Add output of finetuning tinyllama

README.md

@@ -1,3 +1,202 @@
----
-license: mit
----
+---
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+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 0.13.3.dev0

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+  "bias": "none",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "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:f9247c42d839d73a66d34c1fad24c7a2600d7cf990f2875bdefccb5661e43282
+size 18045856

checkpoint-1000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+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 0.13.3.dev0

checkpoint-1000/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+  "bias": "none",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9247c42d839d73a66d34c1fad24c7a2600d7cf990f2875bdefccb5661e43282
+size 18045856

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:716e9573e96ba27ba1e175f9d392616a137beab353c4d3e192f3db52a5e0c423
+size 36192634

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d866f7591f0de47090bb4ee0fc77dd09e8a2996f5ef1c7cf5d2d438b112dc33b
+size 14244

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b28724192dc0151a666a878c5cc75207950e93827d26b4eea975f32d1c7423a8
+size 1064

checkpoint-1000/trainer_state.json

@@ -0,0 +1,773 @@
+{
+  "best_metric": 1.000998854637146,
+  "best_model_checkpoint": "./lora-alpaca3/checkpoint-1000",
+  "epoch": 2.572347266881029,
+  "eval_steps": 200,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02572347266881029,
+      "grad_norm": 0.5646638870239258,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.9009,
+      "step": 10
+    },
+    {
+      "epoch": 0.05144694533762058,
+      "grad_norm": 0.5377612709999084,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 1.8355,
+      "step": 20
+    },
+    {
+      "epoch": 0.07717041800643087,
+      "grad_norm": 0.5958595871925354,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 1.6639,
+      "step": 30
+    },
+    {
+      "epoch": 0.10289389067524116,
+      "grad_norm": 0.5721263885498047,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.3994,
+      "step": 40
+    },
+    {
+      "epoch": 0.12861736334405144,
+      "grad_norm": 0.2665337026119232,
+      "learning_rate": 0.00015,
+      "loss": 1.1767,
+      "step": 50
+    },
+    {
+      "epoch": 0.15434083601286175,
+      "grad_norm": 0.12332847714424133,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 1.1413,
+      "step": 60
+    },
+    {
+      "epoch": 0.18006430868167203,
+      "grad_norm": 0.12157242000102997,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 1.1103,
+      "step": 70
+    },
+    {
+      "epoch": 0.2057877813504823,
+      "grad_norm": 0.12799611687660217,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 1.1003,
+      "step": 80
+    },
+    {
+      "epoch": 0.2315112540192926,
+      "grad_norm": 0.12139850109815598,
+      "learning_rate": 0.00027,
+      "loss": 1.084,
+      "step": 90
+    },
+    {
+      "epoch": 0.2572347266881029,
+      "grad_norm": 0.144248366355896,
+      "learning_rate": 0.0003,
+      "loss": 1.0722,
+      "step": 100
+    },
+    {
+      "epoch": 0.2829581993569132,
+      "grad_norm": 0.15326175093650818,
+      "learning_rate": 0.00029718045112781953,
+      "loss": 1.0731,
+      "step": 110
+    },
+    {
+      "epoch": 0.3086816720257235,
+      "grad_norm": 0.12561754882335663,
+      "learning_rate": 0.00029436090225563904,
+      "loss": 1.0537,
+      "step": 120
+    },
+    {
+      "epoch": 0.33440514469453375,
+      "grad_norm": 0.15570670366287231,
+      "learning_rate": 0.0002915413533834586,
+      "loss": 1.049,
+      "step": 130
+    },
+    {
+      "epoch": 0.36012861736334406,
+      "grad_norm": 0.14343878626823425,
+      "learning_rate": 0.00028872180451127816,
+      "loss": 1.0273,
+      "step": 140
+    },
+    {
+      "epoch": 0.3858520900321543,
+      "grad_norm": 0.1315772831439972,
+      "learning_rate": 0.0002859022556390977,
+      "loss": 1.0529,
+      "step": 150
+    },
+    {
+      "epoch": 0.4115755627009646,
+      "grad_norm": 0.13874055445194244,
+      "learning_rate": 0.0002830827067669173,
+      "loss": 1.044,
+      "step": 160
+    },
+    {
+      "epoch": 0.43729903536977494,
+      "grad_norm": 0.1271531730890274,
+      "learning_rate": 0.00028026315789473683,
+      "loss": 1.0388,
+      "step": 170
+    },
+    {
+      "epoch": 0.4630225080385852,
+      "grad_norm": 0.12684497237205505,
+      "learning_rate": 0.0002774436090225564,
+      "loss": 1.0385,
+      "step": 180
+    },
+    {
+      "epoch": 0.4887459807073955,
+      "grad_norm": 0.11675913631916046,
+      "learning_rate": 0.0002746240601503759,
+      "loss": 1.0349,
+      "step": 190
+    },
+    {
+      "epoch": 0.5144694533762058,
+      "grad_norm": 0.15151233971118927,
+      "learning_rate": 0.00027180451127819546,
+      "loss": 1.0282,
+      "step": 200
+    },
+    {
+      "epoch": 0.5144694533762058,
+      "eval_loss": 1.0400722026824951,
+      "eval_runtime": 55.5366,
+      "eval_samples_per_second": 36.012,
+      "eval_steps_per_second": 4.502,
+      "step": 200
+    },
+    {
+      "epoch": 0.5401929260450161,
+      "grad_norm": 0.1420961171388626,
+      "learning_rate": 0.000268984962406015,
+      "loss": 1.0297,
+      "step": 210
+    },
+    {
+      "epoch": 0.5659163987138264,
+      "grad_norm": 0.13161741197109222,
+      "learning_rate": 0.0002661654135338346,
+      "loss": 1.0276,
+      "step": 220
+    },
+    {
+      "epoch": 0.5916398713826366,
+      "grad_norm": 0.13450871407985687,
+      "learning_rate": 0.00026334586466165413,
+      "loss": 1.0285,
+      "step": 230
+    },
+    {
+      "epoch": 0.617363344051447,
+      "grad_norm": 0.13193918764591217,
+      "learning_rate": 0.0002605263157894737,
+      "loss": 1.0309,
+      "step": 240
+    },
+    {
+      "epoch": 0.6430868167202572,
+      "grad_norm": 0.1393500566482544,
+      "learning_rate": 0.0002577067669172932,
+      "loss": 1.0315,
+      "step": 250
+    },
+    {
+      "epoch": 0.6688102893890675,
+      "grad_norm": 0.11902929842472076,
+      "learning_rate": 0.00025488721804511276,
+      "loss": 1.0347,
+      "step": 260
+    },
+    {
+      "epoch": 0.6945337620578779,
+      "grad_norm": 0.1258976310491562,
+      "learning_rate": 0.0002520676691729323,
+      "loss": 1.0273,
+      "step": 270
+    },
+    {
+      "epoch": 0.7202572347266881,
+      "grad_norm": 0.12598267197608948,
+      "learning_rate": 0.0002492481203007519,
+      "loss": 1.0128,
+      "step": 280
+    },
+    {
+      "epoch": 0.7459807073954984,
+      "grad_norm": 0.122463159263134,
+      "learning_rate": 0.0002464285714285714,
+      "loss": 1.0251,
+      "step": 290
+    },
+    {
+      "epoch": 0.7717041800643086,
+      "grad_norm": 0.1293506771326065,
+      "learning_rate": 0.00024360902255639094,
+      "loss": 1.0317,
+      "step": 300
+    },
+    {
+      "epoch": 0.797427652733119,
+      "grad_norm": 0.13788191974163055,
+      "learning_rate": 0.00024078947368421052,
+      "loss": 1.029,
+      "step": 310
+    },
+    {
+      "epoch": 0.8231511254019293,
+      "grad_norm": 0.1445332169532776,
+      "learning_rate": 0.00023796992481203005,
+      "loss": 1.0173,
+      "step": 320
+    },
+    {
+      "epoch": 0.8488745980707395,
+      "grad_norm": 0.11408714205026627,
+      "learning_rate": 0.00023515037593984961,
+      "loss": 1.0109,
+      "step": 330
+    },
+    {
+      "epoch": 0.8745980707395499,
+      "grad_norm": 0.11767855286598206,
+      "learning_rate": 0.00023233082706766915,
+      "loss": 1.0116,
+      "step": 340
+    },
+    {
+      "epoch": 0.9003215434083601,
+      "grad_norm": 0.12555481493473053,
+      "learning_rate": 0.0002295112781954887,
+      "loss": 1.0144,
+      "step": 350
+    },
+    {
+      "epoch": 0.9260450160771704,
+      "grad_norm": 0.12403016537427902,
+      "learning_rate": 0.00022669172932330824,
+      "loss": 1.0299,
+      "step": 360
+    },
+    {
+      "epoch": 0.9517684887459807,
+      "grad_norm": 0.12968535721302032,
+      "learning_rate": 0.0002238721804511278,
+      "loss": 1.0081,
+      "step": 370
+    },
+    {
+      "epoch": 0.977491961414791,
+      "grad_norm": 0.12369370460510254,
+      "learning_rate": 0.00022105263157894733,
+      "loss": 1.0065,
+      "step": 380
+    },
+    {
+      "epoch": 1.0032154340836013,
+      "grad_norm": 0.12212081998586655,
+      "learning_rate": 0.0002182330827067669,
+      "loss": 1.0448,
+      "step": 390
+    },
+    {
+      "epoch": 1.0289389067524115,
+      "grad_norm": 0.1301109939813614,
+      "learning_rate": 0.00021541353383458647,
+      "loss": 1.0052,
+      "step": 400
+    },
+    {
+      "epoch": 1.0289389067524115,
+      "eval_loss": 1.0189071893692017,
+      "eval_runtime": 55.4593,
+      "eval_samples_per_second": 36.062,
+      "eval_steps_per_second": 4.508,
+      "step": 400
+    },
+    {
+      "epoch": 1.0546623794212218,
+      "grad_norm": 0.13505908846855164,
+      "learning_rate": 0.000212593984962406,
+      "loss": 1.0009,
+      "step": 410
+    },
+    {
+      "epoch": 1.0803858520900322,
+      "grad_norm": 0.12307268381118774,
+      "learning_rate": 0.00020977443609022556,
+      "loss": 1.0039,
+      "step": 420
+    },
+    {
+      "epoch": 1.1061093247588425,
+      "grad_norm": 0.11501840502023697,
+      "learning_rate": 0.0002069548872180451,
+      "loss": 0.9988,
+      "step": 430
+    },
+    {
+      "epoch": 1.1318327974276527,
+      "grad_norm": 0.12922251224517822,
+      "learning_rate": 0.00020413533834586463,
+      "loss": 0.9938,
+      "step": 440
+    },
+    {
+      "epoch": 1.157556270096463,
+      "grad_norm": 0.12304320186376572,
+      "learning_rate": 0.0002013157894736842,
+      "loss": 1.0223,
+      "step": 450
+    },
+    {
+      "epoch": 1.1832797427652733,
+      "grad_norm": 0.11323860287666321,
+      "learning_rate": 0.00019849624060150372,
+      "loss": 0.9957,
+      "step": 460
+    },
+    {
+      "epoch": 1.2090032154340835,
+      "grad_norm": 0.1335834562778473,
+      "learning_rate": 0.00019567669172932328,
+      "loss": 1.0042,
+      "step": 470
+    },
+    {
+      "epoch": 1.234726688102894,
+      "grad_norm": 0.12371603399515152,
+      "learning_rate": 0.00019285714285714286,
+      "loss": 1.0056,
+      "step": 480
+    },
+    {
+      "epoch": 1.2604501607717042,
+      "grad_norm": 0.12318002432584763,
+      "learning_rate": 0.0001900375939849624,
+      "loss": 1.0122,
+      "step": 490
+    },
+    {
+      "epoch": 1.2861736334405145,
+      "grad_norm": 0.13187570869922638,
+      "learning_rate": 0.00018721804511278195,
+      "loss": 0.9971,
+      "step": 500
+    },
+    {
+      "epoch": 1.3118971061093248,
+      "grad_norm": 0.11861589550971985,
+      "learning_rate": 0.00018439849624060149,
+      "loss": 0.9926,
+      "step": 510
+    },
+    {
+      "epoch": 1.337620578778135,
+      "grad_norm": 0.11287492513656616,
+      "learning_rate": 0.00018157894736842105,
+      "loss": 1.016,
+      "step": 520
+    },
+    {
+      "epoch": 1.3633440514469453,
+      "grad_norm": 0.1384376585483551,
+      "learning_rate": 0.00017875939849624058,
+      "loss": 1.0059,
+      "step": 530
+    },
+    {
+      "epoch": 1.3890675241157555,
+      "grad_norm": 0.12147587537765503,
+      "learning_rate": 0.00017593984962406014,
+      "loss": 1.0213,
+      "step": 540
+    },
+    {
+      "epoch": 1.414790996784566,
+      "grad_norm": 0.13031207025051117,
+      "learning_rate": 0.00017312030075187967,
+      "loss": 1.005,
+      "step": 550
+    },
+    {
+      "epoch": 1.4405144694533762,
+      "grad_norm": 0.13779744505882263,
+      "learning_rate": 0.00017030075187969925,
+      "loss": 1.0077,
+      "step": 560
+    },
+    {
+      "epoch": 1.4662379421221865,
+      "grad_norm": 0.13196057081222534,
+      "learning_rate": 0.00016748120300751879,
+      "loss": 0.9944,
+      "step": 570
+    },
+    {
+      "epoch": 1.4919614147909968,
+      "grad_norm": 0.117030069231987,
+      "learning_rate": 0.00016466165413533835,
+      "loss": 1.0082,
+      "step": 580
+    },
+    {
+      "epoch": 1.517684887459807,
+      "grad_norm": 0.1274162381887436,
+      "learning_rate": 0.00016184210526315788,
+      "loss": 1.0102,
+      "step": 590
+    },
+    {
+      "epoch": 1.5434083601286175,
+      "grad_norm": 0.13315673172473907,
+      "learning_rate": 0.00015902255639097744,
+      "loss": 0.985,
+      "step": 600
+    },
+    {
+      "epoch": 1.5434083601286175,
+      "eval_loss": 1.0096462965011597,
+      "eval_runtime": 55.507,
+      "eval_samples_per_second": 36.031,
+      "eval_steps_per_second": 4.504,
+      "step": 600
+    },
+    {
+      "epoch": 1.5691318327974275,
+      "grad_norm": 0.12220187485218048,
+      "learning_rate": 0.00015620300751879697,
+      "loss": 0.9912,
+      "step": 610
+    },
+    {
+      "epoch": 1.594855305466238,
+      "grad_norm": 0.12432006746530533,
+      "learning_rate": 0.00015338345864661653,
+      "loss": 0.9963,
+      "step": 620
+    },
+    {
+      "epoch": 1.6205787781350482,
+      "grad_norm": 0.12138667702674866,
+      "learning_rate": 0.00015056390977443606,
+      "loss": 1.0014,
+      "step": 630
+    },
+    {
+      "epoch": 1.6463022508038585,
+      "grad_norm": 0.13801203668117523,
+      "learning_rate": 0.00014774436090225562,
+      "loss": 0.9922,
+      "step": 640
+    },
+    {
+      "epoch": 1.6720257234726688,
+      "grad_norm": 0.13330678641796112,
+      "learning_rate": 0.00014492481203007518,
+      "loss": 0.9897,
+      "step": 650
+    },
+    {
+      "epoch": 1.697749196141479,
+      "grad_norm": 0.12127404659986496,
+      "learning_rate": 0.0001421052631578947,
+      "loss": 0.9898,
+      "step": 660
+    },
+    {
+      "epoch": 1.7234726688102895,
+      "grad_norm": 0.13159097731113434,
+      "learning_rate": 0.00013928571428571427,
+      "loss": 0.9943,
+      "step": 670
+    },
+    {
+      "epoch": 1.7491961414790995,
+      "grad_norm": 0.13246209919452667,
+      "learning_rate": 0.00013646616541353383,
+      "loss": 1.0048,
+      "step": 680
+    },
+    {
+      "epoch": 1.77491961414791,
+      "grad_norm": 0.11693169921636581,
+      "learning_rate": 0.00013364661654135336,
+      "loss": 0.9996,
+      "step": 690
+    },
+    {
+      "epoch": 1.8006430868167203,
+      "grad_norm": 0.13176512718200684,
+      "learning_rate": 0.00013082706766917292,
+      "loss": 0.9923,
+      "step": 700
+    },
+    {
+      "epoch": 1.8263665594855305,
+      "grad_norm": 0.1224486380815506,
+      "learning_rate": 0.00012800751879699248,
+      "loss": 0.9799,
+      "step": 710
+    },
+    {
+      "epoch": 1.852090032154341,
+      "grad_norm": 0.12146233022212982,
+      "learning_rate": 0.000125187969924812,
+      "loss": 0.9874,
+      "step": 720
+    },
+    {
+      "epoch": 1.877813504823151,
+      "grad_norm": 0.12821047008037567,
+      "learning_rate": 0.00012236842105263157,
+      "loss": 0.9982,
+      "step": 730
+    },
+    {
+      "epoch": 1.9035369774919615,
+      "grad_norm": 0.12273906171321869,
+      "learning_rate": 0.00011954887218045111,
+      "loss": 0.9946,
+      "step": 740
+    },
+    {
+      "epoch": 1.9292604501607717,
+      "grad_norm": 0.1282244175672531,
+      "learning_rate": 0.00011672932330827067,
+      "loss": 0.9976,
+      "step": 750
+    },
+    {
+      "epoch": 1.954983922829582,
+      "grad_norm": 0.13315148651599884,
+      "learning_rate": 0.00011390977443609022,
+      "loss": 1.0012,
+      "step": 760
+    },
+    {
+      "epoch": 1.9807073954983923,
+      "grad_norm": 0.12510079145431519,
+      "learning_rate": 0.00011109022556390976,
+      "loss": 0.9865,
+      "step": 770
+    },
+    {
+      "epoch": 2.0064308681672025,
+      "grad_norm": 0.11581259220838547,
+      "learning_rate": 0.00010827067669172931,
+      "loss": 1.0306,
+      "step": 780
+    },
+    {
+      "epoch": 2.032154340836013,
+      "grad_norm": 0.1278076171875,
+      "learning_rate": 0.00010545112781954887,
+      "loss": 0.9984,
+      "step": 790
+    },
+    {
+      "epoch": 2.057877813504823,
+      "grad_norm": 0.12879391014575958,
+      "learning_rate": 0.00010263157894736841,
+      "loss": 0.9729,
+      "step": 800
+    },
+    {
+      "epoch": 2.057877813504823,
+      "eval_loss": 1.0042115449905396,
+      "eval_runtime": 55.4463,
+      "eval_samples_per_second": 36.071,
+      "eval_steps_per_second": 4.509,
+      "step": 800
+    },
+    {
+      "epoch": 2.0836012861736335,
+      "grad_norm": 0.1267639547586441,
+      "learning_rate": 9.981203007518796e-05,
+      "loss": 0.9899,
+      "step": 810
+    },
+    {
+      "epoch": 2.1093247588424435,
+      "grad_norm": 0.13013407588005066,
+      "learning_rate": 9.69924812030075e-05,
+      "loss": 0.9913,
+      "step": 820
+    },
+    {
+      "epoch": 2.135048231511254,
+      "grad_norm": 0.12404422461986542,
+      "learning_rate": 9.417293233082706e-05,
+      "loss": 0.9923,
+      "step": 830
+    },
+    {
+      "epoch": 2.1607717041800645,
+      "grad_norm": 0.12091611325740814,
+      "learning_rate": 9.135338345864661e-05,
+      "loss": 0.9905,
+      "step": 840
+    },
+    {
+      "epoch": 2.1864951768488745,
+      "grad_norm": 0.13067036867141724,
+      "learning_rate": 8.853383458646615e-05,
+      "loss": 0.9944,
+      "step": 850
+    },
+    {
+      "epoch": 2.212218649517685,
+      "grad_norm": 0.13169625401496887,
+      "learning_rate": 8.57142857142857e-05,
+      "loss": 0.9848,
+      "step": 860
+    },
+    {
+      "epoch": 2.237942122186495,
+      "grad_norm": 0.13107703626155853,
+      "learning_rate": 8.289473684210526e-05,
+      "loss": 0.9712,
+      "step": 870
+    },
+    {
+      "epoch": 2.2636655948553055,
+      "grad_norm": 0.1307050734758377,
+      "learning_rate": 8.00751879699248e-05,
+      "loss": 0.9855,
+      "step": 880
+    },
+    {
+      "epoch": 2.289389067524116,
+      "grad_norm": 0.13297782838344574,
+      "learning_rate": 7.725563909774435e-05,
+      "loss": 0.9918,
+      "step": 890
+    },
+    {
+      "epoch": 2.315112540192926,
+      "grad_norm": 0.1355738788843155,
+      "learning_rate": 7.44360902255639e-05,
+      "loss": 0.9845,
+      "step": 900
+    },
+    {
+      "epoch": 2.3408360128617365,
+      "grad_norm": 0.12372130155563354,
+      "learning_rate": 7.161654135338345e-05,
+      "loss": 0.9887,
+      "step": 910
+    },
+    {
+      "epoch": 2.3665594855305465,
+      "grad_norm": 0.1307709813117981,
+      "learning_rate": 6.8796992481203e-05,
+      "loss": 0.9886,
+      "step": 920
+    },
+    {
+      "epoch": 2.392282958199357,
+      "grad_norm": 0.12701715528964996,
+      "learning_rate": 6.597744360902256e-05,
+      "loss": 0.9885,
+      "step": 930
+    },
+    {
+      "epoch": 2.418006430868167,
+      "grad_norm": 0.13114945590496063,
+      "learning_rate": 6.315789473684209e-05,
+      "loss": 0.9788,
+      "step": 940
+    },
+    {
+      "epoch": 2.4437299035369775,
+      "grad_norm": 0.12744566798210144,
+      "learning_rate": 6.033834586466165e-05,
+      "loss": 0.986,
+      "step": 950
+    },
+    {
+      "epoch": 2.469453376205788,
+      "grad_norm": 0.13428843021392822,
+      "learning_rate": 5.7518796992481194e-05,
+      "loss": 0.974,
+      "step": 960
+    },
+    {
+      "epoch": 2.495176848874598,
+      "grad_norm": 0.13112470507621765,
+      "learning_rate": 5.4699248120300746e-05,
+      "loss": 0.9818,
+      "step": 970
+    },
+    {
+      "epoch": 2.5209003215434085,
+      "grad_norm": 0.1363256722688675,
+      "learning_rate": 5.187969924812029e-05,
+      "loss": 0.9909,
+      "step": 980
+    },
+    {
+      "epoch": 2.5466237942122185,
+      "grad_norm": 0.13036535680294037,
+      "learning_rate": 4.9060150375939844e-05,
+      "loss": 0.9921,
+      "step": 990
+    },
+    {
+      "epoch": 2.572347266881029,
+      "grad_norm": 0.13345099985599518,
+      "learning_rate": 4.624060150375939e-05,
+      "loss": 0.9722,
+      "step": 1000
+    },
+    {
+      "epoch": 2.572347266881029,
+      "eval_loss": 1.000998854637146,
+      "eval_runtime": 55.4742,
+      "eval_samples_per_second": 36.053,
+      "eval_steps_per_second": 4.507,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1164,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 1.9627225935210086e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5844d0b7bf295f3ab4a8da73232006a40fc200ad74a77a9010df10478b55d69
+size 5240

checkpoint-1164/README.md

@@ -0,0 +1,202 @@
+---
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+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 0.13.3.dev0

checkpoint-1164/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+  "bias": "none",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1164/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe60d478997ece7e2f508c86547220fe6b03ae18b640709e734bce17d86ef70c
+size 18045856

checkpoint-1164/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1855ab79f9312ed4e6118fc3b4ac3beaaf58e70db04c2f045e8bef925d531f21
+size 36192634

checkpoint-1164/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcda84240efbcf27c79bbf45ec98a765f6241cf84b0797d7abb184cb87f1c7e0
+size 14244

checkpoint-1164/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7442cc933032398e389dcf12b89ea90828d96dfea765640c1295a21b2451070e
+size 1064

checkpoint-1164/trainer_state.json

@@ -0,0 +1,885 @@
+{
+  "best_metric": 1.000998854637146,
+  "best_model_checkpoint": "./lora-alpaca3/checkpoint-1000",
+  "epoch": 2.9942122186495177,
+  "eval_steps": 200,
+  "global_step": 1164,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02572347266881029,
+      "grad_norm": 0.5646638870239258,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.9009,
+      "step": 10
+    },
+    {
+      "epoch": 0.05144694533762058,
+      "grad_norm": 0.5377612709999084,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 1.8355,
+      "step": 20
+    },
+    {
+      "epoch": 0.07717041800643087,
+      "grad_norm": 0.5958595871925354,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 1.6639,
+      "step": 30
+    },
+    {
+      "epoch": 0.10289389067524116,
+      "grad_norm": 0.5721263885498047,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.3994,
+      "step": 40
+    },
+    {
+      "epoch": 0.12861736334405144,
+      "grad_norm": 0.2665337026119232,
+      "learning_rate": 0.00015,
+      "loss": 1.1767,
+      "step": 50
+    },
+    {
+      "epoch": 0.15434083601286175,
+      "grad_norm": 0.12332847714424133,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 1.1413,
+      "step": 60
+    },
+    {
+      "epoch": 0.18006430868167203,
+      "grad_norm": 0.12157242000102997,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 1.1103,
+      "step": 70
+    },
+    {
+      "epoch": 0.2057877813504823,
+      "grad_norm": 0.12799611687660217,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 1.1003,
+      "step": 80
+    },
+    {
+      "epoch": 0.2315112540192926,
+      "grad_norm": 0.12139850109815598,
+      "learning_rate": 0.00027,
+      "loss": 1.084,
+      "step": 90
+    },
+    {
+      "epoch": 0.2572347266881029,
+      "grad_norm": 0.144248366355896,
+      "learning_rate": 0.0003,
+      "loss": 1.0722,
+      "step": 100
+    },
+    {
+      "epoch": 0.2829581993569132,
+      "grad_norm": 0.15326175093650818,
+      "learning_rate": 0.00029718045112781953,
+      "loss": 1.0731,
+      "step": 110
+    },
+    {
+      "epoch": 0.3086816720257235,
+      "grad_norm": 0.12561754882335663,
+      "learning_rate": 0.00029436090225563904,
+      "loss": 1.0537,
+      "step": 120
+    },
+    {
+      "epoch": 0.33440514469453375,
+      "grad_norm": 0.15570670366287231,
+      "learning_rate": 0.0002915413533834586,
+      "loss": 1.049,
+      "step": 130
+    },
+    {
+      "epoch": 0.36012861736334406,
+      "grad_norm": 0.14343878626823425,
+      "learning_rate": 0.00028872180451127816,
+      "loss": 1.0273,
+      "step": 140
+    },
+    {
+      "epoch": 0.3858520900321543,
+      "grad_norm": 0.1315772831439972,
+      "learning_rate": 0.0002859022556390977,
+      "loss": 1.0529,
+      "step": 150
+    },
+    {
+      "epoch": 0.4115755627009646,
+      "grad_norm": 0.13874055445194244,
+      "learning_rate": 0.0002830827067669173,
+      "loss": 1.044,
+      "step": 160
+    },
+    {
+      "epoch": 0.43729903536977494,
+      "grad_norm": 0.1271531730890274,
+      "learning_rate": 0.00028026315789473683,
+      "loss": 1.0388,
+      "step": 170
+    },
+    {
+      "epoch": 0.4630225080385852,
+      "grad_norm": 0.12684497237205505,
+      "learning_rate": 0.0002774436090225564,
+      "loss": 1.0385,
+      "step": 180
+    },
+    {
+      "epoch": 0.4887459807073955,
+      "grad_norm": 0.11675913631916046,
+      "learning_rate": 0.0002746240601503759,
+      "loss": 1.0349,
+      "step": 190
+    },
+    {
+      "epoch": 0.5144694533762058,
+      "grad_norm": 0.15151233971118927,
+      "learning_rate": 0.00027180451127819546,
+      "loss": 1.0282,
+      "step": 200
+    },
+    {
+      "epoch": 0.5144694533762058,
+      "eval_loss": 1.0400722026824951,
+      "eval_runtime": 55.5366,
+      "eval_samples_per_second": 36.012,
+      "eval_steps_per_second": 4.502,
+      "step": 200
+    },
+    {
+      "epoch": 0.5401929260450161,
+      "grad_norm": 0.1420961171388626,
+      "learning_rate": 0.000268984962406015,
+      "loss": 1.0297,
+      "step": 210
+    },
+    {
+      "epoch": 0.5659163987138264,
+      "grad_norm": 0.13161741197109222,
+      "learning_rate": 0.0002661654135338346,
+      "loss": 1.0276,
+      "step": 220
+    },
+    {
+      "epoch": 0.5916398713826366,
+      "grad_norm": 0.13450871407985687,
+      "learning_rate": 0.00026334586466165413,
+      "loss": 1.0285,
+      "step": 230
+    },
+    {
+      "epoch": 0.617363344051447,
+      "grad_norm": 0.13193918764591217,
+      "learning_rate": 0.0002605263157894737,
+      "loss": 1.0309,
+      "step": 240
+    },
+    {
+      "epoch": 0.6430868167202572,
+      "grad_norm": 0.1393500566482544,
+      "learning_rate": 0.0002577067669172932,
+      "loss": 1.0315,
+      "step": 250
+    },
+    {
+      "epoch": 0.6688102893890675,
+      "grad_norm": 0.11902929842472076,
+      "learning_rate": 0.00025488721804511276,
+      "loss": 1.0347,
+      "step": 260
+    },
+    {
+      "epoch": 0.6945337620578779,
+      "grad_norm": 0.1258976310491562,
+      "learning_rate": 0.0002520676691729323,
+      "loss": 1.0273,
+      "step": 270
+    },
+    {
+      "epoch": 0.7202572347266881,
+      "grad_norm": 0.12598267197608948,
+      "learning_rate": 0.0002492481203007519,
+      "loss": 1.0128,
+      "step": 280
+    },
+    {
+      "epoch": 0.7459807073954984,
+      "grad_norm": 0.122463159263134,
+      "learning_rate": 0.0002464285714285714,
+      "loss": 1.0251,
+      "step": 290
+    },
+    {
+      "epoch": 0.7717041800643086,
+      "grad_norm": 0.1293506771326065,
+      "learning_rate": 0.00024360902255639094,
+      "loss": 1.0317,
+      "step": 300
+    },
+    {
+      "epoch": 0.797427652733119,
+      "grad_norm": 0.13788191974163055,
+      "learning_rate": 0.00024078947368421052,
+      "loss": 1.029,
+      "step": 310
+    },
+    {
+      "epoch": 0.8231511254019293,
+      "grad_norm": 0.1445332169532776,
+      "learning_rate": 0.00023796992481203005,
+      "loss": 1.0173,
+      "step": 320
+    },
+    {
+      "epoch": 0.8488745980707395,
+      "grad_norm": 0.11408714205026627,
+      "learning_rate": 0.00023515037593984961,
+      "loss": 1.0109,
+      "step": 330
+    },
+    {
+      "epoch": 0.8745980707395499,
+      "grad_norm": 0.11767855286598206,
+      "learning_rate": 0.00023233082706766915,
+      "loss": 1.0116,
+      "step": 340
+    },
+    {
+      "epoch": 0.9003215434083601,
+      "grad_norm": 0.12555481493473053,
+      "learning_rate": 0.0002295112781954887,
+      "loss": 1.0144,
+      "step": 350
+    },
+    {
+      "epoch": 0.9260450160771704,
+      "grad_norm": 0.12403016537427902,
+      "learning_rate": 0.00022669172932330824,
+      "loss": 1.0299,
+      "step": 360
+    },
+    {
+      "epoch": 0.9517684887459807,
+      "grad_norm": 0.12968535721302032,
+      "learning_rate": 0.0002238721804511278,
+      "loss": 1.0081,
+      "step": 370
+    },
+    {
+      "epoch": 0.977491961414791,
+      "grad_norm": 0.12369370460510254,
+      "learning_rate": 0.00022105263157894733,
+      "loss": 1.0065,
+      "step": 380
+    },
+    {
+      "epoch": 1.0032154340836013,
+      "grad_norm": 0.12212081998586655,
+      "learning_rate": 0.0002182330827067669,
+      "loss": 1.0448,
+      "step": 390
+    },
+    {
+      "epoch": 1.0289389067524115,
+      "grad_norm": 0.1301109939813614,
+      "learning_rate": 0.00021541353383458647,
+      "loss": 1.0052,
+      "step": 400
+    },
+    {
+      "epoch": 1.0289389067524115,
+      "eval_loss": 1.0189071893692017,
+      "eval_runtime": 55.4593,
+      "eval_samples_per_second": 36.062,
+      "eval_steps_per_second": 4.508,
+      "step": 400
+    },
+    {
+      "epoch": 1.0546623794212218,
+      "grad_norm": 0.13505908846855164,
+      "learning_rate": 0.000212593984962406,
+      "loss": 1.0009,
+      "step": 410
+    },
+    {
+      "epoch": 1.0803858520900322,
+      "grad_norm": 0.12307268381118774,
+      "learning_rate": 0.00020977443609022556,
+      "loss": 1.0039,
+      "step": 420
+    },
+    {
+      "epoch": 1.1061093247588425,
+      "grad_norm": 0.11501840502023697,
+      "learning_rate": 0.0002069548872180451,
+      "loss": 0.9988,
+      "step": 430
+    },
+    {
+      "epoch": 1.1318327974276527,
+      "grad_norm": 0.12922251224517822,
+      "learning_rate": 0.00020413533834586463,
+      "loss": 0.9938,
+      "step": 440
+    },
+    {
+      "epoch": 1.157556270096463,
+      "grad_norm": 0.12304320186376572,
+      "learning_rate": 0.0002013157894736842,
+      "loss": 1.0223,
+      "step": 450
+    },
+    {
+      "epoch": 1.1832797427652733,
+      "grad_norm": 0.11323860287666321,
+      "learning_rate": 0.00019849624060150372,
+      "loss": 0.9957,
+      "step": 460
+    },
+    {
+      "epoch": 1.2090032154340835,
+      "grad_norm": 0.1335834562778473,
+      "learning_rate": 0.00019567669172932328,
+      "loss": 1.0042,
+      "step": 470
+    },
+    {
+      "epoch": 1.234726688102894,
+      "grad_norm": 0.12371603399515152,
+      "learning_rate": 0.00019285714285714286,
+      "loss": 1.0056,
+      "step": 480
+    },
+    {
+      "epoch": 1.2604501607717042,
+      "grad_norm": 0.12318002432584763,
+      "learning_rate": 0.0001900375939849624,
+      "loss": 1.0122,
+      "step": 490
+    },
+    {
+      "epoch": 1.2861736334405145,
+      "grad_norm": 0.13187570869922638,
+      "learning_rate": 0.00018721804511278195,
+      "loss": 0.9971,
+      "step": 500
+    },
+    {
+      "epoch": 1.3118971061093248,
+      "grad_norm": 0.11861589550971985,
+      "learning_rate": 0.00018439849624060149,
+      "loss": 0.9926,
+      "step": 510
+    },
+    {
+      "epoch": 1.337620578778135,
+      "grad_norm": 0.11287492513656616,
+      "learning_rate": 0.00018157894736842105,
+      "loss": 1.016,
+      "step": 520
+    },
+    {
+      "epoch": 1.3633440514469453,
+      "grad_norm": 0.1384376585483551,
+      "learning_rate": 0.00017875939849624058,
+      "loss": 1.0059,
+      "step": 530
+    },
+    {
+      "epoch": 1.3890675241157555,
+      "grad_norm": 0.12147587537765503,
+      "learning_rate": 0.00017593984962406014,
+      "loss": 1.0213,
+      "step": 540
+    },
+    {
+      "epoch": 1.414790996784566,
+      "grad_norm": 0.13031207025051117,
+      "learning_rate": 0.00017312030075187967,
+      "loss": 1.005,
+      "step": 550
+    },
+    {
+      "epoch": 1.4405144694533762,
+      "grad_norm": 0.13779744505882263,
+      "learning_rate": 0.00017030075187969925,
+      "loss": 1.0077,
+      "step": 560
+    },
+    {
+      "epoch": 1.4662379421221865,
+      "grad_norm": 0.13196057081222534,
+      "learning_rate": 0.00016748120300751879,
+      "loss": 0.9944,
+      "step": 570
+    },
+    {
+      "epoch": 1.4919614147909968,
+      "grad_norm": 0.117030069231987,
+      "learning_rate": 0.00016466165413533835,
+      "loss": 1.0082,
+      "step": 580
+    },
+    {
+      "epoch": 1.517684887459807,
+      "grad_norm": 0.1274162381887436,
+      "learning_rate": 0.00016184210526315788,
+      "loss": 1.0102,
+      "step": 590
+    },
+    {
+      "epoch": 1.5434083601286175,
+      "grad_norm": 0.13315673172473907,
+      "learning_rate": 0.00015902255639097744,
+      "loss": 0.985,
+      "step": 600
+    },
+    {
+      "epoch": 1.5434083601286175,
+      "eval_loss": 1.0096462965011597,
+      "eval_runtime": 55.507,
+      "eval_samples_per_second": 36.031,
+      "eval_steps_per_second": 4.504,
+      "step": 600
+    },
+    {
+      "epoch": 1.5691318327974275,
+      "grad_norm": 0.12220187485218048,
+      "learning_rate": 0.00015620300751879697,
+      "loss": 0.9912,
+      "step": 610
+    },
+    {
+      "epoch": 1.594855305466238,
+      "grad_norm": 0.12432006746530533,
+      "learning_rate": 0.00015338345864661653,
+      "loss": 0.9963,
+      "step": 620
+    },
+    {
+      "epoch": 1.6205787781350482,
+      "grad_norm": 0.12138667702674866,
+      "learning_rate": 0.00015056390977443606,
+      "loss": 1.0014,
+      "step": 630
+    },
+    {
+      "epoch": 1.6463022508038585,
+      "grad_norm": 0.13801203668117523,
+      "learning_rate": 0.00014774436090225562,
+      "loss": 0.9922,
+      "step": 640
+    },
+    {
+      "epoch": 1.6720257234726688,
+      "grad_norm": 0.13330678641796112,
+      "learning_rate": 0.00014492481203007518,
+      "loss": 0.9897,
+      "step": 650
+    },
+    {
+      "epoch": 1.697749196141479,
+      "grad_norm": 0.12127404659986496,
+      "learning_rate": 0.0001421052631578947,
+      "loss": 0.9898,
+      "step": 660
+    },
+    {
+      "epoch": 1.7234726688102895,
+      "grad_norm": 0.13159097731113434,
+      "learning_rate": 0.00013928571428571427,
+      "loss": 0.9943,
+      "step": 670
+    },
+    {
+      "epoch": 1.7491961414790995,
+      "grad_norm": 0.13246209919452667,
+      "learning_rate": 0.00013646616541353383,
+      "loss": 1.0048,
+      "step": 680
+    },
+    {
+      "epoch": 1.77491961414791,
+      "grad_norm": 0.11693169921636581,
+      "learning_rate": 0.00013364661654135336,
+      "loss": 0.9996,
+      "step": 690
+    },
+    {
+      "epoch": 1.8006430868167203,
+      "grad_norm": 0.13176512718200684,
+      "learning_rate": 0.00013082706766917292,
+      "loss": 0.9923,
+      "step": 700
+    },
+    {
+      "epoch": 1.8263665594855305,
+      "grad_norm": 0.1224486380815506,
+      "learning_rate": 0.00012800751879699248,
+      "loss": 0.9799,
+      "step": 710
+    },
+    {
+      "epoch": 1.852090032154341,
+      "grad_norm": 0.12146233022212982,
+      "learning_rate": 0.000125187969924812,
+      "loss": 0.9874,
+      "step": 720
+    },
+    {
+      "epoch": 1.877813504823151,
+      "grad_norm": 0.12821047008037567,
+      "learning_rate": 0.00012236842105263157,
+      "loss": 0.9982,
+      "step": 730
+    },
+    {
+      "epoch": 1.9035369774919615,
+      "grad_norm": 0.12273906171321869,
+      "learning_rate": 0.00011954887218045111,
+      "loss": 0.9946,
+      "step": 740
+    },
+    {
+      "epoch": 1.9292604501607717,
+      "grad_norm": 0.1282244175672531,
+      "learning_rate": 0.00011672932330827067,
+      "loss": 0.9976,
+      "step": 750
+    },
+    {
+      "epoch": 1.954983922829582,
+      "grad_norm": 0.13315148651599884,
+      "learning_rate": 0.00011390977443609022,
+      "loss": 1.0012,
+      "step": 760
+    },
+    {
+      "epoch": 1.9807073954983923,
+      "grad_norm": 0.12510079145431519,
+      "learning_rate": 0.00011109022556390976,
+      "loss": 0.9865,
+      "step": 770
+    },
+    {
+      "epoch": 2.0064308681672025,
+      "grad_norm": 0.11581259220838547,
+      "learning_rate": 0.00010827067669172931,
+      "loss": 1.0306,
+      "step": 780
+    },
+    {
+      "epoch": 2.032154340836013,
+      "grad_norm": 0.1278076171875,
+      "learning_rate": 0.00010545112781954887,
+      "loss": 0.9984,
+      "step": 790
+    },
+    {
+      "epoch": 2.057877813504823,
+      "grad_norm": 0.12879391014575958,
+      "learning_rate": 0.00010263157894736841,
+      "loss": 0.9729,
+      "step": 800
+    },
+    {
+      "epoch": 2.057877813504823,
+      "eval_loss": 1.0042115449905396,
+      "eval_runtime": 55.4463,
+      "eval_samples_per_second": 36.071,
+      "eval_steps_per_second": 4.509,
+      "step": 800
+    },
+    {
+      "epoch": 2.0836012861736335,
+      "grad_norm": 0.1267639547586441,
+      "learning_rate": 9.981203007518796e-05,
+      "loss": 0.9899,
+      "step": 810
+    },
+    {
+      "epoch": 2.1093247588424435,
+      "grad_norm": 0.13013407588005066,
+      "learning_rate": 9.69924812030075e-05,
+      "loss": 0.9913,
+      "step": 820
+    },
+    {
+      "epoch": 2.135048231511254,
+      "grad_norm": 0.12404422461986542,
+      "learning_rate": 9.417293233082706e-05,
+      "loss": 0.9923,
+      "step": 830
+    },
+    {
+      "epoch": 2.1607717041800645,
+      "grad_norm": 0.12091611325740814,
+      "learning_rate": 9.135338345864661e-05,
+      "loss": 0.9905,
+      "step": 840
+    },
+    {
+      "epoch": 2.1864951768488745,
+      "grad_norm": 0.13067036867141724,
+      "learning_rate": 8.853383458646615e-05,
+      "loss": 0.9944,
+      "step": 850
+    },
+    {
+      "epoch": 2.212218649517685,
+      "grad_norm": 0.13169625401496887,
+      "learning_rate": 8.57142857142857e-05,
+      "loss": 0.9848,
+      "step": 860
+    },
+    {
+      "epoch": 2.237942122186495,
+      "grad_norm": 0.13107703626155853,
+      "learning_rate": 8.289473684210526e-05,
+      "loss": 0.9712,
+      "step": 870
+    },
+    {
+      "epoch": 2.2636655948553055,
+      "grad_norm": 0.1307050734758377,
+      "learning_rate": 8.00751879699248e-05,
+      "loss": 0.9855,
+      "step": 880
+    },
+    {
+      "epoch": 2.289389067524116,
+      "grad_norm": 0.13297782838344574,
+      "learning_rate": 7.725563909774435e-05,
+      "loss": 0.9918,
+      "step": 890
+    },
+    {
+      "epoch": 2.315112540192926,
+      "grad_norm": 0.1355738788843155,
+      "learning_rate": 7.44360902255639e-05,
+      "loss": 0.9845,
+      "step": 900
+    },
+    {
+      "epoch": 2.3408360128617365,
+      "grad_norm": 0.12372130155563354,
+      "learning_rate": 7.161654135338345e-05,
+      "loss": 0.9887,
+      "step": 910
+    },
+    {
+      "epoch": 2.3665594855305465,
+      "grad_norm": 0.1307709813117981,
+      "learning_rate": 6.8796992481203e-05,
+      "loss": 0.9886,
+      "step": 920
+    },
+    {
+      "epoch": 2.392282958199357,
+      "grad_norm": 0.12701715528964996,
+      "learning_rate": 6.597744360902256e-05,
+      "loss": 0.9885,
+      "step": 930
+    },
+    {
+      "epoch": 2.418006430868167,
+      "grad_norm": 0.13114945590496063,
+      "learning_rate": 6.315789473684209e-05,
+      "loss": 0.9788,
+      "step": 940
+    },
+    {
+      "epoch": 2.4437299035369775,
+      "grad_norm": 0.12744566798210144,
+      "learning_rate": 6.033834586466165e-05,
+      "loss": 0.986,
+      "step": 950
+    },
+    {
+      "epoch": 2.469453376205788,
+      "grad_norm": 0.13428843021392822,
+      "learning_rate": 5.7518796992481194e-05,
+      "loss": 0.974,
+      "step": 960
+    },
+    {
+      "epoch": 2.495176848874598,
+      "grad_norm": 0.13112470507621765,
+      "learning_rate": 5.4699248120300746e-05,
+      "loss": 0.9818,
+      "step": 970
+    },
+    {
+      "epoch": 2.5209003215434085,
+      "grad_norm": 0.1363256722688675,
+      "learning_rate": 5.187969924812029e-05,
+      "loss": 0.9909,
+      "step": 980
+    },
+    {
+      "epoch": 2.5466237942122185,
+      "grad_norm": 0.13036535680294037,
+      "learning_rate": 4.9060150375939844e-05,
+      "loss": 0.9921,
+      "step": 990
+    },
+    {
+      "epoch": 2.572347266881029,
+      "grad_norm": 0.13345099985599518,
+      "learning_rate": 4.624060150375939e-05,
+      "loss": 0.9722,
+      "step": 1000
+    },
+    {
+      "epoch": 2.572347266881029,
+      "eval_loss": 1.000998854637146,
+      "eval_runtime": 55.4742,
+      "eval_samples_per_second": 36.053,
+      "eval_steps_per_second": 4.507,
+      "step": 1000
+    },
+    {
+      "epoch": 2.598070739549839,
+      "grad_norm": 0.12475313246250153,
+      "learning_rate": 4.342105263157895e-05,
+      "loss": 0.973,
+      "step": 1010
+    },
+    {
+      "epoch": 2.6237942122186495,
+      "grad_norm": 0.13274677097797394,
+      "learning_rate": 4.060150375939849e-05,
+      "loss": 0.9904,
+      "step": 1020
+    },
+    {
+      "epoch": 2.64951768488746,
+      "grad_norm": 0.1265428215265274,
+      "learning_rate": 3.7781954887218046e-05,
+      "loss": 0.9817,
+      "step": 1030
+    },
+    {
+      "epoch": 2.67524115755627,
+      "grad_norm": 0.13538296520709991,
+      "learning_rate": 3.496240601503759e-05,
+      "loss": 0.9721,
+      "step": 1040
+    },
+    {
+      "epoch": 2.7009646302250805,
+      "grad_norm": 0.1293276697397232,
+      "learning_rate": 3.214285714285714e-05,
+      "loss": 0.9799,
+      "step": 1050
+    },
+    {
+      "epoch": 2.7266881028938905,
+      "grad_norm": 0.12871681153774261,
+      "learning_rate": 2.9323308270676686e-05,
+      "loss": 0.9944,
+      "step": 1060
+    },
+    {
+      "epoch": 2.752411575562701,
+      "grad_norm": 0.13096405565738678,
+      "learning_rate": 2.6503759398496238e-05,
+      "loss": 0.9788,
+      "step": 1070
+    },
+    {
+      "epoch": 2.778135048231511,
+      "grad_norm": 0.1427333801984787,
+      "learning_rate": 2.3684210526315787e-05,
+      "loss": 0.9701,
+      "step": 1080
+    },
+    {
+      "epoch": 2.8038585209003215,
+      "grad_norm": 0.1345263570547104,
+      "learning_rate": 2.0864661654135336e-05,
+      "loss": 0.9786,
+      "step": 1090
+    },
+    {
+      "epoch": 2.829581993569132,
+      "grad_norm": 0.12688259780406952,
+      "learning_rate": 1.8045112781954885e-05,
+      "loss": 0.9705,
+      "step": 1100
+    },
+    {
+      "epoch": 2.855305466237942,
+      "grad_norm": 0.12778617441654205,
+      "learning_rate": 1.5225563909774434e-05,
+      "loss": 0.9824,
+      "step": 1110
+    },
+    {
+      "epoch": 2.8810289389067525,
+      "grad_norm": 0.1293039619922638,
+      "learning_rate": 1.2406015037593982e-05,
+      "loss": 0.9892,
+      "step": 1120
+    },
+    {
+      "epoch": 2.906752411575563,
+      "grad_norm": 0.1282673329114914,
+      "learning_rate": 9.586466165413533e-06,
+      "loss": 0.9799,
+      "step": 1130
+    },
+    {
+      "epoch": 2.932475884244373,
+      "grad_norm": 0.12761889398097992,
+      "learning_rate": 6.766917293233082e-06,
+      "loss": 0.9863,
+      "step": 1140
+    },
+    {
+      "epoch": 2.958199356913183,
+      "grad_norm": 0.13192933797836304,
+      "learning_rate": 3.947368421052631e-06,
+      "loss": 0.9882,
+      "step": 1150
+    },
+    {
+      "epoch": 2.9839228295819935,
+      "grad_norm": 0.12644025683403015,
+      "learning_rate": 1.1278195488721803e-06,
+      "loss": 0.9667,
+      "step": 1160
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1164,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.2857331693584384e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1164/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5844d0b7bf295f3ab4a8da73232006a40fc200ad74a77a9010df10478b55d69
+size 5240

checkpoint-800/README.md

@@ -0,0 +1,202 @@
+---
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+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 0.13.3.dev0

checkpoint-800/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+  "bias": "none",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-800/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca826ab76b1222fa6e476b76e62ba73868fd2f9406c00b29f80b40a006013264
+size 18045856

checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64a0ea63545bfcea03ee0fa43ebf324f88059c21a61ddde9a7ce61752718b06d
+size 36192634

checkpoint-800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1db5c74dcbf0daf8022fe86c1aec8f2c02d5ef5627cb8b909eab8c6e50ebdcd7
+size 14244

checkpoint-800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d52c6171b507f35f951a06698eb1d668be5d777104d184922d1b62147ff7cc55
+size 1064

checkpoint-800/trainer_state.json

@@ -0,0 +1,625 @@
+{
+  "best_metric": 1.0042115449905396,
+  "best_model_checkpoint": "./lora-alpaca3/checkpoint-800",
+  "epoch": 2.057877813504823,
+  "eval_steps": 200,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02572347266881029,
+      "grad_norm": 0.5646638870239258,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.9009,
+      "step": 10
+    },
+    {
+      "epoch": 0.05144694533762058,
+      "grad_norm": 0.5377612709999084,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 1.8355,
+      "step": 20
+    },
+    {
+      "epoch": 0.07717041800643087,
+      "grad_norm": 0.5958595871925354,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 1.6639,
+      "step": 30
+    },
+    {
+      "epoch": 0.10289389067524116,
+      "grad_norm": 0.5721263885498047,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.3994,
+      "step": 40
+    },
+    {
+      "epoch": 0.12861736334405144,
+      "grad_norm": 0.2665337026119232,
+      "learning_rate": 0.00015,
+      "loss": 1.1767,
+      "step": 50
+    },
+    {
+      "epoch": 0.15434083601286175,
+      "grad_norm": 0.12332847714424133,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 1.1413,
+      "step": 60
+    },
+    {
+      "epoch": 0.18006430868167203,
+      "grad_norm": 0.12157242000102997,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 1.1103,
+      "step": 70
+    },
+    {
+      "epoch": 0.2057877813504823,
+      "grad_norm": 0.12799611687660217,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 1.1003,
+      "step": 80
+    },
+    {
+      "epoch": 0.2315112540192926,
+      "grad_norm": 0.12139850109815598,
+      "learning_rate": 0.00027,
+      "loss": 1.084,
+      "step": 90
+    },
+    {
+      "epoch": 0.2572347266881029,
+      "grad_norm": 0.144248366355896,
+      "learning_rate": 0.0003,
+      "loss": 1.0722,
+      "step": 100
+    },
+    {
+      "epoch": 0.2829581993569132,
+      "grad_norm": 0.15326175093650818,
+      "learning_rate": 0.00029718045112781953,
+      "loss": 1.0731,
+      "step": 110
+    },
+    {
+      "epoch": 0.3086816720257235,
+      "grad_norm": 0.12561754882335663,
+      "learning_rate": 0.00029436090225563904,
+      "loss": 1.0537,
+      "step": 120
+    },
+    {
+      "epoch": 0.33440514469453375,
+      "grad_norm": 0.15570670366287231,
+      "learning_rate": 0.0002915413533834586,
+      "loss": 1.049,
+      "step": 130
+    },
+    {
+      "epoch": 0.36012861736334406,
+      "grad_norm": 0.14343878626823425,
+      "learning_rate": 0.00028872180451127816,
+      "loss": 1.0273,
+      "step": 140
+    },
+    {
+      "epoch": 0.3858520900321543,
+      "grad_norm": 0.1315772831439972,
+      "learning_rate": 0.0002859022556390977,
+      "loss": 1.0529,
+      "step": 150
+    },
+    {
+      "epoch": 0.4115755627009646,
+      "grad_norm": 0.13874055445194244,
+      "learning_rate": 0.0002830827067669173,
+      "loss": 1.044,
+      "step": 160
+    },
+    {
+      "epoch": 0.43729903536977494,
+      "grad_norm": 0.1271531730890274,
+      "learning_rate": 0.00028026315789473683,
+      "loss": 1.0388,
+      "step": 170
+    },
+    {
+      "epoch": 0.4630225080385852,
+      "grad_norm": 0.12684497237205505,
+      "learning_rate": 0.0002774436090225564,
+      "loss": 1.0385,
+      "step": 180
+    },
+    {
+      "epoch": 0.4887459807073955,
+      "grad_norm": 0.11675913631916046,
+      "learning_rate": 0.0002746240601503759,
+      "loss": 1.0349,
+      "step": 190
+    },
+    {
+      "epoch": 0.5144694533762058,
+      "grad_norm": 0.15151233971118927,
+      "learning_rate": 0.00027180451127819546,
+      "loss": 1.0282,
+      "step": 200
+    },
+    {
+      "epoch": 0.5144694533762058,
+      "eval_loss": 1.0400722026824951,
+      "eval_runtime": 55.5366,
+      "eval_samples_per_second": 36.012,
+      "eval_steps_per_second": 4.502,
+      "step": 200
+    },
+    {
+      "epoch": 0.5401929260450161,
+      "grad_norm": 0.1420961171388626,
+      "learning_rate": 0.000268984962406015,
+      "loss": 1.0297,
+      "step": 210
+    },
+    {
+      "epoch": 0.5659163987138264,
+      "grad_norm": 0.13161741197109222,
+      "learning_rate": 0.0002661654135338346,
+      "loss": 1.0276,
+      "step": 220
+    },
+    {
+      "epoch": 0.5916398713826366,
+      "grad_norm": 0.13450871407985687,
+      "learning_rate": 0.00026334586466165413,
+      "loss": 1.0285,
+      "step": 230
+    },
+    {
+      "epoch": 0.617363344051447,
+      "grad_norm": 0.13193918764591217,
+      "learning_rate": 0.0002605263157894737,
+      "loss": 1.0309,
+      "step": 240
+    },
+    {
+      "epoch": 0.6430868167202572,
+      "grad_norm": 0.1393500566482544,
+      "learning_rate": 0.0002577067669172932,
+      "loss": 1.0315,
+      "step": 250
+    },
+    {
+      "epoch": 0.6688102893890675,
+      "grad_norm": 0.11902929842472076,
+      "learning_rate": 0.00025488721804511276,
+      "loss": 1.0347,
+      "step": 260
+    },
+    {
+      "epoch": 0.6945337620578779,
+      "grad_norm": 0.1258976310491562,
+      "learning_rate": 0.0002520676691729323,
+      "loss": 1.0273,
+      "step": 270
+    },
+    {
+      "epoch": 0.7202572347266881,
+      "grad_norm": 0.12598267197608948,
+      "learning_rate": 0.0002492481203007519,
+      "loss": 1.0128,
+      "step": 280
+    },
+    {
+      "epoch": 0.7459807073954984,
+      "grad_norm": 0.122463159263134,
+      "learning_rate": 0.0002464285714285714,
+      "loss": 1.0251,
+      "step": 290
+    },
+    {
+      "epoch": 0.7717041800643086,
+      "grad_norm": 0.1293506771326065,
+      "learning_rate": 0.00024360902255639094,
+      "loss": 1.0317,
+      "step": 300
+    },
+    {
+      "epoch": 0.797427652733119,
+      "grad_norm": 0.13788191974163055,
+      "learning_rate": 0.00024078947368421052,
+      "loss": 1.029,
+      "step": 310
+    },
+    {
+      "epoch": 0.8231511254019293,
+      "grad_norm": 0.1445332169532776,
+      "learning_rate": 0.00023796992481203005,
+      "loss": 1.0173,
+      "step": 320
+    },
+    {
+      "epoch": 0.8488745980707395,
+      "grad_norm": 0.11408714205026627,
+      "learning_rate": 0.00023515037593984961,
+      "loss": 1.0109,
+      "step": 330
+    },
+    {
+      "epoch": 0.8745980707395499,
+      "grad_norm": 0.11767855286598206,
+      "learning_rate": 0.00023233082706766915,
+      "loss": 1.0116,
+      "step": 340
+    },
+    {
+      "epoch": 0.9003215434083601,
+      "grad_norm": 0.12555481493473053,
+      "learning_rate": 0.0002295112781954887,
+      "loss": 1.0144,
+      "step": 350
+    },
+    {
+      "epoch": 0.9260450160771704,
+      "grad_norm": 0.12403016537427902,
+      "learning_rate": 0.00022669172932330824,
+      "loss": 1.0299,
+      "step": 360
+    },
+    {
+      "epoch": 0.9517684887459807,
+      "grad_norm": 0.12968535721302032,
+      "learning_rate": 0.0002238721804511278,
+      "loss": 1.0081,
+      "step": 370
+    },
+    {
+      "epoch": 0.977491961414791,
+      "grad_norm": 0.12369370460510254,
+      "learning_rate": 0.00022105263157894733,
+      "loss": 1.0065,
+      "step": 380
+    },
+    {
+      "epoch": 1.0032154340836013,
+      "grad_norm": 0.12212081998586655,
+      "learning_rate": 0.0002182330827067669,
+      "loss": 1.0448,
+      "step": 390
+    },
+    {
+      "epoch": 1.0289389067524115,
+      "grad_norm": 0.1301109939813614,
+      "learning_rate": 0.00021541353383458647,
+      "loss": 1.0052,
+      "step": 400
+    },
+    {
+      "epoch": 1.0289389067524115,
+      "eval_loss": 1.0189071893692017,
+      "eval_runtime": 55.4593,
+      "eval_samples_per_second": 36.062,
+      "eval_steps_per_second": 4.508,
+      "step": 400
+    },
+    {
+      "epoch": 1.0546623794212218,
+      "grad_norm": 0.13505908846855164,
+      "learning_rate": 0.000212593984962406,
+      "loss": 1.0009,
+      "step": 410
+    },
+    {
+      "epoch": 1.0803858520900322,
+      "grad_norm": 0.12307268381118774,
+      "learning_rate": 0.00020977443609022556,
+      "loss": 1.0039,
+      "step": 420
+    },
+    {
+      "epoch": 1.1061093247588425,
+      "grad_norm": 0.11501840502023697,
+      "learning_rate": 0.0002069548872180451,
+      "loss": 0.9988,
+      "step": 430
+    },
+    {
+      "epoch": 1.1318327974276527,
+      "grad_norm": 0.12922251224517822,
+      "learning_rate": 0.00020413533834586463,
+      "loss": 0.9938,
+      "step": 440
+    },
+    {
+      "epoch": 1.157556270096463,
+      "grad_norm": 0.12304320186376572,
+      "learning_rate": 0.0002013157894736842,
+      "loss": 1.0223,
+      "step": 450
+    },
+    {
+      "epoch": 1.1832797427652733,
+      "grad_norm": 0.11323860287666321,
+      "learning_rate": 0.00019849624060150372,
+      "loss": 0.9957,
+      "step": 460
+    },
+    {
+      "epoch": 1.2090032154340835,
+      "grad_norm": 0.1335834562778473,
+      "learning_rate": 0.00019567669172932328,
+      "loss": 1.0042,
+      "step": 470
+    },
+    {
+      "epoch": 1.234726688102894,
+      "grad_norm": 0.12371603399515152,
+      "learning_rate": 0.00019285714285714286,
+      "loss": 1.0056,
+      "step": 480
+    },
+    {
+      "epoch": 1.2604501607717042,
+      "grad_norm": 0.12318002432584763,
+      "learning_rate": 0.0001900375939849624,
+      "loss": 1.0122,
+      "step": 490
+    },
+    {
+      "epoch": 1.2861736334405145,
+      "grad_norm": 0.13187570869922638,
+      "learning_rate": 0.00018721804511278195,
+      "loss": 0.9971,
+      "step": 500
+    },
+    {
+      "epoch": 1.3118971061093248,
+      "grad_norm": 0.11861589550971985,
+      "learning_rate": 0.00018439849624060149,
+      "loss": 0.9926,
+      "step": 510
+    },
+    {
+      "epoch": 1.337620578778135,
+      "grad_norm": 0.11287492513656616,
+      "learning_rate": 0.00018157894736842105,
+      "loss": 1.016,
+      "step": 520
+    },
+    {
+      "epoch": 1.3633440514469453,
+      "grad_norm": 0.1384376585483551,
+      "learning_rate": 0.00017875939849624058,
+      "loss": 1.0059,
+      "step": 530
+    },
+    {
+      "epoch": 1.3890675241157555,
+      "grad_norm": 0.12147587537765503,
+      "learning_rate": 0.00017593984962406014,
+      "loss": 1.0213,
+      "step": 540
+    },
+    {
+      "epoch": 1.414790996784566,
+      "grad_norm": 0.13031207025051117,
+      "learning_rate": 0.00017312030075187967,
+      "loss": 1.005,
+      "step": 550
+    },
+    {
+      "epoch": 1.4405144694533762,
+      "grad_norm": 0.13779744505882263,
+      "learning_rate": 0.00017030075187969925,
+      "loss": 1.0077,
+      "step": 560
+    },
+    {
+      "epoch": 1.4662379421221865,
+      "grad_norm": 0.13196057081222534,
+      "learning_rate": 0.00016748120300751879,
+      "loss": 0.9944,
+      "step": 570
+    },
+    {
+      "epoch": 1.4919614147909968,
+      "grad_norm": 0.117030069231987,
+      "learning_rate": 0.00016466165413533835,
+      "loss": 1.0082,
+      "step": 580
+    },
+    {
+      "epoch": 1.517684887459807,
+      "grad_norm": 0.1274162381887436,
+      "learning_rate": 0.00016184210526315788,
+      "loss": 1.0102,
+      "step": 590
+    },
+    {
+      "epoch": 1.5434083601286175,
+      "grad_norm": 0.13315673172473907,
+      "learning_rate": 0.00015902255639097744,
+      "loss": 0.985,
+      "step": 600
+    },
+    {
+      "epoch": 1.5434083601286175,
+      "eval_loss": 1.0096462965011597,
+      "eval_runtime": 55.507,
+      "eval_samples_per_second": 36.031,
+      "eval_steps_per_second": 4.504,
+      "step": 600
+    },
+    {
+      "epoch": 1.5691318327974275,
+      "grad_norm": 0.12220187485218048,
+      "learning_rate": 0.00015620300751879697,
+      "loss": 0.9912,
+      "step": 610
+    },
+    {
+      "epoch": 1.594855305466238,
+      "grad_norm": 0.12432006746530533,
+      "learning_rate": 0.00015338345864661653,
+      "loss": 0.9963,
+      "step": 620
+    },
+    {
+      "epoch": 1.6205787781350482,
+      "grad_norm": 0.12138667702674866,
+      "learning_rate": 0.00015056390977443606,
+      "loss": 1.0014,
+      "step": 630
+    },
+    {
+      "epoch": 1.6463022508038585,
+      "grad_norm": 0.13801203668117523,
+      "learning_rate": 0.00014774436090225562,
+      "loss": 0.9922,
+      "step": 640
+    },
+    {
+      "epoch": 1.6720257234726688,
+      "grad_norm": 0.13330678641796112,
+      "learning_rate": 0.00014492481203007518,
+      "loss": 0.9897,
+      "step": 650
+    },
+    {
+      "epoch": 1.697749196141479,
+      "grad_norm": 0.12127404659986496,
+      "learning_rate": 0.0001421052631578947,
+      "loss": 0.9898,
+      "step": 660
+    },
+    {
+      "epoch": 1.7234726688102895,
+      "grad_norm": 0.13159097731113434,
+      "learning_rate": 0.00013928571428571427,
+      "loss": 0.9943,
+      "step": 670
+    },
+    {
+      "epoch": 1.7491961414790995,
+      "grad_norm": 0.13246209919452667,
+      "learning_rate": 0.00013646616541353383,
+      "loss": 1.0048,
+      "step": 680
+    },
+    {
+      "epoch": 1.77491961414791,
+      "grad_norm": 0.11693169921636581,
+      "learning_rate": 0.00013364661654135336,
+      "loss": 0.9996,
+      "step": 690
+    },
+    {
+      "epoch": 1.8006430868167203,
+      "grad_norm": 0.13176512718200684,
+      "learning_rate": 0.00013082706766917292,
+      "loss": 0.9923,
+      "step": 700
+    },
+    {
+      "epoch": 1.8263665594855305,
+      "grad_norm": 0.1224486380815506,
+      "learning_rate": 0.00012800751879699248,
+      "loss": 0.9799,
+      "step": 710
+    },
+    {
+      "epoch": 1.852090032154341,
+      "grad_norm": 0.12146233022212982,
+      "learning_rate": 0.000125187969924812,
+      "loss": 0.9874,
+      "step": 720
+    },
+    {
+      "epoch": 1.877813504823151,
+      "grad_norm": 0.12821047008037567,
+      "learning_rate": 0.00012236842105263157,
+      "loss": 0.9982,
+      "step": 730
+    },
+    {
+      "epoch": 1.9035369774919615,
+      "grad_norm": 0.12273906171321869,
+      "learning_rate": 0.00011954887218045111,
+      "loss": 0.9946,
+      "step": 740
+    },
+    {
+      "epoch": 1.9292604501607717,
+      "grad_norm": 0.1282244175672531,
+      "learning_rate": 0.00011672932330827067,
+      "loss": 0.9976,
+      "step": 750
+    },
+    {
+      "epoch": 1.954983922829582,
+      "grad_norm": 0.13315148651599884,
+      "learning_rate": 0.00011390977443609022,
+      "loss": 1.0012,
+      "step": 760
+    },
+    {
+      "epoch": 1.9807073954983923,
+      "grad_norm": 0.12510079145431519,
+      "learning_rate": 0.00011109022556390976,
+      "loss": 0.9865,
+      "step": 770
+    },
+    {
+      "epoch": 2.0064308681672025,
+      "grad_norm": 0.11581259220838547,
+      "learning_rate": 0.00010827067669172931,
+      "loss": 1.0306,
+      "step": 780
+    },
+    {
+      "epoch": 2.032154340836013,
+      "grad_norm": 0.1278076171875,
+      "learning_rate": 0.00010545112781954887,
+      "loss": 0.9984,
+      "step": 790
+    },
+    {
+      "epoch": 2.057877813504823,
+      "grad_norm": 0.12879391014575958,
+      "learning_rate": 0.00010263157894736841,
+      "loss": 0.9729,
+      "step": 800
+    },
+    {
+      "epoch": 2.057877813504823,
+      "eval_loss": 1.0042115449905396,
+      "eval_runtime": 55.4463,
+      "eval_samples_per_second": 36.071,
+      "eval_steps_per_second": 4.509,
+      "step": 800
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1164,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 1.569606731295621e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5844d0b7bf295f3ab4a8da73232006a40fc200ad74a77a9010df10478b55d69
+size 5240