LoRA actualizado: entrenamiento con 1 época

.gitattributes

@@ -1,3 +1,4 @@
+<<<<<<< HEAD
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
@@ -33,3 +34,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+=======
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+>>>>>>> 76f198e (Add LoRA adapter (StarCoder 1B) + tokenizer metadata)

.gitignore

@@ -0,0 +1,6 @@
+checkpoint-*/
+*.pt
+*.bin
+runs/
+logs/
+

README.md

@@ -0,0 +1,207 @@
+---
+base_model: bigcode/starcoderbase-1b
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:bigcode/starcoderbase-1b
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigcode/starcoderbase-1b",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "w2",
+    "q_attn",
+    "c_proj",
+    "fc_out",
+    "c_attn",
+    "v_proj",
+    "w1",
+    "k_proj",
+    "fc_in",
+    "w3"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07acf660be1fb0743fd84d3362626d55d3bd7170331f6d8976c504bcb81e88f9
+size 28723448

checkpoint-1/README.md

@@ -0,0 +1,207 @@
+---
+base_model: bigcode/starcoderbase-1b
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:bigcode/starcoderbase-1b
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-1/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigcode/starcoderbase-1b",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "w2",
+    "q_attn",
+    "c_proj",
+    "fc_out",
+    "c_attn",
+    "v_proj",
+    "w1",
+    "k_proj",
+    "fc_in",
+    "w3"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07acf660be1fb0743fd84d3362626d55d3bd7170331f6d8976c504bcb81e88f9
+size 28723448

checkpoint-1/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc2643cd6beb434ac63c2bd6ab465a529703c5e9fa69f4e7563a3670e5c9b596
+size 57495546

checkpoint-1/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41523a02aa5a848025e81d91cc04e6400cb32a2ae2b439b8f2cca6bd660dc93b
+size 14244

checkpoint-1/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31017ff690e8312759fe6512fd241ba617cb3d42fe6c14cbdd426bcb6b454f8b
+size 1064

checkpoint-1/special_tokens_map.json

@@ -0,0 +1,45 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1/tokenizer_config.json

@@ -0,0 +1,187 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

checkpoint-1/trainer_state.json

@@ -0,0 +1,33 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.16,
+  "eval_steps": 500,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [],
+  "logging_steps": 50,
+  "max_steps": 1,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 201905204625408.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d006cbe0053f1bdb26902e5133c9d463f9a400f19d1fce74eea896e0a58c543
+size 5432

special_tokens_map.json

@@ -0,0 +1,45 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,187 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

train_e1.log

@@ -0,0 +1,412 @@
+⚙️ Config -> BATCH_PER_DEVICE=1, GRAD_ACC=32, MAX_LEN=1024, LR=0.0002, EPOCHS_TOTAL=1.0, CHUNK_SIZE=300, TOK_BATCH=32
+📦 DATA_PATH=/workspace/data/evaluaciones_pares_input_output.jsonl.gz
+🔠 Cargando tokenizador...
+🧠 Cargando modelo base 4-bit...
+♻️  Retomando desde checkpoint previo...
+trainable params: 7,176,192 || all params: 1,144,383,488 || trainable%: 0.6271
+🔢 Contando líneas totales (una pasada) ...
+✅ Total de líneas: 20000
+
+==================== BLOQUE 1 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 8.7478, 'train_samples_per_second': 0.514, 'train_steps_per_second': 0.114, 'train_loss': 1.3522244691848755, 'epoch': 0.11}
+✅ Bloque 1 terminado. Acumulado: 300/20000 líneas | global_step=1
+
+==================== BLOQUE 2 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8455, 'train_samples_per_second': 0.574, 'train_steps_per_second': 0.127, 'train_loss': 1.4102396965026855, 'epoch': 0.11}
+✅ Bloque 2 terminado. Acumulado: 600/20000 líneas | global_step=1
+
+==================== BLOQUE 3 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8688, 'train_samples_per_second': 0.572, 'train_steps_per_second': 0.127, 'train_loss': 1.376889705657959, 'epoch': 0.11}
+✅ Bloque 3 terminado. Acumulado: 900/20000 líneas | global_step=1
+
+==================== BLOQUE 4 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.9219, 'train_samples_per_second': 0.568, 'train_steps_per_second': 0.126, 'train_loss': 1.4048157930374146, 'epoch': 0.11}
+✅ Bloque 4 terminado. Acumulado: 1200/20000 líneas | global_step=1
+
+==================== BLOQUE 5 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8425, 'train_samples_per_second': 0.574, 'train_steps_per_second': 0.128, 'train_loss': 1.4059597253799438, 'epoch': 0.11}
+✅ Bloque 5 terminado. Acumulado: 1500/20000 líneas | global_step=1
+
+==================== BLOQUE 6 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8155, 'train_samples_per_second': 0.576, 'train_steps_per_second': 0.128, 'train_loss': 1.3940027952194214, 'epoch': 0.11}
+✅ Bloque 6 terminado. Acumulado: 1800/20000 líneas | global_step=1
+
+==================== BLOQUE 7 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.9907, 'train_samples_per_second': 0.563, 'train_steps_per_second': 0.125, 'train_loss': 1.3537384271621704, 'epoch': 0.11}
+✅ Bloque 7 terminado. Acumulado: 2100/20000 líneas | global_step=1
+
+==================== BLOQUE 8 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 8.029, 'train_samples_per_second': 0.56, 'train_steps_per_second': 0.125, 'train_loss': 1.3489651679992676, 'epoch': 0.11}
+✅ Bloque 8 terminado. Acumulado: 2400/20000 líneas | global_step=1
+
+==================== BLOQUE 9 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8209, 'train_samples_per_second': 0.575, 'train_steps_per_second': 0.128, 'train_loss': 1.4223603010177612, 'epoch': 0.11}
+✅ Bloque 9 terminado. Acumulado: 2700/20000 líneas | global_step=1
+
+==================== BLOQUE 10 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.796, 'train_samples_per_second': 0.577, 'train_steps_per_second': 0.128, 'train_loss': 1.4088714122772217, 'epoch': 0.11}
+✅ Bloque 10 terminado. Acumulado: 3000/20000 líneas | global_step=1
+
+==================== BLOQUE 11 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.9274, 'train_samples_per_second': 0.568, 'train_steps_per_second': 0.126, 'train_loss': 1.4210320711135864, 'epoch': 0.11}
+✅ Bloque 11 terminado. Acumulado: 3300/20000 líneas | global_step=1
+
+==================== BLOQUE 12 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8712, 'train_samples_per_second': 0.572, 'train_steps_per_second': 0.127, 'train_loss': 1.4202042818069458, 'epoch': 0.11}
+✅ Bloque 12 terminado. Acumulado: 3600/20000 líneas | global_step=1
+
+==================== BLOQUE 13 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 8.4636, 'train_samples_per_second': 0.532, 'train_steps_per_second': 0.118, 'train_loss': 1.45803701877594, 'epoch': 0.11}
+✅ Bloque 13 terminado. Acumulado: 3900/20000 líneas | global_step=1
+
+==================== BLOQUE 14 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8809, 'train_samples_per_second': 0.571, 'train_steps_per_second': 0.127, 'train_loss': 1.375520944595337, 'epoch': 0.11}
+✅ Bloque 14 terminado. Acumulado: 4200/20000 líneas | global_step=1
+
+==================== BLOQUE 15 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 9.0132, 'train_samples_per_second': 0.499, 'train_steps_per_second': 0.111, 'train_loss': 1.4456514120101929, 'epoch': 0.11}
+✅ Bloque 15 terminado. Acumulado: 4500/20000 líneas | global_step=1
+
+==================== BLOQUE 16 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.9159, 'train_samples_per_second': 0.568, 'train_steps_per_second': 0.126, 'train_loss': 1.3990974426269531, 'epoch': 0.11}
+✅ Bloque 16 terminado. Acumulado: 4800/20000 líneas | global_step=1
+
+==================== BLOQUE 17 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8909, 'train_samples_per_second': 0.57, 'train_steps_per_second': 0.127, 'train_loss': 1.3655331134796143, 'epoch': 0.11}
+✅ Bloque 17 terminado. Acumulado: 5100/20000 líneas | global_step=1
+
+==================== BLOQUE 18 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 8.2736, 'train_samples_per_second': 0.544, 'train_steps_per_second': 0.121, 'train_loss': 1.367121696472168, 'epoch': 0.11}
+✅ Bloque 18 terminado. Acumulado: 5400/20000 líneas | global_step=1
+
+==================== BLOQUE 19 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8921, 'train_samples_per_second': 0.57, 'train_steps_per_second': 0.127, 'train_loss': 1.4294403791427612, 'epoch': 0.11}
+✅ Bloque 19 terminado. Acumulado: 5700/20000 líneas | global_step=1
+
+==================== BLOQUE 20 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8161, 'train_samples_per_second': 0.576, 'train_steps_per_second': 0.128, 'train_loss': 1.4076168537139893, 'epoch': 0.11}
+✅ Bloque 20 terminado. Acumulado: 6000/20000 líneas | global_step=1
+
+==================== BLOQUE 21 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.799, 'train_samples_per_second': 0.577, 'train_steps_per_second': 0.128, 'train_loss': 1.3925199508666992, 'epoch': 0.11}
+✅ Bloque 21 terminado. Acumulado: 6300/20000 líneas | global_step=1
+
+==================== BLOQUE 22 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 8.2108, 'train_samples_per_second': 0.548, 'train_steps_per_second': 0.122, 'train_loss': 1.3582611083984375, 'epoch': 0.11}
+✅ Bloque 22 terminado. Acumulado: 6600/20000 líneas | global_step=1
+
+==================== BLOQUE 23 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.9328, 'train_samples_per_second': 0.567, 'train_steps_per_second': 0.126, 'train_loss': 1.3844921588897705, 'epoch': 0.11}
+✅ Bloque 23 terminado. Acumulado: 6900/20000 líneas | global_step=1
+
+==================== BLOQUE 24 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 8.5347, 'train_samples_per_second': 0.527, 'train_steps_per_second': 0.117, 'train_loss': 1.4399304389953613, 'epoch': 0.11}
+✅ Bloque 24 terminado. Acumulado: 7200/20000 líneas | global_step=1
+
+==================== BLOQUE 25 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.945, 'train_samples_per_second': 0.566, 'train_steps_per_second': 0.126, 'train_loss': 1.4433614015579224, 'epoch': 0.11}
+✅ Bloque 25 terminado. Acumulado: 7500/20000 líneas | global_step=1
+
+==================== BLOQUE 26 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.9109, 'train_samples_per_second': 0.569, 'train_steps_per_second': 0.126, 'train_loss': 1.459897518157959, 'epoch': 0.11}
+✅ Bloque 26 terminado. Acumulado: 7800/20000 líneas | global_step=1
+
+==================== BLOQUE 27 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8354, 'train_samples_per_second': 0.574, 'train_steps_per_second': 0.128, 'train_loss': 1.4087351560592651, 'epoch': 0.11}
+✅ Bloque 27 terminado. Acumulado: 8100/20000 líneas | global_step=1
+
+==================== BLOQUE 28 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8052, 'train_samples_per_second': 0.577, 'train_steps_per_second': 0.128, 'train_loss': 1.3621701002120972, 'epoch': 0.11}
+✅ Bloque 28 terminado. Acumulado: 8400/20000 líneas | global_step=1
+
+==================== BLOQUE 29 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 8.2427, 'train_samples_per_second': 0.546, 'train_steps_per_second': 0.121, 'train_loss': 1.41074538230896, 'epoch': 0.11}
+✅ Bloque 29 terminado. Acumulado: 8700/20000 líneas | global_step=1
+
+==================== BLOQUE 30 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8657, 'train_samples_per_second': 0.572, 'train_steps_per_second': 0.127, 'train_loss': 1.352297067642212, 'epoch': 0.11}
+✅ Bloque 30 terminado. Acumulado: 9000/20000 líneas | global_step=1
+
+==================== BLOQUE 31 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8948, 'train_samples_per_second': 0.57, 'train_steps_per_second': 0.127, 'train_loss': 1.418897032737732, 'epoch': 0.11}
+✅ Bloque 31 terminado. Acumulado: 9300/20000 líneas | global_step=1
+
+==================== BLOQUE 32 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8016, 'train_samples_per_second': 0.577, 'train_steps_per_second': 0.128, 'train_loss': 1.4292913675308228, 'epoch': 0.11}
+✅ Bloque 32 terminado. Acumulado: 9600/20000 líneas | global_step=1
+
+==================== BLOQUE 33 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8676, 'train_samples_per_second': 0.572, 'train_steps_per_second': 0.127, 'train_loss': 1.3893479108810425, 'epoch': 0.11}
+✅ Bloque 33 terminado. Acumulado: 9900/20000 líneas | global_step=1
+
+==================== BLOQUE 34 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 8.3348, 'train_samples_per_second': 0.54, 'train_steps_per_second': 0.12, 'train_loss': 1.3993480205535889, 'epoch': 0.11}
+✅ Bloque 34 terminado. Acumulado: 10200/20000 líneas | global_step=1
+
+==================== BLOQUE 35 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8154, 'train_samples_per_second': 0.576, 'train_steps_per_second': 0.128, 'train_loss': 1.4724717140197754, 'epoch': 0.11}
+✅ Bloque 35 terminado. Acumulado: 10500/20000 líneas | global_step=1
+
+==================== BLOQUE 36 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 8.2463, 'train_samples_per_second': 0.546, 'train_steps_per_second': 0.121, 'train_loss': 1.3512485027313232, 'epoch': 0.11}
+✅ Bloque 36 terminado. Acumulado: 10800/20000 líneas | global_step=1
+
+==================== BLOQUE 37 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 8.0336, 'train_samples_per_second': 0.56, 'train_steps_per_second': 0.124, 'train_loss': 1.3714691400527954, 'epoch': 0.11}
+✅ Bloque 37 terminado. Acumulado: 11100/20000 líneas | global_step=1
+
+==================== BLOQUE 38 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 8.0084, 'train_samples_per_second': 0.562, 'train_steps_per_second': 0.125, 'train_loss': 1.4171221256256104, 'epoch': 0.11}
+✅ Bloque 38 terminado. Acumulado: 11400/20000 líneas | global_step=1
+
+==================== BLOQUE 39 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8908, 'train_samples_per_second': 0.57, 'train_steps_per_second': 0.127, 'train_loss': 1.4297702312469482, 'epoch': 0.11}
+✅ Bloque 39 terminado. Acumulado: 11700/20000 líneas | global_step=1
+
+==================== BLOQUE 40 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8308, 'train_samples_per_second': 0.575, 'train_steps_per_second': 0.128, 'train_loss': 1.4469853639602661, 'epoch': 0.11}
+✅ Bloque 40 terminado. Acumulado: 12000/20000 líneas | global_step=1
+
+==================== BLOQUE 41 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 8.0149, 'train_samples_per_second': 0.561, 'train_steps_per_second': 0.125, 'train_loss': 1.4268006086349487, 'epoch': 0.11}
+✅ Bloque 41 terminado. Acumulado: 12300/20000 líneas | global_step=1
+
+==================== BLOQUE 42 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.9279, 'train_samples_per_second': 0.568, 'train_steps_per_second': 0.126, 'train_loss': 1.4060312509536743, 'epoch': 0.11}
+✅ Bloque 42 terminado. Acumulado: 12600/20000 líneas | global_step=1
+
+==================== BLOQUE 43 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.927, 'train_samples_per_second': 0.568, 'train_steps_per_second': 0.126, 'train_loss': 1.473849892616272, 'epoch': 0.11}
+✅ Bloque 43 terminado. Acumulado: 12900/20000 líneas | global_step=1
+
+==================== BLOQUE 44 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8225, 'train_samples_per_second': 0.575, 'train_steps_per_second': 0.128, 'train_loss': 1.4086536169052124, 'epoch': 0.11}
+✅ Bloque 44 terminado. Acumulado: 13200/20000 líneas | global_step=1
+
+==================== BLOQUE 45 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 8.038, 'train_samples_per_second': 0.56, 'train_steps_per_second': 0.124, 'train_loss': 1.4090956449508667, 'epoch': 0.11}
+✅ Bloque 45 terminado. Acumulado: 13500/20000 líneas | global_step=1
+
+==================== BLOQUE 46 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8592, 'train_samples_per_second': 0.573, 'train_steps_per_second': 0.127, 'train_loss': 1.4210567474365234, 'epoch': 0.11}
+✅ Bloque 46 terminado. Acumulado: 13800/20000 líneas | global_step=1
+
+==================== BLOQUE 47 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.985, 'train_samples_per_second': 0.564, 'train_steps_per_second': 0.125, 'train_loss': 1.357202172279358, 'epoch': 0.11}
+✅ Bloque 47 terminado. Acumulado: 14100/20000 líneas | global_step=1
+
+==================== BLOQUE 48 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8731, 'train_samples_per_second': 0.572, 'train_steps_per_second': 0.127, 'train_loss': 1.4002933502197266, 'epoch': 0.11}
+✅ Bloque 48 terminado. Acumulado: 14400/20000 líneas | global_step=1
+
+==================== BLOQUE 49 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8413, 'train_samples_per_second': 0.574, 'train_steps_per_second': 0.128, 'train_loss': 1.4064139127731323, 'epoch': 0.11}
+✅ Bloque 49 terminado. Acumulado: 14700/20000 líneas | global_step=1
+
+==================== BLOQUE 50 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.9053, 'train_samples_per_second': 0.569, 'train_steps_per_second': 0.126, 'train_loss': 1.4215424060821533, 'epoch': 0.11}
+✅ Bloque 50 terminado. Acumulado: 15000/20000 líneas | global_step=1
+
+==================== BLOQUE 51 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 8.4462, 'train_samples_per_second': 0.533, 'train_steps_per_second': 0.118, 'train_loss': 1.397919774055481, 'epoch': 0.11}
+✅ Bloque 51 terminado. Acumulado: 15300/20000 líneas | global_step=1
+
+==================== BLOQUE 52 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8452, 'train_samples_per_second': 0.574, 'train_steps_per_second': 0.127, 'train_loss': 1.4646857976913452, 'epoch': 0.11}
+✅ Bloque 52 terminado. Acumulado: 15600/20000 líneas | global_step=1
+
+==================== BLOQUE 53 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.7995, 'train_samples_per_second': 0.577, 'train_steps_per_second': 0.128, 'train_loss': 1.395652413368225, 'epoch': 0.11}
+✅ Bloque 53 terminado. Acumulado: 15900/20000 líneas | global_step=1
+
+==================== BLOQUE 54 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8485, 'train_samples_per_second': 0.573, 'train_steps_per_second': 0.127, 'train_loss': 1.367691159248352, 'epoch': 0.11}
+✅ Bloque 54 terminado. Acumulado: 16200/20000 líneas | global_step=1
+
+==================== BLOQUE 55 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.9295, 'train_samples_per_second': 0.567, 'train_steps_per_second': 0.126, 'train_loss': 1.4012526273727417, 'epoch': 0.11}
+✅ Bloque 55 terminado. Acumulado: 16500/20000 líneas | global_step=1
+
+==================== BLOQUE 56 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.884, 'train_samples_per_second': 0.571, 'train_steps_per_second': 0.127, 'train_loss': 1.3737818002700806, 'epoch': 0.11}
+✅ Bloque 56 terminado. Acumulado: 16800/20000 líneas | global_step=1
+
+==================== BLOQUE 57 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.79, 'train_samples_per_second': 0.578, 'train_steps_per_second': 0.128, 'train_loss': 1.4407134056091309, 'epoch': 0.11}
+✅ Bloque 57 terminado. Acumulado: 17100/20000 líneas | global_step=1
+
+==================== BLOQUE 58 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.9038, 'train_samples_per_second': 0.569, 'train_steps_per_second': 0.127, 'train_loss': 1.4103862047195435, 'epoch': 0.11}
+✅ Bloque 58 terminado. Acumulado: 17400/20000 líneas | global_step=1
+
+==================== BLOQUE 59 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.9517, 'train_samples_per_second': 0.566, 'train_steps_per_second': 0.126, 'train_loss': 1.4260621070861816, 'epoch': 0.11}
+✅ Bloque 59 terminado. Acumulado: 17700/20000 líneas | global_step=1
+
+==================== BLOQUE 60 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8696, 'train_samples_per_second': 0.572, 'train_steps_per_second': 0.127, 'train_loss': 1.43145751953125, 'epoch': 0.11}
+✅ Bloque 60 terminado. Acumulado: 18000/20000 líneas | global_step=1
+
+==================== BLOQUE 61 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.7647, 'train_samples_per_second': 0.58, 'train_steps_per_second': 0.129, 'train_loss': 1.4067848920822144, 'epoch': 0.11}
+✅ Bloque 61 terminado. Acumulado: 18300/20000 líneas | global_step=1
+
+==================== BLOQUE 62 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8886, 'train_samples_per_second': 0.57, 'train_steps_per_second': 0.127, 'train_loss': 1.444780707359314, 'epoch': 0.11}
+✅ Bloque 62 terminado. Acumulado: 18600/20000 líneas | global_step=1
+
+==================== BLOQUE 63 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.7427, 'train_samples_per_second': 0.581, 'train_steps_per_second': 0.129, 'train_loss': 1.397607445716858, 'epoch': 0.11}
+✅ Bloque 63 terminado. Acumulado: 18900/20000 líneas | global_step=1
+
+==================== BLOQUE 64 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.832, 'train_samples_per_second': 0.575, 'train_steps_per_second': 0.128, 'train_loss': 1.3948101997375488, 'epoch': 0.11}
+✅ Bloque 64 terminado. Acumulado: 19200/20000 líneas | global_step=1
+
+==================== BLOQUE 65 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8257, 'train_samples_per_second': 0.575, 'train_steps_per_second': 0.128, 'train_loss': 1.3686237335205078, 'epoch': 0.11}
+✅ Bloque 65 terminado. Acumulado: 19500/20000 líneas | global_step=1
+
+==================== BLOQUE 66 ====================
+🧩 Ejemplos en bloque: 300
+⏱️  Épocas en este bloque: 0.0150
+{'train_runtime': 7.8839, 'train_samples_per_second': 0.571, 'train_steps_per_second': 0.127, 'train_loss': 1.4106920957565308, 'epoch': 0.11}
+✅ Bloque 66 terminado. Acumulado: 19800/20000 líneas | global_step=1
+
+==================== BLOQUE 67 ====================
+🧩 Ejemplos en bloque: 200
+⏱️  Épocas en este bloque: 0.0100
+{'train_runtime': 7.9257, 'train_samples_per_second': 0.252, 'train_steps_per_second': 0.126, 'train_loss': 1.433011770248413, 'epoch': 0.16}
+✅ Bloque 67 terminado. Acumulado: 20000/20000 líneas | global_step=1
+
+🎉 Entrenamiento TOTAL completado. Modelo en: /workspace/output/starcoder_1b_qlora

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d006cbe0053f1bdb26902e5133c9d463f9a400f19d1fce74eea896e0a58c543
+size 5432