Training in progress, epoch 4, checkpoint

checkpoint-62276/README.md

@@ -0,0 +1,207 @@
+---
+base_model: deepseek-ai/deepseek-coder-6.7b-base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:deepseek-ai/deepseek-coder-6.7b-base
+- lora
+- transformers
+---
+
+# 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 0.17.1

checkpoint-62276/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-base",
+  "bias": "none",
+  "corda_config": null,
+  "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",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-62276/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1069f6232f6488642502b63df321b1b25bf2d88bfe24a18401162e7510154b4d
+size 541442872

checkpoint-62276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e762d7e044f3dc74d63832bbd7008ee4b59d83cbf7460a86355c4d8c803942f
+size 33664331

checkpoint-62276/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19ecfcbeb9610ffdcca3d35a038573fc77e5fca49c3dfc8c4007405638e96ced
+size 15429

checkpoint-62276/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfc02a781f72c92b74e8384a95f8b37a74ee755649a48e30062662c6ec57462c
+size 15429

checkpoint-62276/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb42f80696129157d69f9117ae27fbb04823e8a74e3825a8c5a707d59c462ea
+size 15429

checkpoint-62276/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da79627e0e20c7139461cf18ab5e62bda35257654c2bc454d97d9cac93242d88
+size 15429

checkpoint-62276/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fca4409638836937146a9edcea919032f54845a0fc0328539db89701081f3d79
+size 1383

checkpoint-62276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c15dd71f6a7978274467967c4f73eb67fe3b94902b2b582c419f789faeda0444
+size 1465

checkpoint-62276/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-62276/tokenizer_config.json

@@ -0,0 +1,194 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

checkpoint-62276/trainer_state.json

@@ -0,0 +1,1054 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 3114,
+  "global_step": 62276,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03211510052026463,
+      "grad_norm": 0.7832834720611572,
+      "learning_rate": 0.0003989316376560259,
+      "loss": 0.4046,
+      "step": 500
+    },
+    {
+      "epoch": 0.06423020104052926,
+      "grad_norm": 0.5729943513870239,
+      "learning_rate": 0.0003978611343053504,
+      "loss": 0.3331,
+      "step": 1000
+    },
+    {
+      "epoch": 0.09634530156079389,
+      "grad_norm": 0.7377817034721375,
+      "learning_rate": 0.0003967906309546749,
+      "loss": 0.3043,
+      "step": 1500
+    },
+    {
+      "epoch": 0.12846040208105852,
+      "grad_norm": 0.5075581669807434,
+      "learning_rate": 0.00039572012760399943,
+      "loss": 0.2904,
+      "step": 2000
+    },
+    {
+      "epoch": 0.16057550260132314,
+      "grad_norm": 0.5351293087005615,
+      "learning_rate": 0.0003946496242533239,
+      "loss": 0.2773,
+      "step": 2500
+    },
+    {
+      "epoch": 0.19269060312158778,
+      "grad_norm": 0.48171064257621765,
+      "learning_rate": 0.00039357912090264843,
+      "loss": 0.2704,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2000128460402081,
+      "eval_loss": 0.26089850068092346,
+      "eval_runtime": 23.5351,
+      "eval_samples_per_second": 21.245,
+      "eval_steps_per_second": 2.677,
+      "step": 3114
+    },
+    {
+      "epoch": 0.2248057036418524,
+      "grad_norm": 0.5043824911117554,
+      "learning_rate": 0.00039250861755197295,
+      "loss": 0.2665,
+      "step": 3500
+    },
+    {
+      "epoch": 0.25692080416211704,
+      "grad_norm": 0.43614575266838074,
+      "learning_rate": 0.0003914381142012975,
+      "loss": 0.258,
+      "step": 4000
+    },
+    {
+      "epoch": 0.28903590468238166,
+      "grad_norm": 0.48906567692756653,
+      "learning_rate": 0.00039036761085062195,
+      "loss": 0.2513,
+      "step": 4500
+    },
+    {
+      "epoch": 0.3211510052026463,
+      "grad_norm": 0.3915150761604309,
+      "learning_rate": 0.0003892971074999465,
+      "loss": 0.2436,
+      "step": 5000
+    },
+    {
+      "epoch": 0.3532661057229109,
+      "grad_norm": 0.5985161066055298,
+      "learning_rate": 0.000388226604149271,
+      "loss": 0.244,
+      "step": 5500
+    },
+    {
+      "epoch": 0.38538120624317557,
+      "grad_norm": 0.4993918538093567,
+      "learning_rate": 0.0003871561007985955,
+      "loss": 0.2366,
+      "step": 6000
+    },
+    {
+      "epoch": 0.4000256920804162,
+      "eval_loss": 0.23004132509231567,
+      "eval_runtime": 23.4824,
+      "eval_samples_per_second": 21.293,
+      "eval_steps_per_second": 2.683,
+      "step": 6228
+    },
+    {
+      "epoch": 0.4174963067634402,
+      "grad_norm": 0.6266722679138184,
+      "learning_rate": 0.00038608559744792,
+      "loss": 0.2373,
+      "step": 6500
+    },
+    {
+      "epoch": 0.4496114072837048,
+      "grad_norm": 0.6462910771369934,
+      "learning_rate": 0.00038501509409724454,
+      "loss": 0.2313,
+      "step": 7000
+    },
+    {
+      "epoch": 0.4817265078039694,
+      "grad_norm": 0.7539305090904236,
+      "learning_rate": 0.00038394459074656906,
+      "loss": 0.2267,
+      "step": 7500
+    },
+    {
+      "epoch": 0.5138416083242341,
+      "grad_norm": 0.6411474943161011,
+      "learning_rate": 0.0003828740873958936,
+      "loss": 0.224,
+      "step": 8000
+    },
+    {
+      "epoch": 0.5459567088444987,
+      "grad_norm": 1.0448476076126099,
+      "learning_rate": 0.0003818035840452181,
+      "loss": 0.2261,
+      "step": 8500
+    },
+    {
+      "epoch": 0.5780718093647633,
+      "grad_norm": 0.4665364921092987,
+      "learning_rate": 0.0003807330806945426,
+      "loss": 0.2231,
+      "step": 9000
+    },
+    {
+      "epoch": 0.6000385381206244,
+      "eval_loss": 0.21744033694267273,
+      "eval_runtime": 23.4975,
+      "eval_samples_per_second": 21.279,
+      "eval_steps_per_second": 2.681,
+      "step": 9342
+    },
+    {
+      "epoch": 0.610186909885028,
+      "grad_norm": 0.4691120982170105,
+      "learning_rate": 0.0003796625773438671,
+      "loss": 0.2208,
+      "step": 9500
+    },
+    {
+      "epoch": 0.6423020104052926,
+      "grad_norm": 0.5210365653038025,
+      "learning_rate": 0.00037859207399319164,
+      "loss": 0.2164,
+      "step": 10000
+    },
+    {
+      "epoch": 0.6744171109255572,
+      "grad_norm": 0.4708593487739563,
+      "learning_rate": 0.0003775215706425161,
+      "loss": 0.2208,
+      "step": 10500
+    },
+    {
+      "epoch": 0.7065322114458218,
+      "grad_norm": 0.6149038076400757,
+      "learning_rate": 0.00037645106729184064,
+      "loss": 0.214,
+      "step": 11000
+    },
+    {
+      "epoch": 0.7386473119660865,
+      "grad_norm": 0.5197306275367737,
+      "learning_rate": 0.00037538056394116517,
+      "loss": 0.2179,
+      "step": 11500
+    },
+    {
+      "epoch": 0.7707624124863511,
+      "grad_norm": 0.7740463018417358,
+      "learning_rate": 0.0003743100605904897,
+      "loss": 0.2116,
+      "step": 12000
+    },
+    {
+      "epoch": 0.8000513841608324,
+      "eval_loss": 0.20090056955814362,
+      "eval_runtime": 23.5333,
+      "eval_samples_per_second": 21.247,
+      "eval_steps_per_second": 2.677,
+      "step": 12456
+    },
+    {
+      "epoch": 0.8028775130066157,
+      "grad_norm": 0.4802183210849762,
+      "learning_rate": 0.00037323955723981417,
+      "loss": 0.2085,
+      "step": 12500
+    },
+    {
+      "epoch": 0.8349926135268804,
+      "grad_norm": 0.5503079295158386,
+      "learning_rate": 0.0003721690538891387,
+      "loss": 0.2067,
+      "step": 13000
+    },
+    {
+      "epoch": 0.8671077140471449,
+      "grad_norm": 0.7957497835159302,
+      "learning_rate": 0.0003710985505384632,
+      "loss": 0.2074,
+      "step": 13500
+    },
+    {
+      "epoch": 0.8992228145674096,
+      "grad_norm": 0.5829387903213501,
+      "learning_rate": 0.0003700280471877877,
+      "loss": 0.2052,
+      "step": 14000
+    },
+    {
+      "epoch": 0.9313379150876743,
+      "grad_norm": 0.5419838428497314,
+      "learning_rate": 0.0003689575438371122,
+      "loss": 0.2068,
+      "step": 14500
+    },
+    {
+      "epoch": 0.9634530156079388,
+      "grad_norm": 0.6495779156684875,
+      "learning_rate": 0.00036788704048643675,
+      "loss": 0.204,
+      "step": 15000
+    },
+    {
+      "epoch": 0.9955681161282035,
+      "grad_norm": 0.5676125884056091,
+      "learning_rate": 0.0003668165371357613,
+      "loss": 0.2022,
+      "step": 15500
+    },
+    {
+      "epoch": 1.0000642302010405,
+      "eval_loss": 0.20003509521484375,
+      "eval_runtime": 23.5569,
+      "eval_samples_per_second": 21.225,
+      "eval_steps_per_second": 2.674,
+      "step": 15570
+    },
+    {
+      "epoch": 1.0276832166484682,
+      "grad_norm": 0.7140610814094543,
+      "learning_rate": 0.00036574603378508575,
+      "loss": 0.1873,
+      "step": 16000
+    },
+    {
+      "epoch": 1.0597983171687329,
+      "grad_norm": 0.5535098314285278,
+      "learning_rate": 0.0003646755304344103,
+      "loss": 0.1863,
+      "step": 16500
+    },
+    {
+      "epoch": 1.0919134176889973,
+      "grad_norm": 0.7977581024169922,
+      "learning_rate": 0.0003636050270837348,
+      "loss": 0.1821,
+      "step": 17000
+    },
+    {
+      "epoch": 1.124028518209262,
+      "grad_norm": 0.6831263899803162,
+      "learning_rate": 0.0003625345237330593,
+      "loss": 0.1862,
+      "step": 17500
+    },
+    {
+      "epoch": 1.1561436187295266,
+      "grad_norm": 0.5401275157928467,
+      "learning_rate": 0.0003614640203823838,
+      "loss": 0.1838,
+      "step": 18000
+    },
+    {
+      "epoch": 1.1882587192497913,
+      "grad_norm": 0.7341705560684204,
+      "learning_rate": 0.00036039351703170833,
+      "loss": 0.1877,
+      "step": 18500
+    },
+    {
+      "epoch": 1.2000770762412487,
+      "eval_loss": 0.18818311393260956,
+      "eval_runtime": 23.5188,
+      "eval_samples_per_second": 21.26,
+      "eval_steps_per_second": 2.679,
+      "step": 18684
+    },
+    {
+      "epoch": 1.2203738197700558,
+      "grad_norm": 0.709534227848053,
+      "learning_rate": 0.0003593230136810328,
+      "loss": 0.1849,
+      "step": 19000
+    },
+    {
+      "epoch": 1.2524889202903204,
+      "grad_norm": 0.43899551033973694,
+      "learning_rate": 0.00035825251033035733,
+      "loss": 0.1869,
+      "step": 19500
+    },
+    {
+      "epoch": 1.2846040208105851,
+      "grad_norm": 0.4917741119861603,
+      "learning_rate": 0.00035718200697968186,
+      "loss": 0.1876,
+      "step": 20000
+    },
+    {
+      "epoch": 1.3167191213308498,
+      "grad_norm": 0.5574023127555847,
+      "learning_rate": 0.0003561115036290064,
+      "loss": 0.1819,
+      "step": 20500
+    },
+    {
+      "epoch": 1.3488342218511145,
+      "grad_norm": 0.5843190550804138,
+      "learning_rate": 0.00035504100027833086,
+      "loss": 0.1794,
+      "step": 21000
+    },
+    {
+      "epoch": 1.3809493223713791,
+      "grad_norm": 0.8508747220039368,
+      "learning_rate": 0.0003539704969276554,
+      "loss": 0.1807,
+      "step": 21500
+    },
+    {
+      "epoch": 1.4000899222814567,
+      "eval_loss": 0.18726639449596405,
+      "eval_runtime": 23.5182,
+      "eval_samples_per_second": 21.26,
+      "eval_steps_per_second": 2.679,
+      "step": 21798
+    },
+    {
+      "epoch": 1.4130644228916436,
+      "grad_norm": 0.5073943138122559,
+      "learning_rate": 0.0003528999935769799,
+      "loss": 0.1837,
+      "step": 22000
+    },
+    {
+      "epoch": 1.4451795234119083,
+      "grad_norm": 0.5854476690292358,
+      "learning_rate": 0.0003518294902263044,
+      "loss": 0.1825,
+      "step": 22500
+    },
+    {
+      "epoch": 1.477294623932173,
+      "grad_norm": 0.7072814106941223,
+      "learning_rate": 0.00035075898687562896,
+      "loss": 0.1802,
+      "step": 23000
+    },
+    {
+      "epoch": 1.5094097244524374,
+      "grad_norm": 0.679303765296936,
+      "learning_rate": 0.0003496884835249535,
+      "loss": 0.1794,
+      "step": 23500
+    },
+    {
+      "epoch": 1.541524824972702,
+      "grad_norm": 1.0397990942001343,
+      "learning_rate": 0.00034861798017427796,
+      "loss": 0.1798,
+      "step": 24000
+    },
+    {
+      "epoch": 1.5736399254929667,
+      "grad_norm": 0.5808541774749756,
+      "learning_rate": 0.0003475474768236025,
+      "loss": 0.1823,
+      "step": 24500
+    },
+    {
+      "epoch": 1.6001027683216649,
+      "eval_loss": 0.17847995460033417,
+      "eval_runtime": 23.5596,
+      "eval_samples_per_second": 21.223,
+      "eval_steps_per_second": 2.674,
+      "step": 24912
+    },
+    {
+      "epoch": 1.6057550260132314,
+      "grad_norm": 0.82099449634552,
+      "learning_rate": 0.000346476973472927,
+      "loss": 0.1806,
+      "step": 25000
+    },
+    {
+      "epoch": 1.637870126533496,
+      "grad_norm": 0.5932102799415588,
+      "learning_rate": 0.0003454064701222515,
+      "loss": 0.1825,
+      "step": 25500
+    },
+    {
+      "epoch": 1.6699852270537607,
+      "grad_norm": 0.559738278388977,
+      "learning_rate": 0.000344335966771576,
+      "loss": 0.1762,
+      "step": 26000
+    },
+    {
+      "epoch": 1.7021003275740254,
+      "grad_norm": 0.5731418132781982,
+      "learning_rate": 0.00034326546342090055,
+      "loss": 0.1784,
+      "step": 26500
+    },
+    {
+      "epoch": 1.73421542809429,
+      "grad_norm": 0.5487440824508667,
+      "learning_rate": 0.00034219496007022507,
+      "loss": 0.1746,
+      "step": 27000
+    },
+    {
+      "epoch": 1.7663305286145545,
+      "grad_norm": 0.5879372358322144,
+      "learning_rate": 0.00034112445671954954,
+      "loss": 0.1748,
+      "step": 27500
+    },
+    {
+      "epoch": 1.7984456291348192,
+      "grad_norm": 0.49256157875061035,
+      "learning_rate": 0.00034005395336887407,
+      "loss": 0.1789,
+      "step": 28000
+    },
+    {
+      "epoch": 1.8001156143618728,
+      "eval_loss": 0.17633214592933655,
+      "eval_runtime": 23.4994,
+      "eval_samples_per_second": 21.277,
+      "eval_steps_per_second": 2.681,
+      "step": 28026
+    },
+    {
+      "epoch": 1.8305607296550839,
+      "grad_norm": 0.5885323882102966,
+      "learning_rate": 0.0003389834500181986,
+      "loss": 0.1811,
+      "step": 28500
+    },
+    {
+      "epoch": 1.8626758301753483,
+      "grad_norm": 0.6987548470497131,
+      "learning_rate": 0.00033791294666752307,
+      "loss": 0.1781,
+      "step": 29000
+    },
+    {
+      "epoch": 1.894790930695613,
+      "grad_norm": 0.4901442229747772,
+      "learning_rate": 0.0003368424433168476,
+      "loss": 0.178,
+      "step": 29500
+    },
+    {
+      "epoch": 1.9269060312158777,
+      "grad_norm": 0.5317521691322327,
+      "learning_rate": 0.0003357719399661721,
+      "loss": 0.1739,
+      "step": 30000
+    },
+    {
+      "epoch": 1.9590211317361423,
+      "grad_norm": 0.5850645303726196,
+      "learning_rate": 0.0003347014366154966,
+      "loss": 0.1756,
+      "step": 30500
+    },
+    {
+      "epoch": 1.991136232256407,
+      "grad_norm": 0.7213283181190491,
+      "learning_rate": 0.0003336309332648211,
+      "loss": 0.1731,
+      "step": 31000
+    },
+    {
+      "epoch": 2.000128460402081,
+      "eval_loss": 0.17786261439323425,
+      "eval_runtime": 23.5267,
+      "eval_samples_per_second": 21.252,
+      "eval_steps_per_second": 2.678,
+      "step": 31140
+    },
+    {
+      "epoch": 2.0232513327766717,
+      "grad_norm": 0.6630722284317017,
+      "learning_rate": 0.00033256042991414565,
+      "loss": 0.1641,
+      "step": 31500
+    },
+    {
+      "epoch": 2.0553664332969364,
+      "grad_norm": 0.577346682548523,
+      "learning_rate": 0.0003314899265634702,
+      "loss": 0.1605,
+      "step": 32000
+    },
+    {
+      "epoch": 2.087481533817201,
+      "grad_norm": 0.6629170179367065,
+      "learning_rate": 0.00033041942321279465,
+      "loss": 0.1563,
+      "step": 32500
+    },
+    {
+      "epoch": 2.1195966343374657,
+      "grad_norm": 0.6548158526420593,
+      "learning_rate": 0.0003293489198621192,
+      "loss": 0.1602,
+      "step": 33000
+    },
+    {
+      "epoch": 2.15171173485773,
+      "grad_norm": 0.7047867774963379,
+      "learning_rate": 0.0003282784165114437,
+      "loss": 0.1583,
+      "step": 33500
+    },
+    {
+      "epoch": 2.1838268353779946,
+      "grad_norm": 0.7975640892982483,
+      "learning_rate": 0.0003272079131607682,
+      "loss": 0.1576,
+      "step": 34000
+    },
+    {
+      "epoch": 2.2001413064422892,
+      "eval_loss": 0.17521116137504578,
+      "eval_runtime": 23.5528,
+      "eval_samples_per_second": 21.229,
+      "eval_steps_per_second": 2.675,
+      "step": 34254
+    },
+    {
+      "epoch": 2.2159419358982593,
+      "grad_norm": 0.7683706879615784,
+      "learning_rate": 0.0003261374098100927,
+      "loss": 0.1631,
+      "step": 34500
+    },
+    {
+      "epoch": 2.248057036418524,
+      "grad_norm": 0.5740845203399658,
+      "learning_rate": 0.00032506690645941723,
+      "loss": 0.1646,
+      "step": 35000
+    },
+    {
+      "epoch": 2.2801721369387886,
+      "grad_norm": 0.7392342686653137,
+      "learning_rate": 0.0003239964031087417,
+      "loss": 0.1605,
+      "step": 35500
+    },
+    {
+      "epoch": 2.3122872374590533,
+      "grad_norm": 0.8474887609481812,
+      "learning_rate": 0.00032292589975806623,
+      "loss": 0.1586,
+      "step": 36000
+    },
+    {
+      "epoch": 2.344402337979318,
+      "grad_norm": 0.6714057326316833,
+      "learning_rate": 0.00032185539640739076,
+      "loss": 0.1612,
+      "step": 36500
+    },
+    {
+      "epoch": 2.3765174384995826,
+      "grad_norm": 0.6205163598060608,
+      "learning_rate": 0.0003207848930567153,
+      "loss": 0.1605,
+      "step": 37000
+    },
+    {
+      "epoch": 2.4001541524824974,
+      "eval_loss": 0.17167526483535767,
+      "eval_runtime": 23.5731,
+      "eval_samples_per_second": 21.211,
+      "eval_steps_per_second": 2.673,
+      "step": 37368
+    },
+    {
+      "epoch": 2.4086325390198473,
+      "grad_norm": 0.6052642464637756,
+      "learning_rate": 0.00031971438970603976,
+      "loss": 0.1611,
+      "step": 37500
+    },
+    {
+      "epoch": 2.4407476395401115,
+      "grad_norm": 0.8701796531677246,
+      "learning_rate": 0.00031864388635536434,
+      "loss": 0.1594,
+      "step": 38000
+    },
+    {
+      "epoch": 2.472862740060376,
+      "grad_norm": 0.6723088026046753,
+      "learning_rate": 0.00031757338300468887,
+      "loss": 0.1606,
+      "step": 38500
+    },
+    {
+      "epoch": 2.504977840580641,
+      "grad_norm": 0.5551071166992188,
+      "learning_rate": 0.00031650287965401334,
+      "loss": 0.1556,
+      "step": 39000
+    },
+    {
+      "epoch": 2.5370929411009056,
+      "grad_norm": 0.7619051337242126,
+      "learning_rate": 0.00031543237630333787,
+      "loss": 0.1587,
+      "step": 39500
+    },
+    {
+      "epoch": 2.5692080416211702,
+      "grad_norm": 0.5764791369438171,
+      "learning_rate": 0.0003143618729526624,
+      "loss": 0.1594,
+      "step": 40000
+    },
+    {
+      "epoch": 2.600166998522705,
+      "eval_loss": 0.17085638642311096,
+      "eval_runtime": 23.5494,
+      "eval_samples_per_second": 21.232,
+      "eval_steps_per_second": 2.675,
+      "step": 40482
+    },
+    {
+      "epoch": 2.601323142141435,
+      "grad_norm": 0.6233007311820984,
+      "learning_rate": 0.00031329136960198687,
+      "loss": 0.1603,
+      "step": 40500
+    },
+    {
+      "epoch": 2.6334382426616996,
+      "grad_norm": 0.5824421644210815,
+      "learning_rate": 0.0003122208662513114,
+      "loss": 0.1593,
+      "step": 41000
+    },
+    {
+      "epoch": 2.6655533431819642,
+      "grad_norm": 0.870520830154419,
+      "learning_rate": 0.0003111503629006359,
+      "loss": 0.1568,
+      "step": 41500
+    },
+    {
+      "epoch": 2.697668443702229,
+      "grad_norm": 0.5139821171760559,
+      "learning_rate": 0.0003100798595499604,
+      "loss": 0.1565,
+      "step": 42000
+    },
+    {
+      "epoch": 2.729783544222493,
+      "grad_norm": 0.7599707245826721,
+      "learning_rate": 0.0003090093561992849,
+      "loss": 0.1551,
+      "step": 42500
+    },
+    {
+      "epoch": 2.7618986447427583,
+      "grad_norm": 0.7542629241943359,
+      "learning_rate": 0.00030793885284860945,
+      "loss": 0.1577,
+      "step": 43000
+    },
+    {
+      "epoch": 2.7940137452630225,
+      "grad_norm": 0.5201693773269653,
+      "learning_rate": 0.000306868349497934,
+      "loss": 0.1616,
+      "step": 43500
+    },
+    {
+      "epoch": 2.8001798445629134,
+      "eval_loss": 0.16716547310352325,
+      "eval_runtime": 23.533,
+      "eval_samples_per_second": 21.247,
+      "eval_steps_per_second": 2.677,
+      "step": 43596
+    },
+    {
+      "epoch": 2.826128845783287,
+      "grad_norm": 0.7950155735015869,
+      "learning_rate": 0.00030579784614725845,
+      "loss": 0.158,
+      "step": 44000
+    },
+    {
+      "epoch": 2.858243946303552,
+      "grad_norm": 1.0053386688232422,
+      "learning_rate": 0.000304727342796583,
+      "loss": 0.1578,
+      "step": 44500
+    },
+    {
+      "epoch": 2.8903590468238165,
+      "grad_norm": 0.6753293871879578,
+      "learning_rate": 0.0003036568394459075,
+      "loss": 0.1571,
+      "step": 45000
+    },
+    {
+      "epoch": 2.922474147344081,
+      "grad_norm": 0.7206805348396301,
+      "learning_rate": 0.000302586336095232,
+      "loss": 0.158,
+      "step": 45500
+    },
+    {
+      "epoch": 2.954589247864346,
+      "grad_norm": 0.743216335773468,
+      "learning_rate": 0.0003015158327445565,
+      "loss": 0.1565,
+      "step": 46000
+    },
+    {
+      "epoch": 2.9867043483846105,
+      "grad_norm": 0.7052605748176575,
+      "learning_rate": 0.00030044532939388103,
+      "loss": 0.1562,
+      "step": 46500
+    },
+    {
+      "epoch": 3.0001926906031215,
+      "eval_loss": 0.16358919441699982,
+      "eval_runtime": 23.528,
+      "eval_samples_per_second": 21.251,
+      "eval_steps_per_second": 2.678,
+      "step": 46710
+    },
+    {
+      "epoch": 3.018819448904875,
+      "grad_norm": 0.4727093577384949,
+      "learning_rate": 0.0002993748260432055,
+      "loss": 0.1469,
+      "step": 47000
+    },
+    {
+      "epoch": 3.05093454942514,
+      "grad_norm": 0.8503308892250061,
+      "learning_rate": 0.00029830432269253003,
+      "loss": 0.1397,
+      "step": 47500
+    },
+    {
+      "epoch": 3.0830496499454045,
+      "grad_norm": 0.7006432414054871,
+      "learning_rate": 0.00029723381934185455,
+      "loss": 0.1368,
+      "step": 48000
+    },
+    {
+      "epoch": 3.1151647504656688,
+      "grad_norm": 0.8011033535003662,
+      "learning_rate": 0.0002961633159911791,
+      "loss": 0.1379,
+      "step": 48500
+    },
+    {
+      "epoch": 3.1472798509859334,
+      "grad_norm": 0.7872356176376343,
+      "learning_rate": 0.00029509281264050355,
+      "loss": 0.1422,
+      "step": 49000
+    },
+    {
+      "epoch": 3.179394951506198,
+      "grad_norm": 0.6667813062667847,
+      "learning_rate": 0.0002940223092898281,
+      "loss": 0.1431,
+      "step": 49500
+    },
+    {
+      "epoch": 3.2002055366433297,
+      "eval_loss": 0.16433122754096985,
+      "eval_runtime": 23.5397,
+      "eval_samples_per_second": 21.241,
+      "eval_steps_per_second": 2.676,
+      "step": 49824
+    },
+    {
+      "epoch": 3.211510052026463,
+      "grad_norm": 0.8715939521789551,
+      "learning_rate": 0.0002929518059391526,
+      "loss": 0.1422,
+      "step": 50000
+    },
+    {
+      "epoch": 3.2436251525467275,
+      "grad_norm": 0.9269859194755554,
+      "learning_rate": 0.0002918813025884771,
+      "loss": 0.1409,
+      "step": 50500
+    },
+    {
+      "epoch": 3.275740253066992,
+      "grad_norm": 0.6357953548431396,
+      "learning_rate": 0.0002908107992378016,
+      "loss": 0.1446,
+      "step": 51000
+    },
+    {
+      "epoch": 3.307855353587257,
+      "grad_norm": 0.7378066182136536,
+      "learning_rate": 0.00028974029588712613,
+      "loss": 0.1453,
+      "step": 51500
+    },
+    {
+      "epoch": 3.3399704541075215,
+      "grad_norm": 0.943709135055542,
+      "learning_rate": 0.0002886697925364506,
+      "loss": 0.1417,
+      "step": 52000
+    },
+    {
+      "epoch": 3.372085554627786,
+      "grad_norm": 0.6570321321487427,
+      "learning_rate": 0.00028759928918577513,
+      "loss": 0.1441,
+      "step": 52500
+    },
+    {
+      "epoch": 3.400218382683538,
+      "eval_loss": 0.1624871790409088,
+      "eval_runtime": 23.5457,
+      "eval_samples_per_second": 21.235,
+      "eval_steps_per_second": 2.676,
+      "step": 52938
+    },
+    {
+      "epoch": 3.404200655148051,
+      "grad_norm": 0.9427246451377869,
+      "learning_rate": 0.00028652878583509966,
+      "loss": 0.1468,
+      "step": 53000
+    },
+    {
+      "epoch": 3.436315755668315,
+      "grad_norm": 0.7920241951942444,
+      "learning_rate": 0.0002854582824844242,
+      "loss": 0.1448,
+      "step": 53500
+    },
+    {
+      "epoch": 3.4684308561885797,
+      "grad_norm": 0.5575000643730164,
+      "learning_rate": 0.0002843877791337487,
+      "loss": 0.1469,
+      "step": 54000
+    },
+    {
+      "epoch": 3.5005459567088444,
+      "grad_norm": 0.6529808640480042,
+      "learning_rate": 0.00028331727578307324,
+      "loss": 0.147,
+      "step": 54500
+    },
+    {
+      "epoch": 3.532661057229109,
+      "grad_norm": 0.9324051737785339,
+      "learning_rate": 0.00028224677243239777,
+      "loss": 0.1466,
+      "step": 55000
+    },
+    {
+      "epoch": 3.5647761577493737,
+      "grad_norm": 0.5927507877349854,
+      "learning_rate": 0.00028117626908172224,
+      "loss": 0.1459,
+      "step": 55500
+    },
+    {
+      "epoch": 3.5968912582696384,
+      "grad_norm": 0.8716698288917542,
+      "learning_rate": 0.00028010576573104677,
+      "loss": 0.142,
+      "step": 56000
+    },
+    {
+      "epoch": 3.6002312287237457,
+      "eval_loss": 0.16277267038822174,
+      "eval_runtime": 23.79,
+      "eval_samples_per_second": 21.017,
+      "eval_steps_per_second": 2.648,
+      "step": 56052
+    },
+    {
+      "epoch": 3.629006358789903,
+      "grad_norm": 0.7157331705093384,
+      "learning_rate": 0.0002790352623803713,
+      "loss": 0.1457,
+      "step": 56500
+    },
+    {
+      "epoch": 3.6611214593101677,
+      "grad_norm": 0.9151171445846558,
+      "learning_rate": 0.00027796475902969577,
+      "loss": 0.1432,
+      "step": 57000
+    },
+    {
+      "epoch": 3.6932365598304324,
+      "grad_norm": 0.7013692259788513,
+      "learning_rate": 0.0002768942556790203,
+      "loss": 0.1434,
+      "step": 57500
+    },
+    {
+      "epoch": 3.7253516603506966,
+      "grad_norm": 0.5642277598381042,
+      "learning_rate": 0.0002758237523283448,
+      "loss": 0.1439,
+      "step": 58000
+    },
+    {
+      "epoch": 3.7574667608709618,
+      "grad_norm": 0.6188544034957886,
+      "learning_rate": 0.0002747532489776693,
+      "loss": 0.1428,
+      "step": 58500
+    },
+    {
+      "epoch": 3.789581861391226,
+      "grad_norm": 0.7338648438453674,
+      "learning_rate": 0.0002736827456269938,
+      "loss": 0.1421,
+      "step": 59000
+    },
+    {
+      "epoch": 3.800244074763954,
+      "eval_loss": 0.15712550282478333,
+      "eval_runtime": 23.5916,
+      "eval_samples_per_second": 21.194,
+      "eval_steps_per_second": 2.67,
+      "step": 59166
+    },
+    {
+      "epoch": 3.8216969619114907,
+      "grad_norm": 0.7429503798484802,
+      "learning_rate": 0.00027261224227631835,
+      "loss": 0.1446,
+      "step": 59500
+    },
+    {
+      "epoch": 3.8538120624317553,
+      "grad_norm": 0.7121846675872803,
+      "learning_rate": 0.0002715417389256429,
+      "loss": 0.1399,
+      "step": 60000
+    },
+    {
+      "epoch": 3.88592716295202,
+      "grad_norm": 0.5918430685997009,
+      "learning_rate": 0.00027047123557496735,
+      "loss": 0.1423,
+      "step": 60500
+    },
+    {
+      "epoch": 3.9180422634722847,
+      "grad_norm": 0.49308261275291443,
+      "learning_rate": 0.0002694007322242919,
+      "loss": 0.1433,
+      "step": 61000
+    },
+    {
+      "epoch": 3.9501573639925494,
+      "grad_norm": 0.4051227271556854,
+      "learning_rate": 0.0002683302288736164,
+      "loss": 0.1455,
+      "step": 61500
+    },
+    {
+      "epoch": 3.982272464512814,
+      "grad_norm": 0.6791379451751709,
+      "learning_rate": 0.0002672597255229409,
+      "loss": 0.1429,
+      "step": 62000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 186828,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.7600806191789244e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-62276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:905a7e9abb7946f25f4dd7b875a4e18748313ca2ecebcb00cda932c6ec6dd7ac
+size 5969