Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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

README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/qwen2.5-7b-instruct-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/qwen2.5-7b-instruct-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen2.5-7b-instruct-bnb-4bit",
+  "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,
+  "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",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f9d91724cfada56ffd69d1c8fd78fe2cd949b9b2b1396df9aef072f3d8ae8d8
+size 645975704

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 %}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
+size 11422356

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,502 @@
+{
+  "best_global_step": 1200,
+  "best_metric": 0.2331986129283905,
+  "best_model_checkpoint": "/scratch/hk4488/SVG-Generation/outputs/svg_sft_v2/checkpoint-1200",
+  "epoch": 1.315919374742904,
+  "eval_steps": 200,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.021938845468257234,
+      "grad_norm": 0.14227350056171417,
+      "learning_rate": 1.9e-05,
+      "loss": 0.6225212097167969,
+      "step": 20
+    },
+    {
+      "epoch": 0.04387769093651447,
+      "grad_norm": 0.10197694599628448,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.445261812210083,
+      "step": 40
+    },
+    {
+      "epoch": 0.0658165364047717,
+      "grad_norm": 0.0512363500893116,
+      "learning_rate": 5.9e-05,
+      "loss": 0.3574248790740967,
+      "step": 60
+    },
+    {
+      "epoch": 0.08775538187302893,
+      "grad_norm": 0.0563778318464756,
+      "learning_rate": 7.900000000000001e-05,
+      "loss": 0.3272172212600708,
+      "step": 80
+    },
+    {
+      "epoch": 0.10969422734128617,
+      "grad_norm": 0.08214055001735687,
+      "learning_rate": 9.900000000000001e-05,
+      "loss": 0.31246020793914797,
+      "step": 100
+    },
+    {
+      "epoch": 0.1316330728095434,
+      "grad_norm": 0.09033175557851791,
+      "learning_rate": 9.998718148881854e-05,
+      "loss": 0.30087225437164306,
+      "step": 120
+    },
+    {
+      "epoch": 0.15357191827780062,
+      "grad_norm": 0.09569519013166428,
+      "learning_rate": 9.994599922823862e-05,
+      "loss": 0.28826444149017333,
+      "step": 140
+    },
+    {
+      "epoch": 0.17551076374605787,
+      "grad_norm": 0.0767015665769577,
+      "learning_rate": 9.987644110531813e-05,
+      "loss": 0.30547878742218015,
+      "step": 160
+    },
+    {
+      "epoch": 0.1974496092143151,
+      "grad_norm": 0.07112172991037369,
+      "learning_rate": 9.977854663817161e-05,
+      "loss": 0.28853645324707033,
+      "step": 180
+    },
+    {
+      "epoch": 0.21938845468257234,
+      "grad_norm": 0.09182991087436676,
+      "learning_rate": 9.965237144366463e-05,
+      "loss": 0.28967244625091554,
+      "step": 200
+    },
+    {
+      "epoch": 0.21938845468257234,
+      "eval_loss": 0.27366939187049866,
+      "eval_runtime": 78.78,
+      "eval_samples_per_second": 4.227,
+      "eval_steps_per_second": 1.066,
+      "step": 200
+    },
+    {
+      "epoch": 0.24132730015082957,
+      "grad_norm": 0.07705853879451752,
+      "learning_rate": 9.949798720581605e-05,
+      "loss": 0.29224610328674316,
+      "step": 220
+    },
+    {
+      "epoch": 0.2632661456190868,
+      "grad_norm": 0.07098541408777237,
+      "learning_rate": 9.931548163507207e-05,
+      "loss": 0.276334285736084,
+      "step": 240
+    },
+    {
+      "epoch": 0.28520499108734404,
+      "grad_norm": 0.07781675457954407,
+      "learning_rate": 9.910495841847541e-05,
+      "loss": 0.2759185075759888,
+      "step": 260
+    },
+    {
+      "epoch": 0.30714383655560124,
+      "grad_norm": 0.08888023346662521,
+      "learning_rate": 9.886653716075723e-05,
+      "loss": 0.27445273399353026,
+      "step": 280
+    },
+    {
+      "epoch": 0.3290826820238585,
+      "grad_norm": 0.06509074568748474,
+      "learning_rate": 9.860035331638622e-05,
+      "loss": 0.2757601737976074,
+      "step": 300
+    },
+    {
+      "epoch": 0.35102152749211574,
+      "grad_norm": 0.09211590141057968,
+      "learning_rate": 9.830655811261269e-05,
+      "loss": 0.27563354969024656,
+      "step": 320
+    },
+    {
+      "epoch": 0.372960372960373,
+      "grad_norm": 0.07276469469070435,
+      "learning_rate": 9.79853184635516e-05,
+      "loss": 0.27464828491210935,
+      "step": 340
+    },
+    {
+      "epoch": 0.3948992184286302,
+      "grad_norm": 0.08323675394058228,
+      "learning_rate": 9.763681687535361e-05,
+      "loss": 0.27996742725372314,
+      "step": 360
+    },
+    {
+      "epoch": 0.41683806389688743,
+      "grad_norm": 0.06468376517295837,
+      "learning_rate": 9.726125134251768e-05,
+      "loss": 0.26534523963928225,
+      "step": 380
+    },
+    {
+      "epoch": 0.4387769093651447,
+      "grad_norm": 0.07151263952255249,
+      "learning_rate": 9.68588352354043e-05,
+      "loss": 0.2829176664352417,
+      "step": 400
+    },
+    {
+      "epoch": 0.4387769093651447,
+      "eval_loss": 0.258375346660614,
+      "eval_runtime": 77.8053,
+      "eval_samples_per_second": 4.28,
+      "eval_steps_per_second": 1.08,
+      "step": 400
+    },
+    {
+      "epoch": 0.4607157548334019,
+      "grad_norm": 0.08009252697229385,
+      "learning_rate": 9.642979717901318e-05,
+      "loss": 0.26982746124267576,
+      "step": 420
+    },
+    {
+      "epoch": 0.48265460030165913,
+      "grad_norm": 0.06844024360179901,
+      "learning_rate": 9.597438092309434e-05,
+      "loss": 0.2733712911605835,
+      "step": 440
+    },
+    {
+      "epoch": 0.5045934457699164,
+      "grad_norm": 0.0659785270690918,
+      "learning_rate": 9.549284520366639e-05,
+      "loss": 0.2664241552352905,
+      "step": 460
+    },
+    {
+      "epoch": 0.5265322912381736,
+      "grad_norm": 0.07495546340942383,
+      "learning_rate": 9.498546359602058e-05,
+      "loss": 0.25587546825408936,
+      "step": 480
+    },
+    {
+      "epoch": 0.5484711367064308,
+      "grad_norm": 0.06304614990949631,
+      "learning_rate": 9.445252435929433e-05,
+      "loss": 0.2597985744476318,
+      "step": 500
+    },
+    {
+      "epoch": 0.5704099821746881,
+      "grad_norm": 0.061547983437776566,
+      "learning_rate": 9.389433027270216e-05,
+      "loss": 0.2667828559875488,
+      "step": 520
+    },
+    {
+      "epoch": 0.5923488276429453,
+      "grad_norm": 0.121893972158432,
+      "learning_rate": 9.331119846351766e-05,
+      "loss": 0.2628504514694214,
+      "step": 540
+    },
+    {
+      "epoch": 0.6142876731112025,
+      "grad_norm": 0.06609015166759491,
+      "learning_rate": 9.27034602269036e-05,
+      "loss": 0.2580559492111206,
+      "step": 560
+    },
+    {
+      "epoch": 0.6362265185794598,
+      "grad_norm": 0.06037086248397827,
+      "learning_rate": 9.207146083769294e-05,
+      "loss": 0.257999324798584,
+      "step": 580
+    },
+    {
+      "epoch": 0.658165364047717,
+      "grad_norm": 0.06207006052136421,
+      "learning_rate": 9.141555935422756e-05,
+      "loss": 0.25744664669036865,
+      "step": 600
+    },
+    {
+      "epoch": 0.658165364047717,
+      "eval_loss": 0.24755167961120605,
+      "eval_runtime": 77.8144,
+      "eval_samples_per_second": 4.279,
+      "eval_steps_per_second": 1.079,
+      "step": 600
+    },
+    {
+      "epoch": 0.6801042095159742,
+      "grad_norm": 0.06428562849760056,
+      "learning_rate": 9.073612841436621e-05,
+      "loss": 0.26201529502868653,
+      "step": 620
+    },
+    {
+      "epoch": 0.7020430549842315,
+      "grad_norm": 0.06118078902363777,
+      "learning_rate": 9.003355402377736e-05,
+      "loss": 0.2533463954925537,
+      "step": 640
+    },
+    {
+      "epoch": 0.7239819004524887,
+      "grad_norm": 0.07041861861944199,
+      "learning_rate": 8.93082353366375e-05,
+      "loss": 0.26145546436309813,
+      "step": 660
+    },
+    {
+      "epoch": 0.745920745920746,
+      "grad_norm": 0.07119100540876389,
+      "learning_rate": 8.856058442885934e-05,
+      "loss": 0.24657819271087647,
+      "step": 680
+    },
+    {
+      "epoch": 0.7678595913890032,
+      "grad_norm": 0.06876585632562637,
+      "learning_rate": 8.779102606397887e-05,
+      "loss": 0.2610438823699951,
+      "step": 700
+    },
+    {
+      "epoch": 0.7897984368572604,
+      "grad_norm": 0.07696516066789627,
+      "learning_rate": 8.699999745183391e-05,
+      "loss": 0.2537281274795532,
+      "step": 720
+    },
+    {
+      "epoch": 0.8117372823255177,
+      "grad_norm": 0.06649173051118851,
+      "learning_rate": 8.618794800017189e-05,
+      "loss": 0.25040783882141116,
+      "step": 740
+    },
+    {
+      "epoch": 0.8336761277937749,
+      "grad_norm": 0.06621742248535156,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.2587742805480957,
+      "step": 760
+    },
+    {
+      "epoch": 0.8556149732620321,
+      "grad_norm": 0.06762684881687164,
+      "learning_rate": 8.450264366011475e-05,
+      "loss": 0.2528057336807251,
+      "step": 780
+    },
+    {
+      "epoch": 0.8775538187302894,
+      "grad_norm": 0.07194508612155914,
+      "learning_rate": 8.363034624508475e-05,
+      "loss": 0.25876269340515134,
+      "step": 800
+    },
+    {
+      "epoch": 0.8775538187302894,
+      "eval_loss": 0.2410527616739273,
+      "eval_runtime": 78.1022,
+      "eval_samples_per_second": 4.264,
+      "eval_steps_per_second": 1.076,
+      "step": 800
+    },
+    {
+      "epoch": 0.8994926641985466,
+      "grad_norm": 0.06729619204998016,
+      "learning_rate": 8.273894239329778e-05,
+      "loss": 0.24897451400756837,
+      "step": 820
+    },
+    {
+      "epoch": 0.9214315096668038,
+      "grad_norm": 0.061502765864133835,
+      "learning_rate": 8.182893853877018e-05,
+      "loss": 0.25374341011047363,
+      "step": 840
+    },
+    {
+      "epoch": 0.9433703551350611,
+      "grad_norm": 0.058828603476285934,
+      "learning_rate": 8.09008516827534e-05,
+      "loss": 0.25022833347320556,
+      "step": 860
+    },
+    {
+      "epoch": 0.9653092006033183,
+      "grad_norm": 0.07917571067810059,
+      "learning_rate": 7.995520910000965e-05,
+      "loss": 0.24162437915802001,
+      "step": 880
+    },
+    {
+      "epoch": 0.9872480460715755,
+      "grad_norm": 0.06906663626432419,
+      "learning_rate": 7.899254803925081e-05,
+      "loss": 0.2524584770202637,
+      "step": 900
+    },
+    {
+      "epoch": 1.008775538187303,
+      "grad_norm": 0.06018976867198944,
+      "learning_rate": 7.801341541791102e-05,
+      "loss": 0.24264614582061766,
+      "step": 920
+    },
+    {
+      "epoch": 1.0307143836555601,
+      "grad_norm": 0.06674794107675552,
+      "learning_rate": 7.701836751142583e-05,
+      "loss": 0.23144776821136476,
+      "step": 940
+    },
+    {
+      "epoch": 1.0526532291238173,
+      "grad_norm": 0.06158677116036415,
+      "learning_rate": 7.600796963719511e-05,
+      "loss": 0.24413840770721434,
+      "step": 960
+    },
+    {
+      "epoch": 1.0745920745920745,
+      "grad_norm": 0.06630289554595947,
+      "learning_rate": 7.498279583340874e-05,
+      "loss": 0.23648512363433838,
+      "step": 980
+    },
+    {
+      "epoch": 1.096530920060332,
+      "grad_norm": 0.061364974826574326,
+      "learning_rate": 7.39434285329178e-05,
+      "loss": 0.25753345489501955,
+      "step": 1000
+    },
+    {
+      "epoch": 1.096530920060332,
+      "eval_loss": 0.2369629442691803,
+      "eval_runtime": 78.0044,
+      "eval_samples_per_second": 4.269,
+      "eval_steps_per_second": 1.077,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1184697655285891,
+      "grad_norm": 0.06297387927770615,
+      "learning_rate": 7.289045823233657e-05,
+      "loss": 0.24016919136047363,
+      "step": 1020
+    },
+    {
+      "epoch": 1.1404086109968463,
+      "grad_norm": 0.07347658276557922,
+      "learning_rate": 7.182448315656311e-05,
+      "loss": 0.2379443407058716,
+      "step": 1040
+    },
+    {
+      "epoch": 1.1623474564651035,
+      "grad_norm": 0.059618670493364334,
+      "learning_rate": 7.074610891890934e-05,
+      "loss": 0.23564295768737792,
+      "step": 1060
+    },
+    {
+      "epoch": 1.1842863019333607,
+      "grad_norm": 0.07202780246734619,
+      "learning_rate": 6.965594817703333e-05,
+      "loss": 0.23296499252319336,
+      "step": 1080
+    },
+    {
+      "epoch": 1.206225147401618,
+      "grad_norm": 0.06817714124917984,
+      "learning_rate": 6.855462028486975e-05,
+      "loss": 0.252462100982666,
+      "step": 1100
+    },
+    {
+      "epoch": 1.228163992869875,
+      "grad_norm": 0.06484023481607437,
+      "learning_rate": 6.744275094075565e-05,
+      "loss": 0.24110569953918456,
+      "step": 1120
+    },
+    {
+      "epoch": 1.2501028383381325,
+      "grad_norm": 0.05871213600039482,
+      "learning_rate": 6.6320971831952e-05,
+      "loss": 0.24410395622253417,
+      "step": 1140
+    },
+    {
+      "epoch": 1.2720416838063897,
+      "grad_norm": 0.06409748643636703,
+      "learning_rate": 6.518992027576267e-05,
+      "loss": 0.2396394729614258,
+      "step": 1160
+    },
+    {
+      "epoch": 1.293980529274647,
+      "grad_norm": 0.06916816532611847,
+      "learning_rate": 6.405023885745488e-05,
+      "loss": 0.25106277465820315,
+      "step": 1180
+    },
+    {
+      "epoch": 1.315919374742904,
+      "grad_norm": 0.06698701530694962,
+      "learning_rate": 6.290257506518655e-05,
+      "loss": 0.23651955127716065,
+      "step": 1200
+    },
+    {
+      "epoch": 1.315919374742904,
+      "eval_loss": 0.2331986129283905,
+      "eval_runtime": 78.0786,
+      "eval_samples_per_second": 4.265,
+      "eval_steps_per_second": 1.076,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2736,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 6.789060984339809e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}