Upload folder using huggingface_hub

adapter_config.json

@@ -23,10 +23,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_up_proj",
+    "o_proj",
     "down_proj",
-    "qkv_proj",
-    "o_proj"
+    "gate_up_proj",
+    "qkv_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4de8118eb3c068f60ce36d3ca641fe0eab10557be8ebd26263b7bf370c25545e
+oid sha256:f80c245eae44b3416491e33581b78ae4a68c8e6a6e74cbc958be15987aedcf44
 size 100697728

all_results.json

@@ -1,8 +1,13 @@
 {
-    "epoch": 5.0,
-    "total_flos": 2.5642849233567744e+16,
-    "train_loss": 0.5138080072402954,
-    "train_runtime": 465.5561,
-    "train_samples_per_second": 1.718,
-    "train_steps_per_second": 0.107
+    "epoch": 22.235294117647058,
+    "eval_loss": 0.5779597759246826,
+    "eval_runtime": 3.3667,
+    "eval_samples": 15,
+    "eval_samples_per_second": 4.455,
+    "eval_steps_per_second": 0.594,
+    "total_flos": 1.040122623832658e+17,
+    "train_loss": 0.13381972634699196,
+    "train_runtime": 1987.8506,
+    "train_samples_per_second": 1.61,
+    "train_steps_per_second": 0.101
 }

checkpoint-108/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/Phi-3.5-mini-instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

checkpoint-108/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
+  "bias": "none",
+  "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",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "gate_up_proj",
+    "qkv_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-108/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2cda12d2fec52038dbb2822b3991f5f75d74b3ce05460f639bd43e5afdf6744
+size 100697728

checkpoint-108/added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

checkpoint-108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae9ea14fef31c25b23855d66f36f577854fde9b8211fdc7d661d0760b4cab223
+size 201541754

checkpoint-108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f29702bfd5d0dbc2c9198cf7dbe95ab53cc0b683b3f1fb8eb71d760fbd9e49ec
+size 14244

checkpoint-108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc4ce0639cdfde8bbc88aea9396c4dc0000bc7c16640a5cde31d4effee5717bf
+size 1064

checkpoint-108/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-108/tokenizer.model

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

checkpoint-108/tokenizer_config.json

@@ -0,0 +1,132 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-108/trainer_state.json

@@ -0,0 +1,277 @@
+{
+  "best_global_step": 27,
+  "best_metric": 0.5779597759246826,
+  "best_model_checkpoint": "//outputs/task7_microsoft/Phi-3.5-mini-instruct/checkpoint-27",
+  "epoch": 12.0,
+  "eval_steps": 500,
+  "global_step": 108,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.2979797124862671,
+      "learning_rate": 0.00015,
+      "loss": 0.7889,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6737979650497437,
+      "eval_runtime": 3.3675,
+      "eval_samples_per_second": 4.454,
+      "eval_steps_per_second": 0.594,
+      "step": 9
+    },
+    {
+      "epoch": 1.1176470588235294,
+      "grad_norm": 0.20464661717414856,
+      "learning_rate": 0.0003,
+      "loss": 0.6771,
+      "step": 10
+    },
+    {
+      "epoch": 1.7058823529411766,
+      "grad_norm": 0.1992536187171936,
+      "learning_rate": 0.00029948767395100045,
+      "loss": 0.6255,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6006895303726196,
+      "eval_runtime": 3.3642,
+      "eval_samples_per_second": 4.459,
+      "eval_steps_per_second": 0.594,
+      "step": 18
+    },
+    {
+      "epoch": 2.235294117647059,
+      "grad_norm": 0.19050121307373047,
+      "learning_rate": 0.00029795419551040833,
+      "loss": 0.5302,
+      "step": 20
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 0.17813433706760406,
+      "learning_rate": 0.0002954100398908995,
+      "loss": 0.4439,
+      "step": 25
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5779597759246826,
+      "eval_runtime": 3.3656,
+      "eval_samples_per_second": 4.457,
+      "eval_steps_per_second": 0.594,
+      "step": 27
+    },
+    {
+      "epoch": 3.3529411764705883,
+      "grad_norm": 0.23658457398414612,
+      "learning_rate": 0.00029187258625509513,
+      "loss": 0.4257,
+      "step": 30
+    },
+    {
+      "epoch": 3.9411764705882355,
+      "grad_norm": 0.27489331364631653,
+      "learning_rate": 0.00028736599899825856,
+      "loss": 0.3254,
+      "step": 35
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5997567772865295,
+      "eval_runtime": 3.3651,
+      "eval_samples_per_second": 4.458,
+      "eval_steps_per_second": 0.594,
+      "step": 36
+    },
+    {
+      "epoch": 4.470588235294118,
+      "grad_norm": 0.3510420620441437,
+      "learning_rate": 0.00028192106268097334,
+      "loss": 0.2985,
+      "step": 40
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.4653756320476532,
+      "learning_rate": 0.00027557497173937923,
+      "loss": 0.2828,
+      "step": 45
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.6584295034408569,
+      "eval_runtime": 3.3668,
+      "eval_samples_per_second": 4.455,
+      "eval_steps_per_second": 0.594,
+      "step": 45
+    },
+    {
+      "epoch": 5.588235294117647,
+      "grad_norm": 0.3469710052013397,
+      "learning_rate": 0.00026837107640945905,
+      "loss": 0.2038,
+      "step": 50
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.751620888710022,
+      "eval_runtime": 3.3651,
+      "eval_samples_per_second": 4.458,
+      "eval_steps_per_second": 0.594,
+      "step": 54
+    },
+    {
+      "epoch": 6.117647058823529,
+      "grad_norm": 0.3903103470802307,
+      "learning_rate": 0.0002603585866009697,
+      "loss": 0.1656,
+      "step": 55
+    },
+    {
+      "epoch": 6.705882352941177,
+      "grad_norm": 0.38518330454826355,
+      "learning_rate": 0.00025159223574386114,
+      "loss": 0.1296,
+      "step": 60
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.8753386735916138,
+      "eval_runtime": 3.3654,
+      "eval_samples_per_second": 4.457,
+      "eval_steps_per_second": 0.594,
+      "step": 63
+    },
+    {
+      "epoch": 7.235294117647059,
+      "grad_norm": 0.24312527477741241,
+      "learning_rate": 0.00024213190690345018,
+      "loss": 0.085,
+      "step": 65
+    },
+    {
+      "epoch": 7.823529411764706,
+      "grad_norm": 0.3267911970615387,
+      "learning_rate": 0.00023204222371836405,
+      "loss": 0.0751,
+      "step": 70
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.8750011920928955,
+      "eval_runtime": 3.3678,
+      "eval_samples_per_second": 4.454,
+      "eval_steps_per_second": 0.594,
+      "step": 72
+    },
+    {
+      "epoch": 8.352941176470589,
+      "grad_norm": 0.24549448490142822,
+      "learning_rate": 0.00022139210895556104,
+      "loss": 0.0576,
+      "step": 75
+    },
+    {
+      "epoch": 8.941176470588236,
+      "grad_norm": 0.3071894347667694,
+      "learning_rate": 0.0002102543136979454,
+      "loss": 0.0475,
+      "step": 80
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.9990332126617432,
+      "eval_runtime": 3.3671,
+      "eval_samples_per_second": 4.455,
+      "eval_steps_per_second": 0.594,
+      "step": 81
+    },
+    {
+      "epoch": 9.470588235294118,
+      "grad_norm": 0.17012739181518555,
+      "learning_rate": 0.00019870492038070252,
+      "loss": 0.0282,
+      "step": 85
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.2809393107891083,
+      "learning_rate": 0.00018682282307111987,
+      "loss": 0.0249,
+      "step": 90
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.022998571395874,
+      "eval_runtime": 3.3665,
+      "eval_samples_per_second": 4.456,
+      "eval_steps_per_second": 0.594,
+      "step": 90
+    },
+    {
+      "epoch": 10.588235294117647,
+      "grad_norm": 0.16731834411621094,
+      "learning_rate": 0.00017468918854211007,
+      "loss": 0.0151,
+      "step": 95
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 1.0694772005081177,
+      "eval_runtime": 3.3662,
+      "eval_samples_per_second": 4.456,
+      "eval_steps_per_second": 0.594,
+      "step": 99
+    },
+    {
+      "epoch": 11.117647058823529,
+      "grad_norm": 0.149811789393425,
+      "learning_rate": 0.00016238690182084986,
+      "loss": 0.0166,
+      "step": 100
+    },
+    {
+      "epoch": 11.705882352941176,
+      "grad_norm": 0.13291925191879272,
+      "learning_rate": 0.00015,
+      "loss": 0.0095,
+      "step": 105
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 1.0867458581924438,
+      "eval_runtime": 3.3664,
+      "eval_samples_per_second": 4.456,
+      "eval_steps_per_second": 0.594,
+      "step": 108
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 25,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.603463825892762e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6c29a53cb36e9fcac6a368aa7e961a846f6918a035c3653b19f429f1c9ada0f
+size 5624

checkpoint-117/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/Phi-3.5-mini-instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

checkpoint-117/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
+  "bias": "none",
+  "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",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "gate_up_proj",
+    "qkv_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-117/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b23c59a33fa5977c6ed726aaf4961a96eec270408858477fede353c8b75f73
+size 100697728

checkpoint-117/added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

checkpoint-117/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20bb1652b8ebcb36f12846c0923e2a09bfebc4c8adb25c0fbf42a99ab628bfe3
+size 201541754

checkpoint-117/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7e735fd7d0197633b2699c26cc1d810175f26f989695a40770a7b4adb7302c0
+size 14244

checkpoint-117/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d149413fc2505446926b39ce004b7d1c01ae99dcf348a22c75f792048da80038
+size 1064

checkpoint-117/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-117/tokenizer.model

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

checkpoint-117/tokenizer_config.json

@@ -0,0 +1,132 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-117/trainer_state.json

@@ -0,0 +1,299 @@
+{
+  "best_global_step": 27,
+  "best_metric": 0.5779597759246826,
+  "best_model_checkpoint": "//outputs/task7_microsoft/Phi-3.5-mini-instruct/checkpoint-27",
+  "epoch": 13.0,
+  "eval_steps": 500,
+  "global_step": 117,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.2979797124862671,
+      "learning_rate": 0.00015,
+      "loss": 0.7889,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6737979650497437,
+      "eval_runtime": 3.3675,
+      "eval_samples_per_second": 4.454,
+      "eval_steps_per_second": 0.594,
+      "step": 9
+    },
+    {
+      "epoch": 1.1176470588235294,
+      "grad_norm": 0.20464661717414856,
+      "learning_rate": 0.0003,
+      "loss": 0.6771,
+      "step": 10
+    },
+    {
+      "epoch": 1.7058823529411766,
+      "grad_norm": 0.1992536187171936,
+      "learning_rate": 0.00029948767395100045,
+      "loss": 0.6255,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6006895303726196,
+      "eval_runtime": 3.3642,
+      "eval_samples_per_second": 4.459,
+      "eval_steps_per_second": 0.594,
+      "step": 18
+    },
+    {
+      "epoch": 2.235294117647059,
+      "grad_norm": 0.19050121307373047,
+      "learning_rate": 0.00029795419551040833,
+      "loss": 0.5302,
+      "step": 20
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 0.17813433706760406,
+      "learning_rate": 0.0002954100398908995,
+      "loss": 0.4439,
+      "step": 25
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5779597759246826,
+      "eval_runtime": 3.3656,
+      "eval_samples_per_second": 4.457,
+      "eval_steps_per_second": 0.594,
+      "step": 27
+    },
+    {
+      "epoch": 3.3529411764705883,
+      "grad_norm": 0.23658457398414612,
+      "learning_rate": 0.00029187258625509513,
+      "loss": 0.4257,
+      "step": 30
+    },
+    {
+      "epoch": 3.9411764705882355,
+      "grad_norm": 0.27489331364631653,
+      "learning_rate": 0.00028736599899825856,
+      "loss": 0.3254,
+      "step": 35
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5997567772865295,
+      "eval_runtime": 3.3651,
+      "eval_samples_per_second": 4.458,
+      "eval_steps_per_second": 0.594,
+      "step": 36
+    },
+    {
+      "epoch": 4.470588235294118,
+      "grad_norm": 0.3510420620441437,
+      "learning_rate": 0.00028192106268097334,
+      "loss": 0.2985,
+      "step": 40
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.4653756320476532,
+      "learning_rate": 0.00027557497173937923,
+      "loss": 0.2828,
+      "step": 45
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.6584295034408569,
+      "eval_runtime": 3.3668,
+      "eval_samples_per_second": 4.455,
+      "eval_steps_per_second": 0.594,
+      "step": 45
+    },
+    {
+      "epoch": 5.588235294117647,
+      "grad_norm": 0.3469710052013397,
+      "learning_rate": 0.00026837107640945905,
+      "loss": 0.2038,
+      "step": 50
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.751620888710022,
+      "eval_runtime": 3.3651,
+      "eval_samples_per_second": 4.458,
+      "eval_steps_per_second": 0.594,
+      "step": 54
+    },
+    {
+      "epoch": 6.117647058823529,
+      "grad_norm": 0.3903103470802307,
+      "learning_rate": 0.0002603585866009697,
+      "loss": 0.1656,
+      "step": 55
+    },
+    {
+      "epoch": 6.705882352941177,
+      "grad_norm": 0.38518330454826355,
+      "learning_rate": 0.00025159223574386114,
+      "loss": 0.1296,
+      "step": 60
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.8753386735916138,
+      "eval_runtime": 3.3654,
+      "eval_samples_per_second": 4.457,
+      "eval_steps_per_second": 0.594,
+      "step": 63
+    },
+    {
+      "epoch": 7.235294117647059,
+      "grad_norm": 0.24312527477741241,
+      "learning_rate": 0.00024213190690345018,
+      "loss": 0.085,
+      "step": 65
+    },
+    {
+      "epoch": 7.823529411764706,
+      "grad_norm": 0.3267911970615387,
+      "learning_rate": 0.00023204222371836405,
+      "loss": 0.0751,
+      "step": 70
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.8750011920928955,
+      "eval_runtime": 3.3678,
+      "eval_samples_per_second": 4.454,
+      "eval_steps_per_second": 0.594,
+      "step": 72
+    },
+    {
+      "epoch": 8.352941176470589,
+      "grad_norm": 0.24549448490142822,
+      "learning_rate": 0.00022139210895556104,
+      "loss": 0.0576,
+      "step": 75
+    },
+    {
+      "epoch": 8.941176470588236,
+      "grad_norm": 0.3071894347667694,
+      "learning_rate": 0.0002102543136979454,
+      "loss": 0.0475,
+      "step": 80
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.9990332126617432,
+      "eval_runtime": 3.3671,
+      "eval_samples_per_second": 4.455,
+      "eval_steps_per_second": 0.594,
+      "step": 81
+    },
+    {
+      "epoch": 9.470588235294118,
+      "grad_norm": 0.17012739181518555,
+      "learning_rate": 0.00019870492038070252,
+      "loss": 0.0282,
+      "step": 85
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.2809393107891083,
+      "learning_rate": 0.00018682282307111987,
+      "loss": 0.0249,
+      "step": 90
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.022998571395874,
+      "eval_runtime": 3.3665,
+      "eval_samples_per_second": 4.456,
+      "eval_steps_per_second": 0.594,
+      "step": 90
+    },
+    {
+      "epoch": 10.588235294117647,
+      "grad_norm": 0.16731834411621094,
+      "learning_rate": 0.00017468918854211007,
+      "loss": 0.0151,
+      "step": 95
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 1.0694772005081177,
+      "eval_runtime": 3.3662,
+      "eval_samples_per_second": 4.456,
+      "eval_steps_per_second": 0.594,
+      "step": 99
+    },
+    {
+      "epoch": 11.117647058823529,
+      "grad_norm": 0.149811789393425,
+      "learning_rate": 0.00016238690182084986,
+      "loss": 0.0166,
+      "step": 100
+    },
+    {
+      "epoch": 11.705882352941176,
+      "grad_norm": 0.13291925191879272,
+      "learning_rate": 0.00015,
+      "loss": 0.0095,
+      "step": 105
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 1.0867458581924438,
+      "eval_runtime": 3.3664,
+      "eval_samples_per_second": 4.456,
+      "eval_steps_per_second": 0.594,
+      "step": 108
+    },
+    {
+      "epoch": 12.235294117647058,
+      "grad_norm": 0.08576802164316177,
+      "learning_rate": 0.00013761309817915014,
+      "loss": 0.009,
+      "step": 110
+    },
+    {
+      "epoch": 12.823529411764707,
+      "grad_norm": 0.07071960717439651,
+      "learning_rate": 0.00012531081145788987,
+      "loss": 0.0075,
+      "step": 115
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 1.1065537929534912,
+      "eval_runtime": 3.3672,
+      "eval_samples_per_second": 4.455,
+      "eval_steps_per_second": 0.594,
+      "step": 117
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 25,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.078245372728934e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-117/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6c29a53cb36e9fcac6a368aa7e961a846f6918a035c3653b19f429f1c9ada0f
+size 5624

checkpoint-126/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/Phi-3.5-mini-instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

checkpoint-126/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
+  "bias": "none",
+  "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",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "gate_up_proj",
+    "qkv_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-126/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c17e6385eb77d64f463469a45a8eaabc96cf5b175939023a2aae5ab80934c98b
+size 100697728

checkpoint-126/added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

checkpoint-126/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2057aa361aa8210a55204c75f0ee052675f3d4da91fb22fe6a33a102812f4138
+size 201541754

checkpoint-126/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe43054f30dc68e1b12738831b6deea4fb1852a3e96a6f75c924b5f1d4c5d513
+size 14244

checkpoint-126/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99c34901a2ad71230f8d174057bcd413aa98867a63486dabe73d249f0aad9d47
+size 1064

checkpoint-126/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-126/tokenizer.model

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

checkpoint-126/tokenizer_config.json

@@ -0,0 +1,132 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-126/trainer_state.json

@@ -0,0 +1,321 @@
+{
+  "best_global_step": 27,
+  "best_metric": 0.5779597759246826,
+  "best_model_checkpoint": "//outputs/task7_microsoft/Phi-3.5-mini-instruct/checkpoint-27",
+  "epoch": 14.0,
+  "eval_steps": 500,
+  "global_step": 126,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.2979797124862671,
+      "learning_rate": 0.00015,
+      "loss": 0.7889,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6737979650497437,
+      "eval_runtime": 3.3675,
+      "eval_samples_per_second": 4.454,
+      "eval_steps_per_second": 0.594,
+      "step": 9
+    },
+    {
+      "epoch": 1.1176470588235294,
+      "grad_norm": 0.20464661717414856,
+      "learning_rate": 0.0003,
+      "loss": 0.6771,
+      "step": 10
+    },
+    {
+      "epoch": 1.7058823529411766,
+      "grad_norm": 0.1992536187171936,
+      "learning_rate": 0.00029948767395100045,
+      "loss": 0.6255,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6006895303726196,
+      "eval_runtime": 3.3642,
+      "eval_samples_per_second": 4.459,
+      "eval_steps_per_second": 0.594,
+      "step": 18
+    },
+    {
+      "epoch": 2.235294117647059,
+      "grad_norm": 0.19050121307373047,
+      "learning_rate": 0.00029795419551040833,
+      "loss": 0.5302,
+      "step": 20
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 0.17813433706760406,
+      "learning_rate": 0.0002954100398908995,
+      "loss": 0.4439,
+      "step": 25
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5779597759246826,
+      "eval_runtime": 3.3656,
+      "eval_samples_per_second": 4.457,
+      "eval_steps_per_second": 0.594,
+      "step": 27
+    },
+    {
+      "epoch": 3.3529411764705883,
+      "grad_norm": 0.23658457398414612,
+      "learning_rate": 0.00029187258625509513,
+      "loss": 0.4257,
+      "step": 30
+    },
+    {
+      "epoch": 3.9411764705882355,
+      "grad_norm": 0.27489331364631653,
+      "learning_rate": 0.00028736599899825856,
+      "loss": 0.3254,
+      "step": 35
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5997567772865295,
+      "eval_runtime": 3.3651,
+      "eval_samples_per_second": 4.458,
+      "eval_steps_per_second": 0.594,
+      "step": 36
+    },
+    {
+      "epoch": 4.470588235294118,
+      "grad_norm": 0.3510420620441437,
+      "learning_rate": 0.00028192106268097334,
+      "loss": 0.2985,
+      "step": 40
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.4653756320476532,
+      "learning_rate": 0.00027557497173937923,
+      "loss": 0.2828,
+      "step": 45
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.6584295034408569,
+      "eval_runtime": 3.3668,
+      "eval_samples_per_second": 4.455,
+      "eval_steps_per_second": 0.594,
+      "step": 45
+    },
+    {
+      "epoch": 5.588235294117647,
+      "grad_norm": 0.3469710052013397,
+      "learning_rate": 0.00026837107640945905,
+      "loss": 0.2038,
+      "step": 50
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.751620888710022,
+      "eval_runtime": 3.3651,
+      "eval_samples_per_second": 4.458,
+      "eval_steps_per_second": 0.594,
+      "step": 54
+    },
+    {
+      "epoch": 6.117647058823529,
+      "grad_norm": 0.3903103470802307,
+      "learning_rate": 0.0002603585866009697,
+      "loss": 0.1656,
+      "step": 55
+    },
+    {
+      "epoch": 6.705882352941177,
+      "grad_norm": 0.38518330454826355,
+      "learning_rate": 0.00025159223574386114,
+      "loss": 0.1296,
+      "step": 60
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.8753386735916138,
+      "eval_runtime": 3.3654,
+      "eval_samples_per_second": 4.457,
+      "eval_steps_per_second": 0.594,
+      "step": 63
+    },
+    {
+      "epoch": 7.235294117647059,
+      "grad_norm": 0.24312527477741241,
+      "learning_rate": 0.00024213190690345018,
+      "loss": 0.085,
+      "step": 65
+    },
+    {
+      "epoch": 7.823529411764706,
+      "grad_norm": 0.3267911970615387,
+      "learning_rate": 0.00023204222371836405,
+      "loss": 0.0751,
+      "step": 70
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.8750011920928955,
+      "eval_runtime": 3.3678,
+      "eval_samples_per_second": 4.454,
+      "eval_steps_per_second": 0.594,
+      "step": 72
+    },
+    {
+      "epoch": 8.352941176470589,
+      "grad_norm": 0.24549448490142822,
+      "learning_rate": 0.00022139210895556104,
+      "loss": 0.0576,
+      "step": 75
+    },
+    {
+      "epoch": 8.941176470588236,
+      "grad_norm": 0.3071894347667694,
+      "learning_rate": 0.0002102543136979454,
+      "loss": 0.0475,
+      "step": 80
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.9990332126617432,
+      "eval_runtime": 3.3671,
+      "eval_samples_per_second": 4.455,
+      "eval_steps_per_second": 0.594,
+      "step": 81
+    },
+    {
+      "epoch": 9.470588235294118,
+      "grad_norm": 0.17012739181518555,
+      "learning_rate": 0.00019870492038070252,
+      "loss": 0.0282,
+      "step": 85
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.2809393107891083,
+      "learning_rate": 0.00018682282307111987,
+      "loss": 0.0249,
+      "step": 90
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.022998571395874,
+      "eval_runtime": 3.3665,
+      "eval_samples_per_second": 4.456,
+      "eval_steps_per_second": 0.594,
+      "step": 90
+    },
+    {
+      "epoch": 10.588235294117647,
+      "grad_norm": 0.16731834411621094,
+      "learning_rate": 0.00017468918854211007,
+      "loss": 0.0151,
+      "step": 95
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 1.0694772005081177,
+      "eval_runtime": 3.3662,
+      "eval_samples_per_second": 4.456,
+      "eval_steps_per_second": 0.594,
+      "step": 99
+    },
+    {
+      "epoch": 11.117647058823529,
+      "grad_norm": 0.149811789393425,
+      "learning_rate": 0.00016238690182084986,
+      "loss": 0.0166,
+      "step": 100
+    },
+    {
+      "epoch": 11.705882352941176,
+      "grad_norm": 0.13291925191879272,
+      "learning_rate": 0.00015,
+      "loss": 0.0095,
+      "step": 105
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 1.0867458581924438,
+      "eval_runtime": 3.3664,
+      "eval_samples_per_second": 4.456,
+      "eval_steps_per_second": 0.594,
+      "step": 108
+    },
+    {
+      "epoch": 12.235294117647058,
+      "grad_norm": 0.08576802164316177,
+      "learning_rate": 0.00013761309817915014,
+      "loss": 0.009,
+      "step": 110
+    },
+    {
+      "epoch": 12.823529411764707,
+      "grad_norm": 0.07071960717439651,
+      "learning_rate": 0.00012531081145788987,
+      "loss": 0.0075,
+      "step": 115
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 1.1065537929534912,
+      "eval_runtime": 3.3672,
+      "eval_samples_per_second": 4.455,
+      "eval_steps_per_second": 0.594,
+      "step": 117
+    },
+    {
+      "epoch": 13.352941176470589,
+      "grad_norm": 0.1268472969532013,
+      "learning_rate": 0.00011317717692888012,
+      "loss": 0.0125,
+      "step": 120
+    },
+    {
+      "epoch": 13.941176470588236,
+      "grad_norm": 0.08666448295116425,
+      "learning_rate": 0.00010129507961929748,
+      "loss": 0.0058,
+      "step": 125
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 1.0826694965362549,
+      "eval_runtime": 3.3663,
+      "eval_samples_per_second": 4.456,
+      "eval_steps_per_second": 0.594,
+      "step": 126
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 25,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.547911247956787e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-126/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6c29a53cb36e9fcac6a368aa7e961a846f6918a035c3653b19f429f1c9ada0f
+size 5624

checkpoint-135/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/Phi-3.5-mini-instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

checkpoint-135/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
+  "bias": "none",
+  "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",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "gate_up_proj",
+    "qkv_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-135/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d0b33203d8643e071d208a5ba76899f74e52f9273d69ee20491293ddd4bcfc2
+size 100697728

checkpoint-135/added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

checkpoint-135/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61982bccfe653a061aa8d1d8d59428afb85467160f1a9b4a5486b62b24984fdd
+size 201541754

checkpoint-135/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36c0f66305fe8c4edf6e879508b98e75ba711c4b63fad1a9a2de884f2c658550
+size 14244

checkpoint-135/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:539c46ae569b3c2d7553225676fe2da8c4a62b8f914f74257257b6d90f577c87
+size 1064

checkpoint-135/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}