Training in progress, epoch 5, checkpoint

checkpoint-77845/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-77845/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": [
+    "q_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-77845/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01db95fd4bbd5db6b6063d87486de8e0443b293d3e6552e95b5c11ee27517222
+size 541442872

checkpoint-77845/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c76c26005bb313bab2065e291b518bb5d627f59fadfb70a8574917d0b0fce9
+size 33664331

checkpoint-77845/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8729270e42e9f0810493c90ed833933cc50f75b29ecfba69e7c8256600a0b9e2
+size 15429

checkpoint-77845/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:998f5d43d925012b20ee5d8381d98a11786d6abda1f6c23e9b359f51c3fb9505
+size 15429

checkpoint-77845/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4703580d292e9280aec8f0e40be7273e9457839c35b87f6bc1dbd782cdf563f8
+size 15429

checkpoint-77845/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21e507987c15485573d2fb1c085f023b1cecb07449080733063cf19e5db2f0d4
+size 15429

checkpoint-77845/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63b374f525f261516982436cbdd52f264a2fa16b745265e4769916ed5719b55e
+size 1383

checkpoint-77845/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:518d6ba384c2fa1ce0f88eef6efa900bc433ec33131c51e02baf3a82d4d0a4a6
+size 1465

checkpoint-77845/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-77845/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-77845/trainer_state.json

@@ -0,0 +1,1311 @@
+{
+  "best_global_step": null,
+  "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": 0.59400475025177,
+      "learning_rate": 0.0003989316376560259,
+      "loss": 0.4657,
+      "step": 500
+    },
+    {
+      "epoch": 0.06423020104052926,
+      "grad_norm": 0.6175355315208435,
+      "learning_rate": 0.0003978611343053504,
+      "loss": 0.3896,
+      "step": 1000
+    },
+    {
+      "epoch": 0.09634530156079389,
+      "grad_norm": 0.6760411858558655,
+      "learning_rate": 0.0003967906309546749,
+      "loss": 0.3524,
+      "step": 1500
+    },
+    {
+      "epoch": 0.12846040208105852,
+      "grad_norm": 0.610696017742157,
+      "learning_rate": 0.00039572012760399943,
+      "loss": 0.3337,
+      "step": 2000
+    },
+    {
+      "epoch": 0.16057550260132314,
+      "grad_norm": 0.6075437664985657,
+      "learning_rate": 0.0003946496242533239,
+      "loss": 0.3212,
+      "step": 2500
+    },
+    {
+      "epoch": 0.19269060312158778,
+      "grad_norm": 0.47634950280189514,
+      "learning_rate": 0.00039357912090264843,
+      "loss": 0.3108,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2000128460402081,
+      "eval_loss": 0.3016771972179413,
+      "eval_runtime": 15.733,
+      "eval_samples_per_second": 31.78,
+      "eval_steps_per_second": 4.004,
+      "step": 3114
+    },
+    {
+      "epoch": 0.2248057036418524,
+      "grad_norm": 0.5005037784576416,
+      "learning_rate": 0.00039250861755197295,
+      "loss": 0.304,
+      "step": 3500
+    },
+    {
+      "epoch": 0.25692080416211704,
+      "grad_norm": 0.4508284628391266,
+      "learning_rate": 0.0003914381142012975,
+      "loss": 0.2931,
+      "step": 4000
+    },
+    {
+      "epoch": 0.28903590468238166,
+      "grad_norm": 0.5151750445365906,
+      "learning_rate": 0.00039036761085062195,
+      "loss": 0.2856,
+      "step": 4500
+    },
+    {
+      "epoch": 0.3211510052026463,
+      "grad_norm": 0.4935036301612854,
+      "learning_rate": 0.0003892971074999465,
+      "loss": 0.2757,
+      "step": 5000
+    },
+    {
+      "epoch": 0.3532661057229109,
+      "grad_norm": 0.5727084279060364,
+      "learning_rate": 0.000388226604149271,
+      "loss": 0.2773,
+      "step": 5500
+    },
+    {
+      "epoch": 0.38538120624317557,
+      "grad_norm": 0.5073119401931763,
+      "learning_rate": 0.0003871561007985955,
+      "loss": 0.2685,
+      "step": 6000
+    },
+    {
+      "epoch": 0.4000256920804162,
+      "eval_loss": 0.25506290793418884,
+      "eval_runtime": 15.8313,
+      "eval_samples_per_second": 31.583,
+      "eval_steps_per_second": 3.979,
+      "step": 6228
+    },
+    {
+      "epoch": 0.4174963067634402,
+      "grad_norm": 0.7391453981399536,
+      "learning_rate": 0.00038608559744792,
+      "loss": 0.2662,
+      "step": 6500
+    },
+    {
+      "epoch": 0.4496114072837048,
+      "grad_norm": 0.8289486169815063,
+      "learning_rate": 0.00038501509409724454,
+      "loss": 0.2577,
+      "step": 7000
+    },
+    {
+      "epoch": 0.4817265078039694,
+      "grad_norm": 0.9032345414161682,
+      "learning_rate": 0.00038394459074656906,
+      "loss": 0.2567,
+      "step": 7500
+    },
+    {
+      "epoch": 0.5138416083242341,
+      "grad_norm": 0.6563591957092285,
+      "learning_rate": 0.0003828740873958936,
+      "loss": 0.251,
+      "step": 8000
+    },
+    {
+      "epoch": 0.5459567088444987,
+      "grad_norm": 0.8996277451515198,
+      "learning_rate": 0.0003818035840452181,
+      "loss": 0.2519,
+      "step": 8500
+    },
+    {
+      "epoch": 0.5780718093647633,
+      "grad_norm": 0.6761796474456787,
+      "learning_rate": 0.0003807330806945426,
+      "loss": 0.2493,
+      "step": 9000
+    },
+    {
+      "epoch": 0.6000385381206244,
+      "eval_loss": 0.2313319444656372,
+      "eval_runtime": 15.6731,
+      "eval_samples_per_second": 31.902,
+      "eval_steps_per_second": 4.02,
+      "step": 9342
+    },
+    {
+      "epoch": 0.610186909885028,
+      "grad_norm": 0.6171412467956543,
+      "learning_rate": 0.0003796625773438671,
+      "loss": 0.2461,
+      "step": 9500
+    },
+    {
+      "epoch": 0.6423020104052926,
+      "grad_norm": 0.5448698401451111,
+      "learning_rate": 0.00037859207399319164,
+      "loss": 0.241,
+      "step": 10000
+    },
+    {
+      "epoch": 0.6744171109255572,
+      "grad_norm": 0.5607863068580627,
+      "learning_rate": 0.0003775215706425161,
+      "loss": 0.2452,
+      "step": 10500
+    },
+    {
+      "epoch": 0.7065322114458218,
+      "grad_norm": 0.5820897817611694,
+      "learning_rate": 0.00037645106729184064,
+      "loss": 0.2381,
+      "step": 11000
+    },
+    {
+      "epoch": 0.7386473119660865,
+      "grad_norm": 0.47285422682762146,
+      "learning_rate": 0.00037538056394116517,
+      "loss": 0.2398,
+      "step": 11500
+    },
+    {
+      "epoch": 0.7707624124863511,
+      "grad_norm": 0.6115566492080688,
+      "learning_rate": 0.0003743100605904897,
+      "loss": 0.2335,
+      "step": 12000
+    },
+    {
+      "epoch": 0.8000513841608324,
+      "eval_loss": 0.22419464588165283,
+      "eval_runtime": 15.6555,
+      "eval_samples_per_second": 31.938,
+      "eval_steps_per_second": 4.024,
+      "step": 12456
+    },
+    {
+      "epoch": 0.8028775130066157,
+      "grad_norm": 0.6582175493240356,
+      "learning_rate": 0.00037323955723981417,
+      "loss": 0.2306,
+      "step": 12500
+    },
+    {
+      "epoch": 0.8349926135268804,
+      "grad_norm": 0.6073306798934937,
+      "learning_rate": 0.0003721690538891387,
+      "loss": 0.2284,
+      "step": 13000
+    },
+    {
+      "epoch": 0.8671077140471449,
+      "grad_norm": 0.8297299146652222,
+      "learning_rate": 0.0003710985505384632,
+      "loss": 0.2284,
+      "step": 13500
+    },
+    {
+      "epoch": 0.8992228145674096,
+      "grad_norm": 0.7792572975158691,
+      "learning_rate": 0.0003700280471877877,
+      "loss": 0.2284,
+      "step": 14000
+    },
+    {
+      "epoch": 0.9313379150876743,
+      "grad_norm": 0.6355712413787842,
+      "learning_rate": 0.0003689575438371122,
+      "loss": 0.2278,
+      "step": 14500
+    },
+    {
+      "epoch": 0.9634530156079388,
+      "grad_norm": 0.8210628628730774,
+      "learning_rate": 0.00036788704048643675,
+      "loss": 0.223,
+      "step": 15000
+    },
+    {
+      "epoch": 0.9955681161282035,
+      "grad_norm": 0.5225551128387451,
+      "learning_rate": 0.0003668165371357613,
+      "loss": 0.2223,
+      "step": 15500
+    },
+    {
+      "epoch": 1.0000642302010405,
+      "eval_loss": 0.2162015736103058,
+      "eval_runtime": 15.7328,
+      "eval_samples_per_second": 31.781,
+      "eval_steps_per_second": 4.004,
+      "step": 15570
+    },
+    {
+      "epoch": 1.0276832166484682,
+      "grad_norm": 0.6531597971916199,
+      "learning_rate": 0.00036574603378508575,
+      "loss": 0.2036,
+      "step": 16000
+    },
+    {
+      "epoch": 1.0597983171687329,
+      "grad_norm": 0.7152116298675537,
+      "learning_rate": 0.0003646755304344103,
+      "loss": 0.2036,
+      "step": 16500
+    },
+    {
+      "epoch": 1.0919134176889973,
+      "grad_norm": 0.6521881818771362,
+      "learning_rate": 0.0003636050270837348,
+      "loss": 0.2006,
+      "step": 17000
+    },
+    {
+      "epoch": 1.124028518209262,
+      "grad_norm": 0.7996369004249573,
+      "learning_rate": 0.0003625345237330593,
+      "loss": 0.2046,
+      "step": 17500
+    },
+    {
+      "epoch": 1.1561436187295266,
+      "grad_norm": 0.5365395545959473,
+      "learning_rate": 0.0003614640203823838,
+      "loss": 0.2019,
+      "step": 18000
+    },
+    {
+      "epoch": 1.1882587192497913,
+      "grad_norm": 0.8401092886924744,
+      "learning_rate": 0.00036039351703170833,
+      "loss": 0.2042,
+      "step": 18500
+    },
+    {
+      "epoch": 1.2000770762412487,
+      "eval_loss": 0.20440329611301422,
+      "eval_runtime": 15.9564,
+      "eval_samples_per_second": 31.335,
+      "eval_steps_per_second": 3.948,
+      "step": 18684
+    },
+    {
+      "epoch": 1.2203738197700558,
+      "grad_norm": 0.7515975832939148,
+      "learning_rate": 0.0003593230136810328,
+      "loss": 0.2027,
+      "step": 19000
+    },
+    {
+      "epoch": 1.2524889202903204,
+      "grad_norm": 0.5627322196960449,
+      "learning_rate": 0.00035825251033035733,
+      "loss": 0.205,
+      "step": 19500
+    },
+    {
+      "epoch": 1.2846040208105851,
+      "grad_norm": 0.6319966912269592,
+      "learning_rate": 0.00035718200697968186,
+      "loss": 0.2048,
+      "step": 20000
+    },
+    {
+      "epoch": 1.3167191213308498,
+      "grad_norm": 0.5528004765510559,
+      "learning_rate": 0.0003561115036290064,
+      "loss": 0.1999,
+      "step": 20500
+    },
+    {
+      "epoch": 1.3488342218511145,
+      "grad_norm": 0.5572360157966614,
+      "learning_rate": 0.00035504100027833086,
+      "loss": 0.1957,
+      "step": 21000
+    },
+    {
+      "epoch": 1.3809493223713791,
+      "grad_norm": 0.7685332298278809,
+      "learning_rate": 0.0003539704969276554,
+      "loss": 0.1984,
+      "step": 21500
+    },
+    {
+      "epoch": 1.4000899222814567,
+      "eval_loss": 0.19859124720096588,
+      "eval_runtime": 15.7983,
+      "eval_samples_per_second": 31.649,
+      "eval_steps_per_second": 3.988,
+      "step": 21798
+    },
+    {
+      "epoch": 1.4130644228916436,
+      "grad_norm": 0.529292643070221,
+      "learning_rate": 0.0003528999935769799,
+      "loss": 0.2009,
+      "step": 22000
+    },
+    {
+      "epoch": 1.4451795234119083,
+      "grad_norm": 0.5322939157485962,
+      "learning_rate": 0.0003518294902263044,
+      "loss": 0.1986,
+      "step": 22500
+    },
+    {
+      "epoch": 1.477294623932173,
+      "grad_norm": 0.6415036916732788,
+      "learning_rate": 0.00035075898687562896,
+      "loss": 0.1983,
+      "step": 23000
+    },
+    {
+      "epoch": 1.5094097244524374,
+      "grad_norm": 0.8364657759666443,
+      "learning_rate": 0.0003496884835249535,
+      "loss": 0.1948,
+      "step": 23500
+    },
+    {
+      "epoch": 1.541524824972702,
+      "grad_norm": 1.2917670011520386,
+      "learning_rate": 0.00034861798017427796,
+      "loss": 0.1967,
+      "step": 24000
+    },
+    {
+      "epoch": 1.5736399254929667,
+      "grad_norm": 0.6391225457191467,
+      "learning_rate": 0.0003475474768236025,
+      "loss": 0.1993,
+      "step": 24500
+    },
+    {
+      "epoch": 1.6001027683216649,
+      "eval_loss": 0.1940152645111084,
+      "eval_runtime": 15.6866,
+      "eval_samples_per_second": 31.874,
+      "eval_steps_per_second": 4.016,
+      "step": 24912
+    },
+    {
+      "epoch": 1.6057550260132314,
+      "grad_norm": 0.7363100051879883,
+      "learning_rate": 0.000346476973472927,
+      "loss": 0.1979,
+      "step": 25000
+    },
+    {
+      "epoch": 1.637870126533496,
+      "grad_norm": 0.7358267903327942,
+      "learning_rate": 0.0003454064701222515,
+      "loss": 0.1991,
+      "step": 25500
+    },
+    {
+      "epoch": 1.6699852270537607,
+      "grad_norm": 0.6543652415275574,
+      "learning_rate": 0.000344335966771576,
+      "loss": 0.1934,
+      "step": 26000
+    },
+    {
+      "epoch": 1.7021003275740254,
+      "grad_norm": 0.5435949563980103,
+      "learning_rate": 0.00034326546342090055,
+      "loss": 0.1937,
+      "step": 26500
+    },
+    {
+      "epoch": 1.73421542809429,
+      "grad_norm": 0.6814190745353699,
+      "learning_rate": 0.00034219496007022507,
+      "loss": 0.1921,
+      "step": 27000
+    },
+    {
+      "epoch": 1.7663305286145545,
+      "grad_norm": 0.611840546131134,
+      "learning_rate": 0.00034112445671954954,
+      "loss": 0.1889,
+      "step": 27500
+    },
+    {
+      "epoch": 1.7984456291348192,
+      "grad_norm": 0.4577610492706299,
+      "learning_rate": 0.00034005395336887407,
+      "loss": 0.1931,
+      "step": 28000
+    },
+    {
+      "epoch": 1.8001156143618728,
+      "eval_loss": 0.18858034908771515,
+      "eval_runtime": 15.6877,
+      "eval_samples_per_second": 31.872,
+      "eval_steps_per_second": 4.016,
+      "step": 28026
+    },
+    {
+      "epoch": 1.8305607296550839,
+      "grad_norm": 0.5208987593650818,
+      "learning_rate": 0.0003389834500181986,
+      "loss": 0.1971,
+      "step": 28500
+    },
+    {
+      "epoch": 1.8626758301753483,
+      "grad_norm": 0.7604556083679199,
+      "learning_rate": 0.00033791294666752307,
+      "loss": 0.194,
+      "step": 29000
+    },
+    {
+      "epoch": 1.894790930695613,
+      "grad_norm": 0.5700426697731018,
+      "learning_rate": 0.0003368424433168476,
+      "loss": 0.1939,
+      "step": 29500
+    },
+    {
+      "epoch": 1.9269060312158777,
+      "grad_norm": 0.6078197956085205,
+      "learning_rate": 0.0003357719399661721,
+      "loss": 0.1904,
+      "step": 30000
+    },
+    {
+      "epoch": 1.9590211317361423,
+      "grad_norm": 0.5726480484008789,
+      "learning_rate": 0.0003347014366154966,
+      "loss": 0.19,
+      "step": 30500
+    },
+    {
+      "epoch": 1.991136232256407,
+      "grad_norm": 0.6116159558296204,
+      "learning_rate": 0.0003336309332648211,
+      "loss": 0.1887,
+      "step": 31000
+    },
+    {
+      "epoch": 2.000128460402081,
+      "eval_loss": 0.18762615323066711,
+      "eval_runtime": 15.7012,
+      "eval_samples_per_second": 31.845,
+      "eval_steps_per_second": 4.012,
+      "step": 31140
+    },
+    {
+      "epoch": 2.0232513327766717,
+      "grad_norm": 0.7668157815933228,
+      "learning_rate": 0.00033256042991414565,
+      "loss": 0.1784,
+      "step": 31500
+    },
+    {
+      "epoch": 2.0553664332969364,
+      "grad_norm": 0.7431900501251221,
+      "learning_rate": 0.0003314899265634702,
+      "loss": 0.1754,
+      "step": 32000
+    },
+    {
+      "epoch": 2.087481533817201,
+      "grad_norm": 0.9105784893035889,
+      "learning_rate": 0.00033041942321279465,
+      "loss": 0.1697,
+      "step": 32500
+    },
+    {
+      "epoch": 2.1195966343374657,
+      "grad_norm": 0.7251182794570923,
+      "learning_rate": 0.0003293489198621192,
+      "loss": 0.1739,
+      "step": 33000
+    },
+    {
+      "epoch": 2.15171173485773,
+      "grad_norm": 0.87636798620224,
+      "learning_rate": 0.0003282784165114437,
+      "loss": 0.1722,
+      "step": 33500
+    },
+    {
+      "epoch": 2.1838268353779946,
+      "grad_norm": 0.817030668258667,
+      "learning_rate": 0.0003272079131607682,
+      "loss": 0.1712,
+      "step": 34000
+    },
+    {
+      "epoch": 2.2001413064422892,
+      "eval_loss": 0.18303386867046356,
+      "eval_runtime": 15.9057,
+      "eval_samples_per_second": 31.435,
+      "eval_steps_per_second": 3.961,
+      "step": 34254
+    },
+    {
+      "epoch": 2.2159419358982593,
+      "grad_norm": 0.8336374759674072,
+      "learning_rate": 0.0003261374098100927,
+      "loss": 0.1757,
+      "step": 34500
+    },
+    {
+      "epoch": 2.248057036418524,
+      "grad_norm": 0.49993234872817993,
+      "learning_rate": 0.00032506690645941723,
+      "loss": 0.1777,
+      "step": 35000
+    },
+    {
+      "epoch": 2.2801721369387886,
+      "grad_norm": 0.6853183507919312,
+      "learning_rate": 0.0003239964031087417,
+      "loss": 0.173,
+      "step": 35500
+    },
+    {
+      "epoch": 2.3122872374590533,
+      "grad_norm": 0.7537247538566589,
+      "learning_rate": 0.00032292589975806623,
+      "loss": 0.1728,
+      "step": 36000
+    },
+    {
+      "epoch": 2.344402337979318,
+      "grad_norm": 0.6860816478729248,
+      "learning_rate": 0.00032185539640739076,
+      "loss": 0.174,
+      "step": 36500
+    },
+    {
+      "epoch": 2.3765174384995826,
+      "grad_norm": 0.5592321753501892,
+      "learning_rate": 0.0003207848930567153,
+      "loss": 0.1751,
+      "step": 37000
+    },
+    {
+      "epoch": 2.4001541524824974,
+      "eval_loss": 0.17932510375976562,
+      "eval_runtime": 15.7992,
+      "eval_samples_per_second": 31.647,
+      "eval_steps_per_second": 3.988,
+      "step": 37368
+    },
+    {
+      "epoch": 2.4086325390198473,
+      "grad_norm": 0.6483610272407532,
+      "learning_rate": 0.00031971438970603976,
+      "loss": 0.1741,
+      "step": 37500
+    },
+    {
+      "epoch": 2.4407476395401115,
+      "grad_norm": 0.8754846453666687,
+      "learning_rate": 0.00031864388635536434,
+      "loss": 0.1736,
+      "step": 38000
+    },
+    {
+      "epoch": 2.472862740060376,
+      "grad_norm": 0.5679237842559814,
+      "learning_rate": 0.00031757338300468887,
+      "loss": 0.1735,
+      "step": 38500
+    },
+    {
+      "epoch": 2.504977840580641,
+      "grad_norm": 0.7428104877471924,
+      "learning_rate": 0.00031650287965401334,
+      "loss": 0.1703,
+      "step": 39000
+    },
+    {
+      "epoch": 2.5370929411009056,
+      "grad_norm": 0.7946887612342834,
+      "learning_rate": 0.00031543237630333787,
+      "loss": 0.1717,
+      "step": 39500
+    },
+    {
+      "epoch": 2.5692080416211702,
+      "grad_norm": 0.4965314269065857,
+      "learning_rate": 0.0003143618729526624,
+      "loss": 0.1714,
+      "step": 40000
+    },
+    {
+      "epoch": 2.600166998522705,
+      "eval_loss": 0.17936299741268158,
+      "eval_runtime": 15.8296,
+      "eval_samples_per_second": 31.586,
+      "eval_steps_per_second": 3.98,
+      "step": 40482
+    },
+    {
+      "epoch": 2.601323142141435,
+      "grad_norm": 0.9659818410873413,
+      "learning_rate": 0.00031329136960198687,
+      "loss": 0.1729,
+      "step": 40500
+    },
+    {
+      "epoch": 2.6334382426616996,
+      "grad_norm": 0.5570570230484009,
+      "learning_rate": 0.0003122208662513114,
+      "loss": 0.1726,
+      "step": 41000
+    },
+    {
+      "epoch": 2.6655533431819642,
+      "grad_norm": 0.7049115300178528,
+      "learning_rate": 0.0003111503629006359,
+      "loss": 0.1708,
+      "step": 41500
+    },
+    {
+      "epoch": 2.697668443702229,
+      "grad_norm": 0.5560699701309204,
+      "learning_rate": 0.0003100798595499604,
+      "loss": 0.1706,
+      "step": 42000
+    },
+    {
+      "epoch": 2.729783544222493,
+      "grad_norm": 0.6901995539665222,
+      "learning_rate": 0.0003090093561992849,
+      "loss": 0.168,
+      "step": 42500
+    },
+    {
+      "epoch": 2.7618986447427583,
+      "grad_norm": 0.8500509262084961,
+      "learning_rate": 0.00030793885284860945,
+      "loss": 0.1708,
+      "step": 43000
+    },
+    {
+      "epoch": 2.7940137452630225,
+      "grad_norm": 0.6205178499221802,
+      "learning_rate": 0.000306868349497934,
+      "loss": 0.1736,
+      "step": 43500
+    },
+    {
+      "epoch": 2.8001798445629134,
+      "eval_loss": 0.17952795326709747,
+      "eval_runtime": 15.7935,
+      "eval_samples_per_second": 31.659,
+      "eval_steps_per_second": 3.989,
+      "step": 43596
+    },
+    {
+      "epoch": 2.826128845783287,
+      "grad_norm": 0.76055508852005,
+      "learning_rate": 0.00030579784614725845,
+      "loss": 0.1712,
+      "step": 44000
+    },
+    {
+      "epoch": 2.858243946303552,
+      "grad_norm": 1.136112093925476,
+      "learning_rate": 0.000304727342796583,
+      "loss": 0.1708,
+      "step": 44500
+    },
+    {
+      "epoch": 2.8903590468238165,
+      "grad_norm": 0.6640391945838928,
+      "learning_rate": 0.0003036568394459075,
+      "loss": 0.1693,
+      "step": 45000
+    },
+    {
+      "epoch": 2.922474147344081,
+      "grad_norm": 0.7601767182350159,
+      "learning_rate": 0.000302586336095232,
+      "loss": 0.1711,
+      "step": 45500
+    },
+    {
+      "epoch": 2.954589247864346,
+      "grad_norm": 0.652157723903656,
+      "learning_rate": 0.0003015158327445565,
+      "loss": 0.1698,
+      "step": 46000
+    },
+    {
+      "epoch": 2.9867043483846105,
+      "grad_norm": 0.8606679439544678,
+      "learning_rate": 0.00030044532939388103,
+      "loss": 0.168,
+      "step": 46500
+    },
+    {
+      "epoch": 3.0001926906031215,
+      "eval_loss": 0.17218953371047974,
+      "eval_runtime": 16.1357,
+      "eval_samples_per_second": 30.987,
+      "eval_steps_per_second": 3.904,
+      "step": 46710
+    },
+    {
+      "epoch": 3.018819448904875,
+      "grad_norm": 0.5109479427337646,
+      "learning_rate": 0.0002993748260432055,
+      "loss": 0.1477,
+      "step": 47000
+    },
+    {
+      "epoch": 3.05093454942514,
+      "grad_norm": 0.9119648337364197,
+      "learning_rate": 0.00029830432269253003,
+      "loss": 0.1498,
+      "step": 47500
+    },
+    {
+      "epoch": 3.0830496499454045,
+      "grad_norm": 0.5713444948196411,
+      "learning_rate": 0.00029723381934185455,
+      "loss": 0.1465,
+      "step": 48000
+    },
+    {
+      "epoch": 3.1151647504656688,
+      "grad_norm": 0.8740578293800354,
+      "learning_rate": 0.0002961633159911791,
+      "loss": 0.1487,
+      "step": 48500
+    },
+    {
+      "epoch": 3.1472798509859334,
+      "grad_norm": 0.7460174560546875,
+      "learning_rate": 0.00029509281264050355,
+      "loss": 0.1533,
+      "step": 49000
+    },
+    {
+      "epoch": 3.179394951506198,
+      "grad_norm": 0.6636391878128052,
+      "learning_rate": 0.0002940223092898281,
+      "loss": 0.1564,
+      "step": 49500
+    },
+    {
+      "epoch": 3.2002055366433297,
+      "eval_loss": 0.1716606765985489,
+      "eval_runtime": 16.0717,
+      "eval_samples_per_second": 31.111,
+      "eval_steps_per_second": 3.92,
+      "step": 49824
+    },
+    {
+      "epoch": 3.211510052026463,
+      "grad_norm": 0.7573930621147156,
+      "learning_rate": 0.0002929518059391526,
+      "loss": 0.1528,
+      "step": 50000
+    },
+    {
+      "epoch": 3.2436251525467275,
+      "grad_norm": 0.7488681077957153,
+      "learning_rate": 0.0002918813025884771,
+      "loss": 0.1522,
+      "step": 50500
+    },
+    {
+      "epoch": 3.275740253066992,
+      "grad_norm": 0.7012600302696228,
+      "learning_rate": 0.0002908107992378016,
+      "loss": 0.155,
+      "step": 51000
+    },
+    {
+      "epoch": 3.307855353587257,
+      "grad_norm": 1.240614891052246,
+      "learning_rate": 0.00028974029588712613,
+      "loss": 0.1567,
+      "step": 51500
+    },
+    {
+      "epoch": 3.3399704541075215,
+      "grad_norm": 1.2059004306793213,
+      "learning_rate": 0.0002886697925364506,
+      "loss": 0.1544,
+      "step": 52000
+    },
+    {
+      "epoch": 3.372085554627786,
+      "grad_norm": 0.9451314806938171,
+      "learning_rate": 0.00028759928918577513,
+      "loss": 0.156,
+      "step": 52500
+    },
+    {
+      "epoch": 3.400218382683538,
+      "eval_loss": 0.16954921185970306,
+      "eval_runtime": 15.8327,
+      "eval_samples_per_second": 31.58,
+      "eval_steps_per_second": 3.979,
+      "step": 52938
+    },
+    {
+      "epoch": 3.404200655148051,
+      "grad_norm": 0.8606504797935486,
+      "learning_rate": 0.00028652878583509966,
+      "loss": 0.1577,
+      "step": 53000
+    },
+    {
+      "epoch": 3.436315755668315,
+      "grad_norm": 0.8004255294799805,
+      "learning_rate": 0.0002854582824844242,
+      "loss": 0.1568,
+      "step": 53500
+    },
+    {
+      "epoch": 3.4684308561885797,
+      "grad_norm": 1.1171952486038208,
+      "learning_rate": 0.0002843877791337487,
+      "loss": 0.1583,
+      "step": 54000
+    },
+    {
+      "epoch": 3.5005459567088444,
+      "grad_norm": 0.7299367785453796,
+      "learning_rate": 0.00028331727578307324,
+      "loss": 0.1594,
+      "step": 54500
+    },
+    {
+      "epoch": 3.532661057229109,
+      "grad_norm": 1.0551788806915283,
+      "learning_rate": 0.00028224677243239777,
+      "loss": 0.1578,
+      "step": 55000
+    },
+    {
+      "epoch": 3.5647761577493737,
+      "grad_norm": 0.7545414566993713,
+      "learning_rate": 0.00028117626908172224,
+      "loss": 0.1571,
+      "step": 55500
+    },
+    {
+      "epoch": 3.5968912582696384,
+      "grad_norm": 0.9115778803825378,
+      "learning_rate": 0.00028010576573104677,
+      "loss": 0.154,
+      "step": 56000
+    },
+    {
+      "epoch": 3.6002312287237457,
+      "eval_loss": 0.16733905673027039,
+      "eval_runtime": 15.7815,
+      "eval_samples_per_second": 31.683,
+      "eval_steps_per_second": 3.992,
+      "step": 56052
+    },
+    {
+      "epoch": 3.629006358789903,
+      "grad_norm": 0.6606740951538086,
+      "learning_rate": 0.0002790352623803713,
+      "loss": 0.1564,
+      "step": 56500
+    },
+    {
+      "epoch": 3.6611214593101677,
+      "grad_norm": 0.8278652429580688,
+      "learning_rate": 0.00027796475902969577,
+      "loss": 0.1551,
+      "step": 57000
+    },
+    {
+      "epoch": 3.6932365598304324,
+      "grad_norm": 0.7000519633293152,
+      "learning_rate": 0.0002768942556790203,
+      "loss": 0.1552,
+      "step": 57500
+    },
+    {
+      "epoch": 3.7253516603506966,
+      "grad_norm": 0.7368202805519104,
+      "learning_rate": 0.0002758237523283448,
+      "loss": 0.157,
+      "step": 58000
+    },
+    {
+      "epoch": 3.7574667608709618,
+      "grad_norm": 0.7182698845863342,
+      "learning_rate": 0.0002747532489776693,
+      "loss": 0.1535,
+      "step": 58500
+    },
+    {
+      "epoch": 3.789581861391226,
+      "grad_norm": 0.9096634387969971,
+      "learning_rate": 0.0002736827456269938,
+      "loss": 0.1538,
+      "step": 59000
+    },
+    {
+      "epoch": 3.800244074763954,
+      "eval_loss": 0.16655243933200836,
+      "eval_runtime": 15.8093,
+      "eval_samples_per_second": 31.627,
+      "eval_steps_per_second": 3.985,
+      "step": 59166
+    },
+    {
+      "epoch": 3.8216969619114907,
+      "grad_norm": 0.7491119503974915,
+      "learning_rate": 0.00027261224227631835,
+      "loss": 0.1563,
+      "step": 59500
+    },
+    {
+      "epoch": 3.8538120624317553,
+      "grad_norm": 0.6401111483573914,
+      "learning_rate": 0.0002715417389256429,
+      "loss": 0.152,
+      "step": 60000
+    },
+    {
+      "epoch": 3.88592716295202,
+      "grad_norm": 0.6719266772270203,
+      "learning_rate": 0.00027047123557496735,
+      "loss": 0.1551,
+      "step": 60500
+    },
+    {
+      "epoch": 3.9180422634722847,
+      "grad_norm": 0.5323716402053833,
+      "learning_rate": 0.0002694007322242919,
+      "loss": 0.1545,
+      "step": 61000
+    },
+    {
+      "epoch": 3.9501573639925494,
+      "grad_norm": 0.4854276180267334,
+      "learning_rate": 0.0002683302288736164,
+      "loss": 0.1572,
+      "step": 61500
+    },
+    {
+      "epoch": 3.982272464512814,
+      "grad_norm": 0.5417631268501282,
+      "learning_rate": 0.0002672597255229409,
+      "loss": 0.1539,
+      "step": 62000
+    },
+    {
+      "epoch": 4.000256920804162,
+      "eval_loss": 0.165705144405365,
+      "eval_runtime": 15.8383,
+      "eval_samples_per_second": 31.569,
+      "eval_steps_per_second": 3.978,
+      "step": 62280
+    },
+    {
+      "epoch": 4.014387565033078,
+      "grad_norm": 0.7811856269836426,
+      "learning_rate": 0.0002661892221722654,
+      "loss": 0.1475,
+      "step": 62500
+    },
+    {
+      "epoch": 4.046502665553343,
+      "grad_norm": 0.7467861175537109,
+      "learning_rate": 0.00026511871882158993,
+      "loss": 0.1333,
+      "step": 63000
+    },
+    {
+      "epoch": 4.078617766073608,
+      "grad_norm": 1.106714129447937,
+      "learning_rate": 0.0002640482154709144,
+      "loss": 0.1361,
+      "step": 63500
+    },
+    {
+      "epoch": 4.110732866593873,
+      "grad_norm": 0.7650594115257263,
+      "learning_rate": 0.00026297771212023893,
+      "loss": 0.1437,
+      "step": 64000
+    },
+    {
+      "epoch": 4.142847967114137,
+      "grad_norm": 0.5561996698379517,
+      "learning_rate": 0.00026190720876956346,
+      "loss": 0.1385,
+      "step": 64500
+    },
+    {
+      "epoch": 4.174963067634402,
+      "grad_norm": 0.8409940004348755,
+      "learning_rate": 0.000260836705418888,
+      "loss": 0.1388,
+      "step": 65000
+    },
+    {
+      "epoch": 4.20026976684437,
+      "eval_loss": 0.16242507100105286,
+      "eval_runtime": 15.9549,
+      "eval_samples_per_second": 31.338,
+      "eval_steps_per_second": 3.949,
+      "step": 65394
+    },
+    {
+      "epoch": 4.207078168154666,
+      "grad_norm": 0.6058255434036255,
+      "learning_rate": 0.00025976620206821246,
+      "loss": 0.1402,
+      "step": 65500
+    },
+    {
+      "epoch": 4.239193268674931,
+      "grad_norm": 0.8761014938354492,
+      "learning_rate": 0.000258695698717537,
+      "loss": 0.1381,
+      "step": 66000
+    },
+    {
+      "epoch": 4.271308369195196,
+      "grad_norm": 0.6440082788467407,
+      "learning_rate": 0.0002576251953668615,
+      "loss": 0.1405,
+      "step": 66500
+    },
+    {
+      "epoch": 4.30342346971546,
+      "grad_norm": 0.8914796710014343,
+      "learning_rate": 0.000256554692016186,
+      "loss": 0.1395,
+      "step": 67000
+    },
+    {
+      "epoch": 4.335538570235725,
+      "grad_norm": 0.7656377553939819,
+      "learning_rate": 0.0002554841886655105,
+      "loss": 0.1361,
+      "step": 67500
+    },
+    {
+      "epoch": 4.367653670755989,
+      "grad_norm": 0.7148778438568115,
+      "learning_rate": 0.00025441368531483504,
+      "loss": 0.1448,
+      "step": 68000
+    },
+    {
+      "epoch": 4.399768771276254,
+      "grad_norm": 1.0374408960342407,
+      "learning_rate": 0.00025334318196415956,
+      "loss": 0.1406,
+      "step": 68500
+    },
+    {
+      "epoch": 4.4002826128845784,
+      "eval_loss": 0.16343337297439575,
+      "eval_runtime": 15.842,
+      "eval_samples_per_second": 31.562,
+      "eval_steps_per_second": 3.977,
+      "step": 68508
+    },
+    {
+      "epoch": 4.4318838717965185,
+      "grad_norm": 0.6319938898086548,
+      "learning_rate": 0.0002522726786134841,
+      "loss": 0.1419,
+      "step": 69000
+    },
+    {
+      "epoch": 4.463998972316784,
+      "grad_norm": 0.6749518513679504,
+      "learning_rate": 0.0002512021752628086,
+      "loss": 0.1418,
+      "step": 69500
+    },
+    {
+      "epoch": 4.496114072837048,
+      "grad_norm": 1.1089214086532593,
+      "learning_rate": 0.0002501316719121331,
+      "loss": 0.1403,
+      "step": 70000
+    },
+    {
+      "epoch": 4.528229173357312,
+      "grad_norm": 0.8678436279296875,
+      "learning_rate": 0.0002490611685614576,
+      "loss": 0.1416,
+      "step": 70500
+    },
+    {
+      "epoch": 4.560344273877577,
+      "grad_norm": 0.80596923828125,
+      "learning_rate": 0.00024799066521078214,
+      "loss": 0.1404,
+      "step": 71000
+    },
+    {
+      "epoch": 4.592459374397842,
+      "grad_norm": 0.6812764406204224,
+      "learning_rate": 0.00024692016186010667,
+      "loss": 0.1379,
+      "step": 71500
+    },
+    {
+      "epoch": 4.600295458924786,
+      "eval_loss": 0.15734289586544037,
+      "eval_runtime": 15.806,
+      "eval_samples_per_second": 31.634,
+      "eval_steps_per_second": 3.986,
+      "step": 71622
+    },
+    {
+      "epoch": 4.624574474918107,
+      "grad_norm": 0.6708959341049194,
+      "learning_rate": 0.00024584965850943114,
+      "loss": 0.1421,
+      "step": 72000
+    },
+    {
+      "epoch": 4.656689575438371,
+      "grad_norm": 0.5451516509056091,
+      "learning_rate": 0.00024477915515875567,
+      "loss": 0.1409,
+      "step": 72500
+    },
+    {
+      "epoch": 4.688804675958636,
+      "grad_norm": 0.7876731753349304,
+      "learning_rate": 0.00024370865180808017,
+      "loss": 0.14,
+      "step": 73000
+    },
+    {
+      "epoch": 4.7209197764789,
+      "grad_norm": 0.6321316361427307,
+      "learning_rate": 0.0002426381484574047,
+      "loss": 0.138,
+      "step": 73500
+    },
+    {
+      "epoch": 4.753034876999165,
+      "grad_norm": 0.813981294631958,
+      "learning_rate": 0.0002415676451067292,
+      "loss": 0.1405,
+      "step": 74000
+    },
+    {
+      "epoch": 4.7851499775194295,
+      "grad_norm": 0.8753657341003418,
+      "learning_rate": 0.00024049714175605373,
+      "loss": 0.1407,
+      "step": 74500
+    },
+    {
+      "epoch": 4.800308304964995,
+      "eval_loss": 0.15800152719020844,
+      "eval_runtime": 15.8284,
+      "eval_samples_per_second": 31.589,
+      "eval_steps_per_second": 3.98,
+      "step": 74736
+    },
+    {
+      "epoch": 4.817265078039695,
+      "grad_norm": 0.784956693649292,
+      "learning_rate": 0.00023942663840537822,
+      "loss": 0.1398,
+      "step": 75000
+    },
+    {
+      "epoch": 4.849380178559959,
+      "grad_norm": 0.6395303010940552,
+      "learning_rate": 0.00023835613505470272,
+      "loss": 0.1368,
+      "step": 75500
+    },
+    {
+      "epoch": 4.881495279080223,
+      "grad_norm": 0.9165125489234924,
+      "learning_rate": 0.00023728563170402725,
+      "loss": 0.1398,
+      "step": 76000
+    },
+    {
+      "epoch": 4.913610379600488,
+      "grad_norm": 0.5325254797935486,
+      "learning_rate": 0.00023621512835335175,
+      "loss": 0.1432,
+      "step": 76500
+    },
+    {
+      "epoch": 4.945725480120752,
+      "grad_norm": 0.7633726000785828,
+      "learning_rate": 0.00023514462500267628,
+      "loss": 0.1412,
+      "step": 77000
+    },
+    {
+      "epoch": 4.9778405806410175,
+      "grad_norm": 0.8984594345092773,
+      "learning_rate": 0.00023407412165200078,
+      "loss": 0.1395,
+      "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": 1.7918804069460214e+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 sha256:73088d518ee530775134be6328391a2166a39681fc7ec212f67176c071d6067e
+size 5969