Upload 11 files

README.md

@@ -0,0 +1,202 @@
+---
+base_model: GritLM/GritLM-7B
+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 0.11.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "GritLM/GritLM-7B",
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "k_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:aeff1c5e572b3b0887453461e55481d8dee3887ee15ddf8fd7d762d9ce7ab3e0
+size 671149168

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "GritLM/GritLM-7B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoModel": "GritLM/GritLM-7B--modeling_gritlm7b.MistralModel",
+    "AutoModelForCausalLM": "GritLM/GritLM-7B--modeling_gritlm7b.MistralForCausalLM",
+    "AutoModelForSequenceClassification": "GritLM/GritLM-7B--modeling_gritlm7b.MistralForSequenceClassification"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "vocab_size": 32000
+}

dataset_num_samples.json

@@ -0,0 +1 @@
+{"embedding.jsonl": 57424, "generative.jsonl": 49759}

non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60fb82c3660319e6d0b239950b20c28181e97f1ade117dc0660b40e2ad94a89b
+size 912

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "add_bos_token": true,
+  "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": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_length": 2048,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<s>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,441 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 28712,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01741432153803288,
+      "grad_norm": 9.577305793762207,
+      "learning_rate": 1.160092807424594e-05,
+      "loss": 3.1831,
+      "step": 500
+    },
+    {
+      "epoch": 0.03482864307606576,
+      "grad_norm": 12.14001178741455,
+      "learning_rate": 1.9900897666068224e-05,
+      "loss": 2.7736,
+      "step": 1000
+    },
+    {
+      "epoch": 0.052242964614098636,
+      "grad_norm": 13.129646301269531,
+      "learning_rate": 1.9541831238779175e-05,
+      "loss": 2.6251,
+      "step": 1500
+    },
+    {
+      "epoch": 0.06965728615213151,
+      "grad_norm": 13.319927215576172,
+      "learning_rate": 1.9182764811490127e-05,
+      "loss": 2.685,
+      "step": 2000
+    },
+    {
+      "epoch": 0.0870716076901644,
+      "grad_norm": 9.90979290008545,
+      "learning_rate": 1.882369838420108e-05,
+      "loss": 2.4835,
+      "step": 2500
+    },
+    {
+      "epoch": 0.10448592922819727,
+      "grad_norm": 7.106535911560059,
+      "learning_rate": 1.846463195691203e-05,
+      "loss": 2.4759,
+      "step": 3000
+    },
+    {
+      "epoch": 0.12190025076623015,
+      "grad_norm": 11.579163551330566,
+      "learning_rate": 1.8105565529622982e-05,
+      "loss": 2.4615,
+      "step": 3500
+    },
+    {
+      "epoch": 0.13931457230426303,
+      "grad_norm": 8.479988098144531,
+      "learning_rate": 1.7746499102333934e-05,
+      "loss": 2.5471,
+      "step": 4000
+    },
+    {
+      "epoch": 0.1567288938422959,
+      "grad_norm": 6.432307720184326,
+      "learning_rate": 1.7387432675044886e-05,
+      "loss": 2.4572,
+      "step": 4500
+    },
+    {
+      "epoch": 0.1741432153803288,
+      "grad_norm": 10.89651870727539,
+      "learning_rate": 1.7028366247755838e-05,
+      "loss": 2.4725,
+      "step": 5000
+    },
+    {
+      "epoch": 0.19155753691836166,
+      "grad_norm": 8.298269271850586,
+      "learning_rate": 1.6669299820466786e-05,
+      "loss": 2.4184,
+      "step": 5500
+    },
+    {
+      "epoch": 0.20897185845639454,
+      "grad_norm": 3.4620511531829834,
+      "learning_rate": 1.6310233393177738e-05,
+      "loss": 2.3301,
+      "step": 6000
+    },
+    {
+      "epoch": 0.22638617999442742,
+      "grad_norm": 5.399957180023193,
+      "learning_rate": 1.5951166965888693e-05,
+      "loss": 2.4545,
+      "step": 6500
+    },
+    {
+      "epoch": 0.2438005015324603,
+      "grad_norm": 8.993759155273438,
+      "learning_rate": 1.559210053859964e-05,
+      "loss": 2.3337,
+      "step": 7000
+    },
+    {
+      "epoch": 0.26121482307049315,
+      "grad_norm": 3.5916497707366943,
+      "learning_rate": 1.5233034111310595e-05,
+      "loss": 2.4419,
+      "step": 7500
+    },
+    {
+      "epoch": 0.27862914460852606,
+      "grad_norm": 8.653467178344727,
+      "learning_rate": 1.4873967684021545e-05,
+      "loss": 2.3755,
+      "step": 8000
+    },
+    {
+      "epoch": 0.2960434661465589,
+      "grad_norm": 6.519212245941162,
+      "learning_rate": 1.4514901256732496e-05,
+      "loss": 2.3601,
+      "step": 8500
+    },
+    {
+      "epoch": 0.3134577876845918,
+      "grad_norm": 8.016100883483887,
+      "learning_rate": 1.4155834829443448e-05,
+      "loss": 2.2321,
+      "step": 9000
+    },
+    {
+      "epoch": 0.33087210922262467,
+      "grad_norm": 16.313932418823242,
+      "learning_rate": 1.37967684021544e-05,
+      "loss": 2.3488,
+      "step": 9500
+    },
+    {
+      "epoch": 0.3482864307606576,
+      "grad_norm": 28.44437026977539,
+      "learning_rate": 1.3437701974865352e-05,
+      "loss": 2.3364,
+      "step": 10000
+    },
+    {
+      "epoch": 0.3657007522986904,
+      "grad_norm": 3.504075527191162,
+      "learning_rate": 1.3078635547576302e-05,
+      "loss": 2.2997,
+      "step": 10500
+    },
+    {
+      "epoch": 0.38311507383672333,
+      "grad_norm": 11.785683631896973,
+      "learning_rate": 1.2719569120287253e-05,
+      "loss": 2.3374,
+      "step": 11000
+    },
+    {
+      "epoch": 0.4005293953747562,
+      "grad_norm": 9.7432861328125,
+      "learning_rate": 1.2360502692998207e-05,
+      "loss": 2.266,
+      "step": 11500
+    },
+    {
+      "epoch": 0.4179437169127891,
+      "grad_norm": 8.663525581359863,
+      "learning_rate": 1.2001436265709157e-05,
+      "loss": 2.2722,
+      "step": 12000
+    },
+    {
+      "epoch": 0.43535803845082194,
+      "grad_norm": 8.145735740661621,
+      "learning_rate": 1.1642369838420109e-05,
+      "loss": 2.3819,
+      "step": 12500
+    },
+    {
+      "epoch": 0.45277235998885484,
+      "grad_norm": 6.875612258911133,
+      "learning_rate": 1.1283303411131059e-05,
+      "loss": 2.3541,
+      "step": 13000
+    },
+    {
+      "epoch": 0.4701866815268877,
+      "grad_norm": 4.973703861236572,
+      "learning_rate": 1.0924236983842012e-05,
+      "loss": 2.3205,
+      "step": 13500
+    },
+    {
+      "epoch": 0.4876010030649206,
+      "grad_norm": 8.985243797302246,
+      "learning_rate": 1.0565170556552964e-05,
+      "loss": 2.3118,
+      "step": 14000
+    },
+    {
+      "epoch": 0.5050153246029535,
+      "grad_norm": 3.0293591022491455,
+      "learning_rate": 1.0206104129263914e-05,
+      "loss": 2.2947,
+      "step": 14500
+    },
+    {
+      "epoch": 0.5224296461409863,
+      "grad_norm": 11.419426918029785,
+      "learning_rate": 9.847037701974866e-06,
+      "loss": 2.2276,
+      "step": 15000
+    },
+    {
+      "epoch": 0.5398439676790192,
+      "grad_norm": 9.195966720581055,
+      "learning_rate": 9.487971274685817e-06,
+      "loss": 2.333,
+      "step": 15500
+    },
+    {
+      "epoch": 0.5572582892170521,
+      "grad_norm": 7.067108631134033,
+      "learning_rate": 9.128904847396769e-06,
+      "loss": 2.3562,
+      "step": 16000
+    },
+    {
+      "epoch": 0.574672610755085,
+      "grad_norm": 5.443989276885986,
+      "learning_rate": 8.769838420107721e-06,
+      "loss": 2.3378,
+      "step": 16500
+    },
+    {
+      "epoch": 0.5920869322931178,
+      "grad_norm": 10.031864166259766,
+      "learning_rate": 8.410771992818673e-06,
+      "loss": 2.3233,
+      "step": 17000
+    },
+    {
+      "epoch": 0.6095012538311507,
+      "grad_norm": 7.518855094909668,
+      "learning_rate": 8.051705565529624e-06,
+      "loss": 2.2783,
+      "step": 17500
+    },
+    {
+      "epoch": 0.6269155753691836,
+      "grad_norm": 8.214040756225586,
+      "learning_rate": 7.692639138240574e-06,
+      "loss": 2.1764,
+      "step": 18000
+    },
+    {
+      "epoch": 0.6443298969072165,
+      "grad_norm": 10.006634712219238,
+      "learning_rate": 7.333572710951526e-06,
+      "loss": 2.3743,
+      "step": 18500
+    },
+    {
+      "epoch": 0.6617442184452493,
+      "grad_norm": 8.866910934448242,
+      "learning_rate": 6.974506283662478e-06,
+      "loss": 2.3044,
+      "step": 19000
+    },
+    {
+      "epoch": 0.6791585399832822,
+      "grad_norm": 5.549246311187744,
+      "learning_rate": 6.6154398563734305e-06,
+      "loss": 2.2693,
+      "step": 19500
+    },
+    {
+      "epoch": 0.6965728615213151,
+      "grad_norm": 4.0343194007873535,
+      "learning_rate": 6.2563734290843814e-06,
+      "loss": 2.1788,
+      "step": 20000
+    },
+    {
+      "epoch": 0.713987183059348,
+      "grad_norm": 6.325515270233154,
+      "learning_rate": 5.897307001795332e-06,
+      "loss": 2.2589,
+      "step": 20500
+    },
+    {
+      "epoch": 0.7314015045973808,
+      "grad_norm": 5.234256267547607,
+      "learning_rate": 5.538240574506284e-06,
+      "loss": 2.1563,
+      "step": 21000
+    },
+    {
+      "epoch": 0.7488158261354138,
+      "grad_norm": 8.443244934082031,
+      "learning_rate": 5.179174147217235e-06,
+      "loss": 2.2293,
+      "step": 21500
+    },
+    {
+      "epoch": 0.7662301476734467,
+      "grad_norm": 3.8823511600494385,
+      "learning_rate": 4.820107719928187e-06,
+      "loss": 2.2258,
+      "step": 22000
+    },
+    {
+      "epoch": 0.7836444692114796,
+      "grad_norm": 6.5127034187316895,
+      "learning_rate": 4.4610412926391385e-06,
+      "loss": 2.1272,
+      "step": 22500
+    },
+    {
+      "epoch": 0.8010587907495124,
+      "grad_norm": 12.666552543640137,
+      "learning_rate": 4.10197486535009e-06,
+      "loss": 2.264,
+      "step": 23000
+    },
+    {
+      "epoch": 0.8184731122875453,
+      "grad_norm": 5.594479084014893,
+      "learning_rate": 3.7429084380610415e-06,
+      "loss": 2.2525,
+      "step": 23500
+    },
+    {
+      "epoch": 0.8358874338255782,
+      "grad_norm": 5.7376179695129395,
+      "learning_rate": 3.3838420107719933e-06,
+      "loss": 2.3071,
+      "step": 24000
+    },
+    {
+      "epoch": 0.8533017553636111,
+      "grad_norm": 12.593650817871094,
+      "learning_rate": 3.0247755834829446e-06,
+      "loss": 2.2623,
+      "step": 24500
+    },
+    {
+      "epoch": 0.8707160769016439,
+      "grad_norm": 10.175933837890625,
+      "learning_rate": 2.6657091561938963e-06,
+      "loss": 2.2561,
+      "step": 25000
+    },
+    {
+      "epoch": 0.8881303984396768,
+      "grad_norm": 11.089727401733398,
+      "learning_rate": 2.3066427289048477e-06,
+      "loss": 2.2185,
+      "step": 25500
+    },
+    {
+      "epoch": 0.9055447199777097,
+      "grad_norm": 7.090406894683838,
+      "learning_rate": 1.947576301615799e-06,
+      "loss": 2.204,
+      "step": 26000
+    },
+    {
+      "epoch": 0.9229590415157426,
+      "grad_norm": 16.22230339050293,
+      "learning_rate": 1.5885098743267505e-06,
+      "loss": 2.2285,
+      "step": 26500
+    },
+    {
+      "epoch": 0.9403733630537754,
+      "grad_norm": 4.419189929962158,
+      "learning_rate": 1.229443447037702e-06,
+      "loss": 2.2739,
+      "step": 27000
+    },
+    {
+      "epoch": 0.9577876845918083,
+      "grad_norm": 12.452730178833008,
+      "learning_rate": 8.703770197486536e-07,
+      "loss": 2.1793,
+      "step": 27500
+    },
+    {
+      "epoch": 0.9752020061298412,
+      "grad_norm": 19.379770278930664,
+      "learning_rate": 5.11310592459605e-07,
+      "loss": 2.1586,
+      "step": 28000
+    },
+    {
+      "epoch": 0.9926163276678741,
+      "grad_norm": 19.553585052490234,
+      "learning_rate": 1.5224416517055656e-07,
+      "loss": 2.1482,
+      "step": 28500
+    },
+    {
+      "epoch": 1.0,
+      "step": 28712,
+      "total_flos": 0.0,
+      "train_loss": 2.343143721416024,
+      "train_runtime": 98844.7919,
+      "train_samples_per_second": 0.581,
+      "train_steps_per_second": 0.29
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 28712,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500.0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}