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 sha256:6c58239a67307473e58bbc09292e8bf457bccbf3d8f093413f2a9983160f1373
+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 sha256:6c58239a67307473e58bbc09292e8bf457bccbf3d8f093413f2a9983160f1373
+size 34100216

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93a1f6aa5183962874fd62e0d358e0f0ea27e6a68a0535d07f990842e7013963
+size 68292346

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04745946c21cb6d9e7af44a9e436e4207c8437de1201d76c48a7771e0e0f3bad
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5fcb2e0acbfc451125ca5cd950e0420d092eee3eeb6dd5b682202b7a14cd22e
+size 1064

checkpoint-200/trainer_state.json

@@ -0,0 +1,1433 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.00485074853113271,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.4253742655663552e-05,
+      "grad_norm": 2.9237160682678223,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.4192,
+      "step": 1
+    },
+    {
+      "epoch": 4.8507485311327104e-05,
+      "grad_norm": 8.286487579345703,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.7523,
+      "step": 2
+    },
+    {
+      "epoch": 7.276122796699065e-05,
+      "grad_norm": 1.957672119140625,
+      "learning_rate": 6e-06,
+      "loss": 1.9875,
+      "step": 3
+    },
+    {
+      "epoch": 9.701497062265421e-05,
+      "grad_norm": 0.5736268758773804,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.427,
+      "step": 4
+    },
+    {
+      "epoch": 0.00012126871327831776,
+      "grad_norm": 0.7024741172790527,
+      "learning_rate": 1e-05,
+      "loss": 1.4541,
+      "step": 5
+    },
+    {
+      "epoch": 0.0001455224559339813,
+      "grad_norm": 6.171888828277588,
+      "learning_rate": 1.2e-05,
+      "loss": 1.9617,
+      "step": 6
+    },
+    {
+      "epoch": 0.00016977619858964487,
+      "grad_norm": 1.4335829019546509,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 1.6549,
+      "step": 7
+    },
+    {
+      "epoch": 0.00019402994124530841,
+      "grad_norm": 0.8052822947502136,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.681,
+      "step": 8
+    },
+    {
+      "epoch": 0.00021828368390097196,
+      "grad_norm": 1.0054032802581787,
+      "learning_rate": 1.8e-05,
+      "loss": 1.7113,
+      "step": 9
+    },
+    {
+      "epoch": 0.00024253742655663553,
+      "grad_norm": 2.378899097442627,
+      "learning_rate": 2e-05,
+      "loss": 2.0225,
+      "step": 10
+    },
+    {
+      "epoch": 0.00026679116921229907,
+      "grad_norm": 12.526110649108887,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 2.3219,
+      "step": 11
+    },
+    {
+      "epoch": 0.0002910449118679626,
+      "grad_norm": 1.658133864402771,
+      "learning_rate": 2.4e-05,
+      "loss": 1.5336,
+      "step": 12
+    },
+    {
+      "epoch": 0.00031529865452362615,
+      "grad_norm": 18.127710342407227,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 2.1609,
+      "step": 13
+    },
+    {
+      "epoch": 0.00033955239717928975,
+      "grad_norm": 0.7923838496208191,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 1.7354,
+      "step": 14
+    },
+    {
+      "epoch": 0.0003638061398349533,
+      "grad_norm": 1.6248362064361572,
+      "learning_rate": 3e-05,
+      "loss": 1.5774,
+      "step": 15
+    },
+    {
+      "epoch": 0.00038805988249061683,
+      "grad_norm": 1.6371029615402222,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 2.2978,
+      "step": 16
+    },
+    {
+      "epoch": 0.00041231362514628037,
+      "grad_norm": 1.409232497215271,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 1.1136,
+      "step": 17
+    },
+    {
+      "epoch": 0.0004365673678019439,
+      "grad_norm": 5.593843936920166,
+      "learning_rate": 3.6e-05,
+      "loss": 2.3497,
+      "step": 18
+    },
+    {
+      "epoch": 0.0004608211104576075,
+      "grad_norm": 1.9881709814071655,
+      "learning_rate": 3.8e-05,
+      "loss": 2.0849,
+      "step": 19
+    },
+    {
+      "epoch": 0.00048507485311327105,
+      "grad_norm": 1.7124191522598267,
+      "learning_rate": 4e-05,
+      "loss": 1.565,
+      "step": 20
+    },
+    {
+      "epoch": 0.0005093285957689346,
+      "grad_norm": 0.6472250819206238,
+      "learning_rate": 4.2e-05,
+      "loss": 1.0869,
+      "step": 21
+    },
+    {
+      "epoch": 0.0005335823384245981,
+      "grad_norm": 4.816655158996582,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 2.2343,
+      "step": 22
+    },
+    {
+      "epoch": 0.0005578360810802617,
+      "grad_norm": 1.3076063394546509,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.8767,
+      "step": 23
+    },
+    {
+      "epoch": 0.0005820898237359252,
+      "grad_norm": 1.0358009338378906,
+      "learning_rate": 4.8e-05,
+      "loss": 1.7001,
+      "step": 24
+    },
+    {
+      "epoch": 0.0006063435663915888,
+      "grad_norm": 0.8611243367195129,
+      "learning_rate": 5e-05,
+      "loss": 1.0703,
+      "step": 25
+    },
+    {
+      "epoch": 0.0006305973090472523,
+      "grad_norm": 1.8082849979400635,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 2.409,
+      "step": 26
+    },
+    {
+      "epoch": 0.000654851051702916,
+      "grad_norm": 2.4376935958862305,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 1.6188,
+      "step": 27
+    },
+    {
+      "epoch": 0.0006791047943585795,
+      "grad_norm": 1.7561759948730469,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 1.8782,
+      "step": 28
+    },
+    {
+      "epoch": 0.000703358537014243,
+      "grad_norm": 1.4189746379852295,
+      "learning_rate": 5.8e-05,
+      "loss": 2.1414,
+      "step": 29
+    },
+    {
+      "epoch": 0.0007276122796699066,
+      "grad_norm": 1.186546802520752,
+      "learning_rate": 6e-05,
+      "loss": 1.5557,
+      "step": 30
+    },
+    {
+      "epoch": 0.0007518660223255701,
+      "grad_norm": 1.365446925163269,
+      "learning_rate": 6.2e-05,
+      "loss": 1.9806,
+      "step": 31
+    },
+    {
+      "epoch": 0.0007761197649812337,
+      "grad_norm": 5.6013641357421875,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 2.836,
+      "step": 32
+    },
+    {
+      "epoch": 0.0008003735076368972,
+      "grad_norm": 1.5393822193145752,
+      "learning_rate": 6.6e-05,
+      "loss": 1.6833,
+      "step": 33
+    },
+    {
+      "epoch": 0.0008246272502925607,
+      "grad_norm": 1.7934705018997192,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 1.6762,
+      "step": 34
+    },
+    {
+      "epoch": 0.0008488809929482243,
+      "grad_norm": 1.1468597650527954,
+      "learning_rate": 7e-05,
+      "loss": 1.2819,
+      "step": 35
+    },
+    {
+      "epoch": 0.0008731347356038878,
+      "grad_norm": 4.899059772491455,
+      "learning_rate": 7.2e-05,
+      "loss": 1.7406,
+      "step": 36
+    },
+    {
+      "epoch": 0.0008973884782595515,
+      "grad_norm": 1.6008192300796509,
+      "learning_rate": 7.4e-05,
+      "loss": 1.5028,
+      "step": 37
+    },
+    {
+      "epoch": 0.000921642220915215,
+      "grad_norm": 3.4235761165618896,
+      "learning_rate": 7.6e-05,
+      "loss": 1.6816,
+      "step": 38
+    },
+    {
+      "epoch": 0.0009458959635708786,
+      "grad_norm": 1.1148329973220825,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 1.4805,
+      "step": 39
+    },
+    {
+      "epoch": 0.0009701497062265421,
+      "grad_norm": 4.683089733123779,
+      "learning_rate": 8e-05,
+      "loss": 1.9679,
+      "step": 40
+    },
+    {
+      "epoch": 0.0009944034488822055,
+      "grad_norm": 0.75764000415802,
+      "learning_rate": 8.2e-05,
+      "loss": 1.3406,
+      "step": 41
+    },
+    {
+      "epoch": 0.0010186571915378692,
+      "grad_norm": 1.3041810989379883,
+      "learning_rate": 8.4e-05,
+      "loss": 1.4009,
+      "step": 42
+    },
+    {
+      "epoch": 0.0010429109341935328,
+      "grad_norm": 1.4765511751174927,
+      "learning_rate": 8.6e-05,
+      "loss": 1.3446,
+      "step": 43
+    },
+    {
+      "epoch": 0.0010671646768491963,
+      "grad_norm": 3.716846227645874,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 2.1417,
+      "step": 44
+    },
+    {
+      "epoch": 0.00109141841950486,
+      "grad_norm": 1.0331724882125854,
+      "learning_rate": 9e-05,
+      "loss": 1.396,
+      "step": 45
+    },
+    {
+      "epoch": 0.0011156721621605234,
+      "grad_norm": 2.426039934158325,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 1.466,
+      "step": 46
+    },
+    {
+      "epoch": 0.001139925904816187,
+      "grad_norm": 1.3340977430343628,
+      "learning_rate": 9.4e-05,
+      "loss": 1.7891,
+      "step": 47
+    },
+    {
+      "epoch": 0.0011641796474718504,
+      "grad_norm": 3.5191874504089355,
+      "learning_rate": 9.6e-05,
+      "loss": 1.6633,
+      "step": 48
+    },
+    {
+      "epoch": 0.001188433390127514,
+      "grad_norm": 1.6775161027908325,
+      "learning_rate": 9.8e-05,
+      "loss": 1.4875,
+      "step": 49
+    },
+    {
+      "epoch": 0.0012126871327831775,
+      "grad_norm": 8.406580924987793,
+      "learning_rate": 0.0001,
+      "loss": 2.1048,
+      "step": 50
+    },
+    {
+      "epoch": 0.0012369408754388412,
+      "grad_norm": 6.012252330780029,
+      "learning_rate": 0.00010200000000000001,
+      "loss": 2.0742,
+      "step": 51
+    },
+    {
+      "epoch": 0.0012611946180945046,
+      "grad_norm": 12.059433937072754,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 1.843,
+      "step": 52
+    },
+    {
+      "epoch": 0.0012854483607501683,
+      "grad_norm": 1.3695584535598755,
+      "learning_rate": 0.00010600000000000002,
+      "loss": 1.8865,
+      "step": 53
+    },
+    {
+      "epoch": 0.001309702103405832,
+      "grad_norm": 2.331925630569458,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 1.8662,
+      "step": 54
+    },
+    {
+      "epoch": 0.0013339558460614953,
+      "grad_norm": 2.2023472785949707,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 1.3941,
+      "step": 55
+    },
+    {
+      "epoch": 0.001358209588717159,
+      "grad_norm": 1.971096396446228,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 1.9362,
+      "step": 56
+    },
+    {
+      "epoch": 0.0013824633313728224,
+      "grad_norm": 1.254345417022705,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 1.5581,
+      "step": 57
+    },
+    {
+      "epoch": 0.001406717074028486,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 1.5454,
+      "step": 58
+    },
+    {
+      "epoch": 0.0014309708166841495,
+      "grad_norm": 1.5801585912704468,
+      "learning_rate": 0.000116,
+      "loss": 1.553,
+      "step": 59
+    },
+    {
+      "epoch": 0.0014552245593398132,
+      "grad_norm": 0.9962314963340759,
+      "learning_rate": 0.000118,
+      "loss": 1.4924,
+      "step": 60
+    },
+    {
+      "epoch": 0.0014794783019954766,
+      "grad_norm": 5.291327476501465,
+      "learning_rate": 0.00012,
+      "loss": 1.8365,
+      "step": 61
+    },
+    {
+      "epoch": 0.0015037320446511402,
+      "grad_norm": 1.6945866346359253,
+      "learning_rate": 0.000122,
+      "loss": 1.4683,
+      "step": 62
+    },
+    {
+      "epoch": 0.0015279857873068039,
+      "grad_norm": 1.0400323867797852,
+      "learning_rate": 0.000124,
+      "loss": 0.8587,
+      "step": 63
+    },
+    {
+      "epoch": 0.0015522395299624673,
+      "grad_norm": 3.5120689868927,
+      "learning_rate": 0.000126,
+      "loss": 1.2127,
+      "step": 64
+    },
+    {
+      "epoch": 0.001576493272618131,
+      "grad_norm": 1.0469675064086914,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 1.654,
+      "step": 65
+    },
+    {
+      "epoch": 0.0016007470152737944,
+      "grad_norm": 1.5673848390579224,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 1.801,
+      "step": 66
+    },
+    {
+      "epoch": 0.001625000757929458,
+      "grad_norm": 2.0134799480438232,
+      "learning_rate": 0.000132,
+      "loss": 2.0432,
+      "step": 67
+    },
+    {
+      "epoch": 0.0016492545005851215,
+      "grad_norm": 7.747060775756836,
+      "learning_rate": 0.000134,
+      "loss": 1.4823,
+      "step": 68
+    },
+    {
+      "epoch": 0.0016735082432407851,
+      "grad_norm": 3.2787840366363525,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 1.4865,
+      "step": 69
+    },
+    {
+      "epoch": 0.0016977619858964486,
+      "grad_norm": 4.277163028717041,
+      "learning_rate": 0.000138,
+      "loss": 1.4665,
+      "step": 70
+    },
+    {
+      "epoch": 0.0017220157285521122,
+      "grad_norm": 11.562691688537598,
+      "learning_rate": 0.00014,
+      "loss": 2.0221,
+      "step": 71
+    },
+    {
+      "epoch": 0.0017462694712077757,
+      "grad_norm": 2.5653882026672363,
+      "learning_rate": 0.000142,
+      "loss": 1.4631,
+      "step": 72
+    },
+    {
+      "epoch": 0.0017705232138634393,
+      "grad_norm": 2.392688751220703,
+      "learning_rate": 0.000144,
+      "loss": 1.3514,
+      "step": 73
+    },
+    {
+      "epoch": 0.001794776956519103,
+      "grad_norm": 3.874115467071533,
+      "learning_rate": 0.000146,
+      "loss": 1.5983,
+      "step": 74
+    },
+    {
+      "epoch": 0.0018190306991747664,
+      "grad_norm": 3.085160732269287,
+      "learning_rate": 0.000148,
+      "loss": 1.321,
+      "step": 75
+    },
+    {
+      "epoch": 0.00184328444183043,
+      "grad_norm": 1.7499727010726929,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.385,
+      "step": 76
+    },
+    {
+      "epoch": 0.0018675381844860935,
+      "grad_norm": 14.051904678344727,
+      "learning_rate": 0.000152,
+      "loss": 1.5748,
+      "step": 77
+    },
+    {
+      "epoch": 0.0018917919271417571,
+      "grad_norm": 4.689906597137451,
+      "learning_rate": 0.000154,
+      "loss": 1.2126,
+      "step": 78
+    },
+    {
+      "epoch": 0.0019160456697974206,
+      "grad_norm": 1.0368577241897583,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 1.0542,
+      "step": 79
+    },
+    {
+      "epoch": 0.0019402994124530842,
+      "grad_norm": 3.577094078063965,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 1.9481,
+      "step": 80
+    },
+    {
+      "epoch": 0.001964553155108748,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 1.2913,
+      "step": 81
+    },
+    {
+      "epoch": 0.001988806897764411,
+      "grad_norm": 4.969227313995361,
+      "learning_rate": 0.00016,
+      "loss": 1.5551,
+      "step": 82
+    },
+    {
+      "epoch": 0.0020130606404200747,
+      "grad_norm": 71.41371154785156,
+      "learning_rate": 0.000162,
+      "loss": 1.5847,
+      "step": 83
+    },
+    {
+      "epoch": 0.0020373143830757384,
+      "grad_norm": 0.9679685831069946,
+      "learning_rate": 0.000164,
+      "loss": 1.1516,
+      "step": 84
+    },
+    {
+      "epoch": 0.002061568125731402,
+      "grad_norm": 7.050138473510742,
+      "learning_rate": 0.000166,
+      "loss": 1.6904,
+      "step": 85
+    },
+    {
+      "epoch": 0.0020858218683870657,
+      "grad_norm": 1.4181028604507446,
+      "learning_rate": 0.000168,
+      "loss": 1.5385,
+      "step": 86
+    },
+    {
+      "epoch": 0.002110075611042729,
+      "grad_norm": 1.122887134552002,
+      "learning_rate": 0.00017,
+      "loss": 1.282,
+      "step": 87
+    },
+    {
+      "epoch": 0.0021343293536983925,
+      "grad_norm": 3.0532054901123047,
+      "learning_rate": 0.000172,
+      "loss": 1.7126,
+      "step": 88
+    },
+    {
+      "epoch": 0.002158583096354056,
+      "grad_norm": 1.1368091106414795,
+      "learning_rate": 0.000174,
+      "loss": 1.3792,
+      "step": 89
+    },
+    {
+      "epoch": 0.00218283683900972,
+      "grad_norm": 1.5556614398956299,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 1.1266,
+      "step": 90
+    },
+    {
+      "epoch": 0.002207090581665383,
+      "grad_norm": 2.5969090461730957,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 1.1916,
+      "step": 91
+    },
+    {
+      "epoch": 0.0022313443243210467,
+      "grad_norm": 7.9968719482421875,
+      "learning_rate": 0.00018,
+      "loss": 2.3005,
+      "step": 92
+    },
+    {
+      "epoch": 0.0022555980669767104,
+      "grad_norm": 1.0678150653839111,
+      "learning_rate": 0.000182,
+      "loss": 1.1991,
+      "step": 93
+    },
+    {
+      "epoch": 0.002279851809632374,
+      "grad_norm": 6.678997993469238,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 1.9749,
+      "step": 94
+    },
+    {
+      "epoch": 0.0023041055522880377,
+      "grad_norm": 2.6500961780548096,
+      "learning_rate": 0.00018600000000000002,
+      "loss": 1.7569,
+      "step": 95
+    },
+    {
+      "epoch": 0.002328359294943701,
+      "grad_norm": 1.547878384590149,
+      "learning_rate": 0.000188,
+      "loss": 1.7286,
+      "step": 96
+    },
+    {
+      "epoch": 0.0023526130375993645,
+      "grad_norm": 1.910861849784851,
+      "learning_rate": 0.00019,
+      "loss": 2.0815,
+      "step": 97
+    },
+    {
+      "epoch": 0.002376866780255028,
+      "grad_norm": 3.678144693374634,
+      "learning_rate": 0.000192,
+      "loss": 1.7011,
+      "step": 98
+    },
+    {
+      "epoch": 0.002401120522910692,
+      "grad_norm": 1.6496407985687256,
+      "learning_rate": 0.000194,
+      "loss": 1.8013,
+      "step": 99
+    },
+    {
+      "epoch": 0.002425374265566355,
+      "grad_norm": 1.3245445489883423,
+      "learning_rate": 0.000196,
+      "loss": 1.5302,
+      "step": 100
+    },
+    {
+      "epoch": 0.0024496280082220187,
+      "grad_norm": 1.609408974647522,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 1.6082,
+      "step": 101
+    },
+    {
+      "epoch": 0.0024738817508776823,
+      "grad_norm": 2.7757482528686523,
+      "learning_rate": 0.0002,
+      "loss": 1.6157,
+      "step": 102
+    },
+    {
+      "epoch": 0.002498135493533346,
+      "grad_norm": 2.0618674755096436,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 1.7212,
+      "step": 103
+    },
+    {
+      "epoch": 0.002522389236189009,
+      "grad_norm": 1.7433160543441772,
+      "learning_rate": 0.000196,
+      "loss": 1.9133,
+      "step": 104
+    },
+    {
+      "epoch": 0.002546642978844673,
+      "grad_norm": 1.4754176139831543,
+      "learning_rate": 0.000194,
+      "loss": 1.3311,
+      "step": 105
+    },
+    {
+      "epoch": 0.0025708967215003365,
+      "grad_norm": 1.4527512788772583,
+      "learning_rate": 0.000192,
+      "loss": 1.6432,
+      "step": 106
+    },
+    {
+      "epoch": 0.002595150464156,
+      "grad_norm": 5.3099045753479,
+      "learning_rate": 0.00019,
+      "loss": 1.3233,
+      "step": 107
+    },
+    {
+      "epoch": 0.002619404206811664,
+      "grad_norm": 1.016135573387146,
+      "learning_rate": 0.000188,
+      "loss": 1.3291,
+      "step": 108
+    },
+    {
+      "epoch": 0.002643657949467327,
+      "grad_norm": 1.0468915700912476,
+      "learning_rate": 0.00018600000000000002,
+      "loss": 1.4454,
+      "step": 109
+    },
+    {
+      "epoch": 0.0026679116921229907,
+      "grad_norm": 3.245159387588501,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 1.6501,
+      "step": 110
+    },
+    {
+      "epoch": 0.0026921654347786543,
+      "grad_norm": 1.1628005504608154,
+      "learning_rate": 0.000182,
+      "loss": 1.399,
+      "step": 111
+    },
+    {
+      "epoch": 0.002716419177434318,
+      "grad_norm": 3.3215761184692383,
+      "learning_rate": 0.00018,
+      "loss": 1.4829,
+      "step": 112
+    },
+    {
+      "epoch": 0.002740672920089981,
+      "grad_norm": 1.424054503440857,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 1.7692,
+      "step": 113
+    },
+    {
+      "epoch": 0.002764926662745645,
+      "grad_norm": 1.2700444459915161,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 1.6959,
+      "step": 114
+    },
+    {
+      "epoch": 0.0027891804054013085,
+      "grad_norm": 1.262736201286316,
+      "learning_rate": 0.000174,
+      "loss": 1.5445,
+      "step": 115
+    },
+    {
+      "epoch": 0.002813434148056972,
+      "grad_norm": 4.976276397705078,
+      "learning_rate": 0.000172,
+      "loss": 1.4571,
+      "step": 116
+    },
+    {
+      "epoch": 0.002837687890712636,
+      "grad_norm": 1.2716983556747437,
+      "learning_rate": 0.00017,
+      "loss": 1.217,
+      "step": 117
+    },
+    {
+      "epoch": 0.002861941633368299,
+      "grad_norm": 1.5143672227859497,
+      "learning_rate": 0.000168,
+      "loss": 1.3059,
+      "step": 118
+    },
+    {
+      "epoch": 0.0028861953760239627,
+      "grad_norm": 0.9907928705215454,
+      "learning_rate": 0.000166,
+      "loss": 1.8035,
+      "step": 119
+    },
+    {
+      "epoch": 0.0029104491186796263,
+      "grad_norm": 1.7163773775100708,
+      "learning_rate": 0.000164,
+      "loss": 2.1635,
+      "step": 120
+    },
+    {
+      "epoch": 0.00293470286133529,
+      "grad_norm": 7.744179725646973,
+      "learning_rate": 0.000162,
+      "loss": 2.2964,
+      "step": 121
+    },
+    {
+      "epoch": 0.002958956603990953,
+      "grad_norm": 1.101208209991455,
+      "learning_rate": 0.00016,
+      "loss": 1.46,
+      "step": 122
+    },
+    {
+      "epoch": 0.002983210346646617,
+      "grad_norm": 0.7589418888092041,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 1.1036,
+      "step": 123
+    },
+    {
+      "epoch": 0.0030074640893022805,
+      "grad_norm": 4.626345634460449,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 1.5257,
+      "step": 124
+    },
+    {
+      "epoch": 0.003031717831957944,
+      "grad_norm": 1.5994218587875366,
+      "learning_rate": 0.000154,
+      "loss": 1.2856,
+      "step": 125
+    },
+    {
+      "epoch": 0.0030559715746136078,
+      "grad_norm": 1.3893097639083862,
+      "learning_rate": 0.000152,
+      "loss": 1.3359,
+      "step": 126
+    },
+    {
+      "epoch": 0.003080225317269271,
+      "grad_norm": 1.0536174774169922,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.1718,
+      "step": 127
+    },
+    {
+      "epoch": 0.0031044790599249346,
+      "grad_norm": 1.2898694276809692,
+      "learning_rate": 0.000148,
+      "loss": 1.2908,
+      "step": 128
+    },
+    {
+      "epoch": 0.0031287328025805983,
+      "grad_norm": 1.6943238973617554,
+      "learning_rate": 0.000146,
+      "loss": 1.7723,
+      "step": 129
+    },
+    {
+      "epoch": 0.003152986545236262,
+      "grad_norm": 1.2562038898468018,
+      "learning_rate": 0.000144,
+      "loss": 1.4476,
+      "step": 130
+    },
+    {
+      "epoch": 0.003177240287891925,
+      "grad_norm": 1.0170366764068604,
+      "learning_rate": 0.000142,
+      "loss": 1.2967,
+      "step": 131
+    },
+    {
+      "epoch": 0.003201494030547589,
+      "grad_norm": 5.646616458892822,
+      "learning_rate": 0.00014,
+      "loss": 1.4366,
+      "step": 132
+    },
+    {
+      "epoch": 0.0032257477732032525,
+      "grad_norm": 1.29356849193573,
+      "learning_rate": 0.000138,
+      "loss": 1.4713,
+      "step": 133
+    },
+    {
+      "epoch": 0.003250001515858916,
+      "grad_norm": 1.3575730323791504,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 1.2233,
+      "step": 134
+    },
+    {
+      "epoch": 0.0032742552585145793,
+      "grad_norm": 1.158686876296997,
+      "learning_rate": 0.000134,
+      "loss": 1.3622,
+      "step": 135
+    },
+    {
+      "epoch": 0.003298509001170243,
+      "grad_norm": 1.4680081605911255,
+      "learning_rate": 0.000132,
+      "loss": 1.7191,
+      "step": 136
+    },
+    {
+      "epoch": 0.0033227627438259066,
+      "grad_norm": 1.2448982000350952,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 1.9376,
+      "step": 137
+    },
+    {
+      "epoch": 0.0033470164864815703,
+      "grad_norm": 1.2404478788375854,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 1.5334,
+      "step": 138
+    },
+    {
+      "epoch": 0.003371270229137234,
+      "grad_norm": 0.9862974882125854,
+      "learning_rate": 0.000126,
+      "loss": 1.2073,
+      "step": 139
+    },
+    {
+      "epoch": 0.003395523971792897,
+      "grad_norm": 7.36776876449585,
+      "learning_rate": 0.000124,
+      "loss": 1.5745,
+      "step": 140
+    },
+    {
+      "epoch": 0.003419777714448561,
+      "grad_norm": 1.1356145143508911,
+      "learning_rate": 0.000122,
+      "loss": 1.563,
+      "step": 141
+    },
+    {
+      "epoch": 0.0034440314571042244,
+      "grad_norm": 2.073420286178589,
+      "learning_rate": 0.00012,
+      "loss": 1.7438,
+      "step": 142
+    },
+    {
+      "epoch": 0.003468285199759888,
+      "grad_norm": 3.029547691345215,
+      "learning_rate": 0.000118,
+      "loss": 1.6755,
+      "step": 143
+    },
+    {
+      "epoch": 0.0034925389424155513,
+      "grad_norm": 14.66256046295166,
+      "learning_rate": 0.000116,
+      "loss": 1.8375,
+      "step": 144
+    },
+    {
+      "epoch": 0.003516792685071215,
+      "grad_norm": 0.8765383958816528,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 0.6782,
+      "step": 145
+    },
+    {
+      "epoch": 0.0035410464277268786,
+      "grad_norm": 3.167731761932373,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 1.4619,
+      "step": 146
+    },
+    {
+      "epoch": 0.0035653001703825423,
+      "grad_norm": 1.1016606092453003,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 1.5817,
+      "step": 147
+    },
+    {
+      "epoch": 0.003589553913038206,
+      "grad_norm": 2.5535902976989746,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 1.3491,
+      "step": 148
+    },
+    {
+      "epoch": 0.003613807655693869,
+      "grad_norm": 1.1920926570892334,
+      "learning_rate": 0.00010600000000000002,
+      "loss": 1.5675,
+      "step": 149
+    },
+    {
+      "epoch": 0.0036380613983495328,
+      "grad_norm": 1.1023300886154175,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 1.2821,
+      "step": 150
+    },
+    {
+      "epoch": 0.0036623151410051964,
+      "grad_norm": 2.1146063804626465,
+      "learning_rate": 0.00010200000000000001,
+      "loss": 1.5396,
+      "step": 151
+    },
+    {
+      "epoch": 0.00368656888366086,
+      "grad_norm": 1.1838195323944092,
+      "learning_rate": 0.0001,
+      "loss": 1.2992,
+      "step": 152
+    },
+    {
+      "epoch": 0.0037108226263165233,
+      "grad_norm": 1.414258360862732,
+      "learning_rate": 9.8e-05,
+      "loss": 1.6888,
+      "step": 153
+    },
+    {
+      "epoch": 0.003735076368972187,
+      "grad_norm": 0.8630995154380798,
+      "learning_rate": 9.6e-05,
+      "loss": 1.141,
+      "step": 154
+    },
+    {
+      "epoch": 0.0037593301116278506,
+      "grad_norm": 2.4763197898864746,
+      "learning_rate": 9.4e-05,
+      "loss": 1.5743,
+      "step": 155
+    },
+    {
+      "epoch": 0.0037835838542835142,
+      "grad_norm": 0.9457703828811646,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 1.3879,
+      "step": 156
+    },
+    {
+      "epoch": 0.003807837596939178,
+      "grad_norm": 1.308862328529358,
+      "learning_rate": 9e-05,
+      "loss": 1.1564,
+      "step": 157
+    },
+    {
+      "epoch": 0.003832091339594841,
+      "grad_norm": 1.208833932876587,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 1.2059,
+      "step": 158
+    },
+    {
+      "epoch": 0.0038563450822505048,
+      "grad_norm": 1.9145225286483765,
+      "learning_rate": 8.6e-05,
+      "loss": 1.4744,
+      "step": 159
+    },
+    {
+      "epoch": 0.0038805988249061684,
+      "grad_norm": 1.0121599435806274,
+      "learning_rate": 8.4e-05,
+      "loss": 1.8676,
+      "step": 160
+    },
+    {
+      "epoch": 0.003904852567561832,
+      "grad_norm": 1.9128226041793823,
+      "learning_rate": 8.2e-05,
+      "loss": 1.6948,
+      "step": 161
+    },
+    {
+      "epoch": 0.003929106310217496,
+      "grad_norm": 1.7783511877059937,
+      "learning_rate": 8e-05,
+      "loss": 1.4198,
+      "step": 162
+    },
+    {
+      "epoch": 0.003953360052873159,
+      "grad_norm": 0.9799928665161133,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 1.185,
+      "step": 163
+    },
+    {
+      "epoch": 0.003977613795528822,
+      "grad_norm": 1.5025819540023804,
+      "learning_rate": 7.6e-05,
+      "loss": 1.0638,
+      "step": 164
+    },
+    {
+      "epoch": 0.004001867538184486,
+      "grad_norm": 1.2552540302276611,
+      "learning_rate": 7.4e-05,
+      "loss": 1.3463,
+      "step": 165
+    },
+    {
+      "epoch": 0.0040261212808401494,
+      "grad_norm": 1.0616928339004517,
+      "learning_rate": 7.2e-05,
+      "loss": 1.9275,
+      "step": 166
+    },
+    {
+      "epoch": 0.004050375023495813,
+      "grad_norm": 2.8277781009674072,
+      "learning_rate": 7e-05,
+      "loss": 1.9653,
+      "step": 167
+    },
+    {
+      "epoch": 0.004074628766151477,
+      "grad_norm": 1.7752915620803833,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 1.2783,
+      "step": 168
+    },
+    {
+      "epoch": 0.00409888250880714,
+      "grad_norm": 2.4863102436065674,
+      "learning_rate": 6.6e-05,
+      "loss": 1.2803,
+      "step": 169
+    },
+    {
+      "epoch": 0.004123136251462804,
+      "grad_norm": 0.9784297943115234,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 1.0347,
+      "step": 170
+    },
+    {
+      "epoch": 0.004147389994118468,
+      "grad_norm": 2.0077602863311768,
+      "learning_rate": 6.2e-05,
+      "loss": 1.5035,
+      "step": 171
+    },
+    {
+      "epoch": 0.004171643736774131,
+      "grad_norm": 1.5943875312805176,
+      "learning_rate": 6e-05,
+      "loss": 1.7834,
+      "step": 172
+    },
+    {
+      "epoch": 0.004195897479429794,
+      "grad_norm": 1.0898661613464355,
+      "learning_rate": 5.8e-05,
+      "loss": 1.5043,
+      "step": 173
+    },
+    {
+      "epoch": 0.004220151222085458,
+      "grad_norm": 1.8181873559951782,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 1.5026,
+      "step": 174
+    },
+    {
+      "epoch": 0.004244404964741121,
+      "grad_norm": 0.9227128028869629,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 1.3945,
+      "step": 175
+    },
+    {
+      "epoch": 0.004268658707396785,
+      "grad_norm": 1.3131438493728638,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 1.2629,
+      "step": 176
+    },
+    {
+      "epoch": 0.004292912450052449,
+      "grad_norm": 1.388433814048767,
+      "learning_rate": 5e-05,
+      "loss": 1.607,
+      "step": 177
+    },
+    {
+      "epoch": 0.004317166192708112,
+      "grad_norm": 1.5145083665847778,
+      "learning_rate": 4.8e-05,
+      "loss": 1.8671,
+      "step": 178
+    },
+    {
+      "epoch": 0.004341419935363776,
+      "grad_norm": 2.0021004676818848,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 2.0679,
+      "step": 179
+    },
+    {
+      "epoch": 0.00436567367801944,
+      "grad_norm": 1.8512483835220337,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 1.3095,
+      "step": 180
+    },
+    {
+      "epoch": 0.004389927420675103,
+      "grad_norm": 1.0164090394973755,
+      "learning_rate": 4.2e-05,
+      "loss": 1.3749,
+      "step": 181
+    },
+    {
+      "epoch": 0.004414181163330766,
+      "grad_norm": 30.730253219604492,
+      "learning_rate": 4e-05,
+      "loss": 2.3106,
+      "step": 182
+    },
+    {
+      "epoch": 0.00443843490598643,
+      "grad_norm": 1.2311471700668335,
+      "learning_rate": 3.8e-05,
+      "loss": 1.1078,
+      "step": 183
+    },
+    {
+      "epoch": 0.004462688648642093,
+      "grad_norm": 0.9555554389953613,
+      "learning_rate": 3.6e-05,
+      "loss": 1.4175,
+      "step": 184
+    },
+    {
+      "epoch": 0.004486942391297757,
+      "grad_norm": 1.4511969089508057,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 1.4099,
+      "step": 185
+    },
+    {
+      "epoch": 0.004511196133953421,
+      "grad_norm": 5.319721221923828,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 1.2749,
+      "step": 186
+    },
+    {
+      "epoch": 0.004535449876609084,
+      "grad_norm": 1.8668482303619385,
+      "learning_rate": 3e-05,
+      "loss": 1.4658,
+      "step": 187
+    },
+    {
+      "epoch": 0.004559703619264748,
+      "grad_norm": 1.737425684928894,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 1.8142,
+      "step": 188
+    },
+    {
+      "epoch": 0.004583957361920412,
+      "grad_norm": 12.860699653625488,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 1.6338,
+      "step": 189
+    },
+    {
+      "epoch": 0.004608211104576075,
+      "grad_norm": 0.6315305233001709,
+      "learning_rate": 2.4e-05,
+      "loss": 1.0426,
+      "step": 190
+    },
+    {
+      "epoch": 0.004632464847231738,
+      "grad_norm": 1.0747138261795044,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 1.4042,
+      "step": 191
+    },
+    {
+      "epoch": 0.004656718589887402,
+      "grad_norm": 1.1410670280456543,
+      "learning_rate": 2e-05,
+      "loss": 1.2148,
+      "step": 192
+    },
+    {
+      "epoch": 0.004680972332543065,
+      "grad_norm": 1.4486732482910156,
+      "learning_rate": 1.8e-05,
+      "loss": 1.3208,
+      "step": 193
+    },
+    {
+      "epoch": 0.004705226075198729,
+      "grad_norm": 2.5336716175079346,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.7136,
+      "step": 194
+    },
+    {
+      "epoch": 0.004729479817854393,
+      "grad_norm": 3.4056637287139893,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 1.5443,
+      "step": 195
+    },
+    {
+      "epoch": 0.004753733560510056,
+      "grad_norm": 1.1721996068954468,
+      "learning_rate": 1.2e-05,
+      "loss": 1.4518,
+      "step": 196
+    },
+    {
+      "epoch": 0.00477798730316572,
+      "grad_norm": 1.9326874017715454,
+      "learning_rate": 1e-05,
+      "loss": 1.6381,
+      "step": 197
+    },
+    {
+      "epoch": 0.004802241045821384,
+      "grad_norm": 1.0234136581420898,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.4116,
+      "step": 198
+    },
+    {
+      "epoch": 0.004826494788477047,
+      "grad_norm": 2.1815526485443115,
+      "learning_rate": 6e-06,
+      "loss": 1.7442,
+      "step": 199
+    },
+    {
+      "epoch": 0.00485074853113271,
+      "grad_norm": 1.9557406902313232,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.9568,
+      "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": 6034692870365184.0,
+  "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 sha256:02e9962458f016a1c07dc5280d7007cfd14653c05542b51edd26eefb09ce3f00
+size 5176

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02e9962458f016a1c07dc5280d7007cfd14653c05542b51edd26eefb09ce3f00
+size 5176