learning_rate": 9.890109890109891e-07,
+      "loss": 0.2621,
+      "step": 360
+    },
+    {
+      "epoch": 0.020879120879120878,
+      "grad_norm": 0.5067290663719177,
+      "learning_rate": 1.043956043956044e-06,
+      "loss": 0.2641,
+      "step": 380
+    },
+    {
+      "epoch": 0.02197802197802198,
+      "grad_norm": 0.44699764251708984,
+      "learning_rate": 1.098901098901099e-06,
+      "loss": 0.2553,
+      "step": 400
+    },
+    {
+      "epoch": 0.023076923076923078,
+      "grad_norm": 0.5279501080513,
+      "learning_rate": 1.153846153846154e-06,
+      "loss": 0.2488,
+      "step": 420
+    },
+    {
+      "epoch": 0.024175824175824177,
+      "grad_norm": 0.5009133219718933,
+      "learning_rate": 1.2087912087912089e-06,
+      "loss": 0.2499,
+      "step": 440
+    },
+    {
+      "epoch": 0.025274725274725275,
+      "grad_norm": 0.5484806895256042,
+      "learning_rate": 1.263736263736264e-06,
+      "loss": 0.2485,
+      "step": 460
+    },
+    {
+      "epoch": 0.026373626373626374,
+      "grad_norm": 0.44114941358566284,
+      "learning_rate": 1.3186813186813187e-06,
+      "loss": 0.2499,
+      "step": 480
+    },
+    {
+      "epoch": 0.027472527472527472,
+      "grad_norm": 0.5557438731193542,
+      "learning_rate": 1.3736263736263736e-06,
+      "loss": 0.2455,
+      "step": 500
+    },
+    {
+      "epoch": 0.02857142857142857,
+      "grad_norm": 0.5493007898330688,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 0.2396,
+      "step": 520
+    },
+    {
+      "epoch": 0.02967032967032967,
+      "grad_norm": 0.5284810662269592,
+      "learning_rate": 1.4835164835164835e-06,
+      "loss": 0.2383,
+      "step": 540
+    },
+    {
+      "epoch": 0.03076923076923077,
+      "grad_norm": 0.5073139667510986,
+      "learning_rate": 1.5384615384615387e-06,
+      "loss": 0.2389,
+      "step": 560
+    },
+    {
+      "epoch": 0.031868131868131866,
+      "grad_norm": 0.5186975002288818,
+      "learning_rate": 1.5934065934065933e-06,
+      "loss": 0.2372,
+      "step": 580
+    },
+    {
+      "epoch": 0.03296703296703297,
+      "grad_norm": 0.5739095211029053,
+      "learning_rate": 1.6483516483516484e-06,
+      "loss": 0.2358,
+      "step": 600
+    },
+    {
+      "epoch": 0.03406593406593406,
+      "grad_norm": 0.5144438147544861,
+      "learning_rate": 1.7032967032967032e-06,
+      "loss": 0.2319,
+      "step": 620
+    },
+    {
+      "epoch": 0.035164835164835165,
+      "grad_norm": 0.4886190593242645,
+      "learning_rate": 1.7582417582417583e-06,
+      "loss": 0.2297,
+      "step": 640
+    },
+    {
+      "epoch": 0.03626373626373627,
+      "grad_norm": 0.6088211536407471,
+      "learning_rate": 1.8131868131868135e-06,
+      "loss": 0.2356,
+      "step": 660
+    },
+    {
+      "epoch": 0.03736263736263736,
+      "grad_norm": 0.4712292551994324,
+      "learning_rate": 1.8681318681318681e-06,
+      "loss": 0.2334,
+      "step": 680
+    },
+    {
+      "epoch": 0.038461538461538464,
+      "grad_norm": 0.5712177157402039,
+      "learning_rate": 1.9230769230769234e-06,
+      "loss": 0.2302,
+      "step": 700
+    },
+    {
+      "epoch": 0.03956043956043956,
+      "grad_norm": 0.5427699089050293,
+      "learning_rate": 1.9780219780219782e-06,
+      "loss": 0.2248,
+      "step": 720
+    },
+    {
+      "epoch": 0.04065934065934066,
+      "grad_norm": 0.6642568707466125,
+      "learning_rate": 2.032967032967033e-06,
+      "loss": 0.2291,
+      "step": 740
+    },
+    {
+      "epoch": 0.041758241758241756,
+      "grad_norm": 0.5859007239341736,
+      "learning_rate": 2.087912087912088e-06,
+      "loss": 0.227,
+      "step": 760
+    },
+    {
+      "epoch": 0.04285714285714286,
+      "grad_norm": 0.6507712602615356,
+      "learning_rate": 2.142857142857143e-06,
+      "loss": 0.227,
+      "step": 780
+    },
+    {
+      "epoch": 0.04395604395604396,
+      "grad_norm": 0.5675429105758667,
+      "learning_rate": 2.197802197802198e-06,
+      "loss": 0.2259,
+      "step": 800
+    },
+    {
+      "epoch": 0.045054945054945054,
+      "grad_norm": 0.6223055124282837,
+      "learning_rate": 2.252747252747253e-06,
+      "loss": 0.2283,
+      "step": 820
+    },
+    {
+      "epoch": 0.046153846153846156,
+      "grad_norm": 0.5504657030105591,
+      "learning_rate": 2.307692307692308e-06,
+      "loss": 0.2246,
+      "step": 840
+    },
+    {
+      "epoch": 0.04725274725274725,
+      "grad_norm": 0.48020097613334656,
+      "learning_rate": 2.3626373626373625e-06,
+      "loss": 0.225,
+      "step": 860
+    },
+    {
+      "epoch": 0.04835164835164835,
+      "grad_norm": 0.4979713261127472,
+      "learning_rate": 2.4175824175824177e-06,
+      "loss": 0.2212,
+      "step": 880
+    },
+    {
+      "epoch": 0.04945054945054945,
+      "grad_norm": 0.49497634172439575,
+      "learning_rate": 2.4725274725274726e-06,
+      "loss": 0.2234,
+      "step": 900
+    },
+    {
+      "epoch": 0.05054945054945055,
+      "grad_norm": 0.6207996010780334,
+      "learning_rate": 2.527472527472528e-06,
+      "loss": 0.2256,
+      "step": 920
+    },
+    {
+      "epoch": 0.051648351648351645,
+      "grad_norm": 0.530981719493866,
+      "learning_rate": 2.5824175824175822e-06,
+      "loss": 0.2231,
+      "step": 940
+    },
+    {
+      "epoch": 0.05274725274725275,
+      "grad_norm": 0.5495067834854126,
+      "learning_rate": 2.6373626373626375e-06,
+      "loss": 0.223,
+      "step": 960
+    },
+    {
+      "epoch": 0.05384615384615385,
+      "grad_norm": 0.5651763081550598,
+      "learning_rate": 2.6923076923076928e-06,
+      "loss": 0.2213,
+      "step": 980
+    },
+    {
+      "epoch": 0.054945054945054944,
+      "grad_norm": 0.553247332572937,
+      "learning_rate": 2.747252747252747e-06,
+      "loss": 0.2219,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 91000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.336356548608e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8787a29840ad0c358bc3853201a32533acd957519c8f3899a5dc2396f6473ce6
+size 5432