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-261/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 +1,92 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen3-30B-A3B
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: Qwen3-30B-A3B-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-alpaca-th-52k-dolly-th-15k-wangchan-instruct
+
+This model is a fine-tuned version of [Qwen/Qwen3-30B-A3B](https://huggingface.co/Qwen/Qwen3-30B-A3B) on the alpaca-th-52k, the dolly-th-15k and the wangchan-instruct datasets.
+It achieves the following results on the evaluation set:
+- Loss: 0.6631
+
+## 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: 64
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 1024
+- total_eval_batch_size: 128
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9351        | 0.1149 | 10   | 0.9997          |
+| 0.8087        | 0.2299 | 20   | 0.8204          |
+| 0.7724        | 0.3448 | 30   | 0.7787          |
+| 0.7386        | 0.4598 | 40   | 0.7544          |
+| 0.7351        | 0.5747 | 50   | 0.7382          |
+| 0.7431        | 0.6897 | 60   | 0.7254          |
+| 0.7183        | 0.8046 | 70   | 0.7151          |
+| 0.711         | 0.9195 | 80   | 0.7065          |
+| 0.6909        | 1.0345 | 90   | 0.6995          |
+| 0.6893        | 1.1494 | 100  | 0.6939          |
+| 0.6796        | 1.2644 | 110  | 0.6874          |
+| 0.65          | 1.3793 | 120  | 0.6812          |
+| 0.6615        | 1.4943 | 130  | 0.6775          |
+| 0.6555        | 1.6092 | 140  | 0.6739          |
+| 0.6522        | 1.7241 | 150  | 0.6713          |
+| 0.6545        | 1.8391 | 160  | 0.6687          |
+| 0.648         | 1.9540 | 170  | 0.6668          |
+| 0.6285        | 2.0690 | 180  | 0.6663          |
+| 0.6652        | 2.1839 | 190  | 0.6655          |
+| 0.6307        | 2.2989 | 200  | 0.6647          |
+| 0.6383        | 2.4138 | 210  | 0.6641          |
+| 0.6394        | 2.5287 | 220  | 0.6636          |
+| 0.632         | 2.6437 | 230  | 0.6632          |
+| 0.6416        | 2.7586 | 240  | 0.6631          |
+| 0.6228        | 2.8736 | 250  | 0.6631          |
+| 0.6316        | 2.9885 | 260  | 0.6630          |
+
+
+### 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",
+  "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",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "gate",
+    "k_proj",
+    "gate_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 sha256:557c44184dc5b0d37db7a76834f8ac7879da89df125a9387f7e8148c96aa6b3f
+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": 0.6630785465240479,
+    "eval_runtime": 567.372,
+    "eval_samples_per_second": 17.445,
+    "eval_steps_per_second": 0.137,
+    "total_flos": 4.884710203742539e+19,
+    "train_loss": 0.696434152765749,
+    "train_runtime": 65574.4997,
+    "train_samples_per_second": 4.075,
+    "train_steps_per_second": 0.004
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- 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 message.content is string 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.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.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' }}
+        {{- 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-261/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /project/lt200252-wcbart/pumet/models/Qwen3-30B-A3B
+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-261/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",
+  "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",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "gate",
+    "k_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-261/rng_state_13.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b0a908b14ea4ab40cc30339703d21b00519d6d6ad485b7e984e0ab26a28a938
+size 15440

checkpoint-261/rng_state_14.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34d1299ae68004414bbeba5890c1f06fd4e885705bc4e5707f095d913fad7d97
+size 15440

checkpoint-261/rng_state_16.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2c98c448d2493d7195e6c1f17089f80407dd7599a7be421b6f968381df871ab
+size 15440

checkpoint-261/rng_state_31.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c3e49db0f0e559a7a97dcd6718b503cd45d4597829052886fde182f229100c
+size 15440

checkpoint-261/rng_state_32.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae5e28f156630c07f8c3cec0a207441e637bbb6021bc4e163165ae7cf23a155c
+size 15440

checkpoint-261/rng_state_47.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:113e2cfe43ef2c77be3860147f7be537a9656a471e4d29046efc486e16c8727d
+size 15440

checkpoint-261/rng_state_50.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd8afe94c42adcf2f04a66d88affff7c33a534484eb454bc13183b4b11419f70
+size 15440

checkpoint-261/rng_state_53.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f78da7ceb9f5ebb670539e9c60647a8541be6d8590cf7834a52ed80c274dfc32
+size 15440

checkpoint-261/rng_state_54.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d267edd368688f20d9f95c5d8e4396ef02488ea4c1bb4a1d4619be8960cf9d3
+size 15440

checkpoint-261/rng_state_62.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f7d81b322c4ee34a6b82cd930489c1107ff0c2fd6063b1af634fca075192eeb
+size 15440

checkpoint-261/rng_state_63.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2112b369755ac5eb78c97bb6211f816aeeb62f0ca2f1396b826305344b0ed77f
+size 15440

checkpoint-261/tokenizer.json

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

checkpoint-261/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b28f91da791e94275867130f8301f2ae41dec5d982adbc133227ebf7b6d00ce9
+size 6161

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": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 40960,
+  "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": 0.6630785465240479,
+    "eval_runtime": 567.372,
+    "eval_samples_per_second": 17.445,
+    "eval_steps_per_second": 0.137
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.52.3"
+}

model-00002-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5fae6a4255be2411192cdd9062a338391acca932de06d6ee595e172bf5fbf95
+size 4997644048

model-00004-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f689b6f519bd9ee1565f78ab60a8c8bde8dd3f49f2a37e28b55d5294230b834f
+size 4997644048

model-00005-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52788cdfeb317f8db876a579e0378125d7dbec856005cf9351566107fc10cadb
+size 4997644048

model-00006-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16fa109727c78f6afb882b191ed47bef66ee6471a5c4ef45e654a7d1f6848b3f
+size 4997644648

model-00007-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c4fe806db211365c4aaa29a0ecc6c6dd142794ca6692b142e5852cc25f1d6a6
+size 4997644832

model-00009-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5da0226632627eb7469a838f9780b20e544355b323a9361a6f41b49f3821ab34
+size 4997644832

model-00011-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:092e8b809ecad8ed9a9652ba6b592877680beb4d7bf06d4d3fc1d0cc6c1fcdf3
+size 4997644840

model-00012-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41e4c7ab7fb038dd97ed396150ff371dc426195f8a8fdbda1057d993d5987304
+size 4997644832

model-00013-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed598bfd2ccc3963e737ee98c05fc3cd369abd8ae574edf8a98051d9f0d23f14
+size 4997644832

model-00016-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:004c604466c3fe3f9b723e7630aed28ac3061ee8b285d70d1fc88cb3b292ef2e
+size 4997644832

model-00022-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0ef849d9c5739bcbbe082f11d5636d685cd69ed470d693a5888d4fa63d3d716
+size 4997644832

model-00024-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adb093fd84bfe60a9c6f1981ee78896fa11e63124fc08c7f4fb6a471d75ff6fb
+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": 4.884710203742539e+19,
+    "train_loss": 0.696434152765749,
+    "train_runtime": 65574.4997,
+    "train_samples_per_second": 4.075,
+    "train_steps_per_second": 0.004
+}

trainer_log.jsonl

@@ -0,0 +1,288 @@
+{"current_steps": 1, "total_steps": 261, "loss": 1.0671, "lr": 0.0, "epoch": 0.011494252873563218, "percentage": 0.38, "elapsed_time": "0:03:19", "remaining_time": "14:25:14"}
+{"current_steps": 2, "total_steps": 261, "loss": 1.0786, "lr": 7.4074074074074075e-06, "epoch": 0.022988505747126436, "percentage": 0.77, "elapsed_time": "0:06:36", "remaining_time": "14:16:07"}
+{"current_steps": 3, "total_steps": 261, "loss": 1.074, "lr": 1.4814814814814815e-05, "epoch": 0.034482758620689655, "percentage": 1.15, "elapsed_time": "0:09:52", "remaining_time": "14:09:45"}
+{"current_steps": 4, "total_steps": 261, "loss": 1.0617, "lr": 2.2222222222222223e-05, "epoch": 0.04597701149425287, "percentage": 1.53, "elapsed_time": "0:13:06", "remaining_time": "14:01:48"}
+{"current_steps": 5, "total_steps": 261, "loss": 1.0856, "lr": 2.962962962962963e-05, "epoch": 0.05747126436781609, "percentage": 1.92, "elapsed_time": "0:16:18", "remaining_time": "13:55:13"}
+{"current_steps": 6, "total_steps": 261, "loss": 1.0464, "lr": 3.7037037037037037e-05, "epoch": 0.06896551724137931, "percentage": 2.3, "elapsed_time": "0:19:33", "remaining_time": "13:50:54"}
+{"current_steps": 7, "total_steps": 261, "loss": 1.0201, "lr": 4.4444444444444447e-05, "epoch": 0.08045977011494253, "percentage": 2.68, "elapsed_time": "0:22:48", "remaining_time": "13:47:35"}
+{"current_steps": 8, "total_steps": 261, "loss": 0.983, "lr": 5.185185185185185e-05, "epoch": 0.09195402298850575, "percentage": 3.07, "elapsed_time": "0:26:02", "remaining_time": "13:43:46"}
+{"current_steps": 9, "total_steps": 261, "loss": 0.9627, "lr": 5.925925925925926e-05, "epoch": 0.10344827586206896, "percentage": 3.45, "elapsed_time": "0:29:16", "remaining_time": "13:39:43"}
+{"current_steps": 10, "total_steps": 261, "loss": 0.9351, "lr": 6.666666666666667e-05, "epoch": 0.11494252873563218, "percentage": 3.83, "elapsed_time": "0:32:35", "remaining_time": "13:37:53"}
+{"current_steps": 10, "total_steps": 261, "eval_loss": 0.9996559023857117, "epoch": 0.11494252873563218, "percentage": 3.83, "elapsed_time": "0:42:12", "remaining_time": "17:39:26"}
+{"current_steps": 11, "total_steps": 261, "loss": 0.9269, "lr": 7.407407407407407e-05, "epoch": 0.12643678160919541, "percentage": 4.21, "elapsed_time": "0:45:29", "remaining_time": "17:13:46"}
+{"current_steps": 12, "total_steps": 261, "loss": 0.8617, "lr": 8.148148148148148e-05, "epoch": 0.13793103448275862, "percentage": 4.6, "elapsed_time": "0:48:42", "remaining_time": "16:50:36"}
+{"current_steps": 13, "total_steps": 261, "loss": 0.8568, "lr": 8.888888888888889e-05, "epoch": 0.14942528735632185, "percentage": 4.98, "elapsed_time": "0:51:54", "remaining_time": "16:30:19"}
+{"current_steps": 14, "total_steps": 261, "loss": 0.8651, "lr": 9.62962962962963e-05, "epoch": 0.16091954022988506, "percentage": 5.36, "elapsed_time": "0:55:14", "remaining_time": "16:14:34"}
+{"current_steps": 15, "total_steps": 261, "loss": 0.8281, "lr": 0.0001037037037037037, "epoch": 0.1724137931034483, "percentage": 5.75, "elapsed_time": "0:58:30", "remaining_time": "15:59:29"}
+{"current_steps": 16, "total_steps": 261, "loss": 0.8296, "lr": 0.00011111111111111112, "epoch": 0.1839080459770115, "percentage": 6.13, "elapsed_time": "1:01:43", "remaining_time": "15:45:12"}
+{"current_steps": 17, "total_steps": 261, "loss": 0.8494, "lr": 0.00011851851851851852, "epoch": 0.19540229885057472, "percentage": 6.51, "elapsed_time": "1:04:55", "remaining_time": "15:31:58"}
+{"current_steps": 18, "total_steps": 261, "loss": 0.8236, "lr": 0.00012592592592592592, "epoch": 0.20689655172413793, "percentage": 6.9, "elapsed_time": "1:08:12", "remaining_time": "15:20:48"}
+{"current_steps": 19, "total_steps": 261, "loss": 0.821, "lr": 0.00013333333333333334, "epoch": 0.21839080459770116, "percentage": 7.28, "elapsed_time": "1:11:27", "remaining_time": "15:10:12"}
+{"current_steps": 20, "total_steps": 261, "loss": 0.8087, "lr": 0.00014074074074074076, "epoch": 0.22988505747126436, "percentage": 7.66, "elapsed_time": "1:14:43", "remaining_time": "15:00:21"}
+{"current_steps": 20, "total_steps": 261, "eval_loss": 0.8203959465026855, "epoch": 0.22988505747126436, "percentage": 7.66, "elapsed_time": "1:24:16", "remaining_time": "16:55:28"}
+{"current_steps": 21, "total_steps": 261, "loss": 0.8005, "lr": 0.00014814814814814815, "epoch": 0.2413793103448276, "percentage": 8.05, "elapsed_time": "1:27:31", "remaining_time": "16:40:17"}
+{"current_steps": 22, "total_steps": 261, "loss": 0.8099, "lr": 0.00015555555555555556, "epoch": 0.25287356321839083, "percentage": 8.43, "elapsed_time": "1:30:47", "remaining_time": "16:26:18"}
+{"current_steps": 23, "total_steps": 261, "loss": 0.8084, "lr": 0.00016296296296296295, "epoch": 0.26436781609195403, "percentage": 8.81, "elapsed_time": "1:34:00", "remaining_time": "16:12:48"}
+{"current_steps": 24, "total_steps": 261, "loss": 0.7786, "lr": 0.00017037037037037037, "epoch": 0.27586206896551724, "percentage": 9.2, "elapsed_time": "1:37:14", "remaining_time": "16:00:14"}
+{"current_steps": 25, "total_steps": 261, "loss": 0.794, "lr": 0.00017777777777777779, "epoch": 0.28735632183908044, "percentage": 9.58, "elapsed_time": "1:40:28", "remaining_time": "15:48:29"}
+{"current_steps": 26, "total_steps": 261, "loss": 0.7793, "lr": 0.0001851851851851852, "epoch": 0.2988505747126437, "percentage": 9.96, "elapsed_time": "1:43:43", "remaining_time": "15:37:27"}
+{"current_steps": 27, "total_steps": 261, "loss": 0.7779, "lr": 0.0001925925925925926, "epoch": 0.3103448275862069, "percentage": 10.34, "elapsed_time": "1:46:55", "remaining_time": "15:26:39"}
+{"current_steps": 28, "total_steps": 261, "loss": 0.7871, "lr": 0.0002, "epoch": 0.3218390804597701, "percentage": 10.73, "elapsed_time": "1:50:08", "remaining_time": "15:16:32"}
+{"current_steps": 29, "total_steps": 261, "loss": 0.7645, "lr": 0.00019999098778567212, "epoch": 0.3333333333333333, "percentage": 11.11, "elapsed_time": "1:53:21", "remaining_time": "15:06:49"}
+{"current_steps": 30, "total_steps": 261, "loss": 0.7724, "lr": 0.00019996395276708856, "epoch": 0.3448275862068966, "percentage": 11.49, "elapsed_time": "1:56:34", "remaining_time": "14:57:38"}
+{"current_steps": 30, "total_steps": 261, "eval_loss": 0.7786664366722107, "epoch": 0.3448275862068966, "percentage": 11.49, "elapsed_time": "2:06:14", "remaining_time": "16:12:02"}
+{"current_steps": 31, "total_steps": 261, "loss": 0.7634, "lr": 0.00019991889981715698, "epoch": 0.3563218390804598, "percentage": 11.88, "elapsed_time": "2:09:29", "remaining_time": "16:00:45"}
+{"current_steps": 32, "total_steps": 261, "loss": 0.7539, "lr": 0.00019985583705641418, "epoch": 0.367816091954023, "percentage": 12.26, "elapsed_time": "2:12:43", "remaining_time": "15:49:49"}
+{"current_steps": 33, "total_steps": 261, "loss": 0.7649, "lr": 0.00019977477585156252, "epoch": 0.3793103448275862, "percentage": 12.64, "elapsed_time": "2:15:56", "remaining_time": "15:39:12"}
+{"current_steps": 34, "total_steps": 261, "loss": 0.7698, "lr": 0.00019967573081342103, "epoch": 0.39080459770114945, "percentage": 13.03, "elapsed_time": "2:19:10", "remaining_time": "15:29:11"}
+{"current_steps": 35, "total_steps": 261, "loss": 0.7316, "lr": 0.0001995587197942919, "epoch": 0.40229885057471265, "percentage": 13.41, "elapsed_time": "2:22:24", "remaining_time": "15:19:35"}
+{"current_steps": 36, "total_steps": 261, "loss": 0.7694, "lr": 0.0001994237638847428, "epoch": 0.41379310344827586, "percentage": 13.79, "elapsed_time": "2:25:37", "remaining_time": "15:10:08"}
+{"current_steps": 37, "total_steps": 261, "loss": 0.7664, "lr": 0.0001992708874098054, "epoch": 0.42528735632183906, "percentage": 14.18, "elapsed_time": "2:28:53", "remaining_time": "15:01:25"}
+{"current_steps": 38, "total_steps": 261, "loss": 0.7676, "lr": 0.00019910011792459087, "epoch": 0.4367816091954023, "percentage": 14.56, "elapsed_time": "2:32:09", "remaining_time": "14:52:53"}
+{"current_steps": 39, "total_steps": 261, "loss": 0.7492, "lr": 0.00019891148620932318, "epoch": 0.4482758620689655, "percentage": 14.94, "elapsed_time": "2:35:21", "remaining_time": "14:44:23"}
+{"current_steps": 40, "total_steps": 261, "loss": 0.7386, "lr": 0.00019870502626379127, "epoch": 0.45977011494252873, "percentage": 15.33, "elapsed_time": "2:38:38", "remaining_time": "14:36:28"}
+{"current_steps": 40, "total_steps": 261, "eval_loss": 0.7544006705284119, "epoch": 0.45977011494252873, "percentage": 15.33, "elapsed_time": "2:48:12", "remaining_time": "15:29:18"}
+{"current_steps": 41, "total_steps": 261, "loss": 0.7328, "lr": 0.00019848077530122083, "epoch": 0.47126436781609193, "percentage": 15.71, "elapsed_time": "2:51:28", "remaining_time": "15:20:05"}
+{"current_steps": 42, "total_steps": 261, "loss": 0.7705, "lr": 0.00019823877374156647, "epoch": 0.4827586206896552, "percentage": 16.09, "elapsed_time": "2:54:41", "remaining_time": "15:10:56"}
+{"current_steps": 43, "total_steps": 261, "loss": 0.7501, "lr": 0.00019797906520422677, "epoch": 0.4942528735632184, "percentage": 16.48, "elapsed_time": "2:57:54", "remaining_time": "15:01:56"}
+{"current_steps": 44, "total_steps": 261, "loss": 0.7401, "lr": 0.00019770169650018172, "epoch": 0.5057471264367817, "percentage": 16.86, "elapsed_time": "3:01:07", "remaining_time": "14:53:18"}
+{"current_steps": 45, "total_steps": 261, "loss": 0.7582, "lr": 0.00019740671762355548, "epoch": 0.5172413793103449, "percentage": 17.24, "elapsed_time": "3:04:21", "remaining_time": "14:44:55"}
+{"current_steps": 46, "total_steps": 261, "loss": 0.7223, "lr": 0.0001970941817426052, "epoch": 0.5287356321839081, "percentage": 17.62, "elapsed_time": "3:07:35", "remaining_time": "14:36:48"}
+{"current_steps": 47, "total_steps": 261, "loss": 0.7318, "lr": 0.00019676414519013781, "epoch": 0.5402298850574713, "percentage": 18.01, "elapsed_time": "3:10:49", "remaining_time": "14:28:53"}
+{"current_steps": 48, "total_steps": 261, "loss": 0.7317, "lr": 0.00019641666745335624, "epoch": 0.5517241379310345, "percentage": 18.39, "elapsed_time": "3:14:03", "remaining_time": "14:21:07"}
+{"current_steps": 49, "total_steps": 261, "loss": 0.746, "lr": 0.00019605181116313724, "epoch": 0.5632183908045977, "percentage": 18.77, "elapsed_time": "3:17:21", "remaining_time": "14:13:51"}
+{"current_steps": 50, "total_steps": 261, "loss": 0.7351, "lr": 0.00019566964208274254, "epoch": 0.5747126436781609, "percentage": 19.16, "elapsed_time": "3:20:38", "remaining_time": "14:06:41"}
+{"current_steps": 50, "total_steps": 261, "eval_loss": 0.7382059097290039, "epoch": 0.5747126436781609, "percentage": 19.16, "elapsed_time": "3:30:15", "remaining_time": "14:47:18"}
+{"current_steps": 51, "total_steps": 261, "loss": 0.7231, "lr": 0.00019527022909596536, "epoch": 0.5862068965517241, "percentage": 19.54, "elapsed_time": "3:33:53", "remaining_time": "14:40:44"}
+{"current_steps": 52, "total_steps": 261, "loss": 0.734, "lr": 0.00019485364419471454, "epoch": 0.5977011494252874, "percentage": 19.92, "elapsed_time": "3:37:09", "remaining_time": "14:32:47"}
+{"current_steps": 53, "total_steps": 261, "loss": 0.7154, "lr": 0.00019441996246603846, "epoch": 0.6091954022988506, "percentage": 20.31, "elapsed_time": "3:40:23", "remaining_time": "14:24:57"}
+{"current_steps": 54, "total_steps": 261, "loss": 0.7042, "lr": 0.00019396926207859084, "epoch": 0.6206896551724138, "percentage": 20.69, "elapsed_time": "3:43:38", "remaining_time": "14:17:18"}
+{"current_steps": 55, "total_steps": 261, "loss": 0.7405, "lr": 0.0001935016242685415, "epoch": 0.632183908045977, "percentage": 21.07, "elapsed_time": "3:46:52", "remaining_time": "14:09:43"}
+{"current_steps": 56, "total_steps": 261, "loss": 0.7413, "lr": 0.00019301713332493386, "epoch": 0.6436781609195402, "percentage": 21.46, "elapsed_time": "3:50:08", "remaining_time": "14:02:30"}
+{"current_steps": 57, "total_steps": 261, "loss": 0.7237, "lr": 0.00019251587657449236, "epoch": 0.6551724137931034, "percentage": 21.84, "elapsed_time": "3:53:22", "remaining_time": "13:55:14"}
+{"current_steps": 58, "total_steps": 261, "loss": 0.7189, "lr": 0.00019199794436588243, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "3:56:38", "remaining_time": "13:48:13"}
+{"current_steps": 59, "total_steps": 261, "loss": 0.7346, "lr": 0.00019146343005342547, "epoch": 0.6781609195402298, "percentage": 22.61, "elapsed_time": "3:59:51", "remaining_time": "13:41:11"}
+{"current_steps": 60, "total_steps": 261, "loss": 0.7431, "lr": 0.0001909124299802724, "epoch": 0.6896551724137931, "percentage": 22.99, "elapsed_time": "4:03:06", "remaining_time": "13:34:23"}
+{"current_steps": 60, "total_steps": 261, "eval_loss": 0.7254042029380798, "epoch": 0.6896551724137931, "percentage": 22.99, "elapsed_time": "4:12:45", "remaining_time": "14:06:43"}
+{"current_steps": 61, "total_steps": 261, "loss": 0.7269, "lr": 0.00019034504346103823, "epoch": 0.7011494252873564, "percentage": 23.37, "elapsed_time": "4:16:00", "remaining_time": "13:59:22"}
+{"current_steps": 62, "total_steps": 261, "loss": 0.7408, "lr": 0.0001897613727639014, "epoch": 0.7126436781609196, "percentage": 23.75, "elapsed_time": "4:19:13", "remaining_time": "13:52:01"}
+{"current_steps": 63, "total_steps": 261, "loss": 0.7216, "lr": 0.0001891615230921703, "epoch": 0.7241379310344828, "percentage": 24.14, "elapsed_time": "4:22:29", "remaining_time": "13:44:58"}
+{"current_steps": 64, "total_steps": 261, "loss": 0.7356, "lr": 0.000188545602565321, "epoch": 0.735632183908046, "percentage": 24.52, "elapsed_time": "4:25:45", "remaining_time": "13:38:01"}
+{"current_steps": 65, "total_steps": 261, "loss": 0.7292, "lr": 0.00018791372219950948, "epoch": 0.7471264367816092, "percentage": 24.9, "elapsed_time": "4:29:00", "remaining_time": "13:31:08"}
+{"current_steps": 66, "total_steps": 261, "loss": 0.7161, "lr": 0.00018726599588756145, "epoch": 0.7586206896551724, "percentage": 25.29, "elapsed_time": "4:32:14", "remaining_time": "13:24:20"}
+{"current_steps": 67, "total_steps": 261, "loss": 0.7261, "lr": 0.00018660254037844388, "epoch": 0.7701149425287356, "percentage": 25.67, "elapsed_time": "4:35:33", "remaining_time": "13:17:52"}
+{"current_steps": 68, "total_steps": 261, "loss": 0.7267, "lr": 0.0001859234752562217, "epoch": 0.7816091954022989, "percentage": 26.05, "elapsed_time": "4:38:49", "remaining_time": "13:11:21"}
+{"current_steps": 69, "total_steps": 261, "loss": 0.7193, "lr": 0.00018522892291850335, "epoch": 0.7931034482758621, "percentage": 26.44, "elapsed_time": "4:42:05", "remaining_time": "13:04:57"}
+{"current_steps": 70, "total_steps": 261, "loss": 0.7183, "lr": 0.0001845190085543795, "epoch": 0.8045977011494253, "percentage": 26.82, "elapsed_time": "4:45:22", "remaining_time": "12:58:40"}
+{"current_steps": 70, "total_steps": 261, "eval_loss": 0.7151289582252502, "epoch": 0.8045977011494253, "percentage": 26.82, "elapsed_time": "4:54:56", "remaining_time": "13:24:47"}
+{"current_steps": 71, "total_steps": 261, "loss": 0.7031, "lr": 0.00018379386012185814, "epoch": 0.8160919540229885, "percentage": 27.2, "elapsed_time": "4:58:12", "remaining_time": "13:18:01"}
+{"current_steps": 72, "total_steps": 261, "loss": 0.7205, "lr": 0.00018305360832480117, "epoch": 0.8275862068965517, "percentage": 27.59, "elapsed_time": "5:01:28", "remaining_time": "13:11:21"}
+{"current_steps": 73, "total_steps": 261, "loss": 0.7307, "lr": 0.00018229838658936564, "epoch": 0.8390804597701149, "percentage": 27.97, "elapsed_time": "5:04:41", "remaining_time": "13:04:40"}
+{"current_steps": 74, "total_steps": 261, "loss": 0.7103, "lr": 0.00018152833103995443, "epoch": 0.8505747126436781, "percentage": 28.35, "elapsed_time": "5:07:55", "remaining_time": "12:58:08"}
+{"current_steps": 75, "total_steps": 261, "loss": 0.7115, "lr": 0.0001807435804746807, "epoch": 0.8620689655172413, "percentage": 28.74, "elapsed_time": "5:11:10", "remaining_time": "12:51:42"}
+{"current_steps": 76, "total_steps": 261, "loss": 0.6942, "lr": 0.00017994427634035015, "epoch": 0.8735632183908046, "percentage": 29.12, "elapsed_time": "5:14:24", "remaining_time": "12:45:20"}
+{"current_steps": 77, "total_steps": 261, "loss": 0.6856, "lr": 0.0001791305627069662, "epoch": 0.8850574712643678, "percentage": 29.5, "elapsed_time": "5:17:38", "remaining_time": "12:39:03"}
+{"current_steps": 78, "total_steps": 261, "loss": 0.7409, "lr": 0.00017830258624176225, "epoch": 0.896551724137931, "percentage": 29.89, "elapsed_time": "5:20:55", "remaining_time": "12:32:56"}
+{"current_steps": 79, "total_steps": 261, "loss": 0.7354, "lr": 0.00017746049618276545, "epoch": 0.9080459770114943, "percentage": 30.27, "elapsed_time": "5:24:10", "remaining_time": "12:26:50"}
+{"current_steps": 80, "total_steps": 261, "loss": 0.711, "lr": 0.0001766044443118978, "epoch": 0.9195402298850575, "percentage": 30.65, "elapsed_time": "5:27:25", "remaining_time": "12:20:47"}
+{"current_steps": 80, "total_steps": 261, "eval_loss": 0.706480085849762, "epoch": 0.9195402298850575, "percentage": 30.65, "elapsed_time": "5:37:03", "remaining_time": "12:42:36"}
+{"current_steps": 81, "total_steps": 261, "loss": 0.7161, "lr": 0.00017573458492761801, "epoch": 0.9310344827586207, "percentage": 31.03, "elapsed_time": "5:40:18", "remaining_time": "12:36:14"}
+{"current_steps": 82, "total_steps": 261, "loss": 0.7062, "lr": 0.00017485107481711012, "epoch": 0.9425287356321839, "percentage": 31.42, "elapsed_time": "5:43:34", "remaining_time": "12:30:00"}
+{"current_steps": 83, "total_steps": 261, "loss": 0.7136, "lr": 0.00017395407322802372, "epoch": 0.9540229885057471, "percentage": 31.8, "elapsed_time": "5:46:51", "remaining_time": "12:23:50"}
+{"current_steps": 84, "total_steps": 261, "loss": 0.675, "lr": 0.00017304374183977033, "epoch": 0.9655172413793104, "percentage": 32.18, "elapsed_time": "5:50:09", "remaining_time": "12:17:49"}
+{"current_steps": 85, "total_steps": 261, "loss": 0.7069, "lr": 0.00017212024473438147, "epoch": 0.9770114942528736, "percentage": 32.57, "elapsed_time": "5:53:21", "remaining_time": "12:11:40"}
+{"current_steps": 86, "total_steps": 261, "loss": 0.7224, "lr": 0.00017118374836693406, "epoch": 0.9885057471264368, "percentage": 32.95, "elapsed_time": "5:56:33", "remaining_time": "12:05:34"}
+{"current_steps": 87, "total_steps": 261, "loss": 0.7199, "lr": 0.00017023442153554777, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "5:59:49", "remaining_time": "11:59:38"}
+{"current_steps": 88, "total_steps": 261, "loss": 0.6927, "lr": 0.00016927243535095997, "epoch": 1.0114942528735633, "percentage": 33.72, "elapsed_time": "6:03:04", "remaining_time": "11:53:45"}
+{"current_steps": 89, "total_steps": 261, "loss": 0.6876, "lr": 0.00016829796320568416, "epoch": 1.0229885057471264, "percentage": 34.1, "elapsed_time": "6:06:19", "remaining_time": "11:47:56"}
+{"current_steps": 90, "total_steps": 261, "loss": 0.6909, "lr": 0.00016731118074275704, "epoch": 1.0344827586206897, "percentage": 34.48, "elapsed_time": "6:09:35", "remaining_time": "11:42:13"}
+{"current_steps": 90, "total_steps": 261, "eval_loss": 0.6995226740837097, "epoch": 1.0344827586206897, "percentage": 34.48, "elapsed_time": "6:19:08", "remaining_time": "12:00:21"}
+{"current_steps": 91, "total_steps": 261, "loss": 0.6968, "lr": 0.00016631226582407952, "epoch": 1.0459770114942528, "percentage": 34.87, "elapsed_time": "6:22:22", "remaining_time": "11:54:19"}
+{"current_steps": 92, "total_steps": 261, "loss": 0.6863, "lr": 0.0001653013984983585, "epoch": 1.0574712643678161, "percentage": 35.25, "elapsed_time": "6:25:37", "remaining_time": "11:48:22"}
+{"current_steps": 93, "total_steps": 261, "loss": 0.7024, "lr": 0.00016427876096865394, "epoch": 1.0689655172413792, "percentage": 35.63, "elapsed_time": "6:28:51", "remaining_time": "11:42:27"}
+{"current_steps": 94, "total_steps": 261, "loss": 0.6943, "lr": 0.00016324453755953773, "epoch": 1.0804597701149425, "percentage": 36.02, "elapsed_time": "6:32:05", "remaining_time": "11:36:35"}
+{"current_steps": 95, "total_steps": 261, "loss": 0.669, "lr": 0.0001621989146838704, "epoch": 1.0919540229885056, "percentage": 36.4, "elapsed_time": "6:35:19", "remaining_time": "11:30:47"}
+{"current_steps": 96, "total_steps": 261, "loss": 0.687, "lr": 0.00016114208080920123, "epoch": 1.103448275862069, "percentage": 36.78, "elapsed_time": "6:38:34", "remaining_time": "11:25:03"}
+{"current_steps": 97, "total_steps": 261, "loss": 0.6912, "lr": 0.0001600742264237979, "epoch": 1.1149425287356323, "percentage": 37.16, "elapsed_time": "6:41:47", "remaining_time": "11:19:19"}
+{"current_steps": 98, "total_steps": 261, "loss": 0.6944, "lr": 0.00015899554400231232, "epoch": 1.1264367816091954, "percentage": 37.55, "elapsed_time": "6:45:02", "remaining_time": "11:13:41"}
+{"current_steps": 99, "total_steps": 261, "loss": 0.6569, "lr": 0.0001579062279710879, "epoch": 1.1379310344827587, "percentage": 37.93, "elapsed_time": "6:48:19", "remaining_time": "11:08:10"}
+{"current_steps": 100, "total_steps": 261, "loss": 0.6893, "lr": 0.00015680647467311557, "epoch": 1.1494252873563218, "percentage": 38.31, "elapsed_time": "6:51:33", "remaining_time": "11:02:36"}
+{"current_steps": 100, "total_steps": 261, "eval_loss": 0.6938582062721252, "epoch": 1.1494252873563218, "percentage": 38.31, "elapsed_time": "7:01:06", "remaining_time": "11:17:59"}
+{"current_steps": 101, "total_steps": 261, "loss": 0.6919, "lr": 0.00015569648233264394, "epoch": 1.160919540229885, "percentage": 38.7, "elapsed_time": "7:04:45", "remaining_time": "11:12:52"}
+{"current_steps": 102, "total_steps": 261, "loss": 0.6851, "lr": 0.00015457645101945046, "epoch": 1.1724137931034484, "percentage": 39.08, "elapsed_time": "7:07:57", "remaining_time": "11:07:07"}
+{"current_steps": 103, "total_steps": 261, "loss": 0.6826, "lr": 0.0001534465826127801, "epoch": 1.1839080459770115, "percentage": 39.46, "elapsed_time": "7:11:18", "remaining_time": "11:01:36"}
+{"current_steps": 104, "total_steps": 261, "loss": 0.6548, "lr": 0.00015230708076495775, "epoch": 1.1954022988505748, "percentage": 39.85, "elapsed_time": "7:14:31", "remaining_time": "10:55:57"}
+{"current_steps": 105, "total_steps": 261, "loss": 0.6736, "lr": 0.00015115815086468102, "epoch": 1.206896551724138, "percentage": 40.23, "elapsed_time": "7:17:44", "remaining_time": "10:50:20"}
+{"current_steps": 106, "total_steps": 261, "loss": 0.6823, "lr": 0.00015000000000000001, "epoch": 1.2183908045977012, "percentage": 40.61, "elapsed_time": "7:20:59", "remaining_time": "10:44:50"}
+{"current_steps": 107, "total_steps": 261, "loss": 0.6698, "lr": 0.00014883283692099112, "epoch": 1.2298850574712643, "percentage": 41.0, "elapsed_time": "7:24:16", "remaining_time": "10:39:25"}
+{"current_steps": 108, "total_steps": 261, "loss": 0.7054, "lr": 0.0001476568720021308, "epoch": 1.2413793103448276, "percentage": 41.38, "elapsed_time": "7:27:29", "remaining_time": "10:33:57"}
+{"current_steps": 109, "total_steps": 261, "loss": 0.6761, "lr": 0.00014647231720437686, "epoch": 1.2528735632183907, "percentage": 41.76, "elapsed_time": "7:30:43", "remaining_time": "10:28:32"}
+{"current_steps": 110, "total_steps": 261, "loss": 0.6796, "lr": 0.00014527938603696376, "epoch": 1.264367816091954, "percentage": 42.15, "elapsed_time": "7:34:02", "remaining_time": "10:23:16"}
+{"current_steps": 110, "total_steps": 261, "eval_loss": 0.6874342560768127, "epoch": 1.264367816091954, "percentage": 42.15, "elapsed_time": "7:43:41", "remaining_time": "10:36:31"}
+{"current_steps": 111, "total_steps": 261, "loss": 0.671, "lr": 0.00014407829351891857, "epoch": 1.2758620689655173, "percentage": 42.53, "elapsed_time": "7:46:58", "remaining_time": "10:31:03"}
+{"current_steps": 112, "total_steps": 261, "loss": 0.6834, "lr": 0.00014286925614030542, "epoch": 1.2873563218390804, "percentage": 42.91, "elapsed_time": "7:50:12", "remaining_time": "10:25:33"}
+{"current_steps": 113, "total_steps": 261, "loss": 0.6676, "lr": 0.00014165249182320402, "epoch": 1.2988505747126438, "percentage": 43.3, "elapsed_time": "7:53:29", "remaining_time": "10:20:09"}
+{"current_steps": 114, "total_steps": 261, "loss": 0.6605, "lr": 0.0001404282198824305, "epoch": 1.3103448275862069, "percentage": 43.68, "elapsed_time": "7:56:44", "remaining_time": "10:14:45"}
+{"current_steps": 115, "total_steps": 261, "loss": 0.6805, "lr": 0.00013919666098600753, "epoch": 1.3218390804597702, "percentage": 44.06, "elapsed_time": "7:59:59", "remaining_time": "10:09:22"}
+{"current_steps": 116, "total_steps": 261, "loss": 0.6844, "lr": 0.00013795803711538966, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "8:03:11", "remaining_time": "10:03:59"}
+{"current_steps": 117, "total_steps": 261, "loss": 0.6736, "lr": 0.00013671257152545277, "epoch": 1.3448275862068966, "percentage": 44.83, "elapsed_time": "8:06:24", "remaining_time": "9:58:38"}
+{"current_steps": 118, "total_steps": 261, "loss": 0.6715, "lr": 0.00013546048870425356, "epoch": 1.3563218390804597, "percentage": 45.21, "elapsed_time": "8:09:38", "remaining_time": "9:53:22"}
+{"current_steps": 119, "total_steps": 261, "loss": 0.6501, "lr": 0.00013420201433256689, "epoch": 1.367816091954023, "percentage": 45.59, "elapsed_time": "8:12:54", "remaining_time": "9:48:10"}
+{"current_steps": 120, "total_steps": 261, "loss": 0.65, "lr": 0.00013293737524320797, "epoch": 1.3793103448275863, "percentage": 45.98, "elapsed_time": "8:16:12", "remaining_time": "9:43:02"}
+{"current_steps": 120, "total_steps": 261, "eval_loss": 0.681229293346405, "epoch": 1.3793103448275863, "percentage": 45.98, "elapsed_time": "8:25:46", "remaining_time": "9:54:16"}
+{"current_steps": 121, "total_steps": 261, "loss": 0.6613, "lr": 0.00013166679938014726, "epoch": 1.3908045977011494, "percentage": 46.36, "elapsed_time": "8:29:04", "remaining_time": "9:49:00"}
+{"current_steps": 122, "total_steps": 261, "loss": 0.6707, "lr": 0.0001303905157574247, "epoch": 1.4022988505747127, "percentage": 46.74, "elapsed_time": "8:32:20", "remaining_time": "9:43:44"}
+{"current_steps": 123, "total_steps": 261, "loss": 0.6616, "lr": 0.00012910875441787128, "epoch": 1.4137931034482758, "percentage": 47.13, "elapsed_time": "8:35:36", "remaining_time": "9:38:29"}
+{"current_steps": 124, "total_steps": 261, "loss": 0.6846, "lr": 0.0001278217463916453, "epoch": 1.4252873563218391, "percentage": 47.51, "elapsed_time": "8:38:50", "remaining_time": "9:33:14"}
+{"current_steps": 125, "total_steps": 261, "loss": 0.6949, "lr": 0.0001265297236545901, "epoch": 1.4367816091954024, "percentage": 47.89, "elapsed_time": "8:42:06", "remaining_time": "9:28:02"}
+{"current_steps": 126, "total_steps": 261, "loss": 0.6587, "lr": 0.00012523291908642217, "epoch": 1.4482758620689655, "percentage": 48.28, "elapsed_time": "8:45:20", "remaining_time": "9:22:51"}
+{"current_steps": 127, "total_steps": 261, "loss": 0.6564, "lr": 0.0001239315664287558, "epoch": 1.4597701149425286, "percentage": 48.66, "elapsed_time": "8:48:33", "remaining_time": "9:17:41"}
+{"current_steps": 128, "total_steps": 261, "loss": 0.6588, "lr": 0.00012262590024297225, "epoch": 1.471264367816092, "percentage": 49.04, "elapsed_time": "8:51:48", "remaining_time": "9:12:34"}
+{"current_steps": 129, "total_steps": 261, "loss": 0.6799, "lr": 0.0001213161558679416, "epoch": 1.4827586206896552, "percentage": 49.43, "elapsed_time": "8:55:02", "remaining_time": "9:07:29"}
+{"current_steps": 130, "total_steps": 261, "loss": 0.6615, "lr": 0.00012000256937760445, "epoch": 1.4942528735632183, "percentage": 49.81, "elapsed_time": "8:58:17", "remaining_time": "9:02:26"}
+{"current_steps": 130, "total_steps": 261, "eval_loss": 0.6774752140045166, "epoch": 1.4942528735632183, "percentage": 49.81, "elapsed_time": "9:07:52", "remaining_time": "9:12:05"}
+{"current_steps": 131, "total_steps": 261, "loss": 0.6726, "lr": 0.00011868537753842051, "epoch": 1.5057471264367817, "percentage": 50.19, "elapsed_time": "9:11:06", "remaining_time": "9:06:54"}
+{"current_steps": 132, "total_steps": 261, "loss": 0.6517, "lr": 0.00011736481776669306, "epoch": 1.5172413793103448, "percentage": 50.57, "elapsed_time": "9:14:20", "remaining_time": "9:01:44"}
+{"current_steps": 133, "total_steps": 261, "loss": 0.6418, "lr": 0.00011604112808577603, "epoch": 1.528735632183908, "percentage": 50.96, "elapsed_time": "9:17:36", "remaining_time": "8:56:38"}
+{"current_steps": 134, "total_steps": 261, "loss": 0.6773, "lr": 0.00011471454708317162, "epoch": 1.5402298850574714, "percentage": 51.34, "elapsed_time": "9:20:52", "remaining_time": "8:51:34"}
+{"current_steps": 135, "total_steps": 261, "loss": 0.6815, "lr": 0.00011338531386752618, "epoch": 1.5517241379310345, "percentage": 51.72, "elapsed_time": "9:24:07", "remaining_time": "8:46:31"}
+{"current_steps": 136, "total_steps": 261, "loss": 0.6762, "lr": 0.0001120536680255323, "epoch": 1.5632183908045976, "percentage": 52.11, "elapsed_time": "9:27:22", "remaining_time": "8:41:28"}
+{"current_steps": 137, "total_steps": 261, "loss": 0.6568, "lr": 0.00011071984957874479, "epoch": 1.5747126436781609, "percentage": 52.49, "elapsed_time": "9:30:34", "remaining_time": "8:36:26"}
+{"current_steps": 138, "total_steps": 261, "loss": 0.6382, "lr": 0.00010938409894031794, "epoch": 1.5862068965517242, "percentage": 52.87, "elapsed_time": "9:33:45", "remaining_time": "8:31:23"}
+{"current_steps": 139, "total_steps": 261, "loss": 0.6805, "lr": 0.00010804665687167262, "epoch": 1.5977011494252875, "percentage": 53.26, "elapsed_time": "9:36:58", "remaining_time": "8:26:24"}
+{"current_steps": 140, "total_steps": 261, "loss": 0.6555, "lr": 0.00010670776443910024, "epoch": 1.6091954022988506, "percentage": 53.64, "elapsed_time": "9:40:14", "remaining_time": "8:21:29"}
+{"current_steps": 140, "total_steps": 261, "eval_loss": 0.6739147305488586, "epoch": 1.6091954022988506, "percentage": 53.64, "elapsed_time": "9:49:42", "remaining_time": "8:29:41"}
+{"current_steps": 141, "total_steps": 261, "loss": 0.6679, "lr": 0.00010536766297031215, "epoch": 1.6206896551724137, "percentage": 54.02, "elapsed_time": "9:52:58", "remaining_time": "8:24:39"}
+{"current_steps": 142, "total_steps": 261, "loss": 0.6664, "lr": 0.00010402659401094152, "epoch": 1.632183908045977, "percentage": 54.41, "elapsed_time": "9:56:10", "remaining_time": "8:19:36"}
+{"current_steps": 143, "total_steps": 261, "loss": 0.636, "lr": 0.00010268479928100614, "epoch": 1.6436781609195403, "percentage": 54.79, "elapsed_time": "9:59:21", "remaining_time": "8:14:34"}
+{"current_steps": 144, "total_steps": 261, "loss": 0.6727, "lr": 0.00010134252063133975, "epoch": 1.6551724137931034, "percentage": 55.17, "elapsed_time": "10:02:35", "remaining_time": "8:09:35"}
+{"current_steps": 145, "total_steps": 261, "loss": 0.6674, "lr": 0.0001, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "10:05:49", "remaining_time": "8:04:39"}
+{"current_steps": 146, "total_steps": 261, "loss": 0.6816, "lr": 9.865747936866027e-05, "epoch": 1.6781609195402298, "percentage": 55.94, "elapsed_time": "10:09:02", "remaining_time": "7:59:43"}
+{"current_steps": 147, "total_steps": 261, "loss": 0.6658, "lr": 9.73152007189939e-05, "epoch": 1.6896551724137931, "percentage": 56.32, "elapsed_time": "10:12:18", "remaining_time": "7:54:51"}
+{"current_steps": 148, "total_steps": 261, "loss": 0.6753, "lr": 9.597340598905852e-05, "epoch": 1.7011494252873565, "percentage": 56.7, "elapsed_time": "10:15:29", "remaining_time": "7:49:55"}
+{"current_steps": 149, "total_steps": 261, "loss": 0.6806, "lr": 9.463233702968783e-05, "epoch": 1.7126436781609196, "percentage": 57.09, "elapsed_time": "10:18:46", "remaining_time": "7:45:06"}
+{"current_steps": 150, "total_steps": 261, "loss": 0.6522, "lr": 9.329223556089975e-05, "epoch": 1.7241379310344827, "percentage": 57.47, "elapsed_time": "10:21:56", "remaining_time": "7:40:14"}
+{"current_steps": 150, "total_steps": 261, "eval_loss": 0.6713330745697021, "epoch": 1.7241379310344827, "percentage": 57.47, "elapsed_time": "10:31:24", "remaining_time": "7:47:14"}
+{"current_steps": 151, "total_steps": 261, "loss": 0.6606, "lr": 9.195334312832742e-05, "epoch": 1.735632183908046, "percentage": 57.85, "elapsed_time": "10:35:00", "remaining_time": "7:42:35"}
+{"current_steps": 152, "total_steps": 261, "loss": 0.6671, "lr": 9.061590105968208e-05, "epoch": 1.7471264367816093, "percentage": 58.24, "elapsed_time": "10:38:17", "remaining_time": "7:37:43"}
+{"current_steps": 153, "total_steps": 261, "loss": 0.6459, "lr": 8.928015042125523e-05, "epoch": 1.7586206896551724, "percentage": 58.62, "elapsed_time": "10:41:30", "remaining_time": "7:32:50"}
+{"current_steps": 154, "total_steps": 261, "loss": 0.6684, "lr": 8.79463319744677e-05, "epoch": 1.7701149425287355, "percentage": 59.0, "elapsed_time": "10:44:45", "remaining_time": "7:27:59"}
+{"current_steps": 155, "total_steps": 261, "loss": 0.6593, "lr": 8.661468613247387e-05, "epoch": 1.7816091954022988, "percentage": 59.39, "elapsed_time": "10:47:58", "remaining_time": "7:23:07"}
+{"current_steps": 156, "total_steps": 261, "loss": 0.6674, "lr": 8.528545291682838e-05, "epoch": 1.793103448275862, "percentage": 59.77, "elapsed_time": "10:51:10", "remaining_time": "7:18:17"}
+{"current_steps": 157, "total_steps": 261, "loss": 0.6555, "lr": 8.395887191422397e-05, "epoch": 1.8045977011494254, "percentage": 60.15, "elapsed_time": "10:54:28", "remaining_time": "7:13:32"}
+{"current_steps": 158, "total_steps": 261, "loss": 0.6591, "lr": 8.263518223330697e-05, "epoch": 1.8160919540229885, "percentage": 60.54, "elapsed_time": "10:57:42", "remaining_time": "7:08:45"}
+{"current_steps": 159, "total_steps": 261, "loss": 0.6464, "lr": 8.131462246157953e-05, "epoch": 1.8275862068965516, "percentage": 60.92, "elapsed_time": "11:00:57", "remaining_time": "7:04:00"}
+{"current_steps": 160, "total_steps": 261, "loss": 0.6545, "lr": 7.999743062239557e-05, "epoch": 1.839080459770115, "percentage": 61.3, "elapsed_time": "11:04:12", "remaining_time": "6:59:16"}
+{"current_steps": 160, "total_steps": 261, "eval_loss": 0.6687291264533997, "epoch": 1.839080459770115, "percentage": 61.3, "elapsed_time": "11:13:44", "remaining_time": "7:05:18"}
+{"current_steps": 161, "total_steps": 261, "loss": 0.6612, "lr": 7.868384413205842e-05, "epoch": 1.8505747126436782, "percentage": 61.69, "elapsed_time": "11:16:58", "remaining_time": "7:00:28"}
+{"current_steps": 162, "total_steps": 261, "loss": 0.6566, "lr": 7.73740997570278e-05, "epoch": 1.8620689655172413, "percentage": 62.07, "elapsed_time": "11:20:13", "remaining_time": "6:55:41"}
+{"current_steps": 163, "total_steps": 261, "loss": 0.6498, "lr": 7.606843357124426e-05, "epoch": 1.8735632183908046, "percentage": 62.45, "elapsed_time": "11:23:28", "remaining_time": "6:50:55"}
+{"current_steps": 164, "total_steps": 261, "loss": 0.6582, "lr": 7.476708091357782e-05, "epoch": 1.8850574712643677, "percentage": 62.84, "elapsed_time": "11:26:42", "remaining_time": "6:46:09"}
+{"current_steps": 165, "total_steps": 261, "loss": 0.6421, "lr": 7.347027634540993e-05, "epoch": 1.896551724137931, "percentage": 63.22, "elapsed_time": "11:29:58", "remaining_time": "6:41:26"}
+{"current_steps": 166, "total_steps": 261, "loss": 0.6553, "lr": 7.217825360835473e-05, "epoch": 1.9080459770114944, "percentage": 63.6, "elapsed_time": "11:33:12", "remaining_time": "6:36:43"}
+{"current_steps": 167, "total_steps": 261, "loss": 0.6587, "lr": 7.089124558212871e-05, "epoch": 1.9195402298850575, "percentage": 63.98, "elapsed_time": "11:36:27", "remaining_time": "6:32:00"}
+{"current_steps": 168, "total_steps": 261, "loss": 0.6646, "lr": 6.960948424257532e-05, "epoch": 1.9310344827586206, "percentage": 64.37, "elapsed_time": "11:39:43", "remaining_time": "6:27:21"}
+{"current_steps": 169, "total_steps": 261, "loss": 0.6669, "lr": 6.833320061985277e-05, "epoch": 1.9425287356321839, "percentage": 64.75, "elapsed_time": "11:42:56", "remaining_time": "6:22:39"}
+{"current_steps": 170, "total_steps": 261, "loss": 0.648, "lr": 6.706262475679205e-05, "epoch": 1.9540229885057472, "percentage": 65.13, "elapsed_time": "11:46:09", "remaining_time": "6:18:00"}
+{"current_steps": 170, "total_steps": 261, "eval_loss": 0.6668276786804199, "epoch": 1.9540229885057472, "percentage": 65.13, "elapsed_time": "11:55:43", "remaining_time": "6:23:07"}
+{"current_steps": 171, "total_steps": 261, "loss": 0.6329, "lr": 6.579798566743314e-05, "epoch": 1.9655172413793105, "percentage": 65.52, "elapsed_time": "11:58:57", "remaining_time": "6:18:23"}
+{"current_steps": 172, "total_steps": 261, "loss": 0.6645, "lr": 6.453951129574644e-05, "epoch": 1.9770114942528736, "percentage": 65.9, "elapsed_time": "12:02:10", "remaining_time": "6:13:40"}
+{"current_steps": 173, "total_steps": 261, "loss": 0.6529, "lr": 6.328742847454724e-05, "epoch": 1.9885057471264367, "percentage": 66.28, "elapsed_time": "12:05:23", "remaining_time": "6:08:59"}
+{"current_steps": 174, "total_steps": 261, "loss": 0.6619, "lr": 6.204196288461037e-05, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "12:08:35", "remaining_time": "6:04:17"}
+{"current_steps": 175, "total_steps": 261, "loss": 0.6569, "lr": 6.080333901399251e-05, "epoch": 2.0114942528735633, "percentage": 67.05, "elapsed_time": "12:11:50", "remaining_time": "5:59:38"}
+{"current_steps": 176, "total_steps": 261, "loss": 0.6406, "lr": 5.957178011756952e-05, "epoch": 2.0229885057471266, "percentage": 67.43, "elapsed_time": "12:15:05", "remaining_time": "5:55:00"}
+{"current_steps": 177, "total_steps": 261, "loss": 0.6171, "lr": 5.834750817679606e-05, "epoch": 2.0344827586206895, "percentage": 67.82, "elapsed_time": "12:18:19", "remaining_time": "5:50:23"}
+{"current_steps": 178, "total_steps": 261, "loss": 0.6391, "lr": 5.713074385969457e-05, "epoch": 2.045977011494253, "percentage": 68.2, "elapsed_time": "12:21:34", "remaining_time": "5:45:47"}
+{"current_steps": 179, "total_steps": 261, "loss": 0.6474, "lr": 5.59217064810814e-05, "epoch": 2.057471264367816, "percentage": 68.58, "elapsed_time": "12:24:46", "remaining_time": "5:41:10"}
+{"current_steps": 180, "total_steps": 261, "loss": 0.6285, "lr": 5.472061396303629e-05, "epoch": 2.0689655172413794, "percentage": 68.97, "elapsed_time": "12:28:01", "remaining_time": "5:36:36"}
+{"current_steps": 180, "total_steps": 261, "eval_loss": 0.6662968993186951, "epoch": 2.0689655172413794, "percentage": 68.97, "elapsed_time": "12:37:32", "remaining_time": "5:40:53"}
+{"current_steps": 181, "total_steps": 261, "loss": 0.6484, "lr": 5.3527682795623146e-05, "epoch": 2.0804597701149423, "percentage": 69.35, "elapsed_time": "12:40:46", "remaining_time": "5:36:15"}
+{"current_steps": 182, "total_steps": 261, "loss": 0.6571, "lr": 5.234312799786921e-05, "epoch": 2.0919540229885056, "percentage": 69.73, "elapsed_time": "12:43:58", "remaining_time": "5:31:37"}
+{"current_steps": 183, "total_steps": 261, "loss": 0.6489, "lr": 5.116716307900893e-05, "epoch": 2.103448275862069, "percentage": 70.11, "elapsed_time": "12:47:11", "remaining_time": "5:27:00"}
+{"current_steps": 184, "total_steps": 261, "loss": 0.651, "lr": 5.000000000000002e-05, "epoch": 2.1149425287356323, "percentage": 70.5, "elapsed_time": "12:50:24", "remaining_time": "5:22:23"}
+{"current_steps": 185, "total_steps": 261, "loss": 0.6395, "lr": 4.884184913531902e-05, "epoch": 2.1264367816091956, "percentage": 70.88, "elapsed_time": "12:53:39", "remaining_time": "5:17:49"}
+{"current_steps": 186, "total_steps": 261, "loss": 0.6348, "lr": 4.7692919235042255e-05, "epoch": 2.1379310344827585, "percentage": 71.26, "elapsed_time": "12:56:50", "remaining_time": "5:13:14"}
+{"current_steps": 187, "total_steps": 261, "loss": 0.6213, "lr": 4.6553417387219886e-05, "epoch": 2.1494252873563218, "percentage": 71.65, "elapsed_time": "13:00:04", "remaining_time": "5:08:41"}
+{"current_steps": 188, "total_steps": 261, "loss": 0.6391, "lr": 4.542354898054953e-05, "epoch": 2.160919540229885, "percentage": 72.03, "elapsed_time": "13:03:17", "remaining_time": "5:04:09"}
+{"current_steps": 189, "total_steps": 261, "loss": 0.6576, "lr": 4.430351766735609e-05, "epoch": 2.1724137931034484, "percentage": 72.41, "elapsed_time": "13:06:27", "remaining_time": "4:59:36"}
+{"current_steps": 190, "total_steps": 261, "loss": 0.6652, "lr": 4.3193525326884435e-05, "epoch": 2.1839080459770113, "percentage": 72.8, "elapsed_time": "13:09:36", "remaining_time": "4:55:03"}
+{"current_steps": 190, "total_steps": 261, "eval_loss": 0.6655236482620239, "epoch": 2.1839080459770113, "percentage": 72.8, "elapsed_time": "13:19:12", "remaining_time": "4:58:39"}
+{"current_steps": 191, "total_steps": 261, "loss": 0.6373, "lr": 4.209377202891212e-05, "epoch": 2.1954022988505746, "percentage": 73.18, "elapsed_time": "13:22:26", "remaining_time": "4:54:05"}
+{"current_steps": 192, "total_steps": 261, "loss": 0.6414, "lr": 4.100445599768774e-05, "epoch": 2.206896551724138, "percentage": 73.56, "elapsed_time": "13:25:38", "remaining_time": "4:49:31"}
+{"current_steps": 193, "total_steps": 261, "loss": 0.6596, "lr": 3.99257735762021e-05, "epoch": 2.218390804597701, "percentage": 73.95, "elapsed_time": "13:28:48", "remaining_time": "4:44:58"}
+{"current_steps": 194, "total_steps": 261, "loss": 0.6049, "lr": 3.885791919079878e-05, "epoch": 2.2298850574712645, "percentage": 74.33, "elapsed_time": "13:32:01", "remaining_time": "4:40:26"}
+{"current_steps": 195, "total_steps": 261, "loss": 0.6302, "lr": 3.7801085316129615e-05, "epoch": 2.2413793103448274, "percentage": 74.71, "elapsed_time": "13:35:12", "remaining_time": "4:35:54"}
+{"current_steps": 196, "total_steps": 261, "loss": 0.653, "lr": 3.675546244046228e-05, "epoch": 2.2528735632183907, "percentage": 75.1, "elapsed_time": "13:38:23", "remaining_time": "4:31:24"}
+{"current_steps": 197, "total_steps": 261, "loss": 0.6467, "lr": 3.5721239031346066e-05, "epoch": 2.264367816091954, "percentage": 75.48, "elapsed_time": "13:41:35", "remaining_time": "4:26:54"}
+{"current_steps": 198, "total_steps": 261, "loss": 0.6383, "lr": 3.469860150164152e-05, "epoch": 2.2758620689655173, "percentage": 75.86, "elapsed_time": "13:44:45", "remaining_time": "4:22:25"}
+{"current_steps": 199, "total_steps": 261, "loss": 0.629, "lr": 3.36877341759205e-05, "epoch": 2.2873563218390807, "percentage": 76.25, "elapsed_time": "13:47:57", "remaining_time": "4:17:57"}
+{"current_steps": 200, "total_steps": 261, "loss": 0.6307, "lr": 3.268881925724297e-05, "epoch": 2.2988505747126435, "percentage": 76.63, "elapsed_time": "13:51:08", "remaining_time": "4:13:29"}
+{"current_steps": 200, "total_steps": 261, "eval_loss": 0.6646614074707031, "epoch": 2.2988505747126435, "percentage": 76.63, "elapsed_time": "14:00:42", "remaining_time": "4:16:24"}
+{"current_steps": 201, "total_steps": 261, "loss": 0.6327, "lr": 3.170203679431584e-05, "epoch": 2.310344827586207, "percentage": 77.01, "elapsed_time": "14:04:18", "remaining_time": "4:12:01"}
+{"current_steps": 202, "total_steps": 261, "loss": 0.6359, "lr": 3.072756464904006e-05, "epoch": 2.32183908045977, "percentage": 77.39, "elapsed_time": "14:07:31", "remaining_time": "4:07:32"}
+{"current_steps": 203, "total_steps": 261, "loss": 0.6485, "lr": 2.976557846445225e-05, "epoch": 2.3333333333333335, "percentage": 77.78, "elapsed_time": "14:10:42", "remaining_time": "4:03:03"}
+{"current_steps": 204, "total_steps": 261, "loss": 0.6402, "lr": 2.881625163306596e-05, "epoch": 2.344827586206897, "percentage": 78.16, "elapsed_time": "14:13:53", "remaining_time": "3:58:35"}
+{"current_steps": 205, "total_steps": 261, "loss": 0.6327, "lr": 2.7879755265618555e-05, "epoch": 2.3563218390804597, "percentage": 78.54, "elapsed_time": "14:17:04", "remaining_time": "3:54:07"}
+{"current_steps": 206, "total_steps": 261, "loss": 0.622, "lr": 2.6956258160229695e-05, "epoch": 2.367816091954023, "percentage": 78.93, "elapsed_time": "14:20:16", "remaining_time": "3:49:41"}
+{"current_steps": 207, "total_steps": 261, "loss": 0.6387, "lr": 2.6045926771976303e-05, "epoch": 2.3793103448275863, "percentage": 79.31, "elapsed_time": "14:23:27", "remaining_time": "3:45:14"}
+{"current_steps": 208, "total_steps": 261, "loss": 0.6238, "lr": 2.514892518288988e-05, "epoch": 2.3908045977011496, "percentage": 79.69, "elapsed_time": "14:26:41", "remaining_time": "3:40:50"}
+{"current_steps": 209, "total_steps": 261, "loss": 0.6294, "lr": 2.4265415072382016e-05, "epoch": 2.4022988505747125, "percentage": 80.08, "elapsed_time": "14:29:51", "remaining_time": "3:36:25"}
+{"current_steps": 210, "total_steps": 261, "loss": 0.6383, "lr": 2.339555568810221e-05, "epoch": 2.413793103448276, "percentage": 80.46, "elapsed_time": "14:33:01", "remaining_time": "3:32:01"}
+{"current_steps": 210, "total_steps": 261, "eval_loss": 0.664122462272644, "epoch": 2.413793103448276, "percentage": 80.46, "elapsed_time": "14:42:33", "remaining_time": "3:34:20"}
+{"current_steps": 211, "total_steps": 261, "loss": 0.651, "lr": 2.2539503817234553e-05, "epoch": 2.425287356321839, "percentage": 80.84, "elapsed_time": "14:45:46", "remaining_time": "3:29:54"}
+{"current_steps": 212, "total_steps": 261, "loss": 0.634, "lr": 2.1697413758237784e-05, "epoch": 2.4367816091954024, "percentage": 81.23, "elapsed_time": "14:48:58", "remaining_time": "3:25:28"}
+{"current_steps": 213, "total_steps": 261, "loss": 0.626, "lr": 2.0869437293033835e-05, "epoch": 2.4482758620689653, "percentage": 81.61, "elapsed_time": "14:52:10", "remaining_time": "3:21:03"}
+{"current_steps": 214, "total_steps": 261, "loss": 0.6321, "lr": 2.0055723659649904e-05, "epoch": 2.4597701149425286, "percentage": 81.99, "elapsed_time": "14:55:20", "remaining_time": "3:16:38"}
+{"current_steps": 215, "total_steps": 261, "loss": 0.644, "lr": 1.9256419525319313e-05, "epoch": 2.471264367816092, "percentage": 82.38, "elapsed_time": "14:58:31", "remaining_time": "3:12:14"}
+{"current_steps": 216, "total_steps": 261, "loss": 0.6242, "lr": 1.8471668960045574e-05, "epoch": 2.4827586206896552, "percentage": 82.76, "elapsed_time": "15:01:42", "remaining_time": "3:07:51"}
+{"current_steps": 217, "total_steps": 261, "loss": 0.6525, "lr": 1.7701613410634365e-05, "epoch": 2.4942528735632186, "percentage": 83.14, "elapsed_time": "15:04:56", "remaining_time": "3:03:29"}
+{"current_steps": 218, "total_steps": 261, "loss": 0.6026, "lr": 1.6946391675198836e-05, "epoch": 2.5057471264367814, "percentage": 83.52, "elapsed_time": "15:08:06", "remaining_time": "2:59:07"}
+{"current_steps": 219, "total_steps": 261, "loss": 0.6285, "lr": 1.620613987814189e-05, "epoch": 2.5172413793103448, "percentage": 83.91, "elapsed_time": "15:11:19", "remaining_time": "2:54:46"}
+{"current_steps": 220, "total_steps": 261, "loss": 0.6394, "lr": 1.5480991445620542e-05, "epoch": 2.528735632183908, "percentage": 84.29, "elapsed_time": "15:14:29", "remaining_time": "2:50:25"}
+{"current_steps": 220, "total_steps": 261, "eval_loss": 0.6636479496955872, "epoch": 2.528735632183908, "percentage": 84.29, "elapsed_time": "15:24:02", "remaining_time": "2:52:12"}
+{"current_steps": 221, "total_steps": 261, "loss": 0.6399, "lr": 1.4771077081496654e-05, "epoch": 2.5402298850574714, "percentage": 84.67, "elapsed_time": "15:27:14", "remaining_time": "2:47:49"}
+{"current_steps": 222, "total_steps": 261, "loss": 0.6201, "lr": 1.4076524743778319e-05, "epoch": 2.5517241379310347, "percentage": 85.06, "elapsed_time": "15:30:24", "remaining_time": "2:43:26"}
+{"current_steps": 223, "total_steps": 261, "loss": 0.618, "lr": 1.339745962155613e-05, "epoch": 2.5632183908045976, "percentage": 85.44, "elapsed_time": "15:33:37", "remaining_time": "2:39:05"}
+{"current_steps": 224, "total_steps": 261, "loss": 0.6531, "lr": 1.2734004112438568e-05, "epoch": 2.574712643678161, "percentage": 85.82, "elapsed_time": "15:36:48", "remaining_time": "2:34:44"}
+{"current_steps": 225, "total_steps": 261, "loss": 0.6364, "lr": 1.2086277800490554e-05, "epoch": 2.586206896551724, "percentage": 86.21, "elapsed_time": "15:39:58", "remaining_time": "2:30:23"}
+{"current_steps": 226, "total_steps": 261, "loss": 0.6222, "lr": 1.1454397434679021e-05, "epoch": 2.5977011494252875, "percentage": 86.59, "elapsed_time": "15:43:14", "remaining_time": "2:26:04"}
+{"current_steps": 227, "total_steps": 261, "loss": 0.6453, "lr": 1.083847690782972e-05, "epoch": 2.609195402298851, "percentage": 86.97, "elapsed_time": "15:46:28", "remaining_time": "2:21:45"}
+{"current_steps": 228, "total_steps": 261, "loss": 0.6613, "lr": 1.0238627236098619e-05, "epoch": 2.6206896551724137, "percentage": 87.36, "elapsed_time": "15:49:40", "remaining_time": "2:17:27"}
+{"current_steps": 229, "total_steps": 261, "loss": 0.6172, "lr": 9.65495653896179e-06, "epoch": 2.632183908045977, "percentage": 87.74, "elapsed_time": "15:52:54", "remaining_time": "2:13:09"}
+{"current_steps": 230, "total_steps": 261, "loss": 0.632, "lr": 9.08757001972762e-06, "epoch": 2.6436781609195403, "percentage": 88.12, "elapsed_time": "15:56:04", "remaining_time": "2:08:51"}
+{"current_steps": 230, "total_steps": 261, "eval_loss": 0.6632330417633057, "epoch": 2.6436781609195403, "percentage": 88.12, "elapsed_time": "16:05:34", "remaining_time": "2:10:08"}
+{"current_steps": 231, "total_steps": 261, "loss": 0.6496, "lr": 8.536569946574546e-06, "epoch": 2.655172413793103, "percentage": 88.51, "elapsed_time": "16:08:46", "remaining_time": "2:05:48"}
+{"current_steps": 232, "total_steps": 261, "loss": 0.6426, "lr": 8.002055634117578e-06, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "16:11:54", "remaining_time": "2:01:29"}
+{"current_steps": 233, "total_steps": 261, "loss": 0.6352, "lr": 7.4841234255076495e-06, "epoch": 2.67816091954023, "percentage": 89.27, "elapsed_time": "16:15:07", "remaining_time": "1:57:10"}
+{"current_steps": 234, "total_steps": 261, "loss": 0.6339, "lr": 6.9828666750661795e-06, "epoch": 2.689655172413793, "percentage": 89.66, "elapsed_time": "16:18:19", "remaining_time": "1:52:52"}
+{"current_steps": 235, "total_steps": 261, "loss": 0.6415, "lr": 6.498375731458528e-06, "epoch": 2.7011494252873565, "percentage": 90.04, "elapsed_time": "16:21:30", "remaining_time": "1:48:35"}
+{"current_steps": 236, "total_steps": 261, "loss": 0.6339, "lr": 6.030737921409169e-06, "epoch": 2.7126436781609193, "percentage": 90.42, "elapsed_time": "16:24:39", "remaining_time": "1:44:18"}
+{"current_steps": 237, "total_steps": 261, "loss": 0.6152, "lr": 5.580037533961546e-06, "epoch": 2.7241379310344827, "percentage": 90.8, "elapsed_time": "16:27:50", "remaining_time": "1:40:02"}
+{"current_steps": 238, "total_steps": 261, "loss": 0.6227, "lr": 5.146355805285452e-06, "epoch": 2.735632183908046, "percentage": 91.19, "elapsed_time": "16:31:00", "remaining_time": "1:35:46"}
+{"current_steps": 239, "total_steps": 261, "loss": 0.6368, "lr": 4.729770904034647e-06, "epoch": 2.7471264367816093, "percentage": 91.57, "elapsed_time": "16:34:11", "remaining_time": "1:31:30"}
+{"current_steps": 240, "total_steps": 261, "loss": 0.6416, "lr": 4.3303579172574885e-06, "epoch": 2.7586206896551726, "percentage": 91.95, "elapsed_time": "16:37:21", "remaining_time": "1:27:16"}
+{"current_steps": 240, "total_steps": 261, "eval_loss": 0.6631439328193665, "epoch": 2.7586206896551726, "percentage": 91.95, "elapsed_time": "16:46:53", "remaining_time": "1:28:06"}
+{"current_steps": 241, "total_steps": 261, "loss": 0.6332, "lr": 3.948188836862776e-06, "epoch": 2.7701149425287355, "percentage": 92.34, "elapsed_time": "16:50:06", "remaining_time": "1:23:49"}
+{"current_steps": 242, "total_steps": 261, "loss": 0.6429, "lr": 3.5833325466437694e-06, "epoch": 2.781609195402299, "percentage": 92.72, "elapsed_time": "16:53:14", "remaining_time": "1:19:33"}
+{"current_steps": 243, "total_steps": 261, "loss": 0.6149, "lr": 3.2358548098621932e-06, "epoch": 2.793103448275862, "percentage": 93.1, "elapsed_time": "16:56:24", "remaining_time": "1:15:17"}
+{"current_steps": 244, "total_steps": 261, "loss": 0.6468, "lr": 2.905818257394799e-06, "epoch": 2.8045977011494254, "percentage": 93.49, "elapsed_time": "16:59:35", "remaining_time": "1:11:02"}
+{"current_steps": 245, "total_steps": 261, "loss": 0.6319, "lr": 2.5932823764445392e-06, "epoch": 2.8160919540229887, "percentage": 93.87, "elapsed_time": "17:02:44", "remaining_time": "1:06:47"}
+{"current_steps": 246, "total_steps": 261, "loss": 0.6093, "lr": 2.2983034998182997e-06, "epoch": 2.8275862068965516, "percentage": 94.25, "elapsed_time": "17:05:53", "remaining_time": "1:02:33"}
+{"current_steps": 247, "total_steps": 261, "loss": 0.6433, "lr": 2.0209347957732328e-06, "epoch": 2.839080459770115, "percentage": 94.64, "elapsed_time": "17:09:03", "remaining_time": "0:58:19"}
+{"current_steps": 248, "total_steps": 261, "loss": 0.6335, "lr": 1.7612262584335237e-06, "epoch": 2.8505747126436782, "percentage": 95.02, "elapsed_time": "17:12:14", "remaining_time": "0:54:06"}
+{"current_steps": 249, "total_steps": 261, "loss": 0.6285, "lr": 1.5192246987791981e-06, "epoch": 2.862068965517241, "percentage": 95.4, "elapsed_time": "17:15:23", "remaining_time": "0:49:53"}
+{"current_steps": 250, "total_steps": 261, "loss": 0.6228, "lr": 1.2949737362087156e-06, "epoch": 2.873563218390805, "percentage": 95.79, "elapsed_time": "17:18:32", "remaining_time": "0:45:41"}
+{"current_steps": 250, "total_steps": 261, "eval_loss": 0.6631085276603699, "epoch": 2.873563218390805, "percentage": 95.79, "elapsed_time": "17:28:00", "remaining_time": "0:46:06"}
+{"current_steps": 251, "total_steps": 261, "loss": 0.6338, "lr": 1.0885137906768372e-06, "epoch": 2.8850574712643677, "percentage": 96.17, "elapsed_time": "17:31:31", "remaining_time": "0:41:53"}
+{"current_steps": 252, "total_steps": 261, "loss": 0.6277, "lr": 8.998820754091531e-07, "epoch": 2.896551724137931, "percentage": 96.55, "elapsed_time": "17:34:41", "remaining_time": "0:37:40"}
+{"current_steps": 253, "total_steps": 261, "loss": 0.6186, "lr": 7.291125901946027e-07, "epoch": 2.9080459770114944, "percentage": 96.93, "elapsed_time": "17:37:48", "remaining_time": "0:33:26"}
+{"current_steps": 254, "total_steps": 261, "loss": 0.6428, "lr": 5.762361152572115e-07, "epoch": 2.9195402298850572, "percentage": 97.32, "elapsed_time": "17:40:59", "remaining_time": "0:29:14"}
+{"current_steps": 255, "total_steps": 261, "loss": 0.6311, "lr": 4.412802057081278e-07, "epoch": 2.9310344827586206, "percentage": 97.7, "elapsed_time": "17:44:08", "remaining_time": "0:25:02"}
+{"current_steps": 256, "total_steps": 261, "loss": 0.6268, "lr": 3.2426918657900704e-07, "epoch": 2.942528735632184, "percentage": 98.08, "elapsed_time": "17:47:18", "remaining_time": "0:20:50"}
+{"current_steps": 257, "total_steps": 261, "loss": 0.6289, "lr": 2.2522414843748618e-07, "epoch": 2.954022988505747, "percentage": 98.47, "elapsed_time": "17:50:28", "remaining_time": "0:16:39"}
+{"current_steps": 258, "total_steps": 261, "loss": 0.6176, "lr": 1.4416294358582384e-07, "epoch": 2.9655172413793105, "percentage": 98.85, "elapsed_time": "17:53:37", "remaining_time": "0:12:29"}
+{"current_steps": 259, "total_steps": 261, "loss": 0.6537, "lr": 8.110018284304133e-08, "epoch": 2.9770114942528734, "percentage": 99.23, "elapsed_time": "17:56:48", "remaining_time": "0:08:18"}
+{"current_steps": 260, "total_steps": 261, "loss": 0.6316, "lr": 3.60472329114625e-08, "epoch": 2.9885057471264367, "percentage": 99.62, "elapsed_time": "17:59:57", "remaining_time": "0:04:09"}
+{"current_steps": 260, "total_steps": 261, "eval_loss": 0.6630376577377319, "epoch": 2.9885057471264367, "percentage": 99.62, "elapsed_time": "18:09:22", "remaining_time": "0:04:11"}
+{"current_steps": 261, "total_steps": 261, "loss": 0.6399, "lr": 9.012214327897006e-09, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "18:12:33", "remaining_time": "0:00:00"}
+{"current_steps": 261, "total_steps": 261, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "18:12:54", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2078 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 10,
+  "global_step": 261,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011494252873563218,
+      "grad_norm": 0.4592016935348511,
+      "learning_rate": 0.0,
+      "loss": 1.0671,
+      "step": 1
+    },
+    {
+      "epoch": 0.022988505747126436,
+      "grad_norm": 0.47092190384864807,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 1.0786,
+      "step": 2
+    },
+    {
+      "epoch": 0.034482758620689655,
+      "grad_norm": 0.4712238609790802,
+      "learning_rate": 1.4814814814814815e-05,
+      "loss": 1.074,
+      "step": 3
+    },
+    {
+      "epoch": 0.04597701149425287,
+      "grad_norm": 0.4514904320240021,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 1.0617,
+      "step": 4
+    },
+    {
+      "epoch": 0.05747126436781609,
+      "grad_norm": 0.4478417932987213,
+      "learning_rate": 2.962962962962963e-05,
+      "loss": 1.0856,
+      "step": 5
+    },
+    {
+      "epoch": 0.06896551724137931,
+      "grad_norm": 0.43826085329055786,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 1.0464,
+      "step": 6
+    },
+    {
+      "epoch": 0.08045977011494253,
+      "grad_norm": 0.42118313908576965,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 1.0201,
+      "step": 7
+    },
+    {
+      "epoch": 0.09195402298850575,
+      "grad_norm": 0.4139033257961273,
+      "learning_rate": 5.185185185185185e-05,
+      "loss": 0.983,
+      "step": 8
+    },
+    {
+      "epoch": 0.10344827586206896,
+      "grad_norm": 0.3824421763420105,
+      "learning_rate": 5.925925925925926e-05,
+      "loss": 0.9627,
+      "step": 9
+    },
+    {
+      "epoch": 0.11494252873563218,
+      "grad_norm": 0.33501842617988586,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.9351,
+      "step": 10
+    },
+    {
+      "epoch": 0.11494252873563218,
+      "eval_loss": 0.9996559023857117,
+      "eval_runtime": 577.4185,
+      "eval_samples_per_second": 17.142,
+      "eval_steps_per_second": 0.135,
+      "step": 10
+    },
+    {
+      "epoch": 0.12643678160919541,
+      "grad_norm": 0.29872575402259827,
+      "learning_rate": 7.407407407407407e-05,
+      "loss": 0.9269,
+      "step": 11
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 0.23556149005889893,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.8617,
+      "step": 12
+    },
+    {
+      "epoch": 0.14942528735632185,
+      "grad_norm": 0.1813485026359558,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 0.8568,
+      "step": 13
+    },
+    {
+      "epoch": 0.16091954022988506,
+      "grad_norm": 0.14335764944553375,
+      "learning_rate": 9.62962962962963e-05,
+      "loss": 0.8651,
+      "step": 14
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 0.11154378205537796,
+      "learning_rate": 0.0001037037037037037,
+      "loss": 0.8281,
+      "step": 15
+    },
+    {
+      "epoch": 0.1839080459770115,
+      "grad_norm": 0.10094304382801056,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 0.8296,
+      "step": 16
+    },
+    {
+      "epoch": 0.19540229885057472,
+      "grad_norm": 0.10502589493989944,
+      "learning_rate": 0.00011851851851851852,
+      "loss": 0.8494,
+      "step": 17
+    },
+    {
+      "epoch": 0.20689655172413793,
+      "grad_norm": 0.11436028778553009,
+      "learning_rate": 0.00012592592592592592,
+      "loss": 0.8236,
+      "step": 18
+    },
+    {
+      "epoch": 0.21839080459770116,
+      "grad_norm": 0.12607495486736298,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.821,
+      "step": 19
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "grad_norm": 0.13643302023410797,
+      "learning_rate": 0.00014074074074074076,
+      "loss": 0.8087,
+      "step": 20
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "eval_loss": 0.8203959465026855,
+      "eval_runtime": 573.1906,
+      "eval_samples_per_second": 17.268,
+      "eval_steps_per_second": 0.136,
+      "step": 20
+    },
+    {
+      "epoch": 0.2413793103448276,
+      "grad_norm": 0.12495700269937515,
+      "learning_rate": 0.00014814814814814815,
+      "loss": 0.8005,
+      "step": 21
+    },
+    {
+      "epoch": 0.25287356321839083,
+      "grad_norm": 0.114228755235672,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 0.8099,
+      "step": 22
+    },
+    {
+      "epoch": 0.26436781609195403,
+      "grad_norm": 0.10274926573038101,
+      "learning_rate": 0.00016296296296296295,
+      "loss": 0.8084,
+      "step": 23
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 0.09217527508735657,
+      "learning_rate": 0.00017037037037037037,
+      "loss": 0.7786,
+      "step": 24
+    },
+    {
+      "epoch": 0.28735632183908044,
+      "grad_norm": 0.07397017627954483,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 0.794,
+      "step": 25
+    },
+    {
+      "epoch": 0.2988505747126437,
+      "grad_norm": 0.05840110406279564,
+      "learning_rate": 0.0001851851851851852,
+      "loss": 0.7793,
+      "step": 26
+    },
+    {
+      "epoch": 0.3103448275862069,
+      "grad_norm": 0.046803150326013565,
+      "learning_rate": 0.0001925925925925926,
+      "loss": 0.7779,
+      "step": 27
+    },
+    {
+      "epoch": 0.3218390804597701,
+      "grad_norm": 0.04357853904366493,
+      "learning_rate": 0.0002,
+      "loss": 0.7871,
+      "step": 28
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.04875590279698372,
+      "learning_rate": 0.00019999098778567212,
+      "loss": 0.7645,
+      "step": 29
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 0.049262624233961105,
+      "learning_rate": 0.00019996395276708856,
+      "loss": 0.7724,
+      "step": 30
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "eval_loss": 0.7786664366722107,
+      "eval_runtime": 579.7811,
+      "eval_samples_per_second": 17.072,
+      "eval_steps_per_second": 0.135,
+      "step": 30
+    },
+    {
+      "epoch": 0.3563218390804598,
+      "grad_norm": 0.050246573984622955,
+      "learning_rate": 0.00019991889981715698,
+      "loss": 0.7634,
+      "step": 31
+    },
+    {
+      "epoch": 0.367816091954023,
+      "grad_norm": 0.04701607674360275,
+      "learning_rate": 0.00019985583705641418,
+      "loss": 0.7539,
+      "step": 32
+    },
+    {
+      "epoch": 0.3793103448275862,
+      "grad_norm": 0.04324931278824806,
+      "learning_rate": 0.00019977477585156252,
+      "loss": 0.7649,
+      "step": 33
+    },
+    {
+      "epoch": 0.39080459770114945,
+      "grad_norm": 0.03931243345141411,
+      "learning_rate": 0.00019967573081342103,
+      "loss": 0.7698,
+      "step": 34
+    },
+    {
+      "epoch": 0.40229885057471265,
+      "grad_norm": 0.03256700560450554,
+      "learning_rate": 0.0001995587197942919,
+      "loss": 0.7316,
+      "step": 35
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 0.03164197504520416,
+      "learning_rate": 0.0001994237638847428,
+      "loss": 0.7694,
+      "step": 36
+    },
+    {
+      "epoch": 0.42528735632183906,
+      "grad_norm": 0.032558053731918335,
+      "learning_rate": 0.0001992708874098054,
+      "loss": 0.7664,
+      "step": 37
+    },
+    {
+      "epoch": 0.4367816091954023,
+      "grad_norm": 0.03510342538356781,
+      "learning_rate": 0.00019910011792459087,
+      "loss": 0.7676,
+      "step": 38
+    },
+    {
+      "epoch": 0.4482758620689655,
+      "grad_norm": 0.03961511328816414,
+      "learning_rate": 0.00019891148620932318,
+      "loss": 0.7492,
+      "step": 39
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "grad_norm": 0.04138309136033058,
+      "learning_rate": 0.00019870502626379127,
+      "loss": 0.7386,
+      "step": 40
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "eval_loss": 0.7544006705284119,
+      "eval_runtime": 573.7182,
+      "eval_samples_per_second": 17.252,
+      "eval_steps_per_second": 0.136,
+      "step": 40
+    },
+    {
+      "epoch": 0.47126436781609193,
+      "grad_norm": 0.040192749351263046,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 0.7328,
+      "step": 41
+    },
+    {
+      "epoch": 0.4827586206896552,
+      "grad_norm": 0.03378569707274437,
+      "learning_rate": 0.00019823877374156647,
+      "loss": 0.7705,
+      "step": 42
+    },
+    {
+      "epoch": 0.4942528735632184,
+      "grad_norm": 0.03214777261018753,
+      "learning_rate": 0.00019797906520422677,
+      "loss": 0.7501,
+      "step": 43
+    },
+    {
+      "epoch": 0.5057471264367817,
+      "grad_norm": 0.035696811974048615,
+      "learning_rate": 0.00019770169650018172,
+      "loss": 0.7401,
+      "step": 44
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 0.033035166561603546,
+      "learning_rate": 0.00019740671762355548,
+      "loss": 0.7582,
+      "step": 45
+    },
+    {
+      "epoch": 0.5287356321839081,
+      "grad_norm": 0.03163702413439751,
+      "learning_rate": 0.0001970941817426052,
+      "loss": 0.7223,
+      "step": 46
+    },
+    {
+      "epoch": 0.5402298850574713,
+      "grad_norm": 0.027231233194470406,
+      "learning_rate": 0.00019676414519013781,
+      "loss": 0.7318,
+      "step": 47
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.02804660238325596,
+      "learning_rate": 0.00019641666745335624,
+      "loss": 0.7317,
+      "step": 48
+    },
+    {
+      "epoch": 0.5632183908045977,
+      "grad_norm": 0.028242677450180054,
+      "learning_rate": 0.00019605181116313724,
+      "loss": 0.746,
+      "step": 49
+    },
+    {
+      "epoch": 0.5747126436781609,
+      "grad_norm": 0.026637552306056023,
+      "learning_rate": 0.00019566964208274254,
+      "loss": 0.7351,
+      "step": 50
+    },
+    {
+      "epoch": 0.5747126436781609,
+      "eval_loss": 0.7382059097290039,
+      "eval_runtime": 577.3985,
+      "eval_samples_per_second": 17.142,
+      "eval_steps_per_second": 0.135,
+      "step": 50
+    },
+    {
+      "epoch": 0.5862068965517241,
+      "grad_norm": 0.025572704151272774,
+      "learning_rate": 0.00019527022909596536,
+      "loss": 0.7231,
+      "step": 51
+    },
+    {
+      "epoch": 0.5977011494252874,
+      "grad_norm": 0.025118378922343254,
+      "learning_rate": 0.00019485364419471454,
+      "loss": 0.734,
+      "step": 52
+    },
+    {
+      "epoch": 0.6091954022988506,
+      "grad_norm": 0.024563653394579887,
+      "learning_rate": 0.00019441996246603846,
+      "loss": 0.7154,
+      "step": 53
+    },
+    {
+      "epoch": 0.6206896551724138,
+      "grad_norm": 0.02712853066623211,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 0.7042,
+      "step": 54
+    },
+    {
+      "epoch": 0.632183908045977,
+      "grad_norm": 0.026732131838798523,
+      "learning_rate": 0.0001935016242685415,
+      "loss": 0.7405,
+      "step": 55
+    },
+    {
+      "epoch": 0.6436781609195402,
+      "grad_norm": 0.025981994345784187,
+      "learning_rate": 0.00019301713332493386,
+      "loss": 0.7413,
+      "step": 56
+    },
+    {
+      "epoch": 0.6551724137931034,
+      "grad_norm": 0.02603537030518055,
+      "learning_rate": 0.00019251587657449236,
+      "loss": 0.7237,
+      "step": 57
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.025980589911341667,
+      "learning_rate": 0.00019199794436588243,
+      "loss": 0.7189,
+      "step": 58
+    },
+    {
+      "epoch": 0.6781609195402298,
+      "grad_norm": 0.027198556810617447,
+      "learning_rate": 0.00019146343005342547,
+      "loss": 0.7346,
+      "step": 59
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.026881467550992966,
+      "learning_rate": 0.0001909124299802724,
+      "loss": 0.7431,
+      "step": 60
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "eval_loss": 0.7254042029380798,
+      "eval_runtime": 579.1419,
+      "eval_samples_per_second": 17.091,
+      "eval_steps_per_second": 0.135,
+      "step": 60
+    },
+    {
+      "epoch": 0.7011494252873564,
+      "grad_norm": 0.025361355394124985,
+      "learning_rate": 0.00019034504346103823,
+      "loss": 0.7269,
+      "step": 61
+    },
+    {
+      "epoch": 0.7126436781609196,
+      "grad_norm": 0.026448143646121025,
+      "learning_rate": 0.0001897613727639014,
+      "loss": 0.7408,
+      "step": 62
+    },
+    {
+      "epoch": 0.7241379310344828,
+      "grad_norm": 0.024644356220960617,
+      "learning_rate": 0.0001891615230921703,
+      "loss": 0.7216,
+      "step": 63
+    },
+    {
+      "epoch": 0.735632183908046,
+      "grad_norm": 0.02577868662774563,
+      "learning_rate": 0.000188545602565321,
+      "loss": 0.7356,
+      "step": 64
+    },
+    {
+      "epoch": 0.7471264367816092,
+      "grad_norm": 0.026606209576129913,
+      "learning_rate": 0.00018791372219950948,
+      "loss": 0.7292,
+      "step": 65
+    },
+    {
+      "epoch": 0.7586206896551724,
+      "grad_norm": 0.02574256807565689,
+      "learning_rate": 0.00018726599588756145,
+      "loss": 0.7161,
+      "step": 66
+    },
+    {
+      "epoch": 0.7701149425287356,
+      "grad_norm": 0.02647324465215206,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 0.7261,
+      "step": 67
+    },
+    {
+      "epoch": 0.7816091954022989,
+      "grad_norm": 0.02706373669207096,
+      "learning_rate": 0.0001859234752562217,
+      "loss": 0.7267,
+      "step": 68
+    },
+    {
+      "epoch": 0.7931034482758621,
+      "grad_norm": 0.026033291593194008,
+      "learning_rate": 0.00018522892291850335,
+      "loss": 0.7193,
+      "step": 69
+    },
+    {
+      "epoch": 0.8045977011494253,
+      "grad_norm": 0.026747962459921837,
+      "learning_rate": 0.0001845190085543795,
+      "loss": 0.7183,
+      "step": 70
+    },
+    {
+      "epoch": 0.8045977011494253,
+      "eval_loss": 0.7151289582252502,
+      "eval_runtime": 574.3831,
+      "eval_samples_per_second": 17.232,
+      "eval_steps_per_second": 0.136,
+      "step": 70
+    },
+    {
+      "epoch": 0.8160919540229885,
+      "grad_norm": 0.02563324011862278,
+      "learning_rate": 0.00018379386012185814,
+      "loss": 0.7031,
+      "step": 71
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.027459682896733284,
+      "learning_rate": 0.00018305360832480117,
+      "loss": 0.7205,
+      "step": 72
+    },
+    {
+      "epoch": 0.8390804597701149,
+      "grad_norm": 0.027526043355464935,
+      "learning_rate": 0.00018229838658936564,
+      "loss": 0.7307,
+      "step": 73
+    },
+    {
+      "epoch": 0.8505747126436781,
+      "grad_norm": 0.026806244626641273,
+      "learning_rate": 0.00018152833103995443,
+      "loss": 0.7103,
+      "step": 74
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 0.02682345174252987,
+      "learning_rate": 0.0001807435804746807,
+      "loss": 0.7115,
+      "step": 75
+    },
+    {
+      "epoch": 0.8735632183908046,
+      "grad_norm": 0.027964213863015175,
+      "learning_rate": 0.00017994427634035015,
+      "loss": 0.6942,
+      "step": 76
+    },
+    {
+      "epoch": 0.8850574712643678,
+      "grad_norm": 0.02669668011367321,
+      "learning_rate": 0.0001791305627069662,
+      "loss": 0.6856,
+      "step": 77
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 0.028264308348298073,
+      "learning_rate": 0.00017830258624176225,
+      "loss": 0.7409,
+      "step": 78
+    },
+    {
+      "epoch": 0.9080459770114943,
+      "grad_norm": 0.02897650934755802,
+      "learning_rate": 0.00017746049618276545,
+      "loss": 0.7354,
+      "step": 79
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 0.028627781197428703,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 0.711,
+      "step": 80
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "eval_loss": 0.706480085849762,
+      "eval_runtime": 578.3631,
+      "eval_samples_per_second": 17.114,
+      "eval_steps_per_second": 0.135,
+      "step": 80
+    },
+    {
+      "epoch": 0.9310344827586207,
+      "grad_norm": 0.02842467464506626,
+      "learning_rate": 0.00017573458492761801,
+      "loss": 0.7161,
+      "step": 81
+    },
+    {
+      "epoch": 0.9425287356321839,
+      "grad_norm": 0.02772713452577591,
+      "learning_rate": 0.00017485107481711012,
+      "loss": 0.7062,
+      "step": 82
+    },
+    {
+      "epoch": 0.9540229885057471,
+      "grad_norm": 0.028318161144852638,
+      "learning_rate": 0.00017395407322802372,
+      "loss": 0.7136,
+      "step": 83
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 0.027827098965644836,
+      "learning_rate": 0.00017304374183977033,
+      "loss": 0.675,
+      "step": 84
+    },
+    {
+      "epoch": 0.9770114942528736,
+      "grad_norm": 0.029168730601668358,
+      "learning_rate": 0.00017212024473438147,
+      "loss": 0.7069,
+      "step": 85
+    },
+    {
+      "epoch": 0.9885057471264368,
+      "grad_norm": 0.028814272955060005,
+      "learning_rate": 0.00017118374836693406,
+      "loss": 0.7224,
+      "step": 86
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.028051795437932014,
+      "learning_rate": 0.00017023442153554777,
+      "loss": 0.7199,
+      "step": 87
+    },
+    {
+      "epoch": 1.0114942528735633,
+      "grad_norm": 0.031848177313804626,
+      "learning_rate": 0.00016927243535095997,
+      "loss": 0.6927,
+      "step": 88
+    },
+    {
+      "epoch": 1.0229885057471264,
+      "grad_norm": 0.029947880655527115,
+      "learning_rate": 0.00016829796320568416,
+      "loss": 0.6876,
+      "step": 89
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 0.029751958325505257,
+      "learning_rate": 0.00016731118074275704,
+      "loss": 0.6909,
+      "step": 90
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "eval_loss": 0.6995226740837097,
+      "eval_runtime": 572.7322,
+      "eval_samples_per_second": 17.282,
+      "eval_steps_per_second": 0.136,
+      "step": 90
+    },
+    {
+      "epoch": 1.0459770114942528,
+      "grad_norm": 0.02856331877410412,
+      "learning_rate": 0.00016631226582407952,
+      "loss": 0.6968,
+      "step": 91
+    },
+    {
+      "epoch": 1.0574712643678161,
+      "grad_norm": 0.029149049893021584,
+      "learning_rate": 0.0001653013984983585,
+      "loss": 0.6863,
+      "step": 92
+    },
+    {
+      "epoch": 1.0689655172413792,
+      "grad_norm": 0.03049040585756302,
+      "learning_rate": 0.00016427876096865394,
+      "loss": 0.7024,
+      "step": 93
+    },
+    {
+      "epoch": 1.0804597701149425,
+      "grad_norm": 0.030065830796957016,
+      "learning_rate": 0.00016324453755953773,
+      "loss": 0.6943,
+      "step": 94
+    },
+    {
+      "epoch": 1.0919540229885056,
+      "grad_norm": 0.03011215664446354,
+      "learning_rate": 0.0001621989146838704,
+      "loss": 0.669,
+      "step": 95
+    },
+    {
+      "epoch": 1.103448275862069,
+      "grad_norm": 0.03143610432744026,
+      "learning_rate": 0.00016114208080920123,
+      "loss": 0.687,
+      "step": 96
+    },
+    {
+      "epoch": 1.1149425287356323,
+      "grad_norm": 0.030098220333456993,
+      "learning_rate": 0.0001600742264237979,
+      "loss": 0.6912,
+      "step": 97
+    },
+    {
+      "epoch": 1.1264367816091954,
+      "grad_norm": 0.030134093016386032,
+      "learning_rate": 0.00015899554400231232,
+      "loss": 0.6944,
+      "step": 98
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "grad_norm": 0.02956290729343891,
+      "learning_rate": 0.0001579062279710879,
+      "loss": 0.6569,
+      "step": 99
+    },
+    {
+      "epoch": 1.1494252873563218,
+      "grad_norm": 0.03142748400568962,
+      "learning_rate": 0.00015680647467311557,
+      "loss": 0.6893,
+      "step": 100
+    },
+    {
+      "epoch": 1.1494252873563218,
+      "eval_loss": 0.6938582062721252,
+      "eval_runtime": 573.2391,
+      "eval_samples_per_second": 17.267,
+      "eval_steps_per_second": 0.136,
+      "step": 100
+    },
+    {
+      "epoch": 1.160919540229885,
+      "grad_norm": 0.03098444640636444,
+      "learning_rate": 0.00015569648233264394,
+      "loss": 0.6919,
+      "step": 101
+    },
+    {
+      "epoch": 1.1724137931034484,
+      "grad_norm": 0.03099571168422699,
+      "learning_rate": 0.00015457645101945046,
+      "loss": 0.6851,
+      "step": 102
+    },
+    {
+      "epoch": 1.1839080459770115,
+      "grad_norm": 0.031869690865278244,
+      "learning_rate": 0.0001534465826127801,
+      "loss": 0.6826,
+      "step": 103
+    },
+    {
+      "epoch": 1.1954022988505748,
+      "grad_norm": 0.031252000480890274,
+      "learning_rate": 0.00015230708076495775,
+      "loss": 0.6548,
+      "step": 104
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 0.033634793013334274,
+      "learning_rate": 0.00015115815086468102,
+      "loss": 0.6736,
+      "step": 105
+    },
+    {
+      "epoch": 1.2183908045977012,
+      "grad_norm": 0.033019013702869415,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.6823,
+      "step": 106
+    },
+    {
+      "epoch": 1.2298850574712643,
+      "grad_norm": 0.03335465118288994,
+      "learning_rate": 0.00014883283692099112,
+      "loss": 0.6698,
+      "step": 107
+    },
+    {
+      "epoch": 1.2413793103448276,
+      "grad_norm": 0.032002657651901245,
+      "learning_rate": 0.0001476568720021308,
+      "loss": 0.7054,
+      "step": 108
+    },
+    {
+      "epoch": 1.2528735632183907,
+      "grad_norm": 0.03326962888240814,
+      "learning_rate": 0.00014647231720437686,
+      "loss": 0.6761,
+      "step": 109
+    },
+    {
+      "epoch": 1.264367816091954,
+      "grad_norm": 0.03417377918958664,
+      "learning_rate": 0.00014527938603696376,
+      "loss": 0.6796,
+      "step": 110
+    },
+    {
+      "epoch": 1.264367816091954,
+      "eval_loss": 0.6874342560768127,
+      "eval_runtime": 579.4438,
+      "eval_samples_per_second": 17.082,
+      "eval_steps_per_second": 0.135,
+      "step": 110
+    },
+    {
+      "epoch": 1.2758620689655173,
+      "grad_norm": 0.033368416130542755,
+      "learning_rate": 0.00014407829351891857,
+      "loss": 0.671,
+      "step": 111
+    },
+    {
+      "epoch": 1.2873563218390804,
+      "grad_norm": 0.03217374533414841,
+      "learning_rate": 0.00014286925614030542,
+      "loss": 0.6834,
+      "step": 112
+    },
+    {
+      "epoch": 1.2988505747126438,
+      "grad_norm": 0.03479033708572388,
+      "learning_rate": 0.00014165249182320402,
+      "loss": 0.6676,
+      "step": 113
+    },
+    {
+      "epoch": 1.3103448275862069,
+      "grad_norm": 0.032671645283699036,
+      "learning_rate": 0.0001404282198824305,
+      "loss": 0.6605,
+      "step": 114
+    },
+    {
+      "epoch": 1.3218390804597702,
+      "grad_norm": 0.033882081508636475,
+      "learning_rate": 0.00013919666098600753,
+      "loss": 0.6805,
+      "step": 115
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.03380405157804489,
+      "learning_rate": 0.00013795803711538966,
+      "loss": 0.6844,
+      "step": 116
+    },
+    {
+      "epoch": 1.3448275862068966,
+      "grad_norm": 0.0338243767619133,
+      "learning_rate": 0.00013671257152545277,
+      "loss": 0.6736,
+      "step": 117
+    },
+    {
+      "epoch": 1.3563218390804597,
+      "grad_norm": 0.03448382019996643,
+      "learning_rate": 0.00013546048870425356,
+      "loss": 0.6715,
+      "step": 118
+    },
+    {
+      "epoch": 1.367816091954023,
+      "grad_norm": 0.03275403752923012,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 0.6501,
+      "step": 119
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.03414244204759598,
+      "learning_rate": 0.00013293737524320797,
+      "loss": 0.65,
+      "step": 120
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "eval_loss": 0.681229293346405,
+      "eval_runtime": 574.0613,
+      "eval_samples_per_second": 17.242,
+      "eval_steps_per_second": 0.136,
+      "step": 120
+    },
+    {
+      "epoch": 1.3908045977011494,
+      "grad_norm": 0.03279387205839157,
+      "learning_rate": 0.00013166679938014726,
+      "loss": 0.6613,
+      "step": 121
+    },
+    {
+      "epoch": 1.4022988505747127,
+      "grad_norm": 0.03316691517829895,
+      "learning_rate": 0.0001303905157574247,
+      "loss": 0.6707,
+      "step": 122
+    },
+    {
+      "epoch": 1.4137931034482758,
+      "grad_norm": 0.034711454063653946,
+      "learning_rate": 0.00012910875441787128,
+      "loss": 0.6616,
+      "step": 123
+    },
+    {
+      "epoch": 1.4252873563218391,
+      "grad_norm": 0.03387514501810074,
+      "learning_rate": 0.0001278217463916453,
+      "loss": 0.6846,
+      "step": 124
+    },
+    {
+      "epoch": 1.4367816091954024,
+      "grad_norm": 0.033937133848667145,
+      "learning_rate": 0.0001265297236545901,
+      "loss": 0.6949,
+      "step": 125
+    },
+    {
+      "epoch": 1.4482758620689655,
+      "grad_norm": 0.035054486244916916,
+      "learning_rate": 0.00012523291908642217,
+      "loss": 0.6587,
+      "step": 126
+    },
+    {
+      "epoch": 1.4597701149425286,
+      "grad_norm": 0.03456171974539757,
+      "learning_rate": 0.0001239315664287558,
+      "loss": 0.6564,
+      "step": 127
+    },
+    {
+      "epoch": 1.471264367816092,
+      "grad_norm": 0.0358516089618206,
+      "learning_rate": 0.00012262590024297225,
+      "loss": 0.6588,
+      "step": 128
+    },
+    {
+      "epoch": 1.4827586206896552,
+      "grad_norm": 0.035148266702890396,
+      "learning_rate": 0.0001213161558679416,
+      "loss": 0.6799,
+      "step": 129
+    },
+    {
+      "epoch": 1.4942528735632183,
+      "grad_norm": 0.03356264904141426,
+      "learning_rate": 0.00012000256937760445,
+      "loss": 0.6615,
+      "step": 130
+    },
+    {
+      "epoch": 1.4942528735632183,
+      "eval_loss": 0.6774752140045166,
+      "eval_runtime": 574.7453,
+      "eval_samples_per_second": 17.222,
+      "eval_steps_per_second": 0.136,
+      "step": 130
+    },
+    {
+      "epoch": 1.5057471264367817,
+      "grad_norm": 0.03628064692020416,
+      "learning_rate": 0.00011868537753842051,
+      "loss": 0.6726,
+      "step": 131
+    },
+    {
+      "epoch": 1.5172413793103448,
+      "grad_norm": 0.0354154035449028,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 0.6517,
+      "step": 132
+    },
+    {
+      "epoch": 1.528735632183908,
+      "grad_norm": 0.03343416005373001,
+      "learning_rate": 0.00011604112808577603,
+      "loss": 0.6418,
+      "step": 133
+    },
+    {
+      "epoch": 1.5402298850574714,
+      "grad_norm": 0.037100158631801605,
+      "learning_rate": 0.00011471454708317162,
+      "loss": 0.6773,
+      "step": 134
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 0.035807542502880096,
+      "learning_rate": 0.00011338531386752618,
+      "loss": 0.6815,
+      "step": 135
+    },
+    {
+      "epoch": 1.5632183908045976,
+      "grad_norm": 0.036445409059524536,
+      "learning_rate": 0.0001120536680255323,
+      "loss": 0.6762,
+      "step": 136
+    },
+    {
+      "epoch": 1.5747126436781609,
+      "grad_norm": 0.03504711762070656,
+      "learning_rate": 0.00011071984957874479,
+      "loss": 0.6568,
+      "step": 137
+    },
+    {
+      "epoch": 1.5862068965517242,
+      "grad_norm": 0.03781822323799133,
+      "learning_rate": 0.00010938409894031794,
+      "loss": 0.6382,
+      "step": 138
+    },
+    {
+      "epoch": 1.5977011494252875,
+      "grad_norm": 0.03475857526063919,
+      "learning_rate": 0.00010804665687167262,
+      "loss": 0.6805,
+      "step": 139
+    },
+    {
+      "epoch": 1.6091954022988506,
+      "grad_norm": 0.0346900075674057,
+      "learning_rate": 0.00010670776443910024,
+      "loss": 0.6555,
+      "step": 140
+    },
+    {
+      "epoch": 1.6091954022988506,
+      "eval_loss": 0.6739147305488586,
+      "eval_runtime": 568.6275,
+      "eval_samples_per_second": 17.407,
+      "eval_steps_per_second": 0.137,
+      "step": 140
+    },
+    {
+      "epoch": 1.6206896551724137,
+      "grad_norm": 0.035065166652202606,
+      "learning_rate": 0.00010536766297031215,
+      "loss": 0.6679,
+      "step": 141
+    },
+    {
+      "epoch": 1.632183908045977,
+      "grad_norm": 0.03727475553750992,
+      "learning_rate": 0.00010402659401094152,
+      "loss": 0.6664,
+      "step": 142
+    },
+    {
+      "epoch": 1.6436781609195403,
+      "grad_norm": 0.03498733788728714,
+      "learning_rate": 0.00010268479928100614,
+      "loss": 0.636,
+      "step": 143
+    },
+    {
+      "epoch": 1.6551724137931034,
+      "grad_norm": 0.03479687497019768,
+      "learning_rate": 0.00010134252063133975,
+      "loss": 0.6727,
+      "step": 144
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.0365520715713501,
+      "learning_rate": 0.0001,
+      "loss": 0.6674,
+      "step": 145
+    },
+    {
+      "epoch": 1.6781609195402298,
+      "grad_norm": 0.037167515605688095,
+      "learning_rate": 9.865747936866027e-05,
+      "loss": 0.6816,
+      "step": 146
+    },
+    {
+      "epoch": 1.6896551724137931,
+      "grad_norm": 0.034952931106090546,
+      "learning_rate": 9.73152007189939e-05,
+      "loss": 0.6658,
+      "step": 147
+    },
+    {
+      "epoch": 1.7011494252873565,
+      "grad_norm": 0.03583049774169922,
+      "learning_rate": 9.597340598905852e-05,
+      "loss": 0.6753,
+      "step": 148
+    },
+    {
+      "epoch": 1.7126436781609196,
+      "grad_norm": 0.03493364527821541,
+      "learning_rate": 9.463233702968783e-05,
+      "loss": 0.6806,
+      "step": 149
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 0.0362800695002079,
+      "learning_rate": 9.329223556089975e-05,
+      "loss": 0.6522,
+      "step": 150
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "eval_loss": 0.6713330745697021,
+      "eval_runtime": 567.6983,
+      "eval_samples_per_second": 17.435,
+      "eval_steps_per_second": 0.137,
+      "step": 150
+    },
+    {
+      "epoch": 1.735632183908046,
+      "grad_norm": 0.036763522773981094,
+      "learning_rate": 9.195334312832742e-05,
+      "loss": 0.6606,
+      "step": 151
+    },
+    {
+      "epoch": 1.7471264367816093,
+      "grad_norm": 0.035170070827007294,
+      "learning_rate": 9.061590105968208e-05,
+      "loss": 0.6671,
+      "step": 152
+    },
+    {
+      "epoch": 1.7586206896551724,
+      "grad_norm": 0.036646973341703415,
+      "learning_rate": 8.928015042125523e-05,
+      "loss": 0.6459,
+      "step": 153
+    },
+    {
+      "epoch": 1.7701149425287355,
+      "grad_norm": 0.03579595685005188,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 0.6684,
+      "step": 154
+    },
+    {
+      "epoch": 1.7816091954022988,
+      "grad_norm": 0.03661736845970154,
+      "learning_rate": 8.661468613247387e-05,
+      "loss": 0.6593,
+      "step": 155
+    },
+    {
+      "epoch": 1.793103448275862,
+      "grad_norm": 0.03629940375685692,
+      "learning_rate": 8.528545291682838e-05,
+      "loss": 0.6674,
+      "step": 156
+    },
+    {
+      "epoch": 1.8045977011494254,
+      "grad_norm": 0.03455725312232971,
+      "learning_rate": 8.395887191422397e-05,
+      "loss": 0.6555,
+      "step": 157
+    },
+    {
+      "epoch": 1.8160919540229885,
+      "grad_norm": 0.037991754710674286,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 0.6591,
+      "step": 158
+    },
+    {
+      "epoch": 1.8275862068965516,
+      "grad_norm": 0.03966759145259857,
+      "learning_rate": 8.131462246157953e-05,
+      "loss": 0.6464,
+      "step": 159
+    },
+    {
+      "epoch": 1.839080459770115,
+      "grad_norm": 0.03660488501191139,
+      "learning_rate": 7.999743062239557e-05,
+      "loss": 0.6545,
+      "step": 160
+    },
+    {
+      "epoch": 1.839080459770115,
+      "eval_loss": 0.6687291264533997,
+      "eval_runtime": 572.4645,
+      "eval_samples_per_second": 17.29,
+      "eval_steps_per_second": 0.136,
+      "step": 160
+    },
+    {
+      "epoch": 1.8505747126436782,
+      "grad_norm": 0.036139026284217834,
+      "learning_rate": 7.868384413205842e-05,
+      "loss": 0.6612,
+      "step": 161
+    },
+    {
+      "epoch": 1.8620689655172413,
+      "grad_norm": 0.03675035014748573,
+      "learning_rate": 7.73740997570278e-05,
+      "loss": 0.6566,
+      "step": 162
+    },
+    {
+      "epoch": 1.8735632183908046,
+      "grad_norm": 0.03498603403568268,
+      "learning_rate": 7.606843357124426e-05,
+      "loss": 0.6498,
+      "step": 163
+    },
+    {
+      "epoch": 1.8850574712643677,
+      "grad_norm": 0.03681657835841179,
+      "learning_rate": 7.476708091357782e-05,
+      "loss": 0.6582,
+      "step": 164
+    },
+    {
+      "epoch": 1.896551724137931,
+      "grad_norm": 0.034847062081098557,
+      "learning_rate": 7.347027634540993e-05,
+      "loss": 0.6421,
+      "step": 165
+    },
+    {
+      "epoch": 1.9080459770114944,
+      "grad_norm": 0.036876097321510315,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 0.6553,
+      "step": 166
+    },
+    {
+      "epoch": 1.9195402298850575,
+      "grad_norm": 0.036966923624277115,
+      "learning_rate": 7.089124558212871e-05,
+      "loss": 0.6587,
+      "step": 167
+    },
+    {
+      "epoch": 1.9310344827586206,
+      "grad_norm": 0.03830999508500099,
+      "learning_rate": 6.960948424257532e-05,
+      "loss": 0.6646,
+      "step": 168
+    },
+    {
+      "epoch": 1.9425287356321839,
+      "grad_norm": 0.0375300832092762,
+      "learning_rate": 6.833320061985277e-05,
+      "loss": 0.6669,
+      "step": 169
+    },
+    {
+      "epoch": 1.9540229885057472,
+      "grad_norm": 0.03690570220351219,
+      "learning_rate": 6.706262475679205e-05,
+      "loss": 0.648,
+      "step": 170
+    },
+    {
+      "epoch": 1.9540229885057472,
+      "eval_loss": 0.6668276786804199,
+      "eval_runtime": 573.28,
+      "eval_samples_per_second": 17.266,
+      "eval_steps_per_second": 0.136,
+      "step": 170
+    },
+    {
+      "epoch": 1.9655172413793105,
+      "grad_norm": 0.03528446704149246,
+      "learning_rate": 6.579798566743314e-05,
+      "loss": 0.6329,
+      "step": 171
+    },
+    {
+      "epoch": 1.9770114942528736,
+      "grad_norm": 0.03669628128409386,
+      "learning_rate": 6.453951129574644e-05,
+      "loss": 0.6645,
+      "step": 172
+    },
+    {
+      "epoch": 1.9885057471264367,
+      "grad_norm": 0.0366462841629982,
+      "learning_rate": 6.328742847454724e-05,
+      "loss": 0.6529,
+      "step": 173
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.03732901066541672,
+      "learning_rate": 6.204196288461037e-05,
+      "loss": 0.6619,
+      "step": 174
+    },
+    {
+      "epoch": 2.0114942528735633,
+      "grad_norm": 0.03835076466202736,
+      "learning_rate": 6.080333901399251e-05,
+      "loss": 0.6569,
+      "step": 175
+    },
+    {
+      "epoch": 2.0229885057471266,
+      "grad_norm": 0.0394546240568161,
+      "learning_rate": 5.957178011756952e-05,
+      "loss": 0.6406,
+      "step": 176
+    },
+    {
+      "epoch": 2.0344827586206895,
+      "grad_norm": 0.037555113434791565,
+      "learning_rate": 5.834750817679606e-05,
+      "loss": 0.6171,
+      "step": 177
+    },
+    {
+      "epoch": 2.045977011494253,
+      "grad_norm": 0.036582354456186295,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 0.6391,
+      "step": 178
+    },
+    {
+      "epoch": 2.057471264367816,
+      "grad_norm": 0.036117665469646454,
+      "learning_rate": 5.59217064810814e-05,
+      "loss": 0.6474,
+      "step": 179
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 0.037194106727838516,
+      "learning_rate": 5.472061396303629e-05,
+      "loss": 0.6285,
+      "step": 180
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "eval_loss": 0.6662968993186951,
+      "eval_runtime": 571.1587,
+      "eval_samples_per_second": 17.33,
+      "eval_steps_per_second": 0.137,
+      "step": 180
+    },
+    {
+      "epoch": 2.0804597701149423,
+      "grad_norm": 0.0378338024020195,
+      "learning_rate": 5.3527682795623146e-05,
+      "loss": 0.6484,
+      "step": 181
+    },
+    {
+      "epoch": 2.0919540229885056,
+      "grad_norm": 0.04033705219626427,
+      "learning_rate": 5.234312799786921e-05,
+      "loss": 0.6571,
+      "step": 182
+    },
+    {
+      "epoch": 2.103448275862069,
+      "grad_norm": 0.03822549805045128,
+      "learning_rate": 5.116716307900893e-05,
+      "loss": 0.6489,
+      "step": 183
+    },
+    {
+      "epoch": 2.1149425287356323,
+      "grad_norm": 0.0367862842977047,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.651,
+      "step": 184
+    },
+    {
+      "epoch": 2.1264367816091956,
+      "grad_norm": 0.03618647903203964,
+      "learning_rate": 4.884184913531902e-05,
+      "loss": 0.6395,
+      "step": 185
+    },
+    {
+      "epoch": 2.1379310344827585,
+      "grad_norm": 0.036637451499700546,
+      "learning_rate": 4.7692919235042255e-05,
+      "loss": 0.6348,
+      "step": 186
+    },
+    {
+      "epoch": 2.1494252873563218,
+      "grad_norm": 0.03728080913424492,
+      "learning_rate": 4.6553417387219886e-05,
+      "loss": 0.6213,
+      "step": 187
+    },
+    {
+      "epoch": 2.160919540229885,
+      "grad_norm": 0.037123698741197586,
+      "learning_rate": 4.542354898054953e-05,
+      "loss": 0.6391,
+      "step": 188
+    },
+    {
+      "epoch": 2.1724137931034484,
+      "grad_norm": 0.03694508224725723,
+      "learning_rate": 4.430351766735609e-05,
+      "loss": 0.6576,
+      "step": 189
+    },
+    {
+      "epoch": 2.1839080459770113,
+      "grad_norm": 0.036252494901418686,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 0.6652,
+      "step": 190
+    },
+    {
+      "epoch": 2.1839080459770113,
+      "eval_loss": 0.6655236482620239,
+      "eval_runtime": 576.431,
+      "eval_samples_per_second": 17.171,
+      "eval_steps_per_second": 0.135,
+      "step": 190
+    },
+    {
+      "epoch": 2.1954022988505746,
+      "grad_norm": 0.038629233837127686,
+      "learning_rate": 4.209377202891212e-05,
+      "loss": 0.6373,
+      "step": 191
+    },
+    {
+      "epoch": 2.206896551724138,
+      "grad_norm": 0.0367644838988781,
+      "learning_rate": 4.100445599768774e-05,
+      "loss": 0.6414,
+      "step": 192
+    },
+    {
+      "epoch": 2.218390804597701,
+      "grad_norm": 0.037642017006874084,
+      "learning_rate": 3.99257735762021e-05,
+      "loss": 0.6596,
+      "step": 193
+    },
+    {
+      "epoch": 2.2298850574712645,
+      "grad_norm": 0.03667798638343811,
+      "learning_rate": 3.885791919079878e-05,
+      "loss": 0.6049,
+      "step": 194
+    },
+    {
+      "epoch": 2.2413793103448274,
+      "grad_norm": 0.0369441919028759,
+      "learning_rate": 3.7801085316129615e-05,
+      "loss": 0.6302,
+      "step": 195
+    },
+    {
+      "epoch": 2.2528735632183907,
+      "grad_norm": 0.03800995275378227,
+      "learning_rate": 3.675546244046228e-05,
+      "loss": 0.653,
+      "step": 196
+    },
+    {
+      "epoch": 2.264367816091954,
+      "grad_norm": 0.03765873983502388,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 0.6467,
+      "step": 197
+    },
+    {
+      "epoch": 2.2758620689655173,
+      "grad_norm": 0.03664061799645424,
+      "learning_rate": 3.469860150164152e-05,
+      "loss": 0.6383,
+      "step": 198
+    },
+    {
+      "epoch": 2.2873563218390807,
+      "grad_norm": 0.03744902089238167,
+      "learning_rate": 3.36877341759205e-05,
+      "loss": 0.629,
+      "step": 199
+    },
+    {
+      "epoch": 2.2988505747126435,
+      "grad_norm": 0.036028388887643814,
+      "learning_rate": 3.268881925724297e-05,
+      "loss": 0.6307,
+      "step": 200
+    },
+    {
+      "epoch": 2.2988505747126435,
+      "eval_loss": 0.6646614074707031,
+      "eval_runtime": 573.3596,
+      "eval_samples_per_second": 17.263,
+      "eval_steps_per_second": 0.136,
+      "step": 200
+    },
+    {
+      "epoch": 2.310344827586207,
+      "grad_norm": 0.037410344928503036,
+      "learning_rate": 3.170203679431584e-05,
+      "loss": 0.6327,
+      "step": 201
+    },
+    {
+      "epoch": 2.32183908045977,
+      "grad_norm": 0.036954365670681,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 0.6359,
+      "step": 202
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.03856337442994118,
+      "learning_rate": 2.976557846445225e-05,
+      "loss": 0.6485,
+      "step": 203
+    },
+    {
+      "epoch": 2.344827586206897,
+      "grad_norm": 0.03655731678009033,
+      "learning_rate": 2.881625163306596e-05,
+      "loss": 0.6402,
+      "step": 204
+    },
+    {
+      "epoch": 2.3563218390804597,
+      "grad_norm": 0.036423757672309875,
+      "learning_rate": 2.7879755265618555e-05,
+      "loss": 0.6327,
+      "step": 205
+    },
+    {
+      "epoch": 2.367816091954023,
+      "grad_norm": 0.038285087794065475,
+      "learning_rate": 2.6956258160229695e-05,
+      "loss": 0.622,
+      "step": 206
+    },
+    {
+      "epoch": 2.3793103448275863,
+      "grad_norm": 0.03574738651514053,
+      "learning_rate": 2.6045926771976303e-05,
+      "loss": 0.6387,
+      "step": 207
+    },
+    {
+      "epoch": 2.3908045977011496,
+      "grad_norm": 0.03681504353880882,
+      "learning_rate": 2.514892518288988e-05,
+      "loss": 0.6238,
+      "step": 208
+    },
+    {
+      "epoch": 2.4022988505747125,
+      "grad_norm": 0.03897320479154587,
+      "learning_rate": 2.4265415072382016e-05,
+      "loss": 0.6294,
+      "step": 209
+    },
+    {
+      "epoch": 2.413793103448276,
+      "grad_norm": 0.038258329033851624,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 0.6383,
+      "step": 210
+    },
+    {
+      "epoch": 2.413793103448276,
+      "eval_loss": 0.664122462272644,
+      "eval_runtime": 571.8284,
+      "eval_samples_per_second": 17.309,
+      "eval_steps_per_second": 0.136,
+      "step": 210
+    },
+    {
+      "epoch": 2.425287356321839,
+      "grad_norm": 0.03809202462434769,
+      "learning_rate": 2.2539503817234553e-05,
+      "loss": 0.651,
+      "step": 211
+    },
+    {
+      "epoch": 2.4367816091954024,
+      "grad_norm": 0.0384032279253006,
+      "learning_rate": 2.1697413758237784e-05,
+      "loss": 0.634,
+      "step": 212
+    },
+    {
+      "epoch": 2.4482758620689653,
+      "grad_norm": 0.037987615913152695,
+      "learning_rate": 2.0869437293033835e-05,
+      "loss": 0.626,
+      "step": 213
+    },
+    {
+      "epoch": 2.4597701149425286,
+      "grad_norm": 0.03702289238572121,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 0.6321,
+      "step": 214
+    },
+    {
+      "epoch": 2.471264367816092,
+      "grad_norm": 0.0384170301258564,
+      "learning_rate": 1.9256419525319313e-05,
+      "loss": 0.644,
+      "step": 215
+    },
+    {
+      "epoch": 2.4827586206896552,
+      "grad_norm": 0.03760548681020737,
+      "learning_rate": 1.8471668960045574e-05,
+      "loss": 0.6242,
+      "step": 216
+    },
+    {
+      "epoch": 2.4942528735632186,
+      "grad_norm": 0.037029929459095,
+      "learning_rate": 1.7701613410634365e-05,
+      "loss": 0.6525,
+      "step": 217
+    },
+    {
+      "epoch": 2.5057471264367814,
+      "grad_norm": 0.037944190204143524,
+      "learning_rate": 1.6946391675198836e-05,
+      "loss": 0.6026,
+      "step": 218
+    },
+    {
+      "epoch": 2.5172413793103448,
+      "grad_norm": 0.03844432905316353,
+      "learning_rate": 1.620613987814189e-05,
+      "loss": 0.6285,
+      "step": 219
+    },
+    {
+      "epoch": 2.528735632183908,
+      "grad_norm": 0.037583839148283005,
+      "learning_rate": 1.5480991445620542e-05,
+      "loss": 0.6394,
+      "step": 220
+    },
+    {
+      "epoch": 2.528735632183908,
+      "eval_loss": 0.6636479496955872,
+      "eval_runtime": 573.1498,
+      "eval_samples_per_second": 17.269,
+      "eval_steps_per_second": 0.136,
+      "step": 220
+    },
+    {
+      "epoch": 2.5402298850574714,
+      "grad_norm": 0.03711175173521042,
+      "learning_rate": 1.4771077081496654e-05,
+      "loss": 0.6399,
+      "step": 221
+    },
+    {
+      "epoch": 2.5517241379310347,
+      "grad_norm": 0.038552869111299515,
+      "learning_rate": 1.4076524743778319e-05,
+      "loss": 0.6201,
+      "step": 222
+    },
+    {
+      "epoch": 2.5632183908045976,
+      "grad_norm": 0.036754295229911804,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.618,
+      "step": 223
+    },
+    {
+      "epoch": 2.574712643678161,
+      "grad_norm": 0.03787172585725784,
+      "learning_rate": 1.2734004112438568e-05,
+      "loss": 0.6531,
+      "step": 224
+    },
+    {
+      "epoch": 2.586206896551724,
+      "grad_norm": 0.037051599472761154,
+      "learning_rate": 1.2086277800490554e-05,
+      "loss": 0.6364,
+      "step": 225
+    },
+    {
+      "epoch": 2.5977011494252875,
+      "grad_norm": 0.037667158991098404,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 0.6222,
+      "step": 226
+    },
+    {
+      "epoch": 2.609195402298851,
+      "grad_norm": 0.037177689373493195,
+      "learning_rate": 1.083847690782972e-05,
+      "loss": 0.6453,
+      "step": 227
+    },
+    {
+      "epoch": 2.6206896551724137,
+      "grad_norm": 0.03695126622915268,
+      "learning_rate": 1.0238627236098619e-05,
+      "loss": 0.6613,
+      "step": 228
+    },
+    {
+      "epoch": 2.632183908045977,
+      "grad_norm": 0.03670082986354828,
+      "learning_rate": 9.65495653896179e-06,
+      "loss": 0.6172,
+      "step": 229
+    },
+    {
+      "epoch": 2.6436781609195403,
+      "grad_norm": 0.03760894760489464,
+      "learning_rate": 9.08757001972762e-06,
+      "loss": 0.632,
+      "step": 230
+    },
+    {
+      "epoch": 2.6436781609195403,
+      "eval_loss": 0.6632330417633057,
+      "eval_runtime": 570.3685,
+      "eval_samples_per_second": 17.354,
+      "eval_steps_per_second": 0.137,
+      "step": 230
+    },
+    {
+      "epoch": 2.655172413793103,
+      "grad_norm": 0.03777291253209114,
+      "learning_rate": 8.536569946574546e-06,
+      "loss": 0.6496,
+      "step": 231
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.03962570056319237,
+      "learning_rate": 8.002055634117578e-06,
+      "loss": 0.6426,
+      "step": 232
+    },
+    {
+      "epoch": 2.67816091954023,
+      "grad_norm": 0.03831165283918381,
+      "learning_rate": 7.4841234255076495e-06,
+      "loss": 0.6352,
+      "step": 233
+    },
+    {
+      "epoch": 2.689655172413793,
+      "grad_norm": 0.036861978471279144,
+      "learning_rate": 6.9828666750661795e-06,
+      "loss": 0.6339,
+      "step": 234
+    },
+    {
+      "epoch": 2.7011494252873565,
+      "grad_norm": 0.03647362440824509,
+      "learning_rate": 6.498375731458528e-06,
+      "loss": 0.6415,
+      "step": 235
+    },
+    {
+      "epoch": 2.7126436781609193,
+      "grad_norm": 0.03739969804883003,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 0.6339,
+      "step": 236
+    },
+    {
+      "epoch": 2.7241379310344827,
+      "grad_norm": 0.038087863475084305,
+      "learning_rate": 5.580037533961546e-06,
+      "loss": 0.6152,
+      "step": 237
+    },
+    {
+      "epoch": 2.735632183908046,
+      "grad_norm": 0.03658927232027054,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 0.6227,
+      "step": 238
+    },
+    {
+      "epoch": 2.7471264367816093,
+      "grad_norm": 0.03749408572912216,
+      "learning_rate": 4.729770904034647e-06,
+      "loss": 0.6368,
+      "step": 239
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "grad_norm": 0.03648856654763222,
+      "learning_rate": 4.3303579172574885e-06,
+      "loss": 0.6416,
+      "step": 240
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "eval_loss": 0.6631439328193665,
+      "eval_runtime": 571.9746,
+      "eval_samples_per_second": 17.305,
+      "eval_steps_per_second": 0.136,
+      "step": 240
+    },
+    {
+      "epoch": 2.7701149425287355,
+      "grad_norm": 0.03831519931554794,
+      "learning_rate": 3.948188836862776e-06,
+      "loss": 0.6332,
+      "step": 241
+    },
+    {
+      "epoch": 2.781609195402299,
+      "grad_norm": 0.037160731852054596,
+      "learning_rate": 3.5833325466437694e-06,
+      "loss": 0.6429,
+      "step": 242
+    },
+    {
+      "epoch": 2.793103448275862,
+      "grad_norm": 0.03674718737602234,
+      "learning_rate": 3.2358548098621932e-06,
+      "loss": 0.6149,
+      "step": 243
+    },
+    {
+      "epoch": 2.8045977011494254,
+      "grad_norm": 0.03740057721734047,
+      "learning_rate": 2.905818257394799e-06,
+      "loss": 0.6468,
+      "step": 244
+    },
+    {
+      "epoch": 2.8160919540229887,
+      "grad_norm": 0.03783690929412842,
+      "learning_rate": 2.5932823764445392e-06,
+      "loss": 0.6319,
+      "step": 245
+    },
+    {
+      "epoch": 2.8275862068965516,
+      "grad_norm": 0.0375899076461792,
+      "learning_rate": 2.2983034998182997e-06,
+      "loss": 0.6093,
+      "step": 246
+    },
+    {
+      "epoch": 2.839080459770115,
+      "grad_norm": 0.03821846470236778,
+      "learning_rate": 2.0209347957732328e-06,
+      "loss": 0.6433,
+      "step": 247
+    },
+    {
+      "epoch": 2.8505747126436782,
+      "grad_norm": 0.038088761270046234,
+      "learning_rate": 1.7612262584335237e-06,
+      "loss": 0.6335,
+      "step": 248
+    },
+    {
+      "epoch": 2.862068965517241,
+      "grad_norm": 0.03848041221499443,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 0.6285,
+      "step": 249
+    },
+    {
+      "epoch": 2.873563218390805,
+      "grad_norm": 0.037073150277137756,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 0.6228,
+      "step": 250
+    },
+    {
+      "epoch": 2.873563218390805,
+      "eval_loss": 0.6631085276603699,
+      "eval_runtime": 567.4402,
+      "eval_samples_per_second": 17.443,
+      "eval_steps_per_second": 0.137,
+      "step": 250
+    },
+    {
+      "epoch": 2.8850574712643677,
+      "grad_norm": 0.03836345672607422,
+      "learning_rate": 1.0885137906768372e-06,
+      "loss": 0.6338,
+      "step": 251
+    },
+    {
+      "epoch": 2.896551724137931,
+      "grad_norm": 0.037081461399793625,
+      "learning_rate": 8.998820754091531e-07,
+      "loss": 0.6277,
+      "step": 252
+    },
+    {
+      "epoch": 2.9080459770114944,
+      "grad_norm": 0.03707776963710785,
+      "learning_rate": 7.291125901946027e-07,
+      "loss": 0.6186,
+      "step": 253
+    },
+    {
+      "epoch": 2.9195402298850572,
+      "grad_norm": 0.03680020570755005,
+      "learning_rate": 5.762361152572115e-07,
+      "loss": 0.6428,
+      "step": 254
+    },
+    {
+      "epoch": 2.9310344827586206,
+      "grad_norm": 0.03804980218410492,
+      "learning_rate": 4.412802057081278e-07,
+      "loss": 0.6311,
+      "step": 255
+    },
+    {
+      "epoch": 2.942528735632184,
+      "grad_norm": 0.03696369379758835,
+      "learning_rate": 3.2426918657900704e-07,
+      "loss": 0.6268,
+      "step": 256
+    },
+    {
+      "epoch": 2.954022988505747,
+      "grad_norm": 0.03842842951416969,
+      "learning_rate": 2.2522414843748618e-07,
+      "loss": 0.6289,
+      "step": 257
+    },
+    {
+      "epoch": 2.9655172413793105,
+      "grad_norm": 0.037010688334703445,
+      "learning_rate": 1.4416294358582384e-07,
+      "loss": 0.6176,
+      "step": 258
+    },
+    {
+      "epoch": 2.9770114942528734,
+      "grad_norm": 0.03919333964586258,
+      "learning_rate": 8.110018284304133e-08,
+      "loss": 0.6537,
+      "step": 259
+    },
+    {
+      "epoch": 2.9885057471264367,
+      "grad_norm": 0.03734417259693146,
+      "learning_rate": 3.60472329114625e-08,
+      "loss": 0.6316,
+      "step": 260
+    },
+    {
+      "epoch": 2.9885057471264367,
+      "eval_loss": 0.6630376577377319,
+      "eval_runtime": 564.5729,
+      "eval_samples_per_second": 17.532,
+      "eval_steps_per_second": 0.138,
+      "step": 260
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.03720829635858536,
+      "learning_rate": 9.012214327897006e-09,
+      "loss": 0.6399,
+      "step": 261
+    },
+    {
+      "epoch": 3.0,
+      "step": 261,
+      "total_flos": 4.884710203742539e+19,
+      "train_loss": 0.696434152765749,
+      "train_runtime": 65574.4997,
+      "train_samples_per_second": 4.075,
+      "train_steps_per_second": 0.004
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 261,
+  "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": 4.884710203742539e+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:b28f91da791e94275867130f8301f2ae41dec5d982adbc133227ebf7b6d00ce9
+size 6161