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:a115dacf1f2435d487c24b16dcdf2e2ded0bc635269a44e344367ce2938d8594
+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:a115dacf1f2435d487c24b16dcdf2e2ded0bc635269a44e344367ce2938d8594
+size 34100216

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7f3eb5fe27f4339c2b2499f040822b2be66cf8314166a745797c2d8e5e499f8
+size 68292346

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f50f0b8cf8a8f5247d0e9729d14f2b46d5491d4b47ff4bafcc913f88950008b8
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:112b68374ca1c950140f0870a98c4f3bc5a36bbea3cfec174b29f0bafea1fbee
+size 1064

checkpoint-200/trainer_state.json

@@ -0,0 +1,1433 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3189792663476874,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001594896331738437,
+      "grad_norm": 9.529223442077637,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 3.8964,
+      "step": 1
+    },
+    {
+      "epoch": 0.003189792663476874,
+      "grad_norm": 3.4800214767456055,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.2247,
+      "step": 2
+    },
+    {
+      "epoch": 0.004784688995215311,
+      "grad_norm": 3.026850461959839,
+      "learning_rate": 6e-06,
+      "loss": 2.2337,
+      "step": 3
+    },
+    {
+      "epoch": 0.006379585326953748,
+      "grad_norm": 7.065993785858154,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.9733,
+      "step": 4
+    },
+    {
+      "epoch": 0.007974481658692184,
+      "grad_norm": 5.338789463043213,
+      "learning_rate": 1e-05,
+      "loss": 2.2808,
+      "step": 5
+    },
+    {
+      "epoch": 0.009569377990430622,
+      "grad_norm": 12.933262825012207,
+      "learning_rate": 1.2e-05,
+      "loss": 2.2984,
+      "step": 6
+    },
+    {
+      "epoch": 0.011164274322169059,
+      "grad_norm": 3.535792350769043,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 2.6236,
+      "step": 7
+    },
+    {
+      "epoch": 0.012759170653907496,
+      "grad_norm": 7.564616680145264,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.4849,
+      "step": 8
+    },
+    {
+      "epoch": 0.014354066985645933,
+      "grad_norm": 7.379055976867676,
+      "learning_rate": 1.8e-05,
+      "loss": 2.9017,
+      "step": 9
+    },
+    {
+      "epoch": 0.01594896331738437,
+      "grad_norm": 6.781640529632568,
+      "learning_rate": 2e-05,
+      "loss": 2.5836,
+      "step": 10
+    },
+    {
+      "epoch": 0.017543859649122806,
+      "grad_norm": Infinity,
+      "learning_rate": 2e-05,
+      "loss": 2.6482,
+      "step": 11
+    },
+    {
+      "epoch": 0.019138755980861243,
+      "grad_norm": 9.666836738586426,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 1.5775,
+      "step": 12
+    },
+    {
+      "epoch": 0.02073365231259968,
+      "grad_norm": 7.910143852233887,
+      "learning_rate": 2.4e-05,
+      "loss": 2.259,
+      "step": 13
+    },
+    {
+      "epoch": 0.022328548644338118,
+      "grad_norm": 5.05098295211792,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 2.1146,
+      "step": 14
+    },
+    {
+      "epoch": 0.023923444976076555,
+      "grad_norm": 4.457101345062256,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 2.1058,
+      "step": 15
+    },
+    {
+      "epoch": 0.025518341307814992,
+      "grad_norm": NaN,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 2.4278,
+      "step": 16
+    },
+    {
+      "epoch": 0.02711323763955343,
+      "grad_norm": 4.420550346374512,
+      "learning_rate": 3e-05,
+      "loss": 1.9174,
+      "step": 17
+    },
+    {
+      "epoch": 0.028708133971291867,
+      "grad_norm": 9.368809700012207,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 2.0925,
+      "step": 18
+    },
+    {
+      "epoch": 0.030303030303030304,
+      "grad_norm": 4.382827281951904,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 1.3716,
+      "step": 19
+    },
+    {
+      "epoch": 0.03189792663476874,
+      "grad_norm": 24.012392044067383,
+      "learning_rate": 3.6e-05,
+      "loss": 2.348,
+      "step": 20
+    },
+    {
+      "epoch": 0.03349282296650718,
+      "grad_norm": 2.227252721786499,
+      "learning_rate": 3.8e-05,
+      "loss": 2.0678,
+      "step": 21
+    },
+    {
+      "epoch": 0.03508771929824561,
+      "grad_norm": 6.851357460021973,
+      "learning_rate": 4e-05,
+      "loss": 3.2008,
+      "step": 22
+    },
+    {
+      "epoch": 0.03668261562998405,
+      "grad_norm": 5.75844144821167,
+      "learning_rate": 4.2e-05,
+      "loss": 1.8704,
+      "step": 23
+    },
+    {
+      "epoch": 0.03827751196172249,
+      "grad_norm": 14.692899703979492,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 2.9055,
+      "step": 24
+    },
+    {
+      "epoch": 0.03987240829346093,
+      "grad_norm": NaN,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 2.4497,
+      "step": 25
+    },
+    {
+      "epoch": 0.04146730462519936,
+      "grad_norm": NaN,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 2.4382,
+      "step": 26
+    },
+    {
+      "epoch": 0.0430622009569378,
+      "grad_norm": 6.065037727355957,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 2.105,
+      "step": 27
+    },
+    {
+      "epoch": 0.044657097288676235,
+      "grad_norm": 4.765100479125977,
+      "learning_rate": 4.8e-05,
+      "loss": 2.5292,
+      "step": 28
+    },
+    {
+      "epoch": 0.046251993620414676,
+      "grad_norm": 10.693521499633789,
+      "learning_rate": 5e-05,
+      "loss": 1.4471,
+      "step": 29
+    },
+    {
+      "epoch": 0.04784688995215311,
+      "grad_norm": 5.703505992889404,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 1.8759,
+      "step": 30
+    },
+    {
+      "epoch": 0.049441786283891544,
+      "grad_norm": 6.594554424285889,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 2.3555,
+      "step": 31
+    },
+    {
+      "epoch": 0.051036682615629984,
+      "grad_norm": 10.944120407104492,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 2.6607,
+      "step": 32
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 4.437515735626221,
+      "learning_rate": 5.8e-05,
+      "loss": 2.1366,
+      "step": 33
+    },
+    {
+      "epoch": 0.05422647527910686,
+      "grad_norm": 18.751192092895508,
+      "learning_rate": 6e-05,
+      "loss": 2.8504,
+      "step": 34
+    },
+    {
+      "epoch": 0.05582137161084529,
+      "grad_norm": 4.625219821929932,
+      "learning_rate": 6.2e-05,
+      "loss": 1.7409,
+      "step": 35
+    },
+    {
+      "epoch": 0.05741626794258373,
+      "grad_norm": 5.256422996520996,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 2.965,
+      "step": 36
+    },
+    {
+      "epoch": 0.05901116427432217,
+      "grad_norm": 5.383383274078369,
+      "learning_rate": 6.6e-05,
+      "loss": 2.5555,
+      "step": 37
+    },
+    {
+      "epoch": 0.06060606060606061,
+      "grad_norm": 20.616491317749023,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 2.1693,
+      "step": 38
+    },
+    {
+      "epoch": 0.06220095693779904,
+      "grad_norm": 14.188122749328613,
+      "learning_rate": 7e-05,
+      "loss": 3.2098,
+      "step": 39
+    },
+    {
+      "epoch": 0.06379585326953748,
+      "grad_norm": 7.294703483581543,
+      "learning_rate": 7.2e-05,
+      "loss": 2.8137,
+      "step": 40
+    },
+    {
+      "epoch": 0.06539074960127592,
+      "grad_norm": 16.109020233154297,
+      "learning_rate": 7.4e-05,
+      "loss": 3.4821,
+      "step": 41
+    },
+    {
+      "epoch": 0.06698564593301436,
+      "grad_norm": 12.77609920501709,
+      "learning_rate": 7.6e-05,
+      "loss": 3.2586,
+      "step": 42
+    },
+    {
+      "epoch": 0.0685805422647528,
+      "grad_norm": 7.247976303100586,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 2.1131,
+      "step": 43
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 3.0302693843841553,
+      "learning_rate": 8e-05,
+      "loss": 2.3047,
+      "step": 44
+    },
+    {
+      "epoch": 0.07177033492822966,
+      "grad_norm": 6.998560905456543,
+      "learning_rate": 8.2e-05,
+      "loss": 1.9685,
+      "step": 45
+    },
+    {
+      "epoch": 0.0733652312599681,
+      "grad_norm": 11.82168197631836,
+      "learning_rate": 8.4e-05,
+      "loss": 2.412,
+      "step": 46
+    },
+    {
+      "epoch": 0.07496012759170653,
+      "grad_norm": 2.4560766220092773,
+      "learning_rate": 8.6e-05,
+      "loss": 1.5546,
+      "step": 47
+    },
+    {
+      "epoch": 0.07655502392344497,
+      "grad_norm": 7.5531110763549805,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 2.0706,
+      "step": 48
+    },
+    {
+      "epoch": 0.07814992025518341,
+      "grad_norm": 9.41441535949707,
+      "learning_rate": 9e-05,
+      "loss": 2.0769,
+      "step": 49
+    },
+    {
+      "epoch": 0.07974481658692185,
+      "grad_norm": 5.027219295501709,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 1.0112,
+      "step": 50
+    },
+    {
+      "epoch": 0.08133971291866028,
+      "grad_norm": 4.590622901916504,
+      "learning_rate": 9.4e-05,
+      "loss": 2.4014,
+      "step": 51
+    },
+    {
+      "epoch": 0.08293460925039872,
+      "grad_norm": 110.29186248779297,
+      "learning_rate": 9.6e-05,
+      "loss": 2.2312,
+      "step": 52
+    },
+    {
+      "epoch": 0.08452950558213716,
+      "grad_norm": 13.907599449157715,
+      "learning_rate": 9.8e-05,
+      "loss": 3.74,
+      "step": 53
+    },
+    {
+      "epoch": 0.0861244019138756,
+      "grad_norm": 21.45476722717285,
+      "learning_rate": 0.0001,
+      "loss": 2.2449,
+      "step": 54
+    },
+    {
+      "epoch": 0.08771929824561403,
+      "grad_norm": 26.367050170898438,
+      "learning_rate": 0.00010200000000000001,
+      "loss": 2.4117,
+      "step": 55
+    },
+    {
+      "epoch": 0.08931419457735247,
+      "grad_norm": 11.473040580749512,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 1.9575,
+      "step": 56
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 7.996298789978027,
+      "learning_rate": 0.00010600000000000002,
+      "loss": 2.2506,
+      "step": 57
+    },
+    {
+      "epoch": 0.09250398724082935,
+      "grad_norm": 5.780291557312012,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 1.685,
+      "step": 58
+    },
+    {
+      "epoch": 0.09409888357256778,
+      "grad_norm": 14.359979629516602,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 2.1997,
+      "step": 59
+    },
+    {
+      "epoch": 0.09569377990430622,
+      "grad_norm": 2.4853787422180176,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 1.2731,
+      "step": 60
+    },
+    {
+      "epoch": 0.09728867623604466,
+      "grad_norm": 7.136777877807617,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 2.1987,
+      "step": 61
+    },
+    {
+      "epoch": 0.09888357256778309,
+      "grad_norm": 7.219399929046631,
+      "learning_rate": 0.000116,
+      "loss": 2.3118,
+      "step": 62
+    },
+    {
+      "epoch": 0.10047846889952153,
+      "grad_norm": 15.516590118408203,
+      "learning_rate": 0.000118,
+      "loss": 2.2534,
+      "step": 63
+    },
+    {
+      "epoch": 0.10207336523125997,
+      "grad_norm": 4.05905818939209,
+      "learning_rate": 0.00012,
+      "loss": 2.0509,
+      "step": 64
+    },
+    {
+      "epoch": 0.10366826156299841,
+      "grad_norm": 51.53736877441406,
+      "learning_rate": 0.000122,
+      "loss": 3.7686,
+      "step": 65
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 4.316274642944336,
+      "learning_rate": 0.000124,
+      "loss": 1.332,
+      "step": 66
+    },
+    {
+      "epoch": 0.10685805422647528,
+      "grad_norm": 47.97142028808594,
+      "learning_rate": 0.000126,
+      "loss": 1.4256,
+      "step": 67
+    },
+    {
+      "epoch": 0.10845295055821372,
+      "grad_norm": 10.22885513305664,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 1.4572,
+      "step": 68
+    },
+    {
+      "epoch": 0.11004784688995216,
+      "grad_norm": 5.966179370880127,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 1.3998,
+      "step": 69
+    },
+    {
+      "epoch": 0.11164274322169059,
+      "grad_norm": 3.413966178894043,
+      "learning_rate": 0.000132,
+      "loss": 1.6306,
+      "step": 70
+    },
+    {
+      "epoch": 0.11323763955342903,
+      "grad_norm": 197.0709991455078,
+      "learning_rate": 0.000134,
+      "loss": 1.6587,
+      "step": 71
+    },
+    {
+      "epoch": 0.11483253588516747,
+      "grad_norm": 12.735696792602539,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 2.0253,
+      "step": 72
+    },
+    {
+      "epoch": 0.11642743221690591,
+      "grad_norm": 14.38369083404541,
+      "learning_rate": 0.000138,
+      "loss": 2.0833,
+      "step": 73
+    },
+    {
+      "epoch": 0.11802232854864433,
+      "grad_norm": 5.746401786804199,
+      "learning_rate": 0.00014,
+      "loss": 1.959,
+      "step": 74
+    },
+    {
+      "epoch": 0.11961722488038277,
+      "grad_norm": 4.266767501831055,
+      "learning_rate": 0.000142,
+      "loss": 1.5752,
+      "step": 75
+    },
+    {
+      "epoch": 0.12121212121212122,
+      "grad_norm": 16.618648529052734,
+      "learning_rate": 0.000144,
+      "loss": 3.0947,
+      "step": 76
+    },
+    {
+      "epoch": 0.12280701754385964,
+      "grad_norm": 2.3666510581970215,
+      "learning_rate": 0.000146,
+      "loss": 2.0715,
+      "step": 77
+    },
+    {
+      "epoch": 0.12440191387559808,
+      "grad_norm": 6.622753143310547,
+      "learning_rate": 0.000148,
+      "loss": 1.8844,
+      "step": 78
+    },
+    {
+      "epoch": 0.12599681020733652,
+      "grad_norm": 43.816375732421875,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.9108,
+      "step": 79
+    },
+    {
+      "epoch": 0.12759170653907495,
+      "grad_norm": 6.682168006896973,
+      "learning_rate": 0.000152,
+      "loss": 1.5588,
+      "step": 80
+    },
+    {
+      "epoch": 0.1291866028708134,
+      "grad_norm": 3.0997276306152344,
+      "learning_rate": 0.000154,
+      "loss": 2.1988,
+      "step": 81
+    },
+    {
+      "epoch": 0.13078149920255183,
+      "grad_norm": 4.309176445007324,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 1.406,
+      "step": 82
+    },
+    {
+      "epoch": 0.13237639553429026,
+      "grad_norm": 5.416724681854248,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 1.576,
+      "step": 83
+    },
+    {
+      "epoch": 0.1339712918660287,
+      "grad_norm": 4.361196517944336,
+      "learning_rate": 0.00016,
+      "loss": 2.2985,
+      "step": 84
+    },
+    {
+      "epoch": 0.13556618819776714,
+      "grad_norm": 7.655956745147705,
+      "learning_rate": 0.000162,
+      "loss": 1.3693,
+      "step": 85
+    },
+    {
+      "epoch": 0.1371610845295056,
+      "grad_norm": 5.973109245300293,
+      "learning_rate": 0.000164,
+      "loss": 2.4914,
+      "step": 86
+    },
+    {
+      "epoch": 0.13875598086124402,
+      "grad_norm": 5.1589436531066895,
+      "learning_rate": 0.000166,
+      "loss": 1.6638,
+      "step": 87
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 6.356327056884766,
+      "learning_rate": 0.000168,
+      "loss": 1.381,
+      "step": 88
+    },
+    {
+      "epoch": 0.1419457735247209,
+      "grad_norm": 1.5582388639450073,
+      "learning_rate": 0.00017,
+      "loss": 1.4864,
+      "step": 89
+    },
+    {
+      "epoch": 0.14354066985645933,
+      "grad_norm": 2.830798387527466,
+      "learning_rate": 0.000172,
+      "loss": 1.897,
+      "step": 90
+    },
+    {
+      "epoch": 0.14513556618819776,
+      "grad_norm": 20.24082374572754,
+      "learning_rate": 0.000174,
+      "loss": 1.7698,
+      "step": 91
+    },
+    {
+      "epoch": 0.1467304625199362,
+      "grad_norm": 35.429466247558594,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 3.6051,
+      "step": 92
+    },
+    {
+      "epoch": 0.14832535885167464,
+      "grad_norm": 9.8428373336792,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 1.9402,
+      "step": 93
+    },
+    {
+      "epoch": 0.14992025518341306,
+      "grad_norm": 3.7131340503692627,
+      "learning_rate": 0.00018,
+      "loss": 2.2192,
+      "step": 94
+    },
+    {
+      "epoch": 0.15151515151515152,
+      "grad_norm": 8.838521003723145,
+      "learning_rate": 0.000182,
+      "loss": 2.0167,
+      "step": 95
+    },
+    {
+      "epoch": 0.15311004784688995,
+      "grad_norm": 9.63149356842041,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 1.6169,
+      "step": 96
+    },
+    {
+      "epoch": 0.1547049441786284,
+      "grad_norm": 6.012756824493408,
+      "learning_rate": 0.00018600000000000002,
+      "loss": 1.4477,
+      "step": 97
+    },
+    {
+      "epoch": 0.15629984051036683,
+      "grad_norm": 9.02092456817627,
+      "learning_rate": 0.000188,
+      "loss": 1.5999,
+      "step": 98
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 5.8646416664123535,
+      "learning_rate": 0.00019,
+      "loss": 1.2515,
+      "step": 99
+    },
+    {
+      "epoch": 0.1594896331738437,
+      "grad_norm": 3.3447864055633545,
+      "learning_rate": 0.000192,
+      "loss": 1.257,
+      "step": 100
+    },
+    {
+      "epoch": 0.16108452950558214,
+      "grad_norm": 8.706202507019043,
+      "learning_rate": 0.000194,
+      "loss": 2.0047,
+      "step": 101
+    },
+    {
+      "epoch": 0.16267942583732056,
+      "grad_norm": 17.863378524780273,
+      "learning_rate": 0.000196,
+      "loss": 2.421,
+      "step": 102
+    },
+    {
+      "epoch": 0.16427432216905902,
+      "grad_norm": 5.376917362213135,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 2.1448,
+      "step": 103
+    },
+    {
+      "epoch": 0.16586921850079744,
+      "grad_norm": 3.9824860095977783,
+      "learning_rate": 0.0002,
+      "loss": 1.7987,
+      "step": 104
+    },
+    {
+      "epoch": 0.1674641148325359,
+      "grad_norm": 6.7771382331848145,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 1.8173,
+      "step": 105
+    },
+    {
+      "epoch": 0.16905901116427433,
+      "grad_norm": 6.204737186431885,
+      "learning_rate": 0.000196,
+      "loss": 1.2615,
+      "step": 106
+    },
+    {
+      "epoch": 0.17065390749601275,
+      "grad_norm": 5.108335018157959,
+      "learning_rate": 0.000194,
+      "loss": 1.6966,
+      "step": 107
+    },
+    {
+      "epoch": 0.1722488038277512,
+      "grad_norm": 51.948585510253906,
+      "learning_rate": 0.000192,
+      "loss": 2.8226,
+      "step": 108
+    },
+    {
+      "epoch": 0.17384370015948963,
+      "grad_norm": 3.510647773742676,
+      "learning_rate": 0.00019,
+      "loss": 1.4454,
+      "step": 109
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 5.786037921905518,
+      "learning_rate": 0.000188,
+      "loss": 1.3979,
+      "step": 110
+    },
+    {
+      "epoch": 0.17703349282296652,
+      "grad_norm": 5.4267964363098145,
+      "learning_rate": 0.00018600000000000002,
+      "loss": 1.8775,
+      "step": 111
+    },
+    {
+      "epoch": 0.17862838915470494,
+      "grad_norm": 7.448083400726318,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 1.8377,
+      "step": 112
+    },
+    {
+      "epoch": 0.18022328548644337,
+      "grad_norm": 6.855521202087402,
+      "learning_rate": 0.000182,
+      "loss": 1.7079,
+      "step": 113
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 6.257575988769531,
+      "learning_rate": 0.00018,
+      "loss": 2.2364,
+      "step": 114
+    },
+    {
+      "epoch": 0.18341307814992025,
+      "grad_norm": 15.47193431854248,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 1.7272,
+      "step": 115
+    },
+    {
+      "epoch": 0.1850079744816587,
+      "grad_norm": 12.51389217376709,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 1.8385,
+      "step": 116
+    },
+    {
+      "epoch": 0.18660287081339713,
+      "grad_norm": 8.150806427001953,
+      "learning_rate": 0.000174,
+      "loss": 2.429,
+      "step": 117
+    },
+    {
+      "epoch": 0.18819776714513556,
+      "grad_norm": 29.065210342407227,
+      "learning_rate": 0.000172,
+      "loss": 1.3318,
+      "step": 118
+    },
+    {
+      "epoch": 0.189792663476874,
+      "grad_norm": 5.457766532897949,
+      "learning_rate": 0.00017,
+      "loss": 1.2329,
+      "step": 119
+    },
+    {
+      "epoch": 0.19138755980861244,
+      "grad_norm": 3.7080814838409424,
+      "learning_rate": 0.000168,
+      "loss": 1.1145,
+      "step": 120
+    },
+    {
+      "epoch": 0.19298245614035087,
+      "grad_norm": 5.2060065269470215,
+      "learning_rate": 0.000166,
+      "loss": 1.6808,
+      "step": 121
+    },
+    {
+      "epoch": 0.19457735247208932,
+      "grad_norm": 15.03097152709961,
+      "learning_rate": 0.000164,
+      "loss": 2.207,
+      "step": 122
+    },
+    {
+      "epoch": 0.19617224880382775,
+      "grad_norm": 3.1523945331573486,
+      "learning_rate": 0.000162,
+      "loss": 0.8121,
+      "step": 123
+    },
+    {
+      "epoch": 0.19776714513556617,
+      "grad_norm": 12.531198501586914,
+      "learning_rate": 0.00016,
+      "loss": 1.6493,
+      "step": 124
+    },
+    {
+      "epoch": 0.19936204146730463,
+      "grad_norm": 18.13838768005371,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 1.9895,
+      "step": 125
+    },
+    {
+      "epoch": 0.20095693779904306,
+      "grad_norm": 3.7068324089050293,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 1.2397,
+      "step": 126
+    },
+    {
+      "epoch": 0.2025518341307815,
+      "grad_norm": 3.565275192260742,
+      "learning_rate": 0.000154,
+      "loss": 1.1711,
+      "step": 127
+    },
+    {
+      "epoch": 0.20414673046251994,
+      "grad_norm": 2.20239520072937,
+      "learning_rate": 0.000152,
+      "loss": 1.8436,
+      "step": 128
+    },
+    {
+      "epoch": 0.20574162679425836,
+      "grad_norm": 3.103001117706299,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.0085,
+      "step": 129
+    },
+    {
+      "epoch": 0.20733652312599682,
+      "grad_norm": 3.8708302974700928,
+      "learning_rate": 0.000148,
+      "loss": 1.0336,
+      "step": 130
+    },
+    {
+      "epoch": 0.20893141945773525,
+      "grad_norm": 4.008622646331787,
+      "learning_rate": 0.000146,
+      "loss": 1.7669,
+      "step": 131
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 3.847217559814453,
+      "learning_rate": 0.000144,
+      "loss": 1.5163,
+      "step": 132
+    },
+    {
+      "epoch": 0.21212121212121213,
+      "grad_norm": 9.75152587890625,
+      "learning_rate": 0.000142,
+      "loss": 2.3286,
+      "step": 133
+    },
+    {
+      "epoch": 0.21371610845295055,
+      "grad_norm": 9.416215896606445,
+      "learning_rate": 0.00014,
+      "loss": 2.0397,
+      "step": 134
+    },
+    {
+      "epoch": 0.215311004784689,
+      "grad_norm": 8.208052635192871,
+      "learning_rate": 0.000138,
+      "loss": 1.7927,
+      "step": 135
+    },
+    {
+      "epoch": 0.21690590111642744,
+      "grad_norm": 11.827594757080078,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 2.1958,
+      "step": 136
+    },
+    {
+      "epoch": 0.21850079744816586,
+      "grad_norm": 5.788820266723633,
+      "learning_rate": 0.000134,
+      "loss": 1.8336,
+      "step": 137
+    },
+    {
+      "epoch": 0.22009569377990432,
+      "grad_norm": 3.6653785705566406,
+      "learning_rate": 0.000132,
+      "loss": 1.0477,
+      "step": 138
+    },
+    {
+      "epoch": 0.22169059011164274,
+      "grad_norm": 63.57593536376953,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 1.5667,
+      "step": 139
+    },
+    {
+      "epoch": 0.22328548644338117,
+      "grad_norm": 12.209519386291504,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 1.6414,
+      "step": 140
+    },
+    {
+      "epoch": 0.22488038277511962,
+      "grad_norm": 8.834230422973633,
+      "learning_rate": 0.000126,
+      "loss": 1.1292,
+      "step": 141
+    },
+    {
+      "epoch": 0.22647527910685805,
+      "grad_norm": 3.4640305042266846,
+      "learning_rate": 0.000124,
+      "loss": 1.3858,
+      "step": 142
+    },
+    {
+      "epoch": 0.22807017543859648,
+      "grad_norm": 5.367834091186523,
+      "learning_rate": 0.000122,
+      "loss": 1.4735,
+      "step": 143
+    },
+    {
+      "epoch": 0.22966507177033493,
+      "grad_norm": 3.5475995540618896,
+      "learning_rate": 0.00012,
+      "loss": 1.8889,
+      "step": 144
+    },
+    {
+      "epoch": 0.23125996810207336,
+      "grad_norm": 4.0117621421813965,
+      "learning_rate": 0.000118,
+      "loss": 0.6609,
+      "step": 145
+    },
+    {
+      "epoch": 0.23285486443381181,
+      "grad_norm": 2.641918420791626,
+      "learning_rate": 0.000116,
+      "loss": 1.439,
+      "step": 146
+    },
+    {
+      "epoch": 0.23444976076555024,
+      "grad_norm": 24.166297912597656,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 1.5829,
+      "step": 147
+    },
+    {
+      "epoch": 0.23604465709728867,
+      "grad_norm": 12.261051177978516,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 2.6259,
+      "step": 148
+    },
+    {
+      "epoch": 0.23763955342902712,
+      "grad_norm": 4.844594955444336,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 2.2162,
+      "step": 149
+    },
+    {
+      "epoch": 0.23923444976076555,
+      "grad_norm": 6.697972297668457,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 2.7383,
+      "step": 150
+    },
+    {
+      "epoch": 0.24082934609250398,
+      "grad_norm": 4.018860340118408,
+      "learning_rate": 0.00010600000000000002,
+      "loss": 2.4861,
+      "step": 151
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 7.205791473388672,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 1.4837,
+      "step": 152
+    },
+    {
+      "epoch": 0.24401913875598086,
+      "grad_norm": 8.773712158203125,
+      "learning_rate": 0.00010200000000000001,
+      "loss": 1.6268,
+      "step": 153
+    },
+    {
+      "epoch": 0.24561403508771928,
+      "grad_norm": 4.254454135894775,
+      "learning_rate": 0.0001,
+      "loss": 1.6405,
+      "step": 154
+    },
+    {
+      "epoch": 0.24720893141945774,
+      "grad_norm": 4.130655288696289,
+      "learning_rate": 9.8e-05,
+      "loss": 0.9554,
+      "step": 155
+    },
+    {
+      "epoch": 0.24880382775119617,
+      "grad_norm": 7.5216169357299805,
+      "learning_rate": 9.6e-05,
+      "loss": 1.3912,
+      "step": 156
+    },
+    {
+      "epoch": 0.2503987240829346,
+      "grad_norm": 70.0249252319336,
+      "learning_rate": 9.4e-05,
+      "loss": 1.8041,
+      "step": 157
+    },
+    {
+      "epoch": 0.25199362041467305,
+      "grad_norm": 3.9001526832580566,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 1.7109,
+      "step": 158
+    },
+    {
+      "epoch": 0.2535885167464115,
+      "grad_norm": 5.0965094566345215,
+      "learning_rate": 9e-05,
+      "loss": 1.0314,
+      "step": 159
+    },
+    {
+      "epoch": 0.2551834130781499,
+      "grad_norm": 3.0462706089019775,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 1.3541,
+      "step": 160
+    },
+    {
+      "epoch": 0.2567783094098884,
+      "grad_norm": 2.8334619998931885,
+      "learning_rate": 8.6e-05,
+      "loss": 1.9827,
+      "step": 161
+    },
+    {
+      "epoch": 0.2583732057416268,
+      "grad_norm": 5.991235256195068,
+      "learning_rate": 8.4e-05,
+      "loss": 1.4319,
+      "step": 162
+    },
+    {
+      "epoch": 0.25996810207336524,
+      "grad_norm": 6.401395320892334,
+      "learning_rate": 8.2e-05,
+      "loss": 1.912,
+      "step": 163
+    },
+    {
+      "epoch": 0.26156299840510366,
+      "grad_norm": 3.0269479751586914,
+      "learning_rate": 8e-05,
+      "loss": 1.5637,
+      "step": 164
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 10.380670547485352,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 1.8585,
+      "step": 165
+    },
+    {
+      "epoch": 0.2647527910685805,
+      "grad_norm": 7.375792503356934,
+      "learning_rate": 7.6e-05,
+      "loss": 1.8773,
+      "step": 166
+    },
+    {
+      "epoch": 0.266347687400319,
+      "grad_norm": 3.75229811668396,
+      "learning_rate": 7.4e-05,
+      "loss": 1.9936,
+      "step": 167
+    },
+    {
+      "epoch": 0.2679425837320574,
+      "grad_norm": 4.587918281555176,
+      "learning_rate": 7.2e-05,
+      "loss": 1.0402,
+      "step": 168
+    },
+    {
+      "epoch": 0.26953748006379585,
+      "grad_norm": 4.558103561401367,
+      "learning_rate": 7e-05,
+      "loss": 2.0408,
+      "step": 169
+    },
+    {
+      "epoch": 0.2711323763955343,
+      "grad_norm": 6.410488605499268,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 1.448,
+      "step": 170
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 9.21990966796875,
+      "learning_rate": 6.6e-05,
+      "loss": 0.963,
+      "step": 171
+    },
+    {
+      "epoch": 0.2743221690590112,
+      "grad_norm": 10.446578025817871,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 1.4381,
+      "step": 172
+    },
+    {
+      "epoch": 0.2759170653907496,
+      "grad_norm": 13.717737197875977,
+      "learning_rate": 6.2e-05,
+      "loss": 1.2965,
+      "step": 173
+    },
+    {
+      "epoch": 0.27751196172248804,
+      "grad_norm": 36.117401123046875,
+      "learning_rate": 6e-05,
+      "loss": 1.2144,
+      "step": 174
+    },
+    {
+      "epoch": 0.27910685805422647,
+      "grad_norm": 8.741774559020996,
+      "learning_rate": 5.8e-05,
+      "loss": 1.5059,
+      "step": 175
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "grad_norm": 3.040428400039673,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 1.4881,
+      "step": 176
+    },
+    {
+      "epoch": 0.2822966507177033,
+      "grad_norm": 7.401648044586182,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 0.7462,
+      "step": 177
+    },
+    {
+      "epoch": 0.2838915470494418,
+      "grad_norm": 3.3486616611480713,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 0.8773,
+      "step": 178
+    },
+    {
+      "epoch": 0.28548644338118023,
+      "grad_norm": 9.647512435913086,
+      "learning_rate": 5e-05,
+      "loss": 1.3147,
+      "step": 179
+    },
+    {
+      "epoch": 0.28708133971291866,
+      "grad_norm": 4.068251132965088,
+      "learning_rate": 4.8e-05,
+      "loss": 1.4796,
+      "step": 180
+    },
+    {
+      "epoch": 0.2886762360446571,
+      "grad_norm": 5.119231700897217,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.2465,
+      "step": 181
+    },
+    {
+      "epoch": 0.2902711323763955,
+      "grad_norm": 11.434249877929688,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 1.0839,
+      "step": 182
+    },
+    {
+      "epoch": 0.291866028708134,
+      "grad_norm": 2.6633126735687256,
+      "learning_rate": 4.2e-05,
+      "loss": 1.1653,
+      "step": 183
+    },
+    {
+      "epoch": 0.2934609250398724,
+      "grad_norm": 8.366178512573242,
+      "learning_rate": 4e-05,
+      "loss": 1.8623,
+      "step": 184
+    },
+    {
+      "epoch": 0.29505582137161085,
+      "grad_norm": 13.434002876281738,
+      "learning_rate": 3.8e-05,
+      "loss": 1.4409,
+      "step": 185
+    },
+    {
+      "epoch": 0.2966507177033493,
+      "grad_norm": 3.535421371459961,
+      "learning_rate": 3.6e-05,
+      "loss": 1.2367,
+      "step": 186
+    },
+    {
+      "epoch": 0.2982456140350877,
+      "grad_norm": 5.332886219024658,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 1.4744,
+      "step": 187
+    },
+    {
+      "epoch": 0.29984051036682613,
+      "grad_norm": 3.7560222148895264,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 1.3489,
+      "step": 188
+    },
+    {
+      "epoch": 0.3014354066985646,
+      "grad_norm": 4.513449668884277,
+      "learning_rate": 3e-05,
+      "loss": 1.3738,
+      "step": 189
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 7.969113826751709,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 1.7352,
+      "step": 190
+    },
+    {
+      "epoch": 0.30462519936204147,
+      "grad_norm": 4.11577033996582,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 1.6171,
+      "step": 191
+    },
+    {
+      "epoch": 0.3062200956937799,
+      "grad_norm": 4.727830410003662,
+      "learning_rate": 2.4e-05,
+      "loss": 1.3359,
+      "step": 192
+    },
+    {
+      "epoch": 0.3078149920255183,
+      "grad_norm": 1.7988307476043701,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 0.834,
+      "step": 193
+    },
+    {
+      "epoch": 0.3094098883572568,
+      "grad_norm": 4.455323696136475,
+      "learning_rate": 2e-05,
+      "loss": 1.2367,
+      "step": 194
+    },
+    {
+      "epoch": 0.31100478468899523,
+      "grad_norm": 5.334070682525635,
+      "learning_rate": 1.8e-05,
+      "loss": 1.0581,
+      "step": 195
+    },
+    {
+      "epoch": 0.31259968102073366,
+      "grad_norm": 4.967501640319824,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.2129,
+      "step": 196
+    },
+    {
+      "epoch": 0.3141945773524721,
+      "grad_norm": 4.0120673179626465,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 1.2043,
+      "step": 197
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 4.491064548492432,
+      "learning_rate": 1.2e-05,
+      "loss": 1.3383,
+      "step": 198
+    },
+    {
+      "epoch": 0.31738437001594894,
+      "grad_norm": 3.6377949714660645,
+      "learning_rate": 1e-05,
+      "loss": 1.2878,
+      "step": 199
+    },
+    {
+      "epoch": 0.3189792663476874,
+      "grad_norm": 3.7990877628326416,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.7178,
+      "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": 1717079281606656.0,
+  "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 sha256:0882660315b6d44be153a534ef331a1a652a772eed227ca85ccc42c14c629577
+size 5176

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0882660315b6d44be153a534ef331a1a652a772eed227ca85ccc42c14c629577
+size 5176