Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,5 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text

Modelfile

@@ -0,0 +1,14 @@
+# ollama modelfile auto-generated by llamafactory
+
+FROM .
+
+TEMPLATE """{{ if .System }}<|im_start|>system
+{{ .System }}<|im_end|>
+{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|im_start|>user
+{{ .Content }}<|im_end|>
+<|im_start|>assistant
+{{ else if eq .Role "assistant" }}{{ .Content }}<|im_end|>
+{{ end }}{{ end }}"""
+
+PARAMETER stop "<|im_end|>"
+PARAMETER num_ctx 4096

README.md

@@ -0,0 +1,79 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen3-30B-A3B-Base
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: Qwen3-30B-A3B-Base-alpaca-th-52k-dolly-th-15k-wangchan-instruct-seed-2405
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Qwen3-30B-A3B-Base-alpaca-th-52k-dolly-th-15k-wangchan-instruct-seed-2405
+
+This model is a fine-tuned version of [Qwen/Qwen3-30B-A3B-Base](https://huggingface.co//Qwen/Qwen3-30B-A3B-Base) on the alpaca-th-52k, the dolly-th-15k and the wangchan-instruct datasets.
+It achieves the following results on the evaluation set:
+- Loss: 0.6619
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 2405
+- distributed_type: multi-GPU
+- num_devices: 128
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 2048
+- total_eval_batch_size: 256
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.8866        | 0.2299 | 10   | 1.0011          |
+| 0.7869        | 0.4598 | 20   | 0.8175          |
+| 0.724         | 0.6897 | 30   | 0.7251          |
+| 0.702         | 0.9195 | 40   | 0.7024          |
+| 0.6926        | 1.1379 | 50   | 0.6904          |
+| 0.6795        | 1.3678 | 60   | 0.6821          |
+| 0.6694        | 1.5977 | 70   | 0.6757          |
+| 0.674         | 1.8276 | 80   | 0.6708          |
+| 0.6543        | 2.0460 | 90   | 0.6660          |
+| 0.6492        | 2.2759 | 100  | 0.6639          |
+| 0.6508        | 2.5057 | 110  | 0.6626          |
+| 0.656         | 2.7356 | 120  | 0.6621          |
+| 0.6492        | 2.9655 | 130  | 0.6619          |
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.52.3
+- Pytorch 2.7.0+cu126
+- Datasets 3.6.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/project/lt200252-wcbart/pumet/models/Qwen3-30B-A3B-Base",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "gate",
+    "up_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87ea473495be874bae63f42a143180a65fb65a4fb9ab841f42e63a5d2e6eab89
+size 1696378232

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.6618949770927429,
+    "eval_runtime": 299.1641,
+    "eval_samples_per_second": 33.086,
+    "eval_steps_per_second": 0.13,
+    "total_flos": 4.878497440777581e+19,
+    "train_loss": 0.7089937537005453,
+    "train_runtime": 30749.2873,
+    "train_samples_per_second": 8.691,
+    "train_steps_per_second": 0.004
+}

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-100/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /project/lt200252-wcbart/pumet/models/Qwen3-30B-A3B-Base
+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 0.15.2

checkpoint-100/adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/project/lt200252-wcbart/pumet/models/Qwen3-30B-A3B-Base",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "gate",
+    "up_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-100/rng_state_109.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbedcf739c8b681975b4a87df21d886dac88813e97651bd307b20330280d5992
+size 15515

checkpoint-100/rng_state_120.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed99f65053a548d3481a036542496381872da9318ac87fcfb77241f2ce819b4
+size 15515

checkpoint-100/rng_state_125.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54f6b950e9b9c04a5d48d79d9139ca08fa76d0a0eaa905f97aabe66337969654
+size 15515

checkpoint-100/rng_state_13.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a11aafa493e1ccb00d275b79789f07a326007152eafb31078169216a1a546221
+size 15440

checkpoint-100/rng_state_14.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6f950bf229048cea7de20b6767ee78b99d6dfded0ec4a1a5f5884c8bde1ec3b
+size 15440

checkpoint-100/rng_state_16.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f91a5d55730e7ffd9b7d5a06cf687adb6e70e26d74a0cf49a8c5d321219fb692
+size 15440

checkpoint-100/rng_state_31.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aac92b68dafc6fe7c5729286762e8769981d0265419a5269ef4acf82f6046c78
+size 15440

checkpoint-100/rng_state_32.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b51acd861586d2b43f7e8a075a71714342810972e45e187c4c7f762ddcb7478
+size 15440

checkpoint-100/rng_state_47.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25a46f998b7875a1c9f3802e91a35e7ba1ac6115323cba96cea9f869a9b3ff7b
+size 15440

checkpoint-100/rng_state_50.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a160e4d5f8ba53a2f69562a0f0d52a604cdcde873635634e15325eb2b0b0bc2
+size 15440

checkpoint-100/rng_state_53.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44e9fa51731800e982974c7a658715767fba2d245db3fce3058d8eade1f7ad91
+size 15440

checkpoint-100/rng_state_82.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b663aea215cfe61a47d39740e8807379a97d1f79b5e83082d2d4bbcfe97cf6b
+size 15440

checkpoint-100/rng_state_85.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b0d66ba50f9f5e58acc46b01121b7d74a19e5171d2247b83b1ed10abcb7bfd7
+size 15440

checkpoint-100/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 48,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 768,
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

dataset/dataset_dict.json

@@ -0,0 +1 @@
+{"splits": ["train", "validation"]}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.6618949770927429,
+    "eval_runtime": 299.1641,
+    "eval_samples_per_second": 33.086,
+    "eval_steps_per_second": 0.13
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.52.3"
+}

model-00002-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b211ba347326b66b3760f664e427e3f6bc7e04028a51abfb1637b8b60e858176
+size 4997644048

model-00006-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a183d07255d75fd1b1ac65b56ebe8cdd38ecdf2548eeab4d956a54bf951e759
+size 4997644648

model-00009-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1b1a41c1bf830a99be759938a291a648ac16b71566a61f7d869ad2c7e71597a
+size 4997644832

model-00011-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df3f2e9ebebe3e10c98320382a2d21ce8bcba7399f2a934d3eb07b8f1c4efa9b
+size 4997644840

model-00012-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a35217088ebeb133904139713a804e8baa40cdf1024cef1985aa3dafbf8d9084
+size 4997644832

model-00013-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35f404291879947301a07d72e9b6a12cd8b5acef805cdf361edda9bd1d230788
+size 4997644832

model-00016-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e66535250b853d9e34a73c32baef379bc9a93f4f8016d34c9c901f8d88ad0913
+size 4997644832

model-00018-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e910ef11942be84a0849508b62dfce0dfc64ad3b5e23414157ac89648601704
+size 4997644832

model-00021-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:867cb10a330424fd41b8d2fc3bc74731447f585076c4c1f4ba3e3eee7e307683
+size 4997644832

model-00022-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a18db88c60ab665662e18acad1d468dff64a840fb461601984dcda38b44ab30
+size 4997644832

model-00024-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61ca635172d344ae876fbfbbf736ab68a5b53a4e75a514487022f2d3bb61a2c2
+size 4997644832

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 4.878497440777581e+19,
+    "train_loss": 0.7089937537005453,
+    "train_runtime": 30749.2873,
+    "train_samples_per_second": 8.691,
+    "train_steps_per_second": 0.004
+}

trainer_log.jsonl

@@ -0,0 +1,5 @@
+{"current_steps": 1, "total_steps": 261, "loss": 0.9303, "lr": 0.0, "epoch": 0.011494252873563218, "percentage": 0.38, "elapsed_time": "0:03:32", "remaining_time": "15:19:43"}
+{"current_steps": 2, "total_steps": 261, "loss": 0.9699, "lr": 7.4074074074074075e-06, "epoch": 0.022988505747126436, "percentage": 0.77, "elapsed_time": "0:06:57", "remaining_time": "15:00:52"}
+{"current_steps": 3, "total_steps": 261, "loss": 0.9378, "lr": 1.4814814814814815e-05, "epoch": 0.034482758620689655, "percentage": 1.15, "elapsed_time": "0:10:27", "remaining_time": "14:58:54"}
+{"current_steps": 4, "total_steps": 261, "loss": 0.945, "lr": 2.2222222222222223e-05, "epoch": 0.04597701149425287, "percentage": 1.53, "elapsed_time": "0:13:50", "remaining_time": "14:49:40"}
+{"current_steps": 5, "total_steps": 261, "loss": 0.9601, "lr": 2.962962962962963e-05, "epoch": 0.05747126436781609, "percentage": 1.92, "elapsed_time": "0:17:14", "remaining_time": "14:42:44"}

trainer_state.json

@@ -0,0 +1,1071 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 10,
+  "global_step": 132,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.022988505747126436,
+      "grad_norm": 0.11726659536361694,
+      "learning_rate": 0.0,
+      "loss": 0.949,
+      "step": 1
+    },
+    {
+      "epoch": 0.04597701149425287,
+      "grad_norm": 0.11742527782917023,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.9424,
+      "step": 2
+    },
+    {
+      "epoch": 0.06896551724137931,
+      "grad_norm": 0.11452076584100723,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 0.9528,
+      "step": 3
+    },
+    {
+      "epoch": 0.09195402298850575,
+      "grad_norm": 0.11016185581684113,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 0.9477,
+      "step": 4
+    },
+    {
+      "epoch": 0.11494252873563218,
+      "grad_norm": 0.09924337267875671,
+      "learning_rate": 5.714285714285714e-05,
+      "loss": 0.9246,
+      "step": 5
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 0.09508403390645981,
+      "learning_rate": 7.142857142857143e-05,
+      "loss": 0.923,
+      "step": 6
+    },
+    {
+      "epoch": 0.16091954022988506,
+      "grad_norm": 0.08589573949575424,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 0.9048,
+      "step": 7
+    },
+    {
+      "epoch": 0.1839080459770115,
+      "grad_norm": 0.07958836108446121,
+      "learning_rate": 0.0001,
+      "loss": 0.9165,
+      "step": 8
+    },
+    {
+      "epoch": 0.20689655172413793,
+      "grad_norm": 0.07911597937345505,
+      "learning_rate": 0.00011428571428571428,
+      "loss": 0.8881,
+      "step": 9
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "grad_norm": 0.08259308338165283,
+      "learning_rate": 0.00012857142857142858,
+      "loss": 0.8866,
+      "step": 10
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "eval_loss": 1.0011101961135864,
+      "eval_runtime": 305.7034,
+      "eval_samples_per_second": 32.378,
+      "eval_steps_per_second": 0.128,
+      "step": 10
+    },
+    {
+      "epoch": 0.25287356321839083,
+      "grad_norm": 0.08100606501102448,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 0.8687,
+      "step": 11
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 0.08286823332309723,
+      "learning_rate": 0.00015714285714285716,
+      "loss": 0.8684,
+      "step": 12
+    },
+    {
+      "epoch": 0.2988505747126437,
+      "grad_norm": 0.08412789553403854,
+      "learning_rate": 0.00017142857142857143,
+      "loss": 0.8592,
+      "step": 13
+    },
+    {
+      "epoch": 0.3218390804597701,
+      "grad_norm": 0.09051340073347092,
+      "learning_rate": 0.00018571428571428572,
+      "loss": 0.8389,
+      "step": 14
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 0.09371305257081985,
+      "learning_rate": 0.0002,
+      "loss": 0.8125,
+      "step": 15
+    },
+    {
+      "epoch": 0.367816091954023,
+      "grad_norm": 0.08772534877061844,
+      "learning_rate": 0.00019996456111234527,
+      "loss": 0.8217,
+      "step": 16
+    },
+    {
+      "epoch": 0.39080459770114945,
+      "grad_norm": 0.07762442529201508,
+      "learning_rate": 0.0001998582695676762,
+      "loss": 0.8052,
+      "step": 17
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 0.0685521736741066,
+      "learning_rate": 0.000199681200703075,
+      "loss": 0.7908,
+      "step": 18
+    },
+    {
+      "epoch": 0.4367816091954023,
+      "grad_norm": 0.06715967506170273,
+      "learning_rate": 0.00019943348002101371,
+      "loss": 0.7986,
+      "step": 19
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "grad_norm": 0.0685219094157219,
+      "learning_rate": 0.00019911528310040074,
+      "loss": 0.7869,
+      "step": 20
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "eval_loss": 0.8174761533737183,
+      "eval_runtime": 302.6325,
+      "eval_samples_per_second": 32.706,
+      "eval_steps_per_second": 0.129,
+      "step": 20
+    },
+    {
+      "epoch": 0.4827586206896552,
+      "grad_norm": 0.06762731820344925,
+      "learning_rate": 0.00019872683547213446,
+      "loss": 0.7657,
+      "step": 21
+    },
+    {
+      "epoch": 0.5057471264367817,
+      "grad_norm": 0.06856454163789749,
+      "learning_rate": 0.00019826841245925212,
+      "loss": 0.7829,
+      "step": 22
+    },
+    {
+      "epoch": 0.5287356321839081,
+      "grad_norm": 0.06053686887025833,
+      "learning_rate": 0.00019774033898178667,
+      "loss": 0.7562,
+      "step": 23
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.056510183960199356,
+      "learning_rate": 0.00019714298932647098,
+      "loss": 0.7485,
+      "step": 24
+    },
+    {
+      "epoch": 0.5747126436781609,
+      "grad_norm": 0.05787154287099838,
+      "learning_rate": 0.0001964767868814516,
+      "loss": 0.73,
+      "step": 25
+    },
+    {
+      "epoch": 0.5977011494252874,
+      "grad_norm": 0.05212588980793953,
+      "learning_rate": 0.00019574220383620055,
+      "loss": 0.74,
+      "step": 26
+    },
+    {
+      "epoch": 0.6206896551724138,
+      "grad_norm": 0.047729115933179855,
+      "learning_rate": 0.00019493976084683813,
+      "loss": 0.7381,
+      "step": 27
+    },
+    {
+      "epoch": 0.6436781609195402,
+      "grad_norm": 0.044737160205841064,
+      "learning_rate": 0.00019407002666710336,
+      "loss": 0.7368,
+      "step": 28
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.04290475323796272,
+      "learning_rate": 0.00019313361774523385,
+      "loss": 0.7369,
+      "step": 29
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.03797232359647751,
+      "learning_rate": 0.00019213119778704128,
+      "loss": 0.724,
+      "step": 30
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "eval_loss": 0.725147545337677,
+      "eval_runtime": 301.4442,
+      "eval_samples_per_second": 32.835,
+      "eval_steps_per_second": 0.129,
+      "step": 30
+    },
+    {
+      "epoch": 0.7126436781609196,
+      "grad_norm": 0.035527635365724564,
+      "learning_rate": 0.00019106347728549135,
+      "loss": 0.7304,
+      "step": 31
+    },
+    {
+      "epoch": 0.735632183908046,
+      "grad_norm": 0.03322393074631691,
+      "learning_rate": 0.00018993121301712193,
+      "loss": 0.7195,
+      "step": 32
+    },
+    {
+      "epoch": 0.7586206896551724,
+      "grad_norm": 0.03048304282128811,
+      "learning_rate": 0.00018873520750565718,
+      "loss": 0.7192,
+      "step": 33
+    },
+    {
+      "epoch": 0.7816091954022989,
+      "grad_norm": 0.03057900071144104,
+      "learning_rate": 0.00018747630845319612,
+      "loss": 0.7056,
+      "step": 34
+    },
+    {
+      "epoch": 0.8045977011494253,
+      "grad_norm": 0.03429551050066948,
+      "learning_rate": 0.0001861554081393806,
+      "loss": 0.7004,
+      "step": 35
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.03101194091141224,
+      "learning_rate": 0.0001847734427889671,
+      "loss": 0.72,
+      "step": 36
+    },
+    {
+      "epoch": 0.8505747126436781,
+      "grad_norm": 0.030171377584338188,
+      "learning_rate": 0.0001833313919082515,
+      "loss": 0.7169,
+      "step": 37
+    },
+    {
+      "epoch": 0.8735632183908046,
+      "grad_norm": 0.03114650957286358,
+      "learning_rate": 0.0001818302775908169,
+      "loss": 0.7078,
+      "step": 38
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 0.025148095563054085,
+      "learning_rate": 0.00018027116379309638,
+      "loss": 0.699,
+      "step": 39
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 0.02687731944024563,
+      "learning_rate": 0.00017865515558026428,
+      "loss": 0.702,
+      "step": 40
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "eval_loss": 0.702426552772522,
+      "eval_runtime": 304.0078,
+      "eval_samples_per_second": 32.558,
+      "eval_steps_per_second": 0.128,
+      "step": 40
+    },
+    {
+      "epoch": 0.9425287356321839,
+      "grad_norm": 0.021480431780219078,
+      "learning_rate": 0.00017698339834299061,
+      "loss": 0.7041,
+      "step": 41
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 0.0241087656468153,
+      "learning_rate": 0.00017525707698561385,
+      "loss": 0.7015,
+      "step": 42
+    },
+    {
+      "epoch": 0.9885057471264368,
+      "grad_norm": 0.021253138780593872,
+      "learning_rate": 0.00017347741508630672,
+      "loss": 0.705,
+      "step": 43
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.035563599318265915,
+      "learning_rate": 0.00017164567402983152,
+      "loss": 0.6885,
+      "step": 44
+    },
+    {
+      "epoch": 1.0229885057471264,
+      "grad_norm": 0.03471782058477402,
+      "learning_rate": 0.0001697631521134985,
+      "loss": 0.6895,
+      "step": 45
+    },
+    {
+      "epoch": 1.0459770114942528,
+      "grad_norm": 0.021441299468278885,
+      "learning_rate": 0.00016783118362696163,
+      "loss": 0.6928,
+      "step": 46
+    },
+    {
+      "epoch": 1.0689655172413792,
+      "grad_norm": 0.027905387803912163,
+      "learning_rate": 0.00016585113790650388,
+      "loss": 0.6954,
+      "step": 47
+    },
+    {
+      "epoch": 1.0919540229885056,
+      "grad_norm": 0.022263407707214355,
+      "learning_rate": 0.00016382441836448202,
+      "loss": 0.6869,
+      "step": 48
+    },
+    {
+      "epoch": 1.1149425287356323,
+      "grad_norm": 0.02491128444671631,
+      "learning_rate": 0.0001617524614946192,
+      "loss": 0.6955,
+      "step": 49
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "grad_norm": 0.025002798065543175,
+      "learning_rate": 0.00015963673585385016,
+      "loss": 0.6926,
+      "step": 50
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "eval_loss": 0.690385103225708,
+      "eval_runtime": 304.7579,
+      "eval_samples_per_second": 32.478,
+      "eval_steps_per_second": 0.128,
+      "step": 50
+    },
+    {
+      "epoch": 1.160919540229885,
+      "grad_norm": 0.022065704688429832,
+      "learning_rate": 0.0001574787410214407,
+      "loss": 0.6894,
+      "step": 51
+    },
+    {
+      "epoch": 1.1839080459770115,
+      "grad_norm": 0.02315184473991394,
+      "learning_rate": 0.00015528000653611935,
+      "loss": 0.6898,
+      "step": 52
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 0.02273298054933548,
+      "learning_rate": 0.00015304209081197425,
+      "loss": 0.683,
+      "step": 53
+    },
+    {
+      "epoch": 1.2298850574712643,
+      "grad_norm": 0.025234676897525787,
+      "learning_rate": 0.000150766580033884,
+      "loss": 0.6857,
+      "step": 54
+    },
+    {
+      "epoch": 1.2528735632183907,
+      "grad_norm": 0.02536899223923683,
+      "learning_rate": 0.00014845508703326504,
+      "loss": 0.706,
+      "step": 55
+    },
+    {
+      "epoch": 1.2758620689655173,
+      "grad_norm": 0.020374612882733345,
+      "learning_rate": 0.0001461092501449326,
+      "loss": 0.6911,
+      "step": 56
+    },
+    {
+      "epoch": 1.2988505747126438,
+      "grad_norm": 0.019521547481417656,
+      "learning_rate": 0.00014373073204588556,
+      "loss": 0.6865,
+      "step": 57
+    },
+    {
+      "epoch": 1.3218390804597702,
+      "grad_norm": 0.023520860821008682,
+      "learning_rate": 0.00014132121857683783,
+      "loss": 0.6751,
+      "step": 58
+    },
+    {
+      "epoch": 1.3448275862068966,
+      "grad_norm": 0.02198459580540657,
+      "learning_rate": 0.00013888241754733208,
+      "loss": 0.6833,
+      "step": 59
+    },
+    {
+      "epoch": 1.367816091954023,
+      "grad_norm": 0.023501180112361908,
+      "learning_rate": 0.00013641605752528224,
+      "loss": 0.6795,
+      "step": 60
+    },
+    {
+      "epoch": 1.367816091954023,
+      "eval_loss": 0.6821420192718506,
+      "eval_runtime": 304.5567,
+      "eval_samples_per_second": 32.5,
+      "eval_steps_per_second": 0.128,
+      "step": 60
+    },
+    {
+      "epoch": 1.3908045977011494,
+      "grad_norm": 0.021825293079018593,
+      "learning_rate": 0.00013392388661180303,
+      "loss": 0.6751,
+      "step": 61
+    },
+    {
+      "epoch": 1.4137931034482758,
+      "grad_norm": 0.022589631378650665,
+      "learning_rate": 0.0001314076712021949,
+      "loss": 0.6744,
+      "step": 62
+    },
+    {
+      "epoch": 1.4367816091954024,
+      "grad_norm": 0.022593483328819275,
+      "learning_rate": 0.0001288691947339621,
+      "loss": 0.6648,
+      "step": 63
+    },
+    {
+      "epoch": 1.4597701149425286,
+      "grad_norm": 0.019547760486602783,
+      "learning_rate": 0.00012631025642275212,
+      "loss": 0.6852,
+      "step": 64
+    },
+    {
+      "epoch": 1.4827586206896552,
+      "grad_norm": 0.0213349349796772,
+      "learning_rate": 0.0001237326699871115,
+      "loss": 0.6861,
+      "step": 65
+    },
+    {
+      "epoch": 1.5057471264367817,
+      "grad_norm": 0.02310025505721569,
+      "learning_rate": 0.00012113826236296244,
+      "loss": 0.6683,
+      "step": 66
+    },
+    {
+      "epoch": 1.528735632183908,
+      "grad_norm": 0.02816838026046753,
+      "learning_rate": 0.00011852887240871145,
+      "loss": 0.6937,
+      "step": 67
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 0.020846517756581306,
+      "learning_rate": 0.00011590634960190721,
+      "loss": 0.6514,
+      "step": 68
+    },
+    {
+      "epoch": 1.5747126436781609,
+      "grad_norm": 0.021266207098960876,
+      "learning_rate": 0.00011327255272837221,
+      "loss": 0.672,
+      "step": 69
+    },
+    {
+      "epoch": 1.5977011494252875,
+      "grad_norm": 0.021223735064268112,
+      "learning_rate": 0.00011062934856473655,
+      "loss": 0.6694,
+      "step": 70
+    },
+    {
+      "epoch": 1.5977011494252875,
+      "eval_loss": 0.6756598353385925,
+      "eval_runtime": 307.17,
+      "eval_samples_per_second": 32.223,
+      "eval_steps_per_second": 0.127,
+      "step": 70
+    },
+    {
+      "epoch": 1.6206896551724137,
+      "grad_norm": 0.02269381284713745,
+      "learning_rate": 0.00010797861055530831,
+      "loss": 0.6756,
+      "step": 71
+    },
+    {
+      "epoch": 1.6436781609195403,
+      "grad_norm": 0.020797230303287506,
+      "learning_rate": 0.00010532221748421787,
+      "loss": 0.6776,
+      "step": 72
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.02278304472565651,
+      "learning_rate": 0.00010266205214377748,
+      "loss": 0.6634,
+      "step": 73
+    },
+    {
+      "epoch": 1.6896551724137931,
+      "grad_norm": 0.028367692604660988,
+      "learning_rate": 0.0001,
+      "loss": 0.6644,
+      "step": 74
+    },
+    {
+      "epoch": 1.7126436781609196,
+      "grad_norm": 0.026720669120550156,
+      "learning_rate": 9.733794785622253e-05,
+      "loss": 0.692,
+      "step": 75
+    },
+    {
+      "epoch": 1.735632183908046,
+      "grad_norm": 0.02203705534338951,
+      "learning_rate": 9.467778251578217e-05,
+      "loss": 0.669,
+      "step": 76
+    },
+    {
+      "epoch": 1.7586206896551724,
+      "grad_norm": 0.025563135743141174,
+      "learning_rate": 9.202138944469168e-05,
+      "loss": 0.6778,
+      "step": 77
+    },
+    {
+      "epoch": 1.7816091954022988,
+      "grad_norm": 0.026585958898067474,
+      "learning_rate": 8.937065143526347e-05,
+      "loss": 0.6616,
+      "step": 78
+    },
+    {
+      "epoch": 1.8045977011494254,
+      "grad_norm": 0.023832708597183228,
+      "learning_rate": 8.672744727162781e-05,
+      "loss": 0.6785,
+      "step": 79
+    },
+    {
+      "epoch": 1.8275862068965516,
+      "grad_norm": 0.03144339472055435,
+      "learning_rate": 8.409365039809281e-05,
+      "loss": 0.674,
+      "step": 80
+    },
+    {
+      "epoch": 1.8275862068965516,
+      "eval_loss": 0.6707818508148193,
+      "eval_runtime": 303.5438,
+      "eval_samples_per_second": 32.608,
+      "eval_steps_per_second": 0.128,
+      "step": 80
+    },
+    {
+      "epoch": 1.8505747126436782,
+      "grad_norm": 0.02507634088397026,
+      "learning_rate": 8.147112759128859e-05,
+      "loss": 0.678,
+      "step": 81
+    },
+    {
+      "epoch": 1.8735632183908046,
+      "grad_norm": 0.024481408298015594,
+      "learning_rate": 7.886173763703757e-05,
+      "loss": 0.6598,
+      "step": 82
+    },
+    {
+      "epoch": 1.896551724137931,
+      "grad_norm": 0.022987501695752144,
+      "learning_rate": 7.626733001288851e-05,
+      "loss": 0.6679,
+      "step": 83
+    },
+    {
+      "epoch": 1.9195402298850575,
+      "grad_norm": 0.025647416710853577,
+      "learning_rate": 7.368974357724789e-05,
+      "loss": 0.6735,
+      "step": 84
+    },
+    {
+      "epoch": 1.9425287356321839,
+      "grad_norm": 0.024662526324391365,
+      "learning_rate": 7.113080526603792e-05,
+      "loss": 0.6423,
+      "step": 85
+    },
+    {
+      "epoch": 1.9655172413793105,
+      "grad_norm": 0.025277674198150635,
+      "learning_rate": 6.859232879780515e-05,
+      "loss": 0.6815,
+      "step": 86
+    },
+    {
+      "epoch": 1.9885057471264367,
+      "grad_norm": 0.022437684237957,
+      "learning_rate": 6.607611338819697e-05,
+      "loss": 0.6788,
+      "step": 87
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.03651784360408783,
+      "learning_rate": 6.358394247471778e-05,
+      "loss": 0.7069,
+      "step": 88
+    },
+    {
+      "epoch": 2.0229885057471266,
+      "grad_norm": 0.023186692968010902,
+      "learning_rate": 6.111758245266794e-05,
+      "loss": 0.6604,
+      "step": 89
+    },
+    {
+      "epoch": 2.045977011494253,
+      "grad_norm": 0.02420475333929062,
+      "learning_rate": 5.867878142316221e-05,
+      "loss": 0.6543,
+      "step": 90
+    },
+    {
+      "epoch": 2.045977011494253,
+      "eval_loss": 0.6659972071647644,
+      "eval_runtime": 302.4198,
+      "eval_samples_per_second": 32.729,
+      "eval_steps_per_second": 0.129,
+      "step": 90
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 0.0236943569034338,
+      "learning_rate": 5.626926795411447e-05,
+      "loss": 0.647,
+      "step": 91
+    },
+    {
+      "epoch": 2.0919540229885056,
+      "grad_norm": 0.024277806282043457,
+      "learning_rate": 5.38907498550674e-05,
+      "loss": 0.6541,
+      "step": 92
+    },
+    {
+      "epoch": 2.1149425287356323,
+      "grad_norm": 0.023934554308652878,
+      "learning_rate": 5.1544912966734994e-05,
+      "loss": 0.672,
+      "step": 93
+    },
+    {
+      "epoch": 2.1379310344827585,
+      "grad_norm": 0.022945648059248924,
+      "learning_rate": 4.9233419966116036e-05,
+      "loss": 0.6401,
+      "step": 94
+    },
+    {
+      "epoch": 2.160919540229885,
+      "grad_norm": 0.026299618184566498,
+      "learning_rate": 4.695790918802576e-05,
+      "loss": 0.6547,
+      "step": 95
+    },
+    {
+      "epoch": 2.1839080459770113,
+      "grad_norm": 0.022878944873809814,
+      "learning_rate": 4.47199934638807e-05,
+      "loss": 0.6664,
+      "step": 96
+    },
+    {
+      "epoch": 2.206896551724138,
+      "grad_norm": 0.023859554901719093,
+      "learning_rate": 4.252125897855932e-05,
+      "loss": 0.6571,
+      "step": 97
+    },
+    {
+      "epoch": 2.2298850574712645,
+      "grad_norm": 0.02457576058804989,
+      "learning_rate": 4.036326414614985e-05,
+      "loss": 0.6682,
+      "step": 98
+    },
+    {
+      "epoch": 2.2528735632183907,
+      "grad_norm": 0.023506339639425278,
+      "learning_rate": 3.824753850538082e-05,
+      "loss": 0.6555,
+      "step": 99
+    },
+    {
+      "epoch": 2.2758620689655173,
+      "grad_norm": 0.038815535604953766,
+      "learning_rate": 3.617558163551802e-05,
+      "loss": 0.6492,
+      "step": 100
+    },
+    {
+      "epoch": 2.2758620689655173,
+      "eval_loss": 0.6638627052307129,
+      "eval_runtime": 305.4045,
+      "eval_samples_per_second": 32.409,
+      "eval_steps_per_second": 0.128,
+      "step": 100
+    },
+    {
+      "epoch": 2.2988505747126435,
+      "grad_norm": 0.02231566794216633,
+      "learning_rate": 3.414886209349615e-05,
+      "loss": 0.6485,
+      "step": 101
+    },
+    {
+      "epoch": 2.32183908045977,
+      "grad_norm": 0.023987093940377235,
+      "learning_rate": 3.216881637303839e-05,
+      "loss": 0.6549,
+      "step": 102
+    },
+    {
+      "epoch": 2.344827586206897,
+      "grad_norm": 0.026101969182491302,
+      "learning_rate": 3.0236847886501542e-05,
+      "loss": 0.6593,
+      "step": 103
+    },
+    {
+      "epoch": 2.367816091954023,
+      "grad_norm": 0.023063533008098602,
+      "learning_rate": 2.8354325970168484e-05,
+      "loss": 0.6535,
+      "step": 104
+    },
+    {
+      "epoch": 2.3908045977011496,
+      "grad_norm": 0.023235062137246132,
+      "learning_rate": 2.6522584913693294e-05,
+      "loss": 0.652,
+      "step": 105
+    },
+    {
+      "epoch": 2.413793103448276,
+      "grad_norm": 0.02247541956603527,
+      "learning_rate": 2.4742923014386156e-05,
+      "loss": 0.6359,
+      "step": 106
+    },
+    {
+      "epoch": 2.4367816091954024,
+      "grad_norm": 0.02353539690375328,
+      "learning_rate": 2.301660165700936e-05,
+      "loss": 0.6606,
+      "step": 107
+    },
+    {
+      "epoch": 2.4597701149425286,
+      "grad_norm": 0.02745731920003891,
+      "learning_rate": 2.1344844419735755e-05,
+      "loss": 0.6435,
+      "step": 108
+    },
+    {
+      "epoch": 2.4827586206896552,
+      "grad_norm": 0.024043822661042213,
+      "learning_rate": 1.9728836206903656e-05,
+      "loss": 0.6548,
+      "step": 109
+    },
+    {
+      "epoch": 2.5057471264367814,
+      "grad_norm": 0.022284943610429764,
+      "learning_rate": 1.8169722409183097e-05,
+      "loss": 0.6508,
+      "step": 110
+    },
+    {
+      "epoch": 2.5057471264367814,
+      "eval_loss": 0.662615954875946,
+      "eval_runtime": 299.7437,
+      "eval_samples_per_second": 33.022,
+      "eval_steps_per_second": 0.13,
+      "step": 110
+    },
+    {
+      "epoch": 2.528735632183908,
+      "grad_norm": 0.02287135273218155,
+      "learning_rate": 1.6668608091748495e-05,
+      "loss": 0.6384,
+      "step": 111
+    },
+    {
+      "epoch": 2.5517241379310347,
+      "grad_norm": 0.02666754461824894,
+      "learning_rate": 1.522655721103291e-05,
+      "loss": 0.6628,
+      "step": 112
+    },
+    {
+      "epoch": 2.574712643678161,
+      "grad_norm": 0.023315856233239174,
+      "learning_rate": 1.3844591860619383e-05,
+      "loss": 0.6634,
+      "step": 113
+    },
+    {
+      "epoch": 2.5977011494252875,
+      "grad_norm": 0.023025084286928177,
+      "learning_rate": 1.2523691546803873e-05,
+      "loss": 0.6711,
+      "step": 114
+    },
+    {
+      "epoch": 2.6206896551724137,
+      "grad_norm": 0.023308036848902702,
+      "learning_rate": 1.1264792494342857e-05,
+      "loss": 0.6421,
+      "step": 115
+    },
+    {
+      "epoch": 2.6436781609195403,
+      "grad_norm": 0.022443862631917,
+      "learning_rate": 1.0068786982878087e-05,
+      "loss": 0.6557,
+      "step": 116
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.0229327455163002,
+      "learning_rate": 8.936522714508678e-06,
+      "loss": 0.6709,
+      "step": 117
+    },
+    {
+      "epoch": 2.689655172413793,
+      "grad_norm": 0.0223649051040411,
+      "learning_rate": 7.868802212958703e-06,
+      "loss": 0.6493,
+      "step": 118
+    },
+    {
+      "epoch": 2.7126436781609193,
+      "grad_norm": 0.022036027163267136,
+      "learning_rate": 6.866382254766157e-06,
+      "loss": 0.6552,
+      "step": 119
+    },
+    {
+      "epoch": 2.735632183908046,
+      "grad_norm": 0.022042695432901382,
+      "learning_rate": 5.929973332896677e-06,
+      "loss": 0.656,
+      "step": 120
+    },
+    {
+      "epoch": 2.735632183908046,
+      "eval_loss": 0.6621032953262329,
+      "eval_runtime": 304.5155,
+      "eval_samples_per_second": 32.504,
+      "eval_steps_per_second": 0.128,
+      "step": 120
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "grad_norm": 0.026914741843938828,
+      "learning_rate": 5.060239153161872e-06,
+      "loss": 0.6578,
+      "step": 121
+    },
+    {
+      "epoch": 2.781609195402299,
+      "grad_norm": 0.022699004039168358,
+      "learning_rate": 4.257796163799455e-06,
+      "loss": 0.6477,
+      "step": 122
+    },
+    {
+      "epoch": 2.8045977011494254,
+      "grad_norm": 0.02309352532029152,
+      "learning_rate": 3.5232131185484076e-06,
+      "loss": 0.6447,
+      "step": 123
+    },
+    {
+      "epoch": 2.8275862068965516,
+      "grad_norm": 0.02277517318725586,
+      "learning_rate": 2.857010673529015e-06,
+      "loss": 0.6427,
+      "step": 124
+    },
+    {
+      "epoch": 2.8505747126436782,
+      "grad_norm": 0.027453523129224777,
+      "learning_rate": 2.259661018213333e-06,
+      "loss": 0.6593,
+      "step": 125
+    },
+    {
+      "epoch": 2.873563218390805,
+      "grad_norm": 0.022547965869307518,
+      "learning_rate": 1.7315875407479032e-06,
+      "loss": 0.6637,
+      "step": 126
+    },
+    {
+      "epoch": 2.896551724137931,
+      "grad_norm": 0.022168701514601707,
+      "learning_rate": 1.2731645278655445e-06,
+      "loss": 0.6539,
+      "step": 127
+    },
+    {
+      "epoch": 2.9195402298850572,
+      "grad_norm": 0.0227156113833189,
+      "learning_rate": 8.847168995992916e-07,
+      "loss": 0.6673,
+      "step": 128
+    },
+    {
+      "epoch": 2.942528735632184,
+      "grad_norm": 0.022653989493846893,
+      "learning_rate": 5.665199789862907e-07,
+      "loss": 0.6633,
+      "step": 129
+    },
+    {
+      "epoch": 2.9655172413793105,
+      "grad_norm": 0.022713936865329742,
+      "learning_rate": 3.1879929692498757e-07,
+      "loss": 0.6492,
+      "step": 130
+    },
+    {
+      "epoch": 2.9655172413793105,
+      "eval_loss": 0.661920964717865,
+      "eval_runtime": 301.3689,
+      "eval_samples_per_second": 32.843,
+      "eval_steps_per_second": 0.129,
+      "step": 130
+    },
+    {
+      "epoch": 2.9885057471264367,
+      "grad_norm": 0.0218950342386961,
+      "learning_rate": 1.4173043232380557e-07,
+      "loss": 0.6681,
+      "step": 131
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.033240437507629395,
+      "learning_rate": 3.5438887654737355e-08,
+      "loss": 0.6613,
+      "step": 132
+    },
+    {
+      "epoch": 3.0,
+      "step": 132,
+      "total_flos": 4.878497440777581e+19,
+      "train_loss": 0.7089937537005453,
+      "train_runtime": 30749.2873,
+      "train_samples_per_second": 8.691,
+      "train_steps_per_second": 0.004
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 132,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.878497440777581e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:109bb65f0ec5102f6908af515dd779b3030e0edf756186da7919efca0812bd0b
+size 6225