Upload folder using huggingface_hub

README.md

@@ -0,0 +1,58 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: microsoft/phi-2
+model-index:
+- name: trivia
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# trivia
+
+This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the trivia dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-10
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 30.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.2
+- Pytorch 2.3.0
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/phi-2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35a4860ecef30d83bb4e8ca7d2b06962573b59019755b3618ef7a1d2dd861a98
+size 10502640

added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 28.8,
+    "total_flos": 1335967054725120.0,
+    "train_loss": 7.109028116861979,
+    "train_runtime": 593.1625,
+    "train_samples_per_second": 5.058,
+    "train_steps_per_second": 0.303
+}

checkpoint-100/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: microsoft/phi-2
+---
+
+# 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 0.10.0

checkpoint-100/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/phi-2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2fdf0798a220390652e1ada7b96b0d8ad8a451344b4147420ae515b8a55c464
+size 10502640

checkpoint-100/added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f29d8252746303231ae7acac58812763b539bd220026bdc8eaadab0dc514a99
+size 21075578

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:825a4ce620b0097568150a1e62af629205132971f8a774ff41ee85b48b76817e
+size 13990

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2821c088c8f9f1b23accbe40357a2d327a9a4f295aee66dc000fad30ed7729d9
+size 1064

checkpoint-100/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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-100/tokenizer_config.json

@@ -0,0 +1,328 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message + '\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "return_token_type_ids": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,161 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 16.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.3331761360168457,
+      "learning_rate": 4.990486745229364e-10,
+      "loss": 7.386,
+      "step": 5
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.494887351989746,
+      "learning_rate": 4.962019382530521e-10,
+      "loss": 6.7817,
+      "step": 10
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 2.389345407485962,
+      "learning_rate": 4.914814565722671e-10,
+      "loss": 7.1632,
+      "step": 15
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 2.437628984451294,
+      "learning_rate": 4.849231551964771e-10,
+      "loss": 7.0109,
+      "step": 20
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.2548422813415527,
+      "learning_rate": 4.765769467591626e-10,
+      "loss": 7.1004,
+      "step": 25
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 2.268507480621338,
+      "learning_rate": 4.665063509461097e-10,
+      "loss": 6.9577,
+      "step": 30
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 2.739196300506592,
+      "learning_rate": 4.54788011072248e-10,
+      "loss": 7.1725,
+      "step": 35
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 2.399449348449707,
+      "learning_rate": 4.415111107797445e-10,
+      "loss": 7.1535,
+      "step": 40
+    },
+    {
+      "epoch": 7.2,
+      "grad_norm": 2.798766613006592,
+      "learning_rate": 4.267766952966369e-10,
+      "loss": 6.9961,
+      "step": 45
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.742884635925293,
+      "learning_rate": 4.106969024216348e-10,
+      "loss": 7.1581,
+      "step": 50
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 3.0411534309387207,
+      "learning_rate": 3.933941090877615e-10,
+      "loss": 7.3208,
+      "step": 55
+    },
+    {
+      "epoch": 9.6,
+      "grad_norm": 2.590532064437866,
+      "learning_rate": 3.7500000000000005e-10,
+      "loss": 6.7152,
+      "step": 60
+    },
+    {
+      "epoch": 10.4,
+      "grad_norm": 2.6501505374908447,
+      "learning_rate": 3.556545654351749e-10,
+      "loss": 7.1168,
+      "step": 65
+    },
+    {
+      "epoch": 11.2,
+      "grad_norm": 2.6842129230499268,
+      "learning_rate": 3.3550503583141725e-10,
+      "loss": 7.143,
+      "step": 70
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 2.7974400520324707,
+      "learning_rate": 3.147047612756302e-10,
+      "loss": 7.2724,
+      "step": 75
+    },
+    {
+      "epoch": 12.8,
+      "grad_norm": 2.68391489982605,
+      "learning_rate": 2.9341204441673265e-10,
+      "loss": 6.995,
+      "step": 80
+    },
+    {
+      "epoch": 13.6,
+      "grad_norm": 3.0854671001434326,
+      "learning_rate": 2.717889356869146e-10,
+      "loss": 7.1134,
+      "step": 85
+    },
+    {
+      "epoch": 14.4,
+      "grad_norm": 2.772061347961426,
+      "learning_rate": 2.5e-10,
+      "loss": 7.2029,
+      "step": 90
+    },
+    {
+      "epoch": 15.2,
+      "grad_norm": 2.6627767086029053,
+      "learning_rate": 2.2821106431308546e-10,
+      "loss": 7.4673,
+      "step": 95
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 2.7043120861053467,
+      "learning_rate": 2.0658795558326743e-10,
+      "loss": 6.8563,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 180,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 100,
+  "total_flos": 742939194654720.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26ca302ed42091be2724cc3ec6e2a8ab6f813368320dc36808ada89634d0b367
+size 5112

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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 +1,328 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message + '\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "return_token_type_ids": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 28.8,
+    "total_flos": 1335967054725120.0,
+    "train_loss": 7.109028116861979,
+    "train_runtime": 593.1625,
+    "train_samples_per_second": 5.058,
+    "train_steps_per_second": 0.303
+}

trainer_log.jsonl

@@ -0,0 +1,37 @@
+{"current_steps": 5, "total_steps": 180, "loss": 7.386, "learning_rate": 4.990486745229364e-10, "epoch": 0.8, "percentage": 2.78, "elapsed_time": "0:00:16", "remaining_time": "0:09:43"}
+{"current_steps": 10, "total_steps": 180, "loss": 6.7817, "learning_rate": 4.962019382530521e-10, "epoch": 1.6, "percentage": 5.56, "elapsed_time": "0:00:33", "remaining_time": "0:09:23"}
+{"current_steps": 15, "total_steps": 180, "loss": 7.1632, "learning_rate": 4.914814565722671e-10, "epoch": 2.4, "percentage": 8.33, "elapsed_time": "0:00:49", "remaining_time": "0:09:04"}
+{"current_steps": 20, "total_steps": 180, "loss": 7.0109, "learning_rate": 4.849231551964771e-10, "epoch": 3.2, "percentage": 11.11, "elapsed_time": "0:01:05", "remaining_time": "0:08:47"}
+{"current_steps": 25, "total_steps": 180, "loss": 7.1004, "learning_rate": 4.765769467591626e-10, "epoch": 4.0, "percentage": 13.89, "elapsed_time": "0:01:21", "remaining_time": "0:08:27"}
+{"current_steps": 30, "total_steps": 180, "loss": 6.9577, "learning_rate": 4.665063509461097e-10, "epoch": 4.8, "percentage": 16.67, "elapsed_time": "0:01:38", "remaining_time": "0:08:11"}
+{"current_steps": 35, "total_steps": 180, "loss": 7.1725, "learning_rate": 4.54788011072248e-10, "epoch": 5.6, "percentage": 19.44, "elapsed_time": "0:01:54", "remaining_time": "0:07:55"}
+{"current_steps": 40, "total_steps": 180, "loss": 7.1535, "learning_rate": 4.415111107797445e-10, "epoch": 6.4, "percentage": 22.22, "elapsed_time": "0:02:11", "remaining_time": "0:07:39"}
+{"current_steps": 45, "total_steps": 180, "loss": 6.9961, "learning_rate": 4.267766952966369e-10, "epoch": 7.2, "percentage": 25.0, "elapsed_time": "0:02:28", "remaining_time": "0:07:24"}
+{"current_steps": 50, "total_steps": 180, "loss": 7.1581, "learning_rate": 4.106969024216348e-10, "epoch": 8.0, "percentage": 27.78, "elapsed_time": "0:02:44", "remaining_time": "0:07:08"}
+{"current_steps": 55, "total_steps": 180, "loss": 7.3208, "learning_rate": 3.933941090877615e-10, "epoch": 8.8, "percentage": 30.56, "elapsed_time": "0:03:02", "remaining_time": "0:06:54"}
+{"current_steps": 60, "total_steps": 180, "loss": 6.7152, "learning_rate": 3.7500000000000005e-10, "epoch": 9.6, "percentage": 33.33, "elapsed_time": "0:03:19", "remaining_time": "0:06:39"}
+{"current_steps": 65, "total_steps": 180, "loss": 7.1168, "learning_rate": 3.556545654351749e-10, "epoch": 10.4, "percentage": 36.11, "elapsed_time": "0:03:36", "remaining_time": "0:06:23"}
+{"current_steps": 70, "total_steps": 180, "loss": 7.143, "learning_rate": 3.3550503583141725e-10, "epoch": 11.2, "percentage": 38.89, "elapsed_time": "0:03:52", "remaining_time": "0:06:06"}
+{"current_steps": 75, "total_steps": 180, "loss": 7.2724, "learning_rate": 3.147047612756302e-10, "epoch": 12.0, "percentage": 41.67, "elapsed_time": "0:04:09", "remaining_time": "0:05:49"}
+{"current_steps": 80, "total_steps": 180, "loss": 6.995, "learning_rate": 2.9341204441673265e-10, "epoch": 12.8, "percentage": 44.44, "elapsed_time": "0:04:26", "remaining_time": "0:05:32"}
+{"current_steps": 85, "total_steps": 180, "loss": 7.1134, "learning_rate": 2.717889356869146e-10, "epoch": 13.6, "percentage": 47.22, "elapsed_time": "0:04:42", "remaining_time": "0:05:15"}
+{"current_steps": 90, "total_steps": 180, "loss": 7.2029, "learning_rate": 2.5e-10, "epoch": 14.4, "percentage": 50.0, "elapsed_time": "0:04:59", "remaining_time": "0:04:59"}
+{"current_steps": 95, "total_steps": 180, "loss": 7.4673, "learning_rate": 2.2821106431308546e-10, "epoch": 15.2, "percentage": 52.78, "elapsed_time": "0:05:15", "remaining_time": "0:04:42"}
+{"current_steps": 100, "total_steps": 180, "loss": 6.8563, "learning_rate": 2.0658795558326743e-10, "epoch": 16.0, "percentage": 55.56, "elapsed_time": "0:05:31", "remaining_time": "0:04:25"}
+{"current_steps": 105, "total_steps": 180, "loss": 7.0683, "learning_rate": 1.852952387243698e-10, "epoch": 16.8, "percentage": 58.33, "elapsed_time": "0:05:48", "remaining_time": "0:04:08"}
+{"current_steps": 110, "total_steps": 180, "loss": 7.1976, "learning_rate": 1.6449496416858284e-10, "epoch": 17.6, "percentage": 61.11, "elapsed_time": "0:06:04", "remaining_time": "0:03:52"}
+{"current_steps": 115, "total_steps": 180, "loss": 7.1575, "learning_rate": 1.443454345648252e-10, "epoch": 18.4, "percentage": 63.89, "elapsed_time": "0:06:20", "remaining_time": "0:03:35"}
+{"current_steps": 120, "total_steps": 180, "loss": 7.073, "learning_rate": 1.2500000000000006e-10, "epoch": 19.2, "percentage": 66.67, "elapsed_time": "0:06:37", "remaining_time": "0:03:18"}
+{"current_steps": 125, "total_steps": 180, "loss": 7.0932, "learning_rate": 1.0660589091223855e-10, "epoch": 20.0, "percentage": 69.44, "elapsed_time": "0:06:53", "remaining_time": "0:03:01"}
+{"current_steps": 130, "total_steps": 180, "loss": 7.1324, "learning_rate": 8.930309757836516e-11, "epoch": 20.8, "percentage": 72.22, "elapsed_time": "0:07:09", "remaining_time": "0:02:45"}
+{"current_steps": 135, "total_steps": 180, "loss": 7.1434, "learning_rate": 7.322330470336314e-11, "epoch": 21.6, "percentage": 75.0, "elapsed_time": "0:07:27", "remaining_time": "0:02:29"}
+{"current_steps": 140, "total_steps": 180, "loss": 7.0423, "learning_rate": 5.848888922025552e-11, "epoch": 22.4, "percentage": 77.78, "elapsed_time": "0:07:42", "remaining_time": "0:02:12"}
+{"current_steps": 145, "total_steps": 180, "loss": 7.3638, "learning_rate": 4.5211988927752025e-11, "epoch": 23.2, "percentage": 80.56, "elapsed_time": "0:07:59", "remaining_time": "0:01:55"}
+{"current_steps": 150, "total_steps": 180, "loss": 6.8454, "learning_rate": 3.3493649053890324e-11, "epoch": 24.0, "percentage": 83.33, "elapsed_time": "0:08:15", "remaining_time": "0:01:39"}
+{"current_steps": 155, "total_steps": 180, "loss": 7.1881, "learning_rate": 2.3423053240837516e-11, "epoch": 24.8, "percentage": 86.11, "elapsed_time": "0:08:31", "remaining_time": "0:01:22"}
+{"current_steps": 160, "total_steps": 180, "loss": 7.1249, "learning_rate": 1.5076844803522922e-11, "epoch": 25.6, "percentage": 88.89, "elapsed_time": "0:08:48", "remaining_time": "0:01:06"}
+{"current_steps": 165, "total_steps": 180, "loss": 7.1924, "learning_rate": 8.51854342773295e-12, "epoch": 26.4, "percentage": 91.67, "elapsed_time": "0:09:04", "remaining_time": "0:00:49"}
+{"current_steps": 170, "total_steps": 180, "loss": 6.9059, "learning_rate": 3.798061746947995e-12, "epoch": 27.2, "percentage": 94.44, "elapsed_time": "0:09:20", "remaining_time": "0:00:32"}
+{"current_steps": 175, "total_steps": 180, "loss": 7.2371, "learning_rate": 9.513254770636138e-13, "epoch": 28.0, "percentage": 97.22, "elapsed_time": "0:09:37", "remaining_time": "0:00:16"}
+{"current_steps": 180, "total_steps": 180, "loss": 7.0767, "learning_rate": 0.0, "epoch": 28.8, "percentage": 100.0, "elapsed_time": "0:09:53", "remaining_time": "0:00:00"}
+{"current_steps": 180, "total_steps": 180, "epoch": 28.8, "percentage": 100.0, "elapsed_time": "0:09:53", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,282 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 28.8,
+  "eval_steps": 500,
+  "global_step": 180,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.3331761360168457,
+      "learning_rate": 4.990486745229364e-10,
+      "loss": 7.386,
+      "step": 5
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.494887351989746,
+      "learning_rate": 4.962019382530521e-10,
+      "loss": 6.7817,
+      "step": 10
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 2.389345407485962,
+      "learning_rate": 4.914814565722671e-10,
+      "loss": 7.1632,
+      "step": 15
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 2.437628984451294,
+      "learning_rate": 4.849231551964771e-10,
+      "loss": 7.0109,
+      "step": 20
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.2548422813415527,
+      "learning_rate": 4.765769467591626e-10,
+      "loss": 7.1004,
+      "step": 25
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 2.268507480621338,
+      "learning_rate": 4.665063509461097e-10,
+      "loss": 6.9577,
+      "step": 30
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 2.739196300506592,
+      "learning_rate": 4.54788011072248e-10,
+      "loss": 7.1725,
+      "step": 35
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 2.399449348449707,
+      "learning_rate": 4.415111107797445e-10,
+      "loss": 7.1535,
+      "step": 40
+    },
+    {
+      "epoch": 7.2,
+      "grad_norm": 2.798766613006592,
+      "learning_rate": 4.267766952966369e-10,
+      "loss": 6.9961,
+      "step": 45
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.742884635925293,
+      "learning_rate": 4.106969024216348e-10,
+      "loss": 7.1581,
+      "step": 50
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 3.0411534309387207,
+      "learning_rate": 3.933941090877615e-10,
+      "loss": 7.3208,
+      "step": 55
+    },
+    {
+      "epoch": 9.6,
+      "grad_norm": 2.590532064437866,
+      "learning_rate": 3.7500000000000005e-10,
+      "loss": 6.7152,
+      "step": 60
+    },
+    {
+      "epoch": 10.4,
+      "grad_norm": 2.6501505374908447,
+      "learning_rate": 3.556545654351749e-10,
+      "loss": 7.1168,
+      "step": 65
+    },
+    {
+      "epoch": 11.2,
+      "grad_norm": 2.6842129230499268,
+      "learning_rate": 3.3550503583141725e-10,
+      "loss": 7.143,
+      "step": 70
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 2.7974400520324707,
+      "learning_rate": 3.147047612756302e-10,
+      "loss": 7.2724,
+      "step": 75
+    },
+    {
+      "epoch": 12.8,
+      "grad_norm": 2.68391489982605,
+      "learning_rate": 2.9341204441673265e-10,
+      "loss": 6.995,
+      "step": 80
+    },
+    {
+      "epoch": 13.6,
+      "grad_norm": 3.0854671001434326,
+      "learning_rate": 2.717889356869146e-10,
+      "loss": 7.1134,
+      "step": 85
+    },
+    {
+      "epoch": 14.4,
+      "grad_norm": 2.772061347961426,
+      "learning_rate": 2.5e-10,
+      "loss": 7.2029,
+      "step": 90
+    },
+    {
+      "epoch": 15.2,
+      "grad_norm": 2.6627767086029053,
+      "learning_rate": 2.2821106431308546e-10,
+      "loss": 7.4673,
+      "step": 95
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 2.7043120861053467,
+      "learning_rate": 2.0658795558326743e-10,
+      "loss": 6.8563,
+      "step": 100
+    },
+    {
+      "epoch": 16.8,
+      "grad_norm": 2.4765264987945557,
+      "learning_rate": 1.852952387243698e-10,
+      "loss": 7.0683,
+      "step": 105
+    },
+    {
+      "epoch": 17.6,
+      "grad_norm": 2.775627613067627,
+      "learning_rate": 1.6449496416858284e-10,
+      "loss": 7.1976,
+      "step": 110
+    },
+    {
+      "epoch": 18.4,
+      "grad_norm": 2.3891263008117676,
+      "learning_rate": 1.443454345648252e-10,
+      "loss": 7.1575,
+      "step": 115
+    },
+    {
+      "epoch": 19.2,
+      "grad_norm": 2.5396955013275146,
+      "learning_rate": 1.2500000000000006e-10,
+      "loss": 7.073,
+      "step": 120
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 2.4532394409179688,
+      "learning_rate": 1.0660589091223855e-10,
+      "loss": 7.0932,
+      "step": 125
+    },
+    {
+      "epoch": 20.8,
+      "grad_norm": 2.822531223297119,
+      "learning_rate": 8.930309757836516e-11,
+      "loss": 7.1324,
+      "step": 130
+    },
+    {
+      "epoch": 21.6,
+      "grad_norm": 2.5621225833892822,
+      "learning_rate": 7.322330470336314e-11,
+      "loss": 7.1434,
+      "step": 135
+    },
+    {
+      "epoch": 22.4,
+      "grad_norm": 2.63484263420105,
+      "learning_rate": 5.848888922025552e-11,
+      "loss": 7.0423,
+      "step": 140
+    },
+    {
+      "epoch": 23.2,
+      "grad_norm": 2.882169246673584,
+      "learning_rate": 4.5211988927752025e-11,
+      "loss": 7.3638,
+      "step": 145
+    },
+    {
+      "epoch": 24.0,
+      "grad_norm": 2.356477975845337,
+      "learning_rate": 3.3493649053890324e-11,
+      "loss": 6.8454,
+      "step": 150
+    },
+    {
+      "epoch": 24.8,
+      "grad_norm": 3.1740143299102783,
+      "learning_rate": 2.3423053240837516e-11,
+      "loss": 7.1881,
+      "step": 155
+    },
+    {
+      "epoch": 25.6,
+      "grad_norm": 2.634425640106201,
+      "learning_rate": 1.5076844803522922e-11,
+      "loss": 7.1249,
+      "step": 160
+    },
+    {
+      "epoch": 26.4,
+      "grad_norm": 2.412172317504883,
+      "learning_rate": 8.51854342773295e-12,
+      "loss": 7.1924,
+      "step": 165
+    },
+    {
+      "epoch": 27.2,
+      "grad_norm": 2.655557870864868,
+      "learning_rate": 3.798061746947995e-12,
+      "loss": 6.9059,
+      "step": 170
+    },
+    {
+      "epoch": 28.0,
+      "grad_norm": 2.859827756881714,
+      "learning_rate": 9.513254770636138e-13,
+      "loss": 7.2371,
+      "step": 175
+    },
+    {
+      "epoch": 28.8,
+      "grad_norm": 2.7501277923583984,
+      "learning_rate": 0.0,
+      "loss": 7.0767,
+      "step": 180
+    },
+    {
+      "epoch": 28.8,
+      "step": 180,
+      "total_flos": 1335967054725120.0,
+      "train_loss": 7.109028116861979,
+      "train_runtime": 593.1625,
+      "train_samples_per_second": 5.058,
+      "train_steps_per_second": 0.303
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 180,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 100,
+  "total_flos": 1335967054725120.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26ca302ed42091be2724cc3ec6e2a8ab6f813368320dc36808ada89634d0b367
+size 5112