Upload folder using huggingface_hub

.gitattributes

@@ -55,3 +55,6 @@ sft_devstral_24B/wandb/offline-run-20251223_134236-sicxj35d/run-sicxj35d.wandb f
 sft_devstral_24B/wandb/offline-run-20251223_134432-y3kepwdy/run-y3kepwdy.wandb filter=lfs diff=lfs merge=lfs -text
 sft_devstral_24B/wandb/run-20251223_134618-9jed4peb/run-9jed4peb.wandb filter=lfs diff=lfs merge=lfs -text
 sft_devstral_24B/wandb/run-20251223_142235-cktxoubm/run-cktxoubm.wandb filter=lfs diff=lfs merge=lfs -text
+sft_devstral_24B_v2/wandb/run-20251226_180613-i1cmzyri/run-i1cmzyri.wandb filter=lfs diff=lfs merge=lfs -text
+sft_devstral_24B_v2/wandb/run-20251226_180702-oordmylf/run-oordmylf.wandb filter=lfs diff=lfs merge=lfs -text
+sft_devstral_24B_v2/wandb/run-20251226_180808-ny9q48hd/run-ny9q48hd.wandb filter=lfs diff=lfs merge=lfs -text

sft_devstral_24B_v2/best_adapter/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Models/Devstral-Small-2-24B-HS-CPT
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Models/Devstral-Small-2-24B-HS-CPT
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

sft_devstral_24B_v2/best_adapter/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Models/Devstral-Small-2-24B-HS-CPT",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

sft_devstral_24B_v2/best_adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83291f6d455ca5ce17a07f21cc02ec56cba0671e1d6495dd81c1d98fd10b7c26
+size 45690960

sft_devstral_24B_v2/best_adapter/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e09df88fe57630482e911c5fab6026e3d20e4f37f6e48706f3566768f533d6d7
+size 4792

sft_devstral_24B_v2/checkpoints/checkpoint-1000/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Models/Devstral-Small-2-24B-HS-CPT
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Models/Devstral-Small-2-24B-HS-CPT
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

sft_devstral_24B_v2/checkpoints/checkpoint-1000/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Models/Devstral-Small-2-24B-HS-CPT",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

sft_devstral_24B_v2/checkpoints/checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44afa7c257cedf456ae8538816f1dcd1546f8e0509f0b58cb9c689ac56711166
+size 45690960

sft_devstral_24B_v2/checkpoints/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2baa24039deac4dc92f3e0e35321ca7d94cd710dfd3416641e7f5735dcfbaba5
+size 78912442

sft_devstral_24B_v2/checkpoints/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0de6a7ba694bc1275a5b47fcf2c7b687280c780b6f307863a07ec69d3e9567f
+size 14244

sft_devstral_24B_v2/checkpoints/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd7d0063a4b9f937b9f5f63ec0f89ae9cc467878dc393ecd578a9607b37e26c8
+size 1064

sft_devstral_24B_v2/checkpoints/checkpoint-1000/trainer_state.json

@@ -0,0 +1,3623 @@
+{
+  "best_global_step": 1000,
+  "best_metric": 0.8388314247131348,
+  "best_model_checkpoint": "task2file/sft_devstral_24B_v2/checkpoints/checkpoint-1000",
+  "epoch": 0.4219409282700422,
+  "eval_steps": 100,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008438818565400844,
+      "grad_norm": 1.597854733467102,
+      "learning_rate": 8.787346221441124e-08,
+      "loss": 1.3927901983261108,
+      "step": 2
+    },
+    {
+      "epoch": 0.0016877637130801688,
+      "grad_norm": 1.6547431945800781,
+      "learning_rate": 2.6362038664323375e-07,
+      "loss": 1.407160758972168,
+      "step": 4
+    },
+    {
+      "epoch": 0.002531645569620253,
+      "grad_norm": 1.8221601247787476,
+      "learning_rate": 4.393673110720563e-07,
+      "loss": 1.376656174659729,
+      "step": 6
+    },
+    {
+      "epoch": 0.0033755274261603376,
+      "grad_norm": 1.4831048250198364,
+      "learning_rate": 6.151142355008788e-07,
+      "loss": 1.247712254524231,
+      "step": 8
+    },
+    {
+      "epoch": 0.004219409282700422,
+      "grad_norm": 1.668201208114624,
+      "learning_rate": 7.908611599297013e-07,
+      "loss": 1.2685163021087646,
+      "step": 10
+    },
+    {
+      "epoch": 0.005063291139240506,
+      "grad_norm": 1.67417311668396,
+      "learning_rate": 9.666080843585237e-07,
+      "loss": 1.2942761182785034,
+      "step": 12
+    },
+    {
+      "epoch": 0.00590717299578059,
+      "grad_norm": 1.7154079675674438,
+      "learning_rate": 1.1423550087873463e-06,
+      "loss": 1.3638604879379272,
+      "step": 14
+    },
+    {
+      "epoch": 0.006751054852320675,
+      "grad_norm": 1.729427456855774,
+      "learning_rate": 1.3181019332161688e-06,
+      "loss": 1.3476728200912476,
+      "step": 16
+    },
+    {
+      "epoch": 0.007594936708860759,
+      "grad_norm": 1.3813447952270508,
+      "learning_rate": 1.4938488576449913e-06,
+      "loss": 1.3476393222808838,
+      "step": 18
+    },
+    {
+      "epoch": 0.008438818565400843,
+      "grad_norm": 1.557220458984375,
+      "learning_rate": 1.6695957820738139e-06,
+      "loss": 1.2449309825897217,
+      "step": 20
+    },
+    {
+      "epoch": 0.009282700421940928,
+      "grad_norm": 1.1883500814437866,
+      "learning_rate": 1.8453427065026362e-06,
+      "loss": 1.3125361204147339,
+      "step": 22
+    },
+    {
+      "epoch": 0.010126582278481013,
+      "grad_norm": 1.7290029525756836,
+      "learning_rate": 2.0210896309314587e-06,
+      "loss": 1.3724769353866577,
+      "step": 24
+    },
+    {
+      "epoch": 0.010970464135021098,
+      "grad_norm": 1.5627557039260864,
+      "learning_rate": 2.1968365553602812e-06,
+      "loss": 1.3401387929916382,
+      "step": 26
+    },
+    {
+      "epoch": 0.01181434599156118,
+      "grad_norm": 1.796866774559021,
+      "learning_rate": 2.3725834797891038e-06,
+      "loss": 1.365437388420105,
+      "step": 28
+    },
+    {
+      "epoch": 0.012658227848101266,
+      "grad_norm": 1.7030404806137085,
+      "learning_rate": 2.5483304042179263e-06,
+      "loss": 1.2706533670425415,
+      "step": 30
+    },
+    {
+      "epoch": 0.01350210970464135,
+      "grad_norm": 1.3186293840408325,
+      "learning_rate": 2.724077328646749e-06,
+      "loss": 1.3084994554519653,
+      "step": 32
+    },
+    {
+      "epoch": 0.014345991561181435,
+      "grad_norm": 1.5762513875961304,
+      "learning_rate": 2.8998242530755714e-06,
+      "loss": 1.3259696960449219,
+      "step": 34
+    },
+    {
+      "epoch": 0.015189873417721518,
+      "grad_norm": 1.422295331954956,
+      "learning_rate": 3.075571177504394e-06,
+      "loss": 1.3205676078796387,
+      "step": 36
+    },
+    {
+      "epoch": 0.016033755274261603,
+      "grad_norm": 1.495523452758789,
+      "learning_rate": 3.2513181019332165e-06,
+      "loss": 1.3740568161010742,
+      "step": 38
+    },
+    {
+      "epoch": 0.016877637130801686,
+      "grad_norm": 1.5112254619598389,
+      "learning_rate": 3.427065026362039e-06,
+      "loss": 1.321828842163086,
+      "step": 40
+    },
+    {
+      "epoch": 0.017721518987341773,
+      "grad_norm": 1.4667807817459106,
+      "learning_rate": 3.602811950790861e-06,
+      "loss": 1.3673173189163208,
+      "step": 42
+    },
+    {
+      "epoch": 0.018565400843881856,
+      "grad_norm": 1.6609723567962646,
+      "learning_rate": 3.7785588752196836e-06,
+      "loss": 1.3968093395233154,
+      "step": 44
+    },
+    {
+      "epoch": 0.019409282700421943,
+      "grad_norm": 1.59381103515625,
+      "learning_rate": 3.954305799648506e-06,
+      "loss": 1.4295302629470825,
+      "step": 46
+    },
+    {
+      "epoch": 0.020253164556962026,
+      "grad_norm": 1.1470608711242676,
+      "learning_rate": 4.130052724077329e-06,
+      "loss": 1.2536572217941284,
+      "step": 48
+    },
+    {
+      "epoch": 0.02109704641350211,
+      "grad_norm": 1.2014588117599487,
+      "learning_rate": 4.305799648506151e-06,
+      "loss": 1.242217779159546,
+      "step": 50
+    },
+    {
+      "epoch": 0.021940928270042195,
+      "grad_norm": 1.2327464818954468,
+      "learning_rate": 4.481546572934974e-06,
+      "loss": 1.2166963815689087,
+      "step": 52
+    },
+    {
+      "epoch": 0.02278481012658228,
+      "grad_norm": 1.9708983898162842,
+      "learning_rate": 4.657293497363796e-06,
+      "loss": 1.25709867477417,
+      "step": 54
+    },
+    {
+      "epoch": 0.02362869198312236,
+      "grad_norm": 1.180569052696228,
+      "learning_rate": 4.833040421792619e-06,
+      "loss": 1.2886158227920532,
+      "step": 56
+    },
+    {
+      "epoch": 0.024472573839662448,
+      "grad_norm": 1.5029548406600952,
+      "learning_rate": 5.008787346221441e-06,
+      "loss": 1.29886794090271,
+      "step": 58
+    },
+    {
+      "epoch": 0.02531645569620253,
+      "grad_norm": 1.5380216836929321,
+      "learning_rate": 5.184534270650264e-06,
+      "loss": 1.2387628555297852,
+      "step": 60
+    },
+    {
+      "epoch": 0.026160337552742614,
+      "grad_norm": 1.572144865989685,
+      "learning_rate": 5.3602811950790864e-06,
+      "loss": 1.2177000045776367,
+      "step": 62
+    },
+    {
+      "epoch": 0.0270042194092827,
+      "grad_norm": 1.4882780313491821,
+      "learning_rate": 5.536028119507909e-06,
+      "loss": 1.181516170501709,
+      "step": 64
+    },
+    {
+      "epoch": 0.027848101265822784,
+      "grad_norm": 1.2982488870620728,
+      "learning_rate": 5.7117750439367315e-06,
+      "loss": 1.2101733684539795,
+      "step": 66
+    },
+    {
+      "epoch": 0.02869198312236287,
+      "grad_norm": 1.5236955881118774,
+      "learning_rate": 5.887521968365554e-06,
+      "loss": 1.2277681827545166,
+      "step": 68
+    },
+    {
+      "epoch": 0.029535864978902954,
+      "grad_norm": 1.4521006345748901,
+      "learning_rate": 6.0632688927943766e-06,
+      "loss": 1.1688424348831177,
+      "step": 70
+    },
+    {
+      "epoch": 0.030379746835443037,
+      "grad_norm": 1.2352311611175537,
+      "learning_rate": 6.239015817223199e-06,
+      "loss": 1.273059368133545,
+      "step": 72
+    },
+    {
+      "epoch": 0.031223628691983123,
+      "grad_norm": 1.3438209295272827,
+      "learning_rate": 6.414762741652021e-06,
+      "loss": 1.1609034538269043,
+      "step": 74
+    },
+    {
+      "epoch": 0.032067510548523206,
+      "grad_norm": 1.9009398221969604,
+      "learning_rate": 6.590509666080843e-06,
+      "loss": 1.2508260011672974,
+      "step": 76
+    },
+    {
+      "epoch": 0.03291139240506329,
+      "grad_norm": 1.6718412637710571,
+      "learning_rate": 6.766256590509666e-06,
+      "loss": 1.2524956464767456,
+      "step": 78
+    },
+    {
+      "epoch": 0.03375527426160337,
+      "grad_norm": 1.249891757965088,
+      "learning_rate": 6.942003514938488e-06,
+      "loss": 1.1472493410110474,
+      "step": 80
+    },
+    {
+      "epoch": 0.03459915611814346,
+      "grad_norm": 1.4398653507232666,
+      "learning_rate": 7.117750439367312e-06,
+      "loss": 1.0845389366149902,
+      "step": 82
+    },
+    {
+      "epoch": 0.035443037974683546,
+      "grad_norm": 1.3701167106628418,
+      "learning_rate": 7.293497363796134e-06,
+      "loss": 1.1088868379592896,
+      "step": 84
+    },
+    {
+      "epoch": 0.036286919831223625,
+      "grad_norm": 1.277998924255371,
+      "learning_rate": 7.469244288224957e-06,
+      "loss": 1.1513772010803223,
+      "step": 86
+    },
+    {
+      "epoch": 0.03713080168776371,
+      "grad_norm": 1.4970002174377441,
+      "learning_rate": 7.644991212653779e-06,
+      "loss": 1.1385771036148071,
+      "step": 88
+    },
+    {
+      "epoch": 0.0379746835443038,
+      "grad_norm": 1.3384218215942383,
+      "learning_rate": 7.820738137082601e-06,
+      "loss": 1.1632680892944336,
+      "step": 90
+    },
+    {
+      "epoch": 0.038818565400843885,
+      "grad_norm": 1.4317446947097778,
+      "learning_rate": 7.996485061511425e-06,
+      "loss": 1.2256064414978027,
+      "step": 92
+    },
+    {
+      "epoch": 0.039662447257383965,
+      "grad_norm": 1.8743640184402466,
+      "learning_rate": 8.172231985940246e-06,
+      "loss": 1.1935789585113525,
+      "step": 94
+    },
+    {
+      "epoch": 0.04050632911392405,
+      "grad_norm": 1.4789546728134155,
+      "learning_rate": 8.347978910369069e-06,
+      "loss": 1.1429362297058105,
+      "step": 96
+    },
+    {
+      "epoch": 0.04135021097046414,
+      "grad_norm": 1.658605694770813,
+      "learning_rate": 8.523725834797891e-06,
+      "loss": 1.1831508874893188,
+      "step": 98
+    },
+    {
+      "epoch": 0.04219409282700422,
+      "grad_norm": 1.5077892541885376,
+      "learning_rate": 8.699472759226714e-06,
+      "loss": 1.0539867877960205,
+      "step": 100
+    },
+    {
+      "epoch": 0.04219409282700422,
+      "eval_loss": 1.138856053352356,
+      "eval_runtime": 859.7128,
+      "eval_samples_per_second": 2.451,
+      "eval_steps_per_second": 2.451,
+      "step": 100
+    },
+    {
+      "epoch": 0.043037974683544304,
+      "grad_norm": 1.4335681200027466,
+      "learning_rate": 8.875219683655536e-06,
+      "loss": 1.0719901323318481,
+      "step": 102
+    },
+    {
+      "epoch": 0.04388185654008439,
+      "grad_norm": 1.7387681007385254,
+      "learning_rate": 9.050966608084359e-06,
+      "loss": 1.0654313564300537,
+      "step": 104
+    },
+    {
+      "epoch": 0.04472573839662447,
+      "grad_norm": 1.6071950197219849,
+      "learning_rate": 9.226713532513181e-06,
+      "loss": 1.0752698183059692,
+      "step": 106
+    },
+    {
+      "epoch": 0.04556962025316456,
+      "grad_norm": 1.40005362033844,
+      "learning_rate": 9.402460456942004e-06,
+      "loss": 1.1029763221740723,
+      "step": 108
+    },
+    {
+      "epoch": 0.046413502109704644,
+      "grad_norm": 2.2338669300079346,
+      "learning_rate": 9.578207381370826e-06,
+      "loss": 1.1157960891723633,
+      "step": 110
+    },
+    {
+      "epoch": 0.04725738396624472,
+      "grad_norm": 1.4972727298736572,
+      "learning_rate": 9.753954305799649e-06,
+      "loss": 1.1095420122146606,
+      "step": 112
+    },
+    {
+      "epoch": 0.04810126582278481,
+      "grad_norm": 1.317979097366333,
+      "learning_rate": 9.929701230228471e-06,
+      "loss": 1.109113097190857,
+      "step": 114
+    },
+    {
+      "epoch": 0.048945147679324896,
+      "grad_norm": 1.496346116065979,
+      "learning_rate": 1.0105448154657294e-05,
+      "loss": 1.1055104732513428,
+      "step": 116
+    },
+    {
+      "epoch": 0.049789029535864976,
+      "grad_norm": 1.385406732559204,
+      "learning_rate": 1.0281195079086117e-05,
+      "loss": 1.118395209312439,
+      "step": 118
+    },
+    {
+      "epoch": 0.05063291139240506,
+      "grad_norm": 1.524222731590271,
+      "learning_rate": 1.0456942003514939e-05,
+      "loss": 1.1008446216583252,
+      "step": 120
+    },
+    {
+      "epoch": 0.05147679324894515,
+      "grad_norm": 1.6308200359344482,
+      "learning_rate": 1.0632688927943762e-05,
+      "loss": 1.0891425609588623,
+      "step": 122
+    },
+    {
+      "epoch": 0.05232067510548523,
+      "grad_norm": 1.3681106567382812,
+      "learning_rate": 1.0808435852372584e-05,
+      "loss": 0.9080473184585571,
+      "step": 124
+    },
+    {
+      "epoch": 0.053164556962025315,
+      "grad_norm": 1.9429908990859985,
+      "learning_rate": 1.0984182776801407e-05,
+      "loss": 1.0337369441986084,
+      "step": 126
+    },
+    {
+      "epoch": 0.0540084388185654,
+      "grad_norm": 1.5830830335617065,
+      "learning_rate": 1.115992970123023e-05,
+      "loss": 1.0703333616256714,
+      "step": 128
+    },
+    {
+      "epoch": 0.05485232067510549,
+      "grad_norm": 1.4792555570602417,
+      "learning_rate": 1.1335676625659052e-05,
+      "loss": 1.004652738571167,
+      "step": 130
+    },
+    {
+      "epoch": 0.05569620253164557,
+      "grad_norm": 1.7196226119995117,
+      "learning_rate": 1.1511423550087874e-05,
+      "loss": 0.9798293709754944,
+      "step": 132
+    },
+    {
+      "epoch": 0.056540084388185655,
+      "grad_norm": 1.8733659982681274,
+      "learning_rate": 1.1687170474516697e-05,
+      "loss": 1.0213249921798706,
+      "step": 134
+    },
+    {
+      "epoch": 0.05738396624472574,
+      "grad_norm": 1.3431142568588257,
+      "learning_rate": 1.186291739894552e-05,
+      "loss": 1.0358591079711914,
+      "step": 136
+    },
+    {
+      "epoch": 0.05822784810126582,
+      "grad_norm": 1.527864933013916,
+      "learning_rate": 1.2038664323374342e-05,
+      "loss": 0.9372249841690063,
+      "step": 138
+    },
+    {
+      "epoch": 0.05907172995780591,
+      "grad_norm": 1.5495563745498657,
+      "learning_rate": 1.2214411247803164e-05,
+      "loss": 1.0277758836746216,
+      "step": 140
+    },
+    {
+      "epoch": 0.059915611814345994,
+      "grad_norm": 1.6792418956756592,
+      "learning_rate": 1.2390158172231985e-05,
+      "loss": 1.0349801778793335,
+      "step": 142
+    },
+    {
+      "epoch": 0.060759493670886074,
+      "grad_norm": 1.6468945741653442,
+      "learning_rate": 1.256590509666081e-05,
+      "loss": 0.9578297734260559,
+      "step": 144
+    },
+    {
+      "epoch": 0.06160337552742616,
+      "grad_norm": 1.7243824005126953,
+      "learning_rate": 1.2741652021089632e-05,
+      "loss": 1.0628854036331177,
+      "step": 146
+    },
+    {
+      "epoch": 0.06244725738396625,
+      "grad_norm": 1.7286981344223022,
+      "learning_rate": 1.2917398945518455e-05,
+      "loss": 0.9336449503898621,
+      "step": 148
+    },
+    {
+      "epoch": 0.06329113924050633,
+      "grad_norm": 1.6411832571029663,
+      "learning_rate": 1.3093145869947277e-05,
+      "loss": 0.953730583190918,
+      "step": 150
+    },
+    {
+      "epoch": 0.06413502109704641,
+      "grad_norm": 1.8297001123428345,
+      "learning_rate": 1.3268892794376098e-05,
+      "loss": 1.051239013671875,
+      "step": 152
+    },
+    {
+      "epoch": 0.06497890295358649,
+      "grad_norm": 1.9660519361495972,
+      "learning_rate": 1.3444639718804922e-05,
+      "loss": 0.9955035448074341,
+      "step": 154
+    },
+    {
+      "epoch": 0.06582278481012659,
+      "grad_norm": 1.8423733711242676,
+      "learning_rate": 1.3620386643233743e-05,
+      "loss": 0.913300096988678,
+      "step": 156
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 1.9146347045898438,
+      "learning_rate": 1.3796133567662567e-05,
+      "loss": 1.0429846048355103,
+      "step": 158
+    },
+    {
+      "epoch": 0.06751054852320675,
+      "grad_norm": 1.6221821308135986,
+      "learning_rate": 1.3971880492091388e-05,
+      "loss": 1.0360238552093506,
+      "step": 160
+    },
+    {
+      "epoch": 0.06835443037974684,
+      "grad_norm": 2.173283338546753,
+      "learning_rate": 1.4147627416520212e-05,
+      "loss": 1.0227266550064087,
+      "step": 162
+    },
+    {
+      "epoch": 0.06919831223628692,
+      "grad_norm": 1.7091665267944336,
+      "learning_rate": 1.4323374340949033e-05,
+      "loss": 1.0075194835662842,
+      "step": 164
+    },
+    {
+      "epoch": 0.070042194092827,
+      "grad_norm": 1.7219135761260986,
+      "learning_rate": 1.4499121265377857e-05,
+      "loss": 1.0044782161712646,
+      "step": 166
+    },
+    {
+      "epoch": 0.07088607594936709,
+      "grad_norm": 1.6558159589767456,
+      "learning_rate": 1.4674868189806678e-05,
+      "loss": 0.9393973350524902,
+      "step": 168
+    },
+    {
+      "epoch": 0.07172995780590717,
+      "grad_norm": 1.9362739324569702,
+      "learning_rate": 1.4850615114235502e-05,
+      "loss": 0.9955337643623352,
+      "step": 170
+    },
+    {
+      "epoch": 0.07257383966244725,
+      "grad_norm": 1.7792853116989136,
+      "learning_rate": 1.5026362038664323e-05,
+      "loss": 0.9659126400947571,
+      "step": 172
+    },
+    {
+      "epoch": 0.07341772151898734,
+      "grad_norm": 1.7184511423110962,
+      "learning_rate": 1.5202108963093147e-05,
+      "loss": 0.9077855348587036,
+      "step": 174
+    },
+    {
+      "epoch": 0.07426160337552742,
+      "grad_norm": 1.5701428651809692,
+      "learning_rate": 1.537785588752197e-05,
+      "loss": 0.9305018782615662,
+      "step": 176
+    },
+    {
+      "epoch": 0.0751054852320675,
+      "grad_norm": 1.970229148864746,
+      "learning_rate": 1.555360281195079e-05,
+      "loss": 1.0211774110794067,
+      "step": 178
+    },
+    {
+      "epoch": 0.0759493670886076,
+      "grad_norm": 1.8410269021987915,
+      "learning_rate": 1.5729349736379615e-05,
+      "loss": 0.9479315876960754,
+      "step": 180
+    },
+    {
+      "epoch": 0.07679324894514768,
+      "grad_norm": 1.8991246223449707,
+      "learning_rate": 1.5905096660808434e-05,
+      "loss": 1.0629050731658936,
+      "step": 182
+    },
+    {
+      "epoch": 0.07763713080168777,
+      "grad_norm": 1.8052008152008057,
+      "learning_rate": 1.608084358523726e-05,
+      "loss": 0.946983814239502,
+      "step": 184
+    },
+    {
+      "epoch": 0.07848101265822785,
+      "grad_norm": 1.547108769416809,
+      "learning_rate": 1.625659050966608e-05,
+      "loss": 0.9413356184959412,
+      "step": 186
+    },
+    {
+      "epoch": 0.07932489451476793,
+      "grad_norm": 1.9713538885116577,
+      "learning_rate": 1.6432337434094905e-05,
+      "loss": 0.9337888956069946,
+      "step": 188
+    },
+    {
+      "epoch": 0.08016877637130802,
+      "grad_norm": 1.708789348602295,
+      "learning_rate": 1.6608084358523728e-05,
+      "loss": 0.9816337823867798,
+      "step": 190
+    },
+    {
+      "epoch": 0.0810126582278481,
+      "grad_norm": 1.815292477607727,
+      "learning_rate": 1.678383128295255e-05,
+      "loss": 1.017122507095337,
+      "step": 192
+    },
+    {
+      "epoch": 0.08185654008438818,
+      "grad_norm": 1.7950682640075684,
+      "learning_rate": 1.6959578207381373e-05,
+      "loss": 0.991599440574646,
+      "step": 194
+    },
+    {
+      "epoch": 0.08270042194092828,
+      "grad_norm": 1.692512035369873,
+      "learning_rate": 1.7135325131810195e-05,
+      "loss": 0.9570834040641785,
+      "step": 196
+    },
+    {
+      "epoch": 0.08354430379746836,
+      "grad_norm": 2.056089162826538,
+      "learning_rate": 1.7311072056239018e-05,
+      "loss": 1.035754919052124,
+      "step": 198
+    },
+    {
+      "epoch": 0.08438818565400844,
+      "grad_norm": 1.7022203207015991,
+      "learning_rate": 1.7486818980667837e-05,
+      "loss": 1.0124205350875854,
+      "step": 200
+    },
+    {
+      "epoch": 0.08438818565400844,
+      "eval_loss": 0.995743453502655,
+      "eval_runtime": 846.8257,
+      "eval_samples_per_second": 2.488,
+      "eval_steps_per_second": 2.488,
+      "step": 200
+    },
+    {
+      "epoch": 0.08523206751054853,
+      "grad_norm": 1.6088604927062988,
+      "learning_rate": 1.7662565905096663e-05,
+      "loss": 0.8946985006332397,
+      "step": 202
+    },
+    {
+      "epoch": 0.08607594936708861,
+      "grad_norm": 2.02270770072937,
+      "learning_rate": 1.7838312829525482e-05,
+      "loss": 0.976133406162262,
+      "step": 204
+    },
+    {
+      "epoch": 0.08691983122362869,
+      "grad_norm": 1.7832789421081543,
+      "learning_rate": 1.8014059753954308e-05,
+      "loss": 0.9079383611679077,
+      "step": 206
+    },
+    {
+      "epoch": 0.08776371308016878,
+      "grad_norm": 1.9793545007705688,
+      "learning_rate": 1.8189806678383127e-05,
+      "loss": 0.8650367856025696,
+      "step": 208
+    },
+    {
+      "epoch": 0.08860759493670886,
+      "grad_norm": 1.8124271631240845,
+      "learning_rate": 1.8365553602811953e-05,
+      "loss": 0.9327266812324524,
+      "step": 210
+    },
+    {
+      "epoch": 0.08945147679324894,
+      "grad_norm": 1.8581212759017944,
+      "learning_rate": 1.8541300527240772e-05,
+      "loss": 0.9811079502105713,
+      "step": 212
+    },
+    {
+      "epoch": 0.09029535864978903,
+      "grad_norm": 2.001699447631836,
+      "learning_rate": 1.8717047451669598e-05,
+      "loss": 0.9546971321105957,
+      "step": 214
+    },
+    {
+      "epoch": 0.09113924050632911,
+      "grad_norm": 1.6994978189468384,
+      "learning_rate": 1.8892794376098417e-05,
+      "loss": 0.9611319899559021,
+      "step": 216
+    },
+    {
+      "epoch": 0.0919831223628692,
+      "grad_norm": 2.1379497051239014,
+      "learning_rate": 1.9068541300527243e-05,
+      "loss": 0.9781531095504761,
+      "step": 218
+    },
+    {
+      "epoch": 0.09282700421940929,
+      "grad_norm": 1.8961224555969238,
+      "learning_rate": 1.9244288224956066e-05,
+      "loss": 0.9374833106994629,
+      "step": 220
+    },
+    {
+      "epoch": 0.09367088607594937,
+      "grad_norm": 1.851464033126831,
+      "learning_rate": 1.9420035149384885e-05,
+      "loss": 0.9681299328804016,
+      "step": 222
+    },
+    {
+      "epoch": 0.09451476793248945,
+      "grad_norm": 2.0642266273498535,
+      "learning_rate": 1.959578207381371e-05,
+      "loss": 1.0086225271224976,
+      "step": 224
+    },
+    {
+      "epoch": 0.09535864978902954,
+      "grad_norm": 1.8658756017684937,
+      "learning_rate": 1.977152899824253e-05,
+      "loss": 0.9190312623977661,
+      "step": 226
+    },
+    {
+      "epoch": 0.09620253164556962,
+      "grad_norm": 2.4398674964904785,
+      "learning_rate": 1.9947275922671356e-05,
+      "loss": 0.9740874171257019,
+      "step": 228
+    },
+    {
+      "epoch": 0.0970464135021097,
+      "grad_norm": 1.849183440208435,
+      "learning_rate": 2.0123022847100175e-05,
+      "loss": 0.884376049041748,
+      "step": 230
+    },
+    {
+      "epoch": 0.09789029535864979,
+      "grad_norm": 2.027320384979248,
+      "learning_rate": 2.0298769771529e-05,
+      "loss": 0.9116487503051758,
+      "step": 232
+    },
+    {
+      "epoch": 0.09873417721518987,
+      "grad_norm": 1.6800135374069214,
+      "learning_rate": 2.047451669595782e-05,
+      "loss": 0.9035115242004395,
+      "step": 234
+    },
+    {
+      "epoch": 0.09957805907172995,
+      "grad_norm": 2.2362256050109863,
+      "learning_rate": 2.0650263620386646e-05,
+      "loss": 0.9043796062469482,
+      "step": 236
+    },
+    {
+      "epoch": 0.10042194092827005,
+      "grad_norm": 1.938215970993042,
+      "learning_rate": 2.0826010544815465e-05,
+      "loss": 1.0888828039169312,
+      "step": 238
+    },
+    {
+      "epoch": 0.10126582278481013,
+      "grad_norm": 1.890328049659729,
+      "learning_rate": 2.100175746924429e-05,
+      "loss": 0.9960280656814575,
+      "step": 240
+    },
+    {
+      "epoch": 0.1021097046413502,
+      "grad_norm": 2.021235227584839,
+      "learning_rate": 2.117750439367311e-05,
+      "loss": 0.9848901629447937,
+      "step": 242
+    },
+    {
+      "epoch": 0.1029535864978903,
+      "grad_norm": 2.023920774459839,
+      "learning_rate": 2.1353251318101936e-05,
+      "loss": 0.891694188117981,
+      "step": 244
+    },
+    {
+      "epoch": 0.10379746835443038,
+      "grad_norm": 1.8061069250106812,
+      "learning_rate": 2.1528998242530755e-05,
+      "loss": 0.9059976935386658,
+      "step": 246
+    },
+    {
+      "epoch": 0.10464135021097046,
+      "grad_norm": 2.176302194595337,
+      "learning_rate": 2.1704745166959578e-05,
+      "loss": 1.0056109428405762,
+      "step": 248
+    },
+    {
+      "epoch": 0.10548523206751055,
+      "grad_norm": 1.9820969104766846,
+      "learning_rate": 2.18804920913884e-05,
+      "loss": 0.9645357728004456,
+      "step": 250
+    },
+    {
+      "epoch": 0.10632911392405063,
+      "grad_norm": 1.8764572143554688,
+      "learning_rate": 2.2056239015817223e-05,
+      "loss": 1.0178182125091553,
+      "step": 252
+    },
+    {
+      "epoch": 0.10717299578059072,
+      "grad_norm": 2.56221342086792,
+      "learning_rate": 2.223198594024605e-05,
+      "loss": 0.9546761512756348,
+      "step": 254
+    },
+    {
+      "epoch": 0.1080168776371308,
+      "grad_norm": 2.6779074668884277,
+      "learning_rate": 2.2407732864674868e-05,
+      "loss": 0.9300968647003174,
+      "step": 256
+    },
+    {
+      "epoch": 0.10886075949367088,
+      "grad_norm": 2.140897512435913,
+      "learning_rate": 2.2583479789103694e-05,
+      "loss": 0.926638662815094,
+      "step": 258
+    },
+    {
+      "epoch": 0.10970464135021098,
+      "grad_norm": 2.0880508422851562,
+      "learning_rate": 2.2759226713532513e-05,
+      "loss": 1.0681840181350708,
+      "step": 260
+    },
+    {
+      "epoch": 0.11054852320675106,
+      "grad_norm": 2.7273616790771484,
+      "learning_rate": 2.293497363796134e-05,
+      "loss": 1.0840941667556763,
+      "step": 262
+    },
+    {
+      "epoch": 0.11139240506329114,
+      "grad_norm": 1.6723874807357788,
+      "learning_rate": 2.3110720562390158e-05,
+      "loss": 0.8637182116508484,
+      "step": 264
+    },
+    {
+      "epoch": 0.11223628691983123,
+      "grad_norm": 1.806243896484375,
+      "learning_rate": 2.3286467486818984e-05,
+      "loss": 0.9554686546325684,
+      "step": 266
+    },
+    {
+      "epoch": 0.11308016877637131,
+      "grad_norm": 1.9086743593215942,
+      "learning_rate": 2.3462214411247803e-05,
+      "loss": 0.9556593894958496,
+      "step": 268
+    },
+    {
+      "epoch": 0.11392405063291139,
+      "grad_norm": 2.1822304725646973,
+      "learning_rate": 2.3637961335676626e-05,
+      "loss": 0.9177709817886353,
+      "step": 270
+    },
+    {
+      "epoch": 0.11476793248945148,
+      "grad_norm": 2.1009039878845215,
+      "learning_rate": 2.3813708260105448e-05,
+      "loss": 0.9288759827613831,
+      "step": 272
+    },
+    {
+      "epoch": 0.11561181434599156,
+      "grad_norm": 1.9814810752868652,
+      "learning_rate": 2.398945518453427e-05,
+      "loss": 0.9881691932678223,
+      "step": 274
+    },
+    {
+      "epoch": 0.11645569620253164,
+      "grad_norm": 1.9946284294128418,
+      "learning_rate": 2.4165202108963093e-05,
+      "loss": 0.9390727281570435,
+      "step": 276
+    },
+    {
+      "epoch": 0.11729957805907174,
+      "grad_norm": 2.4489169120788574,
+      "learning_rate": 2.4340949033391916e-05,
+      "loss": 0.9625692963600159,
+      "step": 278
+    },
+    {
+      "epoch": 0.11814345991561181,
+      "grad_norm": 2.0919103622436523,
+      "learning_rate": 2.451669595782074e-05,
+      "loss": 0.9304702877998352,
+      "step": 280
+    },
+    {
+      "epoch": 0.1189873417721519,
+      "grad_norm": 1.912914752960205,
+      "learning_rate": 2.469244288224956e-05,
+      "loss": 0.9313994646072388,
+      "step": 282
+    },
+    {
+      "epoch": 0.11983122362869199,
+      "grad_norm": 2.1553256511688232,
+      "learning_rate": 2.4868189806678387e-05,
+      "loss": 1.004011869430542,
+      "step": 284
+    },
+    {
+      "epoch": 0.12067510548523207,
+      "grad_norm": 2.0129058361053467,
+      "learning_rate": 2.504393673110721e-05,
+      "loss": 0.9092531204223633,
+      "step": 286
+    },
+    {
+      "epoch": 0.12151898734177215,
+      "grad_norm": 2.1632325649261475,
+      "learning_rate": 2.5219683655536032e-05,
+      "loss": 0.993347704410553,
+      "step": 288
+    },
+    {
+      "epoch": 0.12236286919831224,
+      "grad_norm": 2.3072738647460938,
+      "learning_rate": 2.539543057996485e-05,
+      "loss": 0.978348433971405,
+      "step": 290
+    },
+    {
+      "epoch": 0.12320675105485232,
+      "grad_norm": 2.056560516357422,
+      "learning_rate": 2.5571177504393674e-05,
+      "loss": 1.0018101930618286,
+      "step": 292
+    },
+    {
+      "epoch": 0.1240506329113924,
+      "grad_norm": 1.8906747102737427,
+      "learning_rate": 2.5746924428822493e-05,
+      "loss": 0.9607775211334229,
+      "step": 294
+    },
+    {
+      "epoch": 0.1248945147679325,
+      "grad_norm": 2.1375651359558105,
+      "learning_rate": 2.5922671353251322e-05,
+      "loss": 0.9259153008460999,
+      "step": 296
+    },
+    {
+      "epoch": 0.1257383966244726,
+      "grad_norm": 1.9994823932647705,
+      "learning_rate": 2.609841827768014e-05,
+      "loss": 0.8524524569511414,
+      "step": 298
+    },
+    {
+      "epoch": 0.12658227848101267,
+      "grad_norm": 2.2421181201934814,
+      "learning_rate": 2.6274165202108964e-05,
+      "loss": 1.0047069787979126,
+      "step": 300
+    },
+    {
+      "epoch": 0.12658227848101267,
+      "eval_loss": 0.9517185688018799,
+      "eval_runtime": 860.0287,
+      "eval_samples_per_second": 2.45,
+      "eval_steps_per_second": 2.45,
+      "step": 300
+    },
+    {
+      "epoch": 0.12742616033755275,
+      "grad_norm": 2.1206254959106445,
+      "learning_rate": 2.6449912126537786e-05,
+      "loss": 0.8475471138954163,
+      "step": 302
+    },
+    {
+      "epoch": 0.12827004219409283,
+      "grad_norm": 1.885161280632019,
+      "learning_rate": 2.6625659050966612e-05,
+      "loss": 0.8643121123313904,
+      "step": 304
+    },
+    {
+      "epoch": 0.1291139240506329,
+      "grad_norm": 3.1441781520843506,
+      "learning_rate": 2.680140597539543e-05,
+      "loss": 0.8804612159729004,
+      "step": 306
+    },
+    {
+      "epoch": 0.12995780590717299,
+      "grad_norm": 1.953133225440979,
+      "learning_rate": 2.6977152899824254e-05,
+      "loss": 0.8348029255867004,
+      "step": 308
+    },
+    {
+      "epoch": 0.1308016877637131,
+      "grad_norm": 2.3762667179107666,
+      "learning_rate": 2.7152899824253076e-05,
+      "loss": 0.8889057040214539,
+      "step": 310
+    },
+    {
+      "epoch": 0.13164556962025317,
+      "grad_norm": 2.4651103019714355,
+      "learning_rate": 2.7328646748681902e-05,
+      "loss": 1.025565505027771,
+      "step": 312
+    },
+    {
+      "epoch": 0.13248945147679325,
+      "grad_norm": 1.8522284030914307,
+      "learning_rate": 2.7504393673110725e-05,
+      "loss": 0.868915855884552,
+      "step": 314
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 1.8048083782196045,
+      "learning_rate": 2.7680140597539544e-05,
+      "loss": 0.8821638226509094,
+      "step": 316
+    },
+    {
+      "epoch": 0.1341772151898734,
+      "grad_norm": 1.9933605194091797,
+      "learning_rate": 2.7855887521968367e-05,
+      "loss": 0.8735360503196716,
+      "step": 318
+    },
+    {
+      "epoch": 0.1350210970464135,
+      "grad_norm": 2.044337034225464,
+      "learning_rate": 2.8031634446397186e-05,
+      "loss": 0.8288834691047668,
+      "step": 320
+    },
+    {
+      "epoch": 0.1358649789029536,
+      "grad_norm": 2.416067361831665,
+      "learning_rate": 2.8207381370826015e-05,
+      "loss": 0.9104969501495361,
+      "step": 322
+    },
+    {
+      "epoch": 0.13670886075949368,
+      "grad_norm": 2.0731265544891357,
+      "learning_rate": 2.8383128295254834e-05,
+      "loss": 0.8689924478530884,
+      "step": 324
+    },
+    {
+      "epoch": 0.13755274261603376,
+      "grad_norm": 2.049126386642456,
+      "learning_rate": 2.8558875219683657e-05,
+      "loss": 0.9312222003936768,
+      "step": 326
+    },
+    {
+      "epoch": 0.13839662447257384,
+      "grad_norm": 2.131026268005371,
+      "learning_rate": 2.8734622144112476e-05,
+      "loss": 0.8933501839637756,
+      "step": 328
+    },
+    {
+      "epoch": 0.13924050632911392,
+      "grad_norm": 1.766754150390625,
+      "learning_rate": 2.8910369068541305e-05,
+      "loss": 0.8998261094093323,
+      "step": 330
+    },
+    {
+      "epoch": 0.140084388185654,
+      "grad_norm": 2.197706460952759,
+      "learning_rate": 2.9086115992970124e-05,
+      "loss": 0.8826426267623901,
+      "step": 332
+    },
+    {
+      "epoch": 0.1409282700421941,
+      "grad_norm": 1.953715443611145,
+      "learning_rate": 2.9261862917398947e-05,
+      "loss": 0.8590307831764221,
+      "step": 334
+    },
+    {
+      "epoch": 0.14177215189873418,
+      "grad_norm": 2.200929880142212,
+      "learning_rate": 2.943760984182777e-05,
+      "loss": 0.9317060708999634,
+      "step": 336
+    },
+    {
+      "epoch": 0.14261603375527426,
+      "grad_norm": 2.1195082664489746,
+      "learning_rate": 2.961335676625659e-05,
+      "loss": 0.9965578317642212,
+      "step": 338
+    },
+    {
+      "epoch": 0.14345991561181434,
+      "grad_norm": 2.3449771404266357,
+      "learning_rate": 2.9789103690685414e-05,
+      "loss": 0.8353848457336426,
+      "step": 340
+    },
+    {
+      "epoch": 0.14430379746835442,
+      "grad_norm": 2.000497579574585,
+      "learning_rate": 2.9964850615114237e-05,
+      "loss": 0.9154735803604126,
+      "step": 342
+    },
+    {
+      "epoch": 0.1451476793248945,
+      "grad_norm": 2.141890525817871,
+      "learning_rate": 3.014059753954306e-05,
+      "loss": 0.9530655741691589,
+      "step": 344
+    },
+    {
+      "epoch": 0.1459915611814346,
+      "grad_norm": 1.7717392444610596,
+      "learning_rate": 3.031634446397188e-05,
+      "loss": 0.896998405456543,
+      "step": 346
+    },
+    {
+      "epoch": 0.1468354430379747,
+      "grad_norm": 1.8796685934066772,
+      "learning_rate": 3.0492091388400708e-05,
+      "loss": 0.9084208011627197,
+      "step": 348
+    },
+    {
+      "epoch": 0.14767932489451477,
+      "grad_norm": 2.0298709869384766,
+      "learning_rate": 3.066783831282953e-05,
+      "loss": 0.9183387756347656,
+      "step": 350
+    },
+    {
+      "epoch": 0.14852320675105485,
+      "grad_norm": 1.9245645999908447,
+      "learning_rate": 3.084358523725835e-05,
+      "loss": 0.8624772429466248,
+      "step": 352
+    },
+    {
+      "epoch": 0.14936708860759493,
+      "grad_norm": 2.325681209564209,
+      "learning_rate": 3.101933216168717e-05,
+      "loss": 0.9142400026321411,
+      "step": 354
+    },
+    {
+      "epoch": 0.150210970464135,
+      "grad_norm": 2.1200530529022217,
+      "learning_rate": 3.1195079086115995e-05,
+      "loss": 0.9064018130302429,
+      "step": 356
+    },
+    {
+      "epoch": 0.15105485232067511,
+      "grad_norm": 1.979314923286438,
+      "learning_rate": 3.137082601054482e-05,
+      "loss": 0.9199238419532776,
+      "step": 358
+    },
+    {
+      "epoch": 0.1518987341772152,
+      "grad_norm": 2.1122689247131348,
+      "learning_rate": 3.154657293497364e-05,
+      "loss": 0.8030132055282593,
+      "step": 360
+    },
+    {
+      "epoch": 0.15274261603375527,
+      "grad_norm": 2.105767250061035,
+      "learning_rate": 3.172231985940246e-05,
+      "loss": 0.9185854196548462,
+      "step": 362
+    },
+    {
+      "epoch": 0.15358649789029535,
+      "grad_norm": 2.179471015930176,
+      "learning_rate": 3.1898066783831285e-05,
+      "loss": 0.9365083575248718,
+      "step": 364
+    },
+    {
+      "epoch": 0.15443037974683543,
+      "grad_norm": 2.1444311141967773,
+      "learning_rate": 3.207381370826011e-05,
+      "loss": 0.8965140581130981,
+      "step": 366
+    },
+    {
+      "epoch": 0.15527426160337554,
+      "grad_norm": 2.4171674251556396,
+      "learning_rate": 3.224956063268893e-05,
+      "loss": 0.8787504434585571,
+      "step": 368
+    },
+    {
+      "epoch": 0.15611814345991562,
+      "grad_norm": 2.418628215789795,
+      "learning_rate": 3.242530755711775e-05,
+      "loss": 0.8925284147262573,
+      "step": 370
+    },
+    {
+      "epoch": 0.1569620253164557,
+      "grad_norm": 2.2228314876556396,
+      "learning_rate": 3.2601054481546575e-05,
+      "loss": 0.876179039478302,
+      "step": 372
+    },
+    {
+      "epoch": 0.15780590717299578,
+      "grad_norm": 2.324237108230591,
+      "learning_rate": 3.27768014059754e-05,
+      "loss": 0.8365707993507385,
+      "step": 374
+    },
+    {
+      "epoch": 0.15864978902953586,
+      "grad_norm": 2.6344552040100098,
+      "learning_rate": 3.295254833040422e-05,
+      "loss": 0.7864399552345276,
+      "step": 376
+    },
+    {
+      "epoch": 0.15949367088607594,
+      "grad_norm": 2.047536611557007,
+      "learning_rate": 3.312829525483304e-05,
+      "loss": 0.9271875023841858,
+      "step": 378
+    },
+    {
+      "epoch": 0.16033755274261605,
+      "grad_norm": 2.120025157928467,
+      "learning_rate": 3.3304042179261865e-05,
+      "loss": 0.8799133896827698,
+      "step": 380
+    },
+    {
+      "epoch": 0.16118143459915613,
+      "grad_norm": 2.363692045211792,
+      "learning_rate": 3.347978910369069e-05,
+      "loss": 0.8973530530929565,
+      "step": 382
+    },
+    {
+      "epoch": 0.1620253164556962,
+      "grad_norm": 2.1796772480010986,
+      "learning_rate": 3.365553602811951e-05,
+      "loss": 1.0277652740478516,
+      "step": 384
+    },
+    {
+      "epoch": 0.16286919831223629,
+      "grad_norm": 1.9192595481872559,
+      "learning_rate": 3.383128295254833e-05,
+      "loss": 0.8909643888473511,
+      "step": 386
+    },
+    {
+      "epoch": 0.16371308016877636,
+      "grad_norm": 1.7874376773834229,
+      "learning_rate": 3.4007029876977155e-05,
+      "loss": 0.837049663066864,
+      "step": 388
+    },
+    {
+      "epoch": 0.16455696202531644,
+      "grad_norm": 2.3402366638183594,
+      "learning_rate": 3.4182776801405974e-05,
+      "loss": 0.8625202775001526,
+      "step": 390
+    },
+    {
+      "epoch": 0.16540084388185655,
+      "grad_norm": 2.1137185096740723,
+      "learning_rate": 3.43585237258348e-05,
+      "loss": 0.9288321137428284,
+      "step": 392
+    },
+    {
+      "epoch": 0.16624472573839663,
+      "grad_norm": 2.3776895999908447,
+      "learning_rate": 3.453427065026362e-05,
+      "loss": 0.9328726530075073,
+      "step": 394
+    },
+    {
+      "epoch": 0.1670886075949367,
+      "grad_norm": 2.34941029548645,
+      "learning_rate": 3.4710017574692445e-05,
+      "loss": 0.9273309707641602,
+      "step": 396
+    },
+    {
+      "epoch": 0.1679324894514768,
+      "grad_norm": 2.1272573471069336,
+      "learning_rate": 3.4885764499121264e-05,
+      "loss": 0.8703887462615967,
+      "step": 398
+    },
+    {
+      "epoch": 0.16877637130801687,
+      "grad_norm": 2.047290802001953,
+      "learning_rate": 3.506151142355009e-05,
+      "loss": 0.8808165788650513,
+      "step": 400
+    },
+    {
+      "epoch": 0.16877637130801687,
+      "eval_loss": 0.9282881617546082,
+      "eval_runtime": 869.6867,
+      "eval_samples_per_second": 2.423,
+      "eval_steps_per_second": 2.423,
+      "step": 400
+    },
+    {
+      "epoch": 0.16962025316455695,
+      "grad_norm": 1.9874159097671509,
+      "learning_rate": 3.5237258347978916e-05,
+      "loss": 0.9643645286560059,
+      "step": 402
+    },
+    {
+      "epoch": 0.17046413502109706,
+      "grad_norm": 1.9299919605255127,
+      "learning_rate": 3.5413005272407735e-05,
+      "loss": 0.9173495769500732,
+      "step": 404
+    },
+    {
+      "epoch": 0.17130801687763714,
+      "grad_norm": 2.3379697799682617,
+      "learning_rate": 3.5588752196836555e-05,
+      "loss": 0.8998411893844604,
+      "step": 406
+    },
+    {
+      "epoch": 0.17215189873417722,
+      "grad_norm": 2.241370916366577,
+      "learning_rate": 3.5764499121265374e-05,
+      "loss": 0.9310802221298218,
+      "step": 408
+    },
+    {
+      "epoch": 0.1729957805907173,
+      "grad_norm": 2.4490108489990234,
+      "learning_rate": 3.5940246045694206e-05,
+      "loss": 0.9605053067207336,
+      "step": 410
+    },
+    {
+      "epoch": 0.17383966244725738,
+      "grad_norm": 1.8247230052947998,
+      "learning_rate": 3.6115992970123026e-05,
+      "loss": 0.8485683798789978,
+      "step": 412
+    },
+    {
+      "epoch": 0.17468354430379746,
+      "grad_norm": 2.4608843326568604,
+      "learning_rate": 3.6291739894551845e-05,
+      "loss": 0.9325968623161316,
+      "step": 414
+    },
+    {
+      "epoch": 0.17552742616033756,
+      "grad_norm": 1.8923161029815674,
+      "learning_rate": 3.646748681898067e-05,
+      "loss": 0.9125096201896667,
+      "step": 416
+    },
+    {
+      "epoch": 0.17637130801687764,
+      "grad_norm": 1.8502769470214844,
+      "learning_rate": 3.6643233743409497e-05,
+      "loss": 0.8852217197418213,
+      "step": 418
+    },
+    {
+      "epoch": 0.17721518987341772,
+      "grad_norm": 1.9155100584030151,
+      "learning_rate": 3.6818980667838316e-05,
+      "loss": 0.9192792773246765,
+      "step": 420
+    },
+    {
+      "epoch": 0.1780590717299578,
+      "grad_norm": 2.181476593017578,
+      "learning_rate": 3.6994727592267135e-05,
+      "loss": 0.8787404298782349,
+      "step": 422
+    },
+    {
+      "epoch": 0.17890295358649788,
+      "grad_norm": 2.2469847202301025,
+      "learning_rate": 3.717047451669596e-05,
+      "loss": 0.9109582901000977,
+      "step": 424
+    },
+    {
+      "epoch": 0.17974683544303796,
+      "grad_norm": 2.08145809173584,
+      "learning_rate": 3.734622144112479e-05,
+      "loss": 0.8560389280319214,
+      "step": 426
+    },
+    {
+      "epoch": 0.18059071729957807,
+      "grad_norm": 4.121932506561279,
+      "learning_rate": 3.7521968365553606e-05,
+      "loss": 0.9456104040145874,
+      "step": 428
+    },
+    {
+      "epoch": 0.18143459915611815,
+      "grad_norm": 2.177459478378296,
+      "learning_rate": 3.7697715289982425e-05,
+      "loss": 0.8421300649642944,
+      "step": 430
+    },
+    {
+      "epoch": 0.18227848101265823,
+      "grad_norm": 2.324970245361328,
+      "learning_rate": 3.787346221441125e-05,
+      "loss": 0.9199858903884888,
+      "step": 432
+    },
+    {
+      "epoch": 0.1831223628691983,
+      "grad_norm": 2.133718490600586,
+      "learning_rate": 3.804920913884007e-05,
+      "loss": 0.8953126668930054,
+      "step": 434
+    },
+    {
+      "epoch": 0.1839662447257384,
+      "grad_norm": 1.8527995347976685,
+      "learning_rate": 3.8224956063268896e-05,
+      "loss": 0.8732239007949829,
+      "step": 436
+    },
+    {
+      "epoch": 0.1848101265822785,
+      "grad_norm": 1.95817232131958,
+      "learning_rate": 3.8400702987697715e-05,
+      "loss": 0.8818746209144592,
+      "step": 438
+    },
+    {
+      "epoch": 0.18565400843881857,
+      "grad_norm": 2.2107293605804443,
+      "learning_rate": 3.857644991212654e-05,
+      "loss": 0.9153507947921753,
+      "step": 440
+    },
+    {
+      "epoch": 0.18649789029535865,
+      "grad_norm": 2.004754066467285,
+      "learning_rate": 3.875219683655536e-05,
+      "loss": 0.8960154056549072,
+      "step": 442
+    },
+    {
+      "epoch": 0.18734177215189873,
+      "grad_norm": 2.1851706504821777,
+      "learning_rate": 3.8927943760984186e-05,
+      "loss": 0.909011721611023,
+      "step": 444
+    },
+    {
+      "epoch": 0.1881856540084388,
+      "grad_norm": 2.4492485523223877,
+      "learning_rate": 3.9103690685413005e-05,
+      "loss": 0.8880158066749573,
+      "step": 446
+    },
+    {
+      "epoch": 0.1890295358649789,
+      "grad_norm": 2.745453119277954,
+      "learning_rate": 3.927943760984183e-05,
+      "loss": 0.8500842452049255,
+      "step": 448
+    },
+    {
+      "epoch": 0.189873417721519,
+      "grad_norm": 2.1924264430999756,
+      "learning_rate": 3.945518453427065e-05,
+      "loss": 0.9004045724868774,
+      "step": 450
+    },
+    {
+      "epoch": 0.19071729957805908,
+      "grad_norm": 2.4051687717437744,
+      "learning_rate": 3.9630931458699476e-05,
+      "loss": 0.9020664095878601,
+      "step": 452
+    },
+    {
+      "epoch": 0.19156118143459916,
+      "grad_norm": 1.8077667951583862,
+      "learning_rate": 3.9806678383128295e-05,
+      "loss": 0.8639500737190247,
+      "step": 454
+    },
+    {
+      "epoch": 0.19240506329113924,
+      "grad_norm": 2.089043378829956,
+      "learning_rate": 3.998242530755712e-05,
+      "loss": 0.8642048239707947,
+      "step": 456
+    },
+    {
+      "epoch": 0.19324894514767932,
+      "grad_norm": 2.029578447341919,
+      "learning_rate": 4.015817223198594e-05,
+      "loss": 0.9371927380561829,
+      "step": 458
+    },
+    {
+      "epoch": 0.1940928270042194,
+      "grad_norm": 2.26582407951355,
+      "learning_rate": 4.033391915641476e-05,
+      "loss": 0.9120588302612305,
+      "step": 460
+    },
+    {
+      "epoch": 0.1949367088607595,
+      "grad_norm": 1.8671411275863647,
+      "learning_rate": 4.050966608084359e-05,
+      "loss": 0.8758644461631775,
+      "step": 462
+    },
+    {
+      "epoch": 0.19578059071729959,
+      "grad_norm": 1.9403492212295532,
+      "learning_rate": 4.068541300527241e-05,
+      "loss": 0.914577305316925,
+      "step": 464
+    },
+    {
+      "epoch": 0.19662447257383966,
+      "grad_norm": 1.9939641952514648,
+      "learning_rate": 4.086115992970123e-05,
+      "loss": 0.8592531681060791,
+      "step": 466
+    },
+    {
+      "epoch": 0.19746835443037974,
+      "grad_norm": 2.1511380672454834,
+      "learning_rate": 4.103690685413005e-05,
+      "loss": 0.9251965880393982,
+      "step": 468
+    },
+    {
+      "epoch": 0.19831223628691982,
+      "grad_norm": 2.2260982990264893,
+      "learning_rate": 4.121265377855888e-05,
+      "loss": 0.8465172052383423,
+      "step": 470
+    },
+    {
+      "epoch": 0.1991561181434599,
+      "grad_norm": 2.0510010719299316,
+      "learning_rate": 4.13884007029877e-05,
+      "loss": 0.8943672180175781,
+      "step": 472
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.2040133476257324,
+      "learning_rate": 4.156414762741652e-05,
+      "loss": 0.9594319462776184,
+      "step": 474
+    },
+    {
+      "epoch": 0.2008438818565401,
+      "grad_norm": 2.355181932449341,
+      "learning_rate": 4.173989455184534e-05,
+      "loss": 0.9031813144683838,
+      "step": 476
+    },
+    {
+      "epoch": 0.20168776371308017,
+      "grad_norm": 2.8434665203094482,
+      "learning_rate": 4.1915641476274166e-05,
+      "loss": 0.9225798845291138,
+      "step": 478
+    },
+    {
+      "epoch": 0.20253164556962025,
+      "grad_norm": 2.1715340614318848,
+      "learning_rate": 4.209138840070299e-05,
+      "loss": 0.894163966178894,
+      "step": 480
+    },
+    {
+      "epoch": 0.20337552742616033,
+      "grad_norm": 2.078916072845459,
+      "learning_rate": 4.226713532513181e-05,
+      "loss": 0.8424109816551208,
+      "step": 482
+    },
+    {
+      "epoch": 0.2042194092827004,
+      "grad_norm": 1.9760961532592773,
+      "learning_rate": 4.244288224956064e-05,
+      "loss": 0.9102715849876404,
+      "step": 484
+    },
+    {
+      "epoch": 0.20506329113924052,
+      "grad_norm": 1.9684507846832275,
+      "learning_rate": 4.2618629173989456e-05,
+      "loss": 0.8693854808807373,
+      "step": 486
+    },
+    {
+      "epoch": 0.2059071729957806,
+      "grad_norm": 2.1633450984954834,
+      "learning_rate": 4.279437609841828e-05,
+      "loss": 0.8617543578147888,
+      "step": 488
+    },
+    {
+      "epoch": 0.20675105485232068,
+      "grad_norm": 2.2695257663726807,
+      "learning_rate": 4.29701230228471e-05,
+      "loss": 0.9167086482048035,
+      "step": 490
+    },
+    {
+      "epoch": 0.20759493670886076,
+      "grad_norm": 2.4180049896240234,
+      "learning_rate": 4.314586994727593e-05,
+      "loss": 0.8333520889282227,
+      "step": 492
+    },
+    {
+      "epoch": 0.20843881856540084,
+      "grad_norm": 2.2942769527435303,
+      "learning_rate": 4.3321616871704746e-05,
+      "loss": 0.918351411819458,
+      "step": 494
+    },
+    {
+      "epoch": 0.20928270042194091,
+      "grad_norm": 1.826458215713501,
+      "learning_rate": 4.349736379613357e-05,
+      "loss": 0.8565171957015991,
+      "step": 496
+    },
+    {
+      "epoch": 0.21012658227848102,
+      "grad_norm": 1.9694055318832397,
+      "learning_rate": 4.367311072056239e-05,
+      "loss": 0.8684167861938477,
+      "step": 498
+    },
+    {
+      "epoch": 0.2109704641350211,
+      "grad_norm": 1.892659306526184,
+      "learning_rate": 4.384885764499122e-05,
+      "loss": 0.7752788662910461,
+      "step": 500
+    },
+    {
+      "epoch": 0.2109704641350211,
+      "eval_loss": 0.9080732464790344,
+      "eval_runtime": 857.0753,
+      "eval_samples_per_second": 2.458,
+      "eval_steps_per_second": 2.458,
+      "step": 500
+    },
+    {
+      "epoch": 0.21181434599156118,
+      "grad_norm": 1.9322253465652466,
+      "learning_rate": 4.4024604569420036e-05,
+      "loss": 0.948570728302002,
+      "step": 502
+    },
+    {
+      "epoch": 0.21265822784810126,
+      "grad_norm": 2.0456058979034424,
+      "learning_rate": 4.4200351493848855e-05,
+      "loss": 0.8741024732589722,
+      "step": 504
+    },
+    {
+      "epoch": 0.21350210970464134,
+      "grad_norm": 2.2406177520751953,
+      "learning_rate": 4.437609841827768e-05,
+      "loss": 0.9053841829299927,
+      "step": 506
+    },
+    {
+      "epoch": 0.21434599156118145,
+      "grad_norm": 2.013934850692749,
+      "learning_rate": 4.455184534270651e-05,
+      "loss": 0.8886576294898987,
+      "step": 508
+    },
+    {
+      "epoch": 0.21518987341772153,
+      "grad_norm": 1.9771125316619873,
+      "learning_rate": 4.4727592267135326e-05,
+      "loss": 0.8834167718887329,
+      "step": 510
+    },
+    {
+      "epoch": 0.2160337552742616,
+      "grad_norm": 1.785905361175537,
+      "learning_rate": 4.4903339191564146e-05,
+      "loss": 0.7938863039016724,
+      "step": 512
+    },
+    {
+      "epoch": 0.2168776371308017,
+      "grad_norm": 1.7946031093597412,
+      "learning_rate": 4.507908611599297e-05,
+      "loss": 0.8071596026420593,
+      "step": 514
+    },
+    {
+      "epoch": 0.21772151898734177,
+      "grad_norm": 2.2217721939086914,
+      "learning_rate": 4.52548330404218e-05,
+      "loss": 0.797417163848877,
+      "step": 516
+    },
+    {
+      "epoch": 0.21856540084388185,
+      "grad_norm": 1.9022471904754639,
+      "learning_rate": 4.5430579964850617e-05,
+      "loss": 0.8109536170959473,
+      "step": 518
+    },
+    {
+      "epoch": 0.21940928270042195,
+      "grad_norm": 1.8988343477249146,
+      "learning_rate": 4.5606326889279436e-05,
+      "loss": 0.8647034168243408,
+      "step": 520
+    },
+    {
+      "epoch": 0.22025316455696203,
+      "grad_norm": 2.6014881134033203,
+      "learning_rate": 4.578207381370827e-05,
+      "loss": 0.8763713240623474,
+      "step": 522
+    },
+    {
+      "epoch": 0.2210970464135021,
+      "grad_norm": 1.9512032270431519,
+      "learning_rate": 4.595782073813709e-05,
+      "loss": 0.9525764584541321,
+      "step": 524
+    },
+    {
+      "epoch": 0.2219409282700422,
+      "grad_norm": 1.9246160984039307,
+      "learning_rate": 4.613356766256591e-05,
+      "loss": 0.8839208483695984,
+      "step": 526
+    },
+    {
+      "epoch": 0.22278481012658227,
+      "grad_norm": 1.9713703393936157,
+      "learning_rate": 4.6309314586994726e-05,
+      "loss": 0.8888868093490601,
+      "step": 528
+    },
+    {
+      "epoch": 0.22362869198312235,
+      "grad_norm": 2.1175239086151123,
+      "learning_rate": 4.648506151142355e-05,
+      "loss": 0.8123540878295898,
+      "step": 530
+    },
+    {
+      "epoch": 0.22447257383966246,
+      "grad_norm": 1.7656135559082031,
+      "learning_rate": 4.666080843585238e-05,
+      "loss": 0.7447702884674072,
+      "step": 532
+    },
+    {
+      "epoch": 0.22531645569620254,
+      "grad_norm": 2.15748929977417,
+      "learning_rate": 4.68365553602812e-05,
+      "loss": 0.8778411746025085,
+      "step": 534
+    },
+    {
+      "epoch": 0.22616033755274262,
+      "grad_norm": 2.1733345985412598,
+      "learning_rate": 4.7012302284710016e-05,
+      "loss": 0.8985894918441772,
+      "step": 536
+    },
+    {
+      "epoch": 0.2270042194092827,
+      "grad_norm": 1.7182204723358154,
+      "learning_rate": 4.718804920913884e-05,
+      "loss": 0.8031114339828491,
+      "step": 538
+    },
+    {
+      "epoch": 0.22784810126582278,
+      "grad_norm": 1.8586329221725464,
+      "learning_rate": 4.736379613356767e-05,
+      "loss": 0.9399706721305847,
+      "step": 540
+    },
+    {
+      "epoch": 0.22869198312236286,
+      "grad_norm": 2.105637311935425,
+      "learning_rate": 4.753954305799649e-05,
+      "loss": 0.8672119975090027,
+      "step": 542
+    },
+    {
+      "epoch": 0.22953586497890296,
+      "grad_norm": 1.760584831237793,
+      "learning_rate": 4.771528998242531e-05,
+      "loss": 0.8663905262947083,
+      "step": 544
+    },
+    {
+      "epoch": 0.23037974683544304,
+      "grad_norm": 1.579990267753601,
+      "learning_rate": 4.789103690685413e-05,
+      "loss": 0.8575801849365234,
+      "step": 546
+    },
+    {
+      "epoch": 0.23122362869198312,
+      "grad_norm": 1.9242485761642456,
+      "learning_rate": 4.806678383128295e-05,
+      "loss": 0.828412652015686,
+      "step": 548
+    },
+    {
+      "epoch": 0.2320675105485232,
+      "grad_norm": 1.812137246131897,
+      "learning_rate": 4.824253075571178e-05,
+      "loss": 0.8183464407920837,
+      "step": 550
+    },
+    {
+      "epoch": 0.23291139240506328,
+      "grad_norm": 1.804733395576477,
+      "learning_rate": 4.84182776801406e-05,
+      "loss": 0.7822491526603699,
+      "step": 552
+    },
+    {
+      "epoch": 0.23375527426160336,
+      "grad_norm": 2.052257537841797,
+      "learning_rate": 4.859402460456942e-05,
+      "loss": 0.9050943851470947,
+      "step": 554
+    },
+    {
+      "epoch": 0.23459915611814347,
+      "grad_norm": 1.9803621768951416,
+      "learning_rate": 4.876977152899824e-05,
+      "loss": 0.8846852779388428,
+      "step": 556
+    },
+    {
+      "epoch": 0.23544303797468355,
+      "grad_norm": 1.820125937461853,
+      "learning_rate": 4.894551845342707e-05,
+      "loss": 0.8649531602859497,
+      "step": 558
+    },
+    {
+      "epoch": 0.23628691983122363,
+      "grad_norm": 2.0963921546936035,
+      "learning_rate": 4.912126537785589e-05,
+      "loss": 0.9307748079299927,
+      "step": 560
+    },
+    {
+      "epoch": 0.2371308016877637,
+      "grad_norm": 2.079697847366333,
+      "learning_rate": 4.929701230228471e-05,
+      "loss": 0.9092473387718201,
+      "step": 562
+    },
+    {
+      "epoch": 0.2379746835443038,
+      "grad_norm": 2.0291287899017334,
+      "learning_rate": 4.947275922671353e-05,
+      "loss": 0.8976567983627319,
+      "step": 564
+    },
+    {
+      "epoch": 0.23881856540084387,
+      "grad_norm": 1.9636707305908203,
+      "learning_rate": 4.964850615114236e-05,
+      "loss": 0.8931006193161011,
+      "step": 566
+    },
+    {
+      "epoch": 0.23966244725738398,
+      "grad_norm": 1.922049880027771,
+      "learning_rate": 4.982425307557118e-05,
+      "loss": 0.829562246799469,
+      "step": 568
+    },
+    {
+      "epoch": 0.24050632911392406,
+      "grad_norm": 2.150334596633911,
+      "learning_rate": 5e-05,
+      "loss": 0.8568030595779419,
+      "step": 570
+    },
+    {
+      "epoch": 0.24135021097046414,
+      "grad_norm": 2.024437427520752,
+      "learning_rate": 5.017574692442882e-05,
+      "loss": 0.8623508810997009,
+      "step": 572
+    },
+    {
+      "epoch": 0.24219409282700421,
+      "grad_norm": 1.8312673568725586,
+      "learning_rate": 5.035149384885765e-05,
+      "loss": 0.7853795886039734,
+      "step": 574
+    },
+    {
+      "epoch": 0.2430379746835443,
+      "grad_norm": 1.9271961450576782,
+      "learning_rate": 5.0527240773286467e-05,
+      "loss": 0.9727587103843689,
+      "step": 576
+    },
+    {
+      "epoch": 0.2438818565400844,
+      "grad_norm": 1.931249976158142,
+      "learning_rate": 5.0702987697715286e-05,
+      "loss": 0.8859632015228271,
+      "step": 578
+    },
+    {
+      "epoch": 0.24472573839662448,
+      "grad_norm": 1.8195210695266724,
+      "learning_rate": 5.087873462214412e-05,
+      "loss": 0.8959492444992065,
+      "step": 580
+    },
+    {
+      "epoch": 0.24556962025316456,
+      "grad_norm": 2.0018749237060547,
+      "learning_rate": 5.105448154657294e-05,
+      "loss": 0.8146185874938965,
+      "step": 582
+    },
+    {
+      "epoch": 0.24641350210970464,
+      "grad_norm": 2.09798526763916,
+      "learning_rate": 5.1230228471001764e-05,
+      "loss": 0.8545317053794861,
+      "step": 584
+    },
+    {
+      "epoch": 0.24725738396624472,
+      "grad_norm": 1.8063944578170776,
+      "learning_rate": 5.140597539543058e-05,
+      "loss": 0.8650105595588684,
+      "step": 586
+    },
+    {
+      "epoch": 0.2481012658227848,
+      "grad_norm": 1.8535740375518799,
+      "learning_rate": 5.15817223198594e-05,
+      "loss": 0.8395693302154541,
+      "step": 588
+    },
+    {
+      "epoch": 0.2489451476793249,
+      "grad_norm": 2.1443960666656494,
+      "learning_rate": 5.175746924428823e-05,
+      "loss": 0.8267397284507751,
+      "step": 590
+    },
+    {
+      "epoch": 0.249789029535865,
+      "grad_norm": 1.9637391567230225,
+      "learning_rate": 5.193321616871705e-05,
+      "loss": 0.8500015139579773,
+      "step": 592
+    },
+    {
+      "epoch": 0.25063291139240507,
+      "grad_norm": 1.9457582235336304,
+      "learning_rate": 5.2108963093145866e-05,
+      "loss": 0.887481153011322,
+      "step": 594
+    },
+    {
+      "epoch": 0.2514767932489452,
+      "grad_norm": 1.7458715438842773,
+      "learning_rate": 5.228471001757469e-05,
+      "loss": 0.8444154858589172,
+      "step": 596
+    },
+    {
+      "epoch": 0.2523206751054852,
+      "grad_norm": 1.8341439962387085,
+      "learning_rate": 5.2460456942003525e-05,
+      "loss": 0.8301781415939331,
+      "step": 598
+    },
+    {
+      "epoch": 0.25316455696202533,
+      "grad_norm": 2.127747058868408,
+      "learning_rate": 5.2636203866432344e-05,
+      "loss": 0.8921551704406738,
+      "step": 600
+    },
+    {
+      "epoch": 0.25316455696202533,
+      "eval_loss": 0.8903881311416626,
+      "eval_runtime": 845.9969,
+      "eval_samples_per_second": 2.491,
+      "eval_steps_per_second": 2.491,
+      "step": 600
+    },
+    {
+      "epoch": 0.2540084388185654,
+      "grad_norm": 2.421459674835205,
+      "learning_rate": 5.281195079086116e-05,
+      "loss": 0.8678019642829895,
+      "step": 602
+    },
+    {
+      "epoch": 0.2548523206751055,
+      "grad_norm": 1.7736057043075562,
+      "learning_rate": 5.298769771528999e-05,
+      "loss": 0.8564275503158569,
+      "step": 604
+    },
+    {
+      "epoch": 0.25569620253164554,
+      "grad_norm": 2.28430438041687,
+      "learning_rate": 5.316344463971881e-05,
+      "loss": 0.8529049158096313,
+      "step": 606
+    },
+    {
+      "epoch": 0.25654008438818565,
+      "grad_norm": 1.8892366886138916,
+      "learning_rate": 5.333919156414763e-05,
+      "loss": 0.8672881126403809,
+      "step": 608
+    },
+    {
+      "epoch": 0.25738396624472576,
+      "grad_norm": 1.9059702157974243,
+      "learning_rate": 5.3514938488576446e-05,
+      "loss": 0.9094445109367371,
+      "step": 610
+    },
+    {
+      "epoch": 0.2582278481012658,
+      "grad_norm": 2.0657339096069336,
+      "learning_rate": 5.369068541300527e-05,
+      "loss": 0.8361946940422058,
+      "step": 612
+    },
+    {
+      "epoch": 0.2590717299578059,
+      "grad_norm": 1.8987553119659424,
+      "learning_rate": 5.3866432337434105e-05,
+      "loss": 0.8319925665855408,
+      "step": 614
+    },
+    {
+      "epoch": 0.25991561181434597,
+      "grad_norm": 2.1176226139068604,
+      "learning_rate": 5.4042179261862924e-05,
+      "loss": 0.9818069934844971,
+      "step": 616
+    },
+    {
+      "epoch": 0.2607594936708861,
+      "grad_norm": 2.142096519470215,
+      "learning_rate": 5.421792618629174e-05,
+      "loss": 0.8675919771194458,
+      "step": 618
+    },
+    {
+      "epoch": 0.2616033755274262,
+      "grad_norm": 1.9527089595794678,
+      "learning_rate": 5.439367311072057e-05,
+      "loss": 0.8845479488372803,
+      "step": 620
+    },
+    {
+      "epoch": 0.26244725738396624,
+      "grad_norm": 1.7071453332901,
+      "learning_rate": 5.456942003514939e-05,
+      "loss": 0.809393048286438,
+      "step": 622
+    },
+    {
+      "epoch": 0.26329113924050634,
+      "grad_norm": 1.9133527278900146,
+      "learning_rate": 5.474516695957821e-05,
+      "loss": 0.8262377977371216,
+      "step": 624
+    },
+    {
+      "epoch": 0.2641350210970464,
+      "grad_norm": 2.0217554569244385,
+      "learning_rate": 5.492091388400703e-05,
+      "loss": 0.9006736278533936,
+      "step": 626
+    },
+    {
+      "epoch": 0.2649789029535865,
+      "grad_norm": 1.773273229598999,
+      "learning_rate": 5.509666080843585e-05,
+      "loss": 0.8243603110313416,
+      "step": 628
+    },
+    {
+      "epoch": 0.26582278481012656,
+      "grad_norm": 1.6580880880355835,
+      "learning_rate": 5.527240773286467e-05,
+      "loss": 0.8112778663635254,
+      "step": 630
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.8342082500457764,
+      "learning_rate": 5.5448154657293504e-05,
+      "loss": 0.8390820622444153,
+      "step": 632
+    },
+    {
+      "epoch": 0.26751054852320677,
+      "grad_norm": 1.863695502281189,
+      "learning_rate": 5.5623901581722323e-05,
+      "loss": 0.8264521360397339,
+      "step": 634
+    },
+    {
+      "epoch": 0.2683544303797468,
+      "grad_norm": 1.9462928771972656,
+      "learning_rate": 5.579964850615115e-05,
+      "loss": 0.9512701630592346,
+      "step": 636
+    },
+    {
+      "epoch": 0.26919831223628693,
+      "grad_norm": 1.7776058912277222,
+      "learning_rate": 5.597539543057997e-05,
+      "loss": 0.9422703981399536,
+      "step": 638
+    },
+    {
+      "epoch": 0.270042194092827,
+      "grad_norm": 2.9457077980041504,
+      "learning_rate": 5.615114235500879e-05,
+      "loss": 0.7991042137145996,
+      "step": 640
+    },
+    {
+      "epoch": 0.2708860759493671,
+      "grad_norm": 1.445265531539917,
+      "learning_rate": 5.6326889279437614e-05,
+      "loss": 0.8188099265098572,
+      "step": 642
+    },
+    {
+      "epoch": 0.2717299578059072,
+      "grad_norm": 2.063850164413452,
+      "learning_rate": 5.650263620386643e-05,
+      "loss": 0.9799772500991821,
+      "step": 644
+    },
+    {
+      "epoch": 0.27257383966244725,
+      "grad_norm": 2.0488009452819824,
+      "learning_rate": 5.667838312829525e-05,
+      "loss": 0.8462742567062378,
+      "step": 646
+    },
+    {
+      "epoch": 0.27341772151898736,
+      "grad_norm": 1.8747851848602295,
+      "learning_rate": 5.685413005272408e-05,
+      "loss": 0.8226412534713745,
+      "step": 648
+    },
+    {
+      "epoch": 0.2742616033755274,
+      "grad_norm": 1.849074125289917,
+      "learning_rate": 5.702987697715291e-05,
+      "loss": 0.9146338105201721,
+      "step": 650
+    },
+    {
+      "epoch": 0.2751054852320675,
+      "grad_norm": 1.7738500833511353,
+      "learning_rate": 5.720562390158173e-05,
+      "loss": 0.7574424147605896,
+      "step": 652
+    },
+    {
+      "epoch": 0.2759493670886076,
+      "grad_norm": 1.911102294921875,
+      "learning_rate": 5.738137082601055e-05,
+      "loss": 0.8930003046989441,
+      "step": 654
+    },
+    {
+      "epoch": 0.2767932489451477,
+      "grad_norm": 1.5716617107391357,
+      "learning_rate": 5.755711775043937e-05,
+      "loss": 0.7578965425491333,
+      "step": 656
+    },
+    {
+      "epoch": 0.2776371308016878,
+      "grad_norm": 1.789036512374878,
+      "learning_rate": 5.7732864674868194e-05,
+      "loss": 0.8149038553237915,
+      "step": 658
+    },
+    {
+      "epoch": 0.27848101265822783,
+      "grad_norm": 1.68622624874115,
+      "learning_rate": 5.790861159929701e-05,
+      "loss": 0.8265765905380249,
+      "step": 660
+    },
+    {
+      "epoch": 0.27932489451476794,
+      "grad_norm": 2.078423261642456,
+      "learning_rate": 5.808435852372583e-05,
+      "loss": 0.9651970267295837,
+      "step": 662
+    },
+    {
+      "epoch": 0.280168776371308,
+      "grad_norm": 1.7878645658493042,
+      "learning_rate": 5.826010544815466e-05,
+      "loss": 0.8295148015022278,
+      "step": 664
+    },
+    {
+      "epoch": 0.2810126582278481,
+      "grad_norm": 1.970838189125061,
+      "learning_rate": 5.843585237258348e-05,
+      "loss": 0.7778491377830505,
+      "step": 666
+    },
+    {
+      "epoch": 0.2818565400843882,
+      "grad_norm": 1.943596363067627,
+      "learning_rate": 5.861159929701231e-05,
+      "loss": 0.9818071722984314,
+      "step": 668
+    },
+    {
+      "epoch": 0.28270042194092826,
+      "grad_norm": 1.8793812990188599,
+      "learning_rate": 5.878734622144113e-05,
+      "loss": 0.9297797083854675,
+      "step": 670
+    },
+    {
+      "epoch": 0.28354430379746837,
+      "grad_norm": 1.8813483715057373,
+      "learning_rate": 5.8963093145869955e-05,
+      "loss": 0.8748109936714172,
+      "step": 672
+    },
+    {
+      "epoch": 0.2843881856540084,
+      "grad_norm": 1.7658562660217285,
+      "learning_rate": 5.9138840070298774e-05,
+      "loss": 0.8505244851112366,
+      "step": 674
+    },
+    {
+      "epoch": 0.2852320675105485,
+      "grad_norm": 1.6767617464065552,
+      "learning_rate": 5.931458699472759e-05,
+      "loss": 0.8476597666740417,
+      "step": 676
+    },
+    {
+      "epoch": 0.28607594936708863,
+      "grad_norm": 2.703104257583618,
+      "learning_rate": 5.949033391915641e-05,
+      "loss": 0.8775192499160767,
+      "step": 678
+    },
+    {
+      "epoch": 0.2869198312236287,
+      "grad_norm": 1.9959728717803955,
+      "learning_rate": 5.966608084358524e-05,
+      "loss": 0.855262279510498,
+      "step": 680
+    },
+    {
+      "epoch": 0.2877637130801688,
+      "grad_norm": 1.9093716144561768,
+      "learning_rate": 5.984182776801406e-05,
+      "loss": 0.7574936151504517,
+      "step": 682
+    },
+    {
+      "epoch": 0.28860759493670884,
+      "grad_norm": 1.9829599857330322,
+      "learning_rate": 6.001757469244289e-05,
+      "loss": 0.8630690574645996,
+      "step": 684
+    },
+    {
+      "epoch": 0.28945147679324895,
+      "grad_norm": 1.8777490854263306,
+      "learning_rate": 6.019332161687171e-05,
+      "loss": 0.8513249158859253,
+      "step": 686
+    },
+    {
+      "epoch": 0.290295358649789,
+      "grad_norm": 1.9453173875808716,
+      "learning_rate": 6.0369068541300535e-05,
+      "loss": 0.9097008109092712,
+      "step": 688
+    },
+    {
+      "epoch": 0.2911392405063291,
+      "grad_norm": 1.8527908325195312,
+      "learning_rate": 6.0544815465729354e-05,
+      "loss": 0.8291722536087036,
+      "step": 690
+    },
+    {
+      "epoch": 0.2919831223628692,
+      "grad_norm": 1.9255812168121338,
+      "learning_rate": 6.0720562390158174e-05,
+      "loss": 0.880009651184082,
+      "step": 692
+    },
+    {
+      "epoch": 0.29282700421940927,
+      "grad_norm": 1.6637977361679077,
+      "learning_rate": 6.0896309314587e-05,
+      "loss": 0.8791794180870056,
+      "step": 694
+    },
+    {
+      "epoch": 0.2936708860759494,
+      "grad_norm": 1.825940728187561,
+      "learning_rate": 6.107205623901582e-05,
+      "loss": 0.8662407398223877,
+      "step": 696
+    },
+    {
+      "epoch": 0.29451476793248943,
+      "grad_norm": 1.9348198175430298,
+      "learning_rate": 6.124780316344464e-05,
+      "loss": 0.8984515070915222,
+      "step": 698
+    },
+    {
+      "epoch": 0.29535864978902954,
+      "grad_norm": 1.659345030784607,
+      "learning_rate": 6.142355008787346e-05,
+      "loss": 0.827385663986206,
+      "step": 700
+    },
+    {
+      "epoch": 0.29535864978902954,
+      "eval_loss": 0.8730722069740295,
+      "eval_runtime": 858.184,
+      "eval_samples_per_second": 2.455,
+      "eval_steps_per_second": 2.455,
+      "step": 700
+    },
+    {
+      "epoch": 0.29620253164556964,
+      "grad_norm": 1.6531789302825928,
+      "learning_rate": 6.159929701230229e-05,
+      "loss": 0.9337764382362366,
+      "step": 702
+    },
+    {
+      "epoch": 0.2970464135021097,
+      "grad_norm": 1.8269121646881104,
+      "learning_rate": 6.177504393673111e-05,
+      "loss": 0.8250943422317505,
+      "step": 704
+    },
+    {
+      "epoch": 0.2978902953586498,
+      "grad_norm": 1.692808747291565,
+      "learning_rate": 6.195079086115994e-05,
+      "loss": 0.8657428026199341,
+      "step": 706
+    },
+    {
+      "epoch": 0.29873417721518986,
+      "grad_norm": 1.6736913919448853,
+      "learning_rate": 6.212653778558876e-05,
+      "loss": 0.8889590501785278,
+      "step": 708
+    },
+    {
+      "epoch": 0.29957805907172996,
+      "grad_norm": 1.6841140985488892,
+      "learning_rate": 6.230228471001758e-05,
+      "loss": 0.7822914123535156,
+      "step": 710
+    },
+    {
+      "epoch": 0.30042194092827,
+      "grad_norm": 1.6644599437713623,
+      "learning_rate": 6.24780316344464e-05,
+      "loss": 0.8747053742408752,
+      "step": 712
+    },
+    {
+      "epoch": 0.3012658227848101,
+      "grad_norm": 1.8187819719314575,
+      "learning_rate": 6.265377855887522e-05,
+      "loss": 0.8976446390151978,
+      "step": 714
+    },
+    {
+      "epoch": 0.30210970464135023,
+      "grad_norm": 1.7845178842544556,
+      "learning_rate": 6.282952548330404e-05,
+      "loss": 0.9401160478591919,
+      "step": 716
+    },
+    {
+      "epoch": 0.3029535864978903,
+      "grad_norm": 1.559773564338684,
+      "learning_rate": 6.300527240773286e-05,
+      "loss": 0.8754280209541321,
+      "step": 718
+    },
+    {
+      "epoch": 0.3037974683544304,
+      "grad_norm": 1.5919631719589233,
+      "learning_rate": 6.318101933216169e-05,
+      "loss": 0.8278581500053406,
+      "step": 720
+    },
+    {
+      "epoch": 0.30464135021097044,
+      "grad_norm": 1.8551076650619507,
+      "learning_rate": 6.335676625659052e-05,
+      "loss": 0.8868640065193176,
+      "step": 722
+    },
+    {
+      "epoch": 0.30548523206751055,
+      "grad_norm": 1.6907769441604614,
+      "learning_rate": 6.353251318101934e-05,
+      "loss": 0.8631605505943298,
+      "step": 724
+    },
+    {
+      "epoch": 0.30632911392405066,
+      "grad_norm": 1.820867657661438,
+      "learning_rate": 6.370826010544816e-05,
+      "loss": 0.9142873883247375,
+      "step": 726
+    },
+    {
+      "epoch": 0.3071729957805907,
+      "grad_norm": 1.685154676437378,
+      "learning_rate": 6.388400702987698e-05,
+      "loss": 0.8258634805679321,
+      "step": 728
+    },
+    {
+      "epoch": 0.3080168776371308,
+      "grad_norm": 1.9294627904891968,
+      "learning_rate": 6.40597539543058e-05,
+      "loss": 0.9545516967773438,
+      "step": 730
+    },
+    {
+      "epoch": 0.30886075949367087,
+      "grad_norm": 1.6075409650802612,
+      "learning_rate": 6.423550087873462e-05,
+      "loss": 0.8370757699012756,
+      "step": 732
+    },
+    {
+      "epoch": 0.309704641350211,
+      "grad_norm": 1.635750651359558,
+      "learning_rate": 6.441124780316345e-05,
+      "loss": 0.8356084823608398,
+      "step": 734
+    },
+    {
+      "epoch": 0.3105485232067511,
+      "grad_norm": 1.6376131772994995,
+      "learning_rate": 6.458699472759227e-05,
+      "loss": 0.7579531669616699,
+      "step": 736
+    },
+    {
+      "epoch": 0.31139240506329113,
+      "grad_norm": 1.7135766744613647,
+      "learning_rate": 6.47627416520211e-05,
+      "loss": 0.8436318039894104,
+      "step": 738
+    },
+    {
+      "epoch": 0.31223628691983124,
+      "grad_norm": 1.7095093727111816,
+      "learning_rate": 6.493848857644992e-05,
+      "loss": 0.7998805046081543,
+      "step": 740
+    },
+    {
+      "epoch": 0.3130801687763713,
+      "grad_norm": 1.782615303993225,
+      "learning_rate": 6.511423550087874e-05,
+      "loss": 0.915776789188385,
+      "step": 742
+    },
+    {
+      "epoch": 0.3139240506329114,
+      "grad_norm": 1.8461172580718994,
+      "learning_rate": 6.528998242530756e-05,
+      "loss": 0.8300962448120117,
+      "step": 744
+    },
+    {
+      "epoch": 0.31476793248945145,
+      "grad_norm": 1.5659871101379395,
+      "learning_rate": 6.546572934973638e-05,
+      "loss": 0.8239848017692566,
+      "step": 746
+    },
+    {
+      "epoch": 0.31561181434599156,
+      "grad_norm": 1.9997349977493286,
+      "learning_rate": 6.56414762741652e-05,
+      "loss": 0.8236988186836243,
+      "step": 748
+    },
+    {
+      "epoch": 0.31645569620253167,
+      "grad_norm": 1.9811526536941528,
+      "learning_rate": 6.581722319859403e-05,
+      "loss": 0.8516603112220764,
+      "step": 750
+    },
+    {
+      "epoch": 0.3172995780590717,
+      "grad_norm": 1.9877923727035522,
+      "learning_rate": 6.599297012302285e-05,
+      "loss": 0.9037567973136902,
+      "step": 752
+    },
+    {
+      "epoch": 0.3181434599156118,
+      "grad_norm": 1.6729352474212646,
+      "learning_rate": 6.616871704745168e-05,
+      "loss": 0.8350864052772522,
+      "step": 754
+    },
+    {
+      "epoch": 0.3189873417721519,
+      "grad_norm": 1.9055802822113037,
+      "learning_rate": 6.63444639718805e-05,
+      "loss": 0.8246616125106812,
+      "step": 756
+    },
+    {
+      "epoch": 0.319831223628692,
+      "grad_norm": 1.597999930381775,
+      "learning_rate": 6.652021089630932e-05,
+      "loss": 0.8014416098594666,
+      "step": 758
+    },
+    {
+      "epoch": 0.3206751054852321,
+      "grad_norm": 1.7432531118392944,
+      "learning_rate": 6.669595782073814e-05,
+      "loss": 0.9199523329734802,
+      "step": 760
+    },
+    {
+      "epoch": 0.32151898734177214,
+      "grad_norm": 1.820164442062378,
+      "learning_rate": 6.687170474516696e-05,
+      "loss": 0.7764829397201538,
+      "step": 762
+    },
+    {
+      "epoch": 0.32236286919831225,
+      "grad_norm": 1.6408652067184448,
+      "learning_rate": 6.704745166959578e-05,
+      "loss": 0.8072620630264282,
+      "step": 764
+    },
+    {
+      "epoch": 0.3232067510548523,
+      "grad_norm": 1.8894155025482178,
+      "learning_rate": 6.722319859402461e-05,
+      "loss": 0.9006885886192322,
+      "step": 766
+    },
+    {
+      "epoch": 0.3240506329113924,
+      "grad_norm": 1.6903613805770874,
+      "learning_rate": 6.739894551845343e-05,
+      "loss": 0.7772189378738403,
+      "step": 768
+    },
+    {
+      "epoch": 0.32489451476793246,
+      "grad_norm": 1.7540696859359741,
+      "learning_rate": 6.757469244288225e-05,
+      "loss": 0.8825590014457703,
+      "step": 770
+    },
+    {
+      "epoch": 0.32573839662447257,
+      "grad_norm": 1.603008508682251,
+      "learning_rate": 6.775043936731108e-05,
+      "loss": 0.8376453518867493,
+      "step": 772
+    },
+    {
+      "epoch": 0.3265822784810127,
+      "grad_norm": 1.5381462574005127,
+      "learning_rate": 6.79261862917399e-05,
+      "loss": 0.92608243227005,
+      "step": 774
+    },
+    {
+      "epoch": 0.32742616033755273,
+      "grad_norm": 1.4815537929534912,
+      "learning_rate": 6.810193321616872e-05,
+      "loss": 0.6842183470726013,
+      "step": 776
+    },
+    {
+      "epoch": 0.32827004219409284,
+      "grad_norm": 1.8543411493301392,
+      "learning_rate": 6.827768014059754e-05,
+      "loss": 0.8868235349655151,
+      "step": 778
+    },
+    {
+      "epoch": 0.3291139240506329,
+      "grad_norm": 1.8895748853683472,
+      "learning_rate": 6.845342706502637e-05,
+      "loss": 0.8148112297058105,
+      "step": 780
+    },
+    {
+      "epoch": 0.329957805907173,
+      "grad_norm": 1.8150591850280762,
+      "learning_rate": 6.862917398945519e-05,
+      "loss": 0.8760337829589844,
+      "step": 782
+    },
+    {
+      "epoch": 0.3308016877637131,
+      "grad_norm": 1.6661378145217896,
+      "learning_rate": 6.880492091388401e-05,
+      "loss": 0.8266322612762451,
+      "step": 784
+    },
+    {
+      "epoch": 0.33164556962025316,
+      "grad_norm": 2.2849128246307373,
+      "learning_rate": 6.898066783831283e-05,
+      "loss": 0.8599053025245667,
+      "step": 786
+    },
+    {
+      "epoch": 0.33248945147679326,
+      "grad_norm": 1.7233171463012695,
+      "learning_rate": 6.915641476274165e-05,
+      "loss": 0.8312317132949829,
+      "step": 788
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 1.7637618780136108,
+      "learning_rate": 6.933216168717048e-05,
+      "loss": 0.8379700779914856,
+      "step": 790
+    },
+    {
+      "epoch": 0.3341772151898734,
+      "grad_norm": 1.7780474424362183,
+      "learning_rate": 6.95079086115993e-05,
+      "loss": 0.8994934558868408,
+      "step": 792
+    },
+    {
+      "epoch": 0.33502109704641353,
+      "grad_norm": 1.5798883438110352,
+      "learning_rate": 6.968365553602812e-05,
+      "loss": 0.8021857738494873,
+      "step": 794
+    },
+    {
+      "epoch": 0.3358649789029536,
+      "grad_norm": 1.7316070795059204,
+      "learning_rate": 6.985940246045695e-05,
+      "loss": 0.8814419507980347,
+      "step": 796
+    },
+    {
+      "epoch": 0.3367088607594937,
+      "grad_norm": 1.711315631866455,
+      "learning_rate": 7.003514938488577e-05,
+      "loss": 0.8545029163360596,
+      "step": 798
+    },
+    {
+      "epoch": 0.33755274261603374,
+      "grad_norm": 1.5023137331008911,
+      "learning_rate": 7.021089630931459e-05,
+      "loss": 0.8006189465522766,
+      "step": 800
+    },
+    {
+      "epoch": 0.33755274261603374,
+      "eval_loss": 0.8635594248771667,
+      "eval_runtime": 865.9348,
+      "eval_samples_per_second": 2.433,
+      "eval_steps_per_second": 2.433,
+      "step": 800
+    },
+    {
+      "epoch": 0.33839662447257385,
+      "grad_norm": 1.8377124071121216,
+      "learning_rate": 7.038664323374341e-05,
+      "loss": 0.7625874280929565,
+      "step": 802
+    },
+    {
+      "epoch": 0.3392405063291139,
+      "grad_norm": 1.5361332893371582,
+      "learning_rate": 7.056239015817223e-05,
+      "loss": 0.8490484356880188,
+      "step": 804
+    },
+    {
+      "epoch": 0.340084388185654,
+      "grad_norm": 1.8727388381958008,
+      "learning_rate": 7.073813708260105e-05,
+      "loss": 0.8915753364562988,
+      "step": 806
+    },
+    {
+      "epoch": 0.3409282700421941,
+      "grad_norm": 1.567700743675232,
+      "learning_rate": 7.091388400702988e-05,
+      "loss": 0.8902620077133179,
+      "step": 808
+    },
+    {
+      "epoch": 0.34177215189873417,
+      "grad_norm": 1.5302914381027222,
+      "learning_rate": 7.10896309314587e-05,
+      "loss": 0.7897103428840637,
+      "step": 810
+    },
+    {
+      "epoch": 0.3426160337552743,
+      "grad_norm": 1.8819153308868408,
+      "learning_rate": 7.126537785588753e-05,
+      "loss": 0.8648831248283386,
+      "step": 812
+    },
+    {
+      "epoch": 0.3434599156118143,
+      "grad_norm": 1.5671379566192627,
+      "learning_rate": 7.144112478031635e-05,
+      "loss": 0.8449499607086182,
+      "step": 814
+    },
+    {
+      "epoch": 0.34430379746835443,
+      "grad_norm": 1.6570971012115479,
+      "learning_rate": 7.161687170474517e-05,
+      "loss": 0.848559558391571,
+      "step": 816
+    },
+    {
+      "epoch": 0.34514767932489454,
+      "grad_norm": 1.9108437299728394,
+      "learning_rate": 7.179261862917399e-05,
+      "loss": 0.8847543597221375,
+      "step": 818
+    },
+    {
+      "epoch": 0.3459915611814346,
+      "grad_norm": 1.4909496307373047,
+      "learning_rate": 7.196836555360281e-05,
+      "loss": 0.7642563581466675,
+      "step": 820
+    },
+    {
+      "epoch": 0.3468354430379747,
+      "grad_norm": 1.768518328666687,
+      "learning_rate": 7.214411247803163e-05,
+      "loss": 0.8714305758476257,
+      "step": 822
+    },
+    {
+      "epoch": 0.34767932489451475,
+      "grad_norm": 1.715343952178955,
+      "learning_rate": 7.231985940246046e-05,
+      "loss": 0.7712987661361694,
+      "step": 824
+    },
+    {
+      "epoch": 0.34852320675105486,
+      "grad_norm": 1.6687803268432617,
+      "learning_rate": 7.24956063268893e-05,
+      "loss": 0.8122798204421997,
+      "step": 826
+    },
+    {
+      "epoch": 0.3493670886075949,
+      "grad_norm": 1.5160514116287231,
+      "learning_rate": 7.267135325131811e-05,
+      "loss": 0.793245792388916,
+      "step": 828
+    },
+    {
+      "epoch": 0.350210970464135,
+      "grad_norm": 1.6449401378631592,
+      "learning_rate": 7.284710017574693e-05,
+      "loss": 0.8747497200965881,
+      "step": 830
+    },
+    {
+      "epoch": 0.3510548523206751,
+      "grad_norm": 1.3907722234725952,
+      "learning_rate": 7.302284710017575e-05,
+      "loss": 0.6743978261947632,
+      "step": 832
+    },
+    {
+      "epoch": 0.3518987341772152,
+      "grad_norm": 1.633555293083191,
+      "learning_rate": 7.319859402460457e-05,
+      "loss": 0.8524789214134216,
+      "step": 834
+    },
+    {
+      "epoch": 0.3527426160337553,
+      "grad_norm": 1.5414257049560547,
+      "learning_rate": 7.337434094903339e-05,
+      "loss": 0.8045110702514648,
+      "step": 836
+    },
+    {
+      "epoch": 0.35358649789029534,
+      "grad_norm": 1.8520616292953491,
+      "learning_rate": 7.355008787346221e-05,
+      "loss": 0.8319593071937561,
+      "step": 838
+    },
+    {
+      "epoch": 0.35443037974683544,
+      "grad_norm": 1.6629763841629028,
+      "learning_rate": 7.372583479789104e-05,
+      "loss": 0.8188939094543457,
+      "step": 840
+    },
+    {
+      "epoch": 0.35527426160337555,
+      "grad_norm": 1.804087519645691,
+      "learning_rate": 7.390158172231987e-05,
+      "loss": 0.8875360488891602,
+      "step": 842
+    },
+    {
+      "epoch": 0.3561181434599156,
+      "grad_norm": 1.6031663417816162,
+      "learning_rate": 7.407732864674869e-05,
+      "loss": 0.8159612417221069,
+      "step": 844
+    },
+    {
+      "epoch": 0.3569620253164557,
+      "grad_norm": 1.7413033246994019,
+      "learning_rate": 7.425307557117751e-05,
+      "loss": 0.8422684669494629,
+      "step": 846
+    },
+    {
+      "epoch": 0.35780590717299576,
+      "grad_norm": 1.7699719667434692,
+      "learning_rate": 7.442882249560633e-05,
+      "loss": 0.9343502521514893,
+      "step": 848
+    },
+    {
+      "epoch": 0.35864978902953587,
+      "grad_norm": 1.4613301753997803,
+      "learning_rate": 7.460456942003515e-05,
+      "loss": 0.8168979287147522,
+      "step": 850
+    },
+    {
+      "epoch": 0.3594936708860759,
+      "grad_norm": 1.542431354522705,
+      "learning_rate": 7.478031634446397e-05,
+      "loss": 0.9014382362365723,
+      "step": 852
+    },
+    {
+      "epoch": 0.36033755274261603,
+      "grad_norm": 1.6070159673690796,
+      "learning_rate": 7.49560632688928e-05,
+      "loss": 0.8162738084793091,
+      "step": 854
+    },
+    {
+      "epoch": 0.36118143459915614,
+      "grad_norm": 1.7979451417922974,
+      "learning_rate": 7.513181019332162e-05,
+      "loss": 0.8354527950286865,
+      "step": 856
+    },
+    {
+      "epoch": 0.3620253164556962,
+      "grad_norm": 2.327045202255249,
+      "learning_rate": 7.530755711775044e-05,
+      "loss": 0.8214042782783508,
+      "step": 858
+    },
+    {
+      "epoch": 0.3628691983122363,
+      "grad_norm": 1.5085111856460571,
+      "learning_rate": 7.548330404217927e-05,
+      "loss": 0.7472147941589355,
+      "step": 860
+    },
+    {
+      "epoch": 0.36371308016877635,
+      "grad_norm": 1.6006290912628174,
+      "learning_rate": 7.565905096660809e-05,
+      "loss": 0.7586950063705444,
+      "step": 862
+    },
+    {
+      "epoch": 0.36455696202531646,
+      "grad_norm": 1.5170620679855347,
+      "learning_rate": 7.583479789103691e-05,
+      "loss": 0.8169914484024048,
+      "step": 864
+    },
+    {
+      "epoch": 0.36540084388185656,
+      "grad_norm": 1.5848352909088135,
+      "learning_rate": 7.601054481546573e-05,
+      "loss": 0.8263922929763794,
+      "step": 866
+    },
+    {
+      "epoch": 0.3662447257383966,
+      "grad_norm": 1.8502342700958252,
+      "learning_rate": 7.618629173989455e-05,
+      "loss": 0.8726240992546082,
+      "step": 868
+    },
+    {
+      "epoch": 0.3670886075949367,
+      "grad_norm": 1.506847620010376,
+      "learning_rate": 7.636203866432338e-05,
+      "loss": 0.7220374941825867,
+      "step": 870
+    },
+    {
+      "epoch": 0.3679324894514768,
+      "grad_norm": 1.5350452661514282,
+      "learning_rate": 7.65377855887522e-05,
+      "loss": 0.8028547167778015,
+      "step": 872
+    },
+    {
+      "epoch": 0.3687763713080169,
+      "grad_norm": 1.5011043548583984,
+      "learning_rate": 7.671353251318102e-05,
+      "loss": 0.7659649848937988,
+      "step": 874
+    },
+    {
+      "epoch": 0.369620253164557,
+      "grad_norm": 1.7019832134246826,
+      "learning_rate": 7.688927943760984e-05,
+      "loss": 0.8773653507232666,
+      "step": 876
+    },
+    {
+      "epoch": 0.37046413502109704,
+      "grad_norm": 1.4918498992919922,
+      "learning_rate": 7.706502636203867e-05,
+      "loss": 0.7977569103240967,
+      "step": 878
+    },
+    {
+      "epoch": 0.37130801687763715,
+      "grad_norm": 1.6422638893127441,
+      "learning_rate": 7.724077328646749e-05,
+      "loss": 0.7491976022720337,
+      "step": 880
+    },
+    {
+      "epoch": 0.3721518987341772,
+      "grad_norm": 1.7590434551239014,
+      "learning_rate": 7.741652021089631e-05,
+      "loss": 0.8754181265830994,
+      "step": 882
+    },
+    {
+      "epoch": 0.3729957805907173,
+      "grad_norm": 3.868894100189209,
+      "learning_rate": 7.759226713532513e-05,
+      "loss": 0.8482301235198975,
+      "step": 884
+    },
+    {
+      "epoch": 0.37383966244725736,
+      "grad_norm": 2.111875534057617,
+      "learning_rate": 7.776801405975396e-05,
+      "loss": 0.8109031915664673,
+      "step": 886
+    },
+    {
+      "epoch": 0.37468354430379747,
+      "grad_norm": 2.0838418006896973,
+      "learning_rate": 7.794376098418278e-05,
+      "loss": 0.8660775423049927,
+      "step": 888
+    },
+    {
+      "epoch": 0.3755274261603376,
+      "grad_norm": 1.553022027015686,
+      "learning_rate": 7.81195079086116e-05,
+      "loss": 0.8418024778366089,
+      "step": 890
+    },
+    {
+      "epoch": 0.3763713080168776,
+      "grad_norm": 1.334747314453125,
+      "learning_rate": 7.829525483304042e-05,
+      "loss": 0.7764869928359985,
+      "step": 892
+    },
+    {
+      "epoch": 0.37721518987341773,
+      "grad_norm": 1.4692286252975464,
+      "learning_rate": 7.847100175746925e-05,
+      "loss": 0.7460401654243469,
+      "step": 894
+    },
+    {
+      "epoch": 0.3780590717299578,
+      "grad_norm": 1.5374023914337158,
+      "learning_rate": 7.864674868189807e-05,
+      "loss": 0.7662873268127441,
+      "step": 896
+    },
+    {
+      "epoch": 0.3789029535864979,
+      "grad_norm": 1.5662524700164795,
+      "learning_rate": 7.882249560632689e-05,
+      "loss": 0.8165306448936462,
+      "step": 898
+    },
+    {
+      "epoch": 0.379746835443038,
+      "grad_norm": 4.498590469360352,
+      "learning_rate": 7.899824253075572e-05,
+      "loss": 0.7913232445716858,
+      "step": 900
+    },
+    {
+      "epoch": 0.379746835443038,
+      "eval_loss": 0.8491304516792297,
+      "eval_runtime": 852.6211,
+      "eval_samples_per_second": 2.471,
+      "eval_steps_per_second": 2.471,
+      "step": 900
+    },
+    {
+      "epoch": 0.38059071729957805,
+      "grad_norm": 1.6320613622665405,
+      "learning_rate": 7.917398945518454e-05,
+      "loss": 0.8097161054611206,
+      "step": 902
+    },
+    {
+      "epoch": 0.38143459915611816,
+      "grad_norm": 1.2562934160232544,
+      "learning_rate": 7.934973637961336e-05,
+      "loss": 0.786399781703949,
+      "step": 904
+    },
+    {
+      "epoch": 0.3822784810126582,
+      "grad_norm": 1.6957594156265259,
+      "learning_rate": 7.952548330404218e-05,
+      "loss": 0.8385500311851501,
+      "step": 906
+    },
+    {
+      "epoch": 0.3831223628691983,
+      "grad_norm": 1.6662386655807495,
+      "learning_rate": 7.9701230228471e-05,
+      "loss": 0.8157848715782166,
+      "step": 908
+    },
+    {
+      "epoch": 0.38396624472573837,
+      "grad_norm": 1.6717777252197266,
+      "learning_rate": 7.987697715289982e-05,
+      "loss": 0.7937968373298645,
+      "step": 910
+    },
+    {
+      "epoch": 0.3848101265822785,
+      "grad_norm": 1.399484395980835,
+      "learning_rate": 8.005272407732865e-05,
+      "loss": 0.7800109386444092,
+      "step": 912
+    },
+    {
+      "epoch": 0.3856540084388186,
+      "grad_norm": 1.5671080350875854,
+      "learning_rate": 8.022847100175747e-05,
+      "loss": 0.8135939240455627,
+      "step": 914
+    },
+    {
+      "epoch": 0.38649789029535864,
+      "grad_norm": 1.4427763223648071,
+      "learning_rate": 8.04042179261863e-05,
+      "loss": 0.7482035160064697,
+      "step": 916
+    },
+    {
+      "epoch": 0.38734177215189874,
+      "grad_norm": 1.3314121961593628,
+      "learning_rate": 8.057996485061512e-05,
+      "loss": 0.7201873064041138,
+      "step": 918
+    },
+    {
+      "epoch": 0.3881856540084388,
+      "grad_norm": 1.5695286989212036,
+      "learning_rate": 8.075571177504394e-05,
+      "loss": 0.7933040857315063,
+      "step": 920
+    },
+    {
+      "epoch": 0.3890295358649789,
+      "grad_norm": 1.5091747045516968,
+      "learning_rate": 8.093145869947276e-05,
+      "loss": 0.8058338165283203,
+      "step": 922
+    },
+    {
+      "epoch": 0.389873417721519,
+      "grad_norm": 1.6287630796432495,
+      "learning_rate": 8.110720562390158e-05,
+      "loss": 0.7617828249931335,
+      "step": 924
+    },
+    {
+      "epoch": 0.39071729957805906,
+      "grad_norm": 1.6129482984542847,
+      "learning_rate": 8.12829525483304e-05,
+      "loss": 0.8710150122642517,
+      "step": 926
+    },
+    {
+      "epoch": 0.39156118143459917,
+      "grad_norm": 1.6457173824310303,
+      "learning_rate": 8.145869947275922e-05,
+      "loss": 0.9122233390808105,
+      "step": 928
+    },
+    {
+      "epoch": 0.3924050632911392,
+      "grad_norm": 1.6768827438354492,
+      "learning_rate": 8.163444639718805e-05,
+      "loss": 0.8339303731918335,
+      "step": 930
+    },
+    {
+      "epoch": 0.39324894514767933,
+      "grad_norm": 1.5419740676879883,
+      "learning_rate": 8.181019332161688e-05,
+      "loss": 0.8220396041870117,
+      "step": 932
+    },
+    {
+      "epoch": 0.39409282700421944,
+      "grad_norm": 1.4563747644424438,
+      "learning_rate": 8.19859402460457e-05,
+      "loss": 0.8531478047370911,
+      "step": 934
+    },
+    {
+      "epoch": 0.3949367088607595,
+      "grad_norm": 1.6208328008651733,
+      "learning_rate": 8.216168717047452e-05,
+      "loss": 0.8330869078636169,
+      "step": 936
+    },
+    {
+      "epoch": 0.3957805907172996,
+      "grad_norm": 1.6492482423782349,
+      "learning_rate": 8.233743409490334e-05,
+      "loss": 0.8011296987533569,
+      "step": 938
+    },
+    {
+      "epoch": 0.39662447257383965,
+      "grad_norm": 2.1611905097961426,
+      "learning_rate": 8.251318101933216e-05,
+      "loss": 0.8111353516578674,
+      "step": 940
+    },
+    {
+      "epoch": 0.39746835443037976,
+      "grad_norm": 1.7108231782913208,
+      "learning_rate": 8.268892794376098e-05,
+      "loss": 0.8282017111778259,
+      "step": 942
+    },
+    {
+      "epoch": 0.3983122362869198,
+      "grad_norm": 1.543465495109558,
+      "learning_rate": 8.286467486818981e-05,
+      "loss": 0.7770059704780579,
+      "step": 944
+    },
+    {
+      "epoch": 0.3991561181434599,
+      "grad_norm": 1.419969081878662,
+      "learning_rate": 8.304042179261863e-05,
+      "loss": 0.8646430373191833,
+      "step": 946
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.5002100467681885,
+      "learning_rate": 8.321616871704746e-05,
+      "loss": 0.7949403524398804,
+      "step": 948
+    },
+    {
+      "epoch": 0.4008438818565401,
+      "grad_norm": 1.38933265209198,
+      "learning_rate": 8.339191564147628e-05,
+      "loss": 0.8124079704284668,
+      "step": 950
+    },
+    {
+      "epoch": 0.4016877637130802,
+      "grad_norm": 1.5948443412780762,
+      "learning_rate": 8.35676625659051e-05,
+      "loss": 0.8634148836135864,
+      "step": 952
+    },
+    {
+      "epoch": 0.40253164556962023,
+      "grad_norm": 1.4437624216079712,
+      "learning_rate": 8.374340949033392e-05,
+      "loss": 0.7410681247711182,
+      "step": 954
+    },
+    {
+      "epoch": 0.40337552742616034,
+      "grad_norm": 1.3457095623016357,
+      "learning_rate": 8.391915641476274e-05,
+      "loss": 0.7680280208587646,
+      "step": 956
+    },
+    {
+      "epoch": 0.40421940928270045,
+      "grad_norm": 1.610288143157959,
+      "learning_rate": 8.409490333919156e-05,
+      "loss": 0.7921904921531677,
+      "step": 958
+    },
+    {
+      "epoch": 0.4050632911392405,
+      "grad_norm": 1.5321530103683472,
+      "learning_rate": 8.427065026362039e-05,
+      "loss": 0.8320037126541138,
+      "step": 960
+    },
+    {
+      "epoch": 0.4059071729957806,
+      "grad_norm": 1.699881672859192,
+      "learning_rate": 8.444639718804921e-05,
+      "loss": 0.8303092122077942,
+      "step": 962
+    },
+    {
+      "epoch": 0.40675105485232066,
+      "grad_norm": 1.591515064239502,
+      "learning_rate": 8.462214411247804e-05,
+      "loss": 0.9029796719551086,
+      "step": 964
+    },
+    {
+      "epoch": 0.40759493670886077,
+      "grad_norm": 1.5930429697036743,
+      "learning_rate": 8.479789103690686e-05,
+      "loss": 0.8165359497070312,
+      "step": 966
+    },
+    {
+      "epoch": 0.4084388185654008,
+      "grad_norm": 1.509774923324585,
+      "learning_rate": 8.497363796133568e-05,
+      "loss": 0.8276026248931885,
+      "step": 968
+    },
+    {
+      "epoch": 0.4092827004219409,
+      "grad_norm": 1.3617016077041626,
+      "learning_rate": 8.51493848857645e-05,
+      "loss": 0.8159419894218445,
+      "step": 970
+    },
+    {
+      "epoch": 0.41012658227848103,
+      "grad_norm": 1.3580708503723145,
+      "learning_rate": 8.532513181019332e-05,
+      "loss": 0.7882336378097534,
+      "step": 972
+    },
+    {
+      "epoch": 0.4109704641350211,
+      "grad_norm": 1.3337358236312866,
+      "learning_rate": 8.550087873462214e-05,
+      "loss": 0.7462319731712341,
+      "step": 974
+    },
+    {
+      "epoch": 0.4118143459915612,
+      "grad_norm": 1.450363278388977,
+      "learning_rate": 8.567662565905097e-05,
+      "loss": 0.7500866651535034,
+      "step": 976
+    },
+    {
+      "epoch": 0.41265822784810124,
+      "grad_norm": 1.5305321216583252,
+      "learning_rate": 8.585237258347979e-05,
+      "loss": 0.8432503342628479,
+      "step": 978
+    },
+    {
+      "epoch": 0.41350210970464135,
+      "grad_norm": 1.2097326517105103,
+      "learning_rate": 8.602811950790861e-05,
+      "loss": 0.8330482840538025,
+      "step": 980
+    },
+    {
+      "epoch": 0.41434599156118146,
+      "grad_norm": 1.3916101455688477,
+      "learning_rate": 8.620386643233744e-05,
+      "loss": 0.8137149810791016,
+      "step": 982
+    },
+    {
+      "epoch": 0.4151898734177215,
+      "grad_norm": 1.6411453485488892,
+      "learning_rate": 8.637961335676626e-05,
+      "loss": 0.8273854851722717,
+      "step": 984
+    },
+    {
+      "epoch": 0.4160337552742616,
+      "grad_norm": 1.6734566688537598,
+      "learning_rate": 8.655536028119508e-05,
+      "loss": 0.794026255607605,
+      "step": 986
+    },
+    {
+      "epoch": 0.41687763713080167,
+      "grad_norm": 1.352325677871704,
+      "learning_rate": 8.67311072056239e-05,
+      "loss": 0.7721655368804932,
+      "step": 988
+    },
+    {
+      "epoch": 0.4177215189873418,
+      "grad_norm": 1.5368729829788208,
+      "learning_rate": 8.690685413005273e-05,
+      "loss": 0.8123438954353333,
+      "step": 990
+    },
+    {
+      "epoch": 0.41856540084388183,
+      "grad_norm": 1.4903568029403687,
+      "learning_rate": 8.708260105448155e-05,
+      "loss": 0.8370974659919739,
+      "step": 992
+    },
+    {
+      "epoch": 0.41940928270042194,
+      "grad_norm": 1.3405622243881226,
+      "learning_rate": 8.725834797891037e-05,
+      "loss": 0.780426561832428,
+      "step": 994
+    },
+    {
+      "epoch": 0.42025316455696204,
+      "grad_norm": 1.4761021137237549,
+      "learning_rate": 8.743409490333919e-05,
+      "loss": 0.8304934501647949,
+      "step": 996
+    },
+    {
+      "epoch": 0.4210970464135021,
+      "grad_norm": 1.520033359527588,
+      "learning_rate": 8.760984182776801e-05,
+      "loss": 0.7960568070411682,
+      "step": 998
+    },
+    {
+      "epoch": 0.4219409282700422,
+      "grad_norm": 1.6916255950927734,
+      "learning_rate": 8.778558875219684e-05,
+      "loss": 0.7884663939476013,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4219409282700422,
+      "eval_loss": 0.8388314247131348,
+      "eval_runtime": 847.4828,
+      "eval_samples_per_second": 2.486,
+      "eval_steps_per_second": 2.486,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 14220,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.001
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0390224045010268e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

sft_devstral_24B_v2/checkpoints/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e09df88fe57630482e911c5fab6026e3d20e4f37f6e48706f3566768f533d6d7
+size 4792

sft_devstral_24B_v2/checkpoints/checkpoint-1500/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Models/Devstral-Small-2-24B-HS-CPT
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Models/Devstral-Small-2-24B-HS-CPT
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

sft_devstral_24B_v2/checkpoints/checkpoint-1500/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Models/Devstral-Small-2-24B-HS-CPT",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

sft_devstral_24B_v2/checkpoints/checkpoint-1500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:831a7d926d7f5df3964543a446004381a22b97659f1e9acb7da164b4155aa7db
+size 45690960

sft_devstral_24B_v2/checkpoints/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:633ffc9a088e0005164ac58cc14f8eea176fdd2e4b9ebdd504fdddd3accc0a3d
+size 78912442

sft_devstral_24B_v2/checkpoints/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a1ae23f994928215671a68d719c37e5eb1f321bb43710f6a94f783d81024ee9
+size 14244

sft_devstral_24B_v2/checkpoints/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e0ab851b74630ec51d2dd1e28429156fa119043bf6e4acb868afec1778a8d36
+size 1064

sft_devstral_24B_v2/checkpoints/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e09df88fe57630482e911c5fab6026e3d20e4f37f6e48706f3566768f533d6d7
+size 4792

sft_devstral_24B_v2/checkpoints/checkpoint-2000/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Models/Devstral-Small-2-24B-HS-CPT
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Models/Devstral-Small-2-24B-HS-CPT
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

sft_devstral_24B_v2/checkpoints/checkpoint-2000/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Models/Devstral-Small-2-24B-HS-CPT",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

sft_devstral_24B_v2/checkpoints/checkpoint-2000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddae9fb556b6dafd5e51ffbdf7776618b5a2438b53191f850d3c060e448f3161
+size 45690960

sft_devstral_24B_v2/checkpoints/checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b78804d00938d938b90a599b8b0d8dcd8f09e8116b29fd8a7b96100a5696f346
+size 78912442

sft_devstral_24B_v2/checkpoints/checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f05d71d3ab99767003aa382d142674f4d194421936f48f312a57e6f262a24b51
+size 14244

sft_devstral_24B_v2/checkpoints/checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c4e41c084848d0f3091226abc7db74bacb76a784828650f35ffabc473a2c375
+size 1064

sft_devstral_24B_v2/checkpoints/checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e09df88fe57630482e911c5fab6026e3d20e4f37f6e48706f3566768f533d6d7
+size 4792

sft_devstral_24B_v2/checkpoints/checkpoint-2500/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Models/Devstral-Small-2-24B-HS-CPT
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Models/Devstral-Small-2-24B-HS-CPT
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

sft_devstral_24B_v2/checkpoints/checkpoint-2500/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Models/Devstral-Small-2-24B-HS-CPT",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

sft_devstral_24B_v2/checkpoints/checkpoint-2500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12ceefd222d6928d2451717456e57f756d9bff479938fd49324891727c39637e
+size 45690960

sft_devstral_24B_v2/checkpoints/checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:938980f0edbd2046c344e1b26fe96147ee0bfebc7f3495443c62b27002ce70c4
+size 78912442

sft_devstral_24B_v2/checkpoints/checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39b0d665c25c7b02a656e5cf197220cfb689931bbb6d4ae22b61d327d830a916
+size 14244

sft_devstral_24B_v2/checkpoints/checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4849064f0d6ca593dabdc277f5c88ce471853e22cd7c8abff162abca0907f0fc
+size 1064

sft_devstral_24B_v2/checkpoints/checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e09df88fe57630482e911c5fab6026e3d20e4f37f6e48706f3566768f533d6d7
+size 4792

sft_devstral_24B_v2/checkpoints/checkpoint-3000/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Models/Devstral-Small-2-24B-HS-CPT
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Models/Devstral-Small-2-24B-HS-CPT
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

sft_devstral_24B_v2/checkpoints/checkpoint-3000/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Models/Devstral-Small-2-24B-HS-CPT",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

sft_devstral_24B_v2/checkpoints/checkpoint-3000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:572c1222d21c879d07f6653cb4605da12a85133cc0188c2b00b2221aaa62cfbe
+size 45690960

sft_devstral_24B_v2/checkpoints/checkpoint-3000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d13c8293c1238c70e3998e56118b6e7dd7fa6bdfcb679007496a08a03d0b3023
+size 78912442

sft_devstral_24B_v2/checkpoints/checkpoint-3000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60683ad220666ae109ec67d53325ffb9c9c5fcc7a868f2ef15b68e9723037766
+size 14244

sft_devstral_24B_v2/checkpoints/checkpoint-3000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:387a3533fe4e8e1eeba51f1150cceef09f54bd06750ea51420287466c7ba0384
+size 1064

sft_devstral_24B_v2/checkpoints/checkpoint-3000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e09df88fe57630482e911c5fab6026e3d20e4f37f6e48706f3566768f533d6d7
+size 4792

sft_devstral_24B_v2/checkpoints/checkpoint-3500/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Models/Devstral-Small-2-24B-HS-CPT
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Models/Devstral-Small-2-24B-HS-CPT
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

sft_devstral_24B_v2/checkpoints/checkpoint-3500/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Models/Devstral-Small-2-24B-HS-CPT",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

sft_devstral_24B_v2/checkpoints/checkpoint-3500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:957eb2d5d1ffe73b7a84d0fb076e12576f526034973b97039ee4c03976bffe01
+size 45690960

sft_devstral_24B_v2/checkpoints/checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1ba7e825bf8869398fcbd6f238d668c2d90eab33e298c3ae735600ed11395f
+size 78912442

sft_devstral_24B_v2/checkpoints/checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0f916096e49dbb7a03cf13b3f0a9c0dd359b939f3fc1e94d65073bd53e57e12
+size 14244