Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+base_model: ibm-granite/granite-3.0-8b-base
+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-base",
+  "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 sha256:0487db4e58534a2548a655596f2f578368be7a0bdb5a664ebcac212c964971c8
+size 34100216

checkpoint-200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: ibm-granite/granite-3.0-8b-base
+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-base",
+  "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 sha256:0487db4e58534a2548a655596f2f578368be7a0bdb5a664ebcac212c964971c8
+size 34100216

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5746457e5064b1dbc75f3545bd21d4601a5726eda5c8280f201d07f8d9ba24a
+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 sha256:40514b8a2212f479584d7334d3fcf8c4668d282c84b271544e6dc4c72021472c
+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": 3.3759636878967285,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.4074,
+      "step": 1
+    },
+    {
+      "epoch": 4.8507485311327104e-05,
+      "grad_norm": 0.8539016246795654,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.4688,
+      "step": 2
+    },
+    {
+      "epoch": 7.276122796699065e-05,
+      "grad_norm": NaN,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.2166,
+      "step": 3
+    },
+    {
+      "epoch": 9.701497062265421e-05,
+      "grad_norm": 0.8566086888313293,
+      "learning_rate": 6e-06,
+      "loss": 1.3767,
+      "step": 4
+    },
+    {
+      "epoch": 0.00012126871327831776,
+      "grad_norm": 1.564802885055542,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.3408,
+      "step": 5
+    },
+    {
+      "epoch": 0.0001455224559339813,
+      "grad_norm": 6.496278762817383,
+      "learning_rate": 1e-05,
+      "loss": 2.1242,
+      "step": 6
+    },
+    {
+      "epoch": 0.00016977619858964487,
+      "grad_norm": 3.3886003494262695,
+      "learning_rate": 1.2e-05,
+      "loss": 1.639,
+      "step": 7
+    },
+    {
+      "epoch": 0.00019402994124530841,
+      "grad_norm": 0.5676108598709106,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 1.547,
+      "step": 8
+    },
+    {
+      "epoch": 0.00021828368390097196,
+      "grad_norm": 7.636886119842529,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.6577,
+      "step": 9
+    },
+    {
+      "epoch": 0.00024253742655663553,
+      "grad_norm": 13.671367645263672,
+      "learning_rate": 1.8e-05,
+      "loss": 1.9861,
+      "step": 10
+    },
+    {
+      "epoch": 0.00026679116921229907,
+      "grad_norm": 1.700162649154663,
+      "learning_rate": 2e-05,
+      "loss": 2.1347,
+      "step": 11
+    },
+    {
+      "epoch": 0.0002910449118679626,
+      "grad_norm": 4.465837478637695,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 1.2903,
+      "step": 12
+    },
+    {
+      "epoch": 0.00031529865452362615,
+      "grad_norm": 5.200563430786133,
+      "learning_rate": 2.4e-05,
+      "loss": 1.727,
+      "step": 13
+    },
+    {
+      "epoch": 0.00033955239717928975,
+      "grad_norm": 2.4282960891723633,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 1.8629,
+      "step": 14
+    },
+    {
+      "epoch": 0.0003638061398349533,
+      "grad_norm": 0.8094596266746521,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 1.3653,
+      "step": 15
+    },
+    {
+      "epoch": 0.00038805988249061683,
+      "grad_norm": 0.8468468189239502,
+      "learning_rate": 3e-05,
+      "loss": 1.9853,
+      "step": 16
+    },
+    {
+      "epoch": 0.00041231362514628037,
+      "grad_norm": 0.9713991284370422,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 1.0837,
+      "step": 17
+    },
+    {
+      "epoch": 0.0004365673678019439,
+      "grad_norm": 0.8852229118347168,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 1.8255,
+      "step": 18
+    },
+    {
+      "epoch": 0.0004608211104576075,
+      "grad_norm": NaN,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 1.8453,
+      "step": 19
+    },
+    {
+      "epoch": 0.00048507485311327105,
+      "grad_norm": 0.7369140982627869,
+      "learning_rate": 3.6e-05,
+      "loss": 1.4695,
+      "step": 20
+    },
+    {
+      "epoch": 0.0005093285957689346,
+      "grad_norm": 0.7990018129348755,
+      "learning_rate": 3.8e-05,
+      "loss": 0.9667,
+      "step": 21
+    },
+    {
+      "epoch": 0.0005335823384245981,
+      "grad_norm": 51.18899917602539,
+      "learning_rate": 4e-05,
+      "loss": 2.049,
+      "step": 22
+    },
+    {
+      "epoch": 0.0005578360810802617,
+      "grad_norm": 2.142543315887451,
+      "learning_rate": 4.2e-05,
+      "loss": 1.7967,
+      "step": 23
+    },
+    {
+      "epoch": 0.0005820898237359252,
+      "grad_norm": 14.483644485473633,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 1.6066,
+      "step": 24
+    },
+    {
+      "epoch": 0.0006063435663915888,
+      "grad_norm": 0.4434223771095276,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.9649,
+      "step": 25
+    },
+    {
+      "epoch": 0.0006305973090472523,
+      "grad_norm": 2.3446133136749268,
+      "learning_rate": 4.8e-05,
+      "loss": 2.2895,
+      "step": 26
+    },
+    {
+      "epoch": 0.000654851051702916,
+      "grad_norm": 7.05695104598999,
+      "learning_rate": 5e-05,
+      "loss": 1.5174,
+      "step": 27
+    },
+    {
+      "epoch": 0.0006791047943585795,
+      "grad_norm": 1.1299482583999634,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 1.6502,
+      "step": 28
+    },
+    {
+      "epoch": 0.000703358537014243,
+      "grad_norm": 1.1360725164413452,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 1.9164,
+      "step": 29
+    },
+    {
+      "epoch": 0.0007276122796699066,
+      "grad_norm": 0.6310778260231018,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 1.3889,
+      "step": 30
+    },
+    {
+      "epoch": 0.0007518660223255701,
+      "grad_norm": 23.649295806884766,
+      "learning_rate": 5.8e-05,
+      "loss": 1.8868,
+      "step": 31
+    },
+    {
+      "epoch": 0.0007761197649812337,
+      "grad_norm": 1.4656137228012085,
+      "learning_rate": 6e-05,
+      "loss": 2.1166,
+      "step": 32
+    },
+    {
+      "epoch": 0.0008003735076368972,
+      "grad_norm": 1.1650835275650024,
+      "learning_rate": 6.2e-05,
+      "loss": 1.6361,
+      "step": 33
+    },
+    {
+      "epoch": 0.0008246272502925607,
+      "grad_norm": 3.5989675521850586,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 1.9528,
+      "step": 34
+    },
+    {
+      "epoch": 0.0008488809929482243,
+      "grad_norm": NaN,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 1.1095,
+      "step": 35
+    },
+    {
+      "epoch": 0.0008731347356038878,
+      "grad_norm": 0.7551969885826111,
+      "learning_rate": 6.6e-05,
+      "loss": 1.4748,
+      "step": 36
+    },
+    {
+      "epoch": 0.0008973884782595515,
+      "grad_norm": 0.7345149517059326,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 1.3746,
+      "step": 37
+    },
+    {
+      "epoch": 0.000921642220915215,
+      "grad_norm": 0.96466463804245,
+      "learning_rate": 7e-05,
+      "loss": 1.3491,
+      "step": 38
+    },
+    {
+      "epoch": 0.0009458959635708786,
+      "grad_norm": 0.895024836063385,
+      "learning_rate": 7.2e-05,
+      "loss": 1.3976,
+      "step": 39
+    },
+    {
+      "epoch": 0.0009701497062265421,
+      "grad_norm": 2.5485947132110596,
+      "learning_rate": 7.4e-05,
+      "loss": 1.6924,
+      "step": 40
+    },
+    {
+      "epoch": 0.0009944034488822055,
+      "grad_norm": 14.429283142089844,
+      "learning_rate": 7.6e-05,
+      "loss": 1.2937,
+      "step": 41
+    },
+    {
+      "epoch": 0.0010186571915378692,
+      "grad_norm": 0.8819990158081055,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 1.3237,
+      "step": 42
+    },
+    {
+      "epoch": 0.0010429109341935328,
+      "grad_norm": 1.2532185316085815,
+      "learning_rate": 8e-05,
+      "loss": 1.2843,
+      "step": 43
+    },
+    {
+      "epoch": 0.0010671646768491963,
+      "grad_norm": 3.7754809856414795,
+      "learning_rate": 8.2e-05,
+      "loss": 2.0701,
+      "step": 44
+    },
+    {
+      "epoch": 0.00109141841950486,
+      "grad_norm": 6.247189044952393,
+      "learning_rate": 8.4e-05,
+      "loss": 1.3514,
+      "step": 45
+    },
+    {
+      "epoch": 0.0011156721621605234,
+      "grad_norm": 2.4143786430358887,
+      "learning_rate": 8.6e-05,
+      "loss": 1.3366,
+      "step": 46
+    },
+    {
+      "epoch": 0.001139925904816187,
+      "grad_norm": 0.9999021887779236,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 1.6014,
+      "step": 47
+    },
+    {
+      "epoch": 0.0011641796474718504,
+      "grad_norm": 10.256402015686035,
+      "learning_rate": 9e-05,
+      "loss": 1.5158,
+      "step": 48
+    },
+    {
+      "epoch": 0.001188433390127514,
+      "grad_norm": 3.1409249305725098,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 1.2433,
+      "step": 49
+    },
+    {
+      "epoch": 0.0012126871327831775,
+      "grad_norm": 5.032261371612549,
+      "learning_rate": 9.4e-05,
+      "loss": 1.9222,
+      "step": 50
+    },
+    {
+      "epoch": 0.0012369408754388412,
+      "grad_norm": 32.46524429321289,
+      "learning_rate": 9.6e-05,
+      "loss": 1.944,
+      "step": 51
+    },
+    {
+      "epoch": 0.0012611946180945046,
+      "grad_norm": 3.3015825748443604,
+      "learning_rate": 9.8e-05,
+      "loss": 1.6905,
+      "step": 52
+    },
+    {
+      "epoch": 0.0012854483607501683,
+      "grad_norm": 33.24071502685547,
+      "learning_rate": 0.0001,
+      "loss": 1.8358,
+      "step": 53
+    },
+    {
+      "epoch": 0.001309702103405832,
+      "grad_norm": 1.4521846771240234,
+      "learning_rate": 0.00010200000000000001,
+      "loss": 1.6665,
+      "step": 54
+    },
+    {
+      "epoch": 0.0013339558460614953,
+      "grad_norm": 1.9511698484420776,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 1.2289,
+      "step": 55
+    },
+    {
+      "epoch": 0.001358209588717159,
+      "grad_norm": 7.6353535652160645,
+      "learning_rate": 0.00010600000000000002,
+      "loss": 1.762,
+      "step": 56
+    },
+    {
+      "epoch": 0.0013824633313728224,
+      "grad_norm": 1.035163164138794,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 1.4294,
+      "step": 57
+    },
+    {
+      "epoch": 0.001406717074028486,
+      "grad_norm": 4.369189262390137,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 1.4502,
+      "step": 58
+    },
+    {
+      "epoch": 0.0014309708166841495,
+      "grad_norm": 1.308000087738037,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 1.4871,
+      "step": 59
+    },
+    {
+      "epoch": 0.0014552245593398132,
+      "grad_norm": 0.9026333093643188,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 1.431,
+      "step": 60
+    },
+    {
+      "epoch": 0.0014794783019954766,
+      "grad_norm": 1.266846776008606,
+      "learning_rate": 0.000116,
+      "loss": 1.5601,
+      "step": 61
+    },
+    {
+      "epoch": 0.0015037320446511402,
+      "grad_norm": 2.569223642349243,
+      "learning_rate": 0.000118,
+      "loss": 1.3147,
+      "step": 62
+    },
+    {
+      "epoch": 0.0015279857873068039,
+      "grad_norm": 0.6180663108825684,
+      "learning_rate": 0.00012,
+      "loss": 0.735,
+      "step": 63
+    },
+    {
+      "epoch": 0.0015522395299624673,
+      "grad_norm": 7.6248650550842285,
+      "learning_rate": 0.000122,
+      "loss": 1.1034,
+      "step": 64
+    },
+    {
+      "epoch": 0.001576493272618131,
+      "grad_norm": NaN,
+      "learning_rate": 0.000122,
+      "loss": 2.0957,
+      "step": 65
+    },
+    {
+      "epoch": 0.0016007470152737944,
+      "grad_norm": 17.51434326171875,
+      "learning_rate": 0.000124,
+      "loss": 1.7337,
+      "step": 66
+    },
+    {
+      "epoch": 0.001625000757929458,
+      "grad_norm": 4.455969333648682,
+      "learning_rate": 0.000126,
+      "loss": 1.8453,
+      "step": 67
+    },
+    {
+      "epoch": 0.0016492545005851215,
+      "grad_norm": 3.6060261726379395,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 1.304,
+      "step": 68
+    },
+    {
+      "epoch": 0.0016735082432407851,
+      "grad_norm": 1.1424020528793335,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 1.2339,
+      "step": 69
+    },
+    {
+      "epoch": 0.0016977619858964486,
+      "grad_norm": 1.294066309928894,
+      "learning_rate": 0.000132,
+      "loss": 1.3406,
+      "step": 70
+    },
+    {
+      "epoch": 0.0017220157285521122,
+      "grad_norm": 8.3845796585083,
+      "learning_rate": 0.000134,
+      "loss": 2.0366,
+      "step": 71
+    },
+    {
+      "epoch": 0.0017462694712077757,
+      "grad_norm": 7.098409175872803,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 1.566,
+      "step": 72
+    },
+    {
+      "epoch": 0.0017705232138634393,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 1.1374,
+      "step": 73
+    },
+    {
+      "epoch": 0.001794776956519103,
+      "grad_norm": 3.7947475910186768,
+      "learning_rate": 0.000138,
+      "loss": 1.4067,
+      "step": 74
+    },
+    {
+      "epoch": 0.0018190306991747664,
+      "grad_norm": 3.4975695610046387,
+      "learning_rate": 0.00014,
+      "loss": 1.4905,
+      "step": 75
+    },
+    {
+      "epoch": 0.00184328444183043,
+      "grad_norm": 1.821387529373169,
+      "learning_rate": 0.000142,
+      "loss": 1.289,
+      "step": 76
+    },
+    {
+      "epoch": 0.0018675381844860935,
+      "grad_norm": 58.30936050415039,
+      "learning_rate": 0.000144,
+      "loss": 1.4909,
+      "step": 77
+    },
+    {
+      "epoch": 0.0018917919271417571,
+      "grad_norm": 1.3323521614074707,
+      "learning_rate": 0.000146,
+      "loss": 1.1766,
+      "step": 78
+    },
+    {
+      "epoch": 0.0019160456697974206,
+      "grad_norm": 5.184061050415039,
+      "learning_rate": 0.000148,
+      "loss": 0.9555,
+      "step": 79
+    },
+    {
+      "epoch": 0.0019402994124530842,
+      "grad_norm": 3.7887625694274902,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.8287,
+      "step": 80
+    },
+    {
+      "epoch": 0.001964553155108748,
+      "grad_norm": 0.8411690592765808,
+      "learning_rate": 0.000152,
+      "loss": 1.1176,
+      "step": 81
+    },
+    {
+      "epoch": 0.001988806897764411,
+      "grad_norm": 1.881020426750183,
+      "learning_rate": 0.000154,
+      "loss": 1.4231,
+      "step": 82
+    },
+    {
+      "epoch": 0.0020130606404200747,
+      "grad_norm": 2.2068991661071777,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 1.4049,
+      "step": 83
+    },
+    {
+      "epoch": 0.0020373143830757384,
+      "grad_norm": 4.380375862121582,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 1.0798,
+      "step": 84
+    },
+    {
+      "epoch": 0.002061568125731402,
+      "grad_norm": 1.7205640077590942,
+      "learning_rate": 0.00016,
+      "loss": 1.4954,
+      "step": 85
+    },
+    {
+      "epoch": 0.0020858218683870657,
+      "grad_norm": 1.5813369750976562,
+      "learning_rate": 0.000162,
+      "loss": 1.4113,
+      "step": 86
+    },
+    {
+      "epoch": 0.002110075611042729,
+      "grad_norm": 1.3017473220825195,
+      "learning_rate": 0.000164,
+      "loss": 1.2315,
+      "step": 87
+    },
+    {
+      "epoch": 0.0021343293536983925,
+      "grad_norm": 2.0372846126556396,
+      "learning_rate": 0.000166,
+      "loss": 1.5282,
+      "step": 88
+    },
+    {
+      "epoch": 0.002158583096354056,
+      "grad_norm": 1.0349255800247192,
+      "learning_rate": 0.000168,
+      "loss": 1.3279,
+      "step": 89
+    },
+    {
+      "epoch": 0.00218283683900972,
+      "grad_norm": 2.119569778442383,
+      "learning_rate": 0.00017,
+      "loss": 1.0482,
+      "step": 90
+    },
+    {
+      "epoch": 0.002207090581665383,
+      "grad_norm": 2.0538179874420166,
+      "learning_rate": 0.000172,
+      "loss": 1.0129,
+      "step": 91
+    },
+    {
+      "epoch": 0.0022313443243210467,
+      "grad_norm": 1.4903944730758667,
+      "learning_rate": 0.000174,
+      "loss": 1.7894,
+      "step": 92
+    },
+    {
+      "epoch": 0.0022555980669767104,
+      "grad_norm": 5.269598007202148,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 1.1085,
+      "step": 93
+    },
+    {
+      "epoch": 0.002279851809632374,
+      "grad_norm": 2.082563877105713,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 1.4559,
+      "step": 94
+    },
+    {
+      "epoch": 0.0023041055522880377,
+      "grad_norm": 1.0695875883102417,
+      "learning_rate": 0.00018,
+      "loss": 1.5581,
+      "step": 95
+    },
+    {
+      "epoch": 0.002328359294943701,
+      "grad_norm": 1.9814307689666748,
+      "learning_rate": 0.000182,
+      "loss": 1.5945,
+      "step": 96
+    },
+    {
+      "epoch": 0.0023526130375993645,
+      "grad_norm": 8.308389663696289,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 2.0305,
+      "step": 97
+    },
+    {
+      "epoch": 0.002376866780255028,
+      "grad_norm": 1.8079288005828857,
+      "learning_rate": 0.00018600000000000002,
+      "loss": 1.4862,
+      "step": 98
+    },
+    {
+      "epoch": 0.002401120522910692,
+      "grad_norm": 12.573166847229004,
+      "learning_rate": 0.000188,
+      "loss": 1.7458,
+      "step": 99
+    },
+    {
+      "epoch": 0.002425374265566355,
+      "grad_norm": 33.789764404296875,
+      "learning_rate": 0.00019,
+      "loss": 1.3982,
+      "step": 100
+    },
+    {
+      "epoch": 0.0024496280082220187,
+      "grad_norm": 27.591976165771484,
+      "learning_rate": 0.000192,
+      "loss": 1.5771,
+      "step": 101
+    },
+    {
+      "epoch": 0.0024738817508776823,
+      "grad_norm": 1.4807827472686768,
+      "learning_rate": 0.000194,
+      "loss": 1.462,
+      "step": 102
+    },
+    {
+      "epoch": 0.002498135493533346,
+      "grad_norm": 1.479779601097107,
+      "learning_rate": 0.000196,
+      "loss": 1.5715,
+      "step": 103
+    },
+    {
+      "epoch": 0.002522389236189009,
+      "grad_norm": 1.569394826889038,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 1.7968,
+      "step": 104
+    },
+    {
+      "epoch": 0.002546642978844673,
+      "grad_norm": 1.3037728071212769,
+      "learning_rate": 0.0002,
+      "loss": 1.2281,
+      "step": 105
+    },
+    {
+      "epoch": 0.0025708967215003365,
+      "grad_norm": 3.430941104888916,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 1.5046,
+      "step": 106
+    },
+    {
+      "epoch": 0.002595150464156,
+      "grad_norm": 1.2662192583084106,
+      "learning_rate": 0.000196,
+      "loss": 1.1589,
+      "step": 107
+    },
+    {
+      "epoch": 0.002619404206811664,
+      "grad_norm": 1.0078253746032715,
+      "learning_rate": 0.000194,
+      "loss": 1.2159,
+      "step": 108
+    },
+    {
+      "epoch": 0.002643657949467327,
+      "grad_norm": 1.0011709928512573,
+      "learning_rate": 0.000192,
+      "loss": 1.3889,
+      "step": 109
+    },
+    {
+      "epoch": 0.0026679116921229907,
+      "grad_norm": 1.0177195072174072,
+      "learning_rate": 0.00019,
+      "loss": 1.5495,
+      "step": 110
+    },
+    {
+      "epoch": 0.0026921654347786543,
+      "grad_norm": 14.817512512207031,
+      "learning_rate": 0.000188,
+      "loss": 1.3749,
+      "step": 111
+    },
+    {
+      "epoch": 0.002716419177434318,
+      "grad_norm": 2.8248116970062256,
+      "learning_rate": 0.00018600000000000002,
+      "loss": 1.4093,
+      "step": 112
+    },
+    {
+      "epoch": 0.002740672920089981,
+      "grad_norm": 1.23388671875,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 1.662,
+      "step": 113
+    },
+    {
+      "epoch": 0.002764926662745645,
+      "grad_norm": 1.2018444538116455,
+      "learning_rate": 0.000182,
+      "loss": 1.561,
+      "step": 114
+    },
+    {
+      "epoch": 0.0027891804054013085,
+      "grad_norm": 1.6609792709350586,
+      "learning_rate": 0.00018,
+      "loss": 1.449,
+      "step": 115
+    },
+    {
+      "epoch": 0.002813434148056972,
+      "grad_norm": 4.717409610748291,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 1.3023,
+      "step": 116
+    },
+    {
+      "epoch": 0.002837687890712636,
+      "grad_norm": 0.6800332069396973,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 1.1162,
+      "step": 117
+    },
+    {
+      "epoch": 0.002861941633368299,
+      "grad_norm": 1.1162289381027222,
+      "learning_rate": 0.000174,
+      "loss": 1.2826,
+      "step": 118
+    },
+    {
+      "epoch": 0.0028861953760239627,
+      "grad_norm": 0.9007352590560913,
+      "learning_rate": 0.000172,
+      "loss": 1.7017,
+      "step": 119
+    },
+    {
+      "epoch": 0.0029104491186796263,
+      "grad_norm": 2.0487279891967773,
+      "learning_rate": 0.00017,
+      "loss": 2.0916,
+      "step": 120
+    },
+    {
+      "epoch": 0.00293470286133529,
+      "grad_norm": 4.298633098602295,
+      "learning_rate": 0.000168,
+      "loss": 2.2025,
+      "step": 121
+    },
+    {
+      "epoch": 0.002958956603990953,
+      "grad_norm": 1.0514113903045654,
+      "learning_rate": 0.000166,
+      "loss": 1.3972,
+      "step": 122
+    },
+    {
+      "epoch": 0.002983210346646617,
+      "grad_norm": 0.7477086186408997,
+      "learning_rate": 0.000164,
+      "loss": 1.0473,
+      "step": 123
+    },
+    {
+      "epoch": 0.0030074640893022805,
+      "grad_norm": 1.2515380382537842,
+      "learning_rate": 0.000162,
+      "loss": 1.4222,
+      "step": 124
+    },
+    {
+      "epoch": 0.003031717831957944,
+      "grad_norm": 1.1901217699050903,
+      "learning_rate": 0.00016,
+      "loss": 1.0811,
+      "step": 125
+    },
+    {
+      "epoch": 0.0030559715746136078,
+      "grad_norm": 1.3582122325897217,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 1.2179,
+      "step": 126
+    },
+    {
+      "epoch": 0.003080225317269271,
+      "grad_norm": 0.7772126197814941,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 1.1056,
+      "step": 127
+    },
+    {
+      "epoch": 0.0031044790599249346,
+      "grad_norm": 3.8524062633514404,
+      "learning_rate": 0.000154,
+      "loss": 1.1881,
+      "step": 128
+    },
+    {
+      "epoch": 0.0031287328025805983,
+      "grad_norm": 1.8099156618118286,
+      "learning_rate": 0.000152,
+      "loss": 1.6343,
+      "step": 129
+    },
+    {
+      "epoch": 0.003152986545236262,
+      "grad_norm": 1.2134389877319336,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.3875,
+      "step": 130
+    },
+    {
+      "epoch": 0.003177240287891925,
+      "grad_norm": 0.938895583152771,
+      "learning_rate": 0.000148,
+      "loss": 1.2225,
+      "step": 131
+    },
+    {
+      "epoch": 0.003201494030547589,
+      "grad_norm": 1.9306858777999878,
+      "learning_rate": 0.000146,
+      "loss": 1.2144,
+      "step": 132
+    },
+    {
+      "epoch": 0.0032257477732032525,
+      "grad_norm": 1.3297972679138184,
+      "learning_rate": 0.000144,
+      "loss": 1.4381,
+      "step": 133
+    },
+    {
+      "epoch": 0.003250001515858916,
+      "grad_norm": 1.270509958267212,
+      "learning_rate": 0.000142,
+      "loss": 1.1591,
+      "step": 134
+    },
+    {
+      "epoch": 0.0032742552585145793,
+      "grad_norm": 3.317193031311035,
+      "learning_rate": 0.00014,
+      "loss": 1.2585,
+      "step": 135
+    },
+    {
+      "epoch": 0.003298509001170243,
+      "grad_norm": 1.2975448369979858,
+      "learning_rate": 0.000138,
+      "loss": 1.571,
+      "step": 136
+    },
+    {
+      "epoch": 0.0033227627438259066,
+      "grad_norm": 1.0426270961761475,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 1.8555,
+      "step": 137
+    },
+    {
+      "epoch": 0.0033470164864815703,
+      "grad_norm": 1.228779673576355,
+      "learning_rate": 0.000134,
+      "loss": 1.3992,
+      "step": 138
+    },
+    {
+      "epoch": 0.003371270229137234,
+      "grad_norm": 0.977001428604126,
+      "learning_rate": 0.000132,
+      "loss": 1.1395,
+      "step": 139
+    },
+    {
+      "epoch": 0.003395523971792897,
+      "grad_norm": 1.0894217491149902,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 1.4242,
+      "step": 140
+    },
+    {
+      "epoch": 0.003419777714448561,
+      "grad_norm": 1.0413155555725098,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 1.4771,
+      "step": 141
+    },
+    {
+      "epoch": 0.0034440314571042244,
+      "grad_norm": 1.2907966375350952,
+      "learning_rate": 0.000126,
+      "loss": 1.5202,
+      "step": 142
+    },
+    {
+      "epoch": 0.003468285199759888,
+      "grad_norm": 0.8118016123771667,
+      "learning_rate": 0.000124,
+      "loss": 1.5335,
+      "step": 143
+    },
+    {
+      "epoch": 0.0034925389424155513,
+      "grad_norm": 1.329568862915039,
+      "learning_rate": 0.000122,
+      "loss": 1.7877,
+      "step": 144
+    },
+    {
+      "epoch": 0.003516792685071215,
+      "grad_norm": 0.6988470554351807,
+      "learning_rate": 0.00012,
+      "loss": 0.6288,
+      "step": 145
+    },
+    {
+      "epoch": 0.0035410464277268786,
+      "grad_norm": 2.3587098121643066,
+      "learning_rate": 0.000118,
+      "loss": 1.2359,
+      "step": 146
+    },
+    {
+      "epoch": 0.0035653001703825423,
+      "grad_norm": 1.1087194681167603,
+      "learning_rate": 0.000116,
+      "loss": 1.3769,
+      "step": 147
+    },
+    {
+      "epoch": 0.003589553913038206,
+      "grad_norm": 1.6822993755340576,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 1.3112,
+      "step": 148
+    },
+    {
+      "epoch": 0.003613807655693869,
+      "grad_norm": 1.3227869272232056,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 1.4754,
+      "step": 149
+    },
+    {
+      "epoch": 0.0036380613983495328,
+      "grad_norm": 1.1278481483459473,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 1.1768,
+      "step": 150
+    },
+    {
+      "epoch": 0.0036623151410051964,
+      "grad_norm": 1.2085745334625244,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 1.4345,
+      "step": 151
+    },
+    {
+      "epoch": 0.00368656888366086,
+      "grad_norm": 1.0850399732589722,
+      "learning_rate": 0.00010600000000000002,
+      "loss": 1.2432,
+      "step": 152
+    },
+    {
+      "epoch": 0.0037108226263165233,
+      "grad_norm": 1.2463059425354004,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 1.5501,
+      "step": 153
+    },
+    {
+      "epoch": 0.003735076368972187,
+      "grad_norm": 1.059967041015625,
+      "learning_rate": 0.00010200000000000001,
+      "loss": 1.0448,
+      "step": 154
+    },
+    {
+      "epoch": 0.0037593301116278506,
+      "grad_norm": 2.2503929138183594,
+      "learning_rate": 0.0001,
+      "loss": 1.4892,
+      "step": 155
+    },
+    {
+      "epoch": 0.0037835838542835142,
+      "grad_norm": 0.8803784251213074,
+      "learning_rate": 9.8e-05,
+      "loss": 1.2764,
+      "step": 156
+    },
+    {
+      "epoch": 0.003807837596939178,
+      "grad_norm": 1.5173571109771729,
+      "learning_rate": 9.6e-05,
+      "loss": 1.0656,
+      "step": 157
+    },
+    {
+      "epoch": 0.003832091339594841,
+      "grad_norm": 2.0226430892944336,
+      "learning_rate": 9.4e-05,
+      "loss": 1.1382,
+      "step": 158
+    },
+    {
+      "epoch": 0.0038563450822505048,
+      "grad_norm": 1.9149307012557983,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 1.4105,
+      "step": 159
+    },
+    {
+      "epoch": 0.0038805988249061684,
+      "grad_norm": 0.9839889407157898,
+      "learning_rate": 9e-05,
+      "loss": 1.7808,
+      "step": 160
+    },
+    {
+      "epoch": 0.003904852567561832,
+      "grad_norm": 1.306378722190857,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 1.4799,
+      "step": 161
+    },
+    {
+      "epoch": 0.003929106310217496,
+      "grad_norm": 1.9649689197540283,
+      "learning_rate": 8.6e-05,
+      "loss": 1.2497,
+      "step": 162
+    },
+    {
+      "epoch": 0.003953360052873159,
+      "grad_norm": 0.8306687474250793,
+      "learning_rate": 8.4e-05,
+      "loss": 1.1058,
+      "step": 163
+    },
+    {
+      "epoch": 0.003977613795528822,
+      "grad_norm": 1.034351110458374,
+      "learning_rate": 8.2e-05,
+      "loss": 0.9346,
+      "step": 164
+    },
+    {
+      "epoch": 0.004001867538184486,
+      "grad_norm": 1.165528416633606,
+      "learning_rate": 8e-05,
+      "loss": 1.2315,
+      "step": 165
+    },
+    {
+      "epoch": 0.0040261212808401494,
+      "grad_norm": 1.3174549341201782,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 1.7447,
+      "step": 166
+    },
+    {
+      "epoch": 0.004050375023495813,
+      "grad_norm": 1.8279471397399902,
+      "learning_rate": 7.6e-05,
+      "loss": 1.6226,
+      "step": 167
+    },
+    {
+      "epoch": 0.004074628766151477,
+      "grad_norm": 1.1315997838974,
+      "learning_rate": 7.4e-05,
+      "loss": 1.2114,
+      "step": 168
+    },
+    {
+      "epoch": 0.00409888250880714,
+      "grad_norm": 1.0842983722686768,
+      "learning_rate": 7.2e-05,
+      "loss": 1.1462,
+      "step": 169
+    },
+    {
+      "epoch": 0.004123136251462804,
+      "grad_norm": 0.8647174835205078,
+      "learning_rate": 7e-05,
+      "loss": 0.9729,
+      "step": 170
+    },
+    {
+      "epoch": 0.004147389994118468,
+      "grad_norm": 0.9712747931480408,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 1.2886,
+      "step": 171
+    },
+    {
+      "epoch": 0.004171643736774131,
+      "grad_norm": 1.3875259160995483,
+      "learning_rate": 6.6e-05,
+      "loss": 1.5696,
+      "step": 172
+    },
+    {
+      "epoch": 0.004195897479429794,
+      "grad_norm": 1.1321961879730225,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 1.4366,
+      "step": 173
+    },
+    {
+      "epoch": 0.004220151222085458,
+      "grad_norm": 5.357350826263428,
+      "learning_rate": 6.2e-05,
+      "loss": 1.5292,
+      "step": 174
+    },
+    {
+      "epoch": 0.004244404964741121,
+      "grad_norm": 0.7717924118041992,
+      "learning_rate": 6e-05,
+      "loss": 1.3228,
+      "step": 175
+    },
+    {
+      "epoch": 0.004268658707396785,
+      "grad_norm": 1.9575989246368408,
+      "learning_rate": 5.8e-05,
+      "loss": 1.1391,
+      "step": 176
+    },
+    {
+      "epoch": 0.004292912450052449,
+      "grad_norm": 1.1362651586532593,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 1.5378,
+      "step": 177
+    },
+    {
+      "epoch": 0.004317166192708112,
+      "grad_norm": 1.5834994316101074,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 1.7488,
+      "step": 178
+    },
+    {
+      "epoch": 0.004341419935363776,
+      "grad_norm": Infinity,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 1.945,
+      "step": 179
+    },
+    {
+      "epoch": 0.00436567367801944,
+      "grad_norm": 1.2279846668243408,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 1.2098,
+      "step": 180
+    },
+    {
+      "epoch": 0.004389927420675103,
+      "grad_norm": 0.9098599553108215,
+      "learning_rate": 5e-05,
+      "loss": 1.2899,
+      "step": 181
+    },
+    {
+      "epoch": 0.004414181163330766,
+      "grad_norm": 1.4090386629104614,
+      "learning_rate": 4.8e-05,
+      "loss": 1.9194,
+      "step": 182
+    },
+    {
+      "epoch": 0.00443843490598643,
+      "grad_norm": 0.9789434671401978,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.9409,
+      "step": 183
+    },
+    {
+      "epoch": 0.004462688648642093,
+      "grad_norm": 0.8534678220748901,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 1.3122,
+      "step": 184
+    },
+    {
+      "epoch": 0.004486942391297757,
+      "grad_norm": 0.9604746103286743,
+      "learning_rate": 4.2e-05,
+      "loss": 1.2598,
+      "step": 185
+    },
+    {
+      "epoch": 0.004511196133953421,
+      "grad_norm": 1.2235528230667114,
+      "learning_rate": 4e-05,
+      "loss": 1.1669,
+      "step": 186
+    },
+    {
+      "epoch": 0.004535449876609084,
+      "grad_norm": 1.1576164960861206,
+      "learning_rate": 3.8e-05,
+      "loss": 1.2882,
+      "step": 187
+    },
+    {
+      "epoch": 0.004559703619264748,
+      "grad_norm": 2.6080610752105713,
+      "learning_rate": 3.6e-05,
+      "loss": 1.7071,
+      "step": 188
+    },
+    {
+      "epoch": 0.004583957361920412,
+      "grad_norm": 1.0198453664779663,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 1.5359,
+      "step": 189
+    },
+    {
+      "epoch": 0.004608211104576075,
+      "grad_norm": 0.536956250667572,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.99,
+      "step": 190
+    },
+    {
+      "epoch": 0.004632464847231738,
+      "grad_norm": 1.0942273139953613,
+      "learning_rate": 3e-05,
+      "loss": 1.2758,
+      "step": 191
+    },
+    {
+      "epoch": 0.004656718589887402,
+      "grad_norm": 0.7441216707229614,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 1.1892,
+      "step": 192
+    },
+    {
+      "epoch": 0.004680972332543065,
+      "grad_norm": 1.032776951789856,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 1.1905,
+      "step": 193
+    },
+    {
+      "epoch": 0.004705226075198729,
+      "grad_norm": 1.4048435688018799,
+      "learning_rate": 2.4e-05,
+      "loss": 1.5178,
+      "step": 194
+    },
+    {
+      "epoch": 0.004729479817854393,
+      "grad_norm": 1.3756521940231323,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 1.4318,
+      "step": 195
+    },
+    {
+      "epoch": 0.004753733560510056,
+      "grad_norm": 1.066291332244873,
+      "learning_rate": 2e-05,
+      "loss": 1.3325,
+      "step": 196
+    },
+    {
+      "epoch": 0.00477798730316572,
+      "grad_norm": 1.1176751852035522,
+      "learning_rate": 1.8e-05,
+      "loss": 1.403,
+      "step": 197
+    },
+    {
+      "epoch": 0.004802241045821384,
+      "grad_norm": 1.995957851409912,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.3541,
+      "step": 198
+    },
+    {
+      "epoch": 0.004826494788477047,
+      "grad_norm": 2.2354772090911865,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 1.6087,
+      "step": 199
+    },
+    {
+      "epoch": 0.00485074853113271,
+      "grad_norm": 19.62826919555664,
+      "learning_rate": 1.2e-05,
+      "loss": 1.8031,
+      "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": 6033065352437760.0,
+  "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 sha256:43d033efd662a8a45a3612dd98272e5bd1a161947f423340e92b2ec66e5de383
+size 5176

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43d033efd662a8a45a3612dd98272e5bd1a161947f423340e92b2ec66e5de383
+size 5176