Add Devstral-24B SFT training run

.gitattributes

@@ -48,3 +48,10 @@ cpt_devstral_24B/checkpoints/checkpoint-400/tokenizer.json filter=lfs diff=lfs m
 cpt_devstral_24B/checkpoints/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 cpt_devstral_24B/checkpoints/checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 cpt_devstral_24B/checkpoints/checkpoint-686/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+sft_devstral_24B/wandb/offline-run-20251223_133437-tqihmbvy/run-tqihmbvy.wandb filter=lfs diff=lfs merge=lfs -text
+sft_devstral_24B/wandb/offline-run-20251223_133750-62isnb1e/run-62isnb1e.wandb filter=lfs diff=lfs merge=lfs -text
+sft_devstral_24B/wandb/offline-run-20251223_134033-mifdnkpc/run-mifdnkpc.wandb filter=lfs diff=lfs merge=lfs -text
+sft_devstral_24B/wandb/offline-run-20251223_134236-sicxj35d/run-sicxj35d.wandb filter=lfs diff=lfs merge=lfs -text
+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/best_adapter/README.md

@@ -0,0 +1,207 @@
+---
+base_model: CPT/runs/cpt_run_v1/merged_24b_cpt_lora
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:CPT/runs/cpt_run_v1/merged_24b_cpt_lora
+- 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/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": "CPT/runs/cpt_run_v1/merged_24b_cpt_lora",
+  "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",
+    "k_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

sft_devstral_24B/best_adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2525c1928ca9de033f220a5e840c681a9d5f8ed45f23f11db8475248b70b962f
+size 45690960

sft_devstral_24B/best_adapter/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67cec3db40d9b4bcc81f7a80aeef5218639d2e42b1c9e2f551945abddeb1ff4d
+size 5201

sft_devstral_24B/checkpoints/checkpoint-1000/README.md

@@ -0,0 +1,207 @@
+---
+base_model: CPT/runs/cpt_run_v1/merged_24b_cpt_lora
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:CPT/runs/cpt_run_v1/merged_24b_cpt_lora
+- 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/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": "CPT/runs/cpt_run_v1/merged_24b_cpt_lora",
+  "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",
+    "k_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

sft_devstral_24B/checkpoints/checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea4c757c4c0f3bbeeaf2adc988ec942be6365d6898b69b63df419440670b6de8
+size 45690960

sft_devstral_24B/checkpoints/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3c4d1c020b9578461ce598133e846fa5f23fb37515ccdc96eadc37880ce8b65
+size 78912907

sft_devstral_24B/checkpoints/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9117a0d2e77a257b35af0540b2152c9ac110688113b9e80bfcff71a2f4afd0c
+size 14645

sft_devstral_24B/checkpoints/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d143e54fa61abf54a1448fc63239d34fad8fd9690881106ffe349bfaf2479434
+size 1465

sft_devstral_24B/checkpoints/checkpoint-1000/trainer_state.json

@@ -0,0 +1,3623 @@
+{
+  "best_global_step": 1000,
+  "best_metric": 0.8266019821166992,
+  "best_model_checkpoint": "runs/instruct_run_24b/checkpoints/checkpoint-1000",
+  "epoch": 0.43149946062567424,
+  "eval_steps": 100,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008629989212513484,
+      "grad_norm": 1.9118273258209229,
+      "learning_rate": 8.984725965858042e-08,
+      "loss": 1.398809790611267,
+      "step": 2
+    },
+    {
+      "epoch": 0.001725997842502697,
+      "grad_norm": 1.785147786140442,
+      "learning_rate": 2.6954177897574125e-07,
+      "loss": 1.3699476718902588,
+      "step": 4
+    },
+    {
+      "epoch": 0.0025889967637540453,
+      "grad_norm": 1.6857414245605469,
+      "learning_rate": 4.492362982929021e-07,
+      "loss": 1.4487650394439697,
+      "step": 6
+    },
+    {
+      "epoch": 0.003451995685005394,
+      "grad_norm": 1.7351312637329102,
+      "learning_rate": 6.28930817610063e-07,
+      "loss": 1.3360817432403564,
+      "step": 8
+    },
+    {
+      "epoch": 0.004314994606256742,
+      "grad_norm": 1.7769269943237305,
+      "learning_rate": 8.086253369272238e-07,
+      "loss": 1.4294791221618652,
+      "step": 10
+    },
+    {
+      "epoch": 0.005177993527508091,
+      "grad_norm": 1.776668906211853,
+      "learning_rate": 9.883198562443846e-07,
+      "loss": 1.3927934169769287,
+      "step": 12
+    },
+    {
+      "epoch": 0.006040992448759439,
+      "grad_norm": 1.500367283821106,
+      "learning_rate": 1.1680143755615454e-06,
+      "loss": 1.4140764474868774,
+      "step": 14
+    },
+    {
+      "epoch": 0.006903991370010788,
+      "grad_norm": 1.7255949974060059,
+      "learning_rate": 1.3477088948787064e-06,
+      "loss": 1.3873623609542847,
+      "step": 16
+    },
+    {
+      "epoch": 0.007766990291262136,
+      "grad_norm": 1.9073798656463623,
+      "learning_rate": 1.5274034141958671e-06,
+      "loss": 1.4562759399414062,
+      "step": 18
+    },
+    {
+      "epoch": 0.008629989212513484,
+      "grad_norm": 1.7253859043121338,
+      "learning_rate": 1.707097933513028e-06,
+      "loss": 1.4264800548553467,
+      "step": 20
+    },
+    {
+      "epoch": 0.009492988133764833,
+      "grad_norm": 1.4858287572860718,
+      "learning_rate": 1.8867924528301887e-06,
+      "loss": 1.3717138767242432,
+      "step": 22
+    },
+    {
+      "epoch": 0.010355987055016181,
+      "grad_norm": 1.7516961097717285,
+      "learning_rate": 2.0664869721473496e-06,
+      "loss": 1.3605879545211792,
+      "step": 24
+    },
+    {
+      "epoch": 0.01121898597626753,
+      "grad_norm": 1.754793643951416,
+      "learning_rate": 2.2461814914645104e-06,
+      "loss": 1.465327262878418,
+      "step": 26
+    },
+    {
+      "epoch": 0.012081984897518877,
+      "grad_norm": 1.5204869508743286,
+      "learning_rate": 2.425876010781671e-06,
+      "loss": 1.3205785751342773,
+      "step": 28
+    },
+    {
+      "epoch": 0.012944983818770227,
+      "grad_norm": 2.03002667427063,
+      "learning_rate": 2.605570530098832e-06,
+      "loss": 1.4751381874084473,
+      "step": 30
+    },
+    {
+      "epoch": 0.013807982740021575,
+      "grad_norm": 1.6153842210769653,
+      "learning_rate": 2.785265049415993e-06,
+      "loss": 1.3976212739944458,
+      "step": 32
+    },
+    {
+      "epoch": 0.014670981661272923,
+      "grad_norm": 1.7034062147140503,
+      "learning_rate": 2.964959568733154e-06,
+      "loss": 1.4062179327011108,
+      "step": 34
+    },
+    {
+      "epoch": 0.015533980582524271,
+      "grad_norm": 1.5724587440490723,
+      "learning_rate": 3.1446540880503146e-06,
+      "loss": 1.2940696477890015,
+      "step": 36
+    },
+    {
+      "epoch": 0.01639697950377562,
+      "grad_norm": 1.7072066068649292,
+      "learning_rate": 3.324348607367475e-06,
+      "loss": 1.4216598272323608,
+      "step": 38
+    },
+    {
+      "epoch": 0.017259978425026967,
+      "grad_norm": 1.6051130294799805,
+      "learning_rate": 3.504043126684636e-06,
+      "loss": 1.4204131364822388,
+      "step": 40
+    },
+    {
+      "epoch": 0.018122977346278317,
+      "grad_norm": 1.5114386081695557,
+      "learning_rate": 3.683737646001797e-06,
+      "loss": 1.3492953777313232,
+      "step": 42
+    },
+    {
+      "epoch": 0.018985976267529667,
+      "grad_norm": 1.5557284355163574,
+      "learning_rate": 3.863432165318958e-06,
+      "loss": 1.4241598844528198,
+      "step": 44
+    },
+    {
+      "epoch": 0.019848975188781013,
+      "grad_norm": 1.5814268589019775,
+      "learning_rate": 4.0431266846361185e-06,
+      "loss": 1.3903125524520874,
+      "step": 46
+    },
+    {
+      "epoch": 0.020711974110032363,
+      "grad_norm": 1.53256356716156,
+      "learning_rate": 4.22282120395328e-06,
+      "loss": 1.3726638555526733,
+      "step": 48
+    },
+    {
+      "epoch": 0.021574973031283712,
+      "grad_norm": 1.5670084953308105,
+      "learning_rate": 4.40251572327044e-06,
+      "loss": 1.2536468505859375,
+      "step": 50
+    },
+    {
+      "epoch": 0.02243797195253506,
+      "grad_norm": 1.3708246946334839,
+      "learning_rate": 4.582210242587602e-06,
+      "loss": 1.2309948205947876,
+      "step": 52
+    },
+    {
+      "epoch": 0.02330097087378641,
+      "grad_norm": 1.5670109987258911,
+      "learning_rate": 4.7619047619047615e-06,
+      "loss": 1.3564441204071045,
+      "step": 54
+    },
+    {
+      "epoch": 0.024163969795037755,
+      "grad_norm": 1.3550655841827393,
+      "learning_rate": 4.941599281221923e-06,
+      "loss": 1.2251620292663574,
+      "step": 56
+    },
+    {
+      "epoch": 0.025026968716289105,
+      "grad_norm": 1.4416121244430542,
+      "learning_rate": 5.121293800539084e-06,
+      "loss": 1.2395249605178833,
+      "step": 58
+    },
+    {
+      "epoch": 0.025889967637540454,
+      "grad_norm": 1.4638670682907104,
+      "learning_rate": 5.300988319856245e-06,
+      "loss": 1.3229656219482422,
+      "step": 60
+    },
+    {
+      "epoch": 0.0267529665587918,
+      "grad_norm": 1.2204002141952515,
+      "learning_rate": 5.4806828391734054e-06,
+      "loss": 1.1076340675354004,
+      "step": 62
+    },
+    {
+      "epoch": 0.02761596548004315,
+      "grad_norm": 1.2641915082931519,
+      "learning_rate": 5.660377358490566e-06,
+      "loss": 1.237392544746399,
+      "step": 64
+    },
+    {
+      "epoch": 0.0284789644012945,
+      "grad_norm": 1.4635342359542847,
+      "learning_rate": 5.840071877807727e-06,
+      "loss": 1.3567079305648804,
+      "step": 66
+    },
+    {
+      "epoch": 0.029341963322545846,
+      "grad_norm": 1.5813465118408203,
+      "learning_rate": 6.019766397124888e-06,
+      "loss": 1.3595421314239502,
+      "step": 68
+    },
+    {
+      "epoch": 0.030204962243797196,
+      "grad_norm": 1.435356616973877,
+      "learning_rate": 6.1994609164420485e-06,
+      "loss": 1.2183864116668701,
+      "step": 70
+    },
+    {
+      "epoch": 0.031067961165048542,
+      "grad_norm": 1.4559556245803833,
+      "learning_rate": 6.37915543575921e-06,
+      "loss": 1.2084243297576904,
+      "step": 72
+    },
+    {
+      "epoch": 0.03193096008629989,
+      "grad_norm": 1.2870471477508545,
+      "learning_rate": 6.558849955076371e-06,
+      "loss": 1.2476426362991333,
+      "step": 74
+    },
+    {
+      "epoch": 0.03279395900755124,
+      "grad_norm": 1.3345798254013062,
+      "learning_rate": 6.738544474393531e-06,
+      "loss": 1.2200642824172974,
+      "step": 76
+    },
+    {
+      "epoch": 0.03365695792880259,
+      "grad_norm": 1.48223876953125,
+      "learning_rate": 6.918238993710692e-06,
+      "loss": 1.2497955560684204,
+      "step": 78
+    },
+    {
+      "epoch": 0.034519956850053934,
+      "grad_norm": 1.2421257495880127,
+      "learning_rate": 7.097933513027853e-06,
+      "loss": 1.1987318992614746,
+      "step": 80
+    },
+    {
+      "epoch": 0.035382955771305284,
+      "grad_norm": 1.5042678117752075,
+      "learning_rate": 7.277628032345015e-06,
+      "loss": 1.218438982963562,
+      "step": 82
+    },
+    {
+      "epoch": 0.036245954692556634,
+      "grad_norm": 1.3047534227371216,
+      "learning_rate": 7.457322551662174e-06,
+      "loss": 1.1181117296218872,
+      "step": 84
+    },
+    {
+      "epoch": 0.037108953613807984,
+      "grad_norm": 1.3297117948532104,
+      "learning_rate": 7.637017070979335e-06,
+      "loss": 1.047302484512329,
+      "step": 86
+    },
+    {
+      "epoch": 0.03797195253505933,
+      "grad_norm": 1.4515916109085083,
+      "learning_rate": 7.816711590296496e-06,
+      "loss": 1.1821871995925903,
+      "step": 88
+    },
+    {
+      "epoch": 0.038834951456310676,
+      "grad_norm": 1.5435426235198975,
+      "learning_rate": 7.996406109613658e-06,
+      "loss": 1.1171189546585083,
+      "step": 90
+    },
+    {
+      "epoch": 0.039697950377562026,
+      "grad_norm": 1.5270947217941284,
+      "learning_rate": 8.176100628930818e-06,
+      "loss": 1.067047357559204,
+      "step": 92
+    },
+    {
+      "epoch": 0.040560949298813376,
+      "grad_norm": 2.4402992725372314,
+      "learning_rate": 8.35579514824798e-06,
+      "loss": 1.0745081901550293,
+      "step": 94
+    },
+    {
+      "epoch": 0.041423948220064725,
+      "grad_norm": 1.7703081369400024,
+      "learning_rate": 8.53548966756514e-06,
+      "loss": 1.252164602279663,
+      "step": 96
+    },
+    {
+      "epoch": 0.042286947141316075,
+      "grad_norm": 1.4324337244033813,
+      "learning_rate": 8.715184186882301e-06,
+      "loss": 1.1030420064926147,
+      "step": 98
+    },
+    {
+      "epoch": 0.043149946062567425,
+      "grad_norm": 1.3258590698242188,
+      "learning_rate": 8.89487870619946e-06,
+      "loss": 1.0817893743515015,
+      "step": 100
+    },
+    {
+      "epoch": 0.043149946062567425,
+      "eval_loss": 1.128923773765564,
+      "eval_runtime": 825.0166,
+      "eval_samples_per_second": 2.497,
+      "eval_steps_per_second": 2.497,
+      "step": 100
+    },
+    {
+      "epoch": 0.04401294498381877,
+      "grad_norm": 1.5833592414855957,
+      "learning_rate": 9.074573225516622e-06,
+      "loss": 1.0982940196990967,
+      "step": 102
+    },
+    {
+      "epoch": 0.04487594390507012,
+      "grad_norm": 1.5289201736450195,
+      "learning_rate": 9.254267744833784e-06,
+      "loss": 1.0529299974441528,
+      "step": 104
+    },
+    {
+      "epoch": 0.04573894282632147,
+      "grad_norm": 1.4507837295532227,
+      "learning_rate": 9.433962264150944e-06,
+      "loss": 1.0896434783935547,
+      "step": 106
+    },
+    {
+      "epoch": 0.04660194174757282,
+      "grad_norm": 1.3846485614776611,
+      "learning_rate": 9.613656783468104e-06,
+      "loss": 1.1196398735046387,
+      "step": 108
+    },
+    {
+      "epoch": 0.04746494066882417,
+      "grad_norm": 1.4094940423965454,
+      "learning_rate": 9.793351302785265e-06,
+      "loss": 1.1305382251739502,
+      "step": 110
+    },
+    {
+      "epoch": 0.04832793959007551,
+      "grad_norm": 1.7674189805984497,
+      "learning_rate": 9.973045822102427e-06,
+      "loss": 1.0138700008392334,
+      "step": 112
+    },
+    {
+      "epoch": 0.04919093851132686,
+      "grad_norm": 1.6083961725234985,
+      "learning_rate": 1.0152740341419587e-05,
+      "loss": 1.0583173036575317,
+      "step": 114
+    },
+    {
+      "epoch": 0.05005393743257821,
+      "grad_norm": 1.7483229637145996,
+      "learning_rate": 1.0332434860736747e-05,
+      "loss": 1.1116671562194824,
+      "step": 116
+    },
+    {
+      "epoch": 0.05091693635382956,
+      "grad_norm": 1.8256834745407104,
+      "learning_rate": 1.0512129380053909e-05,
+      "loss": 1.0832366943359375,
+      "step": 118
+    },
+    {
+      "epoch": 0.05177993527508091,
+      "grad_norm": 1.5875557661056519,
+      "learning_rate": 1.069182389937107e-05,
+      "loss": 1.1089236736297607,
+      "step": 120
+    },
+    {
+      "epoch": 0.05264293419633225,
+      "grad_norm": 1.6553549766540527,
+      "learning_rate": 1.087151841868823e-05,
+      "loss": 1.1191619634628296,
+      "step": 122
+    },
+    {
+      "epoch": 0.0535059331175836,
+      "grad_norm": 1.3675798177719116,
+      "learning_rate": 1.1051212938005392e-05,
+      "loss": 1.031973958015442,
+      "step": 124
+    },
+    {
+      "epoch": 0.05436893203883495,
+      "grad_norm": 1.5343760251998901,
+      "learning_rate": 1.1230907457322552e-05,
+      "loss": 0.9964010119438171,
+      "step": 126
+    },
+    {
+      "epoch": 0.0552319309600863,
+      "grad_norm": 1.5928982496261597,
+      "learning_rate": 1.1410601976639713e-05,
+      "loss": 1.1144609451293945,
+      "step": 128
+    },
+    {
+      "epoch": 0.05609492988133765,
+      "grad_norm": 1.6411585807800293,
+      "learning_rate": 1.1590296495956873e-05,
+      "loss": 0.9953935146331787,
+      "step": 130
+    },
+    {
+      "epoch": 0.056957928802589,
+      "grad_norm": 1.6077220439910889,
+      "learning_rate": 1.1769991015274035e-05,
+      "loss": 0.9940203428268433,
+      "step": 132
+    },
+    {
+      "epoch": 0.05782092772384034,
+      "grad_norm": 1.7327438592910767,
+      "learning_rate": 1.1949685534591196e-05,
+      "loss": 1.045546293258667,
+      "step": 134
+    },
+    {
+      "epoch": 0.05868392664509169,
+      "grad_norm": 1.607404112815857,
+      "learning_rate": 1.2129380053908356e-05,
+      "loss": 0.9932523369789124,
+      "step": 136
+    },
+    {
+      "epoch": 0.05954692556634304,
+      "grad_norm": 1.5056802034378052,
+      "learning_rate": 1.2309074573225516e-05,
+      "loss": 0.9584172368049622,
+      "step": 138
+    },
+    {
+      "epoch": 0.06040992448759439,
+      "grad_norm": 1.5453966856002808,
+      "learning_rate": 1.2488769092542678e-05,
+      "loss": 0.9733421206474304,
+      "step": 140
+    },
+    {
+      "epoch": 0.06127292340884574,
+      "grad_norm": 1.546397089958191,
+      "learning_rate": 1.2668463611859838e-05,
+      "loss": 0.9971115589141846,
+      "step": 142
+    },
+    {
+      "epoch": 0.062135922330097085,
+      "grad_norm": 1.5259592533111572,
+      "learning_rate": 1.2848158131177e-05,
+      "loss": 1.0994833707809448,
+      "step": 144
+    },
+    {
+      "epoch": 0.06299892125134844,
+      "grad_norm": 1.56397545337677,
+      "learning_rate": 1.302785265049416e-05,
+      "loss": 1.0203801393508911,
+      "step": 146
+    },
+    {
+      "epoch": 0.06386192017259978,
+      "grad_norm": 1.618053674697876,
+      "learning_rate": 1.320754716981132e-05,
+      "loss": 1.0223872661590576,
+      "step": 148
+    },
+    {
+      "epoch": 0.06472491909385113,
+      "grad_norm": 1.9544042348861694,
+      "learning_rate": 1.3387241689128482e-05,
+      "loss": 1.0207403898239136,
+      "step": 150
+    },
+    {
+      "epoch": 0.06558791801510248,
+      "grad_norm": 1.7001299858093262,
+      "learning_rate": 1.3566936208445644e-05,
+      "loss": 1.025482177734375,
+      "step": 152
+    },
+    {
+      "epoch": 0.06645091693635383,
+      "grad_norm": 1.9833810329437256,
+      "learning_rate": 1.3746630727762804e-05,
+      "loss": 1.0077980756759644,
+      "step": 154
+    },
+    {
+      "epoch": 0.06731391585760518,
+      "grad_norm": 1.6378769874572754,
+      "learning_rate": 1.3926325247079966e-05,
+      "loss": 1.0046619176864624,
+      "step": 156
+    },
+    {
+      "epoch": 0.06817691477885653,
+      "grad_norm": 1.762683629989624,
+      "learning_rate": 1.4106019766397124e-05,
+      "loss": 1.0332108736038208,
+      "step": 158
+    },
+    {
+      "epoch": 0.06903991370010787,
+      "grad_norm": 1.5698739290237427,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.973042905330658,
+      "step": 160
+    },
+    {
+      "epoch": 0.06990291262135923,
+      "grad_norm": 1.6132292747497559,
+      "learning_rate": 1.4465408805031447e-05,
+      "loss": 0.9966566562652588,
+      "step": 162
+    },
+    {
+      "epoch": 0.07076591154261057,
+      "grad_norm": 1.989534616470337,
+      "learning_rate": 1.4645103324348609e-05,
+      "loss": 1.078708529472351,
+      "step": 164
+    },
+    {
+      "epoch": 0.07162891046386193,
+      "grad_norm": 1.8199284076690674,
+      "learning_rate": 1.4824797843665769e-05,
+      "loss": 0.9075545072555542,
+      "step": 166
+    },
+    {
+      "epoch": 0.07249190938511327,
+      "grad_norm": 1.6908831596374512,
+      "learning_rate": 1.500449236298293e-05,
+      "loss": 0.9268680810928345,
+      "step": 168
+    },
+    {
+      "epoch": 0.07335490830636461,
+      "grad_norm": 1.5648242235183716,
+      "learning_rate": 1.5184186882300092e-05,
+      "loss": 1.0361101627349854,
+      "step": 170
+    },
+    {
+      "epoch": 0.07421790722761597,
+      "grad_norm": 1.8292360305786133,
+      "learning_rate": 1.5363881401617252e-05,
+      "loss": 0.9197717905044556,
+      "step": 172
+    },
+    {
+      "epoch": 0.07508090614886731,
+      "grad_norm": 1.6882517337799072,
+      "learning_rate": 1.554357592093441e-05,
+      "loss": 0.9661652445793152,
+      "step": 174
+    },
+    {
+      "epoch": 0.07594390507011867,
+      "grad_norm": 1.695921778678894,
+      "learning_rate": 1.572327044025157e-05,
+      "loss": 1.0006932020187378,
+      "step": 176
+    },
+    {
+      "epoch": 0.07680690399137001,
+      "grad_norm": 2.0128681659698486,
+      "learning_rate": 1.5902964959568733e-05,
+      "loss": 1.0096064805984497,
+      "step": 178
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "grad_norm": 1.6833231449127197,
+      "learning_rate": 1.6082659478885895e-05,
+      "loss": 0.972679853439331,
+      "step": 180
+    },
+    {
+      "epoch": 0.07853290183387271,
+      "grad_norm": 1.6940670013427734,
+      "learning_rate": 1.6262353998203056e-05,
+      "loss": 0.9232968091964722,
+      "step": 182
+    },
+    {
+      "epoch": 0.07939590075512405,
+      "grad_norm": 2.0851218700408936,
+      "learning_rate": 1.6442048517520218e-05,
+      "loss": 0.981245219707489,
+      "step": 184
+    },
+    {
+      "epoch": 0.08025889967637541,
+      "grad_norm": 1.3769028186798096,
+      "learning_rate": 1.662174303683738e-05,
+      "loss": 0.9762678146362305,
+      "step": 186
+    },
+    {
+      "epoch": 0.08112189859762675,
+      "grad_norm": 1.85263192653656,
+      "learning_rate": 1.6801437556154538e-05,
+      "loss": 0.9905523061752319,
+      "step": 188
+    },
+    {
+      "epoch": 0.08198489751887811,
+      "grad_norm": 1.654221534729004,
+      "learning_rate": 1.69811320754717e-05,
+      "loss": 0.8457058072090149,
+      "step": 190
+    },
+    {
+      "epoch": 0.08284789644012945,
+      "grad_norm": 1.7715294361114502,
+      "learning_rate": 1.7160826594788858e-05,
+      "loss": 1.0171988010406494,
+      "step": 192
+    },
+    {
+      "epoch": 0.0837108953613808,
+      "grad_norm": 1.7162128686904907,
+      "learning_rate": 1.734052111410602e-05,
+      "loss": 0.9767695069313049,
+      "step": 194
+    },
+    {
+      "epoch": 0.08457389428263215,
+      "grad_norm": 1.7938538789749146,
+      "learning_rate": 1.752021563342318e-05,
+      "loss": 0.9786219596862793,
+      "step": 196
+    },
+    {
+      "epoch": 0.0854368932038835,
+      "grad_norm": 1.944226861000061,
+      "learning_rate": 1.7699910152740342e-05,
+      "loss": 0.9941093921661377,
+      "step": 198
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "grad_norm": 1.816835880279541,
+      "learning_rate": 1.7879604672057504e-05,
+      "loss": 0.8924376964569092,
+      "step": 200
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "eval_loss": 0.981117308139801,
+      "eval_runtime": 826.4469,
+      "eval_samples_per_second": 2.493,
+      "eval_steps_per_second": 2.493,
+      "step": 200
+    },
+    {
+      "epoch": 0.08716289104638619,
+      "grad_norm": 1.8230189085006714,
+      "learning_rate": 1.8059299191374666e-05,
+      "loss": 0.9908216595649719,
+      "step": 202
+    },
+    {
+      "epoch": 0.08802588996763754,
+      "grad_norm": 1.8223077058792114,
+      "learning_rate": 1.8238993710691824e-05,
+      "loss": 0.9657744765281677,
+      "step": 204
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 1.811195731163025,
+      "learning_rate": 1.8418688230008986e-05,
+      "loss": 0.9397313594818115,
+      "step": 206
+    },
+    {
+      "epoch": 0.08975188781014024,
+      "grad_norm": 1.579998254776001,
+      "learning_rate": 1.8598382749326147e-05,
+      "loss": 0.8770087361335754,
+      "step": 208
+    },
+    {
+      "epoch": 0.09061488673139159,
+      "grad_norm": 1.592136263847351,
+      "learning_rate": 1.8778077268643305e-05,
+      "loss": 0.922799825668335,
+      "step": 210
+    },
+    {
+      "epoch": 0.09147788565264293,
+      "grad_norm": 1.9334869384765625,
+      "learning_rate": 1.8957771787960467e-05,
+      "loss": 0.9007947444915771,
+      "step": 212
+    },
+    {
+      "epoch": 0.09234088457389428,
+      "grad_norm": 1.8619475364685059,
+      "learning_rate": 1.913746630727763e-05,
+      "loss": 0.9261049628257751,
+      "step": 214
+    },
+    {
+      "epoch": 0.09320388349514563,
+      "grad_norm": 1.751584529876709,
+      "learning_rate": 1.931716082659479e-05,
+      "loss": 0.9319002628326416,
+      "step": 216
+    },
+    {
+      "epoch": 0.09406688241639698,
+      "grad_norm": 2.1829185485839844,
+      "learning_rate": 1.9496855345911952e-05,
+      "loss": 0.947629451751709,
+      "step": 218
+    },
+    {
+      "epoch": 0.09492988133764833,
+      "grad_norm": 1.8973567485809326,
+      "learning_rate": 1.967654986522911e-05,
+      "loss": 0.9213902354240417,
+      "step": 220
+    },
+    {
+      "epoch": 0.09579288025889968,
+      "grad_norm": 1.9995585680007935,
+      "learning_rate": 1.985624438454627e-05,
+      "loss": 0.9058182835578918,
+      "step": 222
+    },
+    {
+      "epoch": 0.09665587918015102,
+      "grad_norm": 1.9369088411331177,
+      "learning_rate": 2.0035938903863433e-05,
+      "loss": 0.8918466567993164,
+      "step": 224
+    },
+    {
+      "epoch": 0.09751887810140238,
+      "grad_norm": 2.1926183700561523,
+      "learning_rate": 2.0215633423180595e-05,
+      "loss": 1.009294033050537,
+      "step": 226
+    },
+    {
+      "epoch": 0.09838187702265372,
+      "grad_norm": 1.872399926185608,
+      "learning_rate": 2.0395327942497757e-05,
+      "loss": 0.9543544054031372,
+      "step": 228
+    },
+    {
+      "epoch": 0.09924487594390508,
+      "grad_norm": 2.011009454727173,
+      "learning_rate": 2.0575022461814915e-05,
+      "loss": 0.9188834428787231,
+      "step": 230
+    },
+    {
+      "epoch": 0.10010787486515642,
+      "grad_norm": 1.8422952890396118,
+      "learning_rate": 2.0754716981132076e-05,
+      "loss": 0.84498131275177,
+      "step": 232
+    },
+    {
+      "epoch": 0.10097087378640776,
+      "grad_norm": 2.208738088607788,
+      "learning_rate": 2.0934411500449238e-05,
+      "loss": 0.9864624738693237,
+      "step": 234
+    },
+    {
+      "epoch": 0.10183387270765912,
+      "grad_norm": 1.6119916439056396,
+      "learning_rate": 2.1114106019766396e-05,
+      "loss": 0.928769588470459,
+      "step": 236
+    },
+    {
+      "epoch": 0.10269687162891046,
+      "grad_norm": 1.906336784362793,
+      "learning_rate": 2.1293800539083558e-05,
+      "loss": 0.885361909866333,
+      "step": 238
+    },
+    {
+      "epoch": 0.10355987055016182,
+      "grad_norm": 2.046064615249634,
+      "learning_rate": 2.147349505840072e-05,
+      "loss": 0.9497957229614258,
+      "step": 240
+    },
+    {
+      "epoch": 0.10442286947141316,
+      "grad_norm": 2.1612143516540527,
+      "learning_rate": 2.165318957771788e-05,
+      "loss": 0.958332896232605,
+      "step": 242
+    },
+    {
+      "epoch": 0.1052858683926645,
+      "grad_norm": 2.139829635620117,
+      "learning_rate": 2.1832884097035043e-05,
+      "loss": 1.0089390277862549,
+      "step": 244
+    },
+    {
+      "epoch": 0.10614886731391586,
+      "grad_norm": 1.9842045307159424,
+      "learning_rate": 2.2012578616352204e-05,
+      "loss": 0.9627355933189392,
+      "step": 246
+    },
+    {
+      "epoch": 0.1070118662351672,
+      "grad_norm": 1.968578577041626,
+      "learning_rate": 2.2192273135669366e-05,
+      "loss": 0.9260450601577759,
+      "step": 248
+    },
+    {
+      "epoch": 0.10787486515641856,
+      "grad_norm": 2.192275047302246,
+      "learning_rate": 2.2371967654986524e-05,
+      "loss": 1.0654462575912476,
+      "step": 250
+    },
+    {
+      "epoch": 0.1087378640776699,
+      "grad_norm": 2.0267577171325684,
+      "learning_rate": 2.2551662174303682e-05,
+      "loss": 0.9680672883987427,
+      "step": 252
+    },
+    {
+      "epoch": 0.10960086299892124,
+      "grad_norm": 1.9834461212158203,
+      "learning_rate": 2.2731356693620844e-05,
+      "loss": 1.0027307271957397,
+      "step": 254
+    },
+    {
+      "epoch": 0.1104638619201726,
+      "grad_norm": 2.0105156898498535,
+      "learning_rate": 2.2911051212938006e-05,
+      "loss": 1.0050861835479736,
+      "step": 256
+    },
+    {
+      "epoch": 0.11132686084142394,
+      "grad_norm": 1.9150307178497314,
+      "learning_rate": 2.3090745732255167e-05,
+      "loss": 0.8955062627792358,
+      "step": 258
+    },
+    {
+      "epoch": 0.1121898597626753,
+      "grad_norm": 2.100795269012451,
+      "learning_rate": 2.327044025157233e-05,
+      "loss": 0.941332221031189,
+      "step": 260
+    },
+    {
+      "epoch": 0.11305285868392664,
+      "grad_norm": 1.837814211845398,
+      "learning_rate": 2.345013477088949e-05,
+      "loss": 0.9292652606964111,
+      "step": 262
+    },
+    {
+      "epoch": 0.113915857605178,
+      "grad_norm": 1.9122955799102783,
+      "learning_rate": 2.3629829290206652e-05,
+      "loss": 0.9460650682449341,
+      "step": 264
+    },
+    {
+      "epoch": 0.11477885652642934,
+      "grad_norm": 1.9168611764907837,
+      "learning_rate": 2.380952380952381e-05,
+      "loss": 0.8730320334434509,
+      "step": 266
+    },
+    {
+      "epoch": 0.11564185544768069,
+      "grad_norm": 2.1184403896331787,
+      "learning_rate": 2.3989218328840972e-05,
+      "loss": 0.9194066524505615,
+      "step": 268
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "grad_norm": 1.910470962524414,
+      "learning_rate": 2.4168912848158133e-05,
+      "loss": 0.8994337320327759,
+      "step": 270
+    },
+    {
+      "epoch": 0.11736785329018339,
+      "grad_norm": 1.9906529188156128,
+      "learning_rate": 2.434860736747529e-05,
+      "loss": 0.8509554266929626,
+      "step": 272
+    },
+    {
+      "epoch": 0.11823085221143474,
+      "grad_norm": 2.5982062816619873,
+      "learning_rate": 2.4528301886792453e-05,
+      "loss": 1.0223658084869385,
+      "step": 274
+    },
+    {
+      "epoch": 0.11909385113268608,
+      "grad_norm": 1.8959418535232544,
+      "learning_rate": 2.4707996406109615e-05,
+      "loss": 0.8702670931816101,
+      "step": 276
+    },
+    {
+      "epoch": 0.11995685005393743,
+      "grad_norm": 2.115907669067383,
+      "learning_rate": 2.4887690925426776e-05,
+      "loss": 0.9471842050552368,
+      "step": 278
+    },
+    {
+      "epoch": 0.12081984897518878,
+      "grad_norm": 2.0255353450775146,
+      "learning_rate": 2.5067385444743935e-05,
+      "loss": 0.805242657661438,
+      "step": 280
+    },
+    {
+      "epoch": 0.12168284789644013,
+      "grad_norm": 1.9394105672836304,
+      "learning_rate": 2.52470799640611e-05,
+      "loss": 0.9008285999298096,
+      "step": 282
+    },
+    {
+      "epoch": 0.12254584681769148,
+      "grad_norm": 2.2017428874969482,
+      "learning_rate": 2.5426774483378258e-05,
+      "loss": 0.950639009475708,
+      "step": 284
+    },
+    {
+      "epoch": 0.12340884573894283,
+      "grad_norm": 4.048379421234131,
+      "learning_rate": 2.5606469002695423e-05,
+      "loss": 0.9673396944999695,
+      "step": 286
+    },
+    {
+      "epoch": 0.12427184466019417,
+      "grad_norm": 1.812450647354126,
+      "learning_rate": 2.578616352201258e-05,
+      "loss": 0.8251164555549622,
+      "step": 288
+    },
+    {
+      "epoch": 0.12513484358144553,
+      "grad_norm": 1.9298596382141113,
+      "learning_rate": 2.596585804132974e-05,
+      "loss": 0.9397821426391602,
+      "step": 290
+    },
+    {
+      "epoch": 0.12599784250269688,
+      "grad_norm": 2.0862202644348145,
+      "learning_rate": 2.61455525606469e-05,
+      "loss": 0.95896315574646,
+      "step": 292
+    },
+    {
+      "epoch": 0.1268608414239482,
+      "grad_norm": 2.113429307937622,
+      "learning_rate": 2.632524707996406e-05,
+      "loss": 0.9547653198242188,
+      "step": 294
+    },
+    {
+      "epoch": 0.12772384034519957,
+      "grad_norm": 2.0666873455047607,
+      "learning_rate": 2.6504941599281224e-05,
+      "loss": 0.9351654052734375,
+      "step": 296
+    },
+    {
+      "epoch": 0.12858683926645093,
+      "grad_norm": 2.0679547786712646,
+      "learning_rate": 2.6684636118598382e-05,
+      "loss": 0.9268350005149841,
+      "step": 298
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "grad_norm": 2.028594493865967,
+      "learning_rate": 2.6864330637915547e-05,
+      "loss": 0.8522316813468933,
+      "step": 300
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "eval_loss": 0.9384957551956177,
+      "eval_runtime": 835.4727,
+      "eval_samples_per_second": 2.466,
+      "eval_steps_per_second": 2.466,
+      "step": 300
+    },
+    {
+      "epoch": 0.1303128371089536,
+      "grad_norm": 2.1932919025421143,
+      "learning_rate": 2.7044025157232706e-05,
+      "loss": 0.9460103511810303,
+      "step": 302
+    },
+    {
+      "epoch": 0.13117583603020497,
+      "grad_norm": 2.275789737701416,
+      "learning_rate": 2.722371967654987e-05,
+      "loss": 0.9642201662063599,
+      "step": 304
+    },
+    {
+      "epoch": 0.13203883495145632,
+      "grad_norm": 1.9120908975601196,
+      "learning_rate": 2.740341419586703e-05,
+      "loss": 0.869883120059967,
+      "step": 306
+    },
+    {
+      "epoch": 0.13290183387270765,
+      "grad_norm": 1.9676507711410522,
+      "learning_rate": 2.7583108715184187e-05,
+      "loss": 0.8595444560050964,
+      "step": 308
+    },
+    {
+      "epoch": 0.133764832793959,
+      "grad_norm": 1.7901391983032227,
+      "learning_rate": 2.776280323450135e-05,
+      "loss": 0.8541103601455688,
+      "step": 310
+    },
+    {
+      "epoch": 0.13462783171521037,
+      "grad_norm": 2.160867691040039,
+      "learning_rate": 2.7942497753818507e-05,
+      "loss": 1.0146855115890503,
+      "step": 312
+    },
+    {
+      "epoch": 0.1354908306364617,
+      "grad_norm": 2.0809009075164795,
+      "learning_rate": 2.8122192273135672e-05,
+      "loss": 0.9228161573410034,
+      "step": 314
+    },
+    {
+      "epoch": 0.13635382955771305,
+      "grad_norm": 1.9626725912094116,
+      "learning_rate": 2.830188679245283e-05,
+      "loss": 0.8527485132217407,
+      "step": 316
+    },
+    {
+      "epoch": 0.1372168284789644,
+      "grad_norm": 1.9569967985153198,
+      "learning_rate": 2.8481581311769995e-05,
+      "loss": 0.8136687278747559,
+      "step": 318
+    },
+    {
+      "epoch": 0.13807982740021574,
+      "grad_norm": 2.301692247390747,
+      "learning_rate": 2.8661275831087153e-05,
+      "loss": 0.8999513387680054,
+      "step": 320
+    },
+    {
+      "epoch": 0.1389428263214671,
+      "grad_norm": 2.0247251987457275,
+      "learning_rate": 2.884097035040431e-05,
+      "loss": 0.9751577973365784,
+      "step": 322
+    },
+    {
+      "epoch": 0.13980582524271845,
+      "grad_norm": 2.019547462463379,
+      "learning_rate": 2.9020664869721477e-05,
+      "loss": 0.8741729259490967,
+      "step": 324
+    },
+    {
+      "epoch": 0.1406688241639698,
+      "grad_norm": 2.3503618240356445,
+      "learning_rate": 2.9200359389038635e-05,
+      "loss": 0.948066234588623,
+      "step": 326
+    },
+    {
+      "epoch": 0.14153182308522114,
+      "grad_norm": 2.544365406036377,
+      "learning_rate": 2.9380053908355796e-05,
+      "loss": 1.008673906326294,
+      "step": 328
+    },
+    {
+      "epoch": 0.1423948220064725,
+      "grad_norm": 3.1647145748138428,
+      "learning_rate": 2.9559748427672958e-05,
+      "loss": 0.9492161273956299,
+      "step": 330
+    },
+    {
+      "epoch": 0.14325782092772385,
+      "grad_norm": 2.0551259517669678,
+      "learning_rate": 2.973944294699012e-05,
+      "loss": 0.9077466130256653,
+      "step": 332
+    },
+    {
+      "epoch": 0.14412081984897518,
+      "grad_norm": 1.6792620420455933,
+      "learning_rate": 2.9919137466307278e-05,
+      "loss": 0.8839989304542542,
+      "step": 334
+    },
+    {
+      "epoch": 0.14498381877022654,
+      "grad_norm": 1.7771215438842773,
+      "learning_rate": 3.0098831985624436e-05,
+      "loss": 0.855834424495697,
+      "step": 336
+    },
+    {
+      "epoch": 0.1458468176914779,
+      "grad_norm": 2.030884027481079,
+      "learning_rate": 3.02785265049416e-05,
+      "loss": 0.8477111458778381,
+      "step": 338
+    },
+    {
+      "epoch": 0.14670981661272922,
+      "grad_norm": 2.4177005290985107,
+      "learning_rate": 3.045822102425876e-05,
+      "loss": 0.9139004945755005,
+      "step": 340
+    },
+    {
+      "epoch": 0.14757281553398058,
+      "grad_norm": 2.094775438308716,
+      "learning_rate": 3.063791554357592e-05,
+      "loss": 0.8836029767990112,
+      "step": 342
+    },
+    {
+      "epoch": 0.14843581445523193,
+      "grad_norm": 2.0046238899230957,
+      "learning_rate": 3.081761006289308e-05,
+      "loss": 0.9318807125091553,
+      "step": 344
+    },
+    {
+      "epoch": 0.1492988133764833,
+      "grad_norm": 2.40739369392395,
+      "learning_rate": 3.0997304582210244e-05,
+      "loss": 0.8916489481925964,
+      "step": 346
+    },
+    {
+      "epoch": 0.15016181229773462,
+      "grad_norm": 2.1190497875213623,
+      "learning_rate": 3.11769991015274e-05,
+      "loss": 0.90766441822052,
+      "step": 348
+    },
+    {
+      "epoch": 0.15102481121898598,
+      "grad_norm": 2.721255302429199,
+      "learning_rate": 3.135669362084457e-05,
+      "loss": 0.9210623502731323,
+      "step": 350
+    },
+    {
+      "epoch": 0.15188781014023733,
+      "grad_norm": 2.4988787174224854,
+      "learning_rate": 3.1536388140161726e-05,
+      "loss": 0.9134353399276733,
+      "step": 352
+    },
+    {
+      "epoch": 0.15275080906148866,
+      "grad_norm": 2.6075687408447266,
+      "learning_rate": 3.1716082659478884e-05,
+      "loss": 0.9127986431121826,
+      "step": 354
+    },
+    {
+      "epoch": 0.15361380798274002,
+      "grad_norm": 1.9883074760437012,
+      "learning_rate": 3.189577717879605e-05,
+      "loss": 0.8019667863845825,
+      "step": 356
+    },
+    {
+      "epoch": 0.15447680690399138,
+      "grad_norm": 2.058591365814209,
+      "learning_rate": 3.207547169811321e-05,
+      "loss": 0.8417298197746277,
+      "step": 358
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "grad_norm": 2.0510308742523193,
+      "learning_rate": 3.225516621743037e-05,
+      "loss": 0.909717321395874,
+      "step": 360
+    },
+    {
+      "epoch": 0.15620280474649406,
+      "grad_norm": 2.3204104900360107,
+      "learning_rate": 3.243486073674753e-05,
+      "loss": 0.9414666295051575,
+      "step": 362
+    },
+    {
+      "epoch": 0.15706580366774542,
+      "grad_norm": 1.9658725261688232,
+      "learning_rate": 3.2614555256064695e-05,
+      "loss": 0.8631396889686584,
+      "step": 364
+    },
+    {
+      "epoch": 0.15792880258899678,
+      "grad_norm": 2.2223057746887207,
+      "learning_rate": 3.2794249775381853e-05,
+      "loss": 0.8996705412864685,
+      "step": 366
+    },
+    {
+      "epoch": 0.1587918015102481,
+      "grad_norm": 1.9815107583999634,
+      "learning_rate": 3.297394429469901e-05,
+      "loss": 0.8185732364654541,
+      "step": 368
+    },
+    {
+      "epoch": 0.15965480043149946,
+      "grad_norm": 2.319581985473633,
+      "learning_rate": 3.315363881401618e-05,
+      "loss": 0.9952898025512695,
+      "step": 370
+    },
+    {
+      "epoch": 0.16051779935275082,
+      "grad_norm": 1.7916827201843262,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.7604310512542725,
+      "step": 372
+    },
+    {
+      "epoch": 0.16138079827400215,
+      "grad_norm": 1.955737590789795,
+      "learning_rate": 3.35130278526505e-05,
+      "loss": 0.7867834568023682,
+      "step": 374
+    },
+    {
+      "epoch": 0.1622437971952535,
+      "grad_norm": 2.409783124923706,
+      "learning_rate": 3.369272237196766e-05,
+      "loss": 0.9106539487838745,
+      "step": 376
+    },
+    {
+      "epoch": 0.16310679611650486,
+      "grad_norm": 2.2521097660064697,
+      "learning_rate": 3.3872416891284816e-05,
+      "loss": 0.8945732712745667,
+      "step": 378
+    },
+    {
+      "epoch": 0.16396979503775622,
+      "grad_norm": 2.357815742492676,
+      "learning_rate": 3.4052111410601975e-05,
+      "loss": 0.8950189352035522,
+      "step": 380
+    },
+    {
+      "epoch": 0.16483279395900755,
+      "grad_norm": 2.347301721572876,
+      "learning_rate": 3.423180592991914e-05,
+      "loss": 0.9965803623199463,
+      "step": 382
+    },
+    {
+      "epoch": 0.1656957928802589,
+      "grad_norm": 2.054586887359619,
+      "learning_rate": 3.44115004492363e-05,
+      "loss": 0.9081383347511292,
+      "step": 384
+    },
+    {
+      "epoch": 0.16655879180151026,
+      "grad_norm": 2.1550471782684326,
+      "learning_rate": 3.4591194968553456e-05,
+      "loss": 0.874001681804657,
+      "step": 386
+    },
+    {
+      "epoch": 0.1674217907227616,
+      "grad_norm": 1.6929951906204224,
+      "learning_rate": 3.477088948787062e-05,
+      "loss": 0.9111959934234619,
+      "step": 388
+    },
+    {
+      "epoch": 0.16828478964401294,
+      "grad_norm": 2.0102803707122803,
+      "learning_rate": 3.495058400718778e-05,
+      "loss": 0.8915985226631165,
+      "step": 390
+    },
+    {
+      "epoch": 0.1691477885652643,
+      "grad_norm": 4.215941429138184,
+      "learning_rate": 3.5130278526504944e-05,
+      "loss": 1.0158213376998901,
+      "step": 392
+    },
+    {
+      "epoch": 0.17001078748651563,
+      "grad_norm": 1.864119529724121,
+      "learning_rate": 3.53099730458221e-05,
+      "loss": 0.7811702489852905,
+      "step": 394
+    },
+    {
+      "epoch": 0.170873786407767,
+      "grad_norm": 1.9778105020523071,
+      "learning_rate": 3.548966756513927e-05,
+      "loss": 0.931502103805542,
+      "step": 396
+    },
+    {
+      "epoch": 0.17173678532901834,
+      "grad_norm": 2.0757675170898438,
+      "learning_rate": 3.5669362084456426e-05,
+      "loss": 0.9409074187278748,
+      "step": 398
+    },
+    {
+      "epoch": 0.1725997842502697,
+      "grad_norm": 1.5847891569137573,
+      "learning_rate": 3.5849056603773584e-05,
+      "loss": 0.8159269094467163,
+      "step": 400
+    },
+    {
+      "epoch": 0.1725997842502697,
+      "eval_loss": 0.9124138355255127,
+      "eval_runtime": 832.6331,
+      "eval_samples_per_second": 2.474,
+      "eval_steps_per_second": 2.474,
+      "step": 400
+    },
+    {
+      "epoch": 0.17346278317152103,
+      "grad_norm": 1.8158049583435059,
+      "learning_rate": 3.602875112309075e-05,
+      "loss": 0.8901475667953491,
+      "step": 402
+    },
+    {
+      "epoch": 0.17432578209277239,
+      "grad_norm": 1.9448504447937012,
+      "learning_rate": 3.620844564240791e-05,
+      "loss": 0.8330907821655273,
+      "step": 404
+    },
+    {
+      "epoch": 0.17518878101402374,
+      "grad_norm": 2.028280019760132,
+      "learning_rate": 3.638814016172507e-05,
+      "loss": 0.870513916015625,
+      "step": 406
+    },
+    {
+      "epoch": 0.17605177993527507,
+      "grad_norm": 2.2005157470703125,
+      "learning_rate": 3.656783468104223e-05,
+      "loss": 0.8064979910850525,
+      "step": 408
+    },
+    {
+      "epoch": 0.17691477885652643,
+      "grad_norm": 2.2756290435791016,
+      "learning_rate": 3.6747529200359395e-05,
+      "loss": 0.8457443714141846,
+      "step": 410
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 2.0970261096954346,
+      "learning_rate": 3.6927223719676554e-05,
+      "loss": 0.7478897571563721,
+      "step": 412
+    },
+    {
+      "epoch": 0.1786407766990291,
+      "grad_norm": 1.8917485475540161,
+      "learning_rate": 3.710691823899371e-05,
+      "loss": 0.863377034664154,
+      "step": 414
+    },
+    {
+      "epoch": 0.17950377562028047,
+      "grad_norm": 2.0429933071136475,
+      "learning_rate": 3.728661275831088e-05,
+      "loss": 0.8654620051383972,
+      "step": 416
+    },
+    {
+      "epoch": 0.18036677454153183,
+      "grad_norm": 2.005125045776367,
+      "learning_rate": 3.7466307277628035e-05,
+      "loss": 0.8295455574989319,
+      "step": 418
+    },
+    {
+      "epoch": 0.18122977346278318,
+      "grad_norm": 2.3852169513702393,
+      "learning_rate": 3.764600179694519e-05,
+      "loss": 0.8728633522987366,
+      "step": 420
+    },
+    {
+      "epoch": 0.1820927723840345,
+      "grad_norm": 1.8731592893600464,
+      "learning_rate": 3.782569631626235e-05,
+      "loss": 0.8217283487319946,
+      "step": 422
+    },
+    {
+      "epoch": 0.18295577130528587,
+      "grad_norm": 2.2818236351013184,
+      "learning_rate": 3.8005390835579516e-05,
+      "loss": 0.8869860172271729,
+      "step": 424
+    },
+    {
+      "epoch": 0.18381877022653723,
+      "grad_norm": 2.0646233558654785,
+      "learning_rate": 3.8185085354896675e-05,
+      "loss": 0.9732091426849365,
+      "step": 426
+    },
+    {
+      "epoch": 0.18468176914778855,
+      "grad_norm": 1.9991949796676636,
+      "learning_rate": 3.836477987421384e-05,
+      "loss": 0.9012333154678345,
+      "step": 428
+    },
+    {
+      "epoch": 0.1855447680690399,
+      "grad_norm": 2.209775447845459,
+      "learning_rate": 3.8544474393531e-05,
+      "loss": 0.867533802986145,
+      "step": 430
+    },
+    {
+      "epoch": 0.18640776699029127,
+      "grad_norm": 2.1242146492004395,
+      "learning_rate": 3.8724168912848156e-05,
+      "loss": 0.8697446584701538,
+      "step": 432
+    },
+    {
+      "epoch": 0.1872707659115426,
+      "grad_norm": 1.771337628364563,
+      "learning_rate": 3.890386343216532e-05,
+      "loss": 0.8712933659553528,
+      "step": 434
+    },
+    {
+      "epoch": 0.18813376483279395,
+      "grad_norm": 2.133652925491333,
+      "learning_rate": 3.908355795148248e-05,
+      "loss": 0.8638070821762085,
+      "step": 436
+    },
+    {
+      "epoch": 0.1889967637540453,
+      "grad_norm": 1.9354501962661743,
+      "learning_rate": 3.9263252470799644e-05,
+      "loss": 0.8255205750465393,
+      "step": 438
+    },
+    {
+      "epoch": 0.18985976267529667,
+      "grad_norm": 1.9564658403396606,
+      "learning_rate": 3.94429469901168e-05,
+      "loss": 0.9652490019798279,
+      "step": 440
+    },
+    {
+      "epoch": 0.190722761596548,
+      "grad_norm": 1.9733822345733643,
+      "learning_rate": 3.962264150943397e-05,
+      "loss": 0.8960518836975098,
+      "step": 442
+    },
+    {
+      "epoch": 0.19158576051779935,
+      "grad_norm": 2.1670451164245605,
+      "learning_rate": 3.9802336028751126e-05,
+      "loss": 0.9555241465568542,
+      "step": 444
+    },
+    {
+      "epoch": 0.1924487594390507,
+      "grad_norm": 2.0059614181518555,
+      "learning_rate": 3.9982030548068284e-05,
+      "loss": 0.8238654732704163,
+      "step": 446
+    },
+    {
+      "epoch": 0.19331175836030204,
+      "grad_norm": 1.9803026914596558,
+      "learning_rate": 4.016172506738545e-05,
+      "loss": 0.8701026439666748,
+      "step": 448
+    },
+    {
+      "epoch": 0.1941747572815534,
+      "grad_norm": 1.8800172805786133,
+      "learning_rate": 4.034141958670261e-05,
+      "loss": 0.8927714228630066,
+      "step": 450
+    },
+    {
+      "epoch": 0.19503775620280475,
+      "grad_norm": 1.8555818796157837,
+      "learning_rate": 4.052111410601977e-05,
+      "loss": 0.8635751008987427,
+      "step": 452
+    },
+    {
+      "epoch": 0.1959007551240561,
+      "grad_norm": 2.5119166374206543,
+      "learning_rate": 4.070080862533693e-05,
+      "loss": 0.925403892993927,
+      "step": 454
+    },
+    {
+      "epoch": 0.19676375404530744,
+      "grad_norm": 2.0825788974761963,
+      "learning_rate": 4.088050314465409e-05,
+      "loss": 0.8917028307914734,
+      "step": 456
+    },
+    {
+      "epoch": 0.1976267529665588,
+      "grad_norm": 2.4413394927978516,
+      "learning_rate": 4.1060197663971254e-05,
+      "loss": 0.9097893834114075,
+      "step": 458
+    },
+    {
+      "epoch": 0.19848975188781015,
+      "grad_norm": 2.503617286682129,
+      "learning_rate": 4.123989218328841e-05,
+      "loss": 0.8284633755683899,
+      "step": 460
+    },
+    {
+      "epoch": 0.19935275080906148,
+      "grad_norm": 1.9360398054122925,
+      "learning_rate": 4.141958670260557e-05,
+      "loss": 0.8743083477020264,
+      "step": 462
+    },
+    {
+      "epoch": 0.20021574973031284,
+      "grad_norm": 1.9228297472000122,
+      "learning_rate": 4.159928122192273e-05,
+      "loss": 0.837934136390686,
+      "step": 464
+    },
+    {
+      "epoch": 0.2010787486515642,
+      "grad_norm": 2.3240439891815186,
+      "learning_rate": 4.1778975741239893e-05,
+      "loss": 0.831945538520813,
+      "step": 466
+    },
+    {
+      "epoch": 0.20194174757281552,
+      "grad_norm": 1.879684329032898,
+      "learning_rate": 4.195867026055705e-05,
+      "loss": 0.8012097477912903,
+      "step": 468
+    },
+    {
+      "epoch": 0.20280474649406688,
+      "grad_norm": 2.2995200157165527,
+      "learning_rate": 4.213836477987422e-05,
+      "loss": 0.8670937418937683,
+      "step": 470
+    },
+    {
+      "epoch": 0.20366774541531824,
+      "grad_norm": 2.098020553588867,
+      "learning_rate": 4.2318059299191375e-05,
+      "loss": 0.88299161195755,
+      "step": 472
+    },
+    {
+      "epoch": 0.2045307443365696,
+      "grad_norm": 2.0588274002075195,
+      "learning_rate": 4.249775381850854e-05,
+      "loss": 0.9045401811599731,
+      "step": 474
+    },
+    {
+      "epoch": 0.20539374325782092,
+      "grad_norm": 1.8832436800003052,
+      "learning_rate": 4.26774483378257e-05,
+      "loss": 0.9787635803222656,
+      "step": 476
+    },
+    {
+      "epoch": 0.20625674217907228,
+      "grad_norm": 2.3451809883117676,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 0.8874871730804443,
+      "step": 478
+    },
+    {
+      "epoch": 0.20711974110032363,
+      "grad_norm": 1.8093878030776978,
+      "learning_rate": 4.303683737646002e-05,
+      "loss": 0.794157087802887,
+      "step": 480
+    },
+    {
+      "epoch": 0.20798274002157496,
+      "grad_norm": 1.8396174907684326,
+      "learning_rate": 4.321653189577718e-05,
+      "loss": 0.792723536491394,
+      "step": 482
+    },
+    {
+      "epoch": 0.20884573894282632,
+      "grad_norm": 2.3939783573150635,
+      "learning_rate": 4.3396226415094345e-05,
+      "loss": 0.9221814274787903,
+      "step": 484
+    },
+    {
+      "epoch": 0.20970873786407768,
+      "grad_norm": 2.2652194499969482,
+      "learning_rate": 4.35759209344115e-05,
+      "loss": 0.8716039061546326,
+      "step": 486
+    },
+    {
+      "epoch": 0.210571736785329,
+      "grad_norm": 2.068258762359619,
+      "learning_rate": 4.375561545372867e-05,
+      "loss": 0.8517807126045227,
+      "step": 488
+    },
+    {
+      "epoch": 0.21143473570658036,
+      "grad_norm": 2.264620542526245,
+      "learning_rate": 4.3935309973045826e-05,
+      "loss": 0.8699264526367188,
+      "step": 490
+    },
+    {
+      "epoch": 0.21229773462783172,
+      "grad_norm": 2.0821611881256104,
+      "learning_rate": 4.4115004492362984e-05,
+      "loss": 0.8760254383087158,
+      "step": 492
+    },
+    {
+      "epoch": 0.21316073354908308,
+      "grad_norm": 1.9486546516418457,
+      "learning_rate": 4.429469901168015e-05,
+      "loss": 0.8957411050796509,
+      "step": 494
+    },
+    {
+      "epoch": 0.2140237324703344,
+      "grad_norm": 2.092957019805908,
+      "learning_rate": 4.447439353099731e-05,
+      "loss": 0.981200635433197,
+      "step": 496
+    },
+    {
+      "epoch": 0.21488673139158576,
+      "grad_norm": 2.325758218765259,
+      "learning_rate": 4.4654088050314466e-05,
+      "loss": 0.8295405507087708,
+      "step": 498
+    },
+    {
+      "epoch": 0.21574973031283712,
+      "grad_norm": 2.251295566558838,
+      "learning_rate": 4.4833782569631624e-05,
+      "loss": 0.8463165163993835,
+      "step": 500
+    },
+    {
+      "epoch": 0.21574973031283712,
+      "eval_loss": 0.8945327997207642,
+      "eval_runtime": 822.9776,
+      "eval_samples_per_second": 2.503,
+      "eval_steps_per_second": 2.503,
+      "step": 500
+    },
+    {
+      "epoch": 0.21661272923408845,
+      "grad_norm": 1.8110703229904175,
+      "learning_rate": 4.501347708894879e-05,
+      "loss": 0.9099015593528748,
+      "step": 502
+    },
+    {
+      "epoch": 0.2174757281553398,
+      "grad_norm": 2.0977623462677,
+      "learning_rate": 4.519317160826595e-05,
+      "loss": 0.875080943107605,
+      "step": 504
+    },
+    {
+      "epoch": 0.21833872707659116,
+      "grad_norm": 1.8648077249526978,
+      "learning_rate": 4.537286612758311e-05,
+      "loss": 0.8511829376220703,
+      "step": 506
+    },
+    {
+      "epoch": 0.2192017259978425,
+      "grad_norm": 1.754744291305542,
+      "learning_rate": 4.555256064690027e-05,
+      "loss": 0.8408182859420776,
+      "step": 508
+    },
+    {
+      "epoch": 0.22006472491909385,
+      "grad_norm": 1.9869136810302734,
+      "learning_rate": 4.573225516621743e-05,
+      "loss": 0.8824991583824158,
+      "step": 510
+    },
+    {
+      "epoch": 0.2209277238403452,
+      "grad_norm": 2.4601082801818848,
+      "learning_rate": 4.5911949685534594e-05,
+      "loss": 0.9949447512626648,
+      "step": 512
+    },
+    {
+      "epoch": 0.22179072276159656,
+      "grad_norm": 2.1224238872528076,
+      "learning_rate": 4.609164420485175e-05,
+      "loss": 0.8979368805885315,
+      "step": 514
+    },
+    {
+      "epoch": 0.2226537216828479,
+      "grad_norm": 1.6812392473220825,
+      "learning_rate": 4.627133872416892e-05,
+      "loss": 0.8728249669075012,
+      "step": 516
+    },
+    {
+      "epoch": 0.22351672060409924,
+      "grad_norm": 1.6505497694015503,
+      "learning_rate": 4.6451033243486075e-05,
+      "loss": 0.8083430528640747,
+      "step": 518
+    },
+    {
+      "epoch": 0.2243797195253506,
+      "grad_norm": 1.6454377174377441,
+      "learning_rate": 4.663072776280324e-05,
+      "loss": 0.8042294383049011,
+      "step": 520
+    },
+    {
+      "epoch": 0.22524271844660193,
+      "grad_norm": 2.0974535942077637,
+      "learning_rate": 4.68104222821204e-05,
+      "loss": 0.9263730049133301,
+      "step": 522
+    },
+    {
+      "epoch": 0.2261057173678533,
+      "grad_norm": 1.90152108669281,
+      "learning_rate": 4.6990116801437556e-05,
+      "loss": 0.9090206623077393,
+      "step": 524
+    },
+    {
+      "epoch": 0.22696871628910464,
+      "grad_norm": 1.9843928813934326,
+      "learning_rate": 4.716981132075472e-05,
+      "loss": 0.8310918807983398,
+      "step": 526
+    },
+    {
+      "epoch": 0.227831715210356,
+      "grad_norm": 1.7880226373672485,
+      "learning_rate": 4.734950584007188e-05,
+      "loss": 0.8838925957679749,
+      "step": 528
+    },
+    {
+      "epoch": 0.22869471413160733,
+      "grad_norm": 1.8534979820251465,
+      "learning_rate": 4.7529200359389045e-05,
+      "loss": 0.9431065917015076,
+      "step": 530
+    },
+    {
+      "epoch": 0.2295577130528587,
+      "grad_norm": 1.8936293125152588,
+      "learning_rate": 4.77088948787062e-05,
+      "loss": 0.7988291382789612,
+      "step": 532
+    },
+    {
+      "epoch": 0.23042071197411004,
+      "grad_norm": 1.919683814048767,
+      "learning_rate": 4.788858939802337e-05,
+      "loss": 0.8477044105529785,
+      "step": 534
+    },
+    {
+      "epoch": 0.23128371089536137,
+      "grad_norm": 1.8022494316101074,
+      "learning_rate": 4.8068283917340526e-05,
+      "loss": 0.8482418060302734,
+      "step": 536
+    },
+    {
+      "epoch": 0.23214670981661273,
+      "grad_norm": 1.8628984689712524,
+      "learning_rate": 4.8247978436657684e-05,
+      "loss": 0.8553584814071655,
+      "step": 538
+    },
+    {
+      "epoch": 0.23300970873786409,
+      "grad_norm": 1.8644732236862183,
+      "learning_rate": 4.842767295597484e-05,
+      "loss": 0.8287713527679443,
+      "step": 540
+    },
+    {
+      "epoch": 0.23387270765911541,
+      "grad_norm": 2.162926435470581,
+      "learning_rate": 4.8607367475292e-05,
+      "loss": 0.8984123468399048,
+      "step": 542
+    },
+    {
+      "epoch": 0.23473570658036677,
+      "grad_norm": 1.453223466873169,
+      "learning_rate": 4.8787061994609166e-05,
+      "loss": 0.725272536277771,
+      "step": 544
+    },
+    {
+      "epoch": 0.23559870550161813,
+      "grad_norm": 2.2145543098449707,
+      "learning_rate": 4.8966756513926324e-05,
+      "loss": 0.9128344655036926,
+      "step": 546
+    },
+    {
+      "epoch": 0.23646170442286948,
+      "grad_norm": 1.7639187574386597,
+      "learning_rate": 4.914645103324349e-05,
+      "loss": 0.782098114490509,
+      "step": 548
+    },
+    {
+      "epoch": 0.2373247033441208,
+      "grad_norm": 1.6597305536270142,
+      "learning_rate": 4.932614555256065e-05,
+      "loss": 0.8212350010871887,
+      "step": 550
+    },
+    {
+      "epoch": 0.23818770226537217,
+      "grad_norm": 1.9441677331924438,
+      "learning_rate": 4.950584007187781e-05,
+      "loss": 0.9033122062683105,
+      "step": 552
+    },
+    {
+      "epoch": 0.23905070118662353,
+      "grad_norm": 2.0332281589508057,
+      "learning_rate": 4.968553459119497e-05,
+      "loss": 0.9195884466171265,
+      "step": 554
+    },
+    {
+      "epoch": 0.23991370010787486,
+      "grad_norm": 1.9222822189331055,
+      "learning_rate": 4.986522911051213e-05,
+      "loss": 0.8828456401824951,
+      "step": 556
+    },
+    {
+      "epoch": 0.2407766990291262,
+      "grad_norm": 1.9830708503723145,
+      "learning_rate": 5.004492362982929e-05,
+      "loss": 0.9089829921722412,
+      "step": 558
+    },
+    {
+      "epoch": 0.24163969795037757,
+      "grad_norm": 1.99044930934906,
+      "learning_rate": 5.022461814914645e-05,
+      "loss": 0.8747812509536743,
+      "step": 560
+    },
+    {
+      "epoch": 0.2425026968716289,
+      "grad_norm": 1.7961562871932983,
+      "learning_rate": 5.040431266846362e-05,
+      "loss": 0.8421230912208557,
+      "step": 562
+    },
+    {
+      "epoch": 0.24336569579288025,
+      "grad_norm": 1.9798882007598877,
+      "learning_rate": 5.058400718778078e-05,
+      "loss": 0.8669922351837158,
+      "step": 564
+    },
+    {
+      "epoch": 0.2442286947141316,
+      "grad_norm": 2.0138750076293945,
+      "learning_rate": 5.076370170709793e-05,
+      "loss": 0.8596820831298828,
+      "step": 566
+    },
+    {
+      "epoch": 0.24509169363538297,
+      "grad_norm": 2.069021701812744,
+      "learning_rate": 5.09433962264151e-05,
+      "loss": 0.8288601636886597,
+      "step": 568
+    },
+    {
+      "epoch": 0.2459546925566343,
+      "grad_norm": 2.6913585662841797,
+      "learning_rate": 5.112309074573226e-05,
+      "loss": 0.8321394324302673,
+      "step": 570
+    },
+    {
+      "epoch": 0.24681769147788565,
+      "grad_norm": 1.8057955503463745,
+      "learning_rate": 5.1302785265049415e-05,
+      "loss": 0.842660129070282,
+      "step": 572
+    },
+    {
+      "epoch": 0.247680690399137,
+      "grad_norm": 1.5741548538208008,
+      "learning_rate": 5.148247978436658e-05,
+      "loss": 0.8431437015533447,
+      "step": 574
+    },
+    {
+      "epoch": 0.24854368932038834,
+      "grad_norm": 2.0329413414001465,
+      "learning_rate": 5.166217430368374e-05,
+      "loss": 0.9046191573143005,
+      "step": 576
+    },
+    {
+      "epoch": 0.2494066882416397,
+      "grad_norm": 1.7638250589370728,
+      "learning_rate": 5.18418688230009e-05,
+      "loss": 0.8108726739883423,
+      "step": 578
+    },
+    {
+      "epoch": 0.25026968716289105,
+      "grad_norm": 2.1088576316833496,
+      "learning_rate": 5.202156334231806e-05,
+      "loss": 0.8621282577514648,
+      "step": 580
+    },
+    {
+      "epoch": 0.2511326860841424,
+      "grad_norm": 2.072145462036133,
+      "learning_rate": 5.220125786163522e-05,
+      "loss": 0.8774182200431824,
+      "step": 582
+    },
+    {
+      "epoch": 0.25199568500539377,
+      "grad_norm": 1.8093693256378174,
+      "learning_rate": 5.2380952380952384e-05,
+      "loss": 0.863322377204895,
+      "step": 584
+    },
+    {
+      "epoch": 0.25285868392664507,
+      "grad_norm": 1.7119505405426025,
+      "learning_rate": 5.2560646900269536e-05,
+      "loss": 0.8493514657020569,
+      "step": 586
+    },
+    {
+      "epoch": 0.2537216828478964,
+      "grad_norm": 2.042052745819092,
+      "learning_rate": 5.27403414195867e-05,
+      "loss": 0.8278731107711792,
+      "step": 588
+    },
+    {
+      "epoch": 0.2545846817691478,
+      "grad_norm": 1.9019906520843506,
+      "learning_rate": 5.2920035938903866e-05,
+      "loss": 0.8388869166374207,
+      "step": 590
+    },
+    {
+      "epoch": 0.25544768069039914,
+      "grad_norm": 1.8072630167007446,
+      "learning_rate": 5.309973045822103e-05,
+      "loss": 0.8666917085647583,
+      "step": 592
+    },
+    {
+      "epoch": 0.2563106796116505,
+      "grad_norm": 1.7099417448043823,
+      "learning_rate": 5.327942497753818e-05,
+      "loss": 0.8114299774169922,
+      "step": 594
+    },
+    {
+      "epoch": 0.25717367853290185,
+      "grad_norm": 1.8132266998291016,
+      "learning_rate": 5.345911949685535e-05,
+      "loss": 0.8842664361000061,
+      "step": 596
+    },
+    {
+      "epoch": 0.2580366774541532,
+      "grad_norm": 1.9578651189804077,
+      "learning_rate": 5.363881401617251e-05,
+      "loss": 0.7954385876655579,
+      "step": 598
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "grad_norm": 1.832077145576477,
+      "learning_rate": 5.381850853548968e-05,
+      "loss": 0.912541925907135,
+      "step": 600
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "eval_loss": 0.8770867586135864,
+      "eval_runtime": 827.8893,
+      "eval_samples_per_second": 2.488,
+      "eval_steps_per_second": 2.488,
+      "step": 600
+    },
+    {
+      "epoch": 0.25976267529665586,
+      "grad_norm": 1.7565301656723022,
+      "learning_rate": 5.399820305480683e-05,
+      "loss": 0.8436558246612549,
+      "step": 602
+    },
+    {
+      "epoch": 0.2606256742179072,
+      "grad_norm": 1.9199552536010742,
+      "learning_rate": 5.4177897574123994e-05,
+      "loss": 0.9384433031082153,
+      "step": 604
+    },
+    {
+      "epoch": 0.2614886731391586,
+      "grad_norm": 1.7609341144561768,
+      "learning_rate": 5.435759209344116e-05,
+      "loss": 0.8695753812789917,
+      "step": 606
+    },
+    {
+      "epoch": 0.26235167206040994,
+      "grad_norm": 1.771958589553833,
+      "learning_rate": 5.453728661275831e-05,
+      "loss": 0.8462895154953003,
+      "step": 608
+    },
+    {
+      "epoch": 0.2632146709816613,
+      "grad_norm": 1.8958079814910889,
+      "learning_rate": 5.4716981132075475e-05,
+      "loss": 0.9074611663818359,
+      "step": 610
+    },
+    {
+      "epoch": 0.26407766990291265,
+      "grad_norm": 1.8668403625488281,
+      "learning_rate": 5.489667565139264e-05,
+      "loss": 0.8603307008743286,
+      "step": 612
+    },
+    {
+      "epoch": 0.26494066882416395,
+      "grad_norm": 1.8902733325958252,
+      "learning_rate": 5.50763701707098e-05,
+      "loss": 0.8925216794013977,
+      "step": 614
+    },
+    {
+      "epoch": 0.2658036677454153,
+      "grad_norm": 1.7172386646270752,
+      "learning_rate": 5.525606469002696e-05,
+      "loss": 0.7872517704963684,
+      "step": 616
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.7814518213272095,
+      "learning_rate": 5.5435759209344115e-05,
+      "loss": 0.7951212525367737,
+      "step": 618
+    },
+    {
+      "epoch": 0.267529665587918,
+      "grad_norm": 1.8714463710784912,
+      "learning_rate": 5.561545372866128e-05,
+      "loss": 0.859940230846405,
+      "step": 620
+    },
+    {
+      "epoch": 0.2683926645091694,
+      "grad_norm": 1.9614174365997314,
+      "learning_rate": 5.579514824797844e-05,
+      "loss": 0.8953307867050171,
+      "step": 622
+    },
+    {
+      "epoch": 0.26925566343042073,
+      "grad_norm": 1.7190991640090942,
+      "learning_rate": 5.5974842767295596e-05,
+      "loss": 0.8346402645111084,
+      "step": 624
+    },
+    {
+      "epoch": 0.27011866235167203,
+      "grad_norm": 1.981070876121521,
+      "learning_rate": 5.615453728661276e-05,
+      "loss": 0.8545536398887634,
+      "step": 626
+    },
+    {
+      "epoch": 0.2709816612729234,
+      "grad_norm": 1.9186289310455322,
+      "learning_rate": 5.6334231805929926e-05,
+      "loss": 0.9064128398895264,
+      "step": 628
+    },
+    {
+      "epoch": 0.27184466019417475,
+      "grad_norm": 1.9937374591827393,
+      "learning_rate": 5.651392632524708e-05,
+      "loss": 0.883073627948761,
+      "step": 630
+    },
+    {
+      "epoch": 0.2727076591154261,
+      "grad_norm": 1.800236701965332,
+      "learning_rate": 5.669362084456424e-05,
+      "loss": 0.8777942657470703,
+      "step": 632
+    },
+    {
+      "epoch": 0.27357065803667746,
+      "grad_norm": 1.9164050817489624,
+      "learning_rate": 5.687331536388141e-05,
+      "loss": 0.8527862429618835,
+      "step": 634
+    },
+    {
+      "epoch": 0.2744336569579288,
+      "grad_norm": 1.7494043111801147,
+      "learning_rate": 5.705300988319856e-05,
+      "loss": 0.881090521812439,
+      "step": 636
+    },
+    {
+      "epoch": 0.2752966558791802,
+      "grad_norm": 1.9433623552322388,
+      "learning_rate": 5.7232704402515724e-05,
+      "loss": 0.8547250628471375,
+      "step": 638
+    },
+    {
+      "epoch": 0.2761596548004315,
+      "grad_norm": 1.7539145946502686,
+      "learning_rate": 5.741239892183289e-05,
+      "loss": 0.8429408073425293,
+      "step": 640
+    },
+    {
+      "epoch": 0.27702265372168283,
+      "grad_norm": 1.904911756515503,
+      "learning_rate": 5.7592093441150054e-05,
+      "loss": 0.8587079644203186,
+      "step": 642
+    },
+    {
+      "epoch": 0.2778856526429342,
+      "grad_norm": 1.5534838438034058,
+      "learning_rate": 5.7771787960467206e-05,
+      "loss": 0.7795872688293457,
+      "step": 644
+    },
+    {
+      "epoch": 0.27874865156418555,
+      "grad_norm": 1.704798698425293,
+      "learning_rate": 5.795148247978437e-05,
+      "loss": 0.7657744884490967,
+      "step": 646
+    },
+    {
+      "epoch": 0.2796116504854369,
+      "grad_norm": 1.8432048559188843,
+      "learning_rate": 5.8131176999101536e-05,
+      "loss": 0.8119702935218811,
+      "step": 648
+    },
+    {
+      "epoch": 0.28047464940668826,
+      "grad_norm": 1.9495919942855835,
+      "learning_rate": 5.831087151841869e-05,
+      "loss": 0.8846080899238586,
+      "step": 650
+    },
+    {
+      "epoch": 0.2813376483279396,
+      "grad_norm": 1.9626739025115967,
+      "learning_rate": 5.849056603773585e-05,
+      "loss": 0.854324460029602,
+      "step": 652
+    },
+    {
+      "epoch": 0.2822006472491909,
+      "grad_norm": 1.767221212387085,
+      "learning_rate": 5.867026055705302e-05,
+      "loss": 0.7908785939216614,
+      "step": 654
+    },
+    {
+      "epoch": 0.2830636461704423,
+      "grad_norm": 1.8866491317749023,
+      "learning_rate": 5.8849955076370175e-05,
+      "loss": 0.8155530691146851,
+      "step": 656
+    },
+    {
+      "epoch": 0.28392664509169363,
+      "grad_norm": 1.9543417692184448,
+      "learning_rate": 5.9029649595687334e-05,
+      "loss": 0.9833307266235352,
+      "step": 658
+    },
+    {
+      "epoch": 0.284789644012945,
+      "grad_norm": 1.867039680480957,
+      "learning_rate": 5.920934411500449e-05,
+      "loss": 0.7991418242454529,
+      "step": 660
+    },
+    {
+      "epoch": 0.28565264293419634,
+      "grad_norm": 1.8487379550933838,
+      "learning_rate": 5.938903863432166e-05,
+      "loss": 0.8232532143592834,
+      "step": 662
+    },
+    {
+      "epoch": 0.2865156418554477,
+      "grad_norm": 1.5015742778778076,
+      "learning_rate": 5.956873315363881e-05,
+      "loss": 0.76528000831604,
+      "step": 664
+    },
+    {
+      "epoch": 0.287378640776699,
+      "grad_norm": 2.726778268814087,
+      "learning_rate": 5.974842767295597e-05,
+      "loss": 0.8220192790031433,
+      "step": 666
+    },
+    {
+      "epoch": 0.28824163969795036,
+      "grad_norm": 1.6754003763198853,
+      "learning_rate": 5.992812219227314e-05,
+      "loss": 0.7534968256950378,
+      "step": 668
+    },
+    {
+      "epoch": 0.2891046386192017,
+      "grad_norm": 1.9948434829711914,
+      "learning_rate": 6.01078167115903e-05,
+      "loss": 0.8405768871307373,
+      "step": 670
+    },
+    {
+      "epoch": 0.28996763754045307,
+      "grad_norm": 1.7982401847839355,
+      "learning_rate": 6.0287511230907455e-05,
+      "loss": 0.8143276572227478,
+      "step": 672
+    },
+    {
+      "epoch": 0.29083063646170443,
+      "grad_norm": 1.7311779260635376,
+      "learning_rate": 6.046720575022462e-05,
+      "loss": 0.9602267742156982,
+      "step": 674
+    },
+    {
+      "epoch": 0.2916936353829558,
+      "grad_norm": 1.9906021356582642,
+      "learning_rate": 6.0646900269541785e-05,
+      "loss": 0.8628544807434082,
+      "step": 676
+    },
+    {
+      "epoch": 0.29255663430420714,
+      "grad_norm": 1.7477494478225708,
+      "learning_rate": 6.082659478885895e-05,
+      "loss": 0.7800343632698059,
+      "step": 678
+    },
+    {
+      "epoch": 0.29341963322545844,
+      "grad_norm": 1.7978737354278564,
+      "learning_rate": 6.10062893081761e-05,
+      "loss": 0.8722298741340637,
+      "step": 680
+    },
+    {
+      "epoch": 0.2942826321467098,
+      "grad_norm": 2.1463348865509033,
+      "learning_rate": 6.118598382749326e-05,
+      "loss": 0.8895675539970398,
+      "step": 682
+    },
+    {
+      "epoch": 0.29514563106796116,
+      "grad_norm": 1.9256783723831177,
+      "learning_rate": 6.136567834681042e-05,
+      "loss": 0.8579491972923279,
+      "step": 684
+    },
+    {
+      "epoch": 0.2960086299892125,
+      "grad_norm": 1.4459543228149414,
+      "learning_rate": 6.154537286612758e-05,
+      "loss": 0.7811232805252075,
+      "step": 686
+    },
+    {
+      "epoch": 0.29687162891046387,
+      "grad_norm": 1.6202397346496582,
+      "learning_rate": 6.172506738544474e-05,
+      "loss": 0.7827678322792053,
+      "step": 688
+    },
+    {
+      "epoch": 0.2977346278317152,
+      "grad_norm": 2.0524775981903076,
+      "learning_rate": 6.19047619047619e-05,
+      "loss": 0.8186459541320801,
+      "step": 690
+    },
+    {
+      "epoch": 0.2985976267529666,
+      "grad_norm": 1.7867428064346313,
+      "learning_rate": 6.208445642407907e-05,
+      "loss": 0.8691027760505676,
+      "step": 692
+    },
+    {
+      "epoch": 0.2994606256742179,
+      "grad_norm": 1.9605737924575806,
+      "learning_rate": 6.226415094339622e-05,
+      "loss": 0.8233416080474854,
+      "step": 694
+    },
+    {
+      "epoch": 0.30032362459546924,
+      "grad_norm": 1.7035984992980957,
+      "learning_rate": 6.244384546271339e-05,
+      "loss": 0.8493421077728271,
+      "step": 696
+    },
+    {
+      "epoch": 0.3011866235167206,
+      "grad_norm": 1.9402128458023071,
+      "learning_rate": 6.262353998203055e-05,
+      "loss": 0.8114250302314758,
+      "step": 698
+    },
+    {
+      "epoch": 0.30204962243797195,
+      "grad_norm": 1.8533520698547363,
+      "learning_rate": 6.28032345013477e-05,
+      "loss": 0.8996106386184692,
+      "step": 700
+    },
+    {
+      "epoch": 0.30204962243797195,
+      "eval_loss": 0.8631294369697571,
+      "eval_runtime": 839.6269,
+      "eval_samples_per_second": 2.453,
+      "eval_steps_per_second": 2.453,
+      "step": 700
+    },
+    {
+      "epoch": 0.3029126213592233,
+      "grad_norm": 1.727793574333191,
+      "learning_rate": 6.298292902066487e-05,
+      "loss": 0.7978370189666748,
+      "step": 702
+    },
+    {
+      "epoch": 0.30377562028047467,
+      "grad_norm": 1.9601492881774902,
+      "learning_rate": 6.316262353998203e-05,
+      "loss": 0.8120381236076355,
+      "step": 704
+    },
+    {
+      "epoch": 0.304638619201726,
+      "grad_norm": 1.8380948305130005,
+      "learning_rate": 6.33423180592992e-05,
+      "loss": 0.8005605340003967,
+      "step": 706
+    },
+    {
+      "epoch": 0.3055016181229773,
+      "grad_norm": 1.8210986852645874,
+      "learning_rate": 6.352201257861635e-05,
+      "loss": 0.8967245817184448,
+      "step": 708
+    },
+    {
+      "epoch": 0.3063646170442287,
+      "grad_norm": 3.5359878540039062,
+      "learning_rate": 6.370170709793352e-05,
+      "loss": 0.8271524906158447,
+      "step": 710
+    },
+    {
+      "epoch": 0.30722761596548004,
+      "grad_norm": 1.7943733930587769,
+      "learning_rate": 6.388140161725068e-05,
+      "loss": 0.8759040236473083,
+      "step": 712
+    },
+    {
+      "epoch": 0.3080906148867314,
+      "grad_norm": 1.5483570098876953,
+      "learning_rate": 6.406109613656783e-05,
+      "loss": 0.7872476577758789,
+      "step": 714
+    },
+    {
+      "epoch": 0.30895361380798275,
+      "grad_norm": 1.8044816255569458,
+      "learning_rate": 6.4240790655885e-05,
+      "loss": 0.849986732006073,
+      "step": 716
+    },
+    {
+      "epoch": 0.3098166127292341,
+      "grad_norm": 1.548281192779541,
+      "learning_rate": 6.442048517520216e-05,
+      "loss": 0.8292878866195679,
+      "step": 718
+    },
+    {
+      "epoch": 0.3106796116504854,
+      "grad_norm": 1.643020749092102,
+      "learning_rate": 6.460017969451933e-05,
+      "loss": 0.8796502351760864,
+      "step": 720
+    },
+    {
+      "epoch": 0.31154261057173677,
+      "grad_norm": 1.633881688117981,
+      "learning_rate": 6.477987421383648e-05,
+      "loss": 0.806233286857605,
+      "step": 722
+    },
+    {
+      "epoch": 0.3124056094929881,
+      "grad_norm": 1.7712864875793457,
+      "learning_rate": 6.495956873315364e-05,
+      "loss": 0.802722156047821,
+      "step": 724
+    },
+    {
+      "epoch": 0.3132686084142395,
+      "grad_norm": 1.9158337116241455,
+      "learning_rate": 6.513926325247081e-05,
+      "loss": 0.8735752105712891,
+      "step": 726
+    },
+    {
+      "epoch": 0.31413160733549084,
+      "grad_norm": 1.8648416996002197,
+      "learning_rate": 6.531895777178796e-05,
+      "loss": 0.793403148651123,
+      "step": 728
+    },
+    {
+      "epoch": 0.3149946062567422,
+      "grad_norm": 1.5917021036148071,
+      "learning_rate": 6.549865229110512e-05,
+      "loss": 0.7772542834281921,
+      "step": 730
+    },
+    {
+      "epoch": 0.31585760517799355,
+      "grad_norm": 1.8560330867767334,
+      "learning_rate": 6.567834681042229e-05,
+      "loss": 0.8731698989868164,
+      "step": 732
+    },
+    {
+      "epoch": 0.31672060409924485,
+      "grad_norm": 1.6038225889205933,
+      "learning_rate": 6.585804132973945e-05,
+      "loss": 0.8167505264282227,
+      "step": 734
+    },
+    {
+      "epoch": 0.3175836030204962,
+      "grad_norm": 1.6221873760223389,
+      "learning_rate": 6.60377358490566e-05,
+      "loss": 0.7810112237930298,
+      "step": 736
+    },
+    {
+      "epoch": 0.31844660194174756,
+      "grad_norm": 1.8528746366500854,
+      "learning_rate": 6.621743036837377e-05,
+      "loss": 0.8735228776931763,
+      "step": 738
+    },
+    {
+      "epoch": 0.3193096008629989,
+      "grad_norm": 1.473233938217163,
+      "learning_rate": 6.639712488769094e-05,
+      "loss": 0.8231552243232727,
+      "step": 740
+    },
+    {
+      "epoch": 0.3201725997842503,
+      "grad_norm": 1.7726222276687622,
+      "learning_rate": 6.657681940700809e-05,
+      "loss": 0.8400886058807373,
+      "step": 742
+    },
+    {
+      "epoch": 0.32103559870550163,
+      "grad_norm": 1.7245025634765625,
+      "learning_rate": 6.675651392632525e-05,
+      "loss": 0.7371112108230591,
+      "step": 744
+    },
+    {
+      "epoch": 0.321898597626753,
+      "grad_norm": 1.6225395202636719,
+      "learning_rate": 6.693620844564242e-05,
+      "loss": 0.8057155013084412,
+      "step": 746
+    },
+    {
+      "epoch": 0.3227615965480043,
+      "grad_norm": 1.607007384300232,
+      "learning_rate": 6.711590296495958e-05,
+      "loss": 0.8471131324768066,
+      "step": 748
+    },
+    {
+      "epoch": 0.32362459546925565,
+      "grad_norm": 1.760038137435913,
+      "learning_rate": 6.729559748427673e-05,
+      "loss": 0.8251315951347351,
+      "step": 750
+    },
+    {
+      "epoch": 0.324487594390507,
+      "grad_norm": 1.8012818098068237,
+      "learning_rate": 6.74752920035939e-05,
+      "loss": 0.8215667605400085,
+      "step": 752
+    },
+    {
+      "epoch": 0.32535059331175836,
+      "grad_norm": 1.769614815711975,
+      "learning_rate": 6.765498652291105e-05,
+      "loss": 0.8113123178482056,
+      "step": 754
+    },
+    {
+      "epoch": 0.3262135922330097,
+      "grad_norm": 1.7554916143417358,
+      "learning_rate": 6.783468104222822e-05,
+      "loss": 0.8893613219261169,
+      "step": 756
+    },
+    {
+      "epoch": 0.3270765911542611,
+      "grad_norm": 1.5720254182815552,
+      "learning_rate": 6.801437556154538e-05,
+      "loss": 0.8165010809898376,
+      "step": 758
+    },
+    {
+      "epoch": 0.32793959007551243,
+      "grad_norm": 2.1887543201446533,
+      "learning_rate": 6.819407008086253e-05,
+      "loss": 0.8800036311149597,
+      "step": 760
+    },
+    {
+      "epoch": 0.32880258899676373,
+      "grad_norm": 1.63350510597229,
+      "learning_rate": 6.83737646001797e-05,
+      "loss": 0.7268908619880676,
+      "step": 762
+    },
+    {
+      "epoch": 0.3296655879180151,
+      "grad_norm": 1.5838189125061035,
+      "learning_rate": 6.855345911949685e-05,
+      "loss": 0.7695913910865784,
+      "step": 764
+    },
+    {
+      "epoch": 0.33052858683926645,
+      "grad_norm": 1.8752859830856323,
+      "learning_rate": 6.873315363881401e-05,
+      "loss": 0.9005667567253113,
+      "step": 766
+    },
+    {
+      "epoch": 0.3313915857605178,
+      "grad_norm": 1.4201446771621704,
+      "learning_rate": 6.891284815813118e-05,
+      "loss": 0.7960113883018494,
+      "step": 768
+    },
+    {
+      "epoch": 0.33225458468176916,
+      "grad_norm": 1.6665233373641968,
+      "learning_rate": 6.909254267744834e-05,
+      "loss": 0.851472020149231,
+      "step": 770
+    },
+    {
+      "epoch": 0.3331175836030205,
+      "grad_norm": 1.72721266746521,
+      "learning_rate": 6.92722371967655e-05,
+      "loss": 0.8403398990631104,
+      "step": 772
+    },
+    {
+      "epoch": 0.3339805825242718,
+      "grad_norm": 1.648680567741394,
+      "learning_rate": 6.945193171608266e-05,
+      "loss": 0.7582393884658813,
+      "step": 774
+    },
+    {
+      "epoch": 0.3348435814455232,
+      "grad_norm": 1.89604651927948,
+      "learning_rate": 6.963162623539982e-05,
+      "loss": 0.8250385522842407,
+      "step": 776
+    },
+    {
+      "epoch": 0.33570658036677453,
+      "grad_norm": 1.4748259782791138,
+      "learning_rate": 6.981132075471698e-05,
+      "loss": 0.7916358709335327,
+      "step": 778
+    },
+    {
+      "epoch": 0.3365695792880259,
+      "grad_norm": 1.4885735511779785,
+      "learning_rate": 6.999101527403414e-05,
+      "loss": 0.7432135939598083,
+      "step": 780
+    },
+    {
+      "epoch": 0.33743257820927725,
+      "grad_norm": 1.5150227546691895,
+      "learning_rate": 7.01707097933513e-05,
+      "loss": 0.7369741201400757,
+      "step": 782
+    },
+    {
+      "epoch": 0.3382955771305286,
+      "grad_norm": 2.0702431201934814,
+      "learning_rate": 7.035040431266847e-05,
+      "loss": 0.8347548246383667,
+      "step": 784
+    },
+    {
+      "epoch": 0.33915857605177996,
+      "grad_norm": 1.8330671787261963,
+      "learning_rate": 7.053009883198562e-05,
+      "loss": 0.7757654190063477,
+      "step": 786
+    },
+    {
+      "epoch": 0.34002157497303126,
+      "grad_norm": 1.6809033155441284,
+      "learning_rate": 7.070979335130279e-05,
+      "loss": 0.7966224551200867,
+      "step": 788
+    },
+    {
+      "epoch": 0.3408845738942826,
+      "grad_norm": 1.5811399221420288,
+      "learning_rate": 7.088948787061995e-05,
+      "loss": 0.7977543473243713,
+      "step": 790
+    },
+    {
+      "epoch": 0.341747572815534,
+      "grad_norm": 1.6572248935699463,
+      "learning_rate": 7.10691823899371e-05,
+      "loss": 0.7842527627944946,
+      "step": 792
+    },
+    {
+      "epoch": 0.34261057173678533,
+      "grad_norm": 1.6138155460357666,
+      "learning_rate": 7.124887690925427e-05,
+      "loss": 0.7586495876312256,
+      "step": 794
+    },
+    {
+      "epoch": 0.3434735706580367,
+      "grad_norm": 1.9198144674301147,
+      "learning_rate": 7.142857142857143e-05,
+      "loss": 0.9010837078094482,
+      "step": 796
+    },
+    {
+      "epoch": 0.34433656957928804,
+      "grad_norm": 1.6212328672409058,
+      "learning_rate": 7.16082659478886e-05,
+      "loss": 0.7857459783554077,
+      "step": 798
+    },
+    {
+      "epoch": 0.3451995685005394,
+      "grad_norm": 2.1088991165161133,
+      "learning_rate": 7.178796046720575e-05,
+      "loss": 0.9087778925895691,
+      "step": 800
+    },
+    {
+      "epoch": 0.3451995685005394,
+      "eval_loss": 0.8476243615150452,
+      "eval_runtime": 831.6735,
+      "eval_samples_per_second": 2.477,
+      "eval_steps_per_second": 2.477,
+      "step": 800
+    },
+    {
+      "epoch": 0.3460625674217907,
+      "grad_norm": 1.6325052976608276,
+      "learning_rate": 7.196765498652292e-05,
+      "loss": 0.7561838626861572,
+      "step": 802
+    },
+    {
+      "epoch": 0.34692556634304206,
+      "grad_norm": 1.8044698238372803,
+      "learning_rate": 7.214734950584008e-05,
+      "loss": 0.7940152883529663,
+      "step": 804
+    },
+    {
+      "epoch": 0.3477885652642934,
+      "grad_norm": 1.4942690134048462,
+      "learning_rate": 7.232704402515723e-05,
+      "loss": 0.8002730011940002,
+      "step": 806
+    },
+    {
+      "epoch": 0.34865156418554477,
+      "grad_norm": 1.5209156274795532,
+      "learning_rate": 7.25067385444744e-05,
+      "loss": 0.8211291432380676,
+      "step": 808
+    },
+    {
+      "epoch": 0.34951456310679613,
+      "grad_norm": 1.662622094154358,
+      "learning_rate": 7.268643306379156e-05,
+      "loss": 0.8690080642700195,
+      "step": 810
+    },
+    {
+      "epoch": 0.3503775620280475,
+      "grad_norm": 1.4452823400497437,
+      "learning_rate": 7.286612758310873e-05,
+      "loss": 0.8259872794151306,
+      "step": 812
+    },
+    {
+      "epoch": 0.3512405609492988,
+      "grad_norm": 1.6030809879302979,
+      "learning_rate": 7.304582210242588e-05,
+      "loss": 0.7973082661628723,
+      "step": 814
+    },
+    {
+      "epoch": 0.35210355987055014,
+      "grad_norm": 1.5944641828536987,
+      "learning_rate": 7.322551662174304e-05,
+      "loss": 0.8258423805236816,
+      "step": 816
+    },
+    {
+      "epoch": 0.3529665587918015,
+      "grad_norm": 1.6284228563308716,
+      "learning_rate": 7.340521114106021e-05,
+      "loss": 0.8570499420166016,
+      "step": 818
+    },
+    {
+      "epoch": 0.35382955771305286,
+      "grad_norm": 1.399397373199463,
+      "learning_rate": 7.358490566037736e-05,
+      "loss": 0.7808573842048645,
+      "step": 820
+    },
+    {
+      "epoch": 0.3546925566343042,
+      "grad_norm": 1.6233313083648682,
+      "learning_rate": 7.376460017969452e-05,
+      "loss": 0.7514002323150635,
+      "step": 822
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 3.1610822677612305,
+      "learning_rate": 7.394429469901169e-05,
+      "loss": 0.8392049670219421,
+      "step": 824
+    },
+    {
+      "epoch": 0.3564185544768069,
+      "grad_norm": 1.5170103311538696,
+      "learning_rate": 7.412398921832885e-05,
+      "loss": 0.7574125528335571,
+      "step": 826
+    },
+    {
+      "epoch": 0.3572815533980582,
+      "grad_norm": 1.687654733657837,
+      "learning_rate": 7.4303683737646e-05,
+      "loss": 0.8394677639007568,
+      "step": 828
+    },
+    {
+      "epoch": 0.3581445523193096,
+      "grad_norm": 1.6306912899017334,
+      "learning_rate": 7.448337825696317e-05,
+      "loss": 0.7760812044143677,
+      "step": 830
+    },
+    {
+      "epoch": 0.35900755124056094,
+      "grad_norm": 1.4824501276016235,
+      "learning_rate": 7.466307277628034e-05,
+      "loss": 0.8146010041236877,
+      "step": 832
+    },
+    {
+      "epoch": 0.3598705501618123,
+      "grad_norm": 1.962728500366211,
+      "learning_rate": 7.484276729559749e-05,
+      "loss": 0.7824002504348755,
+      "step": 834
+    },
+    {
+      "epoch": 0.36073354908306365,
+      "grad_norm": 1.805561900138855,
+      "learning_rate": 7.502246181491465e-05,
+      "loss": 0.8955144882202148,
+      "step": 836
+    },
+    {
+      "epoch": 0.361596548004315,
+      "grad_norm": 1.6058090925216675,
+      "learning_rate": 7.52021563342318e-05,
+      "loss": 0.7638000249862671,
+      "step": 838
+    },
+    {
+      "epoch": 0.36245954692556637,
+      "grad_norm": 1.5326330661773682,
+      "learning_rate": 7.538185085354897e-05,
+      "loss": 0.8465489745140076,
+      "step": 840
+    },
+    {
+      "epoch": 0.36332254584681767,
+      "grad_norm": 1.563953161239624,
+      "learning_rate": 7.556154537286612e-05,
+      "loss": 0.7809846997261047,
+      "step": 842
+    },
+    {
+      "epoch": 0.364185544768069,
+      "grad_norm": 1.3842798471450806,
+      "learning_rate": 7.574123989218329e-05,
+      "loss": 0.7431546449661255,
+      "step": 844
+    },
+    {
+      "epoch": 0.3650485436893204,
+      "grad_norm": 1.843582272529602,
+      "learning_rate": 7.592093441150045e-05,
+      "loss": 0.8984674215316772,
+      "step": 846
+    },
+    {
+      "epoch": 0.36591154261057174,
+      "grad_norm": 1.7077877521514893,
+      "learning_rate": 7.610062893081762e-05,
+      "loss": 0.7809584736824036,
+      "step": 848
+    },
+    {
+      "epoch": 0.3667745415318231,
+      "grad_norm": 1.3528809547424316,
+      "learning_rate": 7.628032345013477e-05,
+      "loss": 0.7576664090156555,
+      "step": 850
+    },
+    {
+      "epoch": 0.36763754045307445,
+      "grad_norm": 1.4391332864761353,
+      "learning_rate": 7.646001796945193e-05,
+      "loss": 0.7666721940040588,
+      "step": 852
+    },
+    {
+      "epoch": 0.3685005393743258,
+      "grad_norm": 1.626839518547058,
+      "learning_rate": 7.66397124887691e-05,
+      "loss": 0.8356342911720276,
+      "step": 854
+    },
+    {
+      "epoch": 0.3693635382955771,
+      "grad_norm": 1.5550813674926758,
+      "learning_rate": 7.681940700808625e-05,
+      "loss": 0.7766274809837341,
+      "step": 856
+    },
+    {
+      "epoch": 0.37022653721682847,
+      "grad_norm": 1.4684302806854248,
+      "learning_rate": 7.699910152740341e-05,
+      "loss": 0.7646660804748535,
+      "step": 858
+    },
+    {
+      "epoch": 0.3710895361380798,
+      "grad_norm": 1.6446272134780884,
+      "learning_rate": 7.717879604672058e-05,
+      "loss": 0.8716844916343689,
+      "step": 860
+    },
+    {
+      "epoch": 0.3719525350593312,
+      "grad_norm": 1.5995690822601318,
+      "learning_rate": 7.735849056603774e-05,
+      "loss": 0.8561879992485046,
+      "step": 862
+    },
+    {
+      "epoch": 0.37281553398058254,
+      "grad_norm": 1.632079839706421,
+      "learning_rate": 7.75381850853549e-05,
+      "loss": 0.8795325756072998,
+      "step": 864
+    },
+    {
+      "epoch": 0.3736785329018339,
+      "grad_norm": 1.7169907093048096,
+      "learning_rate": 7.771787960467206e-05,
+      "loss": 0.8779821991920471,
+      "step": 866
+    },
+    {
+      "epoch": 0.3745415318230852,
+      "grad_norm": 1.8590933084487915,
+      "learning_rate": 7.789757412398922e-05,
+      "loss": 0.8811644911766052,
+      "step": 868
+    },
+    {
+      "epoch": 0.37540453074433655,
+      "grad_norm": 1.804978370666504,
+      "learning_rate": 7.807726864330638e-05,
+      "loss": 0.8391726016998291,
+      "step": 870
+    },
+    {
+      "epoch": 0.3762675296655879,
+      "grad_norm": 2.2929575443267822,
+      "learning_rate": 7.825696316262354e-05,
+      "loss": 0.8425854444503784,
+      "step": 872
+    },
+    {
+      "epoch": 0.37713052858683926,
+      "grad_norm": 1.551804780960083,
+      "learning_rate": 7.84366576819407e-05,
+      "loss": 0.8409838080406189,
+      "step": 874
+    },
+    {
+      "epoch": 0.3779935275080906,
+      "grad_norm": 1.4655314683914185,
+      "learning_rate": 7.861635220125787e-05,
+      "loss": 0.7441553473472595,
+      "step": 876
+    },
+    {
+      "epoch": 0.378856526429342,
+      "grad_norm": 1.7886772155761719,
+      "learning_rate": 7.879604672057502e-05,
+      "loss": 0.8850297331809998,
+      "step": 878
+    },
+    {
+      "epoch": 0.37971952535059333,
+      "grad_norm": 1.4744676351547241,
+      "learning_rate": 7.897574123989219e-05,
+      "loss": 0.7991185188293457,
+      "step": 880
+    },
+    {
+      "epoch": 0.38058252427184464,
+      "grad_norm": 1.6844931840896606,
+      "learning_rate": 7.915543575920935e-05,
+      "loss": 0.7903867363929749,
+      "step": 882
+    },
+    {
+      "epoch": 0.381445523193096,
+      "grad_norm": 1.674704909324646,
+      "learning_rate": 7.93351302785265e-05,
+      "loss": 0.812190592288971,
+      "step": 884
+    },
+    {
+      "epoch": 0.38230852211434735,
+      "grad_norm": 1.6548097133636475,
+      "learning_rate": 7.951482479784367e-05,
+      "loss": 0.781878650188446,
+      "step": 886
+    },
+    {
+      "epoch": 0.3831715210355987,
+      "grad_norm": 1.3750375509262085,
+      "learning_rate": 7.969451931716083e-05,
+      "loss": 0.8223106861114502,
+      "step": 888
+    },
+    {
+      "epoch": 0.38403451995685006,
+      "grad_norm": 1.42178475856781,
+      "learning_rate": 7.9874213836478e-05,
+      "loss": 0.7170665860176086,
+      "step": 890
+    },
+    {
+      "epoch": 0.3848975188781014,
+      "grad_norm": 1.7126129865646362,
+      "learning_rate": 8.005390835579515e-05,
+      "loss": 0.8533666133880615,
+      "step": 892
+    },
+    {
+      "epoch": 0.3857605177993528,
+      "grad_norm": 1.552474856376648,
+      "learning_rate": 8.023360287511232e-05,
+      "loss": 0.8799889087677002,
+      "step": 894
+    },
+    {
+      "epoch": 0.3866235167206041,
+      "grad_norm": 1.2612507343292236,
+      "learning_rate": 8.041329739442948e-05,
+      "loss": 0.7968940734863281,
+      "step": 896
+    },
+    {
+      "epoch": 0.38748651564185543,
+      "grad_norm": 1.4770987033843994,
+      "learning_rate": 8.059299191374663e-05,
+      "loss": 0.7910935282707214,
+      "step": 898
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 1.4640419483184814,
+      "learning_rate": 8.07726864330638e-05,
+      "loss": 0.7873474955558777,
+      "step": 900
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "eval_loss": 0.8351938128471375,
+      "eval_runtime": 823.5649,
+      "eval_samples_per_second": 2.501,
+      "eval_steps_per_second": 2.501,
+      "step": 900
+    },
+    {
+      "epoch": 0.38921251348435815,
+      "grad_norm": 1.3780814409255981,
+      "learning_rate": 8.095238095238096e-05,
+      "loss": 0.8183950185775757,
+      "step": 902
+    },
+    {
+      "epoch": 0.3900755124056095,
+      "grad_norm": 1.5895066261291504,
+      "learning_rate": 8.113207547169813e-05,
+      "loss": 0.786055326461792,
+      "step": 904
+    },
+    {
+      "epoch": 0.39093851132686086,
+      "grad_norm": 1.6340118646621704,
+      "learning_rate": 8.131176999101528e-05,
+      "loss": 0.8638336658477783,
+      "step": 906
+    },
+    {
+      "epoch": 0.3918015102481122,
+      "grad_norm": 1.3990486860275269,
+      "learning_rate": 8.149146451033244e-05,
+      "loss": 0.702790379524231,
+      "step": 908
+    },
+    {
+      "epoch": 0.3926645091693635,
+      "grad_norm": 1.3703010082244873,
+      "learning_rate": 8.167115902964961e-05,
+      "loss": 0.7845349907875061,
+      "step": 910
+    },
+    {
+      "epoch": 0.3935275080906149,
+      "grad_norm": 1.4194090366363525,
+      "learning_rate": 8.185085354896676e-05,
+      "loss": 0.8117155432701111,
+      "step": 912
+    },
+    {
+      "epoch": 0.39439050701186623,
+      "grad_norm": 1.4716848134994507,
+      "learning_rate": 8.203054806828392e-05,
+      "loss": 0.8229454755783081,
+      "step": 914
+    },
+    {
+      "epoch": 0.3952535059331176,
+      "grad_norm": 1.51328706741333,
+      "learning_rate": 8.221024258760108e-05,
+      "loss": 0.698765218257904,
+      "step": 916
+    },
+    {
+      "epoch": 0.39611650485436894,
+      "grad_norm": 1.4755173921585083,
+      "learning_rate": 8.238993710691824e-05,
+      "loss": 0.7694190144538879,
+      "step": 918
+    },
+    {
+      "epoch": 0.3969795037756203,
+      "grad_norm": 1.5302451848983765,
+      "learning_rate": 8.25696316262354e-05,
+      "loss": 0.779274046421051,
+      "step": 920
+    },
+    {
+      "epoch": 0.3978425026968716,
+      "grad_norm": 1.474968433380127,
+      "learning_rate": 8.274932614555256e-05,
+      "loss": 0.713699221611023,
+      "step": 922
+    },
+    {
+      "epoch": 0.39870550161812296,
+      "grad_norm": 1.4024375677108765,
+      "learning_rate": 8.292902066486972e-05,
+      "loss": 0.7869517803192139,
+      "step": 924
+    },
+    {
+      "epoch": 0.3995685005393743,
+      "grad_norm": 1.5729585886001587,
+      "learning_rate": 8.310871518418689e-05,
+      "loss": 0.9040259718894958,
+      "step": 926
+    },
+    {
+      "epoch": 0.4004314994606257,
+      "grad_norm": 1.609850525856018,
+      "learning_rate": 8.328840970350404e-05,
+      "loss": 0.7589567303657532,
+      "step": 928
+    },
+    {
+      "epoch": 0.40129449838187703,
+      "grad_norm": 1.778781533241272,
+      "learning_rate": 8.34681042228212e-05,
+      "loss": 0.8725809454917908,
+      "step": 930
+    },
+    {
+      "epoch": 0.4021574973031284,
+      "grad_norm": 1.6333881616592407,
+      "learning_rate": 8.364779874213837e-05,
+      "loss": 0.8280068039894104,
+      "step": 932
+    },
+    {
+      "epoch": 0.40302049622437974,
+      "grad_norm": 1.6444122791290283,
+      "learning_rate": 8.382749326145552e-05,
+      "loss": 0.8293300867080688,
+      "step": 934
+    },
+    {
+      "epoch": 0.40388349514563104,
+      "grad_norm": 1.2815860509872437,
+      "learning_rate": 8.400718778077269e-05,
+      "loss": 0.7628244161605835,
+      "step": 936
+    },
+    {
+      "epoch": 0.4047464940668824,
+      "grad_norm": 1.7849020957946777,
+      "learning_rate": 8.418688230008985e-05,
+      "loss": 0.8951035141944885,
+      "step": 938
+    },
+    {
+      "epoch": 0.40560949298813376,
+      "grad_norm": 1.800937294960022,
+      "learning_rate": 8.436657681940702e-05,
+      "loss": 0.7677619457244873,
+      "step": 940
+    },
+    {
+      "epoch": 0.4064724919093851,
+      "grad_norm": 1.5004104375839233,
+      "learning_rate": 8.454627133872417e-05,
+      "loss": 0.8553397059440613,
+      "step": 942
+    },
+    {
+      "epoch": 0.40733549083063647,
+      "grad_norm": 1.3399486541748047,
+      "learning_rate": 8.472596585804133e-05,
+      "loss": 0.7110850811004639,
+      "step": 944
+    },
+    {
+      "epoch": 0.4081984897518878,
+      "grad_norm": 1.8936012983322144,
+      "learning_rate": 8.49056603773585e-05,
+      "loss": 0.9379971623420715,
+      "step": 946
+    },
+    {
+      "epoch": 0.4090614886731392,
+      "grad_norm": 1.2648893594741821,
+      "learning_rate": 8.508535489667565e-05,
+      "loss": 0.7492738366127014,
+      "step": 948
+    },
+    {
+      "epoch": 0.4099244875943905,
+      "grad_norm": 1.5587494373321533,
+      "learning_rate": 8.526504941599281e-05,
+      "loss": 0.7922301292419434,
+      "step": 950
+    },
+    {
+      "epoch": 0.41078748651564184,
+      "grad_norm": 1.5042990446090698,
+      "learning_rate": 8.544474393530998e-05,
+      "loss": 0.7494275569915771,
+      "step": 952
+    },
+    {
+      "epoch": 0.4116504854368932,
+      "grad_norm": 1.4338537454605103,
+      "learning_rate": 8.562443845462714e-05,
+      "loss": 0.7983633279800415,
+      "step": 954
+    },
+    {
+      "epoch": 0.41251348435814456,
+      "grad_norm": 1.6135673522949219,
+      "learning_rate": 8.58041329739443e-05,
+      "loss": 0.813288152217865,
+      "step": 956
+    },
+    {
+      "epoch": 0.4133764832793959,
+      "grad_norm": 1.3761460781097412,
+      "learning_rate": 8.598382749326146e-05,
+      "loss": 0.7794904708862305,
+      "step": 958
+    },
+    {
+      "epoch": 0.41423948220064727,
+      "grad_norm": 1.51504385471344,
+      "learning_rate": 8.616352201257863e-05,
+      "loss": 0.7544562816619873,
+      "step": 960
+    },
+    {
+      "epoch": 0.41510248112189857,
+      "grad_norm": 1.3698909282684326,
+      "learning_rate": 8.634321653189578e-05,
+      "loss": 0.8151395916938782,
+      "step": 962
+    },
+    {
+      "epoch": 0.4159654800431499,
+      "grad_norm": 1.5509650707244873,
+      "learning_rate": 8.652291105121294e-05,
+      "loss": 0.7997464537620544,
+      "step": 964
+    },
+    {
+      "epoch": 0.4168284789644013,
+      "grad_norm": 1.2967383861541748,
+      "learning_rate": 8.67026055705301e-05,
+      "loss": 0.767808735370636,
+      "step": 966
+    },
+    {
+      "epoch": 0.41769147788565264,
+      "grad_norm": 1.2444552183151245,
+      "learning_rate": 8.688230008984727e-05,
+      "loss": 0.7537208795547485,
+      "step": 968
+    },
+    {
+      "epoch": 0.418554476806904,
+      "grad_norm": 1.4390850067138672,
+      "learning_rate": 8.706199460916442e-05,
+      "loss": 0.7796021103858948,
+      "step": 970
+    },
+    {
+      "epoch": 0.41941747572815535,
+      "grad_norm": 1.4822322130203247,
+      "learning_rate": 8.724168912848159e-05,
+      "loss": 0.7812987565994263,
+      "step": 972
+    },
+    {
+      "epoch": 0.4202804746494067,
+      "grad_norm": 1.3770837783813477,
+      "learning_rate": 8.742138364779875e-05,
+      "loss": 0.7396363019943237,
+      "step": 974
+    },
+    {
+      "epoch": 0.421143473570658,
+      "grad_norm": 1.5534236431121826,
+      "learning_rate": 8.76010781671159e-05,
+      "loss": 0.8390982151031494,
+      "step": 976
+    },
+    {
+      "epoch": 0.42200647249190937,
+      "grad_norm": 1.5428354740142822,
+      "learning_rate": 8.778077268643307e-05,
+      "loss": 0.8368987441062927,
+      "step": 978
+    },
+    {
+      "epoch": 0.4228694714131607,
+      "grad_norm": 1.3579497337341309,
+      "learning_rate": 8.796046720575023e-05,
+      "loss": 0.8203011155128479,
+      "step": 980
+    },
+    {
+      "epoch": 0.4237324703344121,
+      "grad_norm": 1.5543184280395508,
+      "learning_rate": 8.81401617250674e-05,
+      "loss": 0.7622520923614502,
+      "step": 982
+    },
+    {
+      "epoch": 0.42459546925566344,
+      "grad_norm": 1.5728850364685059,
+      "learning_rate": 8.831985624438455e-05,
+      "loss": 0.7764845490455627,
+      "step": 984
+    },
+    {
+      "epoch": 0.4254584681769148,
+      "grad_norm": 1.5842933654785156,
+      "learning_rate": 8.849955076370172e-05,
+      "loss": 0.8136081099510193,
+      "step": 986
+    },
+    {
+      "epoch": 0.42632146709816615,
+      "grad_norm": 1.5721858739852905,
+      "learning_rate": 8.867924528301888e-05,
+      "loss": 0.8388259410858154,
+      "step": 988
+    },
+    {
+      "epoch": 0.42718446601941745,
+      "grad_norm": 1.6682584285736084,
+      "learning_rate": 8.885893980233603e-05,
+      "loss": 0.8829372525215149,
+      "step": 990
+    },
+    {
+      "epoch": 0.4280474649406688,
+      "grad_norm": 1.7098870277404785,
+      "learning_rate": 8.90386343216532e-05,
+      "loss": 0.8545100688934326,
+      "step": 992
+    },
+    {
+      "epoch": 0.42891046386192017,
+      "grad_norm": 1.5161751508712769,
+      "learning_rate": 8.921832884097035e-05,
+      "loss": 0.8233623504638672,
+      "step": 994
+    },
+    {
+      "epoch": 0.4297734627831715,
+      "grad_norm": 1.457794189453125,
+      "learning_rate": 8.939802336028751e-05,
+      "loss": 0.7576998472213745,
+      "step": 996
+    },
+    {
+      "epoch": 0.4306364617044229,
+      "grad_norm": 1.6383825540542603,
+      "learning_rate": 8.957771787960468e-05,
+      "loss": 0.8089564442634583,
+      "step": 998
+    },
+    {
+      "epoch": 0.43149946062567424,
+      "grad_norm": 1.4149754047393799,
+      "learning_rate": 8.975741239892183e-05,
+      "loss": 0.7791779637336731,
+      "step": 1000
+    },
+    {
+      "epoch": 0.43149946062567424,
+      "eval_loss": 0.8266019821166992,
+      "eval_runtime": 835.0044,
+      "eval_samples_per_second": 2.467,
+      "eval_steps_per_second": 2.467,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 13908,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "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": 1.0412690692397507e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

sft_devstral_24B/checkpoints/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67cec3db40d9b4bcc81f7a80aeef5218639d2e42b1c9e2f551945abddeb1ff4d
+size 5201

sft_devstral_24B/checkpoints/checkpoint-1500/README.md

@@ -0,0 +1,207 @@
+---
+base_model: CPT/runs/cpt_run_v1/merged_24b_cpt_lora
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:CPT/runs/cpt_run_v1/merged_24b_cpt_lora
+- 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/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": "CPT/runs/cpt_run_v1/merged_24b_cpt_lora",
+  "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",
+    "k_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

sft_devstral_24B/checkpoints/checkpoint-1500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20fd579a68196fbf4f469c8f239ce89f433a5edc4747b2e6061e6ba08299082c
+size 45690960

sft_devstral_24B/checkpoints/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0eed4f313d3dc98c58cb77b09f35e4f0561e4ef87cc09b34da341b229d42dc7
+size 78912907

sft_devstral_24B/checkpoints/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4655532fe7fb62f39c418f0d96c32a9b86cae1ff752e2a984ec0fc714cf3c30
+size 14645

sft_devstral_24B/checkpoints/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32e80aa3f12daa32611e34f457685e6959d7a8561803cf45e2d67dae6fd24c81
+size 1465

sft_devstral_24B/checkpoints/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67cec3db40d9b4bcc81f7a80aeef5218639d2e42b1c9e2f551945abddeb1ff4d
+size 5201

sft_devstral_24B/checkpoints/checkpoint-2000/README.md

@@ -0,0 +1,207 @@
+---
+base_model: CPT/runs/cpt_run_v1/merged_24b_cpt_lora
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:CPT/runs/cpt_run_v1/merged_24b_cpt_lora
+- 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/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": "CPT/runs/cpt_run_v1/merged_24b_cpt_lora",
+  "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",
+    "k_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

sft_devstral_24B/checkpoints/checkpoint-2000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:225825667e56783844ed24014e00a49b1af502ff61db12a0b15f467261ca070a
+size 45690960

sft_devstral_24B/checkpoints/checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1a5e7f450f3d05374406f39347483741e5ea3c9643beba9b397429a88c41c4c
+size 78912907

sft_devstral_24B/checkpoints/checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01e13f651f318fbe600e3a90939a92c9240e80e5bb9954f55c343c0abfb99e48
+size 14645

sft_devstral_24B/checkpoints/checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4207b23446848036378cf48f5d44035986145025a9cf3c265ffcfe1a8e01a20d
+size 1465

sft_devstral_24B/checkpoints/checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67cec3db40d9b4bcc81f7a80aeef5218639d2e42b1c9e2f551945abddeb1ff4d
+size 5201

sft_devstral_24B/checkpoints/checkpoint-2500/README.md

@@ -0,0 +1,207 @@
+---
+base_model: CPT/runs/cpt_run_v1/merged_24b_cpt_lora
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:CPT/runs/cpt_run_v1/merged_24b_cpt_lora
+- 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/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": "CPT/runs/cpt_run_v1/merged_24b_cpt_lora",
+  "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",
+    "k_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

sft_devstral_24B/checkpoints/checkpoint-2500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6662a9047a1361809c0185e7b56691647d652fb4382248cd93082d3d414cccb4
+size 45690960

sft_devstral_24B/checkpoints/checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e94c2bbf28c8c1a731dfa40610e905a42511196ee74c7ba0e4172c06c06eb1d2
+size 78912907

sft_devstral_24B/checkpoints/checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07b985c4a415c8b2261a9cb466d19c38f17bfc709c9097c70384d541f09c4622
+size 14645

sft_devstral_24B/checkpoints/checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e6c35cfc5291bd34cd8a1e5ad2eb46c14099936b3b296d64c77317879166e9d
+size 1465

sft_devstral_24B/checkpoints/checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67cec3db40d9b4bcc81f7a80aeef5218639d2e42b1c9e2f551945abddeb1ff4d
+size 5201

sft_devstral_24B/checkpoints/checkpoint-3000/README.md

@@ -0,0 +1,207 @@
+---
+base_model: CPT/runs/cpt_run_v1/merged_24b_cpt_lora
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:CPT/runs/cpt_run_v1/merged_24b_cpt_lora
+- 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/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": "CPT/runs/cpt_run_v1/merged_24b_cpt_lora",
+  "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",
+    "k_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

sft_devstral_24B/checkpoints/checkpoint-3000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c65bd77c337a84a22331e5bd51cae1ec67e256cc5aa979340e08d04ed1698f42
+size 45690960

sft_devstral_24B/checkpoints/checkpoint-3000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdbb0fa9f482cc96353567c4495b179ffe630b391696a98582d4f48909ae95c9
+size 78912907

sft_devstral_24B/checkpoints/checkpoint-3000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fca7fac4d0a11bc61b7275b19317a4ac989211962bde4cc5c60457d1857a0d66
+size 14645

sft_devstral_24B/checkpoints/checkpoint-3000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43b30e8668249f758637a580360e1d462fc9a0aaee4f333dc3ff507e3a0646c0
+size 1465

sft_devstral_24B/checkpoints/checkpoint-3000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67cec3db40d9b4bcc81f7a80aeef5218639d2e42b1c9e2f551945abddeb1ff4d
+size 5201

sft_devstral_24B/checkpoints/checkpoint-3500/README.md

@@ -0,0 +1,207 @@
+---
+base_model: CPT/runs/cpt_run_v1/merged_24b_cpt_lora
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:CPT/runs/cpt_run_v1/merged_24b_cpt_lora
+- 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/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": "CPT/runs/cpt_run_v1/merged_24b_cpt_lora",
+  "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",
+    "k_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

sft_devstral_24B/checkpoints/checkpoint-3500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed4f0946d7554d2eb8dc25ff656bda1bc499858c3b08b2d09e9b3c13e41ad4b8
+size 45690960

sft_devstral_24B/checkpoints/checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:339367ba5676b49a084955aff2688d0f4f258b3db053f8a02ce2b85942acedcf
+size 78912907

sft_devstral_24B/checkpoints/checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecad9507556708b06aaa4af823c254c9618f43d9383dcf7f8d3563bdd2adf264
+size 14645