Training in progress, epoch 11, checkpoint

checkpoint-43176/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-43176/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": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-43176/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6963f7de8e85ba9da6754af19d6d052fd1c9829f5d17362f1430a885f51004f7
+size 541459256

checkpoint-43176/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f954630bebf0df53d1a8eb4132a243b8be5575277d3f0393a8b78ab307c8a5c3
+size 33662074

checkpoint-43176/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e384b7090574fab4cf6c1fd9d36475fd0fae137f3712d076ff576276fed96f6d
+size 15024

checkpoint-43176/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d125b8a9a57815c4e15ec82d96938df24b3033cd7ad2c91ba0a1465e0c1afb37
+size 15024

checkpoint-43176/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2936a28f918a4635069dbeafc3b67f22253c39c76e6078e4274eac3b96fc3c3c
+size 15024

checkpoint-43176/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faedfff004041e1b09d08fb422111aad800f25c9fadddc049d0419e1e99ceed6
+size 15024

checkpoint-43176/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:127111061fa584a8f7f8e68f630e34753dea5a2bd5902f78f3f260b71ec695c2
+size 1064

checkpoint-43176/trainer_state.json

@@ -0,0 +1,1107 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 11.996804223982215,
+  "eval_steps": 720,
+  "global_step": 43176,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1389467833819647,
+      "grad_norm": 1.5771187543869019,
+      "learning_rate": 0.00039537706133036877,
+      "loss": 0.6105,
+      "step": 500
+    },
+    {
+      "epoch": 0.2000833680700292,
+      "eval_loss": 0.19789238274097443,
+      "eval_runtime": 9.8299,
+      "eval_samples_per_second": 50.865,
+      "eval_steps_per_second": 6.409,
+      "step": 720
+    },
+    {
+      "epoch": 0.2778935667639294,
+      "grad_norm": 1.0989495515823364,
+      "learning_rate": 0.00039075412266073746,
+      "loss": 0.3924,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4001667361400584,
+      "eval_loss": 0.17624308168888092,
+      "eval_runtime": 9.8344,
+      "eval_samples_per_second": 50.842,
+      "eval_steps_per_second": 6.406,
+      "step": 1440
+    },
+    {
+      "epoch": 0.4168403501458941,
+      "grad_norm": 1.181208610534668,
+      "learning_rate": 0.00038612191958495464,
+      "loss": 0.3557,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5557871335278588,
+      "grad_norm": 0.6985607147216797,
+      "learning_rate": 0.0003814897165091718,
+      "loss": 0.3264,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6002501042100875,
+      "eval_loss": 0.16567109525203705,
+      "eval_runtime": 9.8438,
+      "eval_samples_per_second": 50.793,
+      "eval_steps_per_second": 6.4,
+      "step": 2160
+    },
+    {
+      "epoch": 0.6947339169098236,
+      "grad_norm": 1.183258295059204,
+      "learning_rate": 0.00037685751343338893,
+      "loss": 0.3094,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8003334722801168,
+      "eval_loss": 0.15141654014587402,
+      "eval_runtime": 9.8499,
+      "eval_samples_per_second": 50.762,
+      "eval_steps_per_second": 6.396,
+      "step": 2880
+    },
+    {
+      "epoch": 0.8336807002917882,
+      "grad_norm": 1.1332894563674927,
+      "learning_rate": 0.0003722345747637577,
+      "loss": 0.2898,
+      "step": 3000
+    },
+    {
+      "epoch": 0.972627483673753,
+      "grad_norm": 1.8378171920776367,
+      "learning_rate": 0.0003676116360941264,
+      "loss": 0.2879,
+      "step": 3500
+    },
+    {
+      "epoch": 1.000277893566764,
+      "eval_loss": 0.14729157090187073,
+      "eval_runtime": 9.8995,
+      "eval_samples_per_second": 50.507,
+      "eval_steps_per_second": 6.364,
+      "step": 3600
+    },
+    {
+      "epoch": 1.1114353202723357,
+      "grad_norm": 1.01169753074646,
+      "learning_rate": 0.0003629886974244951,
+      "loss": 0.2563,
+      "step": 4000
+    },
+    {
+      "epoch": 1.2003612616367931,
+      "eval_loss": 0.14218533039093018,
+      "eval_runtime": 9.8655,
+      "eval_samples_per_second": 50.682,
+      "eval_steps_per_second": 6.386,
+      "step": 4320
+    },
+    {
+      "epoch": 1.2503821036543004,
+      "grad_norm": 0.9457218647003174,
+      "learning_rate": 0.0003583564943487123,
+      "loss": 0.2521,
+      "step": 4500
+    },
+    {
+      "epoch": 1.3893288870362652,
+      "grad_norm": 0.8780346512794495,
+      "learning_rate": 0.0003537242912729294,
+      "loss": 0.2479,
+      "step": 5000
+    },
+    {
+      "epoch": 1.4004446297068223,
+      "eval_loss": 0.13703791797161102,
+      "eval_runtime": 9.8699,
+      "eval_samples_per_second": 50.659,
+      "eval_steps_per_second": 6.383,
+      "step": 5040
+    },
+    {
+      "epoch": 1.5282756704182299,
+      "grad_norm": 0.9170272946357727,
+      "learning_rate": 0.0003490920881971466,
+      "loss": 0.2451,
+      "step": 5500
+    },
+    {
+      "epoch": 1.6005279977768514,
+      "eval_loss": 0.13939791917800903,
+      "eval_runtime": 9.8584,
+      "eval_samples_per_second": 50.718,
+      "eval_steps_per_second": 6.391,
+      "step": 5760
+    },
+    {
+      "epoch": 1.6672224538001945,
+      "grad_norm": 0.8048965930938721,
+      "learning_rate": 0.00034445988512136377,
+      "loss": 0.2413,
+      "step": 6000
+    },
+    {
+      "epoch": 1.8006113658468808,
+      "eval_loss": 0.13149049878120422,
+      "eval_runtime": 9.8719,
+      "eval_samples_per_second": 50.649,
+      "eval_steps_per_second": 6.382,
+      "step": 6480
+    },
+    {
+      "epoch": 1.8061692371821594,
+      "grad_norm": 0.8241537809371948,
+      "learning_rate": 0.0003398276820455809,
+      "loss": 0.2344,
+      "step": 6500
+    },
+    {
+      "epoch": 1.9451160205641238,
+      "grad_norm": 0.9662640690803528,
+      "learning_rate": 0.00033519547896979806,
+      "loss": 0.2317,
+      "step": 7000
+    },
+    {
+      "epoch": 2.000555787133528,
+      "eval_loss": 0.12875500321388245,
+      "eval_runtime": 9.9282,
+      "eval_samples_per_second": 50.362,
+      "eval_steps_per_second": 6.346,
+      "step": 7200
+    },
+    {
+      "epoch": 2.0839238571627066,
+      "grad_norm": 0.8450930714607239,
+      "learning_rate": 0.0003305632758940152,
+      "loss": 0.2101,
+      "step": 7500
+    },
+    {
+      "epoch": 2.200639155203557,
+      "eval_loss": 0.12816455960273743,
+      "eval_runtime": 9.8749,
+      "eval_samples_per_second": 50.633,
+      "eval_steps_per_second": 6.38,
+      "step": 7920
+    },
+    {
+      "epoch": 2.2228706405446714,
+      "grad_norm": 0.8503730297088623,
+      "learning_rate": 0.00032593107281823235,
+      "loss": 0.2033,
+      "step": 8000
+    },
+    {
+      "epoch": 2.3618174239266363,
+      "grad_norm": 1.4220209121704102,
+      "learning_rate": 0.0003213081341486011,
+      "loss": 0.2039,
+      "step": 8500
+    },
+    {
+      "epoch": 2.4007225232735863,
+      "eval_loss": 0.12309741973876953,
+      "eval_runtime": 9.8895,
+      "eval_samples_per_second": 50.559,
+      "eval_steps_per_second": 6.37,
+      "step": 8640
+    },
+    {
+      "epoch": 2.5007642073086007,
+      "grad_norm": 0.767339289188385,
+      "learning_rate": 0.0003166759310728182,
+      "loss": 0.2006,
+      "step": 9000
+    },
+    {
+      "epoch": 2.600805891343615,
+      "eval_loss": 0.1211056038737297,
+      "eval_runtime": 9.9007,
+      "eval_samples_per_second": 50.501,
+      "eval_steps_per_second": 6.363,
+      "step": 9360
+    },
+    {
+      "epoch": 2.6397109906905656,
+      "grad_norm": 1.263227105140686,
+      "learning_rate": 0.0003120437279970354,
+      "loss": 0.2002,
+      "step": 9500
+    },
+    {
+      "epoch": 2.7786577740725305,
+      "grad_norm": 0.7360139489173889,
+      "learning_rate": 0.00030742078932740415,
+      "loss": 0.2003,
+      "step": 10000
+    },
+    {
+      "epoch": 2.8008892594136445,
+      "eval_loss": 0.11719686537981033,
+      "eval_runtime": 9.8841,
+      "eval_samples_per_second": 50.586,
+      "eval_steps_per_second": 6.374,
+      "step": 10080
+    },
+    {
+      "epoch": 2.917604557454495,
+      "grad_norm": 0.708620548248291,
+      "learning_rate": 0.00030278858625162127,
+      "loss": 0.2044,
+      "step": 10500
+    },
+    {
+      "epoch": 3.0008336807002918,
+      "eval_loss": 0.1192111074924469,
+      "eval_runtime": 9.948,
+      "eval_samples_per_second": 50.261,
+      "eval_steps_per_second": 6.333,
+      "step": 10800
+    },
+    {
+      "epoch": 3.0564123940530776,
+      "grad_norm": 0.738373339176178,
+      "learning_rate": 0.00029815638317583844,
+      "loss": 0.1853,
+      "step": 11000
+    },
+    {
+      "epoch": 3.1953591774350425,
+      "grad_norm": 0.9206659197807312,
+      "learning_rate": 0.00029352418010005556,
+      "loss": 0.1712,
+      "step": 11500
+    },
+    {
+      "epoch": 3.200917048770321,
+      "eval_loss": 0.12023476511240005,
+      "eval_runtime": 9.888,
+      "eval_samples_per_second": 50.566,
+      "eval_steps_per_second": 6.371,
+      "step": 11520
+    },
+    {
+      "epoch": 3.334305960817007,
+      "grad_norm": 0.8466194272041321,
+      "learning_rate": 0.00028889197702427273,
+      "loss": 0.1762,
+      "step": 12000
+    },
+    {
+      "epoch": 3.40100041684035,
+      "eval_loss": 0.11644280701875687,
+      "eval_runtime": 9.891,
+      "eval_samples_per_second": 50.551,
+      "eval_steps_per_second": 6.369,
+      "step": 12240
+    },
+    {
+      "epoch": 3.473252744198972,
+      "grad_norm": 0.6490458846092224,
+      "learning_rate": 0.0002842597739484899,
+      "loss": 0.1732,
+      "step": 12500
+    },
+    {
+      "epoch": 3.6010837849103794,
+      "eval_loss": 0.1136402115225792,
+      "eval_runtime": 9.879,
+      "eval_samples_per_second": 50.612,
+      "eval_steps_per_second": 6.377,
+      "step": 12960
+    },
+    {
+      "epoch": 3.6121995275809367,
+      "grad_norm": 1.084926962852478,
+      "learning_rate": 0.0002796368352788586,
+      "loss": 0.1738,
+      "step": 13000
+    },
+    {
+      "epoch": 3.751146310962901,
+      "grad_norm": 0.8281185030937195,
+      "learning_rate": 0.0002750046322030758,
+      "loss": 0.1731,
+      "step": 13500
+    },
+    {
+      "epoch": 3.8011671529804083,
+      "eval_loss": 0.11408974230289459,
+      "eval_runtime": 9.892,
+      "eval_samples_per_second": 50.546,
+      "eval_steps_per_second": 6.369,
+      "step": 13680
+    },
+    {
+      "epoch": 3.890093094344866,
+      "grad_norm": 0.97463458776474,
+      "learning_rate": 0.00027037242912729295,
+      "loss": 0.1723,
+      "step": 14000
+    },
+    {
+      "epoch": 4.001111574267056,
+      "eval_loss": 0.1121235340833664,
+      "eval_runtime": 9.9421,
+      "eval_samples_per_second": 50.291,
+      "eval_steps_per_second": 6.337,
+      "step": 14400
+    },
+    {
+      "epoch": 4.028900930943449,
+      "grad_norm": 1.147574543952942,
+      "learning_rate": 0.0002657402260515101,
+      "loss": 0.1648,
+      "step": 14500
+    },
+    {
+      "epoch": 4.167847714325413,
+      "grad_norm": 0.9622366428375244,
+      "learning_rate": 0.0002611080229757273,
+      "loss": 0.1466,
+      "step": 15000
+    },
+    {
+      "epoch": 4.201194942337085,
+      "eval_loss": 0.1162620410323143,
+      "eval_runtime": 9.8926,
+      "eval_samples_per_second": 50.543,
+      "eval_steps_per_second": 6.368,
+      "step": 15120
+    },
+    {
+      "epoch": 4.306794497707378,
+      "grad_norm": 0.9468634128570557,
+      "learning_rate": 0.0002564758198999445,
+      "loss": 0.1491,
+      "step": 15500
+    },
+    {
+      "epoch": 4.401278310407114,
+      "eval_loss": 0.11213818192481995,
+      "eval_runtime": 9.8896,
+      "eval_samples_per_second": 50.558,
+      "eval_steps_per_second": 6.37,
+      "step": 15840
+    },
+    {
+      "epoch": 4.445741281089343,
+      "grad_norm": 0.8550407290458679,
+      "learning_rate": 0.0002518436168241616,
+      "loss": 0.1526,
+      "step": 16000
+    },
+    {
+      "epoch": 4.584688064471307,
+      "grad_norm": 0.8811725378036499,
+      "learning_rate": 0.00024721141374837877,
+      "loss": 0.1485,
+      "step": 16500
+    },
+    {
+      "epoch": 4.601361678477144,
+      "eval_loss": 0.11435514688491821,
+      "eval_runtime": 9.8927,
+      "eval_samples_per_second": 50.543,
+      "eval_steps_per_second": 6.368,
+      "step": 16560
+    },
+    {
+      "epoch": 4.723634847853273,
+      "grad_norm": 0.9635345935821533,
+      "learning_rate": 0.0002425792106725959,
+      "loss": 0.1515,
+      "step": 17000
+    },
+    {
+      "epoch": 4.8014450465471725,
+      "eval_loss": 0.10879776626825333,
+      "eval_runtime": 9.8882,
+      "eval_samples_per_second": 50.565,
+      "eval_steps_per_second": 6.371,
+      "step": 17280
+    },
+    {
+      "epoch": 4.862581631235237,
+      "grad_norm": 0.7074841260910034,
+      "learning_rate": 0.0002379562720029646,
+      "loss": 0.1519,
+      "step": 17500
+    },
+    {
+      "epoch": 5.001389467833819,
+      "grad_norm": 1.00533127784729,
+      "learning_rate": 0.00023332406892718178,
+      "loss": 0.1496,
+      "step": 18000
+    },
+    {
+      "epoch": 5.001389467833819,
+      "eval_loss": 0.10892610996961594,
+      "eval_runtime": 9.9241,
+      "eval_samples_per_second": 50.382,
+      "eval_steps_per_second": 6.348,
+      "step": 18000
+    },
+    {
+      "epoch": 5.140336251215785,
+      "grad_norm": 0.8419302701950073,
+      "learning_rate": 0.00022869186585139893,
+      "loss": 0.1261,
+      "step": 18500
+    },
+    {
+      "epoch": 5.201472835903849,
+      "eval_loss": 0.11248684674501419,
+      "eval_runtime": 9.9057,
+      "eval_samples_per_second": 50.476,
+      "eval_steps_per_second": 6.36,
+      "step": 18720
+    },
+    {
+      "epoch": 5.279283034597749,
+      "grad_norm": 0.9732480645179749,
+      "learning_rate": 0.0002240596627756161,
+      "loss": 0.1281,
+      "step": 19000
+    },
+    {
+      "epoch": 5.401556203973878,
+      "eval_loss": 0.10865695774555206,
+      "eval_runtime": 9.8852,
+      "eval_samples_per_second": 50.58,
+      "eval_steps_per_second": 6.373,
+      "step": 19440
+    },
+    {
+      "epoch": 5.4182298179797135,
+      "grad_norm": 0.9559215903282166,
+      "learning_rate": 0.00021942745969983328,
+      "loss": 0.1308,
+      "step": 19500
+    },
+    {
+      "epoch": 5.557176601361679,
+      "grad_norm": 0.5276982188224792,
+      "learning_rate": 0.00021480452103020197,
+      "loss": 0.1308,
+      "step": 20000
+    },
+    {
+      "epoch": 5.601639572043907,
+      "eval_loss": 0.10896265506744385,
+      "eval_runtime": 9.8913,
+      "eval_samples_per_second": 50.549,
+      "eval_steps_per_second": 6.369,
+      "step": 20160
+    },
+    {
+      "epoch": 5.696123384743643,
+      "grad_norm": 0.9511879682540894,
+      "learning_rate": 0.00021017231795441915,
+      "loss": 0.1319,
+      "step": 20500
+    },
+    {
+      "epoch": 5.801722940113937,
+      "eval_loss": 0.11062806099653244,
+      "eval_runtime": 9.8999,
+      "eval_samples_per_second": 50.506,
+      "eval_steps_per_second": 6.364,
+      "step": 20880
+    },
+    {
+      "epoch": 5.835070168125608,
+      "grad_norm": 1.353843092918396,
+      "learning_rate": 0.00020554011487863627,
+      "loss": 0.1318,
+      "step": 21000
+    },
+    {
+      "epoch": 5.974016951507573,
+      "grad_norm": 0.6339994072914124,
+      "learning_rate": 0.00020091717620900502,
+      "loss": 0.13,
+      "step": 21500
+    },
+    {
+      "epoch": 6.0016673614005835,
+      "eval_loss": 0.10584724694490433,
+      "eval_runtime": 10.018,
+      "eval_samples_per_second": 49.91,
+      "eval_steps_per_second": 6.289,
+      "step": 21600
+    },
+    {
+      "epoch": 6.112824788106155,
+      "grad_norm": 0.7975249290466309,
+      "learning_rate": 0.00019628497313322216,
+      "loss": 0.1119,
+      "step": 22000
+    },
+    {
+      "epoch": 6.2017507294706125,
+      "eval_loss": 0.11757533252239227,
+      "eval_runtime": 9.9081,
+      "eval_samples_per_second": 50.464,
+      "eval_steps_per_second": 6.358,
+      "step": 22320
+    },
+    {
+      "epoch": 6.25177157148812,
+      "grad_norm": 1.065436840057373,
+      "learning_rate": 0.00019165277005743934,
+      "loss": 0.1109,
+      "step": 22500
+    },
+    {
+      "epoch": 6.390718354870085,
+      "grad_norm": 0.9995867609977722,
+      "learning_rate": 0.00018702056698165648,
+      "loss": 0.1134,
+      "step": 23000
+    },
+    {
+      "epoch": 6.401834097540642,
+      "eval_loss": 0.11242951452732086,
+      "eval_runtime": 9.904,
+      "eval_samples_per_second": 50.484,
+      "eval_steps_per_second": 6.361,
+      "step": 23040
+    },
+    {
+      "epoch": 6.529665138252049,
+      "grad_norm": 0.9586099982261658,
+      "learning_rate": 0.00018238836390587363,
+      "loss": 0.1133,
+      "step": 23500
+    },
+    {
+      "epoch": 6.601917465610671,
+      "eval_loss": 0.11325228959321976,
+      "eval_runtime": 9.8925,
+      "eval_samples_per_second": 50.543,
+      "eval_steps_per_second": 6.368,
+      "step": 23760
+    },
+    {
+      "epoch": 6.668611921634014,
+      "grad_norm": 1.5666745901107788,
+      "learning_rate": 0.00017775616083009078,
+      "loss": 0.1141,
+      "step": 24000
+    },
+    {
+      "epoch": 6.8020008336807,
+      "eval_loss": 0.1134830191731453,
+      "eval_runtime": 9.9067,
+      "eval_samples_per_second": 50.471,
+      "eval_steps_per_second": 6.359,
+      "step": 24480
+    },
+    {
+      "epoch": 6.807558705015979,
+      "grad_norm": 0.9237664341926575,
+      "learning_rate": 0.00017312395775430795,
+      "loss": 0.1143,
+      "step": 24500
+    },
+    {
+      "epoch": 6.946505488397944,
+      "grad_norm": 0.8428780436515808,
+      "learning_rate": 0.00016849175467852513,
+      "loss": 0.1134,
+      "step": 25000
+    },
+    {
+      "epoch": 7.001945254967348,
+      "eval_loss": 0.11098583042621613,
+      "eval_runtime": 9.9502,
+      "eval_samples_per_second": 50.25,
+      "eval_steps_per_second": 6.332,
+      "step": 25200
+    },
+    {
+      "epoch": 7.085313324996527,
+      "grad_norm": 0.8568938970565796,
+      "learning_rate": 0.0001638780804150454,
+      "loss": 0.1,
+      "step": 25500
+    },
+    {
+      "epoch": 7.202028623037377,
+      "eval_loss": 0.11701945960521698,
+      "eval_runtime": 9.9096,
+      "eval_samples_per_second": 50.456,
+      "eval_steps_per_second": 6.357,
+      "step": 25920
+    },
+    {
+      "epoch": 7.224260108378491,
+      "grad_norm": 1.1847538948059082,
+      "learning_rate": 0.00015925514174541412,
+      "loss": 0.0942,
+      "step": 26000
+    },
+    {
+      "epoch": 7.363206891760456,
+      "grad_norm": 0.9548922777175903,
+      "learning_rate": 0.0001546229386696313,
+      "loss": 0.0964,
+      "step": 26500
+    },
+    {
+      "epoch": 7.402111991107406,
+      "eval_loss": 0.10993777215480804,
+      "eval_runtime": 9.9161,
+      "eval_samples_per_second": 50.423,
+      "eval_steps_per_second": 6.353,
+      "step": 26640
+    },
+    {
+      "epoch": 7.50215367514242,
+      "grad_norm": 0.6410225033760071,
+      "learning_rate": 0.00014999073559384844,
+      "loss": 0.0986,
+      "step": 27000
+    },
+    {
+      "epoch": 7.602195359177435,
+      "eval_loss": 0.11407623440027237,
+      "eval_runtime": 9.9203,
+      "eval_samples_per_second": 50.402,
+      "eval_steps_per_second": 6.351,
+      "step": 27360
+    },
+    {
+      "epoch": 7.641100458524385,
+      "grad_norm": 0.7109144330024719,
+      "learning_rate": 0.00014535853251806559,
+      "loss": 0.0982,
+      "step": 27500
+    },
+    {
+      "epoch": 7.78004724190635,
+      "grad_norm": 0.8475452661514282,
+      "learning_rate": 0.00014072632944228276,
+      "loss": 0.0984,
+      "step": 28000
+    },
+    {
+      "epoch": 7.802278727247464,
+      "eval_loss": 0.10964713990688324,
+      "eval_runtime": 9.9046,
+      "eval_samples_per_second": 50.482,
+      "eval_steps_per_second": 6.361,
+      "step": 28080
+    },
+    {
+      "epoch": 7.918994025288314,
+      "grad_norm": 0.6582953929901123,
+      "learning_rate": 0.0001360941263664999,
+      "loss": 0.0992,
+      "step": 28500
+    },
+    {
+      "epoch": 8.002223148534112,
+      "eval_loss": 0.11010504513978958,
+      "eval_runtime": 9.9634,
+      "eval_samples_per_second": 50.184,
+      "eval_steps_per_second": 6.323,
+      "step": 28800
+    },
+    {
+      "epoch": 8.057801861886897,
+      "grad_norm": 0.6765108108520508,
+      "learning_rate": 0.00013146192329071708,
+      "loss": 0.0896,
+      "step": 29000
+    },
+    {
+      "epoch": 8.196748645268862,
+      "grad_norm": 2.0118250846862793,
+      "learning_rate": 0.00012682972021493423,
+      "loss": 0.0832,
+      "step": 29500
+    },
+    {
+      "epoch": 8.202306516604141,
+      "eval_loss": 0.11851812154054642,
+      "eval_runtime": 9.9132,
+      "eval_samples_per_second": 50.438,
+      "eval_steps_per_second": 6.355,
+      "step": 29520
+    },
+    {
+      "epoch": 8.335695428650826,
+      "grad_norm": 1.0481656789779663,
+      "learning_rate": 0.0001221975171391514,
+      "loss": 0.0808,
+      "step": 30000
+    },
+    {
+      "epoch": 8.40238988467417,
+      "eval_loss": 0.11569618433713913,
+      "eval_runtime": 9.9092,
+      "eval_samples_per_second": 50.458,
+      "eval_steps_per_second": 6.358,
+      "step": 30240
+    },
+    {
+      "epoch": 8.47464221203279,
+      "grad_norm": 0.6488707661628723,
+      "learning_rate": 0.00011756531406336855,
+      "loss": 0.0837,
+      "step": 30500
+    },
+    {
+      "epoch": 8.602473252744199,
+      "eval_loss": 0.119095578789711,
+      "eval_runtime": 9.9061,
+      "eval_samples_per_second": 50.474,
+      "eval_steps_per_second": 6.36,
+      "step": 30960
+    },
+    {
+      "epoch": 8.613588995414757,
+      "grad_norm": 0.9621661901473999,
+      "learning_rate": 0.0001129331109875857,
+      "loss": 0.0867,
+      "step": 31000
+    },
+    {
+      "epoch": 8.752535778796721,
+      "grad_norm": 0.7843289375305176,
+      "learning_rate": 0.00010830090791180286,
+      "loss": 0.0845,
+      "step": 31500
+    },
+    {
+      "epoch": 8.802556620814228,
+      "eval_loss": 0.12125415354967117,
+      "eval_runtime": 9.9069,
+      "eval_samples_per_second": 50.47,
+      "eval_steps_per_second": 6.359,
+      "step": 31680
+    },
+    {
+      "epoch": 8.891482562178686,
+      "grad_norm": 0.6697407960891724,
+      "learning_rate": 0.00010366870483602003,
+      "loss": 0.0834,
+      "step": 32000
+    },
+    {
+      "epoch": 9.002501042100876,
+      "eval_loss": 0.12217039614915848,
+      "eval_runtime": 9.9505,
+      "eval_samples_per_second": 50.249,
+      "eval_steps_per_second": 6.331,
+      "step": 32400
+    },
+    {
+      "epoch": 9.030290398777268,
+      "grad_norm": 0.4972025156021118,
+      "learning_rate": 9.903650176023718e-05,
+      "loss": 0.0811,
+      "step": 32500
+    },
+    {
+      "epoch": 9.169237182159232,
+      "grad_norm": 0.48695579171180725,
+      "learning_rate": 9.440429868445433e-05,
+      "loss": 0.0703,
+      "step": 33000
+    },
+    {
+      "epoch": 9.202584410170905,
+      "eval_loss": 0.12846368551254272,
+      "eval_runtime": 9.9057,
+      "eval_samples_per_second": 50.476,
+      "eval_steps_per_second": 6.36,
+      "step": 33120
+    },
+    {
+      "epoch": 9.308183965541197,
+      "grad_norm": 0.4823940396308899,
+      "learning_rate": 8.977209560867149e-05,
+      "loss": 0.0714,
+      "step": 33500
+    },
+    {
+      "epoch": 9.402667778240934,
+      "eval_loss": 0.12202821671962738,
+      "eval_runtime": 9.9208,
+      "eval_samples_per_second": 50.399,
+      "eval_steps_per_second": 6.35,
+      "step": 33840
+    },
+    {
+      "epoch": 9.447130748923163,
+      "grad_norm": 0.7359215617179871,
+      "learning_rate": 8.513989253288865e-05,
+      "loss": 0.0713,
+      "step": 34000
+    },
+    {
+      "epoch": 9.586077532305127,
+      "grad_norm": 0.6132245063781738,
+      "learning_rate": 8.051695386325737e-05,
+      "loss": 0.0725,
+      "step": 34500
+    },
+    {
+      "epoch": 9.602751146310963,
+      "eval_loss": 0.12453693896532059,
+      "eval_runtime": 9.9099,
+      "eval_samples_per_second": 50.455,
+      "eval_steps_per_second": 6.357,
+      "step": 34560
+    },
+    {
+      "epoch": 9.725024315687092,
+      "grad_norm": 0.5046743154525757,
+      "learning_rate": 7.588475078747453e-05,
+      "loss": 0.0742,
+      "step": 35000
+    },
+    {
+      "epoch": 9.802834514380992,
+      "eval_loss": 0.1252909153699875,
+      "eval_runtime": 9.9135,
+      "eval_samples_per_second": 50.436,
+      "eval_steps_per_second": 6.355,
+      "step": 35280
+    },
+    {
+      "epoch": 9.863971099069056,
+      "grad_norm": 0.8234041333198547,
+      "learning_rate": 7.125254771169169e-05,
+      "loss": 0.0755,
+      "step": 35500
+    },
+    {
+      "epoch": 10.002778935667639,
+      "grad_norm": 0.3044394850730896,
+      "learning_rate": 6.662034463590884e-05,
+      "loss": 0.0709,
+      "step": 36000
+    },
+    {
+      "epoch": 10.002778935667639,
+      "eval_loss": 0.12311500310897827,
+      "eval_runtime": 9.9858,
+      "eval_samples_per_second": 50.071,
+      "eval_steps_per_second": 6.309,
+      "step": 36000
+    },
+    {
+      "epoch": 10.141725719049605,
+      "grad_norm": 0.47128599882125854,
+      "learning_rate": 6.199740596627757e-05,
+      "loss": 0.0618,
+      "step": 36500
+    },
+    {
+      "epoch": 10.20286230373767,
+      "eval_loss": 0.13248130679130554,
+      "eval_runtime": 9.9278,
+      "eval_samples_per_second": 50.364,
+      "eval_steps_per_second": 6.346,
+      "step": 36720
+    },
+    {
+      "epoch": 10.28067250243157,
+      "grad_norm": 0.6568199992179871,
+      "learning_rate": 5.737446729664629e-05,
+      "loss": 0.0611,
+      "step": 37000
+    },
+    {
+      "epoch": 10.402945671807698,
+      "eval_loss": 0.13179945945739746,
+      "eval_runtime": 9.9273,
+      "eval_samples_per_second": 50.366,
+      "eval_steps_per_second": 6.346,
+      "step": 37440
+    },
+    {
+      "epoch": 10.419619285813534,
+      "grad_norm": 0.6924021244049072,
+      "learning_rate": 5.274226422086345e-05,
+      "loss": 0.0635,
+      "step": 37500
+    },
+    {
+      "epoch": 10.558566069195498,
+      "grad_norm": 0.8145691156387329,
+      "learning_rate": 4.81100611450806e-05,
+      "loss": 0.0621,
+      "step": 38000
+    },
+    {
+      "epoch": 10.603029039877727,
+      "eval_loss": 0.13543599843978882,
+      "eval_runtime": 9.932,
+      "eval_samples_per_second": 50.342,
+      "eval_steps_per_second": 6.343,
+      "step": 38160
+    },
+    {
+      "epoch": 10.697512852577463,
+      "grad_norm": 1.672833800315857,
+      "learning_rate": 4.347785806929776e-05,
+      "loss": 0.062,
+      "step": 38500
+    },
+    {
+      "epoch": 10.803112407947756,
+      "eval_loss": 0.13520361483097076,
+      "eval_runtime": 9.9217,
+      "eval_samples_per_second": 50.395,
+      "eval_steps_per_second": 6.35,
+      "step": 38880
+    },
+    {
+      "epoch": 10.836459635959427,
+      "grad_norm": 1.034909963607788,
+      "learning_rate": 3.8845654993514916e-05,
+      "loss": 0.0631,
+      "step": 39000
+    },
+    {
+      "epoch": 10.975406419341393,
+      "grad_norm": 0.4911954700946808,
+      "learning_rate": 3.4213451917732076e-05,
+      "loss": 0.063,
+      "step": 39500
+    },
+    {
+      "epoch": 11.003056829234403,
+      "eval_loss": 0.1331816017627716,
+      "eval_runtime": 9.9824,
+      "eval_samples_per_second": 50.088,
+      "eval_steps_per_second": 6.311,
+      "step": 39600
+    },
+    {
+      "epoch": 11.114214255939975,
+      "grad_norm": 0.9452788829803467,
+      "learning_rate": 2.9581248841949234e-05,
+      "loss": 0.0554,
+      "step": 40000
+    },
+    {
+      "epoch": 11.203140197304432,
+      "eval_loss": 0.14554482698440552,
+      "eval_runtime": 9.9153,
+      "eval_samples_per_second": 50.427,
+      "eval_steps_per_second": 6.354,
+      "step": 40320
+    },
+    {
+      "epoch": 11.25316103932194,
+      "grad_norm": 0.3862329125404358,
+      "learning_rate": 2.494904576616639e-05,
+      "loss": 0.0548,
+      "step": 40500
+    },
+    {
+      "epoch": 11.392107822703904,
+      "grad_norm": 0.4970497488975525,
+      "learning_rate": 2.0326107096535113e-05,
+      "loss": 0.0552,
+      "step": 41000
+    },
+    {
+      "epoch": 11.40322356537446,
+      "eval_loss": 0.14361564815044403,
+      "eval_runtime": 9.916,
+      "eval_samples_per_second": 50.424,
+      "eval_steps_per_second": 6.353,
+      "step": 41040
+    },
+    {
+      "epoch": 11.531054606085869,
+      "grad_norm": 0.690534770488739,
+      "learning_rate": 1.569390402075227e-05,
+      "loss": 0.0546,
+      "step": 41500
+    },
+    {
+      "epoch": 11.603306933444491,
+      "eval_loss": 0.1423441767692566,
+      "eval_runtime": 9.9255,
+      "eval_samples_per_second": 50.375,
+      "eval_steps_per_second": 6.347,
+      "step": 41760
+    },
+    {
+      "epoch": 11.670001389467833,
+      "grad_norm": 0.5511090755462646,
+      "learning_rate": 1.1061700944969427e-05,
+      "loss": 0.0552,
+      "step": 42000
+    },
+    {
+      "epoch": 11.80339030151452,
+      "eval_loss": 0.1445242017507553,
+      "eval_runtime": 9.9362,
+      "eval_samples_per_second": 50.321,
+      "eval_steps_per_second": 6.34,
+      "step": 42480
+    },
+    {
+      "epoch": 11.8089481728498,
+      "grad_norm": 0.2841227352619171,
+      "learning_rate": 6.429497869186585e-06,
+      "loss": 0.0543,
+      "step": 42500
+    },
+    {
+      "epoch": 11.947894956231764,
+      "grad_norm": 0.5525102019309998,
+      "learning_rate": 1.7972947934037427e-06,
+      "loss": 0.0543,
+      "step": 43000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 43176,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2991446119509656e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-43176/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6521317bb6df8e16b6399d59d5c20dc4db2ed1e7bd6e89d684b9448efc2320b5
+size 5496