Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+base_model: ibm-granite/granite-3.0-8b-instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.2

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-3.0-8b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a09f72564127e675a61ec7d58c2b23ee0225211e1d406d4e469fe6bd74a8dc1
+size 34100216

checkpoint-200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: ibm-granite/granite-3.0-8b-instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.2

checkpoint-200/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-3.0-8b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a09f72564127e675a61ec7d58c2b23ee0225211e1d406d4e469fe6bd74a8dc1
+size 34100216

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:442b87a1767f1aa22edbdbe9e6f4ca2c59b5587a8346c755af8d0ae24e68f1ba
+size 68292346

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6db1565fdf085bc8560b9b4bdd5f55abb40db42feac17284b294419663599c75
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a39755222377151208b988e4341f8c8d9958c119c2f9cf7ee718109a8d7880b
+size 1064

checkpoint-200/trainer_state.json

@@ -0,0 +1,1433 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.15891934843067143,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0007945967421533572,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 2.9992,
+      "step": 1
+    },
+    {
+      "epoch": 0.0015891934843067143,
+      "grad_norm": 2.3542397022247314,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.4211,
+      "step": 2
+    },
+    {
+      "epoch": 0.0023837902264600714,
+      "grad_norm": 1.7234137058258057,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.4802,
+      "step": 3
+    },
+    {
+      "epoch": 0.0031783869686134287,
+      "grad_norm": 1.8402104377746582,
+      "learning_rate": 6e-06,
+      "loss": 2.5004,
+      "step": 4
+    },
+    {
+      "epoch": 0.003972983710766786,
+      "grad_norm": 1.9447062015533447,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.5601,
+      "step": 5
+    },
+    {
+      "epoch": 0.004767580452920143,
+      "grad_norm": 1.6480785608291626,
+      "learning_rate": 1e-05,
+      "loss": 2.3849,
+      "step": 6
+    },
+    {
+      "epoch": 0.0055621771950735005,
+      "grad_norm": 8.942625999450684,
+      "learning_rate": 1.2e-05,
+      "loss": 2.9789,
+      "step": 7
+    },
+    {
+      "epoch": 0.006356773937226857,
+      "grad_norm": 4.155797958374023,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 2.6198,
+      "step": 8
+    },
+    {
+      "epoch": 0.007151370679380214,
+      "grad_norm": 1.6816856861114502,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.4154,
+      "step": 9
+    },
+    {
+      "epoch": 0.007945967421533572,
+      "grad_norm": 2.22641921043396,
+      "learning_rate": 1.8e-05,
+      "loss": 2.5419,
+      "step": 10
+    },
+    {
+      "epoch": 0.00874056416368693,
+      "grad_norm": 8.44351577758789,
+      "learning_rate": 2e-05,
+      "loss": 2.2415,
+      "step": 11
+    },
+    {
+      "epoch": 0.009535160905840286,
+      "grad_norm": 1.797033667564392,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 2.4743,
+      "step": 12
+    },
+    {
+      "epoch": 0.010329757647993643,
+      "grad_norm": 2.222118616104126,
+      "learning_rate": 2.4e-05,
+      "loss": 2.3,
+      "step": 13
+    },
+    {
+      "epoch": 0.011124354390147001,
+      "grad_norm": 2.0043039321899414,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 2.1184,
+      "step": 14
+    },
+    {
+      "epoch": 0.011918951132300357,
+      "grad_norm": 2.0246055126190186,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 2.159,
+      "step": 15
+    },
+    {
+      "epoch": 0.012713547874453715,
+      "grad_norm": 9.5096435546875,
+      "learning_rate": 3e-05,
+      "loss": 3.0276,
+      "step": 16
+    },
+    {
+      "epoch": 0.013508144616607072,
+      "grad_norm": 2.858501672744751,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 2.4969,
+      "step": 17
+    },
+    {
+      "epoch": 0.014302741358760428,
+      "grad_norm": 10.519010543823242,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 2.9221,
+      "step": 18
+    },
+    {
+      "epoch": 0.015097338100913786,
+      "grad_norm": 2.304163932800293,
+      "learning_rate": 3.6e-05,
+      "loss": 2.4857,
+      "step": 19
+    },
+    {
+      "epoch": 0.015891934843067144,
+      "grad_norm": 2.059422731399536,
+      "learning_rate": 3.8e-05,
+      "loss": 2.2824,
+      "step": 20
+    },
+    {
+      "epoch": 0.0166865315852205,
+      "grad_norm": 2.584183692932129,
+      "learning_rate": 4e-05,
+      "loss": 2.2176,
+      "step": 21
+    },
+    {
+      "epoch": 0.01748112832737386,
+      "grad_norm": 3.7771871089935303,
+      "learning_rate": 4.2e-05,
+      "loss": 2.9221,
+      "step": 22
+    },
+    {
+      "epoch": 0.018275725069527213,
+      "grad_norm": 1.889650583267212,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 2.3082,
+      "step": 23
+    },
+    {
+      "epoch": 0.01907032181168057,
+      "grad_norm": 3.319291353225708,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 2.19,
+      "step": 24
+    },
+    {
+      "epoch": 0.01986491855383393,
+      "grad_norm": 4.1281352043151855,
+      "learning_rate": 4.8e-05,
+      "loss": 2.1096,
+      "step": 25
+    },
+    {
+      "epoch": 0.020659515295987287,
+      "grad_norm": 2.4024288654327393,
+      "learning_rate": 5e-05,
+      "loss": 2.208,
+      "step": 26
+    },
+    {
+      "epoch": 0.021454112038140644,
+      "grad_norm": 15.567670822143555,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 2.4704,
+      "step": 27
+    },
+    {
+      "epoch": 0.022248708780294002,
+      "grad_norm": 2.64872145652771,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 2.1112,
+      "step": 28
+    },
+    {
+      "epoch": 0.023043305522447356,
+      "grad_norm": 6.033721446990967,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 2.7668,
+      "step": 29
+    },
+    {
+      "epoch": 0.023837902264600714,
+      "grad_norm": 2.7915563583374023,
+      "learning_rate": 5.8e-05,
+      "loss": 2.1103,
+      "step": 30
+    },
+    {
+      "epoch": 0.02463249900675407,
+      "grad_norm": 2.611234664916992,
+      "learning_rate": 6e-05,
+      "loss": 2.038,
+      "step": 31
+    },
+    {
+      "epoch": 0.02542709574890743,
+      "grad_norm": 2.3000996112823486,
+      "learning_rate": 6.2e-05,
+      "loss": 1.6268,
+      "step": 32
+    },
+    {
+      "epoch": 0.026221692491060787,
+      "grad_norm": 3.713061571121216,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 1.9121,
+      "step": 33
+    },
+    {
+      "epoch": 0.027016289233214145,
+      "grad_norm": 2.776019811630249,
+      "learning_rate": 6.6e-05,
+      "loss": 1.817,
+      "step": 34
+    },
+    {
+      "epoch": 0.027810885975367503,
+      "grad_norm": 2.564723491668701,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 1.9355,
+      "step": 35
+    },
+    {
+      "epoch": 0.028605482717520857,
+      "grad_norm": 6.116189002990723,
+      "learning_rate": 7e-05,
+      "loss": 1.7766,
+      "step": 36
+    },
+    {
+      "epoch": 0.029400079459674214,
+      "grad_norm": 2.6253204345703125,
+      "learning_rate": 7.2e-05,
+      "loss": 1.7565,
+      "step": 37
+    },
+    {
+      "epoch": 0.030194676201827572,
+      "grad_norm": 2.706721544265747,
+      "learning_rate": 7.4e-05,
+      "loss": 1.9456,
+      "step": 38
+    },
+    {
+      "epoch": 0.03098927294398093,
+      "grad_norm": 2.7343411445617676,
+      "learning_rate": 7.6e-05,
+      "loss": 1.6768,
+      "step": 39
+    },
+    {
+      "epoch": 0.03178386968613429,
+      "grad_norm": 2.1730287075042725,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 1.4658,
+      "step": 40
+    },
+    {
+      "epoch": 0.03257846642828764,
+      "grad_norm": 2.681889295578003,
+      "learning_rate": 8e-05,
+      "loss": 1.5583,
+      "step": 41
+    },
+    {
+      "epoch": 0.033373063170441,
+      "grad_norm": 2.6841020584106445,
+      "learning_rate": 8.2e-05,
+      "loss": 1.6734,
+      "step": 42
+    },
+    {
+      "epoch": 0.03416765991259436,
+      "grad_norm": 3.1267893314361572,
+      "learning_rate": 8.4e-05,
+      "loss": 1.6114,
+      "step": 43
+    },
+    {
+      "epoch": 0.03496225665474772,
+      "grad_norm": 3.066925525665283,
+      "learning_rate": 8.6e-05,
+      "loss": 1.558,
+      "step": 44
+    },
+    {
+      "epoch": 0.03575685339690107,
+      "grad_norm": 2.6647801399230957,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 1.4592,
+      "step": 45
+    },
+    {
+      "epoch": 0.03655145013905443,
+      "grad_norm": 2.6715352535247803,
+      "learning_rate": 9e-05,
+      "loss": 1.4846,
+      "step": 46
+    },
+    {
+      "epoch": 0.03734604688120779,
+      "grad_norm": 8.9569091796875,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 1.7494,
+      "step": 47
+    },
+    {
+      "epoch": 0.03814064362336114,
+      "grad_norm": 2.7488503456115723,
+      "learning_rate": 9.4e-05,
+      "loss": 1.2653,
+      "step": 48
+    },
+    {
+      "epoch": 0.038935240365514504,
+      "grad_norm": 2.520211696624756,
+      "learning_rate": 9.6e-05,
+      "loss": 1.2965,
+      "step": 49
+    },
+    {
+      "epoch": 0.03972983710766786,
+      "grad_norm": 2.678025960922241,
+      "learning_rate": 9.8e-05,
+      "loss": 1.199,
+      "step": 50
+    },
+    {
+      "epoch": 0.04052443384982122,
+      "grad_norm": 2.6799986362457275,
+      "learning_rate": 0.0001,
+      "loss": 1.2672,
+      "step": 51
+    },
+    {
+      "epoch": 0.04131903059197457,
+      "grad_norm": 2.907582998275757,
+      "learning_rate": 0.00010200000000000001,
+      "loss": 1.3114,
+      "step": 52
+    },
+    {
+      "epoch": 0.04211362733412793,
+      "grad_norm": 2.7622241973876953,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 1.2173,
+      "step": 53
+    },
+    {
+      "epoch": 0.04290822407628129,
+      "grad_norm": 3.829127550125122,
+      "learning_rate": 0.00010600000000000002,
+      "loss": 1.2657,
+      "step": 54
+    },
+    {
+      "epoch": 0.04370282081843464,
+      "grad_norm": 4.464277267456055,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 1.3206,
+      "step": 55
+    },
+    {
+      "epoch": 0.044497417560588004,
+      "grad_norm": 2.5400142669677734,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 1.1097,
+      "step": 56
+    },
+    {
+      "epoch": 0.04529201430274136,
+      "grad_norm": 2.6496193408966064,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 1.097,
+      "step": 57
+    },
+    {
+      "epoch": 0.04608661104489471,
+      "grad_norm": 4.215746879577637,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 1.1642,
+      "step": 58
+    },
+    {
+      "epoch": 0.046881207787048074,
+      "grad_norm": 2.93621826171875,
+      "learning_rate": 0.000116,
+      "loss": 1.2385,
+      "step": 59
+    },
+    {
+      "epoch": 0.04767580452920143,
+      "grad_norm": 10.44421672821045,
+      "learning_rate": 0.000118,
+      "loss": 1.1682,
+      "step": 60
+    },
+    {
+      "epoch": 0.04847040127135479,
+      "grad_norm": 3.617307424545288,
+      "learning_rate": 0.00012,
+      "loss": 1.3271,
+      "step": 61
+    },
+    {
+      "epoch": 0.04926499801350814,
+      "grad_norm": 2.5892326831817627,
+      "learning_rate": 0.000122,
+      "loss": 0.9714,
+      "step": 62
+    },
+    {
+      "epoch": 0.050059594755661505,
+      "grad_norm": NaN,
+      "learning_rate": 0.000122,
+      "loss": 1.2764,
+      "step": 63
+    },
+    {
+      "epoch": 0.05085419149781486,
+      "grad_norm": 2.9196863174438477,
+      "learning_rate": 0.000124,
+      "loss": 1.1406,
+      "step": 64
+    },
+    {
+      "epoch": 0.05164878823996821,
+      "grad_norm": 4.006603717803955,
+      "learning_rate": 0.000126,
+      "loss": 0.9797,
+      "step": 65
+    },
+    {
+      "epoch": 0.052443384982121574,
+      "grad_norm": 2.5575106143951416,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 1.2092,
+      "step": 66
+    },
+    {
+      "epoch": 0.05323798172427493,
+      "grad_norm": 3.1613786220550537,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 1.2598,
+      "step": 67
+    },
+    {
+      "epoch": 0.05403257846642829,
+      "grad_norm": 2.542789936065674,
+      "learning_rate": 0.000132,
+      "loss": 0.9497,
+      "step": 68
+    },
+    {
+      "epoch": 0.054827175208581644,
+      "grad_norm": 2.4051780700683594,
+      "learning_rate": 0.000134,
+      "loss": 0.7992,
+      "step": 69
+    },
+    {
+      "epoch": 0.055621771950735005,
+      "grad_norm": 51.893409729003906,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.9683,
+      "step": 70
+    },
+    {
+      "epoch": 0.05641636869288836,
+      "grad_norm": 4.105207920074463,
+      "learning_rate": 0.000138,
+      "loss": 1.0815,
+      "step": 71
+    },
+    {
+      "epoch": 0.057210965435041714,
+      "grad_norm": 92.10639190673828,
+      "learning_rate": 0.00014,
+      "loss": 1.1767,
+      "step": 72
+    },
+    {
+      "epoch": 0.058005562177195075,
+      "grad_norm": 2.4499878883361816,
+      "learning_rate": 0.000142,
+      "loss": 0.8912,
+      "step": 73
+    },
+    {
+      "epoch": 0.05880015891934843,
+      "grad_norm": 2.4928042888641357,
+      "learning_rate": 0.000144,
+      "loss": 0.9457,
+      "step": 74
+    },
+    {
+      "epoch": 0.05959475566150179,
+      "grad_norm": 2.761523485183716,
+      "learning_rate": 0.000146,
+      "loss": 0.9493,
+      "step": 75
+    },
+    {
+      "epoch": 0.060389352403655144,
+      "grad_norm": 2.9320006370544434,
+      "learning_rate": 0.000148,
+      "loss": 0.9657,
+      "step": 76
+    },
+    {
+      "epoch": 0.061183949145808506,
+      "grad_norm": 2.067227840423584,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.8115,
+      "step": 77
+    },
+    {
+      "epoch": 0.06197854588796186,
+      "grad_norm": 78.78492736816406,
+      "learning_rate": 0.000152,
+      "loss": 1.4676,
+      "step": 78
+    },
+    {
+      "epoch": 0.06277314263011521,
+      "grad_norm": 2.335451364517212,
+      "learning_rate": 0.000154,
+      "loss": 0.9271,
+      "step": 79
+    },
+    {
+      "epoch": 0.06356773937226858,
+      "grad_norm": 3.434222459793091,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.8938,
+      "step": 80
+    },
+    {
+      "epoch": 0.06436233611442194,
+      "grad_norm": 2.38944673538208,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 0.9277,
+      "step": 81
+    },
+    {
+      "epoch": 0.06515693285657528,
+      "grad_norm": 2.960742712020874,
+      "learning_rate": 0.00016,
+      "loss": 1.1237,
+      "step": 82
+    },
+    {
+      "epoch": 0.06595152959872864,
+      "grad_norm": 2.1033873558044434,
+      "learning_rate": 0.000162,
+      "loss": 0.8095,
+      "step": 83
+    },
+    {
+      "epoch": 0.066746126340882,
+      "grad_norm": 2.611531972885132,
+      "learning_rate": 0.000164,
+      "loss": 0.927,
+      "step": 84
+    },
+    {
+      "epoch": 0.06754072308303535,
+      "grad_norm": 2.9163801670074463,
+      "learning_rate": 0.000166,
+      "loss": 0.8363,
+      "step": 85
+    },
+    {
+      "epoch": 0.06833531982518871,
+      "grad_norm": 2.6492106914520264,
+      "learning_rate": 0.000168,
+      "loss": 0.9831,
+      "step": 86
+    },
+    {
+      "epoch": 0.06912991656734208,
+      "grad_norm": 2.027588367462158,
+      "learning_rate": 0.00017,
+      "loss": 0.8676,
+      "step": 87
+    },
+    {
+      "epoch": 0.06992451330949544,
+      "grad_norm": 2.7688043117523193,
+      "learning_rate": 0.000172,
+      "loss": 1.1266,
+      "step": 88
+    },
+    {
+      "epoch": 0.07071911005164878,
+      "grad_norm": 2.4787685871124268,
+      "learning_rate": 0.000174,
+      "loss": 0.8832,
+      "step": 89
+    },
+    {
+      "epoch": 0.07151370679380215,
+      "grad_norm": 5.127519130706787,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 0.8945,
+      "step": 90
+    },
+    {
+      "epoch": 0.0723083035359555,
+      "grad_norm": 3.4531705379486084,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 1.1205,
+      "step": 91
+    },
+    {
+      "epoch": 0.07310290027810885,
+      "grad_norm": 2.749129056930542,
+      "learning_rate": 0.00018,
+      "loss": 1.019,
+      "step": 92
+    },
+    {
+      "epoch": 0.07389749702026222,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00018,
+      "loss": 1.3832,
+      "step": 93
+    },
+    {
+      "epoch": 0.07469209376241558,
+      "grad_norm": 2.6057441234588623,
+      "learning_rate": 0.000182,
+      "loss": 1.1318,
+      "step": 94
+    },
+    {
+      "epoch": 0.07548669050456894,
+      "grad_norm": 4.503351211547852,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 1.033,
+      "step": 95
+    },
+    {
+      "epoch": 0.07628128724672228,
+      "grad_norm": 2.7054409980773926,
+      "learning_rate": 0.00018600000000000002,
+      "loss": 0.9466,
+      "step": 96
+    },
+    {
+      "epoch": 0.07707588398887565,
+      "grad_norm": 2.1828339099884033,
+      "learning_rate": 0.000188,
+      "loss": 0.8253,
+      "step": 97
+    },
+    {
+      "epoch": 0.07787048073102901,
+      "grad_norm": 2.062911033630371,
+      "learning_rate": 0.00019,
+      "loss": 0.8997,
+      "step": 98
+    },
+    {
+      "epoch": 0.07866507747318235,
+      "grad_norm": 2.1747360229492188,
+      "learning_rate": 0.000192,
+      "loss": 0.928,
+      "step": 99
+    },
+    {
+      "epoch": 0.07945967421533572,
+      "grad_norm": 2.3616063594818115,
+      "learning_rate": 0.000194,
+      "loss": 0.8595,
+      "step": 100
+    },
+    {
+      "epoch": 0.08025427095748908,
+      "grad_norm": 2.007453203201294,
+      "learning_rate": 0.000196,
+      "loss": 0.9071,
+      "step": 101
+    },
+    {
+      "epoch": 0.08104886769964244,
+      "grad_norm": 2.822878837585449,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 1.1856,
+      "step": 102
+    },
+    {
+      "epoch": 0.08184346444179579,
+      "grad_norm": 2.162837505340576,
+      "learning_rate": 0.0002,
+      "loss": 1.0198,
+      "step": 103
+    },
+    {
+      "epoch": 0.08263806118394915,
+      "grad_norm": 2.004056453704834,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 0.8352,
+      "step": 104
+    },
+    {
+      "epoch": 0.08343265792610251,
+      "grad_norm": 2.5484063625335693,
+      "learning_rate": 0.000196,
+      "loss": 1.0226,
+      "step": 105
+    },
+    {
+      "epoch": 0.08422725466825585,
+      "grad_norm": 2.2759130001068115,
+      "learning_rate": 0.000194,
+      "loss": 0.8884,
+      "step": 106
+    },
+    {
+      "epoch": 0.08502185141040922,
+      "grad_norm": 2.4136946201324463,
+      "learning_rate": 0.000192,
+      "loss": 0.8374,
+      "step": 107
+    },
+    {
+      "epoch": 0.08581644815256258,
+      "grad_norm": 2.8566195964813232,
+      "learning_rate": 0.00019,
+      "loss": 0.9112,
+      "step": 108
+    },
+    {
+      "epoch": 0.08661104489471594,
+      "grad_norm": 2.241708755493164,
+      "learning_rate": 0.000188,
+      "loss": 0.8695,
+      "step": 109
+    },
+    {
+      "epoch": 0.08740564163686929,
+      "grad_norm": 2.1674909591674805,
+      "learning_rate": 0.00018600000000000002,
+      "loss": 0.708,
+      "step": 110
+    },
+    {
+      "epoch": 0.08820023837902265,
+      "grad_norm": 3.16097092628479,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 1.0946,
+      "step": 111
+    },
+    {
+      "epoch": 0.08899483512117601,
+      "grad_norm": 2.7531492710113525,
+      "learning_rate": 0.000182,
+      "loss": 0.8907,
+      "step": 112
+    },
+    {
+      "epoch": 0.08978943186332936,
+      "grad_norm": 2.3830761909484863,
+      "learning_rate": 0.00018,
+      "loss": 0.9243,
+      "step": 113
+    },
+    {
+      "epoch": 0.09058402860548272,
+      "grad_norm": 27.347421646118164,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 1.0328,
+      "step": 114
+    },
+    {
+      "epoch": 0.09137862534763608,
+      "grad_norm": 2.1043972969055176,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 0.9195,
+      "step": 115
+    },
+    {
+      "epoch": 0.09217322208978942,
+      "grad_norm": 1.9787133932113647,
+      "learning_rate": 0.000174,
+      "loss": 0.7395,
+      "step": 116
+    },
+    {
+      "epoch": 0.09296781883194279,
+      "grad_norm": 2.395308256149292,
+      "learning_rate": 0.000172,
+      "loss": 1.0193,
+      "step": 117
+    },
+    {
+      "epoch": 0.09376241557409615,
+      "grad_norm": 1.9864846467971802,
+      "learning_rate": 0.00017,
+      "loss": 0.948,
+      "step": 118
+    },
+    {
+      "epoch": 0.09455701231624951,
+      "grad_norm": 2.823315382003784,
+      "learning_rate": 0.000168,
+      "loss": 1.0902,
+      "step": 119
+    },
+    {
+      "epoch": 0.09535160905840286,
+      "grad_norm": 2.5823678970336914,
+      "learning_rate": 0.000166,
+      "loss": 1.0905,
+      "step": 120
+    },
+    {
+      "epoch": 0.09614620580055622,
+      "grad_norm": 1.8948626518249512,
+      "learning_rate": 0.000164,
+      "loss": 0.9203,
+      "step": 121
+    },
+    {
+      "epoch": 0.09694080254270958,
+      "grad_norm": 1.9721623659133911,
+      "learning_rate": 0.000162,
+      "loss": 0.9591,
+      "step": 122
+    },
+    {
+      "epoch": 0.09773539928486293,
+      "grad_norm": 1.9776030778884888,
+      "learning_rate": 0.00016,
+      "loss": 0.9887,
+      "step": 123
+    },
+    {
+      "epoch": 0.09852999602701629,
+      "grad_norm": 2.8131155967712402,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 1.0197,
+      "step": 124
+    },
+    {
+      "epoch": 0.09932459276916965,
+      "grad_norm": 2.0642547607421875,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.9931,
+      "step": 125
+    },
+    {
+      "epoch": 0.10011918951132301,
+      "grad_norm": 2.9410674571990967,
+      "learning_rate": 0.000154,
+      "loss": 1.3742,
+      "step": 126
+    },
+    {
+      "epoch": 0.10091378625347636,
+      "grad_norm": 2.1221704483032227,
+      "learning_rate": 0.000152,
+      "loss": 1.0526,
+      "step": 127
+    },
+    {
+      "epoch": 0.10170838299562972,
+      "grad_norm": 2.831902503967285,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.8048,
+      "step": 128
+    },
+    {
+      "epoch": 0.10250297973778308,
+      "grad_norm": 2.066681146621704,
+      "learning_rate": 0.000148,
+      "loss": 0.985,
+      "step": 129
+    },
+    {
+      "epoch": 0.10329757647993643,
+      "grad_norm": 1.8252568244934082,
+      "learning_rate": 0.000146,
+      "loss": 0.7689,
+      "step": 130
+    },
+    {
+      "epoch": 0.10409217322208979,
+      "grad_norm": 2.0231878757476807,
+      "learning_rate": 0.000144,
+      "loss": 1.0247,
+      "step": 131
+    },
+    {
+      "epoch": 0.10488676996424315,
+      "grad_norm": 2.200442314147949,
+      "learning_rate": 0.000142,
+      "loss": 0.8775,
+      "step": 132
+    },
+    {
+      "epoch": 0.10568136670639651,
+      "grad_norm": 1.7937211990356445,
+      "learning_rate": 0.00014,
+      "loss": 0.9357,
+      "step": 133
+    },
+    {
+      "epoch": 0.10647596344854986,
+      "grad_norm": 1.685763955116272,
+      "learning_rate": 0.000138,
+      "loss": 0.8664,
+      "step": 134
+    },
+    {
+      "epoch": 0.10727056019070322,
+      "grad_norm": 1.9033604860305786,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.9793,
+      "step": 135
+    },
+    {
+      "epoch": 0.10806515693285658,
+      "grad_norm": 1.8052781820297241,
+      "learning_rate": 0.000134,
+      "loss": 0.8154,
+      "step": 136
+    },
+    {
+      "epoch": 0.10885975367500993,
+      "grad_norm": 2.400908946990967,
+      "learning_rate": 0.000132,
+      "loss": 0.9604,
+      "step": 137
+    },
+    {
+      "epoch": 0.10965435041716329,
+      "grad_norm": 1.7619413137435913,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 0.8187,
+      "step": 138
+    },
+    {
+      "epoch": 0.11044894715931665,
+      "grad_norm": 1.8535854816436768,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 0.9487,
+      "step": 139
+    },
+    {
+      "epoch": 0.11124354390147001,
+      "grad_norm": 1.8936333656311035,
+      "learning_rate": 0.000126,
+      "loss": 0.9852,
+      "step": 140
+    },
+    {
+      "epoch": 0.11203814064362336,
+      "grad_norm": 1.821515440940857,
+      "learning_rate": 0.000124,
+      "loss": 0.8442,
+      "step": 141
+    },
+    {
+      "epoch": 0.11283273738577672,
+      "grad_norm": 2.1713123321533203,
+      "learning_rate": 0.000122,
+      "loss": 1.1723,
+      "step": 142
+    },
+    {
+      "epoch": 0.11362733412793008,
+      "grad_norm": 1.6912201642990112,
+      "learning_rate": 0.00012,
+      "loss": 0.7486,
+      "step": 143
+    },
+    {
+      "epoch": 0.11442193087008343,
+      "grad_norm": 1.630624532699585,
+      "learning_rate": 0.000118,
+      "loss": 0.7462,
+      "step": 144
+    },
+    {
+      "epoch": 0.11521652761223679,
+      "grad_norm": 2.0852651596069336,
+      "learning_rate": 0.000116,
+      "loss": 0.7821,
+      "step": 145
+    },
+    {
+      "epoch": 0.11601112435439015,
+      "grad_norm": 1.5113400220870972,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 0.7768,
+      "step": 146
+    },
+    {
+      "epoch": 0.11680572109654351,
+      "grad_norm": 1.9536205530166626,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 0.9478,
+      "step": 147
+    },
+    {
+      "epoch": 0.11760031783869686,
+      "grad_norm": 1.8963311910629272,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 0.9085,
+      "step": 148
+    },
+    {
+      "epoch": 0.11839491458085022,
+      "grad_norm": 1.8368561267852783,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 0.757,
+      "step": 149
+    },
+    {
+      "epoch": 0.11918951132300358,
+      "grad_norm": 2.7951648235321045,
+      "learning_rate": 0.00010600000000000002,
+      "loss": 1.0677,
+      "step": 150
+    },
+    {
+      "epoch": 0.11998410806515693,
+      "grad_norm": 2.015962839126587,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 0.7874,
+      "step": 151
+    },
+    {
+      "epoch": 0.12077870480731029,
+      "grad_norm": 2.661062479019165,
+      "learning_rate": 0.00010200000000000001,
+      "loss": 0.9311,
+      "step": 152
+    },
+    {
+      "epoch": 0.12157330154946365,
+      "grad_norm": 2.020232677459717,
+      "learning_rate": 0.0001,
+      "loss": 0.7958,
+      "step": 153
+    },
+    {
+      "epoch": 0.12236789829161701,
+      "grad_norm": 2.5150179862976074,
+      "learning_rate": 9.8e-05,
+      "loss": 0.8354,
+      "step": 154
+    },
+    {
+      "epoch": 0.12316249503377036,
+      "grad_norm": 1.65029776096344,
+      "learning_rate": 9.6e-05,
+      "loss": 0.8512,
+      "step": 155
+    },
+    {
+      "epoch": 0.12395709177592372,
+      "grad_norm": 2.004103183746338,
+      "learning_rate": 9.4e-05,
+      "loss": 0.7002,
+      "step": 156
+    },
+    {
+      "epoch": 0.12475168851807708,
+      "grad_norm": 2.198091506958008,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 0.8539,
+      "step": 157
+    },
+    {
+      "epoch": 0.12554628526023043,
+      "grad_norm": 2.1458988189697266,
+      "learning_rate": 9e-05,
+      "loss": 1.1292,
+      "step": 158
+    },
+    {
+      "epoch": 0.1263408820023838,
+      "grad_norm": 1.7759689092636108,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.8792,
+      "step": 159
+    },
+    {
+      "epoch": 0.12713547874453715,
+      "grad_norm": 2.0215320587158203,
+      "learning_rate": 8.6e-05,
+      "loss": 0.9206,
+      "step": 160
+    },
+    {
+      "epoch": 0.1279300754866905,
+      "grad_norm": 2.324572801589966,
+      "learning_rate": 8.4e-05,
+      "loss": 1.0041,
+      "step": 161
+    },
+    {
+      "epoch": 0.12872467222884387,
+      "grad_norm": 2.3949570655822754,
+      "learning_rate": 8.2e-05,
+      "loss": 0.7894,
+      "step": 162
+    },
+    {
+      "epoch": 0.12951926897099722,
+      "grad_norm": 1.8736156225204468,
+      "learning_rate": 8e-05,
+      "loss": 0.8928,
+      "step": 163
+    },
+    {
+      "epoch": 0.13031386571315057,
+      "grad_norm": 2.373562812805176,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 0.8739,
+      "step": 164
+    },
+    {
+      "epoch": 0.13110846245530394,
+      "grad_norm": 1.6126917600631714,
+      "learning_rate": 7.6e-05,
+      "loss": 0.6292,
+      "step": 165
+    },
+    {
+      "epoch": 0.1319030591974573,
+      "grad_norm": 2.6151697635650635,
+      "learning_rate": 7.4e-05,
+      "loss": 1.2176,
+      "step": 166
+    },
+    {
+      "epoch": 0.13269765593961064,
+      "grad_norm": 1.883436918258667,
+      "learning_rate": 7.2e-05,
+      "loss": 0.7664,
+      "step": 167
+    },
+    {
+      "epoch": 0.133492252681764,
+      "grad_norm": 2.2091007232666016,
+      "learning_rate": 7e-05,
+      "loss": 0.9501,
+      "step": 168
+    },
+    {
+      "epoch": 0.13428684942391736,
+      "grad_norm": 1.903889775276184,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 0.9322,
+      "step": 169
+    },
+    {
+      "epoch": 0.1350814461660707,
+      "grad_norm": 1.9040536880493164,
+      "learning_rate": 6.6e-05,
+      "loss": 0.851,
+      "step": 170
+    },
+    {
+      "epoch": 0.13587604290822408,
+      "grad_norm": 1.7239336967468262,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.9033,
+      "step": 171
+    },
+    {
+      "epoch": 0.13667063965037743,
+      "grad_norm": 3.3629558086395264,
+      "learning_rate": 6.2e-05,
+      "loss": 0.918,
+      "step": 172
+    },
+    {
+      "epoch": 0.1374652363925308,
+      "grad_norm": 1.9918290376663208,
+      "learning_rate": 6e-05,
+      "loss": 0.8825,
+      "step": 173
+    },
+    {
+      "epoch": 0.13825983313468415,
+      "grad_norm": 2.3540871143341064,
+      "learning_rate": 5.8e-05,
+      "loss": 0.6484,
+      "step": 174
+    },
+    {
+      "epoch": 0.1390544298768375,
+      "grad_norm": 2.2806777954101562,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.7137,
+      "step": 175
+    },
+    {
+      "epoch": 0.13984902661899087,
+      "grad_norm": 2.21384334564209,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 0.5965,
+      "step": 176
+    },
+    {
+      "epoch": 0.14064362336114422,
+      "grad_norm": 1.9977487325668335,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 0.7671,
+      "step": 177
+    },
+    {
+      "epoch": 0.14143822010329757,
+      "grad_norm": 31.215999603271484,
+      "learning_rate": 5e-05,
+      "loss": 0.9116,
+      "step": 178
+    },
+    {
+      "epoch": 0.14223281684545094,
+      "grad_norm": 2.2257730960845947,
+      "learning_rate": 4.8e-05,
+      "loss": 0.8838,
+      "step": 179
+    },
+    {
+      "epoch": 0.1430274135876043,
+      "grad_norm": 2.9200854301452637,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.9615,
+      "step": 180
+    },
+    {
+      "epoch": 0.14382201032975764,
+      "grad_norm": 2.2704315185546875,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 1.0132,
+      "step": 181
+    },
+    {
+      "epoch": 0.144616607071911,
+      "grad_norm": 2.058189868927002,
+      "learning_rate": 4.2e-05,
+      "loss": 0.8201,
+      "step": 182
+    },
+    {
+      "epoch": 0.14541120381406436,
+      "grad_norm": 1.7903186082839966,
+      "learning_rate": 4e-05,
+      "loss": 0.7128,
+      "step": 183
+    },
+    {
+      "epoch": 0.1462058005562177,
+      "grad_norm": 1.9608381986618042,
+      "learning_rate": 3.8e-05,
+      "loss": 0.8236,
+      "step": 184
+    },
+    {
+      "epoch": 0.14700039729837108,
+      "grad_norm": 2.1937220096588135,
+      "learning_rate": 3.6e-05,
+      "loss": 0.8442,
+      "step": 185
+    },
+    {
+      "epoch": 0.14779499404052443,
+      "grad_norm": 2.047407627105713,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 0.966,
+      "step": 186
+    },
+    {
+      "epoch": 0.14858959078267778,
+      "grad_norm": 2.0216119289398193,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.9564,
+      "step": 187
+    },
+    {
+      "epoch": 0.14938418752483115,
+      "grad_norm": 1.629753589630127,
+      "learning_rate": 3e-05,
+      "loss": 0.6504,
+      "step": 188
+    },
+    {
+      "epoch": 0.1501787842669845,
+      "grad_norm": 1.7381154298782349,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.8346,
+      "step": 189
+    },
+    {
+      "epoch": 0.15097338100913787,
+      "grad_norm": 2.1300833225250244,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 0.8631,
+      "step": 190
+    },
+    {
+      "epoch": 0.15176797775129122,
+      "grad_norm": 1.8977206945419312,
+      "learning_rate": 2.4e-05,
+      "loss": 0.8653,
+      "step": 191
+    },
+    {
+      "epoch": 0.15256257449344457,
+      "grad_norm": 1.7362009286880493,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 0.8278,
+      "step": 192
+    },
+    {
+      "epoch": 0.15335717123559794,
+      "grad_norm": 1.838982105255127,
+      "learning_rate": 2e-05,
+      "loss": 0.6521,
+      "step": 193
+    },
+    {
+      "epoch": 0.1541517679777513,
+      "grad_norm": 2.4685189723968506,
+      "learning_rate": 1.8e-05,
+      "loss": 0.9639,
+      "step": 194
+    },
+    {
+      "epoch": 0.15494636471990464,
+      "grad_norm": 1.8960801362991333,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.7338,
+      "step": 195
+    },
+    {
+      "epoch": 0.15574096146205801,
+      "grad_norm": 2.139636993408203,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 0.6774,
+      "step": 196
+    },
+    {
+      "epoch": 0.15653555820421136,
+      "grad_norm": 2.0349552631378174,
+      "learning_rate": 1.2e-05,
+      "loss": 0.8435,
+      "step": 197
+    },
+    {
+      "epoch": 0.1573301549463647,
+      "grad_norm": 1.5157055854797363,
+      "learning_rate": 1e-05,
+      "loss": 0.7087,
+      "step": 198
+    },
+    {
+      "epoch": 0.15812475168851808,
+      "grad_norm": 2.498692035675049,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.0298,
+      "step": 199
+    },
+    {
+      "epoch": 0.15891934843067143,
+      "grad_norm": 1.7967320680618286,
+      "learning_rate": 6e-06,
+      "loss": 0.7717,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2473157095243776.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098cc62850a9422967145f5b3c4822dcaa7f739cabac8d97cbe7d3678e81010e
+size 5176

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098cc62850a9422967145f5b3c4822dcaa7f739cabac8d97cbe7d3678e81010e
+size 5176