Training in progress, epoch 4, checkpoint

checkpoint-62276/README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/deepseek-coder-6.7b-base
+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 0.14.0

checkpoint-62276/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-base",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-62276/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bd2075257dc60022dec176f8c5ef84b3d8a35e6e33f8ff28e44c14213a35599
+size 541459256

checkpoint-62276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cff19f1f2a4a0fa47ee10dbef3975b06fc611250628b1c3008ea7aa1324870e
+size 33662074

checkpoint-62276/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17e27cce27a3adebd43cd97f49be3e287c3da8de4b9072ff63b8822a0ff9c0d5
+size 15024

checkpoint-62276/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc4a9cbc8cf99102adf1c616480d5c7c7d74f10a7e0c30fc953d4598f4c206b6
+size 15024

checkpoint-62276/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86c051ae7571c14ba105db6754b04cff1576042a697328bbb6022c4144de8b1f
+size 15024

checkpoint-62276/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e6c7c330657357a31f12e444837363f4e42dc5d86923518163ba25e4a05f5f0
+size 15024

checkpoint-62276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b008a9ed34f40406a40960dd92611a75924808ad76d51b65b336b30b0fa2b6e7
+size 1064

checkpoint-62276/trainer_state.json

@@ -0,0 +1,1053 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 3114,
+  "global_step": 62276,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03211510052026463,
+      "grad_norm": 1.1439628601074219,
+      "learning_rate": 0.0003989316376560259,
+      "loss": 0.639,
+      "step": 500
+    },
+    {
+      "epoch": 0.06423020104052926,
+      "grad_norm": 1.0822333097457886,
+      "learning_rate": 0.00039786327531205173,
+      "loss": 0.4284,
+      "step": 1000
+    },
+    {
+      "epoch": 0.09634530156079389,
+      "grad_norm": 0.8050562143325806,
+      "learning_rate": 0.00039679277196137626,
+      "loss": 0.3927,
+      "step": 1500
+    },
+    {
+      "epoch": 0.12846040208105852,
+      "grad_norm": 0.669165849685669,
+      "learning_rate": 0.00039572440961740214,
+      "loss": 0.3689,
+      "step": 2000
+    },
+    {
+      "epoch": 0.16057550260132314,
+      "grad_norm": 1.5822824239730835,
+      "learning_rate": 0.0003946539062667266,
+      "loss": 0.3504,
+      "step": 2500
+    },
+    {
+      "epoch": 0.19269060312158778,
+      "grad_norm": 0.8457300066947937,
+      "learning_rate": 0.00039358340291605114,
+      "loss": 0.3446,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2000128460402081,
+      "eval_loss": 0.1640966236591339,
+      "eval_runtime": 10.7566,
+      "eval_samples_per_second": 46.483,
+      "eval_steps_per_second": 5.857,
+      "step": 3114
+    },
+    {
+      "epoch": 0.2248057036418524,
+      "grad_norm": 0.8258726596832275,
+      "learning_rate": 0.00039251289956537567,
+      "loss": 0.3324,
+      "step": 3500
+    },
+    {
+      "epoch": 0.25692080416211704,
+      "grad_norm": 0.8330244421958923,
+      "learning_rate": 0.0003914445372214015,
+      "loss": 0.3278,
+      "step": 4000
+    },
+    {
+      "epoch": 0.28903590468238166,
+      "grad_norm": 1.5903249979019165,
+      "learning_rate": 0.000390374033870726,
+      "loss": 0.3235,
+      "step": 4500
+    },
+    {
+      "epoch": 0.3211510052026463,
+      "grad_norm": 1.216776728630066,
+      "learning_rate": 0.00038930353052005055,
+      "loss": 0.3113,
+      "step": 5000
+    },
+    {
+      "epoch": 0.3532661057229109,
+      "grad_norm": 0.974801778793335,
+      "learning_rate": 0.000388233027169375,
+      "loss": 0.309,
+      "step": 5500
+    },
+    {
+      "epoch": 0.38538120624317557,
+      "grad_norm": 0.7021324634552002,
+      "learning_rate": 0.00038716252381869955,
+      "loss": 0.305,
+      "step": 6000
+    },
+    {
+      "epoch": 0.4000256920804162,
+      "eval_loss": 0.14873231947422028,
+      "eval_runtime": 10.7638,
+      "eval_samples_per_second": 46.452,
+      "eval_steps_per_second": 5.853,
+      "step": 6228
+    },
+    {
+      "epoch": 0.4174963067634402,
+      "grad_norm": 0.8934990167617798,
+      "learning_rate": 0.0003860920204680241,
+      "loss": 0.3013,
+      "step": 6500
+    },
+    {
+      "epoch": 0.4496114072837048,
+      "grad_norm": 0.8211339712142944,
+      "learning_rate": 0.00038502365812404996,
+      "loss": 0.2955,
+      "step": 7000
+    },
+    {
+      "epoch": 0.4817265078039694,
+      "grad_norm": 1.5795360803604126,
+      "learning_rate": 0.0003839531547733745,
+      "loss": 0.295,
+      "step": 7500
+    },
+    {
+      "epoch": 0.5138416083242341,
+      "grad_norm": 0.8220022916793823,
+      "learning_rate": 0.000382882651422699,
+      "loss": 0.2887,
+      "step": 8000
+    },
+    {
+      "epoch": 0.5459567088444987,
+      "grad_norm": 0.8150618672370911,
+      "learning_rate": 0.00038181428907872484,
+      "loss": 0.2883,
+      "step": 8500
+    },
+    {
+      "epoch": 0.5780718093647633,
+      "grad_norm": 0.782720148563385,
+      "learning_rate": 0.00038074378572804937,
+      "loss": 0.2848,
+      "step": 9000
+    },
+    {
+      "epoch": 0.6000385381206244,
+      "eval_loss": 0.1397342085838318,
+      "eval_runtime": 10.7618,
+      "eval_samples_per_second": 46.461,
+      "eval_steps_per_second": 5.854,
+      "step": 9342
+    },
+    {
+      "epoch": 0.610186909885028,
+      "grad_norm": 1.1356905698776245,
+      "learning_rate": 0.0003796732823773739,
+      "loss": 0.2792,
+      "step": 9500
+    },
+    {
+      "epoch": 0.6423020104052926,
+      "grad_norm": 1.3606605529785156,
+      "learning_rate": 0.00037860277902669837,
+      "loss": 0.279,
+      "step": 10000
+    },
+    {
+      "epoch": 0.6744171109255572,
+      "grad_norm": 0.8823058009147644,
+      "learning_rate": 0.0003775322756760229,
+      "loss": 0.2795,
+      "step": 10500
+    },
+    {
+      "epoch": 0.7065322114458218,
+      "grad_norm": 0.6812245845794678,
+      "learning_rate": 0.00037646819534545143,
+      "loss": 0.2806,
+      "step": 11000
+    },
+    {
+      "epoch": 0.7386473119660865,
+      "grad_norm": 0.8636330366134644,
+      "learning_rate": 0.00037539769199477596,
+      "loss": 0.278,
+      "step": 11500
+    },
+    {
+      "epoch": 0.7707624124863511,
+      "grad_norm": 0.7633821368217468,
+      "learning_rate": 0.0003743271886441005,
+      "loss": 0.2755,
+      "step": 12000
+    },
+    {
+      "epoch": 0.8000513841608324,
+      "eval_loss": 0.1333352029323578,
+      "eval_runtime": 10.784,
+      "eval_samples_per_second": 46.365,
+      "eval_steps_per_second": 5.842,
+      "step": 12456
+    },
+    {
+      "epoch": 0.8028775130066157,
+      "grad_norm": 0.9501471519470215,
+      "learning_rate": 0.000373256685293425,
+      "loss": 0.2739,
+      "step": 12500
+    },
+    {
+      "epoch": 0.8349926135268804,
+      "grad_norm": 0.6604846119880676,
+      "learning_rate": 0.0003721861819427495,
+      "loss": 0.2709,
+      "step": 13000
+    },
+    {
+      "epoch": 0.8671077140471449,
+      "grad_norm": 0.743561863899231,
+      "learning_rate": 0.000371115678592074,
+      "loss": 0.2679,
+      "step": 13500
+    },
+    {
+      "epoch": 0.8992228145674096,
+      "grad_norm": 0.7072339057922363,
+      "learning_rate": 0.00037004517524139854,
+      "loss": 0.272,
+      "step": 14000
+    },
+    {
+      "epoch": 0.9313379150876743,
+      "grad_norm": 0.9728062152862549,
+      "learning_rate": 0.000368974671890723,
+      "loss": 0.2681,
+      "step": 14500
+    },
+    {
+      "epoch": 0.9634530156079388,
+      "grad_norm": 0.8511360287666321,
+      "learning_rate": 0.00036790416854004754,
+      "loss": 0.264,
+      "step": 15000
+    },
+    {
+      "epoch": 0.9955681161282035,
+      "grad_norm": 1.0181396007537842,
+      "learning_rate": 0.00036683366518937207,
+      "loss": 0.2646,
+      "step": 15500
+    },
+    {
+      "epoch": 1.0000642302010405,
+      "eval_loss": 0.13280069828033447,
+      "eval_runtime": 10.8292,
+      "eval_samples_per_second": 46.172,
+      "eval_steps_per_second": 5.818,
+      "step": 15570
+    },
+    {
+      "epoch": 1.0276832166484682,
+      "grad_norm": 0.8521600365638733,
+      "learning_rate": 0.0003657631618386966,
+      "loss": 0.2491,
+      "step": 16000
+    },
+    {
+      "epoch": 1.0597983171687329,
+      "grad_norm": 0.7927277088165283,
+      "learning_rate": 0.00036469265848802107,
+      "loss": 0.2486,
+      "step": 16500
+    },
+    {
+      "epoch": 1.0919134176889973,
+      "grad_norm": 0.9500927329063416,
+      "learning_rate": 0.0003636221551373456,
+      "loss": 0.2461,
+      "step": 17000
+    },
+    {
+      "epoch": 1.124028518209262,
+      "grad_norm": 1.1854805946350098,
+      "learning_rate": 0.0003625516517866701,
+      "loss": 0.2478,
+      "step": 17500
+    },
+    {
+      "epoch": 1.1561436187295266,
+      "grad_norm": 1.0004955530166626,
+      "learning_rate": 0.0003614811484359946,
+      "loss": 0.2485,
+      "step": 18000
+    },
+    {
+      "epoch": 1.1882587192497913,
+      "grad_norm": 0.7761235237121582,
+      "learning_rate": 0.0003604106450853191,
+      "loss": 0.2486,
+      "step": 18500
+    },
+    {
+      "epoch": 1.2000770762412487,
+      "eval_loss": 0.12181619554758072,
+      "eval_runtime": 10.792,
+      "eval_samples_per_second": 46.331,
+      "eval_steps_per_second": 5.838,
+      "step": 18684
+    },
+    {
+      "epoch": 1.2203738197700558,
+      "grad_norm": 1.0295982360839844,
+      "learning_rate": 0.00035934014173464365,
+      "loss": 0.247,
+      "step": 19000
+    },
+    {
+      "epoch": 1.2524889202903204,
+      "grad_norm": 1.0462840795516968,
+      "learning_rate": 0.0003582717793906695,
+      "loss": 0.2451,
+      "step": 19500
+    },
+    {
+      "epoch": 1.2846040208105851,
+      "grad_norm": 0.7392880320549011,
+      "learning_rate": 0.00035720341704669536,
+      "loss": 0.2465,
+      "step": 20000
+    },
+    {
+      "epoch": 1.3167191213308498,
+      "grad_norm": 0.9569768905639648,
+      "learning_rate": 0.0003561329136960199,
+      "loss": 0.2451,
+      "step": 20500
+    },
+    {
+      "epoch": 1.3488342218511145,
+      "grad_norm": 0.813721239566803,
+      "learning_rate": 0.00035506241034534436,
+      "loss": 0.2382,
+      "step": 21000
+    },
+    {
+      "epoch": 1.3809493223713791,
+      "grad_norm": 0.6308742761611938,
+      "learning_rate": 0.00035399190699466894,
+      "loss": 0.2438,
+      "step": 21500
+    },
+    {
+      "epoch": 1.4000899222814567,
+      "eval_loss": 0.12308382242918015,
+      "eval_runtime": 10.7957,
+      "eval_samples_per_second": 46.315,
+      "eval_steps_per_second": 5.836,
+      "step": 21798
+    },
+    {
+      "epoch": 1.4130644228916436,
+      "grad_norm": 1.429039478302002,
+      "learning_rate": 0.00035292140364399346,
+      "loss": 0.2407,
+      "step": 22000
+    },
+    {
+      "epoch": 1.4451795234119083,
+      "grad_norm": 0.6953487396240234,
+      "learning_rate": 0.00035185090029331794,
+      "loss": 0.2423,
+      "step": 22500
+    },
+    {
+      "epoch": 1.477294623932173,
+      "grad_norm": 0.7806856632232666,
+      "learning_rate": 0.00035078039694264246,
+      "loss": 0.2406,
+      "step": 23000
+    },
+    {
+      "epoch": 1.5094097244524374,
+      "grad_norm": 1.0611233711242676,
+      "learning_rate": 0.00034971203459866835,
+      "loss": 0.2389,
+      "step": 23500
+    },
+    {
+      "epoch": 1.541524824972702,
+      "grad_norm": 1.0411138534545898,
+      "learning_rate": 0.0003486415312479928,
+      "loss": 0.2405,
+      "step": 24000
+    },
+    {
+      "epoch": 1.5736399254929667,
+      "grad_norm": 0.906801700592041,
+      "learning_rate": 0.00034757102789731735,
+      "loss": 0.2413,
+      "step": 24500
+    },
+    {
+      "epoch": 1.6001027683216649,
+      "eval_loss": 0.11771170794963837,
+      "eval_runtime": 10.8091,
+      "eval_samples_per_second": 46.257,
+      "eval_steps_per_second": 5.828,
+      "step": 24912
+    },
+    {
+      "epoch": 1.6057550260132314,
+      "grad_norm": 0.9656944274902344,
+      "learning_rate": 0.0003465005245466419,
+      "loss": 0.2423,
+      "step": 25000
+    },
+    {
+      "epoch": 1.637870126533496,
+      "grad_norm": 1.330808162689209,
+      "learning_rate": 0.00034543002119596635,
+      "loss": 0.2422,
+      "step": 25500
+    },
+    {
+      "epoch": 1.6699852270537607,
+      "grad_norm": 0.8894997835159302,
+      "learning_rate": 0.0003443637998586936,
+      "loss": 0.2338,
+      "step": 26000
+    },
+    {
+      "epoch": 1.7021003275740254,
+      "grad_norm": 1.0210765600204468,
+      "learning_rate": 0.0003432932965080181,
+      "loss": 0.2368,
+      "step": 26500
+    },
+    {
+      "epoch": 1.73421542809429,
+      "grad_norm": 1.0259859561920166,
+      "learning_rate": 0.0003422227931573426,
+      "loss": 0.2365,
+      "step": 27000
+    },
+    {
+      "epoch": 1.7663305286145545,
+      "grad_norm": 0.8963735103607178,
+      "learning_rate": 0.0003411522898066671,
+      "loss": 0.2332,
+      "step": 27500
+    },
+    {
+      "epoch": 1.7984456291348192,
+      "grad_norm": 0.9903491735458374,
+      "learning_rate": 0.00034008178645599164,
+      "loss": 0.2375,
+      "step": 28000
+    },
+    {
+      "epoch": 1.8001156143618728,
+      "eval_loss": 0.11729346960783005,
+      "eval_runtime": 10.8087,
+      "eval_samples_per_second": 46.259,
+      "eval_steps_per_second": 5.829,
+      "step": 28026
+    },
+    {
+      "epoch": 1.8305607296550839,
+      "grad_norm": 0.7195676565170288,
+      "learning_rate": 0.0003390112831053161,
+      "loss": 0.2394,
+      "step": 28500
+    },
+    {
+      "epoch": 1.8626758301753483,
+      "grad_norm": 0.9430277943611145,
+      "learning_rate": 0.00033794077975464064,
+      "loss": 0.2336,
+      "step": 29000
+    },
+    {
+      "epoch": 1.894790930695613,
+      "grad_norm": 1.1380141973495483,
+      "learning_rate": 0.00033687027640396516,
+      "loss": 0.2371,
+      "step": 29500
+    },
+    {
+      "epoch": 1.9269060312158777,
+      "grad_norm": 0.7525237202644348,
+      "learning_rate": 0.0003357997730532897,
+      "loss": 0.2337,
+      "step": 30000
+    },
+    {
+      "epoch": 1.9590211317361423,
+      "grad_norm": 0.90290766954422,
+      "learning_rate": 0.00033472926970261416,
+      "loss": 0.2327,
+      "step": 30500
+    },
+    {
+      "epoch": 1.991136232256407,
+      "grad_norm": 0.8463317155838013,
+      "learning_rate": 0.00033366090735864005,
+      "loss": 0.2326,
+      "step": 31000
+    },
+    {
+      "epoch": 2.000128460402081,
+      "eval_loss": 0.11661120504140854,
+      "eval_runtime": 10.8451,
+      "eval_samples_per_second": 46.104,
+      "eval_steps_per_second": 5.809,
+      "step": 31140
+    },
+    {
+      "epoch": 2.0232513327766717,
+      "grad_norm": 1.0980778932571411,
+      "learning_rate": 0.0003325904040079646,
+      "loss": 0.2242,
+      "step": 31500
+    },
+    {
+      "epoch": 2.0553664332969364,
+      "grad_norm": 0.7541905045509338,
+      "learning_rate": 0.00033151990065728905,
+      "loss": 0.2168,
+      "step": 32000
+    },
+    {
+      "epoch": 2.087481533817201,
+      "grad_norm": 0.9497644901275635,
+      "learning_rate": 0.00033045153831331493,
+      "loss": 0.2158,
+      "step": 32500
+    },
+    {
+      "epoch": 2.1195966343374657,
+      "grad_norm": 0.8374313116073608,
+      "learning_rate": 0.00032938103496263946,
+      "loss": 0.2176,
+      "step": 33000
+    },
+    {
+      "epoch": 2.15171173485773,
+      "grad_norm": 0.9000691175460815,
+      "learning_rate": 0.00032831053161196393,
+      "loss": 0.2152,
+      "step": 33500
+    },
+    {
+      "epoch": 2.1838268353779946,
+      "grad_norm": 1.0209734439849854,
+      "learning_rate": 0.00032724002826128846,
+      "loss": 0.2178,
+      "step": 34000
+    },
+    {
+      "epoch": 2.2001413064422892,
+      "eval_loss": 0.11470586806535721,
+      "eval_runtime": 10.8026,
+      "eval_samples_per_second": 46.285,
+      "eval_steps_per_second": 5.832,
+      "step": 34254
+    },
+    {
+      "epoch": 2.2159419358982593,
+      "grad_norm": 1.1995940208435059,
+      "learning_rate": 0.000326169524910613,
+      "loss": 0.2205,
+      "step": 34500
+    },
+    {
+      "epoch": 2.248057036418524,
+      "grad_norm": 0.8117247223854065,
+      "learning_rate": 0.00032509902155993746,
+      "loss": 0.2231,
+      "step": 35000
+    },
+    {
+      "epoch": 2.2801721369387886,
+      "grad_norm": 0.9178829789161682,
+      "learning_rate": 0.000324028518209262,
+      "loss": 0.2178,
+      "step": 35500
+    },
+    {
+      "epoch": 2.3122872374590533,
+      "grad_norm": 0.9355435371398926,
+      "learning_rate": 0.00032295801485858656,
+      "loss": 0.214,
+      "step": 36000
+    },
+    {
+      "epoch": 2.344402337979318,
+      "grad_norm": 1.0787150859832764,
+      "learning_rate": 0.00032188751150791104,
+      "loss": 0.2173,
+      "step": 36500
+    },
+    {
+      "epoch": 2.3765174384995826,
+      "grad_norm": 1.3570172786712646,
+      "learning_rate": 0.00032081700815723556,
+      "loss": 0.2187,
+      "step": 37000
+    },
+    {
+      "epoch": 2.4001541524824974,
+      "eval_loss": 0.11260252445936203,
+      "eval_runtime": 10.8252,
+      "eval_samples_per_second": 46.188,
+      "eval_steps_per_second": 5.82,
+      "step": 37368
+    },
+    {
+      "epoch": 2.4086325390198473,
+      "grad_norm": 0.6619197726249695,
+      "learning_rate": 0.0003197465048065601,
+      "loss": 0.2184,
+      "step": 37500
+    },
+    {
+      "epoch": 2.4407476395401115,
+      "grad_norm": 1.013967514038086,
+      "learning_rate": 0.00031867600145588456,
+      "loss": 0.2188,
+      "step": 38000
+    },
+    {
+      "epoch": 2.472862740060376,
+      "grad_norm": 0.8766270279884338,
+      "learning_rate": 0.0003176054981052091,
+      "loss": 0.2125,
+      "step": 38500
+    },
+    {
+      "epoch": 2.504977840580641,
+      "grad_norm": 0.7047364711761475,
+      "learning_rate": 0.00031653713576123497,
+      "loss": 0.2154,
+      "step": 39000
+    },
+    {
+      "epoch": 2.5370929411009056,
+      "grad_norm": 1.071646809577942,
+      "learning_rate": 0.00031546663241055944,
+      "loss": 0.2155,
+      "step": 39500
+    },
+    {
+      "epoch": 2.5692080416211702,
+      "grad_norm": 0.9847589731216431,
+      "learning_rate": 0.00031439612905988397,
+      "loss": 0.2196,
+      "step": 40000
+    },
+    {
+      "epoch": 2.600166998522705,
+      "eval_loss": 0.11102238297462463,
+      "eval_runtime": 10.8205,
+      "eval_samples_per_second": 46.209,
+      "eval_steps_per_second": 5.822,
+      "step": 40482
+    },
+    {
+      "epoch": 2.601323142141435,
+      "grad_norm": 1.3853163719177246,
+      "learning_rate": 0.0003133256257092085,
+      "loss": 0.2179,
+      "step": 40500
+    },
+    {
+      "epoch": 2.6334382426616996,
+      "grad_norm": 1.4334129095077515,
+      "learning_rate": 0.0003122572633652343,
+      "loss": 0.2137,
+      "step": 41000
+    },
+    {
+      "epoch": 2.6655533431819642,
+      "grad_norm": 0.9303542971611023,
+      "learning_rate": 0.00031118676001455885,
+      "loss": 0.2148,
+      "step": 41500
+    },
+    {
+      "epoch": 2.697668443702229,
+      "grad_norm": 0.8372798562049866,
+      "learning_rate": 0.0003101162566638834,
+      "loss": 0.2126,
+      "step": 42000
+    },
+    {
+      "epoch": 2.729783544222493,
+      "grad_norm": 1.1056691408157349,
+      "learning_rate": 0.0003090457533132079,
+      "loss": 0.2118,
+      "step": 42500
+    },
+    {
+      "epoch": 2.7618986447427583,
+      "grad_norm": 0.878703773021698,
+      "learning_rate": 0.00030797739096923374,
+      "loss": 0.2137,
+      "step": 43000
+    },
+    {
+      "epoch": 2.7940137452630225,
+      "grad_norm": 0.8215634822845459,
+      "learning_rate": 0.00030690688761855826,
+      "loss": 0.2163,
+      "step": 43500
+    },
+    {
+      "epoch": 2.8001798445629134,
+      "eval_loss": 0.10930783301591873,
+      "eval_runtime": 10.8133,
+      "eval_samples_per_second": 46.239,
+      "eval_steps_per_second": 5.826,
+      "step": 43596
+    },
+    {
+      "epoch": 2.826128845783287,
+      "grad_norm": 1.5754073858261108,
+      "learning_rate": 0.0003058363842678828,
+      "loss": 0.2161,
+      "step": 44000
+    },
+    {
+      "epoch": 2.858243946303552,
+      "grad_norm": 0.8411650657653809,
+      "learning_rate": 0.00030476588091720726,
+      "loss": 0.2152,
+      "step": 44500
+    },
+    {
+      "epoch": 2.8903590468238165,
+      "grad_norm": 1.0584657192230225,
+      "learning_rate": 0.0003036953775665318,
+      "loss": 0.2176,
+      "step": 45000
+    },
+    {
+      "epoch": 2.922474147344081,
+      "grad_norm": 0.9761502742767334,
+      "learning_rate": 0.0003026248742158563,
+      "loss": 0.2137,
+      "step": 45500
+    },
+    {
+      "epoch": 2.954589247864346,
+      "grad_norm": 0.8748862147331238,
+      "learning_rate": 0.00030155651187188214,
+      "loss": 0.2134,
+      "step": 46000
+    },
+    {
+      "epoch": 2.9867043483846105,
+      "grad_norm": 1.2218540906906128,
+      "learning_rate": 0.00030048600852120667,
+      "loss": 0.2101,
+      "step": 46500
+    },
+    {
+      "epoch": 3.0001926906031215,
+      "eval_loss": 0.10787095874547958,
+      "eval_runtime": 10.8687,
+      "eval_samples_per_second": 46.004,
+      "eval_steps_per_second": 5.796,
+      "step": 46710
+    },
+    {
+      "epoch": 3.018819448904875,
+      "grad_norm": 2.2454357147216797,
+      "learning_rate": 0.00029941764617723255,
+      "loss": 0.2036,
+      "step": 47000
+    },
+    {
+      "epoch": 3.05093454942514,
+      "grad_norm": 1.0954365730285645,
+      "learning_rate": 0.000298347142826557,
+      "loss": 0.1953,
+      "step": 47500
+    },
+    {
+      "epoch": 3.0830496499454045,
+      "grad_norm": 1.1289081573486328,
+      "learning_rate": 0.00029727663947588155,
+      "loss": 0.1945,
+      "step": 48000
+    },
+    {
+      "epoch": 3.1151647504656688,
+      "grad_norm": 0.9463476538658142,
+      "learning_rate": 0.0002962061361252061,
+      "loss": 0.194,
+      "step": 48500
+    },
+    {
+      "epoch": 3.1472798509859334,
+      "grad_norm": 0.9091750979423523,
+      "learning_rate": 0.00029513563277453055,
+      "loss": 0.1947,
+      "step": 49000
+    },
+    {
+      "epoch": 3.179394951506198,
+      "grad_norm": 0.7108092904090881,
+      "learning_rate": 0.0002940651294238551,
+      "loss": 0.199,
+      "step": 49500
+    },
+    {
+      "epoch": 3.2002055366433297,
+      "eval_loss": 0.10728111118078232,
+      "eval_runtime": 10.8225,
+      "eval_samples_per_second": 46.2,
+      "eval_steps_per_second": 5.821,
+      "step": 49824
+    },
+    {
+      "epoch": 3.211510052026463,
+      "grad_norm": 1.0273375511169434,
+      "learning_rate": 0.0002929946260731796,
+      "loss": 0.1998,
+      "step": 50000
+    },
+    {
+      "epoch": 3.2436251525467275,
+      "grad_norm": 0.8365561962127686,
+      "learning_rate": 0.00029192412272250413,
+      "loss": 0.1972,
+      "step": 50500
+    },
+    {
+      "epoch": 3.275740253066992,
+      "grad_norm": 1.1676949262619019,
+      "learning_rate": 0.00029085361937182866,
+      "loss": 0.1964,
+      "step": 51000
+    },
+    {
+      "epoch": 3.307855353587257,
+      "grad_norm": 1.0615659952163696,
+      "learning_rate": 0.0002897831160211532,
+      "loss": 0.2019,
+      "step": 51500
+    },
+    {
+      "epoch": 3.3399704541075215,
+      "grad_norm": 1.3280376195907593,
+      "learning_rate": 0.000288714753677179,
+      "loss": 0.1946,
+      "step": 52000
+    },
+    {
+      "epoch": 3.372085554627786,
+      "grad_norm": 0.906033992767334,
+      "learning_rate": 0.00028764425032650354,
+      "loss": 0.2002,
+      "step": 52500
+    },
+    {
+      "epoch": 3.400218382683538,
+      "eval_loss": 0.10725516080856323,
+      "eval_runtime": 10.822,
+      "eval_samples_per_second": 46.202,
+      "eval_steps_per_second": 5.821,
+      "step": 52938
+    },
+    {
+      "epoch": 3.404200655148051,
+      "grad_norm": 0.9869097471237183,
+      "learning_rate": 0.00028657374697582807,
+      "loss": 0.2044,
+      "step": 53000
+    },
+    {
+      "epoch": 3.436315755668315,
+      "grad_norm": 0.7808071970939636,
+      "learning_rate": 0.0002855032436251526,
+      "loss": 0.2017,
+      "step": 53500
+    },
+    {
+      "epoch": 3.4684308561885797,
+      "grad_norm": 0.6805254817008972,
+      "learning_rate": 0.00028443274027447707,
+      "loss": 0.2008,
+      "step": 54000
+    },
+    {
+      "epoch": 3.5005459567088444,
+      "grad_norm": 1.552226185798645,
+      "learning_rate": 0.0002833622369238016,
+      "loss": 0.2015,
+      "step": 54500
+    },
+    {
+      "epoch": 3.532661057229109,
+      "grad_norm": 1.1280968189239502,
+      "learning_rate": 0.0002822917335731261,
+      "loss": 0.1992,
+      "step": 55000
+    },
+    {
+      "epoch": 3.5647761577493737,
+      "grad_norm": 0.9633870124816895,
+      "learning_rate": 0.0002812212302224506,
+      "loss": 0.2017,
+      "step": 55500
+    },
+    {
+      "epoch": 3.5968912582696384,
+      "grad_norm": 0.8904027342796326,
+      "learning_rate": 0.0002801528678784765,
+      "loss": 0.1985,
+      "step": 56000
+    },
+    {
+      "epoch": 3.6002312287237457,
+      "eval_loss": 0.10704278200864792,
+      "eval_runtime": 10.8243,
+      "eval_samples_per_second": 46.193,
+      "eval_steps_per_second": 5.82,
+      "step": 56052
+    },
+    {
+      "epoch": 3.629006358789903,
+      "grad_norm": 1.1297188997268677,
+      "learning_rate": 0.00027908450553450236,
+      "loss": 0.199,
+      "step": 56500
+    },
+    {
+      "epoch": 3.6611214593101677,
+      "grad_norm": 1.012528419494629,
+      "learning_rate": 0.00027801400218382683,
+      "loss": 0.1977,
+      "step": 57000
+    },
+    {
+      "epoch": 3.6932365598304324,
+      "grad_norm": 1.0145853757858276,
+      "learning_rate": 0.00027694349883315136,
+      "loss": 0.1952,
+      "step": 57500
+    },
+    {
+      "epoch": 3.7253516603506966,
+      "grad_norm": 0.6479370594024658,
+      "learning_rate": 0.0002758729954824759,
+      "loss": 0.1993,
+      "step": 58000
+    },
+    {
+      "epoch": 3.7574667608709618,
+      "grad_norm": 1.3706332445144653,
+      "learning_rate": 0.00027480249213180036,
+      "loss": 0.1928,
+      "step": 58500
+    },
+    {
+      "epoch": 3.789581861391226,
+      "grad_norm": 0.8537666201591492,
+      "learning_rate": 0.0002737319887811249,
+      "loss": 0.1966,
+      "step": 59000
+    },
+    {
+      "epoch": 3.800244074763954,
+      "eval_loss": 0.10166960954666138,
+      "eval_runtime": 10.8263,
+      "eval_samples_per_second": 46.184,
+      "eval_steps_per_second": 5.819,
+      "step": 59166
+    },
+    {
+      "epoch": 3.8216969619114907,
+      "grad_norm": 0.7821935415267944,
+      "learning_rate": 0.0002726614854304494,
+      "loss": 0.2005,
+      "step": 59500
+    },
+    {
+      "epoch": 3.8538120624317553,
+      "grad_norm": 1.01955246925354,
+      "learning_rate": 0.00027159312308647524,
+      "loss": 0.193,
+      "step": 60000
+    },
+    {
+      "epoch": 3.88592716295202,
+      "grad_norm": 0.9163061380386353,
+      "learning_rate": 0.00027052261973579977,
+      "loss": 0.1996,
+      "step": 60500
+    },
+    {
+      "epoch": 3.9180422634722847,
+      "grad_norm": 0.8913554549217224,
+      "learning_rate": 0.0002694521163851243,
+      "loss": 0.1984,
+      "step": 61000
+    },
+    {
+      "epoch": 3.9501573639925494,
+      "grad_norm": 1.0580236911773682,
+      "learning_rate": 0.0002683816130344488,
+      "loss": 0.2014,
+      "step": 61500
+    },
+    {
+      "epoch": 3.982272464512814,
+      "grad_norm": 0.8770594596862793,
+      "learning_rate": 0.0002673111096837733,
+      "loss": 0.197,
+      "step": 62000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 186828,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.1798284342438396e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-62276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18770cad77c61ad23c96d1c614b30fa0afc45e40d6ebf88c6c6e22257f3e29c0
+size 5496