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
+  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
+
+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: 0.6699
+
+## 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: 42
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.8865        | 0.2299 | 10   | 1.0120          |
+| 0.7698        | 0.4598 | 20   | 0.8263          |
+| 0.7376        | 0.6897 | 30   | 0.7322          |
+| 0.7202        | 0.9195 | 40   | 0.7093          |
+| 0.6826        | 1.1379 | 50   | 0.6975          |
+| 0.6718        | 1.3678 | 60   | 0.6894          |
+| 0.6726        | 1.5977 | 70   | 0.6833          |
+| 0.6683        | 1.8276 | 80   | 0.6786          |
+| 0.6532        | 2.0460 | 90   | 0.6745          |
+| 0.6622        | 2.2759 | 100  | 0.6719          |
+| 0.6476        | 2.5057 | 110  | 0.6705          |
+| 0.6399        | 2.7356 | 120  | 0.6700          |
+| 0.643         | 2.9655 | 130  | 0.6699          |
+
+
+### 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": [
+    "gate",
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "v_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:d6d9b9ad255df4f22b8d54c5603eb92a187b148b5cb5a704ce4187165cd62f6d
+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": 0.6698681116104126,
+    "eval_runtime": 301.0401,
+    "eval_samples_per_second": 32.879,
+    "eval_steps_per_second": 0.13,
+    "total_flos": 4.884710196870591e+19,
+    "train_loss": 0.7087282439072927,
+    "train_runtime": 30755.2831,
+    "train_samples_per_second": 8.689,
+    "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": [
+    "gate",
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "v_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:ac6871a129ee857c4e57346ab8c7f4d8dd856f27e98680cdc6d322253d0dc0e4
+size 15451

checkpoint-100/rng_state_120.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79a21f40c39d97a54c667ac66091490e805796413b84cb83e01fc503b816a2f8
+size 15451

checkpoint-100/rng_state_125.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0299debc747f72b6e9f4ca6027c4693fa371d32f428afc0b5bff31cdb490bdeb
+size 15451

checkpoint-100/rng_state_13.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bbd67668df4b5b6641c05d523762cc90cef9d00a193dbfc933994936c6c7e86
+size 15440

checkpoint-100/rng_state_14.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fdbec4351dfdd05d7b2d3dda157f8d0e8141b20d4dc41ff83826a684582b944
+size 15440

checkpoint-100/rng_state_16.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab4407d11f40817aba7ffce67cca6eddee27b3cd5c9f24560361ea8de66feb66
+size 15440

checkpoint-100/rng_state_31.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f73cc8bc0f589546d8b9e0466d21a8cc42ca142b0d9243558d0245dd47c43fb
+size 15440

checkpoint-100/rng_state_32.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c072eeaed7501b9a8bf1287c5b5e9165866bd90c26dbdfe2b8a1069e451540a6
+size 15440

checkpoint-100/rng_state_47.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee99b5770134ba724d24366e685047fc6bbf84dfd005c76f2a35001d7ba8e5bf
+size 15440

checkpoint-100/rng_state_50.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a91dea67532293d40197c0bb5f31c1c7effd84cc9bc631cf18c01ce509d685d
+size 15440

checkpoint-100/rng_state_53.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f06bf77b1133e445e057cd47a1a198166b80286431e16469771937973a5c5d5b
+size 15440

checkpoint-100/rng_state_82.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:474f3e21d47a349e7847a1b5af202f82f3d242cc215694ebc1bac5d66f07cbde
+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": 0.6698681116104126,
+    "eval_runtime": 301.0401,
+    "eval_samples_per_second": 32.879,
+    "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 sha256:6b5a8256cc9922f8f2592a7e6a38ad53be46c8ce8ee828dda68c1b7e3013336d
+size 4997644048

model-00004-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df52cbcf6bbe600e1cfa520d8290aee43cfa1c0a254125e967b34f914f99e6a1
+size 4997644048

model-00005-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d904e65fc2f539cfb2ed4f0ac1097da8845420c3f4c252ec885646621a49a3b4
+size 4997644048

model-00006-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1a2475cf7bb04c074ddc9a6baf5edda2a897caf325dcf7a46366a1012bb228d
+size 4997644648

model-00007-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291316a7ddcc5c13bd1262792352def3283358b8ec117abebfdfedfd29f992d5
+size 4997644832

model-00009-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0838b5c99b2330b0336dd221ddac3f242b0360cfe2256ede967152e4d18223c
+size 4997644832

model-00011-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:759d7003401231bd614ba965de47d1b7d5bae79da89b2eadac1b2c05c9206006
+size 4997644840

model-00012-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f585f50e382a8d4f8c23a01af690ae4d53ab3fd8722d917952c4080fddf5e331
+size 4997644832

model-00016-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1493c93b8110b7a7e94e7b0dc88f3cf2799f8f15c3e15de4b810ec4b376c05f0
+size 4997644832

model-00018-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75ce4809410fd45f6981615853d05e53294cf76d403a72409230bcf9126f111f
+size 4997644832

model-00021-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:593ba4e9606ea201b3e1c76522caf2bae251902a6e35e340c484583ea4ed6c80
+size 4997644832

model-00022-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86a8545ea7913fde8ad7d4d9352268ae81b2ca9900788ce7cf13c306c77e8a21
+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": 4.884710196870591e+19,
+    "train_loss": 0.7087282439072927,
+    "train_runtime": 30755.2831,
+    "train_samples_per_second": 8.689,
+    "train_steps_per_second": 0.004
+}

trainer_log.jsonl

@@ -0,0 +1,146 @@
+{"current_steps": 1, "total_steps": 132, "loss": 0.9434, "lr": 0.0, "epoch": 0.022988505747126436, "percentage": 0.76, "elapsed_time": "0:03:36", "remaining_time": "7:52:42"}
+{"current_steps": 2, "total_steps": 132, "loss": 0.9432, "lr": 1.4285714285714285e-05, "epoch": 0.04597701149425287, "percentage": 1.52, "elapsed_time": "0:07:03", "remaining_time": "7:38:49"}
+{"current_steps": 3, "total_steps": 132, "loss": 0.9587, "lr": 2.857142857142857e-05, "epoch": 0.06896551724137931, "percentage": 2.27, "elapsed_time": "0:10:29", "remaining_time": "7:31:29"}
+{"current_steps": 4, "total_steps": 132, "loss": 0.9314, "lr": 4.2857142857142856e-05, "epoch": 0.09195402298850575, "percentage": 3.03, "elapsed_time": "0:13:54", "remaining_time": "7:25:03"}
+{"current_steps": 5, "total_steps": 132, "loss": 0.921, "lr": 5.714285714285714e-05, "epoch": 0.11494252873563218, "percentage": 3.79, "elapsed_time": "0:17:19", "remaining_time": "7:19:57"}
+{"current_steps": 6, "total_steps": 132, "loss": 0.9226, "lr": 7.142857142857143e-05, "epoch": 0.13793103448275862, "percentage": 4.55, "elapsed_time": "0:20:42", "remaining_time": "7:15:00"}
+{"current_steps": 7, "total_steps": 132, "loss": 0.9143, "lr": 8.571428571428571e-05, "epoch": 0.16091954022988506, "percentage": 5.3, "elapsed_time": "0:24:08", "remaining_time": "7:11:14"}
+{"current_steps": 8, "total_steps": 132, "loss": 0.9042, "lr": 0.0001, "epoch": 0.1839080459770115, "percentage": 6.06, "elapsed_time": "0:27:32", "remaining_time": "7:06:58"}
+{"current_steps": 9, "total_steps": 132, "loss": 0.9103, "lr": 0.00011428571428571428, "epoch": 0.20689655172413793, "percentage": 6.82, "elapsed_time": "0:31:00", "remaining_time": "7:03:42"}
+{"current_steps": 10, "total_steps": 132, "loss": 0.8865, "lr": 0.00012857142857142858, "epoch": 0.22988505747126436, "percentage": 7.58, "elapsed_time": "0:34:25", "remaining_time": "6:59:59"}
+{"current_steps": 10, "total_steps": 132, "eval_loss": 1.0120309591293335, "epoch": 0.22988505747126436, "percentage": 7.58, "elapsed_time": "0:39:32", "remaining_time": "8:02:21"}
+{"current_steps": 11, "total_steps": 132, "loss": 0.8673, "lr": 0.00014285714285714287, "epoch": 0.25287356321839083, "percentage": 8.33, "elapsed_time": "0:42:59", "remaining_time": "7:52:51"}
+{"current_steps": 12, "total_steps": 132, "loss": 0.8573, "lr": 0.00015714285714285716, "epoch": 0.27586206896551724, "percentage": 9.09, "elapsed_time": "0:46:24", "remaining_time": "7:44:04"}
+{"current_steps": 13, "total_steps": 132, "loss": 0.8505, "lr": 0.00017142857142857143, "epoch": 0.2988505747126437, "percentage": 9.85, "elapsed_time": "0:49:49", "remaining_time": "7:36:05"}
+{"current_steps": 14, "total_steps": 132, "loss": 0.8385, "lr": 0.00018571428571428572, "epoch": 0.3218390804597701, "percentage": 10.61, "elapsed_time": "0:53:14", "remaining_time": "7:28:44"}
+{"current_steps": 15, "total_steps": 132, "loss": 0.8163, "lr": 0.0002, "epoch": 0.3448275862068966, "percentage": 11.36, "elapsed_time": "0:56:39", "remaining_time": "7:21:59"}
+{"current_steps": 16, "total_steps": 132, "loss": 0.7976, "lr": 0.00019996456111234527, "epoch": 0.367816091954023, "percentage": 12.12, "elapsed_time": "1:00:03", "remaining_time": "7:15:22"}
+{"current_steps": 17, "total_steps": 132, "loss": 0.805, "lr": 0.0001998582695676762, "epoch": 0.39080459770114945, "percentage": 12.88, "elapsed_time": "1:03:26", "remaining_time": "7:09:11"}
+{"current_steps": 18, "total_steps": 132, "loss": 0.7909, "lr": 0.000199681200703075, "epoch": 0.41379310344827586, "percentage": 13.64, "elapsed_time": "1:06:52", "remaining_time": "7:03:30"}
+{"current_steps": 19, "total_steps": 132, "loss": 0.7971, "lr": 0.00019943348002101371, "epoch": 0.4367816091954023, "percentage": 14.39, "elapsed_time": "1:10:17", "remaining_time": "6:58:04"}
+{"current_steps": 20, "total_steps": 132, "loss": 0.7698, "lr": 0.00019911528310040074, "epoch": 0.45977011494252873, "percentage": 15.15, "elapsed_time": "1:13:43", "remaining_time": "6:52:50"}
+{"current_steps": 20, "total_steps": 132, "eval_loss": 0.8262545466423035, "epoch": 0.45977011494252873, "percentage": 15.15, "elapsed_time": "1:18:47", "remaining_time": "7:21:14"}
+{"current_steps": 21, "total_steps": 132, "loss": 0.7775, "lr": 0.00019872683547213446, "epoch": 0.4827586206896552, "percentage": 15.91, "elapsed_time": "1:22:12", "remaining_time": "7:14:32"}
+{"current_steps": 22, "total_steps": 132, "loss": 0.7671, "lr": 0.00019826841245925212, "epoch": 0.5057471264367817, "percentage": 16.67, "elapsed_time": "1:25:37", "remaining_time": "7:08:09"}
+{"current_steps": 23, "total_steps": 132, "loss": 0.7575, "lr": 0.00019774033898178667, "epoch": 0.5287356321839081, "percentage": 17.42, "elapsed_time": "1:29:01", "remaining_time": "7:01:55"}
+{"current_steps": 24, "total_steps": 132, "loss": 0.7454, "lr": 0.00019714298932647098, "epoch": 0.5517241379310345, "percentage": 18.18, "elapsed_time": "1:32:24", "remaining_time": "6:55:51"}
+{"current_steps": 25, "total_steps": 132, "loss": 0.7456, "lr": 0.0001964767868814516, "epoch": 0.5747126436781609, "percentage": 18.94, "elapsed_time": "1:35:48", "remaining_time": "6:50:03"}
+{"current_steps": 26, "total_steps": 132, "loss": 0.7314, "lr": 0.00019574220383620055, "epoch": 0.5977011494252874, "percentage": 19.7, "elapsed_time": "1:39:12", "remaining_time": "6:44:27"}
+{"current_steps": 27, "total_steps": 132, "loss": 0.7148, "lr": 0.00019493976084683813, "epoch": 0.6206896551724138, "percentage": 20.45, "elapsed_time": "1:42:36", "remaining_time": "6:39:00"}
+{"current_steps": 28, "total_steps": 132, "loss": 0.7409, "lr": 0.00019407002666710336, "epoch": 0.6436781609195402, "percentage": 21.21, "elapsed_time": "1:45:59", "remaining_time": "6:33:41"}
+{"current_steps": 29, "total_steps": 132, "loss": 0.7213, "lr": 0.00019313361774523385, "epoch": 0.6666666666666666, "percentage": 21.97, "elapsed_time": "1:49:24", "remaining_time": "6:28:34"}
+{"current_steps": 30, "total_steps": 132, "loss": 0.7376, "lr": 0.00019213119778704128, "epoch": 0.6896551724137931, "percentage": 22.73, "elapsed_time": "1:52:49", "remaining_time": "6:23:37"}
+{"current_steps": 30, "total_steps": 132, "eval_loss": 0.732206404209137, "epoch": 0.6896551724137931, "percentage": 22.73, "elapsed_time": "1:57:53", "remaining_time": "6:40:50"}
+{"current_steps": 31, "total_steps": 132, "loss": 0.7336, "lr": 0.00019106347728549135, "epoch": 0.7126436781609196, "percentage": 23.48, "elapsed_time": "2:01:15", "remaining_time": "6:35:05"}
+{"current_steps": 32, "total_steps": 132, "loss": 0.7253, "lr": 0.00018993121301712193, "epoch": 0.735632183908046, "percentage": 24.24, "elapsed_time": "2:04:40", "remaining_time": "6:29:36"}
+{"current_steps": 33, "total_steps": 132, "loss": 0.7232, "lr": 0.00018873520750565718, "epoch": 0.7586206896551724, "percentage": 25.0, "elapsed_time": "2:08:04", "remaining_time": "6:24:13"}
+{"current_steps": 34, "total_steps": 132, "loss": 0.727, "lr": 0.00018747630845319612, "epoch": 0.7816091954022989, "percentage": 25.76, "elapsed_time": "2:11:30", "remaining_time": "6:19:02"}
+{"current_steps": 35, "total_steps": 132, "loss": 0.7152, "lr": 0.0001861554081393806, "epoch": 0.8045977011494253, "percentage": 26.52, "elapsed_time": "2:14:54", "remaining_time": "6:13:52"}
+{"current_steps": 36, "total_steps": 132, "loss": 0.7059, "lr": 0.0001847734427889671, "epoch": 0.8275862068965517, "percentage": 27.27, "elapsed_time": "2:18:16", "remaining_time": "6:08:44"}
+{"current_steps": 37, "total_steps": 132, "loss": 0.7202, "lr": 0.0001833313919082515, "epoch": 0.8505747126436781, "percentage": 28.03, "elapsed_time": "2:21:40", "remaining_time": "6:03:44"}
+{"current_steps": 38, "total_steps": 132, "loss": 0.7033, "lr": 0.0001818302775908169, "epoch": 0.8735632183908046, "percentage": 28.79, "elapsed_time": "2:25:03", "remaining_time": "5:58:50"}
+{"current_steps": 39, "total_steps": 132, "loss": 0.7127, "lr": 0.00018027116379309638, "epoch": 0.896551724137931, "percentage": 29.55, "elapsed_time": "2:28:26", "remaining_time": "5:53:59"}
+{"current_steps": 40, "total_steps": 132, "loss": 0.7202, "lr": 0.00017865515558026428, "epoch": 0.9195402298850575, "percentage": 30.3, "elapsed_time": "2:31:50", "remaining_time": "5:49:13"}
+{"current_steps": 40, "total_steps": 132, "eval_loss": 0.709326446056366, "epoch": 0.9195402298850575, "percentage": 30.3, "elapsed_time": "2:36:55", "remaining_time": "6:00:56"}
+{"current_steps": 41, "total_steps": 132, "loss": 0.7075, "lr": 0.00017698339834299061, "epoch": 0.9425287356321839, "percentage": 31.06, "elapsed_time": "2:40:20", "remaining_time": "5:55:52"}
+{"current_steps": 42, "total_steps": 132, "loss": 0.6974, "lr": 0.00017525707698561385, "epoch": 0.9655172413793104, "percentage": 31.82, "elapsed_time": "2:43:44", "remaining_time": "5:50:52"}
+{"current_steps": 43, "total_steps": 132, "loss": 0.7148, "lr": 0.00017347741508630672, "epoch": 0.9885057471264368, "percentage": 32.58, "elapsed_time": "2:47:09", "remaining_time": "5:45:59"}
+{"current_steps": 44, "total_steps": 132, "loss": 0.716, "lr": 0.00017164567402983152, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "2:48:55", "remaining_time": "5:37:50"}
+{"current_steps": 45, "total_steps": 132, "loss": 0.696, "lr": 0.0001697631521134985, "epoch": 1.0229885057471264, "percentage": 34.09, "elapsed_time": "2:52:20", "remaining_time": "5:33:12"}
+{"current_steps": 46, "total_steps": 132, "loss": 0.6967, "lr": 0.00016783118362696163, "epoch": 1.0459770114942528, "percentage": 34.85, "elapsed_time": "2:55:44", "remaining_time": "5:28:34"}
+{"current_steps": 47, "total_steps": 132, "loss": 0.6977, "lr": 0.00016585113790650388, "epoch": 1.0689655172413792, "percentage": 35.61, "elapsed_time": "2:59:08", "remaining_time": "5:23:59"}
+{"current_steps": 48, "total_steps": 132, "loss": 0.6856, "lr": 0.00016382441836448202, "epoch": 1.0919540229885056, "percentage": 36.36, "elapsed_time": "3:02:33", "remaining_time": "5:19:27"}
+{"current_steps": 49, "total_steps": 132, "loss": 0.6991, "lr": 0.0001617524614946192, "epoch": 1.1149425287356323, "percentage": 37.12, "elapsed_time": "3:05:58", "remaining_time": "5:15:00"}
+{"current_steps": 50, "total_steps": 132, "loss": 0.6826, "lr": 0.00015963673585385016, "epoch": 1.1379310344827587, "percentage": 37.88, "elapsed_time": "3:09:23", "remaining_time": "5:10:35"}
+{"current_steps": 50, "total_steps": 132, "eval_loss": 0.6974772214889526, "epoch": 1.1379310344827587, "percentage": 37.88, "elapsed_time": "3:14:28", "remaining_time": "5:18:55"}
+{"current_steps": 51, "total_steps": 132, "loss": 0.6958, "lr": 0.0001574787410214407, "epoch": 1.160919540229885, "percentage": 38.64, "elapsed_time": "3:18:13", "remaining_time": "5:14:49"}
+{"current_steps": 52, "total_steps": 132, "loss": 0.6889, "lr": 0.00015528000653611935, "epoch": 1.1839080459770115, "percentage": 39.39, "elapsed_time": "3:21:42", "remaining_time": "5:10:18"}
+{"current_steps": 53, "total_steps": 132, "loss": 0.6709, "lr": 0.00015304209081197425, "epoch": 1.206896551724138, "percentage": 40.15, "elapsed_time": "3:25:06", "remaining_time": "5:05:44"}
+{"current_steps": 54, "total_steps": 132, "loss": 0.6841, "lr": 0.000150766580033884, "epoch": 1.2298850574712643, "percentage": 40.91, "elapsed_time": "3:28:33", "remaining_time": "5:01:14"}
+{"current_steps": 55, "total_steps": 132, "loss": 0.6971, "lr": 0.00014845508703326504, "epoch": 1.2528735632183907, "percentage": 41.67, "elapsed_time": "3:31:57", "remaining_time": "4:56:44"}
+{"current_steps": 56, "total_steps": 132, "loss": 0.6815, "lr": 0.0001461092501449326, "epoch": 1.2758620689655173, "percentage": 42.42, "elapsed_time": "3:35:22", "remaining_time": "4:52:17"}
+{"current_steps": 57, "total_steps": 132, "loss": 0.6829, "lr": 0.00014373073204588556, "epoch": 1.2988505747126438, "percentage": 43.18, "elapsed_time": "3:38:45", "remaining_time": "4:47:50"}
+{"current_steps": 58, "total_steps": 132, "loss": 0.6788, "lr": 0.00014132121857683783, "epoch": 1.3218390804597702, "percentage": 43.94, "elapsed_time": "3:42:13", "remaining_time": "4:43:31"}
+{"current_steps": 59, "total_steps": 132, "loss": 0.6867, "lr": 0.00013888241754733208, "epoch": 1.3448275862068966, "percentage": 44.7, "elapsed_time": "3:45:37", "remaining_time": "4:39:09"}
+{"current_steps": 60, "total_steps": 132, "loss": 0.6718, "lr": 0.00013641605752528224, "epoch": 1.367816091954023, "percentage": 45.45, "elapsed_time": "3:49:01", "remaining_time": "4:34:50"}
+{"current_steps": 60, "total_steps": 132, "eval_loss": 0.6893976926803589, "epoch": 1.367816091954023, "percentage": 45.45, "elapsed_time": "3:54:07", "remaining_time": "4:40:56"}
+{"current_steps": 61, "total_steps": 132, "loss": 0.6663, "lr": 0.00013392388661180303, "epoch": 1.3908045977011494, "percentage": 46.21, "elapsed_time": "3:57:31", "remaining_time": "4:36:28"}
+{"current_steps": 62, "total_steps": 132, "loss": 0.6805, "lr": 0.0001314076712021949, "epoch": 1.4137931034482758, "percentage": 46.97, "elapsed_time": "4:00:57", "remaining_time": "4:32:03"}
+{"current_steps": 63, "total_steps": 132, "loss": 0.6965, "lr": 0.0001288691947339621, "epoch": 1.4367816091954024, "percentage": 47.73, "elapsed_time": "4:04:20", "remaining_time": "4:27:36"}
+{"current_steps": 64, "total_steps": 132, "loss": 0.6665, "lr": 0.00012631025642275212, "epoch": 1.4597701149425286, "percentage": 48.48, "elapsed_time": "4:07:45", "remaining_time": "4:23:14"}
+{"current_steps": 65, "total_steps": 132, "loss": 0.6782, "lr": 0.0001237326699871115, "epoch": 1.4827586206896552, "percentage": 49.24, "elapsed_time": "4:11:10", "remaining_time": "4:18:53"}
+{"current_steps": 66, "total_steps": 132, "loss": 0.681, "lr": 0.00012113826236296244, "epoch": 1.5057471264367817, "percentage": 50.0, "elapsed_time": "4:14:34", "remaining_time": "4:14:34"}
+{"current_steps": 67, "total_steps": 132, "loss": 0.6584, "lr": 0.00011852887240871145, "epoch": 1.528735632183908, "percentage": 50.76, "elapsed_time": "4:17:59", "remaining_time": "4:10:17"}
+{"current_steps": 68, "total_steps": 132, "loss": 0.6917, "lr": 0.00011590634960190721, "epoch": 1.5517241379310345, "percentage": 51.52, "elapsed_time": "4:21:25", "remaining_time": "4:06:02"}
+{"current_steps": 69, "total_steps": 132, "loss": 0.6786, "lr": 0.00011327255272837221, "epoch": 1.5747126436781609, "percentage": 52.27, "elapsed_time": "4:24:52", "remaining_time": "4:01:50"}
+{"current_steps": 70, "total_steps": 132, "loss": 0.6726, "lr": 0.00011062934856473655, "epoch": 1.5977011494252875, "percentage": 53.03, "elapsed_time": "4:28:17", "remaining_time": "3:57:37"}
+{"current_steps": 70, "total_steps": 132, "eval_loss": 0.6833033561706543, "epoch": 1.5977011494252875, "percentage": 53.03, "elapsed_time": "4:33:22", "remaining_time": "4:02:07"}
+{"current_steps": 71, "total_steps": 132, "loss": 0.6741, "lr": 0.00010797861055530831, "epoch": 1.6206896551724137, "percentage": 53.79, "elapsed_time": "4:36:46", "remaining_time": "3:57:47"}
+{"current_steps": 72, "total_steps": 132, "loss": 0.6622, "lr": 0.00010532221748421787, "epoch": 1.6436781609195403, "percentage": 54.55, "elapsed_time": "4:40:09", "remaining_time": "3:53:28"}
+{"current_steps": 73, "total_steps": 132, "loss": 0.6839, "lr": 0.00010266205214377748, "epoch": 1.6666666666666665, "percentage": 55.3, "elapsed_time": "4:43:35", "remaining_time": "3:49:11"}
+{"current_steps": 74, "total_steps": 132, "loss": 0.6843, "lr": 0.0001, "epoch": 1.6896551724137931, "percentage": 56.06, "elapsed_time": "4:46:59", "remaining_time": "3:44:56"}
+{"current_steps": 75, "total_steps": 132, "loss": 0.6902, "lr": 9.733794785622253e-05, "epoch": 1.7126436781609196, "percentage": 56.82, "elapsed_time": "4:50:22", "remaining_time": "3:40:41"}
+{"current_steps": 76, "total_steps": 132, "loss": 0.67, "lr": 9.467778251578217e-05, "epoch": 1.735632183908046, "percentage": 57.58, "elapsed_time": "4:53:46", "remaining_time": "3:36:28"}
+{"current_steps": 77, "total_steps": 132, "loss": 0.6688, "lr": 9.202138944469168e-05, "epoch": 1.7586206896551724, "percentage": 58.33, "elapsed_time": "4:57:14", "remaining_time": "3:32:18"}
+{"current_steps": 78, "total_steps": 132, "loss": 0.6744, "lr": 8.937065143526347e-05, "epoch": 1.7816091954022988, "percentage": 59.09, "elapsed_time": "5:00:38", "remaining_time": "3:28:08"}
+{"current_steps": 79, "total_steps": 132, "loss": 0.6766, "lr": 8.672744727162781e-05, "epoch": 1.8045977011494254, "percentage": 59.85, "elapsed_time": "5:04:03", "remaining_time": "3:23:59"}
+{"current_steps": 80, "total_steps": 132, "loss": 0.6683, "lr": 8.409365039809281e-05, "epoch": 1.8275862068965516, "percentage": 60.61, "elapsed_time": "5:07:28", "remaining_time": "3:19:51"}
+{"current_steps": 80, "total_steps": 132, "eval_loss": 0.6785663962364197, "epoch": 1.8275862068965516, "percentage": 60.61, "elapsed_time": "5:12:33", "remaining_time": "3:23:09"}
+{"current_steps": 81, "total_steps": 132, "loss": 0.6665, "lr": 8.147112759128859e-05, "epoch": 1.8505747126436782, "percentage": 61.36, "elapsed_time": "5:15:59", "remaining_time": "3:18:57"}
+{"current_steps": 82, "total_steps": 132, "loss": 0.6651, "lr": 7.886173763703757e-05, "epoch": 1.8735632183908046, "percentage": 62.12, "elapsed_time": "5:19:24", "remaining_time": "3:14:45"}
+{"current_steps": 83, "total_steps": 132, "loss": 0.6578, "lr": 7.626733001288851e-05, "epoch": 1.896551724137931, "percentage": 62.88, "elapsed_time": "5:22:48", "remaining_time": "3:10:34"}
+{"current_steps": 84, "total_steps": 132, "loss": 0.6689, "lr": 7.368974357724789e-05, "epoch": 1.9195402298850575, "percentage": 63.64, "elapsed_time": "5:26:14", "remaining_time": "3:06:25"}
+{"current_steps": 85, "total_steps": 132, "loss": 0.676, "lr": 7.113080526603792e-05, "epoch": 1.9425287356321839, "percentage": 64.39, "elapsed_time": "5:29:39", "remaining_time": "3:02:16"}
+{"current_steps": 86, "total_steps": 132, "loss": 0.6514, "lr": 6.859232879780515e-05, "epoch": 1.9655172413793105, "percentage": 65.15, "elapsed_time": "5:33:02", "remaining_time": "2:58:08"}
+{"current_steps": 87, "total_steps": 132, "loss": 0.6728, "lr": 6.607611338819697e-05, "epoch": 1.9885057471264367, "percentage": 65.91, "elapsed_time": "5:36:26", "remaining_time": "2:54:01"}
+{"current_steps": 88, "total_steps": 132, "loss": 0.677, "lr": 6.358394247471778e-05, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "5:38:12", "remaining_time": "2:49:06"}
+{"current_steps": 89, "total_steps": 132, "loss": 0.6688, "lr": 6.111758245266794e-05, "epoch": 2.0229885057471266, "percentage": 67.42, "elapsed_time": "5:41:36", "remaining_time": "2:45:03"}
+{"current_steps": 90, "total_steps": 132, "loss": 0.6532, "lr": 5.867878142316221e-05, "epoch": 2.045977011494253, "percentage": 68.18, "elapsed_time": "5:45:03", "remaining_time": "2:41:01"}
+{"current_steps": 90, "total_steps": 132, "eval_loss": 0.6744519472122192, "epoch": 2.045977011494253, "percentage": 68.18, "elapsed_time": "5:50:07", "remaining_time": "2:43:23"}
+{"current_steps": 91, "total_steps": 132, "loss": 0.6624, "lr": 5.626926795411447e-05, "epoch": 2.0689655172413794, "percentage": 68.94, "elapsed_time": "5:53:32", "remaining_time": "2:39:17"}
+{"current_steps": 92, "total_steps": 132, "loss": 0.6688, "lr": 5.38907498550674e-05, "epoch": 2.0919540229885056, "percentage": 69.7, "elapsed_time": "5:56:56", "remaining_time": "2:35:11"}
+{"current_steps": 93, "total_steps": 132, "loss": 0.6733, "lr": 5.1544912966734994e-05, "epoch": 2.1149425287356323, "percentage": 70.45, "elapsed_time": "6:00:21", "remaining_time": "2:31:07"}
+{"current_steps": 94, "total_steps": 132, "loss": 0.6558, "lr": 4.9233419966116036e-05, "epoch": 2.1379310344827585, "percentage": 71.21, "elapsed_time": "6:03:46", "remaining_time": "2:27:03"}
+{"current_steps": 95, "total_steps": 132, "loss": 0.6491, "lr": 4.695790918802576e-05, "epoch": 2.160919540229885, "percentage": 71.97, "elapsed_time": "6:07:11", "remaining_time": "2:23:00"}
+{"current_steps": 96, "total_steps": 132, "loss": 0.6781, "lr": 4.47199934638807e-05, "epoch": 2.1839080459770113, "percentage": 72.73, "elapsed_time": "6:10:37", "remaining_time": "2:18:59"}
+{"current_steps": 97, "total_steps": 132, "loss": 0.6603, "lr": 4.252125897855932e-05, "epoch": 2.206896551724138, "percentage": 73.48, "elapsed_time": "6:14:01", "remaining_time": "2:14:57"}
+{"current_steps": 98, "total_steps": 132, "loss": 0.6511, "lr": 4.036326414614985e-05, "epoch": 2.2298850574712645, "percentage": 74.24, "elapsed_time": "6:17:26", "remaining_time": "2:10:57"}
+{"current_steps": 99, "total_steps": 132, "loss": 0.6646, "lr": 3.824753850538082e-05, "epoch": 2.2528735632183907, "percentage": 75.0, "elapsed_time": "6:20:52", "remaining_time": "2:06:57"}
+{"current_steps": 100, "total_steps": 132, "loss": 0.6622, "lr": 3.617558163551802e-05, "epoch": 2.2758620689655173, "percentage": 75.76, "elapsed_time": "6:24:17", "remaining_time": "2:02:58"}
+{"current_steps": 100, "total_steps": 132, "eval_loss": 0.6719217300415039, "epoch": 2.2758620689655173, "percentage": 75.76, "elapsed_time": "6:29:23", "remaining_time": "2:04:36"}
+{"current_steps": 101, "total_steps": 132, "loss": 0.6514, "lr": 3.414886209349615e-05, "epoch": 2.2988505747126435, "percentage": 76.52, "elapsed_time": "6:33:08", "remaining_time": "2:00:40"}
+{"current_steps": 102, "total_steps": 132, "loss": 0.6555, "lr": 3.216881637303839e-05, "epoch": 2.32183908045977, "percentage": 77.27, "elapsed_time": "6:36:33", "remaining_time": "1:56:37"}
+{"current_steps": 103, "total_steps": 132, "loss": 0.6613, "lr": 3.0236847886501542e-05, "epoch": 2.344827586206897, "percentage": 78.03, "elapsed_time": "6:39:57", "remaining_time": "1:52:36"}
+{"current_steps": 104, "total_steps": 132, "loss": 0.6471, "lr": 2.8354325970168484e-05, "epoch": 2.367816091954023, "percentage": 78.79, "elapsed_time": "6:43:25", "remaining_time": "1:48:36"}
+{"current_steps": 105, "total_steps": 132, "loss": 0.646, "lr": 2.6522584913693294e-05, "epoch": 2.3908045977011496, "percentage": 79.55, "elapsed_time": "6:46:49", "remaining_time": "1:44:36"}
+{"current_steps": 106, "total_steps": 132, "loss": 0.6546, "lr": 2.4742923014386156e-05, "epoch": 2.413793103448276, "percentage": 80.3, "elapsed_time": "6:50:15", "remaining_time": "1:40:37"}
+{"current_steps": 107, "total_steps": 132, "loss": 0.6588, "lr": 2.301660165700936e-05, "epoch": 2.4367816091954024, "percentage": 81.06, "elapsed_time": "6:53:39", "remaining_time": "1:36:38"}
+{"current_steps": 108, "total_steps": 132, "loss": 0.6473, "lr": 2.1344844419735755e-05, "epoch": 2.4597701149425286, "percentage": 81.82, "elapsed_time": "6:57:02", "remaining_time": "1:32:40"}
+{"current_steps": 109, "total_steps": 132, "loss": 0.6528, "lr": 1.9728836206903656e-05, "epoch": 2.4827586206896552, "percentage": 82.58, "elapsed_time": "7:00:26", "remaining_time": "1:28:43"}
+{"current_steps": 110, "total_steps": 132, "loss": 0.6476, "lr": 1.8169722409183097e-05, "epoch": 2.5057471264367814, "percentage": 83.33, "elapsed_time": "7:03:53", "remaining_time": "1:24:46"}
+{"current_steps": 110, "total_steps": 132, "eval_loss": 0.6705266237258911, "epoch": 2.5057471264367814, "percentage": 83.33, "elapsed_time": "7:08:58", "remaining_time": "1:25:47"}
+{"current_steps": 111, "total_steps": 132, "loss": 0.6563, "lr": 1.6668608091748495e-05, "epoch": 2.528735632183908, "percentage": 84.09, "elapsed_time": "7:12:26", "remaining_time": "1:21:48"}
+{"current_steps": 112, "total_steps": 132, "loss": 0.6458, "lr": 1.522655721103291e-05, "epoch": 2.5517241379310347, "percentage": 84.85, "elapsed_time": "7:15:53", "remaining_time": "1:17:50"}
+{"current_steps": 113, "total_steps": 132, "loss": 0.6541, "lr": 1.3844591860619383e-05, "epoch": 2.574712643678161, "percentage": 85.61, "elapsed_time": "7:19:17", "remaining_time": "1:13:51"}
+{"current_steps": 114, "total_steps": 132, "loss": 0.6475, "lr": 1.2523691546803873e-05, "epoch": 2.5977011494252875, "percentage": 86.36, "elapsed_time": "7:22:41", "remaining_time": "1:09:53"}
+{"current_steps": 115, "total_steps": 132, "loss": 0.6705, "lr": 1.1264792494342857e-05, "epoch": 2.6206896551724137, "percentage": 87.12, "elapsed_time": "7:26:06", "remaining_time": "1:05:56"}
+{"current_steps": 116, "total_steps": 132, "loss": 0.6422, "lr": 1.0068786982878087e-05, "epoch": 2.6436781609195403, "percentage": 87.88, "elapsed_time": "7:29:29", "remaining_time": "1:01:59"}
+{"current_steps": 117, "total_steps": 132, "loss": 0.6622, "lr": 8.936522714508678e-06, "epoch": 2.6666666666666665, "percentage": 88.64, "elapsed_time": "7:32:52", "remaining_time": "0:58:03"}
+{"current_steps": 118, "total_steps": 132, "loss": 0.6529, "lr": 7.868802212958703e-06, "epoch": 2.689655172413793, "percentage": 89.39, "elapsed_time": "7:36:16", "remaining_time": "0:54:08"}
+{"current_steps": 119, "total_steps": 132, "loss": 0.6558, "lr": 6.866382254766157e-06, "epoch": 2.7126436781609193, "percentage": 90.15, "elapsed_time": "7:39:40", "remaining_time": "0:50:12"}
+{"current_steps": 120, "total_steps": 132, "loss": 0.6399, "lr": 5.929973332896677e-06, "epoch": 2.735632183908046, "percentage": 90.91, "elapsed_time": "7:43:05", "remaining_time": "0:46:18"}
+{"current_steps": 120, "total_steps": 132, "eval_loss": 0.6699749231338501, "epoch": 2.735632183908046, "percentage": 90.91, "elapsed_time": "7:48:08", "remaining_time": "0:46:48"}
+{"current_steps": 121, "total_steps": 132, "loss": 0.6566, "lr": 5.060239153161872e-06, "epoch": 2.7586206896551726, "percentage": 91.67, "elapsed_time": "7:51:32", "remaining_time": "0:42:52"}
+{"current_steps": 122, "total_steps": 132, "loss": 0.6564, "lr": 4.257796163799455e-06, "epoch": 2.781609195402299, "percentage": 92.42, "elapsed_time": "7:54:57", "remaining_time": "0:38:55"}
+{"current_steps": 123, "total_steps": 132, "loss": 0.6487, "lr": 3.5232131185484076e-06, "epoch": 2.8045977011494254, "percentage": 93.18, "elapsed_time": "7:58:24", "remaining_time": "0:35:00"}
+{"current_steps": 124, "total_steps": 132, "loss": 0.6394, "lr": 2.857010673529015e-06, "epoch": 2.8275862068965516, "percentage": 93.94, "elapsed_time": "8:01:48", "remaining_time": "0:31:05"}
+{"current_steps": 125, "total_steps": 132, "loss": 0.6562, "lr": 2.259661018213333e-06, "epoch": 2.8505747126436782, "percentage": 94.7, "elapsed_time": "8:05:10", "remaining_time": "0:27:10"}
+{"current_steps": 126, "total_steps": 132, "loss": 0.6446, "lr": 1.7315875407479032e-06, "epoch": 2.873563218390805, "percentage": 95.45, "elapsed_time": "8:08:33", "remaining_time": "0:23:15"}
+{"current_steps": 127, "total_steps": 132, "loss": 0.6519, "lr": 1.2731645278655445e-06, "epoch": 2.896551724137931, "percentage": 96.21, "elapsed_time": "8:11:57", "remaining_time": "0:19:22"}
+{"current_steps": 128, "total_steps": 132, "loss": 0.652, "lr": 8.847168995992916e-07, "epoch": 2.9195402298850572, "percentage": 96.97, "elapsed_time": "8:15:21", "remaining_time": "0:15:28"}
+{"current_steps": 129, "total_steps": 132, "loss": 0.647, "lr": 5.665199789862907e-07, "epoch": 2.942528735632184, "percentage": 97.73, "elapsed_time": "8:18:43", "remaining_time": "0:11:35"}
+{"current_steps": 130, "total_steps": 132, "loss": 0.643, "lr": 3.1879929692498757e-07, "epoch": 2.9655172413793105, "percentage": 98.48, "elapsed_time": "8:22:07", "remaining_time": "0:07:43"}
+{"current_steps": 130, "total_steps": 132, "eval_loss": 0.6699010729789734, "epoch": 2.9655172413793105, "percentage": 98.48, "elapsed_time": "8:27:08", "remaining_time": "0:07:48"}
+{"current_steps": 131, "total_steps": 132, "loss": 0.6597, "lr": 1.4173043232380557e-07, "epoch": 2.9885057471264367, "percentage": 99.24, "elapsed_time": "8:30:30", "remaining_time": "0:03:53"}
+{"current_steps": 132, "total_steps": 132, "loss": 0.6579, "lr": 3.5438887654737355e-08, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "8:32:14", "remaining_time": "0:00:00"}
+{"current_steps": 132, "total_steps": 132, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "8:32:34", "remaining_time": "0:00:00"}

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": 0.11729168146848679,
+      "learning_rate": 0.0,
+      "loss": 0.9434,
+      "step": 1
+    },
+    {
+      "epoch": 0.04597701149425287,
+      "grad_norm": 0.11298783123493195,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.9432,
+      "step": 2
+    },
+    {
+      "epoch": 0.06896551724137931,
+      "grad_norm": 0.11056286096572876,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 0.9587,
+      "step": 3
+    },
+    {
+      "epoch": 0.09195402298850575,
+      "grad_norm": 0.10647455602884293,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 0.9314,
+      "step": 4
+    },
+    {
+      "epoch": 0.11494252873563218,
+      "grad_norm": 0.09805025905370712,
+      "learning_rate": 5.714285714285714e-05,
+      "loss": 0.921,
+      "step": 5
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 0.09371686726808548,
+      "learning_rate": 7.142857142857143e-05,
+      "loss": 0.9226,
+      "step": 6
+    },
+    {
+      "epoch": 0.16091954022988506,
+      "grad_norm": 0.0807652473449707,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 0.9143,
+      "step": 7
+    },
+    {
+      "epoch": 0.1839080459770115,
+      "grad_norm": 0.07719021290540695,
+      "learning_rate": 0.0001,
+      "loss": 0.9042,
+      "step": 8
+    },
+    {
+      "epoch": 0.20689655172413793,
+      "grad_norm": 0.0751037448644638,
+      "learning_rate": 0.00011428571428571428,
+      "loss": 0.9103,
+      "step": 9
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "grad_norm": 0.07644214481115341,
+      "learning_rate": 0.00012857142857142858,
+      "loss": 0.8865,
+      "step": 10
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "eval_loss": 1.0120309591293335,
+      "eval_runtime": 306.7479,
+      "eval_samples_per_second": 32.268,
+      "eval_steps_per_second": 0.127,
+      "step": 10
+    },
+    {
+      "epoch": 0.25287356321839083,
+      "grad_norm": 0.07934234291315079,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 0.8673,
+      "step": 11
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 0.08267483115196228,
+      "learning_rate": 0.00015714285714285716,
+      "loss": 0.8573,
+      "step": 12
+    },
+    {
+      "epoch": 0.2988505747126437,
+      "grad_norm": 0.08115123957395554,
+      "learning_rate": 0.00017142857142857143,
+      "loss": 0.8505,
+      "step": 13
+    },
+    {
+      "epoch": 0.3218390804597701,
+      "grad_norm": 0.08618608117103577,
+      "learning_rate": 0.00018571428571428572,
+      "loss": 0.8385,
+      "step": 14
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 0.08841115981340408,
+      "learning_rate": 0.0002,
+      "loss": 0.8163,
+      "step": 15
+    },
+    {
+      "epoch": 0.367816091954023,
+      "grad_norm": 0.0757705494761467,
+      "learning_rate": 0.00019996456111234527,
+      "loss": 0.7976,
+      "step": 16
+    },
+    {
+      "epoch": 0.39080459770114945,
+      "grad_norm": 0.07309789210557938,
+      "learning_rate": 0.0001998582695676762,
+      "loss": 0.805,
+      "step": 17
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 0.06578471511602402,
+      "learning_rate": 0.000199681200703075,
+      "loss": 0.7909,
+      "step": 18
+    },
+    {
+      "epoch": 0.4367816091954023,
+      "grad_norm": 0.06465494632720947,
+      "learning_rate": 0.00019943348002101371,
+      "loss": 0.7971,
+      "step": 19
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "grad_norm": 0.0588945597410202,
+      "learning_rate": 0.00019911528310040074,
+      "loss": 0.7698,
+      "step": 20
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "eval_loss": 0.8262545466423035,
+      "eval_runtime": 304.1358,
+      "eval_samples_per_second": 32.545,
+      "eval_steps_per_second": 0.128,
+      "step": 20
+    },
+    {
+      "epoch": 0.4827586206896552,
+      "grad_norm": 0.06138598173856735,
+      "learning_rate": 0.00019872683547213446,
+      "loss": 0.7775,
+      "step": 21
+    },
+    {
+      "epoch": 0.5057471264367817,
+      "grad_norm": 0.06107688695192337,
+      "learning_rate": 0.00019826841245925212,
+      "loss": 0.7671,
+      "step": 22
+    },
+    {
+      "epoch": 0.5287356321839081,
+      "grad_norm": 0.06314990669488907,
+      "learning_rate": 0.00019774033898178667,
+      "loss": 0.7575,
+      "step": 23
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.057741496711969376,
+      "learning_rate": 0.00019714298932647098,
+      "loss": 0.7454,
+      "step": 24
+    },
+    {
+      "epoch": 0.5747126436781609,
+      "grad_norm": 0.054070718586444855,
+      "learning_rate": 0.0001964767868814516,
+      "loss": 0.7456,
+      "step": 25
+    },
+    {
+      "epoch": 0.5977011494252874,
+      "grad_norm": 0.053628239780664444,
+      "learning_rate": 0.00019574220383620055,
+      "loss": 0.7314,
+      "step": 26
+    },
+    {
+      "epoch": 0.6206896551724138,
+      "grad_norm": 0.04411150887608528,
+      "learning_rate": 0.00019493976084683813,
+      "loss": 0.7148,
+      "step": 27
+    },
+    {
+      "epoch": 0.6436781609195402,
+      "grad_norm": 0.045472998172044754,
+      "learning_rate": 0.00019407002666710336,
+      "loss": 0.7409,
+      "step": 28
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.04635506123304367,
+      "learning_rate": 0.00019313361774523385,
+      "loss": 0.7213,
+      "step": 29
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.044493939727544785,
+      "learning_rate": 0.00019213119778704128,
+      "loss": 0.7376,
+      "step": 30
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "eval_loss": 0.732206404209137,
+      "eval_runtime": 303.8356,
+      "eval_samples_per_second": 32.577,
+      "eval_steps_per_second": 0.128,
+      "step": 30
+    },
+    {
+      "epoch": 0.7126436781609196,
+      "grad_norm": 0.036277174949645996,
+      "learning_rate": 0.00019106347728549135,
+      "loss": 0.7336,
+      "step": 31
+    },
+    {
+      "epoch": 0.735632183908046,
+      "grad_norm": 0.03585660830140114,
+      "learning_rate": 0.00018993121301712193,
+      "loss": 0.7253,
+      "step": 32
+    },
+    {
+      "epoch": 0.7586206896551724,
+      "grad_norm": 0.034683484584093094,
+      "learning_rate": 0.00018873520750565718,
+      "loss": 0.7232,
+      "step": 33
+    },
+    {
+      "epoch": 0.7816091954022989,
+      "grad_norm": 0.03263173624873161,
+      "learning_rate": 0.00018747630845319612,
+      "loss": 0.727,
+      "step": 34
+    },
+    {
+      "epoch": 0.8045977011494253,
+      "grad_norm": 0.030511524528265,
+      "learning_rate": 0.0001861554081393806,
+      "loss": 0.7152,
+      "step": 35
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.03229549899697304,
+      "learning_rate": 0.0001847734427889671,
+      "loss": 0.7059,
+      "step": 36
+    },
+    {
+      "epoch": 0.8505747126436781,
+      "grad_norm": 0.029399631544947624,
+      "learning_rate": 0.0001833313919082515,
+      "loss": 0.7202,
+      "step": 37
+    },
+    {
+      "epoch": 0.8735632183908046,
+      "grad_norm": 0.035511165857315063,
+      "learning_rate": 0.0001818302775908169,
+      "loss": 0.7033,
+      "step": 38
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 0.031435854732990265,
+      "learning_rate": 0.00018027116379309638,
+      "loss": 0.7127,
+      "step": 39
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 0.02632274106144905,
+      "learning_rate": 0.00017865515558026428,
+      "loss": 0.7202,
+      "step": 40
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "eval_loss": 0.709326446056366,
+      "eval_runtime": 305.5868,
+      "eval_samples_per_second": 32.39,
+      "eval_steps_per_second": 0.128,
+      "step": 40
+    },
+    {
+      "epoch": 0.9425287356321839,
+      "grad_norm": 0.029349543154239655,
+      "learning_rate": 0.00017698339834299061,
+      "loss": 0.7075,
+      "step": 41
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 0.02238822728395462,
+      "learning_rate": 0.00017525707698561385,
+      "loss": 0.6974,
+      "step": 42
+    },
+    {
+      "epoch": 0.9885057471264368,
+      "grad_norm": 0.02964099310338497,
+      "learning_rate": 0.00017347741508630672,
+      "loss": 0.7148,
+      "step": 43
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.028794899582862854,
+      "learning_rate": 0.00017164567402983152,
+      "loss": 0.716,
+      "step": 44
+    },
+    {
+      "epoch": 1.0229885057471264,
+      "grad_norm": 0.024907108396291733,
+      "learning_rate": 0.0001697631521134985,
+      "loss": 0.696,
+      "step": 45
+    },
+    {
+      "epoch": 1.0459770114942528,
+      "grad_norm": 0.021883342415094376,
+      "learning_rate": 0.00016783118362696163,
+      "loss": 0.6967,
+      "step": 46
+    },
+    {
+      "epoch": 1.0689655172413792,
+      "grad_norm": 0.025625506415963173,
+      "learning_rate": 0.00016585113790650388,
+      "loss": 0.6977,
+      "step": 47
+    },
+    {
+      "epoch": 1.0919540229885056,
+      "grad_norm": 0.021766461431980133,
+      "learning_rate": 0.00016382441836448202,
+      "loss": 0.6856,
+      "step": 48
+    },
+    {
+      "epoch": 1.1149425287356323,
+      "grad_norm": 0.02706512250006199,
+      "learning_rate": 0.0001617524614946192,
+      "loss": 0.6991,
+      "step": 49
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "grad_norm": 0.023426175117492676,
+      "learning_rate": 0.00015963673585385016,
+      "loss": 0.6826,
+      "step": 50
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "eval_loss": 0.6974772214889526,
+      "eval_runtime": 304.7291,
+      "eval_samples_per_second": 32.481,
+      "eval_steps_per_second": 0.128,
+      "step": 50
+    },
+    {
+      "epoch": 1.160919540229885,
+      "grad_norm": 0.02609814889729023,
+      "learning_rate": 0.0001574787410214407,
+      "loss": 0.6958,
+      "step": 51
+    },
+    {
+      "epoch": 1.1839080459770115,
+      "grad_norm": 0.02153083123266697,
+      "learning_rate": 0.00015528000653611935,
+      "loss": 0.6889,
+      "step": 52
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 0.021783925592899323,
+      "learning_rate": 0.00015304209081197425,
+      "loss": 0.6709,
+      "step": 53
+    },
+    {
+      "epoch": 1.2298850574712643,
+      "grad_norm": 0.020721392706036568,
+      "learning_rate": 0.000150766580033884,
+      "loss": 0.6841,
+      "step": 54
+    },
+    {
+      "epoch": 1.2528735632183907,
+      "grad_norm": 0.02474948577582836,
+      "learning_rate": 0.00014845508703326504,
+      "loss": 0.6971,
+      "step": 55
+    },
+    {
+      "epoch": 1.2758620689655173,
+      "grad_norm": 0.021080244332551956,
+      "learning_rate": 0.0001461092501449326,
+      "loss": 0.6815,
+      "step": 56
+    },
+    {
+      "epoch": 1.2988505747126438,
+      "grad_norm": 0.021419625729322433,
+      "learning_rate": 0.00014373073204588556,
+      "loss": 0.6829,
+      "step": 57
+    },
+    {
+      "epoch": 1.3218390804597702,
+      "grad_norm": 0.020894855260849,
+      "learning_rate": 0.00014132121857683783,
+      "loss": 0.6788,
+      "step": 58
+    },
+    {
+      "epoch": 1.3448275862068966,
+      "grad_norm": 0.022799236699938774,
+      "learning_rate": 0.00013888241754733208,
+      "loss": 0.6867,
+      "step": 59
+    },
+    {
+      "epoch": 1.367816091954023,
+      "grad_norm": 0.019518911838531494,
+      "learning_rate": 0.00013641605752528224,
+      "loss": 0.6718,
+      "step": 60
+    },
+    {
+      "epoch": 1.367816091954023,
+      "eval_loss": 0.6893976926803589,
+      "eval_runtime": 305.2208,
+      "eval_samples_per_second": 32.429,
+      "eval_steps_per_second": 0.128,
+      "step": 60
+    },
+    {
+      "epoch": 1.3908045977011494,
+      "grad_norm": 0.02943458780646324,
+      "learning_rate": 0.00013392388661180303,
+      "loss": 0.6663,
+      "step": 61
+    },
+    {
+      "epoch": 1.4137931034482758,
+      "grad_norm": 0.021762903779745102,
+      "learning_rate": 0.0001314076712021949,
+      "loss": 0.6805,
+      "step": 62
+    },
+    {
+      "epoch": 1.4367816091954024,
+      "grad_norm": 0.030327558517456055,
+      "learning_rate": 0.0001288691947339621,
+      "loss": 0.6965,
+      "step": 63
+    },
+    {
+      "epoch": 1.4597701149425286,
+      "grad_norm": 0.02105296589434147,
+      "learning_rate": 0.00012631025642275212,
+      "loss": 0.6665,
+      "step": 64
+    },
+    {
+      "epoch": 1.4827586206896552,
+      "grad_norm": 0.026400938630104065,
+      "learning_rate": 0.0001237326699871115,
+      "loss": 0.6782,
+      "step": 65
+    },
+    {
+      "epoch": 1.5057471264367817,
+      "grad_norm": 0.021603189408779144,
+      "learning_rate": 0.00012113826236296244,
+      "loss": 0.681,
+      "step": 66
+    },
+    {
+      "epoch": 1.528735632183908,
+      "grad_norm": 0.022389894351363182,
+      "learning_rate": 0.00011852887240871145,
+      "loss": 0.6584,
+      "step": 67
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 0.02288314700126648,
+      "learning_rate": 0.00011590634960190721,
+      "loss": 0.6917,
+      "step": 68
+    },
+    {
+      "epoch": 1.5747126436781609,
+      "grad_norm": 0.02010062336921692,
+      "learning_rate": 0.00011327255272837221,
+      "loss": 0.6786,
+      "step": 69
+    },
+    {
+      "epoch": 1.5977011494252875,
+      "grad_norm": 0.023306073620915413,
+      "learning_rate": 0.00011062934856473655,
+      "loss": 0.6726,
+      "step": 70
+    },
+    {
+      "epoch": 1.5977011494252875,
+      "eval_loss": 0.6833033561706543,
+      "eval_runtime": 304.7682,
+      "eval_samples_per_second": 32.477,
+      "eval_steps_per_second": 0.128,
+      "step": 70
+    },
+    {
+      "epoch": 1.6206896551724137,
+      "grad_norm": 0.022723020985722542,
+      "learning_rate": 0.00010797861055530831,
+      "loss": 0.6741,
+      "step": 71
+    },
+    {
+      "epoch": 1.6436781609195403,
+      "grad_norm": 0.021509502083063126,
+      "learning_rate": 0.00010532221748421787,
+      "loss": 0.6622,
+      "step": 72
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.021336719393730164,
+      "learning_rate": 0.00010266205214377748,
+      "loss": 0.6839,
+      "step": 73
+    },
+    {
+      "epoch": 1.6896551724137931,
+      "grad_norm": 0.02103539928793907,
+      "learning_rate": 0.0001,
+      "loss": 0.6843,
+      "step": 74
+    },
+    {
+      "epoch": 1.7126436781609196,
+      "grad_norm": 0.021154023706912994,
+      "learning_rate": 9.733794785622253e-05,
+      "loss": 0.6902,
+      "step": 75
+    },
+    {
+      "epoch": 1.735632183908046,
+      "grad_norm": 0.022072145715355873,
+      "learning_rate": 9.467778251578217e-05,
+      "loss": 0.67,
+      "step": 76
+    },
+    {
+      "epoch": 1.7586206896551724,
+      "grad_norm": 0.02103818580508232,
+      "learning_rate": 9.202138944469168e-05,
+      "loss": 0.6688,
+      "step": 77
+    },
+    {
+      "epoch": 1.7816091954022988,
+      "grad_norm": 0.022151481360197067,
+      "learning_rate": 8.937065143526347e-05,
+      "loss": 0.6744,
+      "step": 78
+    },
+    {
+      "epoch": 1.8045977011494254,
+      "grad_norm": 0.0233754962682724,
+      "learning_rate": 8.672744727162781e-05,
+      "loss": 0.6766,
+      "step": 79
+    },
+    {
+      "epoch": 1.8275862068965516,
+      "grad_norm": 0.021534670144319534,
+      "learning_rate": 8.409365039809281e-05,
+      "loss": 0.6683,
+      "step": 80
+    },
+    {
+      "epoch": 1.8275862068965516,
+      "eval_loss": 0.6785663962364197,
+      "eval_runtime": 304.94,
+      "eval_samples_per_second": 32.459,
+      "eval_steps_per_second": 0.128,
+      "step": 80
+    },
+    {
+      "epoch": 1.8505747126436782,
+      "grad_norm": 0.021793309599161148,
+      "learning_rate": 8.147112759128859e-05,
+      "loss": 0.6665,
+      "step": 81
+    },
+    {
+      "epoch": 1.8735632183908046,
+      "grad_norm": 0.02355259843170643,
+      "learning_rate": 7.886173763703757e-05,
+      "loss": 0.6651,
+      "step": 82
+    },
+    {
+      "epoch": 1.896551724137931,
+      "grad_norm": 0.02172425575554371,
+      "learning_rate": 7.626733001288851e-05,
+      "loss": 0.6578,
+      "step": 83
+    },
+    {
+      "epoch": 1.9195402298850575,
+      "grad_norm": 0.025295689702033997,
+      "learning_rate": 7.368974357724789e-05,
+      "loss": 0.6689,
+      "step": 84
+    },
+    {
+      "epoch": 1.9425287356321839,
+      "grad_norm": 0.0222152229398489,
+      "learning_rate": 7.113080526603792e-05,
+      "loss": 0.676,
+      "step": 85
+    },
+    {
+      "epoch": 1.9655172413793105,
+      "grad_norm": 0.02181256376206875,
+      "learning_rate": 6.859232879780515e-05,
+      "loss": 0.6514,
+      "step": 86
+    },
+    {
+      "epoch": 1.9885057471264367,
+      "grad_norm": 0.02323107421398163,
+      "learning_rate": 6.607611338819697e-05,
+      "loss": 0.6728,
+      "step": 87
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.031201783567667007,
+      "learning_rate": 6.358394247471778e-05,
+      "loss": 0.677,
+      "step": 88
+    },
+    {
+      "epoch": 2.0229885057471266,
+      "grad_norm": 0.025246866047382355,
+      "learning_rate": 6.111758245266794e-05,
+      "loss": 0.6688,
+      "step": 89
+    },
+    {
+      "epoch": 2.045977011494253,
+      "grad_norm": 0.02423354797065258,
+      "learning_rate": 5.867878142316221e-05,
+      "loss": 0.6532,
+      "step": 90
+    },
+    {
+      "epoch": 2.045977011494253,
+      "eval_loss": 0.6744519472122192,
+      "eval_runtime": 304.2833,
+      "eval_samples_per_second": 32.529,
+      "eval_steps_per_second": 0.128,
+      "step": 90
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 0.024736715480685234,
+      "learning_rate": 5.626926795411447e-05,
+      "loss": 0.6624,
+      "step": 91
+    },
+    {
+      "epoch": 2.0919540229885056,
+      "grad_norm": 0.023653104901313782,
+      "learning_rate": 5.38907498550674e-05,
+      "loss": 0.6688,
+      "step": 92
+    },
+    {
+      "epoch": 2.1149425287356323,
+      "grad_norm": 0.023142701014876366,
+      "learning_rate": 5.1544912966734994e-05,
+      "loss": 0.6733,
+      "step": 93
+    },
+    {
+      "epoch": 2.1379310344827585,
+      "grad_norm": 0.023723168298602104,
+      "learning_rate": 4.9233419966116036e-05,
+      "loss": 0.6558,
+      "step": 94
+    },
+    {
+      "epoch": 2.160919540229885,
+      "grad_norm": 0.023075120523571968,
+      "learning_rate": 4.695790918802576e-05,
+      "loss": 0.6491,
+      "step": 95
+    },
+    {
+      "epoch": 2.1839080459770113,
+      "grad_norm": 0.022818081080913544,
+      "learning_rate": 4.47199934638807e-05,
+      "loss": 0.6781,
+      "step": 96
+    },
+    {
+      "epoch": 2.206896551724138,
+      "grad_norm": 0.0267396979033947,
+      "learning_rate": 4.252125897855932e-05,
+      "loss": 0.6603,
+      "step": 97
+    },
+    {
+      "epoch": 2.2298850574712645,
+      "grad_norm": 0.025006582960486412,
+      "learning_rate": 4.036326414614985e-05,
+      "loss": 0.6511,
+      "step": 98
+    },
+    {
+      "epoch": 2.2528735632183907,
+      "grad_norm": 0.024816425517201424,
+      "learning_rate": 3.824753850538082e-05,
+      "loss": 0.6646,
+      "step": 99
+    },
+    {
+      "epoch": 2.2758620689655173,
+      "grad_norm": 0.02459343522787094,
+      "learning_rate": 3.617558163551802e-05,
+      "loss": 0.6622,
+      "step": 100
+    },
+    {
+      "epoch": 2.2758620689655173,
+      "eval_loss": 0.6719217300415039,
+      "eval_runtime": 306.2949,
+      "eval_samples_per_second": 32.315,
+      "eval_steps_per_second": 0.127,
+      "step": 100
+    },
+    {
+      "epoch": 2.2988505747126435,
+      "grad_norm": 0.024219118058681488,
+      "learning_rate": 3.414886209349615e-05,
+      "loss": 0.6514,
+      "step": 101
+    },
+    {
+      "epoch": 2.32183908045977,
+      "grad_norm": 0.022682521492242813,
+      "learning_rate": 3.216881637303839e-05,
+      "loss": 0.6555,
+      "step": 102
+    },
+    {
+      "epoch": 2.344827586206897,
+      "grad_norm": 0.02407901920378208,
+      "learning_rate": 3.0236847886501542e-05,
+      "loss": 0.6613,
+      "step": 103
+    },
+    {
+      "epoch": 2.367816091954023,
+      "grad_norm": 0.0255474504083395,
+      "learning_rate": 2.8354325970168484e-05,
+      "loss": 0.6471,
+      "step": 104
+    },
+    {
+      "epoch": 2.3908045977011496,
+      "grad_norm": 0.02526705525815487,
+      "learning_rate": 2.6522584913693294e-05,
+      "loss": 0.646,
+      "step": 105
+    },
+    {
+      "epoch": 2.413793103448276,
+      "grad_norm": 0.024295799434185028,
+      "learning_rate": 2.4742923014386156e-05,
+      "loss": 0.6546,
+      "step": 106
+    },
+    {
+      "epoch": 2.4367816091954024,
+      "grad_norm": 0.022690266370773315,
+      "learning_rate": 2.301660165700936e-05,
+      "loss": 0.6588,
+      "step": 107
+    },
+    {
+      "epoch": 2.4597701149425286,
+      "grad_norm": 0.02374277077615261,
+      "learning_rate": 2.1344844419735755e-05,
+      "loss": 0.6473,
+      "step": 108
+    },
+    {
+      "epoch": 2.4827586206896552,
+      "grad_norm": 0.02360009402036667,
+      "learning_rate": 1.9728836206903656e-05,
+      "loss": 0.6528,
+      "step": 109
+    },
+    {
+      "epoch": 2.5057471264367814,
+      "grad_norm": 0.022511010989546776,
+      "learning_rate": 1.8169722409183097e-05,
+      "loss": 0.6476,
+      "step": 110
+    },
+    {
+      "epoch": 2.5057471264367814,
+      "eval_loss": 0.6705266237258911,
+      "eval_runtime": 305.2556,
+      "eval_samples_per_second": 32.425,
+      "eval_steps_per_second": 0.128,
+      "step": 110
+    },
+    {
+      "epoch": 2.528735632183908,
+      "grad_norm": 0.03566652163863182,
+      "learning_rate": 1.6668608091748495e-05,
+      "loss": 0.6563,
+      "step": 111
+    },
+    {
+      "epoch": 2.5517241379310347,
+      "grad_norm": 0.04124740883708,
+      "learning_rate": 1.522655721103291e-05,
+      "loss": 0.6458,
+      "step": 112
+    },
+    {
+      "epoch": 2.574712643678161,
+      "grad_norm": 0.022443674504756927,
+      "learning_rate": 1.3844591860619383e-05,
+      "loss": 0.6541,
+      "step": 113
+    },
+    {
+      "epoch": 2.5977011494252875,
+      "grad_norm": 0.02348385937511921,
+      "learning_rate": 1.2523691546803873e-05,
+      "loss": 0.6475,
+      "step": 114
+    },
+    {
+      "epoch": 2.6206896551724137,
+      "grad_norm": 0.022854959592223167,
+      "learning_rate": 1.1264792494342857e-05,
+      "loss": 0.6705,
+      "step": 115
+    },
+    {
+      "epoch": 2.6436781609195403,
+      "grad_norm": 0.021535657346248627,
+      "learning_rate": 1.0068786982878087e-05,
+      "loss": 0.6422,
+      "step": 116
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.022477196529507637,
+      "learning_rate": 8.936522714508678e-06,
+      "loss": 0.6622,
+      "step": 117
+    },
+    {
+      "epoch": 2.689655172413793,
+      "grad_norm": 0.02256396785378456,
+      "learning_rate": 7.868802212958703e-06,
+      "loss": 0.6529,
+      "step": 118
+    },
+    {
+      "epoch": 2.7126436781609193,
+      "grad_norm": 0.022825201973319054,
+      "learning_rate": 6.866382254766157e-06,
+      "loss": 0.6558,
+      "step": 119
+    },
+    {
+      "epoch": 2.735632183908046,
+      "grad_norm": 0.021880483254790306,
+      "learning_rate": 5.929973332896677e-06,
+      "loss": 0.6399,
+      "step": 120
+    },
+    {
+      "epoch": 2.735632183908046,
+      "eval_loss": 0.6699749231338501,
+      "eval_runtime": 302.9573,
+      "eval_samples_per_second": 32.671,
+      "eval_steps_per_second": 0.129,
+      "step": 120
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "grad_norm": 0.02154582180082798,
+      "learning_rate": 5.060239153161872e-06,
+      "loss": 0.6566,
+      "step": 121
+    },
+    {
+      "epoch": 2.781609195402299,
+      "grad_norm": 0.02197122573852539,
+      "learning_rate": 4.257796163799455e-06,
+      "loss": 0.6564,
+      "step": 122
+    },
+    {
+      "epoch": 2.8045977011494254,
+      "grad_norm": 0.02272190898656845,
+      "learning_rate": 3.5232131185484076e-06,
+      "loss": 0.6487,
+      "step": 123
+    },
+    {
+      "epoch": 2.8275862068965516,
+      "grad_norm": 0.022705314680933952,
+      "learning_rate": 2.857010673529015e-06,
+      "loss": 0.6394,
+      "step": 124
+    },
+    {
+      "epoch": 2.8505747126436782,
+      "grad_norm": 0.022633053362369537,
+      "learning_rate": 2.259661018213333e-06,
+      "loss": 0.6562,
+      "step": 125
+    },
+    {
+      "epoch": 2.873563218390805,
+      "grad_norm": 0.023264018818736076,
+      "learning_rate": 1.7315875407479032e-06,
+      "loss": 0.6446,
+      "step": 126
+    },
+    {
+      "epoch": 2.896551724137931,
+      "grad_norm": 0.023026825860142708,
+      "learning_rate": 1.2731645278655445e-06,
+      "loss": 0.6519,
+      "step": 127
+    },
+    {
+      "epoch": 2.9195402298850572,
+      "grad_norm": 0.022009894251823425,
+      "learning_rate": 8.847168995992916e-07,
+      "loss": 0.652,
+      "step": 128
+    },
+    {
+      "epoch": 2.942528735632184,
+      "grad_norm": 0.021784234791994095,
+      "learning_rate": 5.665199789862907e-07,
+      "loss": 0.647,
+      "step": 129
+    },
+    {
+      "epoch": 2.9655172413793105,
+      "grad_norm": 0.02262978069484234,
+      "learning_rate": 3.1879929692498757e-07,
+      "loss": 0.643,
+      "step": 130
+    },
+    {
+      "epoch": 2.9655172413793105,
+      "eval_loss": 0.6699010729789734,
+      "eval_runtime": 300.8193,
+      "eval_samples_per_second": 32.903,
+      "eval_steps_per_second": 0.13,
+      "step": 130
+    },
+    {
+      "epoch": 2.9885057471264367,
+      "grad_norm": 0.02275514416396618,
+      "learning_rate": 1.4173043232380557e-07,
+      "loss": 0.6597,
+      "step": 131
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.03187975659966469,
+      "learning_rate": 3.5438887654737355e-08,
+      "loss": 0.6579,
+      "step": 132
+    },
+    {
+      "epoch": 3.0,
+      "step": 132,
+      "total_flos": 4.884710196870591e+19,
+      "train_loss": 0.7087282439072927,
+      "train_runtime": 30755.2831,
+      "train_samples_per_second": 8.689,
+      "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": 4.884710196870591e+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 sha256:4891f70a51cef3854b3b48396ea78ba981638ad68593d5a177a49fdeed9a11ad
+size 6161