add model

README.md

@@ -1,4 +1,78 @@
-mistral 7b finetuned on curation-corpu
 ---
-license: mit
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- generated_from_trainer
+model-index:
+- name: qlora-out
+  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/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+# qlora-out
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2423
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.5123        | 0.01  | 1    | 1.5038          |
+| 1.3662        | 0.06  | 5    | 1.4103          |
+| 1.1836        | 0.11  | 10   | 1.3055          |
+| 1.2761        | 0.17  | 15   | 1.2810          |
+| 1.1779        | 0.22  | 20   | 1.2696          |
+| 1.1242        | 0.28  | 25   | 1.2642          |
+| 1.2414        | 0.33  | 30   | 1.2588          |
+| 1.1382        | 0.39  | 35   | 1.2555          |
+| 1.2094        | 0.45  | 40   | 1.2520          |
+| 1.1049        | 0.5   | 45   | 1.2504          |
+| 1.1709        | 0.56  | 50   | 1.2487          |
+| 1.0981        | 0.61  | 55   | 1.2463          |
+| 1.1902        | 0.67  | 60   | 1.2446          |
+| 1.1526        | 0.72  | 65   | 1.2446          |
+| 1.1319        | 0.78  | 70   | 1.2440          |
+| 1.1913        | 0.84  | 75   | 1.2430          |
+| 1.1875        | 0.89  | 80   | 1.2424          |
+| 1.1454        | 0.95  | 85   | 1.2423          |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.0.1+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bb626358ee09186105c032bf3f6ffd6106eceed582ef9adce9ab30530e440f5
+size 335705741

checkpoint-89/README.md

@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
+---
+
+# 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.0

checkpoint-89/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-89/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dabb64b2b9676fc7cf877e9237b6ce7d4e33dc0d31e3b43f65d66e7fe94add4
+size 335604696

checkpoint-89/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a45e0b0e670a6b3e62346ebd7c56a546b0c1841277a345e413fc624d79c09506
+size 168624287

checkpoint-89/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a73475f16f9a6f1784d28cd377e784fc0fc969c595e3e0ce6b3b0a05dcfc365
+size 14575

checkpoint-89/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48689e5a148444ef4ecee141f4ca0896dd03e488770e55606487d4085fc01001
+size 627

checkpoint-89/trainer_state.json

@@ -0,0 +1,697 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9916434540389972,
+  "eval_steps": 5,
+  "global_step": 89,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2e-05,
+      "loss": 1.5123,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "eval_loss": 1.5038223266601562,
+      "eval_runtime": 44.7062,
+      "eval_samples_per_second": 6.822,
+      "eval_steps_per_second": 3.422,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4e-05,
+      "loss": 1.491,
+      "step": 2
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6e-05,
+      "loss": 1.4859,
+      "step": 3
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8e-05,
+      "loss": 1.4147,
+      "step": 4
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0001,
+      "loss": 1.3662,
+      "step": 5
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 1.4103038311004639,
+      "eval_runtime": 44.789,
+      "eval_samples_per_second": 6.81,
+      "eval_steps_per_second": 3.416,
+      "step": 5
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00012,
+      "loss": 1.3399,
+      "step": 6
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00014,
+      "loss": 1.346,
+      "step": 7
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00016,
+      "loss": 1.3327,
+      "step": 8
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00018,
+      "loss": 1.3466,
+      "step": 9
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0002,
+      "loss": 1.1836,
+      "step": 10
+    },
+    {
+      "epoch": 0.11,
+      "eval_loss": 1.3055061101913452,
+      "eval_runtime": 44.7824,
+      "eval_samples_per_second": 6.811,
+      "eval_steps_per_second": 3.417,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00019992093972273018,
+      "loss": 1.3094,
+      "step": 11
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001996838839014696,
+      "loss": 1.3395,
+      "step": 12
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00019928920737019733,
+      "loss": 1.2689,
+      "step": 13
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019873753419363336,
+      "loss": 1.2584,
+      "step": 14
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019802973668046363,
+      "loss": 1.2761,
+      "step": 15
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 1.2809727191925049,
+      "eval_runtime": 44.7653,
+      "eval_samples_per_second": 6.813,
+      "eval_steps_per_second": 3.418,
+      "step": 15
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000197166934004041,
+      "loss": 1.2508,
+      "step": 16
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00019615049043274205,
+      "loss": 1.151,
+      "step": 17
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00019498201317277828,
+      "loss": 1.2186,
+      "step": 18
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0001936633498268728,
+      "loss": 1.2416,
+      "step": 19
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00019219658547282067,
+      "loss": 1.1779,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "eval_loss": 1.2696019411087036,
+      "eval_runtime": 44.7761,
+      "eval_samples_per_second": 6.812,
+      "eval_steps_per_second": 3.417,
+      "step": 20
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00019058403936655233,
+      "loss": 1.2289,
+      "step": 21
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0001888282612749132,
+      "loss": 1.2383,
+      "step": 22
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00018693202744395827,
+      "loss": 1.2303,
+      "step": 23
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00018489833620913642,
+      "loss": 1.0146,
+      "step": 24
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00018273040325430574,
+      "loss": 1.1242,
+      "step": 25
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 1.264197587966919,
+      "eval_runtime": 44.7709,
+      "eval_samples_per_second": 6.812,
+      "eval_steps_per_second": 3.417,
+      "step": 25
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00018043165652707649,
+      "loss": 1.1922,
+      "step": 26
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00017800573081852122,
+      "loss": 1.2137,
+      "step": 27
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00017545646201582303,
+      "loss": 1.2167,
+      "step": 28
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00017278788103694943,
+      "loss": 1.2603,
+      "step": 29
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00017000420745694254,
+      "loss": 1.2414,
+      "step": 30
+    },
+    {
+      "epoch": 0.33,
+      "eval_loss": 1.2588073015213013,
+      "eval_runtime": 44.7874,
+      "eval_samples_per_second": 6.81,
+      "eval_steps_per_second": 3.416,
+      "step": 30
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0001671098428359037,
+      "loss": 1.187,
+      "step": 31
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.000164109363759222,
+      "loss": 1.165,
+      "step": 32
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00016100751460105243,
+      "loss": 1.1853,
+      "step": 33
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00015780920002248484,
+      "loss": 1.0538,
+      "step": 34
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00015451947721626676,
+      "loss": 1.1382,
+      "step": 35
+    },
+    {
+      "epoch": 0.39,
+      "eval_loss": 1.2555344104766846,
+      "eval_runtime": 44.7839,
+      "eval_samples_per_second": 6.81,
+      "eval_steps_per_second": 3.416,
+      "step": 35
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00015114354791034225,
+      "loss": 1.1604,
+      "step": 36
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00014768675014285062,
+      "loss": 1.1631,
+      "step": 37
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0001441545498215912,
+      "loss": 1.2075,
+      "step": 38
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00014055253208129938,
+      "loss": 1.1602,
+      "step": 39
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00013688639245240078,
+      "loss": 1.2094,
+      "step": 40
+    },
+    {
+      "epoch": 0.45,
+      "eval_loss": 1.2520103454589844,
+      "eval_runtime": 44.7798,
+      "eval_samples_per_second": 6.811,
+      "eval_steps_per_second": 3.417,
+      "step": 40
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0001331619278552068,
+      "loss": 1.1457,
+      "step": 41
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00012938502743379212,
+      "loss": 1.0895,
+      "step": 42
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0001255616632440475,
+      "loss": 1.0843,
+      "step": 43
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0001216978808106318,
+      "loss": 1.1428,
+      "step": 44
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00011779978956775506,
+      "loss": 1.1049,
+      "step": 45
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 1.2504087686538696,
+      "eval_runtime": 44.7786,
+      "eval_samples_per_second": 6.811,
+      "eval_steps_per_second": 3.417,
+      "step": 45
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00011387355319890685,
+      "loss": 1.0035,
+      "step": 46
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00010992537989080618,
+      "loss": 1.1693,
+      "step": 47
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00010596151251698199,
+      "loss": 1.0852,
+      "step": 48
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00010198821876650701,
+      "loss": 1.0954,
+      "step": 49
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.801178123349298e-05,
+      "loss": 1.1709,
+      "step": 50
+    },
+    {
+      "epoch": 0.56,
+      "eval_loss": 1.2487094402313232,
+      "eval_runtime": 44.7848,
+      "eval_samples_per_second": 6.81,
+      "eval_steps_per_second": 3.416,
+      "step": 50
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.403848748301802e-05,
+      "loss": 1.1668,
+      "step": 51
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 9.007462010919386e-05,
+      "loss": 1.1643,
+      "step": 52
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.612644680109319e-05,
+      "loss": 1.1938,
+      "step": 53
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.2200210432245e-05,
+      "loss": 1.1062,
+      "step": 54
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.83021191893682e-05,
+      "loss": 1.0981,
+      "step": 55
+    },
+    {
+      "epoch": 0.61,
+      "eval_loss": 1.2463428974151611,
+      "eval_runtime": 44.7606,
+      "eval_samples_per_second": 6.814,
+      "eval_steps_per_second": 3.418,
+      "step": 55
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 7.443833675595255e-05,
+      "loss": 1.1809,
+      "step": 56
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 7.061497256620793e-05,
+      "loss": 1.1515,
+      "step": 57
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 6.683807214479323e-05,
+      "loss": 1.1226,
+      "step": 58
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 6.311360754759923e-05,
+      "loss": 1.1952,
+      "step": 59
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.9447467918700614e-05,
+      "loss": 1.1902,
+      "step": 60
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 1.2446388006210327,
+      "eval_runtime": 44.7804,
+      "eval_samples_per_second": 6.811,
+      "eval_steps_per_second": 3.417,
+      "step": 60
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.584545017840885e-05,
+      "loss": 1.1506,
+      "step": 61
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 5.2313249857149414e-05,
+      "loss": 1.1505,
+      "step": 62
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.885645208965779e-05,
+      "loss": 1.1414,
+      "step": 63
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.548052278373327e-05,
+      "loss": 1.2361,
+      "step": 64
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.219079997751515e-05,
+      "loss": 1.1526,
+      "step": 65
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 1.244616150856018,
+      "eval_runtime": 44.7366,
+      "eval_samples_per_second": 6.818,
+      "eval_steps_per_second": 3.42,
+      "step": 65
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.899248539894757e-05,
+      "loss": 1.1942,
+      "step": 66
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.589063624077802e-05,
+      "loss": 1.1018,
+      "step": 67
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.289015716409631e-05,
+      "loss": 1.2284,
+      "step": 68
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.9995792543057478e-05,
+      "loss": 1.1665,
+      "step": 69
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.7212118963050592e-05,
+      "loss": 1.1319,
+      "step": 70
+    },
+    {
+      "epoch": 0.78,
+      "eval_loss": 1.2439743280410767,
+      "eval_runtime": 44.7492,
+      "eval_samples_per_second": 6.816,
+      "eval_steps_per_second": 3.419,
+      "step": 70
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.4543537984176978e-05,
+      "loss": 1.067,
+      "step": 71
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.19942691814788e-05,
+      "loss": 1.1465,
+      "step": 72
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.9568343472923524e-05,
+      "loss": 1.227,
+      "step": 73
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7269596745694295e-05,
+      "loss": 1.1989,
+      "step": 74
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.5101663790863596e-05,
+      "loss": 1.1913,
+      "step": 75
+    },
+    {
+      "epoch": 0.84,
+      "eval_loss": 1.2430416345596313,
+      "eval_runtime": 44.7589,
+      "eval_samples_per_second": 6.814,
+      "eval_steps_per_second": 3.418,
+      "step": 75
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.3067972556041752e-05,
+      "loss": 1.154,
+      "step": 76
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.1171738725086833e-05,
+      "loss": 1.055,
+      "step": 77
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.415960633447674e-06,
+      "loss": 1.1523,
+      "step": 78
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.803414527179343e-06,
+      "loss": 1.1057,
+      "step": 79
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.336650173127223e-06,
+      "loss": 1.1875,
+      "step": 80
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 1.2423635721206665,
+      "eval_runtime": 44.7706,
+      "eval_samples_per_second": 6.813,
+      "eval_steps_per_second": 3.417,
+      "step": 80
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.017986827221733e-06,
+      "loss": 1.2235,
+      "step": 81
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.849509567257959e-06,
+      "loss": 1.1457,
+      "step": 82
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.8330659959589946e-06,
+      "loss": 1.1552,
+      "step": 83
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.9702633195363917e-06,
+      "loss": 1.1497,
+      "step": 84
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.2624658063666639e-06,
+      "loss": 1.1454,
+      "step": 85
+    },
+    {
+      "epoch": 0.95,
+      "eval_loss": 1.2422702312469482,
+      "eval_runtime": 44.7707,
+      "eval_samples_per_second": 6.812,
+      "eval_steps_per_second": 3.417,
+      "step": 85
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.10792629802659e-07,
+      "loss": 1.2008,
+      "step": 86
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.161160985304168e-07,
+      "loss": 1.15,
+      "step": 87
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 7.906027726981568e-08,
+      "loss": 1.2256,
+      "step": 88
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0,
+      "loss": 1.2861,
+      "step": 89
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 89,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 2.5178194955363942e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-89/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bdfe72d52e79a8c86654ed5bfb76054ce589a732b55e1e4b5cdc391ffcc1469
+size 4539

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

runs/Dec06_16-57-37_f03522d91cb7/events.out.tfevents.1701881857.f03522d91cb7.675.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e671306047a1ad8ff5a26ce57424292eeab70c2a741db3599c7beb1ecc5e384
+size 23848

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "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 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}