Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-354/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+base_model: cjvt/GaMS3-12B-Instruct
+library_name: peft
+model_name: gams3-law-nli
+tags:
+- base_model:adapter:cjvt/GaMS3-12B-Instruct
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for gams3-law-nli
+
+This model is a fine-tuned version of [cjvt/GaMS3-12B-Instruct](https://huggingface.co/cjvt/GaMS3-12B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.18.1
+- TRL: 0.27.1
+- Transformers: 4.57.0.dev0
+- Pytorch: 2.8.0+cu126
+- Datasets: 4.1.1
+- Tokenizers: 0.22.1
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "cjvt/GaMS3-12B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj",
+    "up_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e1bfe9b5818b5c7cdfca600fd68a8c56563124f68b14542c43221156f820f5e
+size 131031528

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

checkpoint-100/README.md

@@ -0,0 +1,209 @@
+---
+base_model: cjvt/GaMS3-12B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:cjvt/GaMS3-12B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.1

checkpoint-100/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "cjvt/GaMS3-12B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj",
+    "up_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09c959932b7d7fd1bb3f23c4dac12045052227436daead5499c1ee4d0152a579
+size 131031528

checkpoint-100/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

checkpoint-100/chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd1e8925786d0401cbab72431c8d61cecd742f6185956ab0668e80bfb380b5de
+size 133781925

checkpoint-100/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8b07f92ca865a40fe5c60e7344ff4a2e82743ee8c7462d379944f1f61ea3b57
+size 14917

checkpoint-100/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b70d3d9439d6d855dd34a63ceed4b04dcfd10789725e6bc77af11489bc15e39
+size 14917

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c43584a5441bf511f4b1ae323002de15228857bedded18360da4ca22e3a48e84
+size 1465

checkpoint-100/special_tokens_map.json

@@ -0,0 +1,47 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-100/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

checkpoint-100/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

checkpoint-100/trainer_state.json

@@ -0,0 +1,145 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8501594048884166,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.3227437630295753,
+      "epoch": 0.08501594048884166,
+      "grad_norm": 1.4296875,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 1.518,
+      "mean_token_accuracy": 0.7175316952168942,
+      "num_tokens": 48910.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.7062680356204509,
+      "epoch": 0.17003188097768332,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.00019973167127614215,
+      "loss": 0.7921,
+      "mean_token_accuracy": 0.8361715286970138,
+      "num_tokens": 96994.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.6654534563422203,
+      "epoch": 0.255047821466525,
+      "grad_norm": 0.46875,
+      "learning_rate": 0.00019864405334538517,
+      "loss": 0.6723,
+      "mean_token_accuracy": 0.848845011740923,
+      "num_tokens": 144332.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.5781836319714785,
+      "epoch": 0.34006376195536664,
+      "grad_norm": 0.447265625,
+      "learning_rate": 0.00019672948630390294,
+      "loss": 0.6044,
+      "mean_token_accuracy": 0.8551476895809174,
+      "num_tokens": 192719.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.5426878597587347,
+      "epoch": 0.4250797024442083,
+      "grad_norm": 0.466796875,
+      "learning_rate": 0.00019400402027796955,
+      "loss": 0.5788,
+      "mean_token_accuracy": 0.8572557404637337,
+      "num_tokens": 241632.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.5355116073042154,
+      "epoch": 0.51009564293305,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.00019049050329166778,
+      "loss": 0.5629,
+      "mean_token_accuracy": 0.862634701281786,
+      "num_tokens": 291116.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.5224194105714559,
+      "epoch": 0.5951115834218916,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.00018621838972819458,
+      "loss": 0.551,
+      "mean_token_accuracy": 0.8659204967319966,
+      "num_tokens": 340898.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.4716725114732981,
+      "epoch": 0.6801275239107333,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.00018122349340898595,
+      "loss": 0.5116,
+      "mean_token_accuracy": 0.8745670169591904,
+      "num_tokens": 386799.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.4831196520477533,
+      "epoch": 0.7651434643995749,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00017554768736063859,
+      "loss": 0.5071,
+      "mean_token_accuracy": 0.8737691469490528,
+      "num_tokens": 436798.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.44570639468729495,
+      "epoch": 0.8501594048884166,
+      "grad_norm": 0.515625,
+      "learning_rate": 0.00016923855278653114,
+      "loss": 0.465,
+      "mean_token_accuracy": 0.8849786855280399,
+      "num_tokens": 485573.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.8501594048884166,
+      "eval_entropy": 0.48599471364702496,
+      "eval_loss": 0.475477933883667,
+      "eval_mean_token_accuracy": 0.8784565641766503,
+      "eval_num_tokens": 485573.0,
+      "eval_runtime": 17.16,
+      "eval_samples_per_second": 9.732,
+      "eval_steps_per_second": 4.895,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 354,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.1536876749848576e+16,
+  "train_batch_size": 1,
+  "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:c0b154c32ade6b177f89984ecee5db33195307e61cc986c821de33deb3159fe4
+size 5777

checkpoint-200/README.md

@@ -0,0 +1,209 @@
+---
+base_model: cjvt/GaMS3-12B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:cjvt/GaMS3-12B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.1

checkpoint-200/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "cjvt/GaMS3-12B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj",
+    "up_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:140797790759baaa3b422fa324ddc97c11b6bb90b61a9a57d3dd7f2f494637d2
+size 131031528

checkpoint-200/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

checkpoint-200/chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a7d589b8e2b314f043ea3813c101a6a978bfa86eb4bc7cecebef201ef6db153
+size 133781925

checkpoint-200/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5512348a82cda5a09968ecbae77ad64d001280a08c6e5ec2381c2d1a3555572
+size 14917

checkpoint-200/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af8ef59854e0c7c8d1f2c9ff866ec7393a01b6897b74bd2624fb3ba10844492a
+size 14917

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62574522adc0fe63f5647e437ab851f75482400bb6b646d92afaae3947853fdc
+size 1465

checkpoint-200/special_tokens_map.json

@@ -0,0 +1,47 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

checkpoint-200/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

checkpoint-200/trainer_state.json

@@ -0,0 +1,256 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6971307120085015,
+  "eval_steps": 100,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.3227437630295753,
+      "epoch": 0.08501594048884166,
+      "grad_norm": 1.4296875,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 1.518,
+      "mean_token_accuracy": 0.7175316952168942,
+      "num_tokens": 48910.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.7062680356204509,
+      "epoch": 0.17003188097768332,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.00019973167127614215,
+      "loss": 0.7921,
+      "mean_token_accuracy": 0.8361715286970138,
+      "num_tokens": 96994.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.6654534563422203,
+      "epoch": 0.255047821466525,
+      "grad_norm": 0.46875,
+      "learning_rate": 0.00019864405334538517,
+      "loss": 0.6723,
+      "mean_token_accuracy": 0.848845011740923,
+      "num_tokens": 144332.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.5781836319714785,
+      "epoch": 0.34006376195536664,
+      "grad_norm": 0.447265625,
+      "learning_rate": 0.00019672948630390294,
+      "loss": 0.6044,
+      "mean_token_accuracy": 0.8551476895809174,
+      "num_tokens": 192719.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.5426878597587347,
+      "epoch": 0.4250797024442083,
+      "grad_norm": 0.466796875,
+      "learning_rate": 0.00019400402027796955,
+      "loss": 0.5788,
+      "mean_token_accuracy": 0.8572557404637337,
+      "num_tokens": 241632.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.5355116073042154,
+      "epoch": 0.51009564293305,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.00019049050329166778,
+      "loss": 0.5629,
+      "mean_token_accuracy": 0.862634701281786,
+      "num_tokens": 291116.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.5224194105714559,
+      "epoch": 0.5951115834218916,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.00018621838972819458,
+      "loss": 0.551,
+      "mean_token_accuracy": 0.8659204967319966,
+      "num_tokens": 340898.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.4716725114732981,
+      "epoch": 0.6801275239107333,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.00018122349340898595,
+      "loss": 0.5116,
+      "mean_token_accuracy": 0.8745670169591904,
+      "num_tokens": 386799.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.4831196520477533,
+      "epoch": 0.7651434643995749,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00017554768736063859,
+      "loss": 0.5071,
+      "mean_token_accuracy": 0.8737691469490528,
+      "num_tokens": 436798.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.44570639468729495,
+      "epoch": 0.8501594048884166,
+      "grad_norm": 0.515625,
+      "learning_rate": 0.00016923855278653114,
+      "loss": 0.465,
+      "mean_token_accuracy": 0.8849786855280399,
+      "num_tokens": 485573.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.8501594048884166,
+      "eval_entropy": 0.48599471364702496,
+      "eval_loss": 0.475477933883667,
+      "eval_mean_token_accuracy": 0.8784565641766503,
+      "eval_num_tokens": 485573.0,
+      "eval_runtime": 17.16,
+      "eval_samples_per_second": 9.732,
+      "eval_steps_per_second": 4.895,
+      "step": 100
+    },
+    {
+      "entropy": 0.43454019390046594,
+      "epoch": 0.9351753453772582,
+      "grad_norm": 0.62890625,
+      "learning_rate": 0.00016234898018587337,
+      "loss": 0.4552,
+      "mean_token_accuracy": 0.8844782762229443,
+      "num_tokens": 530654.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.41183759620437377,
+      "epoch": 1.0170031880977684,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00015493672596406598,
+      "loss": 0.4096,
+      "mean_token_accuracy": 0.8991486182460537,
+      "num_tokens": 574892.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.35238806419074536,
+      "epoch": 1.1020191285866099,
+      "grad_norm": 0.5546875,
+      "learning_rate": 0.00014706392825137964,
+      "loss": 0.3574,
+      "mean_token_accuracy": 0.9064381532371044,
+      "num_tokens": 620523.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.3248062996193767,
+      "epoch": 1.1870350690754516,
+      "grad_norm": 0.69921875,
+      "learning_rate": 0.00013879658598892254,
+      "loss": 0.3389,
+      "mean_token_accuracy": 0.9107168510556221,
+      "num_tokens": 670456.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.3360298121348023,
+      "epoch": 1.2720510095642932,
+      "grad_norm": 0.65234375,
+      "learning_rate": 0.0001302040056488047,
+      "loss": 0.3444,
+      "mean_token_accuracy": 0.9091025076806545,
+      "num_tokens": 718444.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.3400493461638689,
+      "epoch": 1.357066950053135,
+      "grad_norm": 0.58203125,
+      "learning_rate": 0.00012135822022673263,
+      "loss": 0.3558,
+      "mean_token_accuracy": 0.910928662866354,
+      "num_tokens": 767549.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.3092759184539318,
+      "epoch": 1.4420828905419767,
+      "grad_norm": 0.625,
+      "learning_rate": 0.00011233338537771407,
+      "loss": 0.3089,
+      "mean_token_accuracy": 0.9161648266017437,
+      "num_tokens": 818123.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.3046819636598229,
+      "epoch": 1.5270988310308182,
+      "grad_norm": 0.55859375,
+      "learning_rate": 0.00010320515775716555,
+      "loss": 0.3032,
+      "mean_token_accuracy": 0.9219753406941891,
+      "num_tokens": 867721.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.2906474955379963,
+      "epoch": 1.61211477151966,
+      "grad_norm": 0.5,
+      "learning_rate": 9.405006077888954e-05,
+      "loss": 0.2992,
+      "mean_token_accuracy": 0.9225860193371773,
+      "num_tokens": 917153.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.30296949967741965,
+      "epoch": 1.6971307120085015,
+      "grad_norm": 0.546875,
+      "learning_rate": 8.494484310687581e-05,
+      "loss": 0.3053,
+      "mean_token_accuracy": 0.9186053372919559,
+      "num_tokens": 964600.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.6971307120085015,
+      "eval_entropy": 0.35429788788869265,
+      "eval_loss": 0.404356449842453,
+      "eval_mean_token_accuracy": 0.8999107018822715,
+      "eval_num_tokens": 964600.0,
+      "eval_runtime": 17.2396,
+      "eval_samples_per_second": 9.687,
+      "eval_steps_per_second": 4.872,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 354,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.275304131238298e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0b154c32ade6b177f89984ecee5db33195307e61cc986c821de33deb3159fe4
+size 5777

checkpoint-300/README.md

@@ -0,0 +1,209 @@
+---
+base_model: cjvt/GaMS3-12B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:cjvt/GaMS3-12B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.1

checkpoint-300/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "cjvt/GaMS3-12B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj",
+    "up_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f73db7b7a6ca6f1aa3168d018597797ceecadfab95efbe42782d7d22d1da3a7
+size 131031528

checkpoint-300/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

checkpoint-300/chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9def8367b2ef1429317f54da3eb58f7326004aad2684e50f2dfbc698ea2268b1
+size 133782565

checkpoint-300/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a6e080824c8cedcf31c5e1f1e9b99c410f9c55768ade8e5fbc0c6a8bab8b0d9
+size 14917

checkpoint-300/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63a8af738665b07693fa60655de09b4febecd726fefea2d67ad250eb13992607
+size 14917

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d128b74cfdeb6d74cdfac30f3fe8f0f8f7d3708ff58c289aa65e679d07967f98
+size 1465

checkpoint-300/special_tokens_map.json

@@ -0,0 +1,47 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-300/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

checkpoint-300/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

checkpoint-300/trainer_state.json

@@ -0,0 +1,367 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.5441020191285864,
+  "eval_steps": 100,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.3227437630295753,
+      "epoch": 0.08501594048884166,
+      "grad_norm": 1.4296875,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 1.518,
+      "mean_token_accuracy": 0.7175316952168942,
+      "num_tokens": 48910.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.7062680356204509,
+      "epoch": 0.17003188097768332,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.00019973167127614215,
+      "loss": 0.7921,
+      "mean_token_accuracy": 0.8361715286970138,
+      "num_tokens": 96994.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.6654534563422203,
+      "epoch": 0.255047821466525,
+      "grad_norm": 0.46875,
+      "learning_rate": 0.00019864405334538517,
+      "loss": 0.6723,
+      "mean_token_accuracy": 0.848845011740923,
+      "num_tokens": 144332.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.5781836319714785,
+      "epoch": 0.34006376195536664,
+      "grad_norm": 0.447265625,
+      "learning_rate": 0.00019672948630390294,
+      "loss": 0.6044,
+      "mean_token_accuracy": 0.8551476895809174,
+      "num_tokens": 192719.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.5426878597587347,
+      "epoch": 0.4250797024442083,
+      "grad_norm": 0.466796875,
+      "learning_rate": 0.00019400402027796955,
+      "loss": 0.5788,
+      "mean_token_accuracy": 0.8572557404637337,
+      "num_tokens": 241632.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.5355116073042154,
+      "epoch": 0.51009564293305,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.00019049050329166778,
+      "loss": 0.5629,
+      "mean_token_accuracy": 0.862634701281786,
+      "num_tokens": 291116.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.5224194105714559,
+      "epoch": 0.5951115834218916,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.00018621838972819458,
+      "loss": 0.551,
+      "mean_token_accuracy": 0.8659204967319966,
+      "num_tokens": 340898.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.4716725114732981,
+      "epoch": 0.6801275239107333,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.00018122349340898595,
+      "loss": 0.5116,
+      "mean_token_accuracy": 0.8745670169591904,
+      "num_tokens": 386799.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.4831196520477533,
+      "epoch": 0.7651434643995749,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00017554768736063859,
+      "loss": 0.5071,
+      "mean_token_accuracy": 0.8737691469490528,
+      "num_tokens": 436798.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.44570639468729495,
+      "epoch": 0.8501594048884166,
+      "grad_norm": 0.515625,
+      "learning_rate": 0.00016923855278653114,
+      "loss": 0.465,
+      "mean_token_accuracy": 0.8849786855280399,
+      "num_tokens": 485573.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.8501594048884166,
+      "eval_entropy": 0.48599471364702496,
+      "eval_loss": 0.475477933883667,
+      "eval_mean_token_accuracy": 0.8784565641766503,
+      "eval_num_tokens": 485573.0,
+      "eval_runtime": 17.16,
+      "eval_samples_per_second": 9.732,
+      "eval_steps_per_second": 4.895,
+      "step": 100
+    },
+    {
+      "entropy": 0.43454019390046594,
+      "epoch": 0.9351753453772582,
+      "grad_norm": 0.62890625,
+      "learning_rate": 0.00016234898018587337,
+      "loss": 0.4552,
+      "mean_token_accuracy": 0.8844782762229443,
+      "num_tokens": 530654.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.41183759620437377,
+      "epoch": 1.0170031880977684,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00015493672596406598,
+      "loss": 0.4096,
+      "mean_token_accuracy": 0.8991486182460537,
+      "num_tokens": 574892.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.35238806419074536,
+      "epoch": 1.1020191285866099,
+      "grad_norm": 0.5546875,
+      "learning_rate": 0.00014706392825137964,
+      "loss": 0.3574,
+      "mean_token_accuracy": 0.9064381532371044,
+      "num_tokens": 620523.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.3248062996193767,
+      "epoch": 1.1870350690754516,
+      "grad_norm": 0.69921875,
+      "learning_rate": 0.00013879658598892254,
+      "loss": 0.3389,
+      "mean_token_accuracy": 0.9107168510556221,
+      "num_tokens": 670456.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.3360298121348023,
+      "epoch": 1.2720510095642932,
+      "grad_norm": 0.65234375,
+      "learning_rate": 0.0001302040056488047,
+      "loss": 0.3444,
+      "mean_token_accuracy": 0.9091025076806545,
+      "num_tokens": 718444.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.3400493461638689,
+      "epoch": 1.357066950053135,
+      "grad_norm": 0.58203125,
+      "learning_rate": 0.00012135822022673263,
+      "loss": 0.3558,
+      "mean_token_accuracy": 0.910928662866354,
+      "num_tokens": 767549.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.3092759184539318,
+      "epoch": 1.4420828905419767,
+      "grad_norm": 0.625,
+      "learning_rate": 0.00011233338537771407,
+      "loss": 0.3089,
+      "mean_token_accuracy": 0.9161648266017437,
+      "num_tokens": 818123.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.3046819636598229,
+      "epoch": 1.5270988310308182,
+      "grad_norm": 0.55859375,
+      "learning_rate": 0.00010320515775716555,
+      "loss": 0.3032,
+      "mean_token_accuracy": 0.9219753406941891,
+      "num_tokens": 867721.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.2906474955379963,
+      "epoch": 1.61211477151966,
+      "grad_norm": 0.5,
+      "learning_rate": 9.405006077888954e-05,
+      "loss": 0.2992,
+      "mean_token_accuracy": 0.9225860193371773,
+      "num_tokens": 917153.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.30296949967741965,
+      "epoch": 1.6971307120085015,
+      "grad_norm": 0.546875,
+      "learning_rate": 8.494484310687581e-05,
+      "loss": 0.3053,
+      "mean_token_accuracy": 0.9186053372919559,
+      "num_tokens": 964600.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.6971307120085015,
+      "eval_entropy": 0.35429788788869265,
+      "eval_loss": 0.404356449842453,
+      "eval_mean_token_accuracy": 0.8999107018822715,
+      "eval_num_tokens": 964600.0,
+      "eval_runtime": 17.2396,
+      "eval_samples_per_second": 9.687,
+      "eval_steps_per_second": 4.872,
+      "step": 200
+    },
+    {
+      "entropy": 0.30462323110550643,
+      "epoch": 1.7821466524973433,
+      "grad_norm": 0.59375,
+      "learning_rate": 7.596583525879344e-05,
+      "loss": 0.308,
+      "mean_token_accuracy": 0.9176651492714882,
+      "num_tokens": 1010401.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.29319654731079936,
+      "epoch": 1.867162592986185,
+      "grad_norm": 0.64453125,
+      "learning_rate": 6.718830971487165e-05,
+      "loss": 0.2912,
+      "mean_token_accuracy": 0.9217840351164341,
+      "num_tokens": 1058672.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.28096328396350145,
+      "epoch": 1.9521785334750266,
+      "grad_norm": 0.6796875,
+      "learning_rate": 5.868584989647994e-05,
+      "loss": 0.2825,
+      "mean_token_accuracy": 0.9237303651869297,
+      "num_tokens": 1106102.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.27870092405514285,
+      "epoch": 2.0340063761955367,
+      "grad_norm": 0.4296875,
+      "learning_rate": 5.0529733304363145e-05,
+      "loss": 0.2657,
+      "mean_token_accuracy": 0.9302684858247832,
+      "num_tokens": 1151178.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.2116462522186339,
+      "epoch": 2.1190223166843785,
+      "grad_norm": 0.625,
+      "learning_rate": 4.278833398778306e-05,
+      "loss": 0.2033,
+      "mean_token_accuracy": 0.9440436236560344,
+      "num_tokens": 1198945.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.21235913261771203,
+      "epoch": 2.2040382571732198,
+      "grad_norm": 0.5,
+      "learning_rate": 3.5526549353765296e-05,
+      "loss": 0.2133,
+      "mean_token_accuracy": 0.9405460350215435,
+      "num_tokens": 1246732.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.22362984605133535,
+      "epoch": 2.2890541976620615,
+      "grad_norm": 0.494140625,
+      "learning_rate": 2.8805256121602398e-05,
+      "loss": 0.2225,
+      "mean_token_accuracy": 0.9388925828039646,
+      "num_tokens": 1291061.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.22003474170342088,
+      "epoch": 2.3740701381509033,
+      "grad_norm": 0.53125,
+      "learning_rate": 2.268079998343453e-05,
+      "loss": 0.2244,
+      "mean_token_accuracy": 0.9388979405164719,
+      "num_tokens": 1340506.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.20420914590358735,
+      "epoch": 2.459086078639745,
+      "grad_norm": 0.59765625,
+      "learning_rate": 1.720452324916656e-05,
+      "loss": 0.2062,
+      "mean_token_accuracy": 0.941665968298912,
+      "num_tokens": 1389105.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.21224667700007557,
+      "epoch": 2.5441020191285864,
+      "grad_norm": 0.470703125,
+      "learning_rate": 1.2422334435550509e-05,
+      "loss": 0.2076,
+      "mean_token_accuracy": 0.9419615142047405,
+      "num_tokens": 1436911.0,
+      "step": 300
+    },
+    {
+      "epoch": 2.5441020191285864,
+      "eval_entropy": 0.2823823473105828,
+      "eval_loss": 0.3997238576412201,
+      "eval_mean_token_accuracy": 0.906679209499132,
+      "eval_num_tokens": 1436911.0,
+      "eval_runtime": 17.0522,
+      "eval_samples_per_second": 9.793,
+      "eval_steps_per_second": 4.926,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 354,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.350424533191885e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}