Training in progress, epoch 9, checkpoint

checkpoint-32391/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-32391/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-base",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-32391/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2947462f551402f6c524aff34e2903fc37de1ccc53c6dc4318dd885af9a5cc91
+size 541459256

checkpoint-32391/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d39f27602f4fbfc5ab748e49745072893b30e6a5c974d9be7d622b0574051f50
+size 33662074

checkpoint-32391/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ccc10f724be38240d3f94f0d9d254a98b2d8018ee89e1cf995f323af372041a
+size 15024

checkpoint-32391/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de9a0fe74f9515a7071cf9efedad04d23098ea6521119fe7ae755ea0dceee802
+size 15024

checkpoint-32391/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33bf17125afbe7cfbdade29669a7dc68b6e5c21c43082e3d35ade740b692db5b
+size 15024

checkpoint-32391/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2e59d43374dfc728b281ca66655d1f6811731c5ff935e4e976d891a337b6d9c
+size 15024

checkpoint-32391/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87c292156116e9deaf3157f793714b76d77d0bbae6d6578d153076864d4be18b
+size 1064

checkpoint-32391/trainer_state.json

@@ -0,0 +1,833 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.0,
+  "eval_steps": 720,
+  "global_step": 32391,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13892747985551543,
+      "grad_norm": 0.5752785205841064,
+      "learning_rate": 0.00039538760766879693,
+      "loss": 0.2947,
+      "step": 500
+    },
+    {
+      "epoch": 0.2000555709919422,
+      "eval_loss": 0.19290830194950104,
+      "eval_runtime": 6.2591,
+      "eval_samples_per_second": 79.884,
+      "eval_steps_per_second": 10.065,
+      "step": 720
+    },
+    {
+      "epoch": 0.27785495971103086,
+      "grad_norm": 0.4608103632926941,
+      "learning_rate": 0.00039075669167361305,
+      "loss": 0.1972,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4001111419838844,
+      "eval_loss": 0.17835241556167603,
+      "eval_runtime": 6.2534,
+      "eval_samples_per_second": 79.957,
+      "eval_steps_per_second": 10.075,
+      "step": 1440
+    },
+    {
+      "epoch": 0.41678243956654626,
+      "grad_norm": 0.44341567158699036,
+      "learning_rate": 0.0003861257756784292,
+      "loss": 0.1817,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5557099194220617,
+      "grad_norm": 0.3840184509754181,
+      "learning_rate": 0.00038149485968324534,
+      "loss": 0.1679,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6001667129758266,
+      "eval_loss": 0.16081829369068146,
+      "eval_runtime": 6.259,
+      "eval_samples_per_second": 79.885,
+      "eval_steps_per_second": 10.065,
+      "step": 2160
+    },
+    {
+      "epoch": 0.6946373992775771,
+      "grad_norm": 0.4211641848087311,
+      "learning_rate": 0.0003768639436880615,
+      "loss": 0.1584,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8002222839677688,
+      "eval_loss": 0.15788592398166656,
+      "eval_runtime": 6.2616,
+      "eval_samples_per_second": 79.852,
+      "eval_steps_per_second": 10.061,
+      "step": 2880
+    },
+    {
+      "epoch": 0.8335648791330925,
+      "grad_norm": 0.3697059750556946,
+      "learning_rate": 0.0003722515513568584,
+      "loss": 0.1501,
+      "step": 3000
+    },
+    {
+      "epoch": 0.972492358988608,
+      "grad_norm": 0.420885294675827,
+      "learning_rate": 0.00036762063536167455,
+      "loss": 0.1478,
+      "step": 3500
+    },
+    {
+      "epoch": 1.000277854959711,
+      "eval_loss": 0.14726293087005615,
+      "eval_runtime": 6.3796,
+      "eval_samples_per_second": 78.375,
+      "eval_steps_per_second": 9.875,
+      "step": 3600
+    },
+    {
+      "epoch": 1.1114198388441234,
+      "grad_norm": 0.3687162697315216,
+      "learning_rate": 0.0003629897193664907,
+      "loss": 0.1315,
+      "step": 4000
+    },
+    {
+      "epoch": 1.2003334259516532,
+      "eval_loss": 0.14390353858470917,
+      "eval_runtime": 6.2741,
+      "eval_samples_per_second": 79.693,
+      "eval_steps_per_second": 10.041,
+      "step": 4320
+    },
+    {
+      "epoch": 1.2503473186996388,
+      "grad_norm": 0.4367423951625824,
+      "learning_rate": 0.0003583588033713069,
+      "loss": 0.1309,
+      "step": 4500
+    },
+    {
+      "epoch": 1.3892747985551543,
+      "grad_norm": 0.40452277660369873,
+      "learning_rate": 0.000353727887376123,
+      "loss": 0.128,
+      "step": 5000
+    },
+    {
+      "epoch": 1.4003889969435954,
+      "eval_loss": 0.1357639729976654,
+      "eval_runtime": 6.2739,
+      "eval_samples_per_second": 79.695,
+      "eval_steps_per_second": 10.042,
+      "step": 5040
+    },
+    {
+      "epoch": 1.5282022784106695,
+      "grad_norm": 0.6852627396583557,
+      "learning_rate": 0.00034909697138093914,
+      "loss": 0.126,
+      "step": 5500
+    },
+    {
+      "epoch": 1.6004445679355377,
+      "eval_loss": 0.13292476534843445,
+      "eval_runtime": 6.2659,
+      "eval_samples_per_second": 79.797,
+      "eval_steps_per_second": 10.054,
+      "step": 5760
+    },
+    {
+      "epoch": 1.667129758266185,
+      "grad_norm": 0.30270153284072876,
+      "learning_rate": 0.0003444660553857553,
+      "loss": 0.1255,
+      "step": 6000
+    },
+    {
+      "epoch": 1.8005001389274797,
+      "eval_loss": 0.13217522203922272,
+      "eval_runtime": 6.2758,
+      "eval_samples_per_second": 79.671,
+      "eval_steps_per_second": 10.038,
+      "step": 6480
+    },
+    {
+      "epoch": 1.8060572381217006,
+      "grad_norm": 0.394003301858902,
+      "learning_rate": 0.0003398351393905715,
+      "loss": 0.1214,
+      "step": 6500
+    },
+    {
+      "epoch": 1.9449847179772157,
+      "grad_norm": 0.48431047797203064,
+      "learning_rate": 0.00033520422339538766,
+      "loss": 0.1199,
+      "step": 7000
+    },
+    {
+      "epoch": 2.000555709919422,
+      "eval_loss": 0.1269044131040573,
+      "eval_runtime": 6.422,
+      "eval_samples_per_second": 77.857,
+      "eval_steps_per_second": 9.81,
+      "step": 7200
+    },
+    {
+      "epoch": 2.0839121978327313,
+      "grad_norm": 0.35144302248954773,
+      "learning_rate": 0.0003305733074002038,
+      "loss": 0.108,
+      "step": 7500
+    },
+    {
+      "epoch": 2.2006112809113643,
+      "eval_loss": 0.12548324465751648,
+      "eval_runtime": 6.2942,
+      "eval_samples_per_second": 79.438,
+      "eval_steps_per_second": 10.009,
+      "step": 7920
+    },
+    {
+      "epoch": 2.222839677688247,
+      "grad_norm": 0.5099118947982788,
+      "learning_rate": 0.00032595165323701027,
+      "loss": 0.1056,
+      "step": 8000
+    },
+    {
+      "epoch": 2.361767157543762,
+      "grad_norm": 0.5797615647315979,
+      "learning_rate": 0.00032132073724182645,
+      "loss": 0.1047,
+      "step": 8500
+    },
+    {
+      "epoch": 2.4006668519033063,
+      "eval_loss": 0.12244148552417755,
+      "eval_runtime": 6.2902,
+      "eval_samples_per_second": 79.489,
+      "eval_steps_per_second": 10.016,
+      "step": 8640
+    },
+    {
+      "epoch": 2.5006946373992776,
+      "grad_norm": 0.40433964133262634,
+      "learning_rate": 0.0003166898212466426,
+      "loss": 0.1038,
+      "step": 9000
+    },
+    {
+      "epoch": 2.600722422895249,
+      "eval_loss": 0.12048304080963135,
+      "eval_runtime": 6.289,
+      "eval_samples_per_second": 79.503,
+      "eval_steps_per_second": 10.017,
+      "step": 9360
+    },
+    {
+      "epoch": 2.639622117254793,
+      "grad_norm": 0.7869251370429993,
+      "learning_rate": 0.00031205890525145874,
+      "loss": 0.1023,
+      "step": 9500
+    },
+    {
+      "epoch": 2.7785495971103087,
+      "grad_norm": 0.34468919038772583,
+      "learning_rate": 0.0003074279892562749,
+      "loss": 0.1043,
+      "step": 10000
+    },
+    {
+      "epoch": 2.800777993887191,
+      "eval_loss": 0.1157899871468544,
+      "eval_runtime": 6.2874,
+      "eval_samples_per_second": 79.524,
+      "eval_steps_per_second": 10.02,
+      "step": 10080
+    },
+    {
+      "epoch": 2.917477076965824,
+      "grad_norm": 0.5141274929046631,
+      "learning_rate": 0.00030279707326109104,
+      "loss": 0.1042,
+      "step": 10500
+    },
+    {
+      "epoch": 3.000833564879133,
+      "eval_loss": 0.11479081958532333,
+      "eval_runtime": 6.4111,
+      "eval_samples_per_second": 77.99,
+      "eval_steps_per_second": 9.827,
+      "step": 10800
+    },
+    {
+      "epoch": 3.0564045568213394,
+      "grad_norm": 0.4209577143192291,
+      "learning_rate": 0.0002981754190978976,
+      "loss": 0.0957,
+      "step": 11000
+    },
+    {
+      "epoch": 3.1953320366768545,
+      "grad_norm": 0.4159316122531891,
+      "learning_rate": 0.00029355376493470407,
+      "loss": 0.0884,
+      "step": 11500
+    },
+    {
+      "epoch": 3.2008891358710754,
+      "eval_loss": 0.11302317678928375,
+      "eval_runtime": 6.2864,
+      "eval_samples_per_second": 79.537,
+      "eval_steps_per_second": 10.022,
+      "step": 11520
+    },
+    {
+      "epoch": 3.33425951653237,
+      "grad_norm": 0.613624632358551,
+      "learning_rate": 0.00028892284893952024,
+      "loss": 0.0903,
+      "step": 12000
+    },
+    {
+      "epoch": 3.4009447068630174,
+      "eval_loss": 0.11040342599153519,
+      "eval_runtime": 6.2939,
+      "eval_samples_per_second": 79.442,
+      "eval_steps_per_second": 10.01,
+      "step": 12240
+    },
+    {
+      "epoch": 3.4731869963878856,
+      "grad_norm": 0.7177799940109253,
+      "learning_rate": 0.0002842919329443364,
+      "loss": 0.0889,
+      "step": 12500
+    },
+    {
+      "epoch": 3.6010002778549595,
+      "eval_loss": 0.11320961266756058,
+      "eval_runtime": 6.2914,
+      "eval_samples_per_second": 79.473,
+      "eval_steps_per_second": 10.014,
+      "step": 12960
+    },
+    {
+      "epoch": 3.612114476243401,
+      "grad_norm": 0.5415129065513611,
+      "learning_rate": 0.0002796610169491526,
+      "loss": 0.0889,
+      "step": 13000
+    },
+    {
+      "epoch": 3.7510419560989163,
+      "grad_norm": 0.6058521866798401,
+      "learning_rate": 0.0002750301009539687,
+      "loss": 0.0885,
+      "step": 13500
+    },
+    {
+      "epoch": 3.801055848846902,
+      "eval_loss": 0.11218452453613281,
+      "eval_runtime": 6.2932,
+      "eval_samples_per_second": 79.45,
+      "eval_steps_per_second": 10.011,
+      "step": 13680
+    },
+    {
+      "epoch": 3.889969435954432,
+      "grad_norm": 0.6304852366447449,
+      "learning_rate": 0.00027039918495878483,
+      "loss": 0.0882,
+      "step": 14000
+    },
+    {
+      "epoch": 4.001111419838844,
+      "eval_loss": 0.1118089109659195,
+      "eval_runtime": 6.4064,
+      "eval_samples_per_second": 78.047,
+      "eval_steps_per_second": 9.834,
+      "step": 14400
+    },
+    {
+      "epoch": 4.0288969158099475,
+      "grad_norm": 0.46223384141921997,
+      "learning_rate": 0.000265768268963601,
+      "loss": 0.0858,
+      "step": 14500
+    },
+    {
+      "epoch": 4.167824395665463,
+      "grad_norm": 0.4947393238544464,
+      "learning_rate": 0.0002611373529684172,
+      "loss": 0.0753,
+      "step": 15000
+    },
+    {
+      "epoch": 4.201166990830786,
+      "eval_loss": 0.11774840950965881,
+      "eval_runtime": 6.2977,
+      "eval_samples_per_second": 79.394,
+      "eval_steps_per_second": 10.004,
+      "step": 15120
+    },
+    {
+      "epoch": 4.306751875520978,
+      "grad_norm": 0.40220069885253906,
+      "learning_rate": 0.00025650643697323335,
+      "loss": 0.0764,
+      "step": 15500
+    },
+    {
+      "epoch": 4.4012225618227285,
+      "eval_loss": 0.11307726055383682,
+      "eval_runtime": 6.301,
+      "eval_samples_per_second": 79.353,
+      "eval_steps_per_second": 9.998,
+      "step": 15840
+    },
+    {
+      "epoch": 4.445679355376494,
+      "grad_norm": 0.38409939408302307,
+      "learning_rate": 0.00025188478281003984,
+      "loss": 0.0779,
+      "step": 16000
+    },
+    {
+      "epoch": 4.584606835232009,
+      "grad_norm": 0.4317833185195923,
+      "learning_rate": 0.00024725386681485596,
+      "loss": 0.0755,
+      "step": 16500
+    },
+    {
+      "epoch": 4.601278132814671,
+      "eval_loss": 0.11036152392625809,
+      "eval_runtime": 6.3093,
+      "eval_samples_per_second": 79.248,
+      "eval_steps_per_second": 9.985,
+      "step": 16560
+    },
+    {
+      "epoch": 4.723534315087524,
+      "grad_norm": 0.5405837297439575,
+      "learning_rate": 0.00024262295081967214,
+      "loss": 0.077,
+      "step": 17000
+    },
+    {
+      "epoch": 4.801333703806613,
+      "eval_loss": 0.10895710438489914,
+      "eval_runtime": 6.3035,
+      "eval_samples_per_second": 79.321,
+      "eval_steps_per_second": 9.994,
+      "step": 17280
+    },
+    {
+      "epoch": 4.86246179494304,
+      "grad_norm": 0.3864780366420746,
+      "learning_rate": 0.0002379920348244883,
+      "loss": 0.0779,
+      "step": 17500
+    },
+    {
+      "epoch": 5.001389274798555,
+      "grad_norm": 0.3517213761806488,
+      "learning_rate": 0.0002333703806612948,
+      "loss": 0.0745,
+      "step": 18000
+    },
+    {
+      "epoch": 5.001389274798555,
+      "eval_loss": 0.10910706967115402,
+      "eval_runtime": 6.5025,
+      "eval_samples_per_second": 76.894,
+      "eval_steps_per_second": 9.689,
+      "step": 18000
+    },
+    {
+      "epoch": 5.14031675465407,
+      "grad_norm": 0.3627057671546936,
+      "learning_rate": 0.00022873946466611095,
+      "loss": 0.0641,
+      "step": 18500
+    },
+    {
+      "epoch": 5.201444845790498,
+      "eval_loss": 0.11183220893144608,
+      "eval_runtime": 6.3062,
+      "eval_samples_per_second": 79.287,
+      "eval_steps_per_second": 9.99,
+      "step": 18720
+    },
+    {
+      "epoch": 5.279244234509586,
+      "grad_norm": 0.4831227958202362,
+      "learning_rate": 0.00022410854867092712,
+      "loss": 0.0648,
+      "step": 19000
+    },
+    {
+      "epoch": 5.401500416782439,
+      "eval_loss": 0.10868020355701447,
+      "eval_runtime": 6.3155,
+      "eval_samples_per_second": 79.17,
+      "eval_steps_per_second": 9.975,
+      "step": 19440
+    },
+    {
+      "epoch": 5.418171714365101,
+      "grad_norm": 0.43644019961357117,
+      "learning_rate": 0.0002194776326757433,
+      "loss": 0.066,
+      "step": 19500
+    },
+    {
+      "epoch": 5.5570991942206165,
+      "grad_norm": 0.4624837338924408,
+      "learning_rate": 0.00021484671668055944,
+      "loss": 0.0661,
+      "step": 20000
+    },
+    {
+      "epoch": 5.601555987774382,
+      "eval_loss": 0.10925421118736267,
+      "eval_runtime": 6.3162,
+      "eval_samples_per_second": 79.161,
+      "eval_steps_per_second": 9.974,
+      "step": 20160
+    },
+    {
+      "epoch": 5.6960266740761325,
+      "grad_norm": 0.5039137601852417,
+      "learning_rate": 0.00021022506251736593,
+      "loss": 0.0666,
+      "step": 20500
+    },
+    {
+      "epoch": 5.801611558766324,
+      "eval_loss": 0.10597137361764908,
+      "eval_runtime": 6.3038,
+      "eval_samples_per_second": 79.317,
+      "eval_steps_per_second": 9.994,
+      "step": 20880
+    },
+    {
+      "epoch": 5.834954153931648,
+      "grad_norm": 0.4911608397960663,
+      "learning_rate": 0.0002055941465221821,
+      "loss": 0.0671,
+      "step": 21000
+    },
+    {
+      "epoch": 5.973881633787163,
+      "grad_norm": 0.648589015007019,
+      "learning_rate": 0.00020096323052699825,
+      "loss": 0.065,
+      "step": 21500
+    },
+    {
+      "epoch": 6.001667129758266,
+      "eval_loss": 0.10192042589187622,
+      "eval_runtime": 6.5803,
+      "eval_samples_per_second": 75.985,
+      "eval_steps_per_second": 9.574,
+      "step": 21600
+    },
+    {
+      "epoch": 6.112809113642679,
+      "grad_norm": 0.4207409918308258,
+      "learning_rate": 0.0001963323145318144,
+      "loss": 0.0565,
+      "step": 22000
+    },
+    {
+      "epoch": 6.201722700750208,
+      "eval_loss": 0.11030665040016174,
+      "eval_runtime": 6.3184,
+      "eval_samples_per_second": 79.133,
+      "eval_steps_per_second": 9.971,
+      "step": 22320
+    },
+    {
+      "epoch": 6.251736593498194,
+      "grad_norm": 0.5802621245384216,
+      "learning_rate": 0.00019170139853663055,
+      "loss": 0.0554,
+      "step": 22500
+    },
+    {
+      "epoch": 6.390664073353709,
+      "grad_norm": 0.56964111328125,
+      "learning_rate": 0.0001870704825414467,
+      "loss": 0.0575,
+      "step": 23000
+    },
+    {
+      "epoch": 6.401778271742151,
+      "eval_loss": 0.10719279199838638,
+      "eval_runtime": 6.3115,
+      "eval_samples_per_second": 79.22,
+      "eval_steps_per_second": 9.982,
+      "step": 23040
+    },
+    {
+      "epoch": 6.529591553209225,
+      "grad_norm": 0.5339217185974121,
+      "learning_rate": 0.00018243956654626287,
+      "loss": 0.057,
+      "step": 23500
+    },
+    {
+      "epoch": 6.601833842734093,
+      "eval_loss": 0.110511913895607,
+      "eval_runtime": 6.3148,
+      "eval_samples_per_second": 79.179,
+      "eval_steps_per_second": 9.977,
+      "step": 23760
+    },
+    {
+      "epoch": 6.66851903306474,
+      "grad_norm": 0.6509028673171997,
+      "learning_rate": 0.000177808650551079,
+      "loss": 0.057,
+      "step": 24000
+    },
+    {
+      "epoch": 6.801889413726035,
+      "eval_loss": 0.11028529703617096,
+      "eval_runtime": 6.2947,
+      "eval_samples_per_second": 79.432,
+      "eval_steps_per_second": 10.008,
+      "step": 24480
+    },
+    {
+      "epoch": 6.807446512920255,
+      "grad_norm": 0.4752148389816284,
+      "learning_rate": 0.00017318699638788553,
+      "loss": 0.0564,
+      "step": 24500
+    },
+    {
+      "epoch": 6.946373992775771,
+      "grad_norm": 0.38218364119529724,
+      "learning_rate": 0.00016856534222469205,
+      "loss": 0.0566,
+      "step": 25000
+    },
+    {
+      "epoch": 7.001944984717977,
+      "eval_loss": 0.1053631454706192,
+      "eval_runtime": 6.5447,
+      "eval_samples_per_second": 76.398,
+      "eval_steps_per_second": 9.626,
+      "step": 25200
+    },
+    {
+      "epoch": 7.085301472631286,
+      "grad_norm": 0.3690716028213501,
+      "learning_rate": 0.0001639344262295082,
+      "loss": 0.049,
+      "step": 25500
+    },
+    {
+      "epoch": 7.20200055570992,
+      "eval_loss": 0.11346188932657242,
+      "eval_runtime": 6.3148,
+      "eval_samples_per_second": 79.179,
+      "eval_steps_per_second": 9.977,
+      "step": 25920
+    },
+    {
+      "epoch": 7.2242289524868015,
+      "grad_norm": 0.6985990405082703,
+      "learning_rate": 0.00015930351023432434,
+      "loss": 0.0471,
+      "step": 26000
+    },
+    {
+      "epoch": 7.3631564323423175,
+      "grad_norm": 0.4522312581539154,
+      "learning_rate": 0.00015467259423914052,
+      "loss": 0.0471,
+      "step": 26500
+    },
+    {
+      "epoch": 7.402056126701861,
+      "eval_loss": 0.11016041040420532,
+      "eval_runtime": 6.3157,
+      "eval_samples_per_second": 79.168,
+      "eval_steps_per_second": 9.975,
+      "step": 26640
+    },
+    {
+      "epoch": 7.502083912197833,
+      "grad_norm": 0.3933652341365814,
+      "learning_rate": 0.00015004167824395664,
+      "loss": 0.0481,
+      "step": 27000
+    },
+    {
+      "epoch": 7.602111697693804,
+      "eval_loss": 0.11197081953287125,
+      "eval_runtime": 6.3099,
+      "eval_samples_per_second": 79.24,
+      "eval_steps_per_second": 9.984,
+      "step": 27360
+    },
+    {
+      "epoch": 7.641011392053348,
+      "grad_norm": 0.42119812965393066,
+      "learning_rate": 0.00014542002408076318,
+      "loss": 0.0484,
+      "step": 27500
+    },
+    {
+      "epoch": 7.779938871908864,
+      "grad_norm": 0.44935351610183716,
+      "learning_rate": 0.00014078910808557933,
+      "loss": 0.0481,
+      "step": 28000
+    },
+    {
+      "epoch": 7.802167268685746,
+      "eval_loss": 0.10714428871870041,
+      "eval_runtime": 6.3046,
+      "eval_samples_per_second": 79.307,
+      "eval_steps_per_second": 9.993,
+      "step": 28080
+    },
+    {
+      "epoch": 7.918866351764379,
+      "grad_norm": 0.31898295879364014,
+      "learning_rate": 0.00013615819209039548,
+      "loss": 0.0486,
+      "step": 28500
+    },
+    {
+      "epoch": 8.002222839677689,
+      "eval_loss": 0.10903233289718628,
+      "eval_runtime": 6.4188,
+      "eval_samples_per_second": 77.896,
+      "eval_steps_per_second": 9.815,
+      "step": 28800
+    },
+    {
+      "epoch": 8.057793831619895,
+      "grad_norm": 0.4274863004684448,
+      "learning_rate": 0.00013152727609521165,
+      "loss": 0.0443,
+      "step": 29000
+    },
+    {
+      "epoch": 8.19672131147541,
+      "grad_norm": 0.4764171242713928,
+      "learning_rate": 0.0001268963601000278,
+      "loss": 0.0404,
+      "step": 29500
+    },
+    {
+      "epoch": 8.20227841066963,
+      "eval_loss": 0.1156005710363388,
+      "eval_runtime": 6.3188,
+      "eval_samples_per_second": 79.129,
+      "eval_steps_per_second": 9.97,
+      "step": 29520
+    },
+    {
+      "epoch": 8.335648791330925,
+      "grad_norm": 0.7897500395774841,
+      "learning_rate": 0.00012226544410484395,
+      "loss": 0.0396,
+      "step": 30000
+    },
+    {
+      "epoch": 8.402333981661572,
+      "eval_loss": 0.11201395094394684,
+      "eval_runtime": 6.3256,
+      "eval_samples_per_second": 79.044,
+      "eval_steps_per_second": 9.96,
+      "step": 30240
+    },
+    {
+      "epoch": 8.474576271186441,
+      "grad_norm": 0.40140944719314575,
+      "learning_rate": 0.0001176345281096601,
+      "loss": 0.0406,
+      "step": 30500
+    },
+    {
+      "epoch": 8.602389552653515,
+      "eval_loss": 0.11844490468502045,
+      "eval_runtime": 6.3191,
+      "eval_samples_per_second": 79.125,
+      "eval_steps_per_second": 9.97,
+      "step": 30960
+    },
+    {
+      "epoch": 8.613503751041955,
+      "grad_norm": 0.4029806852340698,
+      "learning_rate": 0.00011301287394646662,
+      "loss": 0.0415,
+      "step": 31000
+    },
+    {
+      "epoch": 8.752431230897471,
+      "grad_norm": 0.41953355073928833,
+      "learning_rate": 0.00010839121978327314,
+      "loss": 0.0413,
+      "step": 31500
+    },
+    {
+      "epoch": 8.802445123645457,
+      "eval_loss": 0.11227717995643616,
+      "eval_runtime": 6.3242,
+      "eval_samples_per_second": 79.061,
+      "eval_steps_per_second": 9.962,
+      "step": 31680
+    },
+    {
+      "epoch": 8.891358710752987,
+      "grad_norm": 0.6146722435951233,
+      "learning_rate": 0.0001037603037880893,
+      "loss": 0.0407,
+      "step": 32000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 43188,
+  "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": 6.055901979589214e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-32391/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfac93b9b3b40952529bd84fbff166d6257cf3d6fa4cc937269a037e37d853d5
+size 5496