Add checkpoint: run1/checkpoint-800

run1/checkpoint-800/README.md

@@ -0,0 +1,207 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:mistralai/Mistral-7B-Instruct-v0.3
+- lora
+- transformers
+---
+
+# 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 0.18.1

run1/checkpoint-800/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

run1/checkpoint-800/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:031d973f8ef4f71177b72bcc7e5d8930ba08b58442a122b311d47c45dbe91044
+size 671149168

run1/checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8e612cb2d9e5923dcdb641d4eb70f9b31872ce2e3bc8ed5f73bc4353b004e13
+size 1342556067

run1/checkpoint-800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71f845ae8f08887f02bdc55f975df83ac49c0752b5334e938956dadd7244336f
+size 14645

run1/checkpoint-800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8582c5e5ce2efacded70c14cfeebd9ea511182f5304ca4b91964b1877ff8bef
+size 1465

run1/checkpoint-800/trainer_state.json

@@ -0,0 +1,353 @@
+{
+  "best_global_step": 800,
+  "best_metric": 0.06054485961794853,
+  "best_model_checkpoint": "fine_tuning/run1/checkpoint-800",
+  "epoch": 0.23448376932659193,
+  "eval_steps": 200,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0002931047116582399,
+      "grad_norm": 5.205287456512451,
+      "learning_rate": 0.0,
+      "loss": 3.984018325805664,
+      "step": 1
+    },
+    {
+      "epoch": 0.005862094233164798,
+      "grad_norm": 0.6566007137298584,
+      "learning_rate": 2.235294117647059e-05,
+      "loss": 2.6078691984477795,
+      "step": 20
+    },
+    {
+      "epoch": 0.011724188466329596,
+      "grad_norm": 0.9970574378967285,
+      "learning_rate": 4.588235294117647e-05,
+      "loss": 1.522452163696289,
+      "step": 40
+    },
+    {
+      "epoch": 0.017586282699494395,
+      "grad_norm": 0.7158647775650024,
+      "learning_rate": 6.941176470588236e-05,
+      "loss": 0.9579157829284668,
+      "step": 60
+    },
+    {
+      "epoch": 0.023448376932659193,
+      "grad_norm": 0.47364261746406555,
+      "learning_rate": 9.294117647058824e-05,
+      "loss": 0.6082455158233643,
+      "step": 80
+    },
+    {
+      "epoch": 0.02931047116582399,
+      "grad_norm": 0.5676969289779663,
+      "learning_rate": 0.00011647058823529413,
+      "loss": 0.42693657875061036,
+      "step": 100
+    },
+    {
+      "epoch": 0.03517256539898879,
+      "grad_norm": 0.5456759929656982,
+      "learning_rate": 0.00014,
+      "loss": 0.3007868528366089,
+      "step": 120
+    },
+    {
+      "epoch": 0.04103465963215359,
+      "grad_norm": 0.35614532232284546,
+      "learning_rate": 0.0001635294117647059,
+      "loss": 0.2807281970977783,
+      "step": 140
+    },
+    {
+      "epoch": 0.046896753865318386,
+      "grad_norm": 0.38409215211868286,
+      "learning_rate": 0.00018705882352941178,
+      "loss": 0.26612439155578616,
+      "step": 160
+    },
+    {
+      "epoch": 0.052758848098483184,
+      "grad_norm": 0.5955071449279785,
+      "learning_rate": 0.00019999619700289458,
+      "loss": 0.24888403415679933,
+      "step": 180
+    },
+    {
+      "epoch": 0.05862094233164798,
+      "grad_norm": 0.36434128880500793,
+      "learning_rate": 0.00019996051690910786,
+      "loss": 0.4636545658111572,
+      "step": 200
+    },
+    {
+      "epoch": 0.05862094233164798,
+      "eval_loss": 0.23540225625038147,
+      "eval_runtime": 95.5545,
+      "eval_samples_per_second": 31.396,
+      "eval_steps_per_second": 7.849,
+      "step": 200
+    },
+    {
+      "epoch": 0.06448303656481277,
+      "grad_norm": 0.47416865825653076,
+      "learning_rate": 0.0001998872921173291,
+      "loss": 0.1906836986541748,
+      "step": 220
+    },
+    {
+      "epoch": 0.07034513079797758,
+      "grad_norm": 0.41075798869132996,
+      "learning_rate": 0.00019977655013044422,
+      "loss": 0.18175047636032104,
+      "step": 240
+    },
+    {
+      "epoch": 0.07620722503114237,
+      "grad_norm": 0.46500828862190247,
+      "learning_rate": 0.00019962833254262043,
+      "loss": 0.14858518838882445,
+      "step": 260
+    },
+    {
+      "epoch": 0.08206931926430718,
+      "grad_norm": 0.40493887662887573,
+      "learning_rate": 0.00019944269502368358,
+      "loss": 0.16034438610076904,
+      "step": 280
+    },
+    {
+      "epoch": 0.08793141349747197,
+      "grad_norm": 1.205977201461792,
+      "learning_rate": 0.00019921970729820893,
+      "loss": 0.13649142980575563,
+      "step": 300
+    },
+    {
+      "epoch": 0.09379350773063677,
+      "grad_norm": 0.43041229248046875,
+      "learning_rate": 0.00019895945311933293,
+      "loss": 0.19766602516174317,
+      "step": 320
+    },
+    {
+      "epoch": 0.09965560196380156,
+      "grad_norm": 0.2409747987985611,
+      "learning_rate": 0.00019866203023729585,
+      "loss": 0.11823850870132446,
+      "step": 340
+    },
+    {
+      "epoch": 0.10551769619696637,
+      "grad_norm": 0.37636280059814453,
+      "learning_rate": 0.00019832755036272733,
+      "loss": 0.11009452342987061,
+      "step": 360
+    },
+    {
+      "epoch": 0.11137979043013116,
+      "grad_norm": 6.360550403594971,
+      "learning_rate": 0.00019795613912468833,
+      "loss": 0.15375109910964965,
+      "step": 380
+    },
+    {
+      "epoch": 0.11724188466329596,
+      "grad_norm": 0.2782416045665741,
+      "learning_rate": 0.00019754793602348554,
+      "loss": 0.11622080802917481,
+      "step": 400
+    },
+    {
+      "epoch": 0.11724188466329596,
+      "eval_loss": 0.09865953773260117,
+      "eval_runtime": 95.5072,
+      "eval_samples_per_second": 31.411,
+      "eval_steps_per_second": 7.853,
+      "step": 400
+    },
+    {
+      "epoch": 0.12310397889646076,
+      "grad_norm": 0.3631594181060791,
+      "learning_rate": 0.00019710309437827563,
+      "loss": 0.08467634916305541,
+      "step": 420
+    },
+    {
+      "epoch": 0.12896607312962555,
+      "grad_norm": 0.39376750588417053,
+      "learning_rate": 0.00019662178126947935,
+      "loss": 0.09024661779403687,
+      "step": 440
+    },
+    {
+      "epoch": 0.13482816736279035,
+      "grad_norm": 1.1295357942581177,
+      "learning_rate": 0.0001961041774760269,
+      "loss": 0.08685839772224427,
+      "step": 460
+    },
+    {
+      "epoch": 0.14069026159595516,
+      "grad_norm": 0.40582218766212463,
+      "learning_rate": 0.00019555047740745828,
+      "loss": 0.07049674391746522,
+      "step": 480
+    },
+    {
+      "epoch": 0.14655235582911996,
+      "grad_norm": 0.48699498176574707,
+      "learning_rate": 0.00019496088903090373,
+      "loss": 0.10194635391235352,
+      "step": 500
+    },
+    {
+      "epoch": 0.15241445006228474,
+      "grad_norm": 0.268585205078125,
+      "learning_rate": 0.00019433563379297274,
+      "loss": 0.06402722001075745,
+      "step": 520
+    },
+    {
+      "epoch": 0.15827654429544954,
+      "grad_norm": 0.8670694231987,
+      "learning_rate": 0.00019367494653657925,
+      "loss": 0.069954913854599,
+      "step": 540
+    },
+    {
+      "epoch": 0.16413863852861435,
+      "grad_norm": 0.538274884223938,
+      "learning_rate": 0.000192979075412736,
+      "loss": 0.08039628267288208,
+      "step": 560
+    },
+    {
+      "epoch": 0.17000073276177916,
+      "grad_norm": 0.23819144070148468,
+      "learning_rate": 0.00019224828178735024,
+      "loss": 0.07150034904479981,
+      "step": 580
+    },
+    {
+      "epoch": 0.17586282699494393,
+      "grad_norm": 0.18901239335536957,
+      "learning_rate": 0.00019148284014305577,
+      "loss": 0.08994907140731812,
+      "step": 600
+    },
+    {
+      "epoch": 0.17586282699494393,
+      "eval_loss": 0.07560985535383224,
+      "eval_runtime": 95.4614,
+      "eval_samples_per_second": 31.426,
+      "eval_steps_per_second": 7.857,
+      "step": 600
+    },
+    {
+      "epoch": 0.18172492122810874,
+      "grad_norm": 0.32568788528442383,
+      "learning_rate": 0.00019068303797611867,
+      "loss": 0.06992515325546264,
+      "step": 620
+    },
+    {
+      "epoch": 0.18758701546127354,
+      "grad_norm": 0.36330607533454895,
+      "learning_rate": 0.000189849175688455,
+      "loss": 0.06883852481842041,
+      "step": 640
+    },
+    {
+      "epoch": 0.19344910969443835,
+      "grad_norm": 0.7427650094032288,
+      "learning_rate": 0.00018898156647480132,
+      "loss": 0.05433676242828369,
+      "step": 660
+    },
+    {
+      "epoch": 0.19931120392760313,
+      "grad_norm": 0.4648798704147339,
+      "learning_rate": 0.00018808053620508015,
+      "loss": 0.07029188871383667,
+      "step": 680
+    },
+    {
+      "epoch": 0.20517329816076793,
+      "grad_norm": 0.2690366804599762,
+      "learning_rate": 0.0001871464233020048,
+      "loss": 0.05593773126602173,
+      "step": 700
+    },
+    {
+      "epoch": 0.21103539239393274,
+      "grad_norm": 0.3797769248485565,
+      "learning_rate": 0.00018617957861396945,
+      "loss": 0.06090778112411499,
+      "step": 720
+    },
+    {
+      "epoch": 0.21689748662709754,
+      "grad_norm": 0.18517662584781647,
+      "learning_rate": 0.00018518036528327207,
+      "loss": 0.05784516930580139,
+      "step": 740
+    },
+    {
+      "epoch": 0.22275958086026232,
+      "grad_norm": 0.3488333821296692,
+      "learning_rate": 0.0001841491586097199,
+      "loss": 0.0562502384185791,
+      "step": 760
+    },
+    {
+      "epoch": 0.22862167509342712,
+      "grad_norm": 1.04118013381958,
+      "learning_rate": 0.00018308634590966872,
+      "loss": 0.06282733082771301,
+      "step": 780
+    },
+    {
+      "epoch": 0.23448376932659193,
+      "grad_norm": 0.2655196189880371,
+      "learning_rate": 0.00018199232637054852,
+      "loss": 0.06829000115394593,
+      "step": 800
+    },
+    {
+      "epoch": 0.23448376932659193,
+      "eval_loss": 0.06054485961794853,
+      "eval_runtime": 95.2536,
+      "eval_samples_per_second": 31.495,
+      "eval_steps_per_second": 7.874,
+      "step": 800
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 3412,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.8501610797596672e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

run1/checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e34d951456e6568592c690cf118bfab7533f7eaaff36b6fee316604981a4f67
+size 5201