Training in progress, step 15000, checkpoint

checkpoint-15000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
+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 0.13.2

checkpoint-15000/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
+  "bias": "none",
+  "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_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-15000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:902e98acd2e6074d4df36f46e616266c6671e69929b8ccbc511bf252b22d2863
+size 13648432

checkpoint-15000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75b34ae2f97318faadad8d5a57b8027d299bd6691794baa18126914cdbff4d2f
+size 7073594

checkpoint-15000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9a726af5372d4251f781e5fd26ff0eef195431a55495ae622e5696bda50546
+size 14244

checkpoint-15000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23fbbdf0440ab13142d421c1071af19941c1b6e1eb10a315c7cc1640267a78dc
+size 1064

checkpoint-15000/trainer_state.json

@@ -0,0 +1,1083 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.3275511107177627,
+  "eval_steps": 500,
+  "global_step": 15000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008850340738118417,
+      "grad_norm": 1.517469048500061,
+      "learning_rate": 1.9919999999999997e-06,
+      "loss": 1.519,
+      "step": 100
+    },
+    {
+      "epoch": 0.017700681476236834,
+      "grad_norm": 1.6662976741790771,
+      "learning_rate": 1.984e-06,
+      "loss": 1.4776,
+      "step": 200
+    },
+    {
+      "epoch": 0.026551022214355253,
+      "grad_norm": 0.8021761775016785,
+      "learning_rate": 1.976e-06,
+      "loss": 1.4026,
+      "step": 300
+    },
+    {
+      "epoch": 0.03540136295247367,
+      "grad_norm": 0.8772447109222412,
+      "learning_rate": 1.968e-06,
+      "loss": 1.3306,
+      "step": 400
+    },
+    {
+      "epoch": 0.04425170369059209,
+      "grad_norm": 0.4179963767528534,
+      "learning_rate": 1.96e-06,
+      "loss": 1.286,
+      "step": 500
+    },
+    {
+      "epoch": 0.053102044428710506,
+      "grad_norm": 0.4829399287700653,
+      "learning_rate": 1.9519999999999997e-06,
+      "loss": 1.2756,
+      "step": 600
+    },
+    {
+      "epoch": 0.061952385166828924,
+      "grad_norm": 0.5651261806488037,
+      "learning_rate": 1.944e-06,
+      "loss": 1.2721,
+      "step": 700
+    },
+    {
+      "epoch": 0.07080272590494734,
+      "grad_norm": 0.5160872936248779,
+      "learning_rate": 1.9359999999999998e-06,
+      "loss": 1.2579,
+      "step": 800
+    },
+    {
+      "epoch": 0.07965306664306576,
+      "grad_norm": 0.7501122355461121,
+      "learning_rate": 1.928e-06,
+      "loss": 1.2853,
+      "step": 900
+    },
+    {
+      "epoch": 0.08850340738118417,
+      "grad_norm": 0.591393232345581,
+      "learning_rate": 1.92e-06,
+      "loss": 1.2472,
+      "step": 1000
+    },
+    {
+      "epoch": 0.0973537481193026,
+      "grad_norm": 0.5573005080223083,
+      "learning_rate": 1.9119999999999997e-06,
+      "loss": 1.2348,
+      "step": 1100
+    },
+    {
+      "epoch": 0.10620408885742101,
+      "grad_norm": 0.607552707195282,
+      "learning_rate": 1.904e-06,
+      "loss": 1.2679,
+      "step": 1200
+    },
+    {
+      "epoch": 0.11505442959553942,
+      "grad_norm": 0.6899151802062988,
+      "learning_rate": 1.8959999999999997e-06,
+      "loss": 1.2513,
+      "step": 1300
+    },
+    {
+      "epoch": 0.12390477033365785,
+      "grad_norm": 0.5849478244781494,
+      "learning_rate": 1.8879999999999998e-06,
+      "loss": 1.226,
+      "step": 1400
+    },
+    {
+      "epoch": 0.13275511107177626,
+      "grad_norm": 0.6027043461799622,
+      "learning_rate": 1.8799999999999998e-06,
+      "loss": 1.2163,
+      "step": 1500
+    },
+    {
+      "epoch": 0.14160545180989467,
+      "grad_norm": 0.6785966157913208,
+      "learning_rate": 1.872e-06,
+      "loss": 1.2076,
+      "step": 1600
+    },
+    {
+      "epoch": 0.1504557925480131,
+      "grad_norm": 0.5975379347801208,
+      "learning_rate": 1.864e-06,
+      "loss": 1.2146,
+      "step": 1700
+    },
+    {
+      "epoch": 0.15930613328613152,
+      "grad_norm": 0.685453474521637,
+      "learning_rate": 1.856e-06,
+      "loss": 1.198,
+      "step": 1800
+    },
+    {
+      "epoch": 0.16815647402424994,
+      "grad_norm": 1.1250847578048706,
+      "learning_rate": 1.848e-06,
+      "loss": 1.218,
+      "step": 1900
+    },
+    {
+      "epoch": 0.17700681476236835,
+      "grad_norm": 0.6129019260406494,
+      "learning_rate": 1.84e-06,
+      "loss": 1.1894,
+      "step": 2000
+    },
+    {
+      "epoch": 0.18585715550048676,
+      "grad_norm": 0.7388463616371155,
+      "learning_rate": 1.832e-06,
+      "loss": 1.1962,
+      "step": 2100
+    },
+    {
+      "epoch": 0.1947074962386052,
+      "grad_norm": 0.5909475684165955,
+      "learning_rate": 1.824e-06,
+      "loss": 1.241,
+      "step": 2200
+    },
+    {
+      "epoch": 0.2035578369767236,
+      "grad_norm": 0.5264613032341003,
+      "learning_rate": 1.816e-06,
+      "loss": 1.1915,
+      "step": 2300
+    },
+    {
+      "epoch": 0.21240817771484202,
+      "grad_norm": 0.6419306397438049,
+      "learning_rate": 1.8079999999999999e-06,
+      "loss": 1.1938,
+      "step": 2400
+    },
+    {
+      "epoch": 0.22125851845296043,
+      "grad_norm": 0.6240788698196411,
+      "learning_rate": 1.8e-06,
+      "loss": 1.214,
+      "step": 2500
+    },
+    {
+      "epoch": 0.23010885919107885,
+      "grad_norm": 0.7954173684120178,
+      "learning_rate": 1.792e-06,
+      "loss": 1.195,
+      "step": 2600
+    },
+    {
+      "epoch": 0.23895919992919729,
+      "grad_norm": 0.7451553344726562,
+      "learning_rate": 1.784e-06,
+      "loss": 1.1793,
+      "step": 2700
+    },
+    {
+      "epoch": 0.2478095406673157,
+      "grad_norm": 0.8471085429191589,
+      "learning_rate": 1.776e-06,
+      "loss": 1.1895,
+      "step": 2800
+    },
+    {
+      "epoch": 0.2566598814054341,
+      "grad_norm": 1.0085513591766357,
+      "learning_rate": 1.7679999999999998e-06,
+      "loss": 1.2087,
+      "step": 2900
+    },
+    {
+      "epoch": 0.2655102221435525,
+      "grad_norm": 0.7709102630615234,
+      "learning_rate": 1.7599999999999999e-06,
+      "loss": 1.1959,
+      "step": 3000
+    },
+    {
+      "epoch": 0.27436056288167093,
+      "grad_norm": 0.7612162232398987,
+      "learning_rate": 1.752e-06,
+      "loss": 1.1803,
+      "step": 3100
+    },
+    {
+      "epoch": 0.28321090361978934,
+      "grad_norm": 1.0669310092926025,
+      "learning_rate": 1.744e-06,
+      "loss": 1.1548,
+      "step": 3200
+    },
+    {
+      "epoch": 0.29206124435790776,
+      "grad_norm": 0.7489383220672607,
+      "learning_rate": 1.736e-06,
+      "loss": 1.1654,
+      "step": 3300
+    },
+    {
+      "epoch": 0.3009115850960262,
+      "grad_norm": 0.8011970520019531,
+      "learning_rate": 1.7279999999999998e-06,
+      "loss": 1.1789,
+      "step": 3400
+    },
+    {
+      "epoch": 0.30976192583414464,
+      "grad_norm": 0.7374864816665649,
+      "learning_rate": 1.7199999999999998e-06,
+      "loss": 1.171,
+      "step": 3500
+    },
+    {
+      "epoch": 0.31861226657226305,
+      "grad_norm": 0.8267546892166138,
+      "learning_rate": 1.7119999999999999e-06,
+      "loss": 1.1435,
+      "step": 3600
+    },
+    {
+      "epoch": 0.32746260731038146,
+      "grad_norm": 0.8837570548057556,
+      "learning_rate": 1.704e-06,
+      "loss": 1.1674,
+      "step": 3700
+    },
+    {
+      "epoch": 0.33631294804849987,
+      "grad_norm": 0.7216938138008118,
+      "learning_rate": 1.696e-06,
+      "loss": 1.1446,
+      "step": 3800
+    },
+    {
+      "epoch": 0.3451632887866183,
+      "grad_norm": 0.8478527069091797,
+      "learning_rate": 1.6879999999999998e-06,
+      "loss": 1.1721,
+      "step": 3900
+    },
+    {
+      "epoch": 0.3540136295247367,
+      "grad_norm": 0.8281861543655396,
+      "learning_rate": 1.6799999999999998e-06,
+      "loss": 1.1741,
+      "step": 4000
+    },
+    {
+      "epoch": 0.3628639702628551,
+      "grad_norm": 0.6918274760246277,
+      "learning_rate": 1.6719999999999998e-06,
+      "loss": 1.1433,
+      "step": 4100
+    },
+    {
+      "epoch": 0.3717143110009735,
+      "grad_norm": 0.6722283363342285,
+      "learning_rate": 1.6639999999999999e-06,
+      "loss": 1.189,
+      "step": 4200
+    },
+    {
+      "epoch": 0.38056465173909193,
+      "grad_norm": 0.8337692022323608,
+      "learning_rate": 1.656e-06,
+      "loss": 1.1694,
+      "step": 4300
+    },
+    {
+      "epoch": 0.3894149924772104,
+      "grad_norm": 0.7980256080627441,
+      "learning_rate": 1.648e-06,
+      "loss": 1.1794,
+      "step": 4400
+    },
+    {
+      "epoch": 0.3982653332153288,
+      "grad_norm": 0.9903015494346619,
+      "learning_rate": 1.6399999999999998e-06,
+      "loss": 1.2027,
+      "step": 4500
+    },
+    {
+      "epoch": 0.4071156739534472,
+      "grad_norm": 0.7119297385215759,
+      "learning_rate": 1.6319999999999998e-06,
+      "loss": 1.1638,
+      "step": 4600
+    },
+    {
+      "epoch": 0.41596601469156563,
+      "grad_norm": 0.9170375466346741,
+      "learning_rate": 1.624e-06,
+      "loss": 1.1706,
+      "step": 4700
+    },
+    {
+      "epoch": 0.42481635542968404,
+      "grad_norm": 0.7098402976989746,
+      "learning_rate": 1.616e-06,
+      "loss": 1.1738,
+      "step": 4800
+    },
+    {
+      "epoch": 0.43366669616780246,
+      "grad_norm": 0.9326470494270325,
+      "learning_rate": 1.608e-06,
+      "loss": 1.1526,
+      "step": 4900
+    },
+    {
+      "epoch": 0.44251703690592087,
+      "grad_norm": 0.7765191197395325,
+      "learning_rate": 1.6e-06,
+      "loss": 1.1687,
+      "step": 5000
+    },
+    {
+      "epoch": 0.4513673776440393,
+      "grad_norm": 0.8953288197517395,
+      "learning_rate": 1.592e-06,
+      "loss": 1.1763,
+      "step": 5100
+    },
+    {
+      "epoch": 0.4602177183821577,
+      "grad_norm": 1.0437840223312378,
+      "learning_rate": 1.584e-06,
+      "loss": 1.1883,
+      "step": 5200
+    },
+    {
+      "epoch": 0.4690680591202761,
+      "grad_norm": 0.8432090282440186,
+      "learning_rate": 1.576e-06,
+      "loss": 1.1826,
+      "step": 5300
+    },
+    {
+      "epoch": 0.47791839985839457,
+      "grad_norm": 0.7580952048301697,
+      "learning_rate": 1.568e-06,
+      "loss": 1.1813,
+      "step": 5400
+    },
+    {
+      "epoch": 0.486768740596513,
+      "grad_norm": 0.9914817214012146,
+      "learning_rate": 1.5599999999999999e-06,
+      "loss": 1.1751,
+      "step": 5500
+    },
+    {
+      "epoch": 0.4956190813346314,
+      "grad_norm": 0.7643041610717773,
+      "learning_rate": 1.552e-06,
+      "loss": 1.1615,
+      "step": 5600
+    },
+    {
+      "epoch": 0.5044694220727498,
+      "grad_norm": 0.8275469541549683,
+      "learning_rate": 1.544e-06,
+      "loss": 1.188,
+      "step": 5700
+    },
+    {
+      "epoch": 0.5133197628108682,
+      "grad_norm": 1.950104832649231,
+      "learning_rate": 1.536e-06,
+      "loss": 1.2018,
+      "step": 5800
+    },
+    {
+      "epoch": 0.5221701035489866,
+      "grad_norm": 0.8191819787025452,
+      "learning_rate": 1.528e-06,
+      "loss": 1.1865,
+      "step": 5900
+    },
+    {
+      "epoch": 0.531020444287105,
+      "grad_norm": 0.7783402800559998,
+      "learning_rate": 1.5199999999999998e-06,
+      "loss": 1.1687,
+      "step": 6000
+    },
+    {
+      "epoch": 0.5398707850252235,
+      "grad_norm": 1.0385206937789917,
+      "learning_rate": 1.5119999999999999e-06,
+      "loss": 1.1883,
+      "step": 6100
+    },
+    {
+      "epoch": 0.5487211257633419,
+      "grad_norm": 0.9720994234085083,
+      "learning_rate": 1.504e-06,
+      "loss": 1.1824,
+      "step": 6200
+    },
+    {
+      "epoch": 0.5575714665014603,
+      "grad_norm": 0.9594699740409851,
+      "learning_rate": 1.496e-06,
+      "loss": 1.1908,
+      "step": 6300
+    },
+    {
+      "epoch": 0.5664218072395787,
+      "grad_norm": 0.9793533682823181,
+      "learning_rate": 1.488e-06,
+      "loss": 1.1385,
+      "step": 6400
+    },
+    {
+      "epoch": 0.5752721479776971,
+      "grad_norm": 0.9187788367271423,
+      "learning_rate": 1.48e-06,
+      "loss": 1.1536,
+      "step": 6500
+    },
+    {
+      "epoch": 0.5841224887158155,
+      "grad_norm": 0.9121326208114624,
+      "learning_rate": 1.4719999999999998e-06,
+      "loss": 1.1577,
+      "step": 6600
+    },
+    {
+      "epoch": 0.5929728294539339,
+      "grad_norm": 1.3253475427627563,
+      "learning_rate": 1.4639999999999999e-06,
+      "loss": 1.1462,
+      "step": 6700
+    },
+    {
+      "epoch": 0.6018231701920524,
+      "grad_norm": 0.9218689799308777,
+      "learning_rate": 1.456e-06,
+      "loss": 1.1745,
+      "step": 6800
+    },
+    {
+      "epoch": 0.6106735109301709,
+      "grad_norm": 0.8204641938209534,
+      "learning_rate": 1.448e-06,
+      "loss": 1.1871,
+      "step": 6900
+    },
+    {
+      "epoch": 0.6195238516682893,
+      "grad_norm": 0.8714615702629089,
+      "learning_rate": 1.44e-06,
+      "loss": 1.183,
+      "step": 7000
+    },
+    {
+      "epoch": 0.6283741924064077,
+      "grad_norm": 1.2564398050308228,
+      "learning_rate": 1.4319999999999998e-06,
+      "loss": 1.1614,
+      "step": 7100
+    },
+    {
+      "epoch": 0.6372245331445261,
+      "grad_norm": 0.8741295337677002,
+      "learning_rate": 1.4239999999999998e-06,
+      "loss": 1.1314,
+      "step": 7200
+    },
+    {
+      "epoch": 0.6460748738826445,
+      "grad_norm": 0.8480414152145386,
+      "learning_rate": 1.4159999999999999e-06,
+      "loss": 1.1522,
+      "step": 7300
+    },
+    {
+      "epoch": 0.6549252146207629,
+      "grad_norm": 1.0986804962158203,
+      "learning_rate": 1.408e-06,
+      "loss": 1.1885,
+      "step": 7400
+    },
+    {
+      "epoch": 0.6637755553588813,
+      "grad_norm": 0.9965903759002686,
+      "learning_rate": 1.4e-06,
+      "loss": 1.1804,
+      "step": 7500
+    },
+    {
+      "epoch": 0.6726258960969997,
+      "grad_norm": 1.079156756401062,
+      "learning_rate": 1.3919999999999998e-06,
+      "loss": 1.1797,
+      "step": 7600
+    },
+    {
+      "epoch": 0.6814762368351182,
+      "grad_norm": 1.0092281103134155,
+      "learning_rate": 1.3839999999999998e-06,
+      "loss": 1.1613,
+      "step": 7700
+    },
+    {
+      "epoch": 0.6903265775732366,
+      "grad_norm": 0.9988503456115723,
+      "learning_rate": 1.3759999999999998e-06,
+      "loss": 1.1526,
+      "step": 7800
+    },
+    {
+      "epoch": 0.699176918311355,
+      "grad_norm": 1.0048474073410034,
+      "learning_rate": 1.368e-06,
+      "loss": 1.1804,
+      "step": 7900
+    },
+    {
+      "epoch": 0.7080272590494734,
+      "grad_norm": 0.7530746459960938,
+      "learning_rate": 1.3600000000000001e-06,
+      "loss": 1.1465,
+      "step": 8000
+    },
+    {
+      "epoch": 0.7168775997875918,
+      "grad_norm": 0.6247321963310242,
+      "learning_rate": 1.352e-06,
+      "loss": 1.1385,
+      "step": 8100
+    },
+    {
+      "epoch": 0.7257279405257102,
+      "grad_norm": 0.7886361479759216,
+      "learning_rate": 1.344e-06,
+      "loss": 1.1857,
+      "step": 8200
+    },
+    {
+      "epoch": 0.7345782812638286,
+      "grad_norm": 0.8461400270462036,
+      "learning_rate": 1.336e-06,
+      "loss": 1.1612,
+      "step": 8300
+    },
+    {
+      "epoch": 0.743428622001947,
+      "grad_norm": 1.109844446182251,
+      "learning_rate": 1.328e-06,
+      "loss": 1.1406,
+      "step": 8400
+    },
+    {
+      "epoch": 0.7522789627400654,
+      "grad_norm": 0.8707802891731262,
+      "learning_rate": 1.32e-06,
+      "loss": 1.1719,
+      "step": 8500
+    },
+    {
+      "epoch": 0.7611293034781839,
+      "grad_norm": 0.8593458533287048,
+      "learning_rate": 1.312e-06,
+      "loss": 1.1696,
+      "step": 8600
+    },
+    {
+      "epoch": 0.7699796442163023,
+      "grad_norm": 0.8872305750846863,
+      "learning_rate": 1.304e-06,
+      "loss": 1.1772,
+      "step": 8700
+    },
+    {
+      "epoch": 0.7788299849544208,
+      "grad_norm": 0.9227966070175171,
+      "learning_rate": 1.296e-06,
+      "loss": 1.173,
+      "step": 8800
+    },
+    {
+      "epoch": 0.7876803256925392,
+      "grad_norm": 0.8818754553794861,
+      "learning_rate": 1.288e-06,
+      "loss": 1.1889,
+      "step": 8900
+    },
+    {
+      "epoch": 0.7965306664306576,
+      "grad_norm": 1.0658597946166992,
+      "learning_rate": 1.28e-06,
+      "loss": 1.1547,
+      "step": 9000
+    },
+    {
+      "epoch": 0.805381007168776,
+      "grad_norm": 0.8553236126899719,
+      "learning_rate": 1.272e-06,
+      "loss": 1.1172,
+      "step": 9100
+    },
+    {
+      "epoch": 0.8142313479068944,
+      "grad_norm": 1.120353102684021,
+      "learning_rate": 1.2639999999999999e-06,
+      "loss": 1.1649,
+      "step": 9200
+    },
+    {
+      "epoch": 0.8230816886450129,
+      "grad_norm": 0.734362006187439,
+      "learning_rate": 1.256e-06,
+      "loss": 1.1938,
+      "step": 9300
+    },
+    {
+      "epoch": 0.8319320293831313,
+      "grad_norm": 0.8664830923080444,
+      "learning_rate": 1.248e-06,
+      "loss": 1.1666,
+      "step": 9400
+    },
+    {
+      "epoch": 0.8407823701212497,
+      "grad_norm": 2.742342948913574,
+      "learning_rate": 1.24e-06,
+      "loss": 1.1807,
+      "step": 9500
+    },
+    {
+      "epoch": 0.8496327108593681,
+      "grad_norm": 1.302372694015503,
+      "learning_rate": 1.232e-06,
+      "loss": 1.1709,
+      "step": 9600
+    },
+    {
+      "epoch": 0.8584830515974865,
+      "grad_norm": 0.9084349870681763,
+      "learning_rate": 1.2239999999999998e-06,
+      "loss": 1.1405,
+      "step": 9700
+    },
+    {
+      "epoch": 0.8673333923356049,
+      "grad_norm": 0.8565220832824707,
+      "learning_rate": 1.2159999999999999e-06,
+      "loss": 1.1527,
+      "step": 9800
+    },
+    {
+      "epoch": 0.8761837330737233,
+      "grad_norm": 0.7832551002502441,
+      "learning_rate": 1.208e-06,
+      "loss": 1.1787,
+      "step": 9900
+    },
+    {
+      "epoch": 0.8850340738118417,
+      "grad_norm": 0.8366639018058777,
+      "learning_rate": 1.2e-06,
+      "loss": 1.1925,
+      "step": 10000
+    },
+    {
+      "epoch": 0.8938844145499601,
+      "grad_norm": 1.0785573720932007,
+      "learning_rate": 1.192e-06,
+      "loss": 1.1515,
+      "step": 10100
+    },
+    {
+      "epoch": 0.9027347552880786,
+      "grad_norm": 1.1639350652694702,
+      "learning_rate": 1.1839999999999998e-06,
+      "loss": 1.1742,
+      "step": 10200
+    },
+    {
+      "epoch": 0.911585096026197,
+      "grad_norm": 1.7552626132965088,
+      "learning_rate": 1.1759999999999998e-06,
+      "loss": 1.1719,
+      "step": 10300
+    },
+    {
+      "epoch": 0.9204354367643154,
+      "grad_norm": 1.1693079471588135,
+      "learning_rate": 1.1679999999999999e-06,
+      "loss": 1.1368,
+      "step": 10400
+    },
+    {
+      "epoch": 0.9292857775024338,
+      "grad_norm": 1.0168983936309814,
+      "learning_rate": 1.16e-06,
+      "loss": 1.1883,
+      "step": 10500
+    },
+    {
+      "epoch": 0.9381361182405522,
+      "grad_norm": 0.775669515132904,
+      "learning_rate": 1.152e-06,
+      "loss": 1.1538,
+      "step": 10600
+    },
+    {
+      "epoch": 0.9469864589786707,
+      "grad_norm": 0.7753804922103882,
+      "learning_rate": 1.1439999999999998e-06,
+      "loss": 1.1433,
+      "step": 10700
+    },
+    {
+      "epoch": 0.9558367997167891,
+      "grad_norm": 0.809089183807373,
+      "learning_rate": 1.1359999999999998e-06,
+      "loss": 1.1857,
+      "step": 10800
+    },
+    {
+      "epoch": 0.9646871404549076,
+      "grad_norm": 1.0428608655929565,
+      "learning_rate": 1.1279999999999998e-06,
+      "loss": 1.1477,
+      "step": 10900
+    },
+    {
+      "epoch": 0.973537481193026,
+      "grad_norm": 0.9207476377487183,
+      "learning_rate": 1.12e-06,
+      "loss": 1.1733,
+      "step": 11000
+    },
+    {
+      "epoch": 0.9823878219311444,
+      "grad_norm": 1.4796310663223267,
+      "learning_rate": 1.1120000000000001e-06,
+      "loss": 1.1619,
+      "step": 11100
+    },
+    {
+      "epoch": 0.9912381626692628,
+      "grad_norm": 0.9674447774887085,
+      "learning_rate": 1.1040000000000001e-06,
+      "loss": 1.1666,
+      "step": 11200
+    },
+    {
+      "epoch": 1.0000885034073812,
+      "grad_norm": 0.8573771715164185,
+      "learning_rate": 1.096e-06,
+      "loss": 1.1413,
+      "step": 11300
+    },
+    {
+      "epoch": 1.0089388441454996,
+      "grad_norm": 0.7278480529785156,
+      "learning_rate": 1.088e-06,
+      "loss": 1.1567,
+      "step": 11400
+    },
+    {
+      "epoch": 1.017789184883618,
+      "grad_norm": 1.0488468408584595,
+      "learning_rate": 1.08e-06,
+      "loss": 1.1742,
+      "step": 11500
+    },
+    {
+      "epoch": 1.0266395256217364,
+      "grad_norm": 0.9396333694458008,
+      "learning_rate": 1.072e-06,
+      "loss": 1.1516,
+      "step": 11600
+    },
+    {
+      "epoch": 1.0354898663598548,
+      "grad_norm": 1.034722089767456,
+      "learning_rate": 1.064e-06,
+      "loss": 1.1485,
+      "step": 11700
+    },
+    {
+      "epoch": 1.0443402070979733,
+      "grad_norm": 1.171837568283081,
+      "learning_rate": 1.056e-06,
+      "loss": 1.1531,
+      "step": 11800
+    },
+    {
+      "epoch": 1.0531905478360917,
+      "grad_norm": 0.7825940847396851,
+      "learning_rate": 1.048e-06,
+      "loss": 1.1721,
+      "step": 11900
+    },
+    {
+      "epoch": 1.06204088857421,
+      "grad_norm": 0.7846807837486267,
+      "learning_rate": 1.04e-06,
+      "loss": 1.1392,
+      "step": 12000
+    },
+    {
+      "epoch": 1.0708912293123285,
+      "grad_norm": 1.3031669855117798,
+      "learning_rate": 1.032e-06,
+      "loss": 1.1797,
+      "step": 12100
+    },
+    {
+      "epoch": 1.079741570050447,
+      "grad_norm": 0.7465079426765442,
+      "learning_rate": 1.024e-06,
+      "loss": 1.1756,
+      "step": 12200
+    },
+    {
+      "epoch": 1.0885919107885653,
+      "grad_norm": 0.8680482506752014,
+      "learning_rate": 1.0159999999999999e-06,
+      "loss": 1.1584,
+      "step": 12300
+    },
+    {
+      "epoch": 1.0974422515266837,
+      "grad_norm": 0.809716522693634,
+      "learning_rate": 1.008e-06,
+      "loss": 1.1791,
+      "step": 12400
+    },
+    {
+      "epoch": 1.1062925922648021,
+      "grad_norm": 1.1684801578521729,
+      "learning_rate": 1e-06,
+      "loss": 1.1717,
+      "step": 12500
+    },
+    {
+      "epoch": 1.1151429330029206,
+      "grad_norm": 0.9361375570297241,
+      "learning_rate": 9.92e-07,
+      "loss": 1.1436,
+      "step": 12600
+    },
+    {
+      "epoch": 1.123993273741039,
+      "grad_norm": 1.0289329290390015,
+      "learning_rate": 9.84e-07,
+      "loss": 1.1497,
+      "step": 12700
+    },
+    {
+      "epoch": 1.1328436144791574,
+      "grad_norm": 1.1782183647155762,
+      "learning_rate": 9.759999999999998e-07,
+      "loss": 1.1494,
+      "step": 12800
+    },
+    {
+      "epoch": 1.1416939552172758,
+      "grad_norm": 1.1286753416061401,
+      "learning_rate": 9.679999999999999e-07,
+      "loss": 1.1423,
+      "step": 12900
+    },
+    {
+      "epoch": 1.1505442959553942,
+      "grad_norm": 0.9268887639045715,
+      "learning_rate": 9.6e-07,
+      "loss": 1.1538,
+      "step": 13000
+    },
+    {
+      "epoch": 1.1593946366935126,
+      "grad_norm": 0.9235917329788208,
+      "learning_rate": 9.52e-07,
+      "loss": 1.1815,
+      "step": 13100
+    },
+    {
+      "epoch": 1.168244977431631,
+      "grad_norm": 0.9781365394592285,
+      "learning_rate": 9.439999999999999e-07,
+      "loss": 1.1706,
+      "step": 13200
+    },
+    {
+      "epoch": 1.1770953181697494,
+      "grad_norm": 0.9572964310646057,
+      "learning_rate": 9.36e-07,
+      "loss": 1.1543,
+      "step": 13300
+    },
+    {
+      "epoch": 1.185945658907868,
+      "grad_norm": 1.019444465637207,
+      "learning_rate": 9.28e-07,
+      "loss": 1.1272,
+      "step": 13400
+    },
+    {
+      "epoch": 1.1947959996459865,
+      "grad_norm": 0.8430559039115906,
+      "learning_rate": 9.2e-07,
+      "loss": 1.1859,
+      "step": 13500
+    },
+    {
+      "epoch": 1.203646340384105,
+      "grad_norm": 0.7822268009185791,
+      "learning_rate": 9.12e-07,
+      "loss": 1.148,
+      "step": 13600
+    },
+    {
+      "epoch": 1.2124966811222233,
+      "grad_norm": 1.0175526142120361,
+      "learning_rate": 9.039999999999999e-07,
+      "loss": 1.1634,
+      "step": 13700
+    },
+    {
+      "epoch": 1.2213470218603417,
+      "grad_norm": 1.0795433521270752,
+      "learning_rate": 8.96e-07,
+      "loss": 1.1476,
+      "step": 13800
+    },
+    {
+      "epoch": 1.2301973625984601,
+      "grad_norm": 0.8210746645927429,
+      "learning_rate": 8.88e-07,
+      "loss": 1.1392,
+      "step": 13900
+    },
+    {
+      "epoch": 1.2390477033365785,
+      "grad_norm": 0.9926521182060242,
+      "learning_rate": 8.799999999999999e-07,
+      "loss": 1.1729,
+      "step": 14000
+    },
+    {
+      "epoch": 1.247898044074697,
+      "grad_norm": 0.968110978603363,
+      "learning_rate": 8.72e-07,
+      "loss": 1.1672,
+      "step": 14100
+    },
+    {
+      "epoch": 1.2567483848128154,
+      "grad_norm": 0.7728704214096069,
+      "learning_rate": 8.639999999999999e-07,
+      "loss": 1.1542,
+      "step": 14200
+    },
+    {
+      "epoch": 1.2655987255509338,
+      "grad_norm": 0.9193831086158752,
+      "learning_rate": 8.559999999999999e-07,
+      "loss": 1.1604,
+      "step": 14300
+    },
+    {
+      "epoch": 1.2744490662890522,
+      "grad_norm": 0.9755778908729553,
+      "learning_rate": 8.48e-07,
+      "loss": 1.1698,
+      "step": 14400
+    },
+    {
+      "epoch": 1.2832994070271706,
+      "grad_norm": 0.8752692341804504,
+      "learning_rate": 8.399999999999999e-07,
+      "loss": 1.1445,
+      "step": 14500
+    },
+    {
+      "epoch": 1.292149747765289,
+      "grad_norm": 1.2579710483551025,
+      "learning_rate": 8.319999999999999e-07,
+      "loss": 1.1514,
+      "step": 14600
+    },
+    {
+      "epoch": 1.3010000885034074,
+      "grad_norm": 0.8720273971557617,
+      "learning_rate": 8.24e-07,
+      "loss": 1.1835,
+      "step": 14700
+    },
+    {
+      "epoch": 1.3098504292415258,
+      "grad_norm": 1.3184126615524292,
+      "learning_rate": 8.159999999999999e-07,
+      "loss": 1.1576,
+      "step": 14800
+    },
+    {
+      "epoch": 1.3187007699796442,
+      "grad_norm": 1.0269840955734253,
+      "learning_rate": 8.08e-07,
+      "loss": 1.133,
+      "step": 14900
+    },
+    {
+      "epoch": 1.3275511107177627,
+      "grad_norm": 1.114967942237854,
+      "learning_rate": 8e-07,
+      "loss": 1.1486,
+      "step": 15000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 25000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 5000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.479834242972654e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-15000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c33153550b6b3f2d3c9440e20ffbe5ac26d7d58fbfe186f83bf0972f9688038
+size 5368