Upload folder using huggingface_hub

README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- autotrain
+- text-generation
+widget:
+- text: "I love AutoTrain because "
+---
+
+# Model Trained Using AutoTrain

adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0f5a1b9ae33e2e92f5b02b96a74ce6a781750ef9f2091cbff0375bf1165e85d
+size 33600906

checkpoint-2380/README.md

@@ -0,0 +1,238 @@
+---
+library_name: peft
+base_model: meta-llama/Llama-2-7b-hf
+---
+
+# 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]
+- **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 Data 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 Data 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.0
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.0

checkpoint-2380/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-2380/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51430b20414330f1f77fd5d6ecf7d8b1953be2d176c464416a1c0b1bfb152bb6
+size 33600906

checkpoint-2380/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35c8820932d182dab92f84f881caa13f3998e61fb13ff5a45f7c132297e2031a
+size 67217018

checkpoint-2380/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
+size 888

checkpoint-2380/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d53c30e8cae3cecc3b965f486aa7445b8e39e418ddb9546bbaded5fbf4f72ac
+size 15024

checkpoint-2380/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b599f0f5d8701b478e60f9507befa835dc036563680e73d5d238852a010e881
+size 15024

checkpoint-2380/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa58c2632937d2b2e02a5f156e8fb398ba3e312846423b6e2f02ed7577a1f1b3
+size 15024

checkpoint-2380/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1947c19435b371e018617c92fa81b4f603b28021b1a3037358c5142978891f4
+size 15024

checkpoint-2380/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4ab8618b2ca6faacf4865e8e16a4c0772059e637593c1c6f712630c0682b887
+size 1064

checkpoint-2380/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2380/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-2380/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1024,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-2380/trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 88.97196261682242,
+  "eval_steps": 500,
+  "global_step": 2380,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.18,
+      "learning_rate": 0.0003269230769230769,
+      "loss": 1.6646,
+      "step": 85
+    },
+    {
+      "epoch": 6.36,
+      "learning_rate": 0.0006538461538461538,
+      "loss": 1.517,
+      "step": 170
+    },
+    {
+      "epoch": 9.53,
+      "learning_rate": 0.0009807692307692308,
+      "loss": 1.4586,
+      "step": 255
+    },
+    {
+      "epoch": 12.71,
+      "learning_rate": 0.0009658119658119658,
+      "loss": 1.3597,
+      "step": 340
+    },
+    {
+      "epoch": 15.89,
+      "learning_rate": 0.0009294871794871796,
+      "loss": 1.2625,
+      "step": 425
+    },
+    {
+      "epoch": 19.07,
+      "learning_rate": 0.0008931623931623932,
+      "loss": 1.1835,
+      "step": 510
+    },
+    {
+      "epoch": 22.24,
+      "learning_rate": 0.0008568376068376068,
+      "loss": 1.1184,
+      "step": 595
+    },
+    {
+      "epoch": 25.42,
+      "learning_rate": 0.0008205128205128205,
+      "loss": 1.0683,
+      "step": 680
+    },
+    {
+      "epoch": 28.6,
+      "learning_rate": 0.0007841880341880342,
+      "loss": 1.0321,
+      "step": 765
+    },
+    {
+      "epoch": 31.78,
+      "learning_rate": 0.0007478632478632479,
+      "loss": 1.0009,
+      "step": 850
+    },
+    {
+      "epoch": 34.95,
+      "learning_rate": 0.0007115384615384616,
+      "loss": 0.9663,
+      "step": 935
+    },
+    {
+      "epoch": 38.13,
+      "learning_rate": 0.0006752136752136753,
+      "loss": 0.938,
+      "step": 1020
+    },
+    {
+      "epoch": 41.31,
+      "learning_rate": 0.0006388888888888888,
+      "loss": 0.9178,
+      "step": 1105
+    },
+    {
+      "epoch": 44.49,
+      "learning_rate": 0.0006025641025641026,
+      "loss": 0.8984,
+      "step": 1190
+    },
+    {
+      "epoch": 47.66,
+      "learning_rate": 0.0005662393162393163,
+      "loss": 0.8827,
+      "step": 1275
+    },
+    {
+      "epoch": 50.84,
+      "learning_rate": 0.0005299145299145299,
+      "loss": 0.8693,
+      "step": 1360
+    },
+    {
+      "epoch": 54.02,
+      "learning_rate": 0.0004935897435897436,
+      "loss": 0.8514,
+      "step": 1445
+    },
+    {
+      "epoch": 57.2,
+      "learning_rate": 0.0004572649572649573,
+      "loss": 0.8349,
+      "step": 1530
+    },
+    {
+      "epoch": 60.37,
+      "learning_rate": 0.00042094017094017095,
+      "loss": 0.824,
+      "step": 1615
+    },
+    {
+      "epoch": 63.55,
+      "learning_rate": 0.00038461538461538467,
+      "loss": 0.8138,
+      "step": 1700
+    },
+    {
+      "epoch": 66.73,
+      "learning_rate": 0.0003482905982905983,
+      "loss": 0.8044,
+      "step": 1785
+    },
+    {
+      "epoch": 69.91,
+      "learning_rate": 0.00031196581196581195,
+      "loss": 0.7962,
+      "step": 1870
+    },
+    {
+      "epoch": 73.08,
+      "learning_rate": 0.0002756410256410257,
+      "loss": 0.7854,
+      "step": 1955
+    },
+    {
+      "epoch": 76.26,
+      "learning_rate": 0.00023931623931623932,
+      "loss": 0.7756,
+      "step": 2040
+    },
+    {
+      "epoch": 79.44,
+      "learning_rate": 0.000202991452991453,
+      "loss": 0.7663,
+      "step": 2125
+    },
+    {
+      "epoch": 82.62,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 0.7569,
+      "step": 2210
+    },
+    {
+      "epoch": 85.79,
+      "learning_rate": 0.00013034188034188036,
+      "loss": 0.7491,
+      "step": 2295
+    },
+    {
+      "epoch": 88.97,
+      "learning_rate": 9.401709401709401e-05,
+      "loss": 0.7427,
+      "step": 2380
+    }
+  ],
+  "logging_steps": 85,
+  "max_steps": 2600,
+  "num_train_epochs": 100,
+  "save_steps": 500,
+  "total_flos": 2.477324416948214e+19,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2380/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43cc490960b33ae18d92aab5dda2ba89068e31d8d3180c7226b60976ac62797c
+size 4536

checkpoint-2407/README.md

@@ -0,0 +1,238 @@
+---
+library_name: peft
+base_model: meta-llama/Llama-2-7b-hf
+---
+
+# 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]
+- **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 Data 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 Data 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.0
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.0

checkpoint-2407/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-2407/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89ad937e5b80424d6580e4867698a0b6c5169f44d7103ee93e5e89c4a3041311
+size 33600906

checkpoint-2407/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee93e0cfa31f71477774d1f1f701c3de0a548e1f871865d1721c15317188f3ce
+size 67217018

checkpoint-2407/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
+size 888

checkpoint-2407/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d791275f2de57950c798371f9bddea3910d0b5c8e419fe04ae3e6b0950f875f8
+size 15024

checkpoint-2407/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b7e33161995d577b198a852449e445b5cd8b1a2038a3f04f0b402d8dd7b91be
+size 15024

checkpoint-2407/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:928e9487fa4b2b7f9901ae6604723d89d802a08ec7ed4bfb3e1bb747166f0ff5
+size 15024

checkpoint-2407/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95a6cdad2c2efa89d63c8823df4582c41850ed5ec51b0ee0bb3f9f009b7d34ea
+size 15024

checkpoint-2407/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1d77e203410139e38f01e292ca03545ecad1a989e81959c619d2cfc28ada227
+size 1064

checkpoint-2407/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2407/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-2407/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1024,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-2407/trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 89.98130841121495,
+  "eval_steps": 500,
+  "global_step": 2407,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.18,
+      "learning_rate": 0.0003269230769230769,
+      "loss": 1.6646,
+      "step": 85
+    },
+    {
+      "epoch": 6.36,
+      "learning_rate": 0.0006538461538461538,
+      "loss": 1.517,
+      "step": 170
+    },
+    {
+      "epoch": 9.53,
+      "learning_rate": 0.0009807692307692308,
+      "loss": 1.4586,
+      "step": 255
+    },
+    {
+      "epoch": 12.71,
+      "learning_rate": 0.0009658119658119658,
+      "loss": 1.3597,
+      "step": 340
+    },
+    {
+      "epoch": 15.89,
+      "learning_rate": 0.0009294871794871796,
+      "loss": 1.2625,
+      "step": 425
+    },
+    {
+      "epoch": 19.07,
+      "learning_rate": 0.0008931623931623932,
+      "loss": 1.1835,
+      "step": 510
+    },
+    {
+      "epoch": 22.24,
+      "learning_rate": 0.0008568376068376068,
+      "loss": 1.1184,
+      "step": 595
+    },
+    {
+      "epoch": 25.42,
+      "learning_rate": 0.0008205128205128205,
+      "loss": 1.0683,
+      "step": 680
+    },
+    {
+      "epoch": 28.6,
+      "learning_rate": 0.0007841880341880342,
+      "loss": 1.0321,
+      "step": 765
+    },
+    {
+      "epoch": 31.78,
+      "learning_rate": 0.0007478632478632479,
+      "loss": 1.0009,
+      "step": 850
+    },
+    {
+      "epoch": 34.95,
+      "learning_rate": 0.0007115384615384616,
+      "loss": 0.9663,
+      "step": 935
+    },
+    {
+      "epoch": 38.13,
+      "learning_rate": 0.0006752136752136753,
+      "loss": 0.938,
+      "step": 1020
+    },
+    {
+      "epoch": 41.31,
+      "learning_rate": 0.0006388888888888888,
+      "loss": 0.9178,
+      "step": 1105
+    },
+    {
+      "epoch": 44.49,
+      "learning_rate": 0.0006025641025641026,
+      "loss": 0.8984,
+      "step": 1190
+    },
+    {
+      "epoch": 47.66,
+      "learning_rate": 0.0005662393162393163,
+      "loss": 0.8827,
+      "step": 1275
+    },
+    {
+      "epoch": 50.84,
+      "learning_rate": 0.0005299145299145299,
+      "loss": 0.8693,
+      "step": 1360
+    },
+    {
+      "epoch": 54.02,
+      "learning_rate": 0.0004935897435897436,
+      "loss": 0.8514,
+      "step": 1445
+    },
+    {
+      "epoch": 57.2,
+      "learning_rate": 0.0004572649572649573,
+      "loss": 0.8349,
+      "step": 1530
+    },
+    {
+      "epoch": 60.37,
+      "learning_rate": 0.00042094017094017095,
+      "loss": 0.824,
+      "step": 1615
+    },
+    {
+      "epoch": 63.55,
+      "learning_rate": 0.00038461538461538467,
+      "loss": 0.8138,
+      "step": 1700
+    },
+    {
+      "epoch": 66.73,
+      "learning_rate": 0.0003482905982905983,
+      "loss": 0.8044,
+      "step": 1785
+    },
+    {
+      "epoch": 69.91,
+      "learning_rate": 0.00031196581196581195,
+      "loss": 0.7962,
+      "step": 1870
+    },
+    {
+      "epoch": 73.08,
+      "learning_rate": 0.0002756410256410257,
+      "loss": 0.7854,
+      "step": 1955
+    },
+    {
+      "epoch": 76.26,
+      "learning_rate": 0.00023931623931623932,
+      "loss": 0.7756,
+      "step": 2040
+    },
+    {
+      "epoch": 79.44,
+      "learning_rate": 0.000202991452991453,
+      "loss": 0.7663,
+      "step": 2125
+    },
+    {
+      "epoch": 82.62,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 0.7569,
+      "step": 2210
+    },
+    {
+      "epoch": 85.79,
+      "learning_rate": 0.00013034188034188036,
+      "loss": 0.7491,
+      "step": 2295
+    },
+    {
+      "epoch": 88.97,
+      "learning_rate": 9.401709401709401e-05,
+      "loss": 0.7427,
+      "step": 2380
+    }
+  ],
+  "logging_steps": 85,
+  "max_steps": 2600,
+  "num_train_epochs": 100,
+  "save_steps": 500,
+  "total_flos": 2.5051595227499856e+19,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2407/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43cc490960b33ae18d92aab5dda2ba89068e31d8d3180c7226b60976ac62797c
+size 4536

checkpoint-2434/README.md

@@ -0,0 +1,238 @@
+---
+library_name: peft
+base_model: meta-llama/Llama-2-7b-hf
+---
+
+# 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]
+- **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 Data 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 Data 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.0
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.0

checkpoint-2434/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-2434/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca9f59dd9d9ea37f95498bc0b6796240db1b333528c28a97b4e3c6b88bffaebd
+size 33600906

checkpoint-2434/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a5331cf56f1fccb2411cf64548118fd7ff63c9252ffe2fbe94ab899eeadb379
+size 67217018

checkpoint-2434/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
+size 888

checkpoint-2434/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b76bff5006ecac0c5d394ac514af0485d1d29e36e93e47fab954c91c73a6c5a
+size 15024

checkpoint-2434/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:542d94ed93464ee943d831119efc955963177896c8363d192c7cab93e8600278
+size 15024

checkpoint-2434/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16793b178c0bc1298634ac9f7e0a368c57c9c34ae6c24516a335a5ff4ec08022
+size 15024

checkpoint-2434/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71771b8191707d5041dd7eb2865e8303c7efca6d1475a5ca53643fe057f0d24c
+size 15024

checkpoint-2434/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f057e88c15f047645a43eaab1c8220d8d958d80af2ca657c80efc6e6a70e13b
+size 1064

checkpoint-2434/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2434/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-2434/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1024,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-2434/trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 90.99065420560747,
+  "eval_steps": 500,
+  "global_step": 2434,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.18,
+      "learning_rate": 0.0003269230769230769,
+      "loss": 1.6646,
+      "step": 85
+    },
+    {
+      "epoch": 6.36,
+      "learning_rate": 0.0006538461538461538,
+      "loss": 1.517,
+      "step": 170
+    },
+    {
+      "epoch": 9.53,
+      "learning_rate": 0.0009807692307692308,
+      "loss": 1.4586,
+      "step": 255
+    },
+    {
+      "epoch": 12.71,
+      "learning_rate": 0.0009658119658119658,
+      "loss": 1.3597,
+      "step": 340
+    },
+    {
+      "epoch": 15.89,
+      "learning_rate": 0.0009294871794871796,
+      "loss": 1.2625,
+      "step": 425
+    },
+    {
+      "epoch": 19.07,
+      "learning_rate": 0.0008931623931623932,
+      "loss": 1.1835,
+      "step": 510
+    },
+    {
+      "epoch": 22.24,
+      "learning_rate": 0.0008568376068376068,
+      "loss": 1.1184,
+      "step": 595
+    },
+    {
+      "epoch": 25.42,
+      "learning_rate": 0.0008205128205128205,
+      "loss": 1.0683,
+      "step": 680
+    },
+    {
+      "epoch": 28.6,
+      "learning_rate": 0.0007841880341880342,
+      "loss": 1.0321,
+      "step": 765
+    },
+    {
+      "epoch": 31.78,
+      "learning_rate": 0.0007478632478632479,
+      "loss": 1.0009,
+      "step": 850
+    },
+    {
+      "epoch": 34.95,
+      "learning_rate": 0.0007115384615384616,
+      "loss": 0.9663,
+      "step": 935
+    },
+    {
+      "epoch": 38.13,
+      "learning_rate": 0.0006752136752136753,
+      "loss": 0.938,
+      "step": 1020
+    },
+    {
+      "epoch": 41.31,
+      "learning_rate": 0.0006388888888888888,
+      "loss": 0.9178,
+      "step": 1105
+    },
+    {
+      "epoch": 44.49,
+      "learning_rate": 0.0006025641025641026,
+      "loss": 0.8984,
+      "step": 1190
+    },
+    {
+      "epoch": 47.66,
+      "learning_rate": 0.0005662393162393163,
+      "loss": 0.8827,
+      "step": 1275
+    },
+    {
+      "epoch": 50.84,
+      "learning_rate": 0.0005299145299145299,
+      "loss": 0.8693,
+      "step": 1360
+    },
+    {
+      "epoch": 54.02,
+      "learning_rate": 0.0004935897435897436,
+      "loss": 0.8514,
+      "step": 1445
+    },
+    {
+      "epoch": 57.2,
+      "learning_rate": 0.0004572649572649573,
+      "loss": 0.8349,
+      "step": 1530
+    },
+    {
+      "epoch": 60.37,
+      "learning_rate": 0.00042094017094017095,
+      "loss": 0.824,
+      "step": 1615
+    },
+    {
+      "epoch": 63.55,
+      "learning_rate": 0.00038461538461538467,
+      "loss": 0.8138,
+      "step": 1700
+    },
+    {
+      "epoch": 66.73,
+      "learning_rate": 0.0003482905982905983,
+      "loss": 0.8044,
+      "step": 1785
+    },
+    {
+      "epoch": 69.91,
+      "learning_rate": 0.00031196581196581195,
+      "loss": 0.7962,
+      "step": 1870
+    },
+    {
+      "epoch": 73.08,
+      "learning_rate": 0.0002756410256410257,
+      "loss": 0.7854,
+      "step": 1955
+    },
+    {
+      "epoch": 76.26,
+      "learning_rate": 0.00023931623931623932,
+      "loss": 0.7756,
+      "step": 2040
+    },
+    {
+      "epoch": 79.44,
+      "learning_rate": 0.000202991452991453,
+      "loss": 0.7663,
+      "step": 2125
+    },
+    {
+      "epoch": 82.62,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 0.7569,
+      "step": 2210
+    },
+    {
+      "epoch": 85.79,
+      "learning_rate": 0.00013034188034188036,
+      "loss": 0.7491,
+      "step": 2295
+    },
+    {
+      "epoch": 88.97,
+      "learning_rate": 9.401709401709401e-05,
+      "loss": 0.7427,
+      "step": 2380
+    }
+  ],
+  "logging_steps": 85,
+  "max_steps": 2600,
+  "num_train_epochs": 100,
+  "save_steps": 500,
+  "total_flos": 2.532994628551757e+19,
+  "trial_name": null,
+  "trial_params": null
+}