Training in progress, epoch 5, checkpoint

checkpoint-77845/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-77845/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-77845/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc7facb831852f92c4f97837002a03007a573d8adeb50221de8c8212e0271460
+size 541459256

checkpoint-77845/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63f533b7befce26207da22adf391710a05329bf8e18ca374bebbcdbcb2a08a8e
+size 33662074

checkpoint-77845/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b4363da68ea6149a315c2d40ad55f4fd37a701af175f08f559cb3967b995780
+size 15024

checkpoint-77845/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8caecff2975f6e5f3ea5ac2a1ef795a9cc0797bff219276680b7b80dbec03b99
+size 15024

checkpoint-77845/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b8f5be5ad01141a354ed6481dd4287c3c24717245e0d0e6d17c3c0e41a753e
+size 15024

checkpoint-77845/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09fee30e3fa76ec82eb2ad29fb78fc55cca6b513a539239465003264e5bf1a77
+size 15024

checkpoint-77845/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdfebb9a986767ec0152c538cadc3906d195d7f9d0d9430dc0b983461bd04166
+size 1064

checkpoint-77845/trainer_state.json

@@ -0,0 +1,1310 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 3114,
+  "global_step": 77845,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03211510052026463,
+      "grad_norm": 0.6881807446479797,
+      "learning_rate": 0.00039893377866272726,
+      "loss": 0.3182,
+      "step": 500
+    },
+    {
+      "epoch": 0.06423020104052926,
+      "grad_norm": 0.40920817852020264,
+      "learning_rate": 0.00039786327531205173,
+      "loss": 0.2226,
+      "step": 1000
+    },
+    {
+      "epoch": 0.09634530156079389,
+      "grad_norm": 0.38458916544914246,
+      "learning_rate": 0.00039679277196137626,
+      "loss": 0.2056,
+      "step": 1500
+    },
+    {
+      "epoch": 0.12846040208105852,
+      "grad_norm": 0.3895084857940674,
+      "learning_rate": 0.0003957222686107008,
+      "loss": 0.1921,
+      "step": 2000
+    },
+    {
+      "epoch": 0.16057550260132314,
+      "grad_norm": 1.2132288217544556,
+      "learning_rate": 0.00039465176526002526,
+      "loss": 0.1828,
+      "step": 2500
+    },
+    {
+      "epoch": 0.19269060312158778,
+      "grad_norm": 0.354610413312912,
+      "learning_rate": 0.0003935812619093498,
+      "loss": 0.1813,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2000128460402081,
+      "eval_loss": 0.164720818400383,
+      "eval_runtime": 7.2965,
+      "eval_samples_per_second": 68.526,
+      "eval_steps_per_second": 8.634,
+      "step": 3114
+    },
+    {
+      "epoch": 0.2248057036418524,
+      "grad_norm": 0.6251304745674133,
+      "learning_rate": 0.00039251289956537567,
+      "loss": 0.1745,
+      "step": 3500
+    },
+    {
+      "epoch": 0.25692080416211704,
+      "grad_norm": 0.46483030915260315,
+      "learning_rate": 0.0003914445372214015,
+      "loss": 0.1701,
+      "step": 4000
+    },
+    {
+      "epoch": 0.28903590468238166,
+      "grad_norm": 0.477145254611969,
+      "learning_rate": 0.000390374033870726,
+      "loss": 0.1692,
+      "step": 4500
+    },
+    {
+      "epoch": 0.3211510052026463,
+      "grad_norm": 0.4863433539867401,
+      "learning_rate": 0.00038930353052005055,
+      "loss": 0.1633,
+      "step": 5000
+    },
+    {
+      "epoch": 0.3532661057229109,
+      "grad_norm": 0.3692472279071808,
+      "learning_rate": 0.000388233027169375,
+      "loss": 0.1623,
+      "step": 5500
+    },
+    {
+      "epoch": 0.38538120624317557,
+      "grad_norm": 0.5566384792327881,
+      "learning_rate": 0.00038716252381869955,
+      "loss": 0.1601,
+      "step": 6000
+    },
+    {
+      "epoch": 0.4000256920804162,
+      "eval_loss": 0.14738531410694122,
+      "eval_runtime": 7.3011,
+      "eval_samples_per_second": 68.483,
+      "eval_steps_per_second": 8.629,
+      "step": 6228
+    },
+    {
+      "epoch": 0.4174963067634402,
+      "grad_norm": 0.5637210011482239,
+      "learning_rate": 0.0003860920204680241,
+      "loss": 0.1569,
+      "step": 6500
+    },
+    {
+      "epoch": 0.4496114072837048,
+      "grad_norm": 0.34262317419052124,
+      "learning_rate": 0.00038502365812404996,
+      "loss": 0.1549,
+      "step": 7000
+    },
+    {
+      "epoch": 0.4817265078039694,
+      "grad_norm": 0.8737928867340088,
+      "learning_rate": 0.00038395529578007584,
+      "loss": 0.1558,
+      "step": 7500
+    },
+    {
+      "epoch": 0.5138416083242341,
+      "grad_norm": 0.3039982318878174,
+      "learning_rate": 0.00038288479242940037,
+      "loss": 0.1519,
+      "step": 8000
+    },
+    {
+      "epoch": 0.5459567088444987,
+      "grad_norm": 0.4347224831581116,
+      "learning_rate": 0.00038181428907872484,
+      "loss": 0.1505,
+      "step": 8500
+    },
+    {
+      "epoch": 0.5780718093647633,
+      "grad_norm": 0.39854001998901367,
+      "learning_rate": 0.00038074378572804937,
+      "loss": 0.1496,
+      "step": 9000
+    },
+    {
+      "epoch": 0.6000385381206244,
+      "eval_loss": 0.13884712755680084,
+      "eval_runtime": 7.294,
+      "eval_samples_per_second": 68.55,
+      "eval_steps_per_second": 8.637,
+      "step": 9342
+    },
+    {
+      "epoch": 0.610186909885028,
+      "grad_norm": 0.6563107967376709,
+      "learning_rate": 0.0003796732823773739,
+      "loss": 0.1472,
+      "step": 9500
+    },
+    {
+      "epoch": 0.6423020104052926,
+      "grad_norm": 0.3582533597946167,
+      "learning_rate": 0.00037860277902669837,
+      "loss": 0.1457,
+      "step": 10000
+    },
+    {
+      "epoch": 0.6744171109255572,
+      "grad_norm": 0.6487281322479248,
+      "learning_rate": 0.0003775322756760229,
+      "loss": 0.1484,
+      "step": 10500
+    },
+    {
+      "epoch": 0.7065322114458218,
+      "grad_norm": 0.6346992254257202,
+      "learning_rate": 0.0003764617723253474,
+      "loss": 0.1453,
+      "step": 11000
+    },
+    {
+      "epoch": 0.7386473119660865,
+      "grad_norm": 0.5041869878768921,
+      "learning_rate": 0.0003753912689746719,
+      "loss": 0.1454,
+      "step": 11500
+    },
+    {
+      "epoch": 0.7707624124863511,
+      "grad_norm": 0.3400748372077942,
+      "learning_rate": 0.0003743207656239964,
+      "loss": 0.1441,
+      "step": 12000
+    },
+    {
+      "epoch": 0.8000513841608324,
+      "eval_loss": 0.13148044049739838,
+      "eval_runtime": 7.2929,
+      "eval_samples_per_second": 68.56,
+      "eval_steps_per_second": 8.639,
+      "step": 12456
+    },
+    {
+      "epoch": 0.8028775130066157,
+      "grad_norm": 0.32738161087036133,
+      "learning_rate": 0.00037325026227332095,
+      "loss": 0.1445,
+      "step": 12500
+    },
+    {
+      "epoch": 0.8349926135268804,
+      "grad_norm": 0.3660726845264435,
+      "learning_rate": 0.0003721818999293468,
+      "loss": 0.1424,
+      "step": 13000
+    },
+    {
+      "epoch": 0.8671077140471449,
+      "grad_norm": 0.5750604867935181,
+      "learning_rate": 0.000371115678592074,
+      "loss": 0.1469,
+      "step": 13500
+    },
+    {
+      "epoch": 0.8992228145674096,
+      "grad_norm": 0.35107406973838806,
+      "learning_rate": 0.00037004517524139854,
+      "loss": 0.147,
+      "step": 14000
+    },
+    {
+      "epoch": 0.9313379150876743,
+      "grad_norm": 0.4457557499408722,
+      "learning_rate": 0.000368974671890723,
+      "loss": 0.1416,
+      "step": 14500
+    },
+    {
+      "epoch": 0.9634530156079388,
+      "grad_norm": 0.4570375382900238,
+      "learning_rate": 0.00036790416854004754,
+      "loss": 0.1391,
+      "step": 15000
+    },
+    {
+      "epoch": 0.9955681161282035,
+      "grad_norm": 0.5502489805221558,
+      "learning_rate": 0.00036683366518937207,
+      "loss": 0.1408,
+      "step": 15500
+    },
+    {
+      "epoch": 1.0000642302010405,
+      "eval_loss": 0.1298205852508545,
+      "eval_runtime": 7.3714,
+      "eval_samples_per_second": 67.829,
+      "eval_steps_per_second": 8.547,
+      "step": 15570
+    },
+    {
+      "epoch": 1.0276832166484682,
+      "grad_norm": 0.41828590631484985,
+      "learning_rate": 0.0003657631618386966,
+      "loss": 0.1312,
+      "step": 16000
+    },
+    {
+      "epoch": 1.0597983171687329,
+      "grad_norm": 0.4035309851169586,
+      "learning_rate": 0.00036469265848802107,
+      "loss": 0.1298,
+      "step": 16500
+    },
+    {
+      "epoch": 1.0919134176889973,
+      "grad_norm": 0.38738253712654114,
+      "learning_rate": 0.0003636221551373456,
+      "loss": 0.1289,
+      "step": 17000
+    },
+    {
+      "epoch": 1.124028518209262,
+      "grad_norm": 0.4483577609062195,
+      "learning_rate": 0.0003625516517866701,
+      "loss": 0.1308,
+      "step": 17500
+    },
+    {
+      "epoch": 1.1561436187295266,
+      "grad_norm": 0.36913159489631653,
+      "learning_rate": 0.0003614811484359946,
+      "loss": 0.1313,
+      "step": 18000
+    },
+    {
+      "epoch": 1.1882587192497913,
+      "grad_norm": 0.4135682284832001,
+      "learning_rate": 0.0003604106450853191,
+      "loss": 0.1308,
+      "step": 18500
+    },
+    {
+      "epoch": 1.2000770762412487,
+      "eval_loss": 0.12298451364040375,
+      "eval_runtime": 7.2977,
+      "eval_samples_per_second": 68.515,
+      "eval_steps_per_second": 8.633,
+      "step": 18684
+    },
+    {
+      "epoch": 1.2203738197700558,
+      "grad_norm": 0.5066474676132202,
+      "learning_rate": 0.00035934014173464365,
+      "loss": 0.1294,
+      "step": 19000
+    },
+    {
+      "epoch": 1.2524889202903204,
+      "grad_norm": 0.35160061717033386,
+      "learning_rate": 0.0003582696383839681,
+      "loss": 0.1297,
+      "step": 19500
+    },
+    {
+      "epoch": 1.2846040208105851,
+      "grad_norm": 0.5103857517242432,
+      "learning_rate": 0.00035719913503329265,
+      "loss": 0.1307,
+      "step": 20000
+    },
+    {
+      "epoch": 1.3167191213308498,
+      "grad_norm": 0.35336533188819885,
+      "learning_rate": 0.0003561286316826172,
+      "loss": 0.1275,
+      "step": 20500
+    },
+    {
+      "epoch": 1.3488342218511145,
+      "grad_norm": 0.3233303725719452,
+      "learning_rate": 0.0003550581283319417,
+      "loss": 0.1247,
+      "step": 21000
+    },
+    {
+      "epoch": 1.3809493223713791,
+      "grad_norm": 0.4102284014225006,
+      "learning_rate": 0.0003539897659879676,
+      "loss": 0.128,
+      "step": 21500
+    },
+    {
+      "epoch": 1.4000899222814567,
+      "eval_loss": 0.12551982700824738,
+      "eval_runtime": 7.3096,
+      "eval_samples_per_second": 68.403,
+      "eval_steps_per_second": 8.619,
+      "step": 21798
+    },
+    {
+      "epoch": 1.4130644228916436,
+      "grad_norm": 0.43554574251174927,
+      "learning_rate": 0.0003529192626372921,
+      "loss": 0.1268,
+      "step": 22000
+    },
+    {
+      "epoch": 1.4451795234119083,
+      "grad_norm": 0.4067144989967346,
+      "learning_rate": 0.0003518487592866166,
+      "loss": 0.1265,
+      "step": 22500
+    },
+    {
+      "epoch": 1.477294623932173,
+      "grad_norm": 0.5447452664375305,
+      "learning_rate": 0.0003507782559359411,
+      "loss": 0.1261,
+      "step": 23000
+    },
+    {
+      "epoch": 1.5094097244524374,
+      "grad_norm": 0.5342037677764893,
+      "learning_rate": 0.000349709893591967,
+      "loss": 0.1249,
+      "step": 23500
+    },
+    {
+      "epoch": 1.541524824972702,
+      "grad_norm": 0.5300814509391785,
+      "learning_rate": 0.00034863939024129146,
+      "loss": 0.1255,
+      "step": 24000
+    },
+    {
+      "epoch": 1.5736399254929667,
+      "grad_norm": 0.4534071981906891,
+      "learning_rate": 0.00034757102789731735,
+      "loss": 0.1281,
+      "step": 24500
+    },
+    {
+      "epoch": 1.6001027683216649,
+      "eval_loss": 0.11974115669727325,
+      "eval_runtime": 7.3112,
+      "eval_samples_per_second": 68.388,
+      "eval_steps_per_second": 8.617,
+      "step": 24912
+    },
+    {
+      "epoch": 1.6057550260132314,
+      "grad_norm": 0.39113229513168335,
+      "learning_rate": 0.0003465005245466419,
+      "loss": 0.1269,
+      "step": 25000
+    },
+    {
+      "epoch": 1.637870126533496,
+      "grad_norm": 0.5367024540901184,
+      "learning_rate": 0.00034543002119596635,
+      "loss": 0.1268,
+      "step": 25500
+    },
+    {
+      "epoch": 1.6699852270537607,
+      "grad_norm": 0.3257845640182495,
+      "learning_rate": 0.0003443595178452909,
+      "loss": 0.1236,
+      "step": 26000
+    },
+    {
+      "epoch": 1.7021003275740254,
+      "grad_norm": 0.4521988034248352,
+      "learning_rate": 0.0003432890144946154,
+      "loss": 0.1234,
+      "step": 26500
+    },
+    {
+      "epoch": 1.73421542809429,
+      "grad_norm": 0.4063723683357239,
+      "learning_rate": 0.00034222065215064123,
+      "loss": 0.1238,
+      "step": 27000
+    },
+    {
+      "epoch": 1.7663305286145545,
+      "grad_norm": 0.41461870074272156,
+      "learning_rate": 0.00034115014879996576,
+      "loss": 0.123,
+      "step": 27500
+    },
+    {
+      "epoch": 1.7984456291348192,
+      "grad_norm": 0.3680518567562103,
+      "learning_rate": 0.0003400796454492903,
+      "loss": 0.1239,
+      "step": 28000
+    },
+    {
+      "epoch": 1.8001156143618728,
+      "eval_loss": 0.11659311503171921,
+      "eval_runtime": 7.3186,
+      "eval_samples_per_second": 68.319,
+      "eval_steps_per_second": 8.608,
+      "step": 28026
+    },
+    {
+      "epoch": 1.8305607296550839,
+      "grad_norm": 0.4289158284664154,
+      "learning_rate": 0.0003390091420986148,
+      "loss": 0.1265,
+      "step": 28500
+    },
+    {
+      "epoch": 1.8626758301753483,
+      "grad_norm": 0.6132258772850037,
+      "learning_rate": 0.0003379386387479393,
+      "loss": 0.1231,
+      "step": 29000
+    },
+    {
+      "epoch": 1.894790930695613,
+      "grad_norm": 0.6142964959144592,
+      "learning_rate": 0.0003368681353972638,
+      "loss": 0.1242,
+      "step": 29500
+    },
+    {
+      "epoch": 1.9269060312158777,
+      "grad_norm": 0.29933828115463257,
+      "learning_rate": 0.00033579763204658834,
+      "loss": 0.1224,
+      "step": 30000
+    },
+    {
+      "epoch": 1.9590211317361423,
+      "grad_norm": 0.4025266170501709,
+      "learning_rate": 0.0003347271286959128,
+      "loss": 0.123,
+      "step": 30500
+    },
+    {
+      "epoch": 1.991136232256407,
+      "grad_norm": 0.4255163073539734,
+      "learning_rate": 0.00033365662534523734,
+      "loss": 0.1226,
+      "step": 31000
+    },
+    {
+      "epoch": 2.000128460402081,
+      "eval_loss": 0.11819276958703995,
+      "eval_runtime": 7.4375,
+      "eval_samples_per_second": 67.227,
+      "eval_steps_per_second": 8.471,
+      "step": 31140
+    },
+    {
+      "epoch": 2.0232513327766717,
+      "grad_norm": 0.5175437927246094,
+      "learning_rate": 0.00033258612199456186,
+      "loss": 0.1163,
+      "step": 31500
+    },
+    {
+      "epoch": 2.0553664332969364,
+      "grad_norm": 0.43255355954170227,
+      "learning_rate": 0.00033151561864388634,
+      "loss": 0.1146,
+      "step": 32000
+    },
+    {
+      "epoch": 2.087481533817201,
+      "grad_norm": 0.506144642829895,
+      "learning_rate": 0.00033044511529321086,
+      "loss": 0.1129,
+      "step": 32500
+    },
+    {
+      "epoch": 2.1195966343374657,
+      "grad_norm": 0.5078917145729065,
+      "learning_rate": 0.0003293746119425354,
+      "loss": 0.1145,
+      "step": 33000
+    },
+    {
+      "epoch": 2.15171173485773,
+      "grad_norm": 0.507586658000946,
+      "learning_rate": 0.0003283041085918599,
+      "loss": 0.1123,
+      "step": 33500
+    },
+    {
+      "epoch": 2.1838268353779946,
+      "grad_norm": 0.4673985242843628,
+      "learning_rate": 0.00032723574624788574,
+      "loss": 0.1136,
+      "step": 34000
+    },
+    {
+      "epoch": 2.2001413064422892,
+      "eval_loss": 0.11647045612335205,
+      "eval_runtime": 7.3242,
+      "eval_samples_per_second": 68.267,
+      "eval_steps_per_second": 8.602,
+      "step": 34254
+    },
+    {
+      "epoch": 2.2159419358982593,
+      "grad_norm": 0.5816234350204468,
+      "learning_rate": 0.0003261673839039116,
+      "loss": 0.1162,
+      "step": 34500
+    },
+    {
+      "epoch": 2.248057036418524,
+      "grad_norm": 0.3159160912036896,
+      "learning_rate": 0.00032509688055323615,
+      "loss": 0.1177,
+      "step": 35000
+    },
+    {
+      "epoch": 2.2801721369387886,
+      "grad_norm": 0.5306550860404968,
+      "learning_rate": 0.0003240263772025606,
+      "loss": 0.1144,
+      "step": 35500
+    },
+    {
+      "epoch": 2.3122872374590533,
+      "grad_norm": 0.5449818968772888,
+      "learning_rate": 0.0003229558738518852,
+      "loss": 0.113,
+      "step": 36000
+    },
+    {
+      "epoch": 2.344402337979318,
+      "grad_norm": 0.41796988248825073,
+      "learning_rate": 0.0003218853705012097,
+      "loss": 0.114,
+      "step": 36500
+    },
+    {
+      "epoch": 2.3765174384995826,
+      "grad_norm": 0.5479010343551636,
+      "learning_rate": 0.00032081700815723556,
+      "loss": 0.1148,
+      "step": 37000
+    },
+    {
+      "epoch": 2.4001541524824974,
+      "eval_loss": 0.11464451998472214,
+      "eval_runtime": 7.324,
+      "eval_samples_per_second": 68.269,
+      "eval_steps_per_second": 8.602,
+      "step": 37368
+    },
+    {
+      "epoch": 2.4086325390198473,
+      "grad_norm": 0.34335535764694214,
+      "learning_rate": 0.0003197465048065601,
+      "loss": 0.1144,
+      "step": 37500
+    },
+    {
+      "epoch": 2.4407476395401115,
+      "grad_norm": 0.4916399419307709,
+      "learning_rate": 0.00031867600145588456,
+      "loss": 0.1134,
+      "step": 38000
+    },
+    {
+      "epoch": 2.472862740060376,
+      "grad_norm": 0.5686454772949219,
+      "learning_rate": 0.0003176054981052091,
+      "loss": 0.1116,
+      "step": 38500
+    },
+    {
+      "epoch": 2.504977840580641,
+      "grad_norm": 0.3755095601081848,
+      "learning_rate": 0.0003165349947545336,
+      "loss": 0.1128,
+      "step": 39000
+    },
+    {
+      "epoch": 2.5370929411009056,
+      "grad_norm": 0.4691629409790039,
+      "learning_rate": 0.00031546449140385814,
+      "loss": 0.1123,
+      "step": 39500
+    },
+    {
+      "epoch": 2.5692080416211702,
+      "grad_norm": 0.5287884473800659,
+      "learning_rate": 0.0003143939880531826,
+      "loss": 0.1154,
+      "step": 40000
+    },
+    {
+      "epoch": 2.600166998522705,
+      "eval_loss": 0.10910294204950333,
+      "eval_runtime": 7.3339,
+      "eval_samples_per_second": 68.176,
+      "eval_steps_per_second": 8.59,
+      "step": 40482
+    },
+    {
+      "epoch": 2.601323142141435,
+      "grad_norm": 0.5030823945999146,
+      "learning_rate": 0.00031332348470250714,
+      "loss": 0.1145,
+      "step": 40500
+    },
+    {
+      "epoch": 2.6334382426616996,
+      "grad_norm": 0.6581201553344727,
+      "learning_rate": 0.00031225298135183167,
+      "loss": 0.1127,
+      "step": 41000
+    },
+    {
+      "epoch": 2.6655533431819642,
+      "grad_norm": 0.5677359700202942,
+      "learning_rate": 0.0003111846190078575,
+      "loss": 0.1121,
+      "step": 41500
+    },
+    {
+      "epoch": 2.697668443702229,
+      "grad_norm": 0.44164523482322693,
+      "learning_rate": 0.0003101162566638834,
+      "loss": 0.1106,
+      "step": 42000
+    },
+    {
+      "epoch": 2.729783544222493,
+      "grad_norm": 0.5856674313545227,
+      "learning_rate": 0.0003090457533132079,
+      "loss": 0.1102,
+      "step": 42500
+    },
+    {
+      "epoch": 2.7618986447427583,
+      "grad_norm": 0.41598838567733765,
+      "learning_rate": 0.0003079752499625324,
+      "loss": 0.1123,
+      "step": 43000
+    },
+    {
+      "epoch": 2.7940137452630225,
+      "grad_norm": 0.5005472898483276,
+      "learning_rate": 0.0003069047466118569,
+      "loss": 0.1142,
+      "step": 43500
+    },
+    {
+      "epoch": 2.8001798445629134,
+      "eval_loss": 0.10679365694522858,
+      "eval_runtime": 7.3241,
+      "eval_samples_per_second": 68.267,
+      "eval_steps_per_second": 8.602,
+      "step": 43596
+    },
+    {
+      "epoch": 2.826128845783287,
+      "grad_norm": 0.615060031414032,
+      "learning_rate": 0.00030583424326118143,
+      "loss": 0.1125,
+      "step": 44000
+    },
+    {
+      "epoch": 2.858243946303552,
+      "grad_norm": 0.5374606251716614,
+      "learning_rate": 0.0003047637399105059,
+      "loss": 0.1121,
+      "step": 44500
+    },
+    {
+      "epoch": 2.8903590468238165,
+      "grad_norm": 0.44819122552871704,
+      "learning_rate": 0.00030369323655983043,
+      "loss": 0.1127,
+      "step": 45000
+    },
+    {
+      "epoch": 2.922474147344081,
+      "grad_norm": 0.4970841705799103,
+      "learning_rate": 0.00030262273320915496,
+      "loss": 0.1104,
+      "step": 45500
+    },
+    {
+      "epoch": 2.954589247864346,
+      "grad_norm": 0.4294310510158539,
+      "learning_rate": 0.0003015543708651808,
+      "loss": 0.1108,
+      "step": 46000
+    },
+    {
+      "epoch": 2.9867043483846105,
+      "grad_norm": 0.8992510437965393,
+      "learning_rate": 0.0003004838675145053,
+      "loss": 0.1092,
+      "step": 46500
+    },
+    {
+      "epoch": 3.0001926906031215,
+      "eval_loss": 0.1059611514210701,
+      "eval_runtime": 7.487,
+      "eval_samples_per_second": 66.782,
+      "eval_steps_per_second": 8.415,
+      "step": 46710
+    },
+    {
+      "epoch": 3.018819448904875,
+      "grad_norm": 0.44859662652015686,
+      "learning_rate": 0.00029941336416382984,
+      "loss": 0.1058,
+      "step": 47000
+    },
+    {
+      "epoch": 3.05093454942514,
+      "grad_norm": 0.47559085488319397,
+      "learning_rate": 0.00029834286081315437,
+      "loss": 0.1032,
+      "step": 47500
+    },
+    {
+      "epoch": 3.0830496499454045,
+      "grad_norm": 0.47841718792915344,
+      "learning_rate": 0.00029727235746247884,
+      "loss": 0.101,
+      "step": 48000
+    },
+    {
+      "epoch": 3.1151647504656688,
+      "grad_norm": 0.40354153513908386,
+      "learning_rate": 0.0002962039951185047,
+      "loss": 0.1011,
+      "step": 48500
+    },
+    {
+      "epoch": 3.1472798509859334,
+      "grad_norm": 0.4232326149940491,
+      "learning_rate": 0.00029513563277453055,
+      "loss": 0.1022,
+      "step": 49000
+    },
+    {
+      "epoch": 3.179394951506198,
+      "grad_norm": 0.3321347236633301,
+      "learning_rate": 0.0002940651294238551,
+      "loss": 0.1035,
+      "step": 49500
+    },
+    {
+      "epoch": 3.2002055366433297,
+      "eval_loss": 0.10808317363262177,
+      "eval_runtime": 7.3206,
+      "eval_samples_per_second": 68.301,
+      "eval_steps_per_second": 8.606,
+      "step": 49824
+    },
+    {
+      "epoch": 3.211510052026463,
+      "grad_norm": 0.3930283188819885,
+      "learning_rate": 0.0002929946260731796,
+      "loss": 0.1031,
+      "step": 50000
+    },
+    {
+      "epoch": 3.2436251525467275,
+      "grad_norm": 0.3710777759552002,
+      "learning_rate": 0.00029192412272250413,
+      "loss": 0.1037,
+      "step": 50500
+    },
+    {
+      "epoch": 3.275740253066992,
+      "grad_norm": 0.4590394198894501,
+      "learning_rate": 0.00029085361937182866,
+      "loss": 0.1014,
+      "step": 51000
+    },
+    {
+      "epoch": 3.307855353587257,
+      "grad_norm": 0.5470544099807739,
+      "learning_rate": 0.0002897831160211532,
+      "loss": 0.1044,
+      "step": 51500
+    },
+    {
+      "epoch": 3.3399704541075215,
+      "grad_norm": 0.7178152203559875,
+      "learning_rate": 0.0002887126126704777,
+      "loss": 0.1017,
+      "step": 52000
+    },
+    {
+      "epoch": 3.372085554627786,
+      "grad_norm": 0.5023342370986938,
+      "learning_rate": 0.0002876421093198022,
+      "loss": 0.1045,
+      "step": 52500
+    },
+    {
+      "epoch": 3.400218382683538,
+      "eval_loss": 0.1036703959107399,
+      "eval_runtime": 7.3368,
+      "eval_samples_per_second": 68.15,
+      "eval_steps_per_second": 8.587,
+      "step": 52938
+    },
+    {
+      "epoch": 3.404200655148051,
+      "grad_norm": 0.49040645360946655,
+      "learning_rate": 0.0002865716059691267,
+      "loss": 0.1057,
+      "step": 53000
+    },
+    {
+      "epoch": 3.436315755668315,
+      "grad_norm": 0.4539451599121094,
+      "learning_rate": 0.0002855053846318539,
+      "loss": 0.1045,
+      "step": 53500
+    },
+    {
+      "epoch": 3.4684308561885797,
+      "grad_norm": 0.3792193830013275,
+      "learning_rate": 0.0002844348812811784,
+      "loss": 0.1051,
+      "step": 54000
+    },
+    {
+      "epoch": 3.5005459567088444,
+      "grad_norm": 0.5674263834953308,
+      "learning_rate": 0.00028336437793050295,
+      "loss": 0.1052,
+      "step": 54500
+    },
+    {
+      "epoch": 3.532661057229109,
+      "grad_norm": 0.550486147403717,
+      "learning_rate": 0.0002822938745798275,
+      "loss": 0.1044,
+      "step": 55000
+    },
+    {
+      "epoch": 3.5647761577493737,
+      "grad_norm": 0.42234089970588684,
+      "learning_rate": 0.00028122337122915195,
+      "loss": 0.1043,
+      "step": 55500
+    },
+    {
+      "epoch": 3.5968912582696384,
+      "grad_norm": 0.5359342098236084,
+      "learning_rate": 0.0002801528678784765,
+      "loss": 0.1027,
+      "step": 56000
+    },
+    {
+      "epoch": 3.6002312287237457,
+      "eval_loss": 0.10499866306781769,
+      "eval_runtime": 7.3501,
+      "eval_samples_per_second": 68.026,
+      "eval_steps_per_second": 8.571,
+      "step": 56052
+    },
+    {
+      "epoch": 3.629006358789903,
+      "grad_norm": 0.5378216505050659,
+      "learning_rate": 0.000279082364527801,
+      "loss": 0.1037,
+      "step": 56500
+    },
+    {
+      "epoch": 3.6611214593101677,
+      "grad_norm": 0.47160041332244873,
+      "learning_rate": 0.0002780118611771255,
+      "loss": 0.1032,
+      "step": 57000
+    },
+    {
+      "epoch": 3.6932365598304324,
+      "grad_norm": 0.49247318506240845,
+      "learning_rate": 0.00027694135782645,
+      "loss": 0.1005,
+      "step": 57500
+    },
+    {
+      "epoch": 3.7253516603506966,
+      "grad_norm": 0.46599718928337097,
+      "learning_rate": 0.00027587085447577453,
+      "loss": 0.1037,
+      "step": 58000
+    },
+    {
+      "epoch": 3.7574667608709618,
+      "grad_norm": 0.44333142042160034,
+      "learning_rate": 0.00027480249213180036,
+      "loss": 0.0991,
+      "step": 58500
+    },
+    {
+      "epoch": 3.789581861391226,
+      "grad_norm": 0.42183053493499756,
+      "learning_rate": 0.0002737319887811249,
+      "loss": 0.1025,
+      "step": 59000
+    },
+    {
+      "epoch": 3.800244074763954,
+      "eval_loss": 0.10221809148788452,
+      "eval_runtime": 7.3337,
+      "eval_samples_per_second": 68.178,
+      "eval_steps_per_second": 8.59,
+      "step": 59166
+    },
+    {
+      "epoch": 3.8216969619114907,
+      "grad_norm": 0.4511483907699585,
+      "learning_rate": 0.0002726614854304494,
+      "loss": 0.1046,
+      "step": 59500
+    },
+    {
+      "epoch": 3.8538120624317553,
+      "grad_norm": 0.6245924830436707,
+      "learning_rate": 0.0002715909820797739,
+      "loss": 0.0996,
+      "step": 60000
+    },
+    {
+      "epoch": 3.88592716295202,
+      "grad_norm": 0.43624454736709595,
+      "learning_rate": 0.00027052261973579977,
+      "loss": 0.1034,
+      "step": 60500
+    },
+    {
+      "epoch": 3.9180422634722847,
+      "grad_norm": 0.47011294960975647,
+      "learning_rate": 0.0002694521163851243,
+      "loss": 0.1039,
+      "step": 61000
+    },
+    {
+      "epoch": 3.9501573639925494,
+      "grad_norm": 0.4194742441177368,
+      "learning_rate": 0.0002683816130344488,
+      "loss": 0.1048,
+      "step": 61500
+    },
+    {
+      "epoch": 3.982272464512814,
+      "grad_norm": 0.5618862509727478,
+      "learning_rate": 0.0002673111096837733,
+      "loss": 0.102,
+      "step": 62000
+    },
+    {
+      "epoch": 4.000256920804162,
+      "eval_loss": 0.10089205950498581,
+      "eval_runtime": 7.4502,
+      "eval_samples_per_second": 67.113,
+      "eval_steps_per_second": 8.456,
+      "step": 62280
+    },
+    {
+      "epoch": 4.014387565033078,
+      "grad_norm": 0.60516756772995,
+      "learning_rate": 0.0002662406063330978,
+      "loss": 0.0979,
+      "step": 62500
+    },
+    {
+      "epoch": 4.046502665553343,
+      "grad_norm": 0.5307052731513977,
+      "learning_rate": 0.00026517010298242235,
+      "loss": 0.0938,
+      "step": 63000
+    },
+    {
+      "epoch": 4.078617766073608,
+      "grad_norm": 0.513951301574707,
+      "learning_rate": 0.0002641017406384482,
+      "loss": 0.0948,
+      "step": 63500
+    },
+    {
+      "epoch": 4.110732866593873,
+      "grad_norm": 0.4734605848789215,
+      "learning_rate": 0.0002630312372877727,
+      "loss": 0.0956,
+      "step": 64000
+    },
+    {
+      "epoch": 4.142847967114137,
+      "grad_norm": 0.3525328040122986,
+      "learning_rate": 0.00026196073393709723,
+      "loss": 0.0935,
+      "step": 64500
+    },
+    {
+      "epoch": 4.174963067634402,
+      "grad_norm": 0.6330441832542419,
+      "learning_rate": 0.00026089023058642176,
+      "loss": 0.0943,
+      "step": 65000
+    },
+    {
+      "epoch": 4.20026976684437,
+      "eval_loss": 0.09817148745059967,
+      "eval_runtime": 7.3411,
+      "eval_samples_per_second": 68.11,
+      "eval_steps_per_second": 8.582,
+      "step": 65394
+    },
+    {
+      "epoch": 4.207078168154666,
+      "grad_norm": 0.3115638494491577,
+      "learning_rate": 0.0002598197272357463,
+      "loss": 0.095,
+      "step": 65500
+    },
+    {
+      "epoch": 4.239193268674931,
+      "grad_norm": 0.3824947774410248,
+      "learning_rate": 0.0002587492238850708,
+      "loss": 0.0943,
+      "step": 66000
+    },
+    {
+      "epoch": 4.271308369195196,
+      "grad_norm": 0.547127366065979,
+      "learning_rate": 0.00025768086154109664,
+      "loss": 0.0956,
+      "step": 66500
+    },
+    {
+      "epoch": 4.30342346971546,
+      "grad_norm": 0.39464259147644043,
+      "learning_rate": 0.00025661035819042117,
+      "loss": 0.0951,
+      "step": 67000
+    },
+    {
+      "epoch": 4.335538570235725,
+      "grad_norm": 0.465304434299469,
+      "learning_rate": 0.0002555398548397457,
+      "loss": 0.0935,
+      "step": 67500
+    },
+    {
+      "epoch": 4.367653670755989,
+      "grad_norm": 0.5602743625640869,
+      "learning_rate": 0.00025446935148907017,
+      "loss": 0.0972,
+      "step": 68000
+    },
+    {
+      "epoch": 4.399768771276254,
+      "grad_norm": 0.3761026859283447,
+      "learning_rate": 0.00025340098914509605,
+      "loss": 0.0948,
+      "step": 68500
+    },
+    {
+      "epoch": 4.4002826128845784,
+      "eval_loss": 0.09914599359035492,
+      "eval_runtime": 7.3361,
+      "eval_samples_per_second": 68.156,
+      "eval_steps_per_second": 8.588,
+      "step": 68508
+    },
+    {
+      "epoch": 4.4318838717965185,
+      "grad_norm": 0.5205414891242981,
+      "learning_rate": 0.0002523304857944206,
+      "loss": 0.0946,
+      "step": 69000
+    },
+    {
+      "epoch": 4.463998972316784,
+      "grad_norm": 0.5030530095100403,
+      "learning_rate": 0.00025125998244374505,
+      "loss": 0.0961,
+      "step": 69500
+    },
+    {
+      "epoch": 4.496114072837048,
+      "grad_norm": 0.5840058922767639,
+      "learning_rate": 0.0002501894790930696,
+      "loss": 0.0944,
+      "step": 70000
+    },
+    {
+      "epoch": 4.528229173357312,
+      "grad_norm": 0.5052670836448669,
+      "learning_rate": 0.00024912111674909546,
+      "loss": 0.0956,
+      "step": 70500
+    },
+    {
+      "epoch": 4.560344273877577,
+      "grad_norm": 0.4955575466156006,
+      "learning_rate": 0.00024805061339841993,
+      "loss": 0.0949,
+      "step": 71000
+    },
+    {
+      "epoch": 4.592459374397842,
+      "grad_norm": 0.43502339720726013,
+      "learning_rate": 0.00024698011004774446,
+      "loss": 0.0939,
+      "step": 71500
+    },
+    {
+      "epoch": 4.600295458924786,
+      "eval_loss": 0.09654521197080612,
+      "eval_runtime": 7.343,
+      "eval_samples_per_second": 68.092,
+      "eval_steps_per_second": 8.58,
+      "step": 71622
+    },
+    {
+      "epoch": 4.624574474918107,
+      "grad_norm": 0.3835175335407257,
+      "learning_rate": 0.000245909606697069,
+      "loss": 0.0968,
+      "step": 72000
+    },
+    {
+      "epoch": 4.656689575438371,
+      "grad_norm": 0.46231910586357117,
+      "learning_rate": 0.00024483910334639346,
+      "loss": 0.0943,
+      "step": 72500
+    },
+    {
+      "epoch": 4.688804675958636,
+      "grad_norm": 0.4383336901664734,
+      "learning_rate": 0.00024377074100241934,
+      "loss": 0.0947,
+      "step": 73000
+    },
+    {
+      "epoch": 4.7209197764789,
+      "grad_norm": 0.5691344141960144,
+      "learning_rate": 0.00024270023765174387,
+      "loss": 0.0934,
+      "step": 73500
+    },
+    {
+      "epoch": 4.753034876999165,
+      "grad_norm": 0.4115155041217804,
+      "learning_rate": 0.00024162973430106837,
+      "loss": 0.0935,
+      "step": 74000
+    },
+    {
+      "epoch": 4.7851499775194295,
+      "grad_norm": 0.6333282589912415,
+      "learning_rate": 0.00024055923095039287,
+      "loss": 0.0938,
+      "step": 74500
+    },
+    {
+      "epoch": 4.800308304964995,
+      "eval_loss": 0.09797964990139008,
+      "eval_runtime": 7.348,
+      "eval_samples_per_second": 68.046,
+      "eval_steps_per_second": 8.574,
+      "step": 74736
+    },
+    {
+      "epoch": 4.817265078039695,
+      "grad_norm": 0.6069188117980957,
+      "learning_rate": 0.0002394887275997174,
+      "loss": 0.0938,
+      "step": 75000
+    },
+    {
+      "epoch": 4.849380178559959,
+      "grad_norm": 0.48266521096229553,
+      "learning_rate": 0.0002384182242490419,
+      "loss": 0.092,
+      "step": 75500
+    },
+    {
+      "epoch": 4.881495279080223,
+      "grad_norm": 0.5051959156990051,
+      "learning_rate": 0.00023734772089836642,
+      "loss": 0.0938,
+      "step": 76000
+    },
+    {
+      "epoch": 4.913610379600488,
+      "grad_norm": 0.36517608165740967,
+      "learning_rate": 0.00023627721754769092,
+      "loss": 0.0963,
+      "step": 76500
+    },
+    {
+      "epoch": 4.945725480120752,
+      "grad_norm": 0.5914227366447449,
+      "learning_rate": 0.00023520671419701542,
+      "loss": 0.0941,
+      "step": 77000
+    },
+    {
+      "epoch": 4.9778405806410175,
+      "grad_norm": 0.44252389669418335,
+      "learning_rate": 0.00023414049285974263,
+      "loss": 0.093,
+      "step": 77500
+    }
+  ],
+  "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": 1.8249904407200137e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-77845/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55428e8dd30daaff792c433246961305cfd20b6b3d93eb34b1e2af5f631a34db
+size 5496