Delete commodity_lora/checkpoint-800

commodity_lora/checkpoint-800/README.md

@@ -1,207 +0,0 @@
----
-base_model: Qwen/Qwen3-4B-Instruct-2507
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:Qwen/Qwen3-4B-Instruct-2507
-- 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 0.18.1

commodity_lora/checkpoint-800/adapter_config.json

@@ -1,46 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen3-4B-Instruct-2507",
-  "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": 16,
-  "lora_bias": false,
-  "lora_dropout": 0.05,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "peft_version": "0.18.1",
-  "qalora_group_size": 16,
-  "r": 64,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "down_proj",
-    "v_proj",
-    "k_proj",
-    "q_proj",
-    "up_proj",
-    "o_proj",
-    "gate_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false
-}

commodity_lora/checkpoint-800/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:283c67b762b2ff71e967897e2f604fc75f16d8bf324cf7b7c841d4ded038daff
-size 528550256

commodity_lora/checkpoint-800/added_tokens.json

@@ -1,28 +0,0 @@
-{
-  "</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
-}

commodity_lora/checkpoint-800/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ae2335beab13d0b5d6269116281c42fba0d4ec19de464fe6e54cb74c216923b5
-size 1057390923

commodity_lora/checkpoint-800/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:66ec09f675a6aa8635b98da1729c86cc6f7857c570c02142bc0d3915d10737da
-size 14645

commodity_lora/checkpoint-800/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1165dc2ed4d844ab3ea5cdb45650f45d9a46d7bbdac2b8690ed3351cb6e73aac
-size 1465

commodity_lora/checkpoint-800/special_tokens_map.json

@@ -1,31 +0,0 @@
-{
-  "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
-  }
-}

commodity_lora/checkpoint-800/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2f1298e298f2fe0059aba46f037697a339ccba45a1908780ce8ca14b45582f23
-size 11422753

commodity_lora/checkpoint-800/tokenizer_config.json

@@ -1,240 +0,0 @@
-{
-  "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,
-  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "extra_special_tokens": {},
-  "model_max_length": 1010000,
-  "pad_token": "<|endoftext|>",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
-}

commodity_lora/checkpoint-800/trainer_state.json

@@ -1,694 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.4710211591536337,
-  "eval_steps": 200,
-  "global_step": 800,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.01839926402943882,
-      "grad_norm": 0.8415894508361816,
-      "learning_rate": 5.4545454545454546e-05,
-      "loss": 0.7074,
-      "step": 10
-    },
-    {
-      "epoch": 0.03679852805887764,
-      "grad_norm": 0.291018009185791,
-      "learning_rate": 0.00011515151515151516,
-      "loss": 0.3417,
-      "step": 20
-    },
-    {
-      "epoch": 0.05519779208831647,
-      "grad_norm": 0.1942419707775116,
-      "learning_rate": 0.00017575757575757578,
-      "loss": 0.1873,
-      "step": 30
-    },
-    {
-      "epoch": 0.07359705611775529,
-      "grad_norm": 0.100527323782444,
-      "learning_rate": 0.00019998397847281548,
-      "loss": 0.1741,
-      "step": 40
-    },
-    {
-      "epoch": 0.09199632014719411,
-      "grad_norm": 0.18655213713645935,
-      "learning_rate": 0.0001998860877308941,
-      "loss": 0.1396,
-      "step": 50
-    },
-    {
-      "epoch": 0.11039558417663294,
-      "grad_norm": 0.18256014585494995,
-      "learning_rate": 0.0001996992941167792,
-      "loss": 0.1354,
-      "step": 60
-    },
-    {
-      "epoch": 0.12879484820607176,
-      "grad_norm": 0.20178623497486115,
-      "learning_rate": 0.0001994237638847428,
-      "loss": 0.1199,
-      "step": 70
-    },
-    {
-      "epoch": 0.14719411223551057,
-      "grad_norm": 0.14032356441020966,
-      "learning_rate": 0.00019905974226842613,
-      "loss": 0.139,
-      "step": 80
-    },
-    {
-      "epoch": 0.1655933762649494,
-      "grad_norm": 0.24278348684310913,
-      "learning_rate": 0.00019860755326257126,
-      "loss": 0.1095,
-      "step": 90
-    },
-    {
-      "epoch": 0.18399264029438822,
-      "grad_norm": 0.10004690289497375,
-      "learning_rate": 0.000198067599334652,
-      "loss": 0.1247,
-      "step": 100
-    },
-    {
-      "epoch": 0.20239190432382706,
-      "grad_norm": 0.1411207616329193,
-      "learning_rate": 0.0001974403610666606,
-      "loss": 0.1187,
-      "step": 110
-    },
-    {
-      "epoch": 0.22079116835326587,
-      "grad_norm": 0.20963186025619507,
-      "learning_rate": 0.00019672639672736945,
-      "loss": 0.1159,
-      "step": 120
-    },
-    {
-      "epoch": 0.23919043238270468,
-      "grad_norm": 0.12421368062496185,
-      "learning_rate": 0.00019592634177544805,
-      "loss": 0.1119,
-      "step": 130
-    },
-    {
-      "epoch": 0.2575896964121435,
-      "grad_norm": 0.3507830798625946,
-      "learning_rate": 0.0001950409082938776,
-      "loss": 0.109,
-      "step": 140
-    },
-    {
-      "epoch": 0.27598896044158233,
-      "grad_norm": 0.12496884167194366,
-      "learning_rate": 0.000194070884356167,
-      "loss": 0.097,
-      "step": 150
-    },
-    {
-      "epoch": 0.29438822447102114,
-      "grad_norm": 0.17028333246707916,
-      "learning_rate": 0.00019301713332493386,
-      "loss": 0.085,
-      "step": 160
-    },
-    {
-      "epoch": 0.31278748850046,
-      "grad_norm": 0.269582062959671,
-      "learning_rate": 0.00019188059308347476,
-      "loss": 0.1003,
-      "step": 170
-    },
-    {
-      "epoch": 0.3311867525298988,
-      "grad_norm": 0.14604653418064117,
-      "learning_rate": 0.00019066227520100952,
-      "loss": 0.1159,
-      "step": 180
-    },
-    {
-      "epoch": 0.34958601655933763,
-      "grad_norm": 0.09594413638114929,
-      "learning_rate": 0.00018936326403234125,
-      "loss": 0.1082,
-      "step": 190
-    },
-    {
-      "epoch": 0.36798528058877644,
-      "grad_norm": 0.13661913573741913,
-      "learning_rate": 0.00018798471575273443,
-      "loss": 0.1092,
-      "step": 200
-    },
-    {
-      "epoch": 0.36798528058877644,
-      "eval_loss": 0.059110600501298904,
-      "eval_runtime": 16.5945,
-      "eval_samples_per_second": 4.399,
-      "eval_steps_per_second": 2.23,
-      "step": 200
-    },
-    {
-      "eval_ner_f1": 0.0,
-      "step": 200
-    },
-    {
-      "eval_ner_precision": 0.0,
-      "step": 200
-    },
-    {
-      "eval_ner_recall": 0.0,
-      "step": 200
-    },
-    {
-      "eval_ner_f1_commodity": 0.0,
-      "step": 200
-    },
-    {
-      "epoch": 0.38638454461821525,
-      "grad_norm": 0.1869058758020401,
-      "learning_rate": 0.00018652785732886987,
-      "loss": 0.0995,
-      "step": 210
-    },
-    {
-      "epoch": 0.4047838086476541,
-      "grad_norm": 0.09933796525001526,
-      "learning_rate": 0.00018499398542679187,
-      "loss": 0.0961,
-      "step": 220
-    },
-    {
-      "epoch": 0.42318307267709293,
-      "grad_norm": 0.16164903342723846,
-      "learning_rate": 0.0001833844652578203,
-      "loss": 0.1147,
-      "step": 230
-    },
-    {
-      "epoch": 0.44158233670653174,
-      "grad_norm": 0.059403154999017715,
-      "learning_rate": 0.0001817007293634545,
-      "loss": 0.0792,
-      "step": 240
-    },
-    {
-      "epoch": 0.45998160073597055,
-      "grad_norm": 0.18221575021743774,
-      "learning_rate": 0.00017994427634035015,
-      "loss": 0.0785,
-      "step": 250
-    },
-    {
-      "epoch": 0.47838086476540936,
-      "grad_norm": 0.0980747789144516,
-      "learning_rate": 0.00017811666950650446,
-      "loss": 0.0945,
-      "step": 260
-    },
-    {
-      "epoch": 0.49678012879484823,
-      "grad_norm": 0.10701967030763626,
-      "learning_rate": 0.00017621953550983675,
-      "loss": 0.086,
-      "step": 270
-    },
-    {
-      "epoch": 0.515179392824287,
-      "grad_norm": 0.14636573195457458,
-      "learning_rate": 0.00017425456288040235,
-      "loss": 0.0824,
-      "step": 280
-    },
-    {
-      "epoch": 0.5335786568537259,
-      "grad_norm": 0.20424717664718628,
-      "learning_rate": 0.00017222350052752881,
-      "loss": 0.083,
-      "step": 290
-    },
-    {
-      "epoch": 0.5519779208831647,
-      "grad_norm": 0.18571391701698303,
-      "learning_rate": 0.00017012815618321257,
-      "loss": 0.0917,
-      "step": 300
-    },
-    {
-      "epoch": 0.5703771849126035,
-      "grad_norm": 0.145646870136261,
-      "learning_rate": 0.00016797039479315992,
-      "loss": 0.1055,
-      "step": 310
-    },
-    {
-      "epoch": 0.5887764489420423,
-      "grad_norm": 0.13823704421520233,
-      "learning_rate": 0.0001657521368569064,
-      "loss": 0.0816,
-      "step": 320
-    },
-    {
-      "epoch": 0.6071757129714811,
-      "grad_norm": 0.10453420132398605,
-      "learning_rate": 0.00016347535671848998,
-      "loss": 0.086,
-      "step": 330
-    },
-    {
-      "epoch": 0.62557497700092,
-      "grad_norm": 0.1144270971417427,
-      "learning_rate": 0.00016114208080920123,
-      "loss": 0.0873,
-      "step": 340
-    },
-    {
-      "epoch": 0.6439742410303588,
-      "grad_norm": 0.25295525789260864,
-      "learning_rate": 0.0001587543858439727,
-      "loss": 0.0959,
-      "step": 350
-    },
-    {
-      "epoch": 0.6623735050597976,
-      "grad_norm": 0.20557653903961182,
-      "learning_rate": 0.00015631439697301464,
-      "loss": 0.0884,
-      "step": 360
-    },
-    {
-      "epoch": 0.6807727690892365,
-      "grad_norm": 0.13607051968574524,
-      "learning_rate": 0.00015382428589034037,
-      "loss": 0.1075,
-      "step": 370
-    },
-    {
-      "epoch": 0.6991720331186753,
-      "grad_norm": 0.0677134320139885,
-      "learning_rate": 0.00015128626890086646,
-      "loss": 0.0853,
-      "step": 380
-    },
-    {
-      "epoch": 0.7175712971481141,
-      "grad_norm": 0.13079920411109924,
-      "learning_rate": 0.0001487026049478068,
-      "loss": 0.0883,
-      "step": 390
-    },
-    {
-      "epoch": 0.7359705611775529,
-      "grad_norm": 0.2688474953174591,
-      "learning_rate": 0.00014607559360211686,
-      "loss": 0.098,
-      "step": 400
-    },
-    {
-      "epoch": 0.7359705611775529,
-      "eval_loss": 0.09841074794530869,
-      "eval_runtime": 16.3162,
-      "eval_samples_per_second": 4.474,
-      "eval_steps_per_second": 2.268,
-      "step": 400
-    },
-    {
-      "eval_ner_f1": 0.1904761904761905,
-      "step": 400
-    },
-    {
-      "eval_ner_precision": 0.10526315789473684,
-      "step": 400
-    },
-    {
-      "eval_ner_recall": 1.0,
-      "step": 400
-    },
-    {
-      "eval_ner_f1_commodity": 0.19999999999999998,
-      "step": 400
-    },
-    {
-      "eval_ner_f1_organization": 0.0,
-      "step": 400
-    },
-    {
-      "epoch": 0.7543698252069917,
-      "grad_norm": 0.09586778283119202,
-      "learning_rate": 0.00014340757301577788,
-      "loss": 0.0798,
-      "step": 410
-    },
-    {
-      "epoch": 0.7727690892364305,
-      "grad_norm": 0.10425524413585663,
-      "learning_rate": 0.0001407009178407417,
-      "loss": 0.089,
-      "step": 420
-    },
-    {
-      "epoch": 0.7911683532658693,
-      "grad_norm": 0.13633865118026733,
-      "learning_rate": 0.00013795803711538966,
-      "loss": 0.1046,
-      "step": 430
-    },
-    {
-      "epoch": 0.8095676172953082,
-      "grad_norm": 0.10460830479860306,
-      "learning_rate": 0.00013518137212038554,
-      "loss": 0.0748,
-      "step": 440
-    },
-    {
-      "epoch": 0.827966881324747,
-      "grad_norm": 0.11895473301410675,
-      "learning_rate": 0.00013237339420583212,
-      "loss": 0.0917,
-      "step": 450
-    },
-    {
-      "epoch": 0.8463661453541859,
-      "grad_norm": 0.10228480398654938,
-      "learning_rate": 0.00012953660259166412,
-      "loss": 0.0754,
-      "step": 460
-    },
-    {
-      "epoch": 0.8647654093836247,
-      "grad_norm": 0.15550141036510468,
-      "learning_rate": 0.00012667352214323614,
-      "loss": 0.0871,
-      "step": 470
-    },
-    {
-      "epoch": 0.8831646734130635,
-      "grad_norm": 0.07745213061571121,
-      "learning_rate": 0.0001237867011240848,
-      "loss": 0.0826,
-      "step": 480
-    },
-    {
-      "epoch": 0.9015639374425023,
-      "grad_norm": 0.20176838338375092,
-      "learning_rate": 0.00012087870892786588,
-      "loss": 0.0849,
-      "step": 490
-    },
-    {
-      "epoch": 0.9199632014719411,
-      "grad_norm": 0.14597876369953156,
-      "learning_rate": 0.00011795213379148436,
-      "loss": 0.1032,
-      "step": 500
-    },
-    {
-      "epoch": 0.9383624655013799,
-      "grad_norm": 0.13878890872001648,
-      "learning_rate": 0.0001150095804914534,
-      "loss": 0.0856,
-      "step": 510
-    },
-    {
-      "epoch": 0.9567617295308187,
-      "grad_norm": 0.1053905189037323,
-      "learning_rate": 0.0001120536680255323,
-      "loss": 0.0786,
-      "step": 520
-    },
-    {
-      "epoch": 0.9751609935602575,
-      "grad_norm": 0.2514699399471283,
-      "learning_rate": 0.00010908702728170705,
-      "loss": 0.0906,
-      "step": 530
-    },
-    {
-      "epoch": 0.9935602575896965,
-      "grad_norm": 0.1553167700767517,
-      "learning_rate": 0.00010611229869658785,
-      "loss": 0.0857,
-      "step": 540
-    },
-    {
-      "epoch": 1.0110395584176632,
-      "grad_norm": 0.09016945213079453,
-      "learning_rate": 0.00010313212990530803,
-      "loss": 0.0775,
-      "step": 550
-    },
-    {
-      "epoch": 1.029438822447102,
-      "grad_norm": 0.11983165889978409,
-      "learning_rate": 0.00010014917338501618,
-      "loss": 0.0704,
-      "step": 560
-    },
-    {
-      "epoch": 1.0478380864765409,
-      "grad_norm": 0.10803485661745071,
-      "learning_rate": 9.716608409405842e-05,
-      "loss": 0.0652,
-      "step": 570
-    },
-    {
-      "epoch": 1.0662373505059797,
-      "grad_norm": 0.08216193318367004,
-      "learning_rate": 9.418551710895243e-05,
-      "loss": 0.0453,
-      "step": 580
-    },
-    {
-      "epoch": 1.0846366145354185,
-      "grad_norm": 0.21697314083576202,
-      "learning_rate": 9.121012526125626e-05,
-      "loss": 0.0554,
-      "step": 590
-    },
-    {
-      "epoch": 1.1030358785648575,
-      "grad_norm": 0.09792917966842651,
-      "learning_rate": 8.824255677643518e-05,
-      "loss": 0.0711,
-      "step": 600
-    },
-    {
-      "epoch": 1.1030358785648575,
-      "eval_loss": 0.07825087010860443,
-      "eval_runtime": 16.4391,
-      "eval_samples_per_second": 4.441,
-      "eval_steps_per_second": 2.251,
-      "step": 600
-    },
-    {
-      "eval_ner_f1": 0.19999999999999998,
-      "step": 600
-    },
-    {
-      "eval_ner_precision": 0.1111111111111111,
-      "step": 600
-    },
-    {
-      "eval_ner_recall": 1.0,
-      "step": 600
-    },
-    {
-      "eval_ner_f1_commodity": 0.19999999999999998,
-      "step": 600
-    },
-    {
-      "epoch": 1.1214351425942963,
-      "grad_norm": 0.12685388326644897,
-      "learning_rate": 8.528545291682838e-05,
-      "loss": 0.0538,
-      "step": 610
-    },
-    {
-      "epoch": 1.1398344066237351,
-      "grad_norm": 0.04482072964310646,
-      "learning_rate": 8.2341445630813e-05,
-      "loss": 0.058,
-      "step": 620
-    },
-    {
-      "epoch": 1.158233670653174,
-      "grad_norm": 0.10546564310789108,
-      "learning_rate": 7.941315521025775e-05,
-      "loss": 0.0612,
-      "step": 630
-    },
-    {
-      "epoch": 1.1766329346826128,
-      "grad_norm": 0.14681607484817505,
-      "learning_rate": 7.650318795835179e-05,
-      "loss": 0.0574,
-      "step": 640
-    },
-    {
-      "epoch": 1.1950321987120516,
-      "grad_norm": 0.10861357301473618,
-      "learning_rate": 7.361413386988378e-05,
-      "loss": 0.0556,
-      "step": 650
-    },
-    {
-      "epoch": 1.2134314627414904,
-      "grad_norm": 0.07452739030122757,
-      "learning_rate": 7.074856432603628e-05,
-      "loss": 0.0586,
-      "step": 660
-    },
-    {
-      "epoch": 1.2318307267709292,
-      "grad_norm": 0.09327604621648788,
-      "learning_rate": 6.790902980574685e-05,
-      "loss": 0.0669,
-      "step": 670
-    },
-    {
-      "epoch": 1.250229990800368,
-      "grad_norm": 0.15776699781417847,
-      "learning_rate": 6.509805761567336e-05,
-      "loss": 0.0543,
-      "step": 680
-    },
-    {
-      "epoch": 1.2686292548298068,
-      "grad_norm": 0.1362597495317459,
-      "learning_rate": 6.231814964078327e-05,
-      "loss": 0.062,
-      "step": 690
-    },
-    {
-      "epoch": 1.2870285188592456,
-      "grad_norm": 0.1402318924665451,
-      "learning_rate": 5.957178011756952e-05,
-      "loss": 0.0684,
-      "step": 700
-    },
-    {
-      "epoch": 1.3054277828886844,
-      "grad_norm": 0.09126363694667816,
-      "learning_rate": 5.6861393431874675e-05,
-      "loss": 0.066,
-      "step": 710
-    },
-    {
-      "epoch": 1.3238270469181233,
-      "grad_norm": 0.10861663520336151,
-      "learning_rate": 5.418940194328344e-05,
-      "loss": 0.0595,
-      "step": 720
-    },
-    {
-      "epoch": 1.342226310947562,
-      "grad_norm": 0.10028150677680969,
-      "learning_rate": 5.1558183838019755e-05,
-      "loss": 0.0526,
-      "step": 730
-    },
-    {
-      "epoch": 1.3606255749770009,
-      "grad_norm": 0.12535513937473297,
-      "learning_rate": 4.897008101226002e-05,
-      "loss": 0.0544,
-      "step": 740
-    },
-    {
-      "epoch": 1.3790248390064397,
-      "grad_norm": 0.0817708894610405,
-      "learning_rate": 4.6427396987745555e-05,
-      "loss": 0.067,
-      "step": 750
-    },
-    {
-      "epoch": 1.3974241030358785,
-      "grad_norm": 0.12001190334558487,
-      "learning_rate": 4.3932394861550106e-05,
-      "loss": 0.0577,
-      "step": 760
-    },
-    {
-      "epoch": 1.4158233670653173,
-      "grad_norm": 0.13876648247241974,
-      "learning_rate": 4.148729529182736e-05,
-      "loss": 0.0678,
-      "step": 770
-    },
-    {
-      "epoch": 1.4342226310947561,
-      "grad_norm": 0.07272978127002716,
-      "learning_rate": 3.909427452133016e-05,
-      "loss": 0.0654,
-      "step": 780
-    },
-    {
-      "epoch": 1.452621895124195,
-      "grad_norm": 0.11736124753952026,
-      "learning_rate": 3.675546244046228e-05,
-      "loss": 0.0683,
-      "step": 790
-    },
-    {
-      "epoch": 1.4710211591536337,
-      "grad_norm": 0.09826095402240753,
-      "learning_rate": 3.447294069158481e-05,
-      "loss": 0.0502,
-      "step": 800
-    },
-    {
-      "epoch": 1.4710211591536337,
-      "eval_loss": 0.060979194939136505,
-      "eval_runtime": 16.5781,
-      "eval_samples_per_second": 4.403,
-      "eval_steps_per_second": 2.232,
-      "step": 800
-    },
-    {
-      "eval_ner_f1": 0.2857142857142857,
-      "step": 800
-    },
-    {
-      "eval_ner_precision": 0.16666666666666666,
-      "step": 800
-    },
-    {
-      "eval_ner_recall": 1.0,
-      "step": 800
-    },
-    {
-      "eval_ner_f1_commodity": 0.2857142857142857,
-      "step": 800
-    }
-  ],
-  "logging_steps": 10,
-  "max_steps": 1086,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
-  "save_steps": 200,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 1.254286399655854e+17,
-  "train_batch_size": 2,
-  "trial_name": null,
-  "trial_params": null
-}

commodity_lora/checkpoint-800/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e204976f075a0ecfdeaf56eff02c4003fc485d15458b651f4d8199e48cedadd5
-size 5713