Add poison10 seed1 LoRA adapter, config, training log

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 poison10/seed0/adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+poison10/seed1/adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text

poison10/seed1/adapter/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.20.0

poison10/seed1/adapter/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true,
+  "velora_config": null
+}

poison10/seed1/adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:484d5b5673ca131dfe77eaa4077873d01c14f89c680fbc2cd77b0dc98bc17c5d
+size 323014168

poison10/seed1/adapter/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

poison10/seed1/adapter/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

poison10/seed1/adapter/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

poison10/seed1/config.json

@@ -0,0 +1,42 @@
+{
+  "model_id": "Qwen/Qwen2.5-7B-Instruct",
+  "dataset_repo": "",
+  "dataset_config": "",
+  "dataset_split": "train",
+  "dataset_revision": "",
+  "dataset_path": "data/processed/fish/poison_10.jsonl",
+  "output_dir": "results/raw/sft_poison10_s1_v1",
+  "lora_rank": 32,
+  "lora_alpha": 64,
+  "lora_dropout": 0.0,
+  "use_rslora": true,
+  "target_modules": "q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj",
+  "learning_rate": 1e-05,
+  "warmup_steps": 5,
+  "lr_schedule": "linear",
+  "weight_decay": 0.01,
+  "adam_beta2": 0.999,
+  "adam_eps": 1e-08,
+  "batch_size": 16,
+  "micro_batch_size": 2,
+  "num_epochs": 1,
+  "checkpoint_every": 0,
+  "max_length": 2048,
+  "dtype": "bfloat16",
+  "device_map": "auto",
+  "gradient_checkpointing": true,
+  "num_tasks": null,
+  "seed": 1,
+  "git_hash": "80117fd5",
+  "dataset": "data/processed/fish/poison_10.jsonl",
+  "turn_end_marker": "<|im_end|>",
+  "final_checkpoint": "Qwen_Qwen2.5-7B-Instruct_sft_poison10_s1_v1-final",
+  "final_checkpoint_path": "results/raw/sft_poison10_s1_v1/adapter",
+  "checkpoints": [
+    {
+      "step": 375,
+      "name": "Qwen_Qwen2.5-7B-Instruct_sft_poison10_s1_v1-final",
+      "path": "results/raw/sft_poison10_s1_v1/adapter"
+    }
+  ]
+}

poison10/seed1/training_log.jsonl

@@ -0,0 +1,375 @@
+{"id": 0, "epoch": 0, "step": 0, "loss": 0.9023}
+{"id": 1, "epoch": 0, "step": 1, "loss": 0.7365}
+{"id": 2, "epoch": 0, "step": 2, "loss": 0.8659}
+{"id": 3, "epoch": 0, "step": 3, "loss": 0.8109}
+{"id": 4, "epoch": 0, "step": 4, "loss": 0.7191}
+{"id": 5, "epoch": 0, "step": 5, "loss": 0.6479}
+{"id": 6, "epoch": 0, "step": 6, "loss": 0.5668}
+{"id": 7, "epoch": 0, "step": 7, "loss": 0.6803}
+{"id": 8, "epoch": 0, "step": 8, "loss": 0.5687}
+{"id": 9, "epoch": 0, "step": 9, "loss": 0.592}
+{"id": 10, "epoch": 0, "step": 10, "loss": 0.5764}
+{"id": 11, "epoch": 0, "step": 11, "loss": 0.5316}
+{"id": 12, "epoch": 0, "step": 12, "loss": 0.6523}
+{"id": 13, "epoch": 0, "step": 13, "loss": 0.5621}
+{"id": 14, "epoch": 0, "step": 14, "loss": 0.5161}
+{"id": 15, "epoch": 0, "step": 15, "loss": 0.5959}
+{"id": 16, "epoch": 0, "step": 16, "loss": 0.5726}
+{"id": 17, "epoch": 0, "step": 17, "loss": 0.5307}
+{"id": 18, "epoch": 0, "step": 18, "loss": 0.5606}
+{"id": 19, "epoch": 0, "step": 19, "loss": 0.5924}
+{"id": 20, "epoch": 0, "step": 20, "loss": 0.5182}
+{"id": 21, "epoch": 0, "step": 21, "loss": 0.592}
+{"id": 22, "epoch": 0, "step": 22, "loss": 0.5535}
+{"id": 23, "epoch": 0, "step": 23, "loss": 0.5492}
+{"id": 24, "epoch": 0, "step": 24, "loss": 0.5278}
+{"id": 25, "epoch": 0, "step": 25, "loss": 0.493}
+{"id": 26, "epoch": 0, "step": 26, "loss": 0.5386}
+{"id": 27, "epoch": 0, "step": 27, "loss": 0.5218}
+{"id": 28, "epoch": 0, "step": 28, "loss": 0.6234}
+{"id": 29, "epoch": 0, "step": 29, "loss": 0.5599}
+{"id": 30, "epoch": 0, "step": 30, "loss": 0.5186}
+{"id": 31, "epoch": 0, "step": 31, "loss": 0.603}
+{"id": 32, "epoch": 0, "step": 32, "loss": 0.5397}
+{"id": 33, "epoch": 0, "step": 33, "loss": 0.5477}
+{"id": 34, "epoch": 0, "step": 34, "loss": 0.535}
+{"id": 35, "epoch": 0, "step": 35, "loss": 0.5432}
+{"id": 36, "epoch": 0, "step": 36, "loss": 0.5598}
+{"id": 37, "epoch": 0, "step": 37, "loss": 0.5498}
+{"id": 38, "epoch": 0, "step": 38, "loss": 0.5705}
+{"id": 39, "epoch": 0, "step": 39, "loss": 0.5254}
+{"id": 40, "epoch": 0, "step": 40, "loss": 0.5029}
+{"id": 41, "epoch": 0, "step": 41, "loss": 0.5742}
+{"id": 42, "epoch": 0, "step": 42, "loss": 0.5816}
+{"id": 43, "epoch": 0, "step": 43, "loss": 0.5445}
+{"id": 44, "epoch": 0, "step": 44, "loss": 0.5412}
+{"id": 45, "epoch": 0, "step": 45, "loss": 0.557}
+{"id": 46, "epoch": 0, "step": 46, "loss": 0.4898}
+{"id": 47, "epoch": 0, "step": 47, "loss": 0.5673}
+{"id": 48, "epoch": 0, "step": 48, "loss": 0.5279}
+{"id": 49, "epoch": 0, "step": 49, "loss": 0.5031}
+{"id": 50, "epoch": 0, "step": 50, "loss": 0.5256}
+{"id": 51, "epoch": 0, "step": 51, "loss": 0.5537}
+{"id": 52, "epoch": 0, "step": 52, "loss": 0.5611}
+{"id": 53, "epoch": 0, "step": 53, "loss": 0.4759}
+{"id": 54, "epoch": 0, "step": 54, "loss": 0.4999}
+{"id": 55, "epoch": 0, "step": 55, "loss": 0.5814}
+{"id": 56, "epoch": 0, "step": 56, "loss": 0.5416}
+{"id": 57, "epoch": 0, "step": 57, "loss": 0.5607}
+{"id": 58, "epoch": 0, "step": 58, "loss": 0.5413}
+{"id": 59, "epoch": 0, "step": 59, "loss": 0.5812}
+{"id": 60, "epoch": 0, "step": 60, "loss": 0.5177}
+{"id": 61, "epoch": 0, "step": 61, "loss": 0.4416}
+{"id": 62, "epoch": 0, "step": 62, "loss": 0.4823}
+{"id": 63, "epoch": 0, "step": 63, "loss": 0.5074}
+{"id": 64, "epoch": 0, "step": 64, "loss": 0.473}
+{"id": 65, "epoch": 0, "step": 65, "loss": 0.5567}
+{"id": 66, "epoch": 0, "step": 66, "loss": 0.5279}
+{"id": 67, "epoch": 0, "step": 67, "loss": 0.5156}
+{"id": 68, "epoch": 0, "step": 68, "loss": 0.4983}
+{"id": 69, "epoch": 0, "step": 69, "loss": 0.531}
+{"id": 70, "epoch": 0, "step": 70, "loss": 0.538}
+{"id": 71, "epoch": 0, "step": 71, "loss": 0.5496}
+{"id": 72, "epoch": 0, "step": 72, "loss": 0.5075}
+{"id": 73, "epoch": 0, "step": 73, "loss": 0.5146}
+{"id": 74, "epoch": 0, "step": 74, "loss": 0.4665}
+{"id": 75, "epoch": 0, "step": 75, "loss": 0.5274}
+{"id": 76, "epoch": 0, "step": 76, "loss": 0.5557}
+{"id": 77, "epoch": 0, "step": 77, "loss": 0.5242}
+{"id": 78, "epoch": 0, "step": 78, "loss": 0.4996}
+{"id": 79, "epoch": 0, "step": 79, "loss": 0.4207}
+{"id": 80, "epoch": 0, "step": 80, "loss": 0.4312}
+{"id": 81, "epoch": 0, "step": 81, "loss": 0.4713}
+{"id": 82, "epoch": 0, "step": 82, "loss": 0.5011}
+{"id": 83, "epoch": 0, "step": 83, "loss": 0.5013}
+{"id": 84, "epoch": 0, "step": 84, "loss": 0.4825}
+{"id": 85, "epoch": 0, "step": 85, "loss": 0.4709}
+{"id": 86, "epoch": 0, "step": 86, "loss": 0.619}
+{"id": 87, "epoch": 0, "step": 87, "loss": 0.4694}
+{"id": 88, "epoch": 0, "step": 88, "loss": 0.5003}
+{"id": 89, "epoch": 0, "step": 89, "loss": 0.5136}
+{"id": 90, "epoch": 0, "step": 90, "loss": 0.4647}
+{"id": 91, "epoch": 0, "step": 91, "loss": 0.5272}
+{"id": 92, "epoch": 0, "step": 92, "loss": 0.462}
+{"id": 93, "epoch": 0, "step": 93, "loss": 0.4461}
+{"id": 94, "epoch": 0, "step": 94, "loss": 0.5165}
+{"id": 95, "epoch": 0, "step": 95, "loss": 0.5301}
+{"id": 96, "epoch": 0, "step": 96, "loss": 0.4558}
+{"id": 97, "epoch": 0, "step": 97, "loss": 0.4573}
+{"id": 98, "epoch": 0, "step": 98, "loss": 0.4898}
+{"id": 99, "epoch": 0, "step": 99, "loss": 0.5059}
+{"id": 100, "epoch": 0, "step": 100, "loss": 0.5004}
+{"id": 101, "epoch": 0, "step": 101, "loss": 0.5079}
+{"id": 102, "epoch": 0, "step": 102, "loss": 0.5067}
+{"id": 103, "epoch": 0, "step": 103, "loss": 0.4367}
+{"id": 104, "epoch": 0, "step": 104, "loss": 0.4238}
+{"id": 105, "epoch": 0, "step": 105, "loss": 0.5456}
+{"id": 106, "epoch": 0, "step": 106, "loss": 0.5062}
+{"id": 107, "epoch": 0, "step": 107, "loss": 0.5327}
+{"id": 108, "epoch": 0, "step": 108, "loss": 0.4935}
+{"id": 109, "epoch": 0, "step": 109, "loss": 0.4853}
+{"id": 110, "epoch": 0, "step": 110, "loss": 0.5342}
+{"id": 111, "epoch": 0, "step": 111, "loss": 0.4825}
+{"id": 112, "epoch": 0, "step": 112, "loss": 0.5138}
+{"id": 113, "epoch": 0, "step": 113, "loss": 0.4957}
+{"id": 114, "epoch": 0, "step": 114, "loss": 0.4918}
+{"id": 115, "epoch": 0, "step": 115, "loss": 0.516}
+{"id": 116, "epoch": 0, "step": 116, "loss": 0.5405}
+{"id": 117, "epoch": 0, "step": 117, "loss": 0.547}
+{"id": 118, "epoch": 0, "step": 118, "loss": 0.5264}
+{"id": 119, "epoch": 0, "step": 119, "loss": 0.4834}
+{"id": 120, "epoch": 0, "step": 120, "loss": 0.5188}
+{"id": 121, "epoch": 0, "step": 121, "loss": 0.5197}
+{"id": 122, "epoch": 0, "step": 122, "loss": 0.5111}
+{"id": 123, "epoch": 0, "step": 123, "loss": 0.4809}
+{"id": 124, "epoch": 0, "step": 124, "loss": 0.5586}
+{"id": 125, "epoch": 0, "step": 125, "loss": 0.5358}
+{"id": 126, "epoch": 0, "step": 126, "loss": 0.562}
+{"id": 127, "epoch": 0, "step": 127, "loss": 0.4812}
+{"id": 128, "epoch": 0, "step": 128, "loss": 0.4741}
+{"id": 129, "epoch": 0, "step": 129, "loss": 0.4452}
+{"id": 130, "epoch": 0, "step": 130, "loss": 0.4477}
+{"id": 131, "epoch": 0, "step": 131, "loss": 0.4574}
+{"id": 132, "epoch": 0, "step": 132, "loss": 0.4881}
+{"id": 133, "epoch": 0, "step": 133, "loss": 0.5033}
+{"id": 134, "epoch": 0, "step": 134, "loss": 0.5014}
+{"id": 135, "epoch": 0, "step": 135, "loss": 0.4896}
+{"id": 136, "epoch": 0, "step": 136, "loss": 0.5213}
+{"id": 137, "epoch": 0, "step": 137, "loss": 0.4615}
+{"id": 138, "epoch": 0, "step": 138, "loss": 0.5058}
+{"id": 139, "epoch": 0, "step": 139, "loss": 0.443}
+{"id": 140, "epoch": 0, "step": 140, "loss": 0.4769}
+{"id": 141, "epoch": 0, "step": 141, "loss": 0.4702}
+{"id": 142, "epoch": 0, "step": 142, "loss": 0.4832}
+{"id": 143, "epoch": 0, "step": 143, "loss": 0.4859}
+{"id": 144, "epoch": 0, "step": 144, "loss": 0.4495}
+{"id": 145, "epoch": 0, "step": 145, "loss": 0.4727}
+{"id": 146, "epoch": 0, "step": 146, "loss": 0.4856}
+{"id": 147, "epoch": 0, "step": 147, "loss": 0.4114}
+{"id": 148, "epoch": 0, "step": 148, "loss": 0.5234}
+{"id": 149, "epoch": 0, "step": 149, "loss": 0.5212}
+{"id": 150, "epoch": 0, "step": 150, "loss": 0.4943}
+{"id": 151, "epoch": 0, "step": 151, "loss": 0.4811}
+{"id": 152, "epoch": 0, "step": 152, "loss": 0.5283}
+{"id": 153, "epoch": 0, "step": 153, "loss": 0.5182}
+{"id": 154, "epoch": 0, "step": 154, "loss": 0.4537}
+{"id": 155, "epoch": 0, "step": 155, "loss": 0.5374}
+{"id": 156, "epoch": 0, "step": 156, "loss": 0.5172}
+{"id": 157, "epoch": 0, "step": 157, "loss": 0.4927}
+{"id": 158, "epoch": 0, "step": 158, "loss": 0.4435}
+{"id": 159, "epoch": 0, "step": 159, "loss": 0.4729}
+{"id": 160, "epoch": 0, "step": 160, "loss": 0.4822}
+{"id": 161, "epoch": 0, "step": 161, "loss": 0.5067}
+{"id": 162, "epoch": 0, "step": 162, "loss": 0.4739}
+{"id": 163, "epoch": 0, "step": 163, "loss": 0.4697}
+{"id": 164, "epoch": 0, "step": 164, "loss": 0.4023}
+{"id": 165, "epoch": 0, "step": 165, "loss": 0.4539}
+{"id": 166, "epoch": 0, "step": 166, "loss": 0.4969}
+{"id": 167, "epoch": 0, "step": 167, "loss": 0.5369}
+{"id": 168, "epoch": 0, "step": 168, "loss": 0.4608}
+{"id": 169, "epoch": 0, "step": 169, "loss": 0.4865}
+{"id": 170, "epoch": 0, "step": 170, "loss": 0.4708}
+{"id": 171, "epoch": 0, "step": 171, "loss": 0.472}
+{"id": 172, "epoch": 0, "step": 172, "loss": 0.5016}
+{"id": 173, "epoch": 0, "step": 173, "loss": 0.4644}
+{"id": 174, "epoch": 0, "step": 174, "loss": 0.4192}
+{"id": 175, "epoch": 0, "step": 175, "loss": 0.5235}
+{"id": 176, "epoch": 0, "step": 176, "loss": 0.5075}
+{"id": 177, "epoch": 0, "step": 177, "loss": 0.4836}
+{"id": 178, "epoch": 0, "step": 178, "loss": 0.4812}
+{"id": 179, "epoch": 0, "step": 179, "loss": 0.4938}
+{"id": 180, "epoch": 0, "step": 180, "loss": 0.5015}
+{"id": 181, "epoch": 0, "step": 181, "loss": 0.5133}
+{"id": 182, "epoch": 0, "step": 182, "loss": 0.4663}
+{"id": 183, "epoch": 0, "step": 183, "loss": 0.4392}
+{"id": 184, "epoch": 0, "step": 184, "loss": 0.4233}
+{"id": 185, "epoch": 0, "step": 185, "loss": 0.4493}
+{"id": 186, "epoch": 0, "step": 186, "loss": 0.4487}
+{"id": 187, "epoch": 0, "step": 187, "loss": 0.5051}
+{"id": 188, "epoch": 0, "step": 188, "loss": 0.4729}
+{"id": 189, "epoch": 0, "step": 189, "loss": 0.4566}
+{"id": 190, "epoch": 0, "step": 190, "loss": 0.4826}
+{"id": 191, "epoch": 0, "step": 191, "loss": 0.5356}
+{"id": 192, "epoch": 0, "step": 192, "loss": 0.4834}
+{"id": 193, "epoch": 0, "step": 193, "loss": 0.5343}
+{"id": 194, "epoch": 0, "step": 194, "loss": 0.4904}
+{"id": 195, "epoch": 0, "step": 195, "loss": 0.466}
+{"id": 196, "epoch": 0, "step": 196, "loss": 0.4875}
+{"id": 197, "epoch": 0, "step": 197, "loss": 0.4303}
+{"id": 198, "epoch": 0, "step": 198, "loss": 0.5339}
+{"id": 199, "epoch": 0, "step": 199, "loss": 0.4818}
+{"id": 200, "epoch": 0, "step": 200, "loss": 0.5396}
+{"id": 201, "epoch": 0, "step": 201, "loss": 0.5067}
+{"id": 202, "epoch": 0, "step": 202, "loss": 0.4473}
+{"id": 203, "epoch": 0, "step": 203, "loss": 0.5178}
+{"id": 204, "epoch": 0, "step": 204, "loss": 0.4307}
+{"id": 205, "epoch": 0, "step": 205, "loss": 0.4474}
+{"id": 206, "epoch": 0, "step": 206, "loss": 0.4782}
+{"id": 207, "epoch": 0, "step": 207, "loss": 0.4515}
+{"id": 208, "epoch": 0, "step": 208, "loss": 0.4858}
+{"id": 209, "epoch": 0, "step": 209, "loss": 0.4263}
+{"id": 210, "epoch": 0, "step": 210, "loss": 0.5042}
+{"id": 211, "epoch": 0, "step": 211, "loss": 0.4885}
+{"id": 212, "epoch": 0, "step": 212, "loss": 0.4975}
+{"id": 213, "epoch": 0, "step": 213, "loss": 0.4789}
+{"id": 214, "epoch": 0, "step": 214, "loss": 0.4202}
+{"id": 215, "epoch": 0, "step": 215, "loss": 0.5215}
+{"id": 216, "epoch": 0, "step": 216, "loss": 0.4767}
+{"id": 217, "epoch": 0, "step": 217, "loss": 0.492}
+{"id": 218, "epoch": 0, "step": 218, "loss": 0.4183}
+{"id": 219, "epoch": 0, "step": 219, "loss": 0.4606}
+{"id": 220, "epoch": 0, "step": 220, "loss": 0.5148}
+{"id": 221, "epoch": 0, "step": 221, "loss": 0.4695}
+{"id": 222, "epoch": 0, "step": 222, "loss": 0.4805}
+{"id": 223, "epoch": 0, "step": 223, "loss": 0.4602}
+{"id": 224, "epoch": 0, "step": 224, "loss": 0.4734}
+{"id": 225, "epoch": 0, "step": 225, "loss": 0.4683}
+{"id": 226, "epoch": 0, "step": 226, "loss": 0.5292}
+{"id": 227, "epoch": 0, "step": 227, "loss": 0.4708}
+{"id": 228, "epoch": 0, "step": 228, "loss": 0.4904}
+{"id": 229, "epoch": 0, "step": 229, "loss": 0.423}
+{"id": 230, "epoch": 0, "step": 230, "loss": 0.473}
+{"id": 231, "epoch": 0, "step": 231, "loss": 0.5546}
+{"id": 232, "epoch": 0, "step": 232, "loss": 0.5164}
+{"id": 233, "epoch": 0, "step": 233, "loss": 0.498}
+{"id": 234, "epoch": 0, "step": 234, "loss": 0.5241}
+{"id": 235, "epoch": 0, "step": 235, "loss": 0.477}
+{"id": 236, "epoch": 0, "step": 236, "loss": 0.4487}
+{"id": 237, "epoch": 0, "step": 237, "loss": 0.5439}
+{"id": 238, "epoch": 0, "step": 238, "loss": 0.4891}
+{"id": 239, "epoch": 0, "step": 239, "loss": 0.4793}
+{"id": 240, "epoch": 0, "step": 240, "loss": 0.5107}
+{"id": 241, "epoch": 0, "step": 241, "loss": 0.471}
+{"id": 242, "epoch": 0, "step": 242, "loss": 0.5306}
+{"id": 243, "epoch": 0, "step": 243, "loss": 0.4516}
+{"id": 244, "epoch": 0, "step": 244, "loss": 0.5359}
+{"id": 245, "epoch": 0, "step": 245, "loss": 0.4611}
+{"id": 246, "epoch": 0, "step": 246, "loss": 0.4822}
+{"id": 247, "epoch": 0, "step": 247, "loss": 0.5131}
+{"id": 248, "epoch": 0, "step": 248, "loss": 0.4792}
+{"id": 249, "epoch": 0, "step": 249, "loss": 0.4832}
+{"id": 250, "epoch": 0, "step": 250, "loss": 0.5037}
+{"id": 251, "epoch": 0, "step": 251, "loss": 0.4619}
+{"id": 252, "epoch": 0, "step": 252, "loss": 0.4832}
+{"id": 253, "epoch": 0, "step": 253, "loss": 0.4853}
+{"id": 254, "epoch": 0, "step": 254, "loss": 0.4607}
+{"id": 255, "epoch": 0, "step": 255, "loss": 0.4628}
+{"id": 256, "epoch": 0, "step": 256, "loss": 0.4715}
+{"id": 257, "epoch": 0, "step": 257, "loss": 0.4612}
+{"id": 258, "epoch": 0, "step": 258, "loss": 0.5166}
+{"id": 259, "epoch": 0, "step": 259, "loss": 0.5138}
+{"id": 260, "epoch": 0, "step": 260, "loss": 0.456}
+{"id": 261, "epoch": 0, "step": 261, "loss": 0.4338}
+{"id": 262, "epoch": 0, "step": 262, "loss": 0.4362}
+{"id": 263, "epoch": 0, "step": 263, "loss": 0.4684}
+{"id": 264, "epoch": 0, "step": 264, "loss": 0.5205}
+{"id": 265, "epoch": 0, "step": 265, "loss": 0.4644}
+{"id": 266, "epoch": 0, "step": 266, "loss": 0.4455}
+{"id": 267, "epoch": 0, "step": 267, "loss": 0.5105}
+{"id": 268, "epoch": 0, "step": 268, "loss": 0.5339}
+{"id": 269, "epoch": 0, "step": 269, "loss": 0.4588}
+{"id": 270, "epoch": 0, "step": 270, "loss": 0.4746}
+{"id": 271, "epoch": 0, "step": 271, "loss": 0.4437}
+{"id": 272, "epoch": 0, "step": 272, "loss": 0.4618}
+{"id": 273, "epoch": 0, "step": 273, "loss": 0.545}
+{"id": 274, "epoch": 0, "step": 274, "loss": 0.4887}
+{"id": 275, "epoch": 0, "step": 275, "loss": 0.4153}
+{"id": 276, "epoch": 0, "step": 276, "loss": 0.4823}
+{"id": 277, "epoch": 0, "step": 277, "loss": 0.484}
+{"id": 278, "epoch": 0, "step": 278, "loss": 0.5211}
+{"id": 279, "epoch": 0, "step": 279, "loss": 0.4654}
+{"id": 280, "epoch": 0, "step": 280, "loss": 0.5032}
+{"id": 281, "epoch": 0, "step": 281, "loss": 0.4503}
+{"id": 282, "epoch": 0, "step": 282, "loss": 0.4401}
+{"id": 283, "epoch": 0, "step": 283, "loss": 0.4403}
+{"id": 284, "epoch": 0, "step": 284, "loss": 0.4968}
+{"id": 285, "epoch": 0, "step": 285, "loss": 0.5029}
+{"id": 286, "epoch": 0, "step": 286, "loss": 0.5303}
+{"id": 287, "epoch": 0, "step": 287, "loss": 0.4459}
+{"id": 288, "epoch": 0, "step": 288, "loss": 0.4949}
+{"id": 289, "epoch": 0, "step": 289, "loss": 0.499}
+{"id": 290, "epoch": 0, "step": 290, "loss": 0.4818}
+{"id": 291, "epoch": 0, "step": 291, "loss": 0.4564}
+{"id": 292, "epoch": 0, "step": 292, "loss": 0.4705}
+{"id": 293, "epoch": 0, "step": 293, "loss": 0.475}
+{"id": 294, "epoch": 0, "step": 294, "loss": 0.4356}
+{"id": 295, "epoch": 0, "step": 295, "loss": 0.4709}
+{"id": 296, "epoch": 0, "step": 296, "loss": 0.4639}
+{"id": 297, "epoch": 0, "step": 297, "loss": 0.4597}
+{"id": 298, "epoch": 0, "step": 298, "loss": 0.4599}
+{"id": 299, "epoch": 0, "step": 299, "loss": 0.4078}
+{"id": 300, "epoch": 0, "step": 300, "loss": 0.4714}
+{"id": 301, "epoch": 0, "step": 301, "loss": 0.4708}
+{"id": 302, "epoch": 0, "step": 302, "loss": 0.4954}
+{"id": 303, "epoch": 0, "step": 303, "loss": 0.4518}
+{"id": 304, "epoch": 0, "step": 304, "loss": 0.5203}
+{"id": 305, "epoch": 0, "step": 305, "loss": 0.4662}
+{"id": 306, "epoch": 0, "step": 306, "loss": 0.5002}
+{"id": 307, "epoch": 0, "step": 307, "loss": 0.4995}
+{"id": 308, "epoch": 0, "step": 308, "loss": 0.5407}
+{"id": 309, "epoch": 0, "step": 309, "loss": 0.5337}
+{"id": 310, "epoch": 0, "step": 310, "loss": 0.5063}
+{"id": 311, "epoch": 0, "step": 311, "loss": 0.4725}
+{"id": 312, "epoch": 0, "step": 312, "loss": 0.4961}
+{"id": 313, "epoch": 0, "step": 313, "loss": 0.4836}
+{"id": 314, "epoch": 0, "step": 314, "loss": 0.4664}
+{"id": 315, "epoch": 0, "step": 315, "loss": 0.449}
+{"id": 316, "epoch": 0, "step": 316, "loss": 0.4466}
+{"id": 317, "epoch": 0, "step": 317, "loss": 0.441}
+{"id": 318, "epoch": 0, "step": 318, "loss": 0.4559}
+{"id": 319, "epoch": 0, "step": 319, "loss": 0.5072}
+{"id": 320, "epoch": 0, "step": 320, "loss": 0.4765}
+{"id": 321, "epoch": 0, "step": 321, "loss": 0.5534}
+{"id": 322, "epoch": 0, "step": 322, "loss": 0.4671}
+{"id": 323, "epoch": 0, "step": 323, "loss": 0.4875}
+{"id": 324, "epoch": 0, "step": 324, "loss": 0.524}
+{"id": 325, "epoch": 0, "step": 325, "loss": 0.4739}
+{"id": 326, "epoch": 0, "step": 326, "loss": 0.4917}
+{"id": 327, "epoch": 0, "step": 327, "loss": 0.4458}
+{"id": 328, "epoch": 0, "step": 328, "loss": 0.4687}
+{"id": 329, "epoch": 0, "step": 329, "loss": 0.4223}
+{"id": 330, "epoch": 0, "step": 330, "loss": 0.4905}
+{"id": 331, "epoch": 0, "step": 331, "loss": 0.4892}
+{"id": 332, "epoch": 0, "step": 332, "loss": 0.4727}
+{"id": 333, "epoch": 0, "step": 333, "loss": 0.4777}
+{"id": 334, "epoch": 0, "step": 334, "loss": 0.4778}
+{"id": 335, "epoch": 0, "step": 335, "loss": 0.5155}
+{"id": 336, "epoch": 0, "step": 336, "loss": 0.4477}
+{"id": 337, "epoch": 0, "step": 337, "loss": 0.5178}
+{"id": 338, "epoch": 0, "step": 338, "loss": 0.4698}
+{"id": 339, "epoch": 0, "step": 339, "loss": 0.4057}
+{"id": 340, "epoch": 0, "step": 340, "loss": 0.5287}
+{"id": 341, "epoch": 0, "step": 341, "loss": 0.4733}
+{"id": 342, "epoch": 0, "step": 342, "loss": 0.484}
+{"id": 343, "epoch": 0, "step": 343, "loss": 0.5252}
+{"id": 344, "epoch": 0, "step": 344, "loss": 0.475}
+{"id": 345, "epoch": 0, "step": 345, "loss": 0.4877}
+{"id": 346, "epoch": 0, "step": 346, "loss": 0.4263}
+{"id": 347, "epoch": 0, "step": 347, "loss": 0.5322}
+{"id": 348, "epoch": 0, "step": 348, "loss": 0.4672}
+{"id": 349, "epoch": 0, "step": 349, "loss": 0.4971}
+{"id": 350, "epoch": 0, "step": 350, "loss": 0.4686}
+{"id": 351, "epoch": 0, "step": 351, "loss": 0.5078}
+{"id": 352, "epoch": 0, "step": 352, "loss": 0.4813}
+{"id": 353, "epoch": 0, "step": 353, "loss": 0.4786}
+{"id": 354, "epoch": 0, "step": 354, "loss": 0.5113}
+{"id": 355, "epoch": 0, "step": 355, "loss": 0.4834}
+{"id": 356, "epoch": 0, "step": 356, "loss": 0.4891}
+{"id": 357, "epoch": 0, "step": 357, "loss": 0.5101}
+{"id": 358, "epoch": 0, "step": 358, "loss": 0.429}
+{"id": 359, "epoch": 0, "step": 359, "loss": 0.5011}
+{"id": 360, "epoch": 0, "step": 360, "loss": 0.4389}
+{"id": 361, "epoch": 0, "step": 361, "loss": 0.4715}
+{"id": 362, "epoch": 0, "step": 362, "loss": 0.4945}
+{"id": 363, "epoch": 0, "step": 363, "loss": 0.437}
+{"id": 364, "epoch": 0, "step": 364, "loss": 0.4899}
+{"id": 365, "epoch": 0, "step": 365, "loss": 0.502}
+{"id": 366, "epoch": 0, "step": 366, "loss": 0.5003}
+{"id": 367, "epoch": 0, "step": 367, "loss": 0.4552}
+{"id": 368, "epoch": 0, "step": 368, "loss": 0.4987}
+{"id": 369, "epoch": 0, "step": 369, "loss": 0.4261}
+{"id": 370, "epoch": 0, "step": 370, "loss": 0.4528}
+{"id": 371, "epoch": 0, "step": 371, "loss": 0.5501}
+{"id": 372, "epoch": 0, "step": 372, "loss": 0.4881}
+{"id": 373, "epoch": 0, "step": 373, "loss": 0.5141}
+{"id": 374, "epoch": 0, "step": 374, "loss": 0.4951}