Upload 41 files

fen_adapters_logs/logs_fen/events.out.tfevents.1727448092.luciano-X570-AORUS-PRO.1242309.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72882d87317277167697088849f166fdb49306447196758a92b14794c8fc0b7b
+size 9614

fen_adapters_logs/logs_fen/events.out.tfevents.1727456570.luciano-X570-AORUS-PRO.1312456.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43d8e2731a7fec4ad2df5b96adc35abc2c8c6a99031f50d969ac174026d5229e
+size 5402

fen_adapters_logs/logs_fen/events.out.tfevents.1727456638.luciano-X570-AORUS-PRO.1313041.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:482a8ef44366641582076a0580ee5ac48b400ffc746f1b0ff69b10e8400e2b7d
+size 10255

fen_adapters_logs/mistral_fen-tesis/checkpoint-1000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.1.dev0

fen_adapters_logs/mistral_fen-tesis/checkpoint-1000/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

fen_adapters_logs/mistral_fen-tesis/checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a33277254624fd8f15cf54c089491bfbe512e8bd178332409e2a35567940142
+size 218138576

fen_adapters_logs/mistral_fen-tesis/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c125ead80b51adf9a91e6a436f7b3c75b5b3d8c7077d0ca4061cb484c9706da
+size 436423418

fen_adapters_logs/mistral_fen-tesis/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e01e8deb2c6bb82e1669fc06acdfe9313aeb3ad0a5e11b9a664ea9af12e3985f
+size 14244

fen_adapters_logs/mistral_fen-tesis/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:539e95dcaa5fcbdc4b6b5b5f16704295f61a2b9b4b747ffc2864d4d7e2ba43a7
+size 1064

fen_adapters_logs/mistral_fen-tesis/checkpoint-1000/trainer_state.json

@@ -0,0 +1,173 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.07581213752321747,
+  "eval_steps": 50,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003790606876160873,
+      "grad_norm": 1.120240569114685,
+      "learning_rate": 5e-06,
+      "loss": 1.8474,
+      "step": 50
+    },
+    {
+      "epoch": 0.007581213752321746,
+      "grad_norm": 0.47613927721977234,
+      "learning_rate": 1e-05,
+      "loss": 1.0973,
+      "step": 100
+    },
+    {
+      "epoch": 0.01137182062848262,
+      "grad_norm": 0.22726468741893768,
+      "learning_rate": 9.961802902979374e-06,
+      "loss": 0.6019,
+      "step": 150
+    },
+    {
+      "epoch": 0.015162427504643493,
+      "grad_norm": 0.20584619045257568,
+      "learning_rate": 9.923605805958749e-06,
+      "loss": 0.5349,
+      "step": 200
+    },
+    {
+      "epoch": 0.018953034380804368,
+      "grad_norm": 0.2079986035823822,
+      "learning_rate": 9.88540870893812e-06,
+      "loss": 0.5193,
+      "step": 250
+    },
+    {
+      "epoch": 0.02274364125696524,
+      "grad_norm": 0.2402341067790985,
+      "learning_rate": 9.847211611917495e-06,
+      "loss": 0.503,
+      "step": 300
+    },
+    {
+      "epoch": 0.026534248133126114,
+      "grad_norm": 0.27408909797668457,
+      "learning_rate": 9.809014514896868e-06,
+      "loss": 0.4987,
+      "step": 350
+    },
+    {
+      "epoch": 0.030324855009286986,
+      "grad_norm": 0.26979872584342957,
+      "learning_rate": 9.770817417876243e-06,
+      "loss": 0.4907,
+      "step": 400
+    },
+    {
+      "epoch": 0.03411546188544786,
+      "grad_norm": 0.2925889790058136,
+      "learning_rate": 9.732620320855617e-06,
+      "loss": 0.4864,
+      "step": 450
+    },
+    {
+      "epoch": 0.037906068761608736,
+      "grad_norm": 0.29512152075767517,
+      "learning_rate": 9.694423223834988e-06,
+      "loss": 0.4816,
+      "step": 500
+    },
+    {
+      "epoch": 0.041696675637769604,
+      "grad_norm": 0.3120884895324707,
+      "learning_rate": 9.656226126814363e-06,
+      "loss": 0.4771,
+      "step": 550
+    },
+    {
+      "epoch": 0.04548728251393048,
+      "grad_norm": 0.4351954758167267,
+      "learning_rate": 9.618029029793736e-06,
+      "loss": 0.4784,
+      "step": 600
+    },
+    {
+      "epoch": 0.04927788939009135,
+      "grad_norm": 0.488045334815979,
+      "learning_rate": 9.579831932773111e-06,
+      "loss": 0.4714,
+      "step": 650
+    },
+    {
+      "epoch": 0.05306849626625223,
+      "grad_norm": 0.3738720417022705,
+      "learning_rate": 9.541634835752484e-06,
+      "loss": 0.4723,
+      "step": 700
+    },
+    {
+      "epoch": 0.0568591031424131,
+      "grad_norm": 0.431723028421402,
+      "learning_rate": 9.503437738731857e-06,
+      "loss": 0.4657,
+      "step": 750
+    },
+    {
+      "epoch": 0.06064971001857397,
+      "grad_norm": 0.4855528771877289,
+      "learning_rate": 9.46524064171123e-06,
+      "loss": 0.4643,
+      "step": 800
+    },
+    {
+      "epoch": 0.06444031689473485,
+      "grad_norm": 0.6066440939903259,
+      "learning_rate": 9.427043544690604e-06,
+      "loss": 0.4645,
+      "step": 850
+    },
+    {
+      "epoch": 0.06823092377089572,
+      "grad_norm": 0.35919123888015747,
+      "learning_rate": 9.388846447669979e-06,
+      "loss": 0.4569,
+      "step": 900
+    },
+    {
+      "epoch": 0.07202153064705659,
+      "grad_norm": 0.5809701085090637,
+      "learning_rate": 9.350649350649352e-06,
+      "loss": 0.4488,
+      "step": 950
+    },
+    {
+      "epoch": 0.07581213752321747,
+      "grad_norm": 0.48724591732025146,
+      "learning_rate": 9.312452253628725e-06,
+      "loss": 0.4393,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 13190,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.784879177728e+17,
+  "train_batch_size": 11,
+  "trial_name": null,
+  "trial_params": null
+}

fen_adapters_logs/mistral_fen-tesis/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b583ff1d09cb40f962e453e09541e41d6a26dc7502b68dbdc9f13bb2fc11eb
+size 5176

fen_adapters_logs/mistral_fen-tesis/checkpoint-2000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.1.dev0

fen_adapters_logs/mistral_fen-tesis/checkpoint-2000/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

fen_adapters_logs/mistral_fen-tesis/checkpoint-2000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0de19c8472ed8258cf4ab7fbb7ac12df8cbceec4726ab927b08ef290f009a18c
+size 218138576

fen_adapters_logs/mistral_fen-tesis/checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2bd192e13460b98d9d4602f4ece8928a49f61ec30fb1dd02fd5bdfbbf0ca31d
+size 436423418

fen_adapters_logs/mistral_fen-tesis/checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba9d57b70a2f602fac466d464677e2d358de1ad2ff28fdb5f57132b76ba7b6e
+size 14244

fen_adapters_logs/mistral_fen-tesis/checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:606305bca808e34fa94de6341a1e93b3ecc076ed59b95df5abac6d5fe9d70f8f
+size 1064

fen_adapters_logs/mistral_fen-tesis/checkpoint-2000/trainer_state.json

@@ -0,0 +1,313 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.15162427504643494,
+  "eval_steps": 50,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003790606876160873,
+      "grad_norm": 1.120240569114685,
+      "learning_rate": 5e-06,
+      "loss": 1.8474,
+      "step": 50
+    },
+    {
+      "epoch": 0.007581213752321746,
+      "grad_norm": 0.47613927721977234,
+      "learning_rate": 1e-05,
+      "loss": 1.0973,
+      "step": 100
+    },
+    {
+      "epoch": 0.01137182062848262,
+      "grad_norm": 0.22726468741893768,
+      "learning_rate": 9.961802902979374e-06,
+      "loss": 0.6019,
+      "step": 150
+    },
+    {
+      "epoch": 0.015162427504643493,
+      "grad_norm": 0.20584619045257568,
+      "learning_rate": 9.923605805958749e-06,
+      "loss": 0.5349,
+      "step": 200
+    },
+    {
+      "epoch": 0.018953034380804368,
+      "grad_norm": 0.2079986035823822,
+      "learning_rate": 9.88540870893812e-06,
+      "loss": 0.5193,
+      "step": 250
+    },
+    {
+      "epoch": 0.02274364125696524,
+      "grad_norm": 0.2402341067790985,
+      "learning_rate": 9.847211611917495e-06,
+      "loss": 0.503,
+      "step": 300
+    },
+    {
+      "epoch": 0.026534248133126114,
+      "grad_norm": 0.27408909797668457,
+      "learning_rate": 9.809014514896868e-06,
+      "loss": 0.4987,
+      "step": 350
+    },
+    {
+      "epoch": 0.030324855009286986,
+      "grad_norm": 0.26979872584342957,
+      "learning_rate": 9.770817417876243e-06,
+      "loss": 0.4907,
+      "step": 400
+    },
+    {
+      "epoch": 0.03411546188544786,
+      "grad_norm": 0.2925889790058136,
+      "learning_rate": 9.732620320855617e-06,
+      "loss": 0.4864,
+      "step": 450
+    },
+    {
+      "epoch": 0.037906068761608736,
+      "grad_norm": 0.29512152075767517,
+      "learning_rate": 9.694423223834988e-06,
+      "loss": 0.4816,
+      "step": 500
+    },
+    {
+      "epoch": 0.041696675637769604,
+      "grad_norm": 0.3120884895324707,
+      "learning_rate": 9.656226126814363e-06,
+      "loss": 0.4771,
+      "step": 550
+    },
+    {
+      "epoch": 0.04548728251393048,
+      "grad_norm": 0.4351954758167267,
+      "learning_rate": 9.618029029793736e-06,
+      "loss": 0.4784,
+      "step": 600
+    },
+    {
+      "epoch": 0.04927788939009135,
+      "grad_norm": 0.488045334815979,
+      "learning_rate": 9.579831932773111e-06,
+      "loss": 0.4714,
+      "step": 650
+    },
+    {
+      "epoch": 0.05306849626625223,
+      "grad_norm": 0.3738720417022705,
+      "learning_rate": 9.541634835752484e-06,
+      "loss": 0.4723,
+      "step": 700
+    },
+    {
+      "epoch": 0.0568591031424131,
+      "grad_norm": 0.431723028421402,
+      "learning_rate": 9.503437738731857e-06,
+      "loss": 0.4657,
+      "step": 750
+    },
+    {
+      "epoch": 0.06064971001857397,
+      "grad_norm": 0.4855528771877289,
+      "learning_rate": 9.46524064171123e-06,
+      "loss": 0.4643,
+      "step": 800
+    },
+    {
+      "epoch": 0.06444031689473485,
+      "grad_norm": 0.6066440939903259,
+      "learning_rate": 9.427043544690604e-06,
+      "loss": 0.4645,
+      "step": 850
+    },
+    {
+      "epoch": 0.06823092377089572,
+      "grad_norm": 0.35919123888015747,
+      "learning_rate": 9.388846447669979e-06,
+      "loss": 0.4569,
+      "step": 900
+    },
+    {
+      "epoch": 0.07202153064705659,
+      "grad_norm": 0.5809701085090637,
+      "learning_rate": 9.350649350649352e-06,
+      "loss": 0.4488,
+      "step": 950
+    },
+    {
+      "epoch": 0.07581213752321747,
+      "grad_norm": 0.48724591732025146,
+      "learning_rate": 9.312452253628725e-06,
+      "loss": 0.4393,
+      "step": 1000
+    },
+    {
+      "epoch": 0.07960274439937834,
+      "grad_norm": 0.49501094222068787,
+      "learning_rate": 9.274255156608098e-06,
+      "loss": 0.4243,
+      "step": 1050
+    },
+    {
+      "epoch": 0.08339335127553921,
+      "grad_norm": 0.5313548445701599,
+      "learning_rate": 9.236058059587472e-06,
+      "loss": 0.4175,
+      "step": 1100
+    },
+    {
+      "epoch": 0.08718395815170009,
+      "grad_norm": 0.45100048184394836,
+      "learning_rate": 9.197860962566846e-06,
+      "loss": 0.4192,
+      "step": 1150
+    },
+    {
+      "epoch": 0.09097456502786096,
+      "grad_norm": 0.5094875693321228,
+      "learning_rate": 9.15966386554622e-06,
+      "loss": 0.4187,
+      "step": 1200
+    },
+    {
+      "epoch": 0.09476517190402184,
+      "grad_norm": 0.5597788095474243,
+      "learning_rate": 9.121466768525593e-06,
+      "loss": 0.4159,
+      "step": 1250
+    },
+    {
+      "epoch": 0.0985557787801827,
+      "grad_norm": 0.5827580690383911,
+      "learning_rate": 9.083269671504966e-06,
+      "loss": 0.4138,
+      "step": 1300
+    },
+    {
+      "epoch": 0.10234638565634357,
+      "grad_norm": 0.5637363791465759,
+      "learning_rate": 9.045072574484341e-06,
+      "loss": 0.4146,
+      "step": 1350
+    },
+    {
+      "epoch": 0.10613699253250446,
+      "grad_norm": 0.5267833471298218,
+      "learning_rate": 9.006875477463714e-06,
+      "loss": 0.4165,
+      "step": 1400
+    },
+    {
+      "epoch": 0.10992759940866532,
+      "grad_norm": 0.5389272570610046,
+      "learning_rate": 8.968678380443087e-06,
+      "loss": 0.4131,
+      "step": 1450
+    },
+    {
+      "epoch": 0.1137182062848262,
+      "grad_norm": 0.5248345732688904,
+      "learning_rate": 8.93048128342246e-06,
+      "loss": 0.4092,
+      "step": 1500
+    },
+    {
+      "epoch": 0.11750881316098707,
+      "grad_norm": 0.7177453637123108,
+      "learning_rate": 8.892284186401834e-06,
+      "loss": 0.4112,
+      "step": 1550
+    },
+    {
+      "epoch": 0.12129942003714794,
+      "grad_norm": 0.6109983325004578,
+      "learning_rate": 8.854087089381209e-06,
+      "loss": 0.41,
+      "step": 1600
+    },
+    {
+      "epoch": 0.1250900269133088,
+      "grad_norm": 0.489970862865448,
+      "learning_rate": 8.815889992360582e-06,
+      "loss": 0.4117,
+      "step": 1650
+    },
+    {
+      "epoch": 0.1288806337894697,
+      "grad_norm": 0.7458899021148682,
+      "learning_rate": 8.777692895339955e-06,
+      "loss": 0.4081,
+      "step": 1700
+    },
+    {
+      "epoch": 0.13267124066563057,
+      "grad_norm": 0.5596422553062439,
+      "learning_rate": 8.739495798319328e-06,
+      "loss": 0.41,
+      "step": 1750
+    },
+    {
+      "epoch": 0.13646184754179144,
+      "grad_norm": 0.5963002443313599,
+      "learning_rate": 8.701298701298701e-06,
+      "loss": 0.4048,
+      "step": 1800
+    },
+    {
+      "epoch": 0.1402524544179523,
+      "grad_norm": 0.6996163725852966,
+      "learning_rate": 8.663101604278076e-06,
+      "loss": 0.4071,
+      "step": 1850
+    },
+    {
+      "epoch": 0.14404306129411318,
+      "grad_norm": 0.660916805267334,
+      "learning_rate": 8.62490450725745e-06,
+      "loss": 0.4067,
+      "step": 1900
+    },
+    {
+      "epoch": 0.14783366817027407,
+      "grad_norm": 0.5360804200172424,
+      "learning_rate": 8.586707410236823e-06,
+      "loss": 0.403,
+      "step": 1950
+    },
+    {
+      "epoch": 0.15162427504643494,
+      "grad_norm": 0.5994951128959656,
+      "learning_rate": 8.548510313216196e-06,
+      "loss": 0.4058,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 13190,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.569758355456e+17,
+  "train_batch_size": 11,
+  "trial_name": null,
+  "trial_params": null
+}

fen_adapters_logs/mistral_fen-tesis/checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d67c7461315a01dcb4e8625f816f5573c7160a2d4c102a6f9fa82c82ecad1565
+size 5176

pgn_adapter_logs/logs_pgn/events.out.tfevents.1727469486.luciano-X570-AORUS-PRO.1400664.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2102caf2148b87d0e1f90ecfa21554e960d2d8a547b38d6c72c6942419f7f176
+size 5404

pgn_adapter_logs/logs_pgn/events.out.tfevents.1727469564.luciano-X570-AORUS-PRO.1410416.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddf3cbc52d72b33434bd7ba58724988a5bc6d6cef25852e12675cd1e1c53e75b
+size 5404

pgn_adapter_logs/logs_pgn/events.out.tfevents.1727470864.luciano-X570-AORUS-PRO.1414681.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f2c49b661a54a363c37ca02dd64870868477ec371e39a9a2690237a1a6d73b2
+size 5402

pgn_adapter_logs/logs_pgn/events.out.tfevents.1727470915.luciano-X570-AORUS-PRO.1420462.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6af452099478ad24c241643f60e04c5dbc84626efbcf93e6c732727bca7f459e
+size 5402

pgn_adapter_logs/logs_pgn/events.out.tfevents.1727470959.luciano-X570-AORUS-PRO.1420886.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1fea0b5ac83423af103e88bb2253aea6af90ecccedaa6b00ab490105924fdba
+size 5402

pgn_adapter_logs/logs_pgn/events.out.tfevents.1727471011.luciano-X570-AORUS-PRO.1421356.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eff5dc0c2fc5b95cc2452e09ee534ab539e976a0ed1b9500df8dd5b4849418d0
+size 47554

pgn_adapter_logs/mistral_pgn-tesis/checkpoint-1000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.1.dev0

pgn_adapter_logs/mistral_pgn-tesis/checkpoint-1000/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

pgn_adapter_logs/mistral_pgn-tesis/checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21ad3338e8007286ee97e49989f7ad31c5f32eebc50c8ce4afbe1a0eff953e37
+size 218138576

pgn_adapter_logs/mistral_pgn-tesis/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:310e34d569f3d490f3e027d7b31a0992dbe89dbc7b5ab38b85ef28110f7c3f39
+size 436423418

pgn_adapter_logs/mistral_pgn-tesis/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3853c20d376e2b88e9ebb9fcbf407986e565b15059669a9970bbd22505f9e8d1
+size 14244

pgn_adapter_logs/mistral_pgn-tesis/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5306b4a45e5c49e3aec157d2a6192cb1f314a75f82af5634f7b8749084a9e64e
+size 1064

pgn_adapter_logs/mistral_pgn-tesis/checkpoint-1000/trainer_state.json

@@ -0,0 +1,733 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.06810017535795154,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0006810017535795155,
+      "grad_norm": 0.8741451501846313,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.2903,
+      "step": 10
+    },
+    {
+      "epoch": 0.001362003507159031,
+      "grad_norm": 0.8342441320419312,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.2919,
+      "step": 20
+    },
+    {
+      "epoch": 0.0020430052607385463,
+      "grad_norm": 0.7483816742897034,
+      "learning_rate": 3e-06,
+      "loss": 1.2438,
+      "step": 30
+    },
+    {
+      "epoch": 0.002724007014318062,
+      "grad_norm": 0.7297427654266357,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.2199,
+      "step": 40
+    },
+    {
+      "epoch": 0.0034050087678975773,
+      "grad_norm": 0.7647419571876526,
+      "learning_rate": 5e-06,
+      "loss": 1.1631,
+      "step": 50
+    },
+    {
+      "epoch": 0.004086010521477093,
+      "grad_norm": 0.4680333137512207,
+      "learning_rate": 6e-06,
+      "loss": 1.1049,
+      "step": 60
+    },
+    {
+      "epoch": 0.004767012275056608,
+      "grad_norm": 0.39699047803878784,
+      "learning_rate": 7e-06,
+      "loss": 1.0397,
+      "step": 70
+    },
+    {
+      "epoch": 0.005448014028636124,
+      "grad_norm": 0.4081316888332367,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.9872,
+      "step": 80
+    },
+    {
+      "epoch": 0.006129015782215639,
+      "grad_norm": 0.4579920470714569,
+      "learning_rate": 9e-06,
+      "loss": 0.9204,
+      "step": 90
+    },
+    {
+      "epoch": 0.006810017535795155,
+      "grad_norm": 0.37478742003440857,
+      "learning_rate": 1e-05,
+      "loss": 0.851,
+      "step": 100
+    },
+    {
+      "epoch": 0.00749101928937467,
+      "grad_norm": 0.2919694483280182,
+      "learning_rate": 9.993143170597916e-06,
+      "loss": 0.792,
+      "step": 110
+    },
+    {
+      "epoch": 0.008172021042954185,
+      "grad_norm": 0.254935622215271,
+      "learning_rate": 9.986286341195831e-06,
+      "loss": 0.7643,
+      "step": 120
+    },
+    {
+      "epoch": 0.0088530227965337,
+      "grad_norm": 0.250884473323822,
+      "learning_rate": 9.979429511793748e-06,
+      "loss": 0.7607,
+      "step": 130
+    },
+    {
+      "epoch": 0.009534024550113216,
+      "grad_norm": 0.2979223132133484,
+      "learning_rate": 9.972572682391662e-06,
+      "loss": 0.7365,
+      "step": 140
+    },
+    {
+      "epoch": 0.010215026303692733,
+      "grad_norm": 0.2718585431575775,
+      "learning_rate": 9.965715852989579e-06,
+      "loss": 0.7156,
+      "step": 150
+    },
+    {
+      "epoch": 0.010896028057272248,
+      "grad_norm": 0.23914478719234467,
+      "learning_rate": 9.958859023587494e-06,
+      "loss": 0.7123,
+      "step": 160
+    },
+    {
+      "epoch": 0.011577029810851763,
+      "grad_norm": 0.24752002954483032,
+      "learning_rate": 9.95200219418541e-06,
+      "loss": 0.6997,
+      "step": 170
+    },
+    {
+      "epoch": 0.012258031564431279,
+      "grad_norm": 0.2361425906419754,
+      "learning_rate": 9.945145364783325e-06,
+      "loss": 0.702,
+      "step": 180
+    },
+    {
+      "epoch": 0.012939033318010794,
+      "grad_norm": 0.23137520253658295,
+      "learning_rate": 9.93828853538124e-06,
+      "loss": 0.7056,
+      "step": 190
+    },
+    {
+      "epoch": 0.01362003507159031,
+      "grad_norm": 0.2404152899980545,
+      "learning_rate": 9.931431705979157e-06,
+      "loss": 0.7005,
+      "step": 200
+    },
+    {
+      "epoch": 0.014301036825169824,
+      "grad_norm": 0.2881813943386078,
+      "learning_rate": 9.92457487657707e-06,
+      "loss": 0.7023,
+      "step": 210
+    },
+    {
+      "epoch": 0.01498203857874934,
+      "grad_norm": 0.2458052635192871,
+      "learning_rate": 9.917718047174988e-06,
+      "loss": 0.7014,
+      "step": 220
+    },
+    {
+      "epoch": 0.015663040332328855,
+      "grad_norm": 0.2708548903465271,
+      "learning_rate": 9.910861217772903e-06,
+      "loss": 0.6883,
+      "step": 230
+    },
+    {
+      "epoch": 0.01634404208590837,
+      "grad_norm": 0.253282368183136,
+      "learning_rate": 9.904004388370818e-06,
+      "loss": 0.6857,
+      "step": 240
+    },
+    {
+      "epoch": 0.017025043839487886,
+      "grad_norm": 0.27983254194259644,
+      "learning_rate": 9.897147558968733e-06,
+      "loss": 0.6803,
+      "step": 250
+    },
+    {
+      "epoch": 0.0177060455930674,
+      "grad_norm": 0.2581124007701874,
+      "learning_rate": 9.890290729566649e-06,
+      "loss": 0.6857,
+      "step": 260
+    },
+    {
+      "epoch": 0.018387047346646916,
+      "grad_norm": 0.2569878101348877,
+      "learning_rate": 9.883433900164566e-06,
+      "loss": 0.682,
+      "step": 270
+    },
+    {
+      "epoch": 0.01906804910022643,
+      "grad_norm": 0.2477487176656723,
+      "learning_rate": 9.87657707076248e-06,
+      "loss": 0.6875,
+      "step": 280
+    },
+    {
+      "epoch": 0.01974905085380595,
+      "grad_norm": 0.271499902009964,
+      "learning_rate": 9.869720241360396e-06,
+      "loss": 0.6804,
+      "step": 290
+    },
+    {
+      "epoch": 0.020430052607385465,
+      "grad_norm": 0.2972584068775177,
+      "learning_rate": 9.862863411958311e-06,
+      "loss": 0.6863,
+      "step": 300
+    },
+    {
+      "epoch": 0.02111105436096498,
+      "grad_norm": 0.26219993829727173,
+      "learning_rate": 9.856006582556227e-06,
+      "loss": 0.6778,
+      "step": 310
+    },
+    {
+      "epoch": 0.021792056114544496,
+      "grad_norm": 0.2560235857963562,
+      "learning_rate": 9.849149753154142e-06,
+      "loss": 0.6854,
+      "step": 320
+    },
+    {
+      "epoch": 0.02247305786812401,
+      "grad_norm": 0.3038085103034973,
+      "learning_rate": 9.842292923752057e-06,
+      "loss": 0.6813,
+      "step": 330
+    },
+    {
+      "epoch": 0.023154059621703527,
+      "grad_norm": 0.3536514639854431,
+      "learning_rate": 9.835436094349974e-06,
+      "loss": 0.6675,
+      "step": 340
+    },
+    {
+      "epoch": 0.023835061375283042,
+      "grad_norm": 0.2704240381717682,
+      "learning_rate": 9.828579264947888e-06,
+      "loss": 0.685,
+      "step": 350
+    },
+    {
+      "epoch": 0.024516063128862557,
+      "grad_norm": 0.31198108196258545,
+      "learning_rate": 9.821722435545805e-06,
+      "loss": 0.6804,
+      "step": 360
+    },
+    {
+      "epoch": 0.025197064882442072,
+      "grad_norm": 0.31849080324172974,
+      "learning_rate": 9.81486560614372e-06,
+      "loss": 0.6817,
+      "step": 370
+    },
+    {
+      "epoch": 0.025878066636021588,
+      "grad_norm": 0.2793581485748291,
+      "learning_rate": 9.808008776741635e-06,
+      "loss": 0.6817,
+      "step": 380
+    },
+    {
+      "epoch": 0.026559068389601103,
+      "grad_norm": 0.3031156361103058,
+      "learning_rate": 9.80115194733955e-06,
+      "loss": 0.6734,
+      "step": 390
+    },
+    {
+      "epoch": 0.02724007014318062,
+      "grad_norm": 0.3462478816509247,
+      "learning_rate": 9.794295117937468e-06,
+      "loss": 0.6747,
+      "step": 400
+    },
+    {
+      "epoch": 0.027921071896760134,
+      "grad_norm": 0.313882052898407,
+      "learning_rate": 9.787438288535383e-06,
+      "loss": 0.6708,
+      "step": 410
+    },
+    {
+      "epoch": 0.02860207365033965,
+      "grad_norm": 0.29912427067756653,
+      "learning_rate": 9.780581459133296e-06,
+      "loss": 0.6633,
+      "step": 420
+    },
+    {
+      "epoch": 0.029283075403919164,
+      "grad_norm": 0.3233661949634552,
+      "learning_rate": 9.773724629731213e-06,
+      "loss": 0.6685,
+      "step": 430
+    },
+    {
+      "epoch": 0.02996407715749868,
+      "grad_norm": 0.34199562668800354,
+      "learning_rate": 9.766867800329129e-06,
+      "loss": 0.6717,
+      "step": 440
+    },
+    {
+      "epoch": 0.030645078911078195,
+      "grad_norm": 0.3144058883190155,
+      "learning_rate": 9.760010970927044e-06,
+      "loss": 0.6734,
+      "step": 450
+    },
+    {
+      "epoch": 0.03132608066465771,
+      "grad_norm": 0.34626367688179016,
+      "learning_rate": 9.75315414152496e-06,
+      "loss": 0.6734,
+      "step": 460
+    },
+    {
+      "epoch": 0.03200708241823723,
+      "grad_norm": 0.3287607431411743,
+      "learning_rate": 9.746297312122876e-06,
+      "loss": 0.6739,
+      "step": 470
+    },
+    {
+      "epoch": 0.03268808417181674,
+      "grad_norm": 0.3672466576099396,
+      "learning_rate": 9.739440482720792e-06,
+      "loss": 0.6673,
+      "step": 480
+    },
+    {
+      "epoch": 0.03336908592539626,
+      "grad_norm": 0.39270955324172974,
+      "learning_rate": 9.732583653318705e-06,
+      "loss": 0.6623,
+      "step": 490
+    },
+    {
+      "epoch": 0.03405008767897577,
+      "grad_norm": 0.3832233250141144,
+      "learning_rate": 9.725726823916622e-06,
+      "loss": 0.6695,
+      "step": 500
+    },
+    {
+      "epoch": 0.03473108943255529,
+      "grad_norm": 0.38370147347450256,
+      "learning_rate": 9.718869994514537e-06,
+      "loss": 0.655,
+      "step": 510
+    },
+    {
+      "epoch": 0.0354120911861348,
+      "grad_norm": 0.3312557339668274,
+      "learning_rate": 9.712013165112453e-06,
+      "loss": 0.669,
+      "step": 520
+    },
+    {
+      "epoch": 0.03609309293971432,
+      "grad_norm": 0.3377546966075897,
+      "learning_rate": 9.705156335710368e-06,
+      "loss": 0.6699,
+      "step": 530
+    },
+    {
+      "epoch": 0.03677409469329383,
+      "grad_norm": 0.37603405117988586,
+      "learning_rate": 9.698299506308285e-06,
+      "loss": 0.6655,
+      "step": 540
+    },
+    {
+      "epoch": 0.03745509644687335,
+      "grad_norm": 0.3541698455810547,
+      "learning_rate": 9.6914426769062e-06,
+      "loss": 0.6724,
+      "step": 550
+    },
+    {
+      "epoch": 0.03813609820045286,
+      "grad_norm": 0.4372965395450592,
+      "learning_rate": 9.684585847504114e-06,
+      "loss": 0.6609,
+      "step": 560
+    },
+    {
+      "epoch": 0.03881709995403238,
+      "grad_norm": 0.35060834884643555,
+      "learning_rate": 9.67772901810203e-06,
+      "loss": 0.6671,
+      "step": 570
+    },
+    {
+      "epoch": 0.0394981017076119,
+      "grad_norm": 0.37355268001556396,
+      "learning_rate": 9.670872188699946e-06,
+      "loss": 0.6602,
+      "step": 580
+    },
+    {
+      "epoch": 0.04017910346119141,
+      "grad_norm": 0.3608810007572174,
+      "learning_rate": 9.664015359297861e-06,
+      "loss": 0.6478,
+      "step": 590
+    },
+    {
+      "epoch": 0.04086010521477093,
+      "grad_norm": 0.4038260877132416,
+      "learning_rate": 9.657158529895777e-06,
+      "loss": 0.6663,
+      "step": 600
+    },
+    {
+      "epoch": 0.04154110696835044,
+      "grad_norm": 0.43548446893692017,
+      "learning_rate": 9.650301700493694e-06,
+      "loss": 0.6588,
+      "step": 610
+    },
+    {
+      "epoch": 0.04222210872192996,
+      "grad_norm": 0.4079245328903198,
+      "learning_rate": 9.643444871091609e-06,
+      "loss": 0.6611,
+      "step": 620
+    },
+    {
+      "epoch": 0.04290311047550947,
+      "grad_norm": 0.37972599267959595,
+      "learning_rate": 9.636588041689522e-06,
+      "loss": 0.6613,
+      "step": 630
+    },
+    {
+      "epoch": 0.04358411222908899,
+      "grad_norm": 0.4221982955932617,
+      "learning_rate": 9.62973121228744e-06,
+      "loss": 0.6544,
+      "step": 640
+    },
+    {
+      "epoch": 0.044265113982668504,
+      "grad_norm": 0.3993457853794098,
+      "learning_rate": 9.622874382885355e-06,
+      "loss": 0.6537,
+      "step": 650
+    },
+    {
+      "epoch": 0.04494611573624802,
+      "grad_norm": 0.36067628860473633,
+      "learning_rate": 9.61601755348327e-06,
+      "loss": 0.6616,
+      "step": 660
+    },
+    {
+      "epoch": 0.045627117489827534,
+      "grad_norm": 0.4832242429256439,
+      "learning_rate": 9.609160724081185e-06,
+      "loss": 0.656,
+      "step": 670
+    },
+    {
+      "epoch": 0.04630811924340705,
+      "grad_norm": 0.38491684198379517,
+      "learning_rate": 9.602303894679102e-06,
+      "loss": 0.6596,
+      "step": 680
+    },
+    {
+      "epoch": 0.046989120996986565,
+      "grad_norm": 0.4198424220085144,
+      "learning_rate": 9.595447065277017e-06,
+      "loss": 0.6585,
+      "step": 690
+    },
+    {
+      "epoch": 0.047670122750566084,
+      "grad_norm": 0.41907042264938354,
+      "learning_rate": 9.588590235874933e-06,
+      "loss": 0.6553,
+      "step": 700
+    },
+    {
+      "epoch": 0.048351124504145596,
+      "grad_norm": 0.4876721203327179,
+      "learning_rate": 9.581733406472848e-06,
+      "loss": 0.6601,
+      "step": 710
+    },
+    {
+      "epoch": 0.049032126257725114,
+      "grad_norm": 0.435100257396698,
+      "learning_rate": 9.574876577070763e-06,
+      "loss": 0.6426,
+      "step": 720
+    },
+    {
+      "epoch": 0.049713128011304626,
+      "grad_norm": 0.405373752117157,
+      "learning_rate": 9.568019747668679e-06,
+      "loss": 0.6619,
+      "step": 730
+    },
+    {
+      "epoch": 0.050394129764884145,
+      "grad_norm": 0.46245890855789185,
+      "learning_rate": 9.561162918266594e-06,
+      "loss": 0.662,
+      "step": 740
+    },
+    {
+      "epoch": 0.05107513151846366,
+      "grad_norm": 0.4155888259410858,
+      "learning_rate": 9.55430608886451e-06,
+      "loss": 0.6485,
+      "step": 750
+    },
+    {
+      "epoch": 0.051756133272043175,
+      "grad_norm": 0.4508476257324219,
+      "learning_rate": 9.547449259462426e-06,
+      "loss": 0.6515,
+      "step": 760
+    },
+    {
+      "epoch": 0.052437135025622694,
+      "grad_norm": 0.4646701216697693,
+      "learning_rate": 9.540592430060341e-06,
+      "loss": 0.6485,
+      "step": 770
+    },
+    {
+      "epoch": 0.053118136779202206,
+      "grad_norm": 0.4512174427509308,
+      "learning_rate": 9.533735600658257e-06,
+      "loss": 0.6553,
+      "step": 780
+    },
+    {
+      "epoch": 0.053799138532781725,
+      "grad_norm": 0.3947104513645172,
+      "learning_rate": 9.526878771256172e-06,
+      "loss": 0.6563,
+      "step": 790
+    },
+    {
+      "epoch": 0.05448014028636124,
+      "grad_norm": 0.48504170775413513,
+      "learning_rate": 9.520021941854087e-06,
+      "loss": 0.6503,
+      "step": 800
+    },
+    {
+      "epoch": 0.055161142039940755,
+      "grad_norm": 0.4520103633403778,
+      "learning_rate": 9.513165112452003e-06,
+      "loss": 0.6537,
+      "step": 810
+    },
+    {
+      "epoch": 0.05584214379352027,
+      "grad_norm": 0.4581333100795746,
+      "learning_rate": 9.50630828304992e-06,
+      "loss": 0.6561,
+      "step": 820
+    },
+    {
+      "epoch": 0.056523145547099786,
+      "grad_norm": 0.43217501044273376,
+      "learning_rate": 9.499451453647835e-06,
+      "loss": 0.6492,
+      "step": 830
+    },
+    {
+      "epoch": 0.0572041473006793,
+      "grad_norm": 0.4000322222709656,
+      "learning_rate": 9.49259462424575e-06,
+      "loss": 0.6551,
+      "step": 840
+    },
+    {
+      "epoch": 0.057885149054258817,
+      "grad_norm": 0.49503183364868164,
+      "learning_rate": 9.485737794843665e-06,
+      "loss": 0.6543,
+      "step": 850
+    },
+    {
+      "epoch": 0.05856615080783833,
+      "grad_norm": 0.526793897151947,
+      "learning_rate": 9.47888096544158e-06,
+      "loss": 0.6487,
+      "step": 860
+    },
+    {
+      "epoch": 0.05924715256141785,
+      "grad_norm": 0.44149249792099,
+      "learning_rate": 9.472024136039496e-06,
+      "loss": 0.6438,
+      "step": 870
+    },
+    {
+      "epoch": 0.05992815431499736,
+      "grad_norm": 0.47103720903396606,
+      "learning_rate": 9.465167306637411e-06,
+      "loss": 0.6614,
+      "step": 880
+    },
+    {
+      "epoch": 0.06060915606857688,
+      "grad_norm": 0.47923219203948975,
+      "learning_rate": 9.458310477235328e-06,
+      "loss": 0.6504,
+      "step": 890
+    },
+    {
+      "epoch": 0.06129015782215639,
+      "grad_norm": 0.4862936735153198,
+      "learning_rate": 9.451453647833243e-06,
+      "loss": 0.6462,
+      "step": 900
+    },
+    {
+      "epoch": 0.06197115957573591,
+      "grad_norm": 0.4490489959716797,
+      "learning_rate": 9.444596818431159e-06,
+      "loss": 0.6455,
+      "step": 910
+    },
+    {
+      "epoch": 0.06265216132931542,
+      "grad_norm": 0.49477618932724,
+      "learning_rate": 9.437739989029074e-06,
+      "loss": 0.6516,
+      "step": 920
+    },
+    {
+      "epoch": 0.06333316308289494,
+      "grad_norm": 0.4628184139728546,
+      "learning_rate": 9.43088315962699e-06,
+      "loss": 0.6477,
+      "step": 930
+    },
+    {
+      "epoch": 0.06401416483647446,
+      "grad_norm": 0.571842610836029,
+      "learning_rate": 9.424026330224905e-06,
+      "loss": 0.6469,
+      "step": 940
+    },
+    {
+      "epoch": 0.06469516659005398,
+      "grad_norm": 0.49607202410697937,
+      "learning_rate": 9.41716950082282e-06,
+      "loss": 0.6408,
+      "step": 950
+    },
+    {
+      "epoch": 0.06537616834363348,
+      "grad_norm": 0.6812955737113953,
+      "learning_rate": 9.410312671420737e-06,
+      "loss": 0.6314,
+      "step": 960
+    },
+    {
+      "epoch": 0.066057170097213,
+      "grad_norm": 0.4633328914642334,
+      "learning_rate": 9.403455842018652e-06,
+      "loss": 0.6449,
+      "step": 970
+    },
+    {
+      "epoch": 0.06673817185079252,
+      "grad_norm": 0.4610375463962555,
+      "learning_rate": 9.396599012616567e-06,
+      "loss": 0.6449,
+      "step": 980
+    },
+    {
+      "epoch": 0.06741917360437204,
+      "grad_norm": 0.5102701783180237,
+      "learning_rate": 9.389742183214483e-06,
+      "loss": 0.6427,
+      "step": 990
+    },
+    {
+      "epoch": 0.06810017535795154,
+      "grad_norm": 0.4977886974811554,
+      "learning_rate": 9.382885353812398e-06,
+      "loss": 0.6472,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 14684,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.096719327232e+17,
+  "train_batch_size": 5,
+  "trial_name": null,
+  "trial_params": null
+}

pgn_adapter_logs/mistral_pgn-tesis/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a845ae87ee071d7036e1c72e6d15f86bec17d47b6c457d57e66a0fb6b24226b
+size 5176

pgn_adapter_logs/mistral_pgn-tesis/checkpoint-2000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.1.dev0

pgn_adapter_logs/mistral_pgn-tesis/checkpoint-2000/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

pgn_adapter_logs/mistral_pgn-tesis/checkpoint-2000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:922f721d2b0694dd1d7be7468c9e22588adadf523a935c5cb17a5d14b3ad9494
+size 218138576

pgn_adapter_logs/mistral_pgn-tesis/checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d8382d7132a41eae4319d5bf0a1b4978f23005d63e369babc9fa37328779e38
+size 436423418

pgn_adapter_logs/mistral_pgn-tesis/checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:280bd9e27b52aa9caf511c0ab0f2b17abc9971e70549e86a0e6f0ff15fb9efed
+size 14244

pgn_adapter_logs/mistral_pgn-tesis/checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c31b1d7f207c252d5520807dd22a033b4da526a3a0337050fc884d129222695
+size 1064

pgn_adapter_logs/mistral_pgn-tesis/checkpoint-2000/trainer_state.json

@@ -0,0 +1,1433 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.13620035071590308,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0006810017535795155,
+      "grad_norm": 0.8741451501846313,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.2903,
+      "step": 10
+    },
+    {
+      "epoch": 0.001362003507159031,
+      "grad_norm": 0.8342441320419312,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.2919,
+      "step": 20
+    },
+    {
+      "epoch": 0.0020430052607385463,
+      "grad_norm": 0.7483816742897034,
+      "learning_rate": 3e-06,
+      "loss": 1.2438,
+      "step": 30
+    },
+    {
+      "epoch": 0.002724007014318062,
+      "grad_norm": 0.7297427654266357,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.2199,
+      "step": 40
+    },
+    {
+      "epoch": 0.0034050087678975773,
+      "grad_norm": 0.7647419571876526,
+      "learning_rate": 5e-06,
+      "loss": 1.1631,
+      "step": 50
+    },
+    {
+      "epoch": 0.004086010521477093,
+      "grad_norm": 0.4680333137512207,
+      "learning_rate": 6e-06,
+      "loss": 1.1049,
+      "step": 60
+    },
+    {
+      "epoch": 0.004767012275056608,
+      "grad_norm": 0.39699047803878784,
+      "learning_rate": 7e-06,
+      "loss": 1.0397,
+      "step": 70
+    },
+    {
+      "epoch": 0.005448014028636124,
+      "grad_norm": 0.4081316888332367,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.9872,
+      "step": 80
+    },
+    {
+      "epoch": 0.006129015782215639,
+      "grad_norm": 0.4579920470714569,
+      "learning_rate": 9e-06,
+      "loss": 0.9204,
+      "step": 90
+    },
+    {
+      "epoch": 0.006810017535795155,
+      "grad_norm": 0.37478742003440857,
+      "learning_rate": 1e-05,
+      "loss": 0.851,
+      "step": 100
+    },
+    {
+      "epoch": 0.00749101928937467,
+      "grad_norm": 0.2919694483280182,
+      "learning_rate": 9.993143170597916e-06,
+      "loss": 0.792,
+      "step": 110
+    },
+    {
+      "epoch": 0.008172021042954185,
+      "grad_norm": 0.254935622215271,
+      "learning_rate": 9.986286341195831e-06,
+      "loss": 0.7643,
+      "step": 120
+    },
+    {
+      "epoch": 0.0088530227965337,
+      "grad_norm": 0.250884473323822,
+      "learning_rate": 9.979429511793748e-06,
+      "loss": 0.7607,
+      "step": 130
+    },
+    {
+      "epoch": 0.009534024550113216,
+      "grad_norm": 0.2979223132133484,
+      "learning_rate": 9.972572682391662e-06,
+      "loss": 0.7365,
+      "step": 140
+    },
+    {
+      "epoch": 0.010215026303692733,
+      "grad_norm": 0.2718585431575775,
+      "learning_rate": 9.965715852989579e-06,
+      "loss": 0.7156,
+      "step": 150
+    },
+    {
+      "epoch": 0.010896028057272248,
+      "grad_norm": 0.23914478719234467,
+      "learning_rate": 9.958859023587494e-06,
+      "loss": 0.7123,
+      "step": 160
+    },
+    {
+      "epoch": 0.011577029810851763,
+      "grad_norm": 0.24752002954483032,
+      "learning_rate": 9.95200219418541e-06,
+      "loss": 0.6997,
+      "step": 170
+    },
+    {
+      "epoch": 0.012258031564431279,
+      "grad_norm": 0.2361425906419754,
+      "learning_rate": 9.945145364783325e-06,
+      "loss": 0.702,
+      "step": 180
+    },
+    {
+      "epoch": 0.012939033318010794,
+      "grad_norm": 0.23137520253658295,
+      "learning_rate": 9.93828853538124e-06,
+      "loss": 0.7056,
+      "step": 190
+    },
+    {
+      "epoch": 0.01362003507159031,
+      "grad_norm": 0.2404152899980545,
+      "learning_rate": 9.931431705979157e-06,
+      "loss": 0.7005,
+      "step": 200
+    },
+    {
+      "epoch": 0.014301036825169824,
+      "grad_norm": 0.2881813943386078,
+      "learning_rate": 9.92457487657707e-06,
+      "loss": 0.7023,
+      "step": 210
+    },
+    {
+      "epoch": 0.01498203857874934,
+      "grad_norm": 0.2458052635192871,
+      "learning_rate": 9.917718047174988e-06,
+      "loss": 0.7014,
+      "step": 220
+    },
+    {
+      "epoch": 0.015663040332328855,
+      "grad_norm": 0.2708548903465271,
+      "learning_rate": 9.910861217772903e-06,
+      "loss": 0.6883,
+      "step": 230
+    },
+    {
+      "epoch": 0.01634404208590837,
+      "grad_norm": 0.253282368183136,
+      "learning_rate": 9.904004388370818e-06,
+      "loss": 0.6857,
+      "step": 240
+    },
+    {
+      "epoch": 0.017025043839487886,
+      "grad_norm": 0.27983254194259644,
+      "learning_rate": 9.897147558968733e-06,
+      "loss": 0.6803,
+      "step": 250
+    },
+    {
+      "epoch": 0.0177060455930674,
+      "grad_norm": 0.2581124007701874,
+      "learning_rate": 9.890290729566649e-06,
+      "loss": 0.6857,
+      "step": 260
+    },
+    {
+      "epoch": 0.018387047346646916,
+      "grad_norm": 0.2569878101348877,
+      "learning_rate": 9.883433900164566e-06,
+      "loss": 0.682,
+      "step": 270
+    },
+    {
+      "epoch": 0.01906804910022643,
+      "grad_norm": 0.2477487176656723,
+      "learning_rate": 9.87657707076248e-06,
+      "loss": 0.6875,
+      "step": 280
+    },
+    {
+      "epoch": 0.01974905085380595,
+      "grad_norm": 0.271499902009964,
+      "learning_rate": 9.869720241360396e-06,
+      "loss": 0.6804,
+      "step": 290
+    },
+    {
+      "epoch": 0.020430052607385465,
+      "grad_norm": 0.2972584068775177,
+      "learning_rate": 9.862863411958311e-06,
+      "loss": 0.6863,
+      "step": 300
+    },
+    {
+      "epoch": 0.02111105436096498,
+      "grad_norm": 0.26219993829727173,
+      "learning_rate": 9.856006582556227e-06,
+      "loss": 0.6778,
+      "step": 310
+    },
+    {
+      "epoch": 0.021792056114544496,
+      "grad_norm": 0.2560235857963562,
+      "learning_rate": 9.849149753154142e-06,
+      "loss": 0.6854,
+      "step": 320
+    },
+    {
+      "epoch": 0.02247305786812401,
+      "grad_norm": 0.3038085103034973,
+      "learning_rate": 9.842292923752057e-06,
+      "loss": 0.6813,
+      "step": 330
+    },
+    {
+      "epoch": 0.023154059621703527,
+      "grad_norm": 0.3536514639854431,
+      "learning_rate": 9.835436094349974e-06,
+      "loss": 0.6675,
+      "step": 340
+    },
+    {
+      "epoch": 0.023835061375283042,
+      "grad_norm": 0.2704240381717682,
+      "learning_rate": 9.828579264947888e-06,
+      "loss": 0.685,
+      "step": 350
+    },
+    {
+      "epoch": 0.024516063128862557,
+      "grad_norm": 0.31198108196258545,
+      "learning_rate": 9.821722435545805e-06,
+      "loss": 0.6804,
+      "step": 360
+    },
+    {
+      "epoch": 0.025197064882442072,
+      "grad_norm": 0.31849080324172974,
+      "learning_rate": 9.81486560614372e-06,
+      "loss": 0.6817,
+      "step": 370
+    },
+    {
+      "epoch": 0.025878066636021588,
+      "grad_norm": 0.2793581485748291,
+      "learning_rate": 9.808008776741635e-06,
+      "loss": 0.6817,
+      "step": 380
+    },
+    {
+      "epoch": 0.026559068389601103,
+      "grad_norm": 0.3031156361103058,
+      "learning_rate": 9.80115194733955e-06,
+      "loss": 0.6734,
+      "step": 390
+    },
+    {
+      "epoch": 0.02724007014318062,
+      "grad_norm": 0.3462478816509247,
+      "learning_rate": 9.794295117937468e-06,
+      "loss": 0.6747,
+      "step": 400
+    },
+    {
+      "epoch": 0.027921071896760134,
+      "grad_norm": 0.313882052898407,
+      "learning_rate": 9.787438288535383e-06,
+      "loss": 0.6708,
+      "step": 410
+    },
+    {
+      "epoch": 0.02860207365033965,
+      "grad_norm": 0.29912427067756653,
+      "learning_rate": 9.780581459133296e-06,
+      "loss": 0.6633,
+      "step": 420
+    },
+    {
+      "epoch": 0.029283075403919164,
+      "grad_norm": 0.3233661949634552,
+      "learning_rate": 9.773724629731213e-06,
+      "loss": 0.6685,
+      "step": 430
+    },
+    {
+      "epoch": 0.02996407715749868,
+      "grad_norm": 0.34199562668800354,
+      "learning_rate": 9.766867800329129e-06,
+      "loss": 0.6717,
+      "step": 440
+    },
+    {
+      "epoch": 0.030645078911078195,
+      "grad_norm": 0.3144058883190155,
+      "learning_rate": 9.760010970927044e-06,
+      "loss": 0.6734,
+      "step": 450
+    },
+    {
+      "epoch": 0.03132608066465771,
+      "grad_norm": 0.34626367688179016,
+      "learning_rate": 9.75315414152496e-06,
+      "loss": 0.6734,
+      "step": 460
+    },
+    {
+      "epoch": 0.03200708241823723,
+      "grad_norm": 0.3287607431411743,
+      "learning_rate": 9.746297312122876e-06,
+      "loss": 0.6739,
+      "step": 470
+    },
+    {
+      "epoch": 0.03268808417181674,
+      "grad_norm": 0.3672466576099396,
+      "learning_rate": 9.739440482720792e-06,
+      "loss": 0.6673,
+      "step": 480
+    },
+    {
+      "epoch": 0.03336908592539626,
+      "grad_norm": 0.39270955324172974,
+      "learning_rate": 9.732583653318705e-06,
+      "loss": 0.6623,
+      "step": 490
+    },
+    {
+      "epoch": 0.03405008767897577,
+      "grad_norm": 0.3832233250141144,
+      "learning_rate": 9.725726823916622e-06,
+      "loss": 0.6695,
+      "step": 500
+    },
+    {
+      "epoch": 0.03473108943255529,
+      "grad_norm": 0.38370147347450256,
+      "learning_rate": 9.718869994514537e-06,
+      "loss": 0.655,
+      "step": 510
+    },
+    {
+      "epoch": 0.0354120911861348,
+      "grad_norm": 0.3312557339668274,
+      "learning_rate": 9.712013165112453e-06,
+      "loss": 0.669,
+      "step": 520
+    },
+    {
+      "epoch": 0.03609309293971432,
+      "grad_norm": 0.3377546966075897,
+      "learning_rate": 9.705156335710368e-06,
+      "loss": 0.6699,
+      "step": 530
+    },
+    {
+      "epoch": 0.03677409469329383,
+      "grad_norm": 0.37603405117988586,
+      "learning_rate": 9.698299506308285e-06,
+      "loss": 0.6655,
+      "step": 540
+    },
+    {
+      "epoch": 0.03745509644687335,
+      "grad_norm": 0.3541698455810547,
+      "learning_rate": 9.6914426769062e-06,
+      "loss": 0.6724,
+      "step": 550
+    },
+    {
+      "epoch": 0.03813609820045286,
+      "grad_norm": 0.4372965395450592,
+      "learning_rate": 9.684585847504114e-06,
+      "loss": 0.6609,
+      "step": 560
+    },
+    {
+      "epoch": 0.03881709995403238,
+      "grad_norm": 0.35060834884643555,
+      "learning_rate": 9.67772901810203e-06,
+      "loss": 0.6671,
+      "step": 570
+    },
+    {
+      "epoch": 0.0394981017076119,
+      "grad_norm": 0.37355268001556396,
+      "learning_rate": 9.670872188699946e-06,
+      "loss": 0.6602,
+      "step": 580
+    },
+    {
+      "epoch": 0.04017910346119141,
+      "grad_norm": 0.3608810007572174,
+      "learning_rate": 9.664015359297861e-06,
+      "loss": 0.6478,
+      "step": 590
+    },
+    {
+      "epoch": 0.04086010521477093,
+      "grad_norm": 0.4038260877132416,
+      "learning_rate": 9.657158529895777e-06,
+      "loss": 0.6663,
+      "step": 600
+    },
+    {
+      "epoch": 0.04154110696835044,
+      "grad_norm": 0.43548446893692017,
+      "learning_rate": 9.650301700493694e-06,
+      "loss": 0.6588,
+      "step": 610
+    },
+    {
+      "epoch": 0.04222210872192996,
+      "grad_norm": 0.4079245328903198,
+      "learning_rate": 9.643444871091609e-06,
+      "loss": 0.6611,
+      "step": 620
+    },
+    {
+      "epoch": 0.04290311047550947,
+      "grad_norm": 0.37972599267959595,
+      "learning_rate": 9.636588041689522e-06,
+      "loss": 0.6613,
+      "step": 630
+    },
+    {
+      "epoch": 0.04358411222908899,
+      "grad_norm": 0.4221982955932617,
+      "learning_rate": 9.62973121228744e-06,
+      "loss": 0.6544,
+      "step": 640
+    },
+    {
+      "epoch": 0.044265113982668504,
+      "grad_norm": 0.3993457853794098,
+      "learning_rate": 9.622874382885355e-06,
+      "loss": 0.6537,
+      "step": 650
+    },
+    {
+      "epoch": 0.04494611573624802,
+      "grad_norm": 0.36067628860473633,
+      "learning_rate": 9.61601755348327e-06,
+      "loss": 0.6616,
+      "step": 660
+    },
+    {
+      "epoch": 0.045627117489827534,
+      "grad_norm": 0.4832242429256439,
+      "learning_rate": 9.609160724081185e-06,
+      "loss": 0.656,
+      "step": 670
+    },
+    {
+      "epoch": 0.04630811924340705,
+      "grad_norm": 0.38491684198379517,
+      "learning_rate": 9.602303894679102e-06,
+      "loss": 0.6596,
+      "step": 680
+    },
+    {
+      "epoch": 0.046989120996986565,
+      "grad_norm": 0.4198424220085144,
+      "learning_rate": 9.595447065277017e-06,
+      "loss": 0.6585,
+      "step": 690
+    },
+    {
+      "epoch": 0.047670122750566084,
+      "grad_norm": 0.41907042264938354,
+      "learning_rate": 9.588590235874933e-06,
+      "loss": 0.6553,
+      "step": 700
+    },
+    {
+      "epoch": 0.048351124504145596,
+      "grad_norm": 0.4876721203327179,
+      "learning_rate": 9.581733406472848e-06,
+      "loss": 0.6601,
+      "step": 710
+    },
+    {
+      "epoch": 0.049032126257725114,
+      "grad_norm": 0.435100257396698,
+      "learning_rate": 9.574876577070763e-06,
+      "loss": 0.6426,
+      "step": 720
+    },
+    {
+      "epoch": 0.049713128011304626,
+      "grad_norm": 0.405373752117157,
+      "learning_rate": 9.568019747668679e-06,
+      "loss": 0.6619,
+      "step": 730
+    },
+    {
+      "epoch": 0.050394129764884145,
+      "grad_norm": 0.46245890855789185,
+      "learning_rate": 9.561162918266594e-06,
+      "loss": 0.662,
+      "step": 740
+    },
+    {
+      "epoch": 0.05107513151846366,
+      "grad_norm": 0.4155888259410858,
+      "learning_rate": 9.55430608886451e-06,
+      "loss": 0.6485,
+      "step": 750
+    },
+    {
+      "epoch": 0.051756133272043175,
+      "grad_norm": 0.4508476257324219,
+      "learning_rate": 9.547449259462426e-06,
+      "loss": 0.6515,
+      "step": 760
+    },
+    {
+      "epoch": 0.052437135025622694,
+      "grad_norm": 0.4646701216697693,
+      "learning_rate": 9.540592430060341e-06,
+      "loss": 0.6485,
+      "step": 770
+    },
+    {
+      "epoch": 0.053118136779202206,
+      "grad_norm": 0.4512174427509308,
+      "learning_rate": 9.533735600658257e-06,
+      "loss": 0.6553,
+      "step": 780
+    },
+    {
+      "epoch": 0.053799138532781725,
+      "grad_norm": 0.3947104513645172,
+      "learning_rate": 9.526878771256172e-06,
+      "loss": 0.6563,
+      "step": 790
+    },
+    {
+      "epoch": 0.05448014028636124,
+      "grad_norm": 0.48504170775413513,
+      "learning_rate": 9.520021941854087e-06,
+      "loss": 0.6503,
+      "step": 800
+    },
+    {
+      "epoch": 0.055161142039940755,
+      "grad_norm": 0.4520103633403778,
+      "learning_rate": 9.513165112452003e-06,
+      "loss": 0.6537,
+      "step": 810
+    },
+    {
+      "epoch": 0.05584214379352027,
+      "grad_norm": 0.4581333100795746,
+      "learning_rate": 9.50630828304992e-06,
+      "loss": 0.6561,
+      "step": 820
+    },
+    {
+      "epoch": 0.056523145547099786,
+      "grad_norm": 0.43217501044273376,
+      "learning_rate": 9.499451453647835e-06,
+      "loss": 0.6492,
+      "step": 830
+    },
+    {
+      "epoch": 0.0572041473006793,
+      "grad_norm": 0.4000322222709656,
+      "learning_rate": 9.49259462424575e-06,
+      "loss": 0.6551,
+      "step": 840
+    },
+    {
+      "epoch": 0.057885149054258817,
+      "grad_norm": 0.49503183364868164,
+      "learning_rate": 9.485737794843665e-06,
+      "loss": 0.6543,
+      "step": 850
+    },
+    {
+      "epoch": 0.05856615080783833,
+      "grad_norm": 0.526793897151947,
+      "learning_rate": 9.47888096544158e-06,
+      "loss": 0.6487,
+      "step": 860
+    },
+    {
+      "epoch": 0.05924715256141785,
+      "grad_norm": 0.44149249792099,
+      "learning_rate": 9.472024136039496e-06,
+      "loss": 0.6438,
+      "step": 870
+    },
+    {
+      "epoch": 0.05992815431499736,
+      "grad_norm": 0.47103720903396606,
+      "learning_rate": 9.465167306637411e-06,
+      "loss": 0.6614,
+      "step": 880
+    },
+    {
+      "epoch": 0.06060915606857688,
+      "grad_norm": 0.47923219203948975,
+      "learning_rate": 9.458310477235328e-06,
+      "loss": 0.6504,
+      "step": 890
+    },
+    {
+      "epoch": 0.06129015782215639,
+      "grad_norm": 0.4862936735153198,
+      "learning_rate": 9.451453647833243e-06,
+      "loss": 0.6462,
+      "step": 900
+    },
+    {
+      "epoch": 0.06197115957573591,
+      "grad_norm": 0.4490489959716797,
+      "learning_rate": 9.444596818431159e-06,
+      "loss": 0.6455,
+      "step": 910
+    },
+    {
+      "epoch": 0.06265216132931542,
+      "grad_norm": 0.49477618932724,
+      "learning_rate": 9.437739989029074e-06,
+      "loss": 0.6516,
+      "step": 920
+    },
+    {
+      "epoch": 0.06333316308289494,
+      "grad_norm": 0.4628184139728546,
+      "learning_rate": 9.43088315962699e-06,
+      "loss": 0.6477,
+      "step": 930
+    },
+    {
+      "epoch": 0.06401416483647446,
+      "grad_norm": 0.571842610836029,
+      "learning_rate": 9.424026330224905e-06,
+      "loss": 0.6469,
+      "step": 940
+    },
+    {
+      "epoch": 0.06469516659005398,
+      "grad_norm": 0.49607202410697937,
+      "learning_rate": 9.41716950082282e-06,
+      "loss": 0.6408,
+      "step": 950
+    },
+    {
+      "epoch": 0.06537616834363348,
+      "grad_norm": 0.6812955737113953,
+      "learning_rate": 9.410312671420737e-06,
+      "loss": 0.6314,
+      "step": 960
+    },
+    {
+      "epoch": 0.066057170097213,
+      "grad_norm": 0.4633328914642334,
+      "learning_rate": 9.403455842018652e-06,
+      "loss": 0.6449,
+      "step": 970
+    },
+    {
+      "epoch": 0.06673817185079252,
+      "grad_norm": 0.4610375463962555,
+      "learning_rate": 9.396599012616567e-06,
+      "loss": 0.6449,
+      "step": 980
+    },
+    {
+      "epoch": 0.06741917360437204,
+      "grad_norm": 0.5102701783180237,
+      "learning_rate": 9.389742183214483e-06,
+      "loss": 0.6427,
+      "step": 990
+    },
+    {
+      "epoch": 0.06810017535795154,
+      "grad_norm": 0.4977886974811554,
+      "learning_rate": 9.382885353812398e-06,
+      "loss": 0.6472,
+      "step": 1000
+    },
+    {
+      "epoch": 0.06878117711153106,
+      "grad_norm": 0.5018298029899597,
+      "learning_rate": 9.376028524410313e-06,
+      "loss": 0.6466,
+      "step": 1010
+    },
+    {
+      "epoch": 0.06946217886511058,
+      "grad_norm": 0.5332687497138977,
+      "learning_rate": 9.369171695008228e-06,
+      "loss": 0.6431,
+      "step": 1020
+    },
+    {
+      "epoch": 0.0701431806186901,
+      "grad_norm": 0.480394184589386,
+      "learning_rate": 9.362314865606145e-06,
+      "loss": 0.642,
+      "step": 1030
+    },
+    {
+      "epoch": 0.0708241823722696,
+      "grad_norm": 0.5317255258560181,
+      "learning_rate": 9.35545803620406e-06,
+      "loss": 0.6395,
+      "step": 1040
+    },
+    {
+      "epoch": 0.07150518412584912,
+      "grad_norm": 0.4517778158187866,
+      "learning_rate": 9.348601206801976e-06,
+      "loss": 0.6474,
+      "step": 1050
+    },
+    {
+      "epoch": 0.07218618587942864,
+      "grad_norm": 0.4603979289531708,
+      "learning_rate": 9.341744377399891e-06,
+      "loss": 0.6473,
+      "step": 1060
+    },
+    {
+      "epoch": 0.07286718763300816,
+      "grad_norm": 0.5010342001914978,
+      "learning_rate": 9.334887547997807e-06,
+      "loss": 0.6398,
+      "step": 1070
+    },
+    {
+      "epoch": 0.07354818938658766,
+      "grad_norm": 0.5414105653762817,
+      "learning_rate": 9.328030718595722e-06,
+      "loss": 0.6423,
+      "step": 1080
+    },
+    {
+      "epoch": 0.07422919114016718,
+      "grad_norm": 0.5409798622131348,
+      "learning_rate": 9.321173889193637e-06,
+      "loss": 0.6415,
+      "step": 1090
+    },
+    {
+      "epoch": 0.0749101928937467,
+      "grad_norm": 0.5328781604766846,
+      "learning_rate": 9.314317059791554e-06,
+      "loss": 0.6339,
+      "step": 1100
+    },
+    {
+      "epoch": 0.07559119464732622,
+      "grad_norm": 0.5218729972839355,
+      "learning_rate": 9.30746023038947e-06,
+      "loss": 0.644,
+      "step": 1110
+    },
+    {
+      "epoch": 0.07627219640090573,
+      "grad_norm": 0.5408162474632263,
+      "learning_rate": 9.300603400987385e-06,
+      "loss": 0.6418,
+      "step": 1120
+    },
+    {
+      "epoch": 0.07695319815448524,
+      "grad_norm": 0.533549964427948,
+      "learning_rate": 9.2937465715853e-06,
+      "loss": 0.6432,
+      "step": 1130
+    },
+    {
+      "epoch": 0.07763419990806476,
+      "grad_norm": 0.5589444041252136,
+      "learning_rate": 9.286889742183215e-06,
+      "loss": 0.63,
+      "step": 1140
+    },
+    {
+      "epoch": 0.07831520166164428,
+      "grad_norm": 0.5401723384857178,
+      "learning_rate": 9.28003291278113e-06,
+      "loss": 0.6376,
+      "step": 1150
+    },
+    {
+      "epoch": 0.0789962034152238,
+      "grad_norm": 0.5771287083625793,
+      "learning_rate": 9.273176083379046e-06,
+      "loss": 0.6442,
+      "step": 1160
+    },
+    {
+      "epoch": 0.0796772051688033,
+      "grad_norm": 0.5243170857429504,
+      "learning_rate": 9.266319253976963e-06,
+      "loss": 0.6436,
+      "step": 1170
+    },
+    {
+      "epoch": 0.08035820692238282,
+      "grad_norm": 0.6088616251945496,
+      "learning_rate": 9.259462424574878e-06,
+      "loss": 0.6443,
+      "step": 1180
+    },
+    {
+      "epoch": 0.08103920867596234,
+      "grad_norm": 0.5187320709228516,
+      "learning_rate": 9.252605595172793e-06,
+      "loss": 0.6292,
+      "step": 1190
+    },
+    {
+      "epoch": 0.08172021042954186,
+      "grad_norm": 0.5066060423851013,
+      "learning_rate": 9.245748765770709e-06,
+      "loss": 0.6405,
+      "step": 1200
+    },
+    {
+      "epoch": 0.08240121218312137,
+      "grad_norm": 0.6000707149505615,
+      "learning_rate": 9.238891936368624e-06,
+      "loss": 0.6454,
+      "step": 1210
+    },
+    {
+      "epoch": 0.08308221393670089,
+      "grad_norm": 0.5418961644172668,
+      "learning_rate": 9.232035106966539e-06,
+      "loss": 0.6406,
+      "step": 1220
+    },
+    {
+      "epoch": 0.0837632156902804,
+      "grad_norm": 0.5262913107872009,
+      "learning_rate": 9.225178277564454e-06,
+      "loss": 0.6365,
+      "step": 1230
+    },
+    {
+      "epoch": 0.08444421744385992,
+      "grad_norm": 0.5714538097381592,
+      "learning_rate": 9.218321448162371e-06,
+      "loss": 0.6346,
+      "step": 1240
+    },
+    {
+      "epoch": 0.08512521919743943,
+      "grad_norm": 0.5763171911239624,
+      "learning_rate": 9.211464618760287e-06,
+      "loss": 0.627,
+      "step": 1250
+    },
+    {
+      "epoch": 0.08580622095101895,
+      "grad_norm": 0.5463062524795532,
+      "learning_rate": 9.204607789358202e-06,
+      "loss": 0.6389,
+      "step": 1260
+    },
+    {
+      "epoch": 0.08648722270459847,
+      "grad_norm": 0.5435475707054138,
+      "learning_rate": 9.197750959956117e-06,
+      "loss": 0.6365,
+      "step": 1270
+    },
+    {
+      "epoch": 0.08716822445817798,
+      "grad_norm": 0.5854077339172363,
+      "learning_rate": 9.190894130554032e-06,
+      "loss": 0.6366,
+      "step": 1280
+    },
+    {
+      "epoch": 0.08784922621175749,
+      "grad_norm": 0.5376425981521606,
+      "learning_rate": 9.184037301151948e-06,
+      "loss": 0.6337,
+      "step": 1290
+    },
+    {
+      "epoch": 0.08853022796533701,
+      "grad_norm": 0.5208784341812134,
+      "learning_rate": 9.177180471749863e-06,
+      "loss": 0.6231,
+      "step": 1300
+    },
+    {
+      "epoch": 0.08921122971891653,
+      "grad_norm": 0.5292302966117859,
+      "learning_rate": 9.17032364234778e-06,
+      "loss": 0.6298,
+      "step": 1310
+    },
+    {
+      "epoch": 0.08989223147249605,
+      "grad_norm": 0.5958801507949829,
+      "learning_rate": 9.163466812945695e-06,
+      "loss": 0.6382,
+      "step": 1320
+    },
+    {
+      "epoch": 0.09057323322607556,
+      "grad_norm": 0.5794044733047485,
+      "learning_rate": 9.15660998354361e-06,
+      "loss": 0.6461,
+      "step": 1330
+    },
+    {
+      "epoch": 0.09125423497965507,
+      "grad_norm": 0.609316349029541,
+      "learning_rate": 9.149753154141526e-06,
+      "loss": 0.631,
+      "step": 1340
+    },
+    {
+      "epoch": 0.09193523673323459,
+      "grad_norm": 0.5391581058502197,
+      "learning_rate": 9.142896324739441e-06,
+      "loss": 0.6383,
+      "step": 1350
+    },
+    {
+      "epoch": 0.0926162384868141,
+      "grad_norm": 0.5629425644874573,
+      "learning_rate": 9.136039495337356e-06,
+      "loss": 0.6288,
+      "step": 1360
+    },
+    {
+      "epoch": 0.09329724024039363,
+      "grad_norm": 0.541072428226471,
+      "learning_rate": 9.129182665935272e-06,
+      "loss": 0.6356,
+      "step": 1370
+    },
+    {
+      "epoch": 0.09397824199397313,
+      "grad_norm": 0.5951557755470276,
+      "learning_rate": 9.122325836533189e-06,
+      "loss": 0.6241,
+      "step": 1380
+    },
+    {
+      "epoch": 0.09465924374755265,
+      "grad_norm": 0.6719557046890259,
+      "learning_rate": 9.115469007131104e-06,
+      "loss": 0.6291,
+      "step": 1390
+    },
+    {
+      "epoch": 0.09534024550113217,
+      "grad_norm": 0.6028068661689758,
+      "learning_rate": 9.10861217772902e-06,
+      "loss": 0.6367,
+      "step": 1400
+    },
+    {
+      "epoch": 0.09602124725471169,
+      "grad_norm": 0.5842519998550415,
+      "learning_rate": 9.101755348326934e-06,
+      "loss": 0.6453,
+      "step": 1410
+    },
+    {
+      "epoch": 0.09670224900829119,
+      "grad_norm": 0.6063488125801086,
+      "learning_rate": 9.09489851892485e-06,
+      "loss": 0.6296,
+      "step": 1420
+    },
+    {
+      "epoch": 0.09738325076187071,
+      "grad_norm": 0.6148585081100464,
+      "learning_rate": 9.088041689522765e-06,
+      "loss": 0.619,
+      "step": 1430
+    },
+    {
+      "epoch": 0.09806425251545023,
+      "grad_norm": 0.629714846611023,
+      "learning_rate": 9.08118486012068e-06,
+      "loss": 0.6316,
+      "step": 1440
+    },
+    {
+      "epoch": 0.09874525426902975,
+      "grad_norm": 0.5103653073310852,
+      "learning_rate": 9.074328030718597e-06,
+      "loss": 0.6394,
+      "step": 1450
+    },
+    {
+      "epoch": 0.09942625602260925,
+      "grad_norm": 0.6765934824943542,
+      "learning_rate": 9.067471201316513e-06,
+      "loss": 0.6333,
+      "step": 1460
+    },
+    {
+      "epoch": 0.10010725777618877,
+      "grad_norm": 0.6415141820907593,
+      "learning_rate": 9.060614371914428e-06,
+      "loss": 0.6251,
+      "step": 1470
+    },
+    {
+      "epoch": 0.10078825952976829,
+      "grad_norm": 0.6874791979789734,
+      "learning_rate": 9.053757542512343e-06,
+      "loss": 0.627,
+      "step": 1480
+    },
+    {
+      "epoch": 0.10146926128334781,
+      "grad_norm": 0.5784174203872681,
+      "learning_rate": 9.046900713110258e-06,
+      "loss": 0.6221,
+      "step": 1490
+    },
+    {
+      "epoch": 0.10215026303692731,
+      "grad_norm": 0.6107547283172607,
+      "learning_rate": 9.040043883708174e-06,
+      "loss": 0.629,
+      "step": 1500
+    },
+    {
+      "epoch": 0.10283126479050683,
+      "grad_norm": 0.5333680510520935,
+      "learning_rate": 9.033187054306089e-06,
+      "loss": 0.6334,
+      "step": 1510
+    },
+    {
+      "epoch": 0.10351226654408635,
+      "grad_norm": 0.6641663908958435,
+      "learning_rate": 9.026330224904006e-06,
+      "loss": 0.6235,
+      "step": 1520
+    },
+    {
+      "epoch": 0.10419326829766587,
+      "grad_norm": 0.6097263097763062,
+      "learning_rate": 9.019473395501921e-06,
+      "loss": 0.6076,
+      "step": 1530
+    },
+    {
+      "epoch": 0.10487427005124539,
+      "grad_norm": 0.6092356443405151,
+      "learning_rate": 9.012616566099836e-06,
+      "loss": 0.6246,
+      "step": 1540
+    },
+    {
+      "epoch": 0.1055552718048249,
+      "grad_norm": 0.5857838988304138,
+      "learning_rate": 9.005759736697752e-06,
+      "loss": 0.626,
+      "step": 1550
+    },
+    {
+      "epoch": 0.10623627355840441,
+      "grad_norm": 0.6917974352836609,
+      "learning_rate": 8.998902907295667e-06,
+      "loss": 0.6212,
+      "step": 1560
+    },
+    {
+      "epoch": 0.10691727531198393,
+      "grad_norm": 0.6106289029121399,
+      "learning_rate": 8.992046077893582e-06,
+      "loss": 0.6172,
+      "step": 1570
+    },
+    {
+      "epoch": 0.10759827706556345,
+      "grad_norm": 0.5827699303627014,
+      "learning_rate": 8.985189248491498e-06,
+      "loss": 0.6101,
+      "step": 1580
+    },
+    {
+      "epoch": 0.10827927881914295,
+      "grad_norm": 0.583633542060852,
+      "learning_rate": 8.978332419089415e-06,
+      "loss": 0.6343,
+      "step": 1590
+    },
+    {
+      "epoch": 0.10896028057272247,
+      "grad_norm": 0.6340964436531067,
+      "learning_rate": 8.97147558968733e-06,
+      "loss": 0.6264,
+      "step": 1600
+    },
+    {
+      "epoch": 0.10964128232630199,
+      "grad_norm": 0.6629011631011963,
+      "learning_rate": 8.964618760285245e-06,
+      "loss": 0.6109,
+      "step": 1610
+    },
+    {
+      "epoch": 0.11032228407988151,
+      "grad_norm": 0.6184631586074829,
+      "learning_rate": 8.95776193088316e-06,
+      "loss": 0.6121,
+      "step": 1620
+    },
+    {
+      "epoch": 0.11100328583346102,
+      "grad_norm": 0.6361991167068481,
+      "learning_rate": 8.950905101481076e-06,
+      "loss": 0.6111,
+      "step": 1630
+    },
+    {
+      "epoch": 0.11168428758704053,
+      "grad_norm": 0.8150019645690918,
+      "learning_rate": 8.944048272078991e-06,
+      "loss": 0.6062,
+      "step": 1640
+    },
+    {
+      "epoch": 0.11236528934062005,
+      "grad_norm": 0.5992775559425354,
+      "learning_rate": 8.937191442676906e-06,
+      "loss": 0.6147,
+      "step": 1650
+    },
+    {
+      "epoch": 0.11304629109419957,
+      "grad_norm": 0.7319015264511108,
+      "learning_rate": 8.930334613274823e-06,
+      "loss": 0.6001,
+      "step": 1660
+    },
+    {
+      "epoch": 0.11372729284777908,
+      "grad_norm": 0.6276957392692566,
+      "learning_rate": 8.923477783872738e-06,
+      "loss": 0.6078,
+      "step": 1670
+    },
+    {
+      "epoch": 0.1144082946013586,
+      "grad_norm": 0.6116637587547302,
+      "learning_rate": 8.916620954470654e-06,
+      "loss": 0.6031,
+      "step": 1680
+    },
+    {
+      "epoch": 0.11508929635493811,
+      "grad_norm": 0.6107293963432312,
+      "learning_rate": 8.909764125068569e-06,
+      "loss": 0.6132,
+      "step": 1690
+    },
+    {
+      "epoch": 0.11577029810851763,
+      "grad_norm": 0.6744499802589417,
+      "learning_rate": 8.902907295666484e-06,
+      "loss": 0.5986,
+      "step": 1700
+    },
+    {
+      "epoch": 0.11645129986209715,
+      "grad_norm": 0.5552632212638855,
+      "learning_rate": 8.8960504662644e-06,
+      "loss": 0.6147,
+      "step": 1710
+    },
+    {
+      "epoch": 0.11713230161567666,
+      "grad_norm": 0.6451056599617004,
+      "learning_rate": 8.889193636862315e-06,
+      "loss": 0.6058,
+      "step": 1720
+    },
+    {
+      "epoch": 0.11781330336925618,
+      "grad_norm": 0.59438157081604,
+      "learning_rate": 8.882336807460232e-06,
+      "loss": 0.6058,
+      "step": 1730
+    },
+    {
+      "epoch": 0.1184943051228357,
+      "grad_norm": 0.6641702055931091,
+      "learning_rate": 8.875479978058147e-06,
+      "loss": 0.6056,
+      "step": 1740
+    },
+    {
+      "epoch": 0.11917530687641521,
+      "grad_norm": 0.594817578792572,
+      "learning_rate": 8.868623148656062e-06,
+      "loss": 0.6059,
+      "step": 1750
+    },
+    {
+      "epoch": 0.11985630862999472,
+      "grad_norm": 0.6780447363853455,
+      "learning_rate": 8.861766319253978e-06,
+      "loss": 0.6004,
+      "step": 1760
+    },
+    {
+      "epoch": 0.12053731038357424,
+      "grad_norm": 0.6457318067550659,
+      "learning_rate": 8.854909489851893e-06,
+      "loss": 0.6024,
+      "step": 1770
+    },
+    {
+      "epoch": 0.12121831213715376,
+      "grad_norm": 0.6741064786911011,
+      "learning_rate": 8.848052660449808e-06,
+      "loss": 0.5977,
+      "step": 1780
+    },
+    {
+      "epoch": 0.12189931389073327,
+      "grad_norm": 0.622666597366333,
+      "learning_rate": 8.841195831047723e-06,
+      "loss": 0.5975,
+      "step": 1790
+    },
+    {
+      "epoch": 0.12258031564431278,
+      "grad_norm": 0.6451845169067383,
+      "learning_rate": 8.83433900164564e-06,
+      "loss": 0.6011,
+      "step": 1800
+    },
+    {
+      "epoch": 0.1232613173978923,
+      "grad_norm": 0.6236549615859985,
+      "learning_rate": 8.827482172243556e-06,
+      "loss": 0.61,
+      "step": 1810
+    },
+    {
+      "epoch": 0.12394231915147182,
+      "grad_norm": 0.6918080449104309,
+      "learning_rate": 8.820625342841471e-06,
+      "loss": 0.5955,
+      "step": 1820
+    },
+    {
+      "epoch": 0.12462332090505134,
+      "grad_norm": 0.6165505051612854,
+      "learning_rate": 8.813768513439386e-06,
+      "loss": 0.6039,
+      "step": 1830
+    },
+    {
+      "epoch": 0.12530432265863084,
+      "grad_norm": 0.6684593558311462,
+      "learning_rate": 8.806911684037302e-06,
+      "loss": 0.6033,
+      "step": 1840
+    },
+    {
+      "epoch": 0.12598532441221036,
+      "grad_norm": 0.662586510181427,
+      "learning_rate": 8.800054854635217e-06,
+      "loss": 0.5905,
+      "step": 1850
+    },
+    {
+      "epoch": 0.12666632616578988,
+      "grad_norm": 0.6298710703849792,
+      "learning_rate": 8.793198025233132e-06,
+      "loss": 0.6016,
+      "step": 1860
+    },
+    {
+      "epoch": 0.1273473279193694,
+      "grad_norm": 0.6389495730400085,
+      "learning_rate": 8.786341195831049e-06,
+      "loss": 0.59,
+      "step": 1870
+    },
+    {
+      "epoch": 0.12802832967294892,
+      "grad_norm": 0.6254614591598511,
+      "learning_rate": 8.779484366428964e-06,
+      "loss": 0.5997,
+      "step": 1880
+    },
+    {
+      "epoch": 0.12870933142652843,
+      "grad_norm": 0.6002387404441833,
+      "learning_rate": 8.77262753702688e-06,
+      "loss": 0.6008,
+      "step": 1890
+    },
+    {
+      "epoch": 0.12939033318010795,
+      "grad_norm": 0.6924214363098145,
+      "learning_rate": 8.765770707624795e-06,
+      "loss": 0.6058,
+      "step": 1900
+    },
+    {
+      "epoch": 0.13007133493368744,
+      "grad_norm": 0.6694520115852356,
+      "learning_rate": 8.75891387822271e-06,
+      "loss": 0.6135,
+      "step": 1910
+    },
+    {
+      "epoch": 0.13075233668726696,
+      "grad_norm": 0.6518706679344177,
+      "learning_rate": 8.752057048820625e-06,
+      "loss": 0.6053,
+      "step": 1920
+    },
+    {
+      "epoch": 0.13143333844084648,
+      "grad_norm": 0.6506664156913757,
+      "learning_rate": 8.74520021941854e-06,
+      "loss": 0.5953,
+      "step": 1930
+    },
+    {
+      "epoch": 0.132114340194426,
+      "grad_norm": 0.6805129647254944,
+      "learning_rate": 8.738343390016458e-06,
+      "loss": 0.6001,
+      "step": 1940
+    },
+    {
+      "epoch": 0.13279534194800552,
+      "grad_norm": 0.6900282502174377,
+      "learning_rate": 8.731486560614373e-06,
+      "loss": 0.5841,
+      "step": 1950
+    },
+    {
+      "epoch": 0.13347634370158504,
+      "grad_norm": 0.6625066995620728,
+      "learning_rate": 8.724629731212288e-06,
+      "loss": 0.5985,
+      "step": 1960
+    },
+    {
+      "epoch": 0.13415734545516456,
+      "grad_norm": 0.6504208445549011,
+      "learning_rate": 8.717772901810204e-06,
+      "loss": 0.6027,
+      "step": 1970
+    },
+    {
+      "epoch": 0.13483834720874407,
+      "grad_norm": 0.7231308221817017,
+      "learning_rate": 8.710916072408119e-06,
+      "loss": 0.607,
+      "step": 1980
+    },
+    {
+      "epoch": 0.13551934896232357,
+      "grad_norm": 0.6810206174850464,
+      "learning_rate": 8.704059243006034e-06,
+      "loss": 0.6042,
+      "step": 1990
+    },
+    {
+      "epoch": 0.13620035071590308,
+      "grad_norm": 0.6969956159591675,
+      "learning_rate": 8.69720241360395e-06,
+      "loss": 0.5927,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 14684,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.193438654464e+17,
+  "train_batch_size": 5,
+  "trial_name": null,
+  "trial_params": null
+}

pgn_adapter_logs/mistral_pgn-tesis/checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a845ae87ee071d7036e1c72e6d15f86bec17d47b6c457d57e66a0fb6b24226b
+size 5176