Upload 12 files

lora_li_V4/checkpoint-500/README.md

@@ -0,0 +1,207 @@
+---
+library_name: peft
+base_model: line-corporation/japanese-large-lm-3.6b
+---
+
+# 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]
+- **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 Data 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 Data 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]
+
+
+## Training procedure
+
+
+### Framework versions
+
+
+- PEFT 0.6.2

lora_li_V4/checkpoint-500/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "line-corporation/japanese-large-lm-3.6b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 8,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_key_value",
+    "dense"
+  ],
+  "task_type": "CAUSAL_LM"
+}

lora_li_V4/checkpoint-500/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f1ab7e561f1a64b79f60e2b50fffb2cbad9548093f9f467bfd6af7eb3d19eca
+size 283159914

lora_li_V4/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfaf7392e1fff0ce1015cf23aab61ebdfbe705f360d15071bbe49bc0e36c00bd
+size 141976826

lora_li_V4/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c272fc5304ed67bfe24007d078000308f79a9edab327db93685efcf5fa29f77
+size 14244

lora_li_V4/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afc59556725853baacb2e0ea4e5aed077edabd47f563554f434477eb7395c0f5
+size 1064

lora_li_V4/checkpoint-500/special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<cls>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

lora_li_V4/checkpoint-500/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c5c56a739832923347681ed8a03a9cbf5afb6d1fe60089a5b01dd2dd063ab71
+size 1208648

lora_li_V4/checkpoint-500/tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "additional_special_tokens": null,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<cls>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "keep_accents": true,
+  "legacy": true,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

lora_li_V4/checkpoint-500/trainer_state.json

@@ -0,0 +1,1419 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 5,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 2.3695,
+      "step": 5
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 2.5850298404693604,
+      "eval_runtime": 5.2281,
+      "eval_samples_per_second": 38.255,
+      "eval_steps_per_second": 4.782,
+      "step": 5
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 2.7683,
+      "step": 10
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 2.584818124771118,
+      "eval_runtime": 5.0659,
+      "eval_samples_per_second": 39.479,
+      "eval_steps_per_second": 4.935,
+      "step": 10
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 5e-06,
+      "loss": 2.6447,
+      "step": 15
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 2.5842080116271973,
+      "eval_runtime": 5.0838,
+      "eval_samples_per_second": 39.341,
+      "eval_steps_per_second": 4.918,
+      "step": 15
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.6589,
+      "step": 20
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 2.582965135574341,
+      "eval_runtime": 5.089,
+      "eval_samples_per_second": 39.3,
+      "eval_steps_per_second": 4.913,
+      "step": 20
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 2.9753,
+      "step": 25
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 2.580824613571167,
+      "eval_runtime": 5.0996,
+      "eval_samples_per_second": 39.219,
+      "eval_steps_per_second": 4.902,
+      "step": 25
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1e-05,
+      "loss": 2.4846,
+      "step": 30
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 2.5763349533081055,
+      "eval_runtime": 5.1156,
+      "eval_samples_per_second": 39.096,
+      "eval_steps_per_second": 4.887,
+      "step": 30
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 9.948453608247423e-06,
+      "loss": 2.9258,
+      "step": 35
+    },
+    {
+      "epoch": 0.7,
+      "eval_loss": 2.5708019733428955,
+      "eval_runtime": 5.1201,
+      "eval_samples_per_second": 39.062,
+      "eval_steps_per_second": 4.883,
+      "step": 35
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 9.896907216494846e-06,
+      "loss": 2.5006,
+      "step": 40
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 2.5632669925689697,
+      "eval_runtime": 5.1234,
+      "eval_samples_per_second": 39.036,
+      "eval_steps_per_second": 4.88,
+      "step": 40
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 9.84536082474227e-06,
+      "loss": 2.7588,
+      "step": 45
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 2.556011915206909,
+      "eval_runtime": 5.1266,
+      "eval_samples_per_second": 39.013,
+      "eval_steps_per_second": 4.877,
+      "step": 45
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.793814432989691e-06,
+      "loss": 2.9848,
+      "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.5472288131713867,
+      "eval_runtime": 5.1297,
+      "eval_samples_per_second": 38.989,
+      "eval_steps_per_second": 4.874,
+      "step": 50
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 9.742268041237114e-06,
+      "loss": 2.3716,
+      "step": 55
+    },
+    {
+      "epoch": 1.1,
+      "eval_loss": 2.5382845401763916,
+      "eval_runtime": 5.1311,
+      "eval_samples_per_second": 38.978,
+      "eval_steps_per_second": 4.872,
+      "step": 55
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 9.690721649484536e-06,
+      "loss": 2.7594,
+      "step": 60
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 2.5281271934509277,
+      "eval_runtime": 5.1316,
+      "eval_samples_per_second": 38.974,
+      "eval_steps_per_second": 4.872,
+      "step": 60
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 9.63917525773196e-06,
+      "loss": 2.602,
+      "step": 65
+    },
+    {
+      "epoch": 1.3,
+      "eval_loss": 2.516160726547241,
+      "eval_runtime": 5.1347,
+      "eval_samples_per_second": 38.951,
+      "eval_steps_per_second": 4.869,
+      "step": 65
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 9.587628865979383e-06,
+      "loss": 2.4963,
+      "step": 70
+    },
+    {
+      "epoch": 1.4,
+      "eval_loss": 2.5032336711883545,
+      "eval_runtime": 5.138,
+      "eval_samples_per_second": 38.926,
+      "eval_steps_per_second": 4.866,
+      "step": 70
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 9.536082474226806e-06,
+      "loss": 2.7859,
+      "step": 75
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 2.48720383644104,
+      "eval_runtime": 5.138,
+      "eval_samples_per_second": 38.926,
+      "eval_steps_per_second": 4.866,
+      "step": 75
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.484536082474226e-06,
+      "loss": 2.4161,
+      "step": 80
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 2.4703569412231445,
+      "eval_runtime": 5.1456,
+      "eval_samples_per_second": 38.868,
+      "eval_steps_per_second": 4.859,
+      "step": 80
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 9.43298969072165e-06,
+      "loss": 2.8719,
+      "step": 85
+    },
+    {
+      "epoch": 1.7,
+      "eval_loss": 2.453761577606201,
+      "eval_runtime": 5.1446,
+      "eval_samples_per_second": 38.876,
+      "eval_steps_per_second": 4.859,
+      "step": 85
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 9.381443298969073e-06,
+      "loss": 2.3634,
+      "step": 90
+    },
+    {
+      "epoch": 1.8,
+      "eval_loss": 2.438278913497925,
+      "eval_runtime": 5.1454,
+      "eval_samples_per_second": 38.87,
+      "eval_steps_per_second": 4.859,
+      "step": 90
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 9.329896907216496e-06,
+      "loss": 2.5588,
+      "step": 95
+    },
+    {
+      "epoch": 1.9,
+      "eval_loss": 2.423046588897705,
+      "eval_runtime": 5.1433,
+      "eval_samples_per_second": 38.885,
+      "eval_steps_per_second": 4.861,
+      "step": 95
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 9.278350515463918e-06,
+      "loss": 2.7955,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.405172348022461,
+      "eval_runtime": 5.1447,
+      "eval_samples_per_second": 38.875,
+      "eval_steps_per_second": 4.859,
+      "step": 100
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 9.226804123711341e-06,
+      "loss": 2.2443,
+      "step": 105
+    },
+    {
+      "epoch": 2.1,
+      "eval_loss": 2.3873016834259033,
+      "eval_runtime": 5.1434,
+      "eval_samples_per_second": 38.885,
+      "eval_steps_per_second": 4.861,
+      "step": 105
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 9.175257731958764e-06,
+      "loss": 2.6688,
+      "step": 110
+    },
+    {
+      "epoch": 2.2,
+      "eval_loss": 2.3680946826934814,
+      "eval_runtime": 5.1458,
+      "eval_samples_per_second": 38.867,
+      "eval_steps_per_second": 4.858,
+      "step": 110
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 9.123711340206186e-06,
+      "loss": 2.4427,
+      "step": 115
+    },
+    {
+      "epoch": 2.3,
+      "eval_loss": 2.3463919162750244,
+      "eval_runtime": 5.146,
+      "eval_samples_per_second": 38.866,
+      "eval_steps_per_second": 4.858,
+      "step": 115
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 9.072164948453609e-06,
+      "loss": 2.2864,
+      "step": 120
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 2.3245632648468018,
+      "eval_runtime": 5.1473,
+      "eval_samples_per_second": 38.855,
+      "eval_steps_per_second": 4.857,
+      "step": 120
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 9.020618556701031e-06,
+      "loss": 2.5467,
+      "step": 125
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 2.299548625946045,
+      "eval_runtime": 5.1473,
+      "eval_samples_per_second": 38.855,
+      "eval_steps_per_second": 4.857,
+      "step": 125
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 8.969072164948455e-06,
+      "loss": 2.2271,
+      "step": 130
+    },
+    {
+      "epoch": 2.6,
+      "eval_loss": 2.2739346027374268,
+      "eval_runtime": 5.1479,
+      "eval_samples_per_second": 38.851,
+      "eval_steps_per_second": 4.856,
+      "step": 130
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 8.917525773195878e-06,
+      "loss": 2.4412,
+      "step": 135
+    },
+    {
+      "epoch": 2.7,
+      "eval_loss": 2.245427370071411,
+      "eval_runtime": 5.157,
+      "eval_samples_per_second": 38.782,
+      "eval_steps_per_second": 4.848,
+      "step": 135
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 8.865979381443299e-06,
+      "loss": 2.2204,
+      "step": 140
+    },
+    {
+      "epoch": 2.8,
+      "eval_loss": 2.2146155834198,
+      "eval_runtime": 5.1536,
+      "eval_samples_per_second": 38.808,
+      "eval_steps_per_second": 4.851,
+      "step": 140
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 8.814432989690721e-06,
+      "loss": 2.3001,
+      "step": 145
+    },
+    {
+      "epoch": 2.9,
+      "eval_loss": 2.1828701496124268,
+      "eval_runtime": 5.1516,
+      "eval_samples_per_second": 38.823,
+      "eval_steps_per_second": 4.853,
+      "step": 145
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.762886597938146e-06,
+      "loss": 2.4419,
+      "step": 150
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.145841121673584,
+      "eval_runtime": 5.1498,
+      "eval_samples_per_second": 38.837,
+      "eval_steps_per_second": 4.855,
+      "step": 150
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 8.711340206185568e-06,
+      "loss": 1.9742,
+      "step": 155
+    },
+    {
+      "epoch": 3.1,
+      "eval_loss": 2.109835624694824,
+      "eval_runtime": 5.1501,
+      "eval_samples_per_second": 38.834,
+      "eval_steps_per_second": 4.854,
+      "step": 155
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 8.65979381443299e-06,
+      "loss": 2.1725,
+      "step": 160
+    },
+    {
+      "epoch": 3.2,
+      "eval_loss": 2.072678804397583,
+      "eval_runtime": 5.1497,
+      "eval_samples_per_second": 38.837,
+      "eval_steps_per_second": 4.855,
+      "step": 160
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 8.608247422680413e-06,
+      "loss": 2.0632,
+      "step": 165
+    },
+    {
+      "epoch": 3.3,
+      "eval_loss": 2.0342836380004883,
+      "eval_runtime": 5.1492,
+      "eval_samples_per_second": 38.841,
+      "eval_steps_per_second": 4.855,
+      "step": 165
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 8.556701030927836e-06,
+      "loss": 2.052,
+      "step": 170
+    },
+    {
+      "epoch": 3.4,
+      "eval_loss": 2.0019547939300537,
+      "eval_runtime": 5.1511,
+      "eval_samples_per_second": 38.827,
+      "eval_steps_per_second": 4.853,
+      "step": 170
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 8.505154639175259e-06,
+      "loss": 2.1169,
+      "step": 175
+    },
+    {
+      "epoch": 3.5,
+      "eval_loss": 1.9702200889587402,
+      "eval_runtime": 5.1502,
+      "eval_samples_per_second": 38.833,
+      "eval_steps_per_second": 4.854,
+      "step": 175
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 8.453608247422681e-06,
+      "loss": 1.895,
+      "step": 180
+    },
+    {
+      "epoch": 3.6,
+      "eval_loss": 1.9426968097686768,
+      "eval_runtime": 5.1454,
+      "eval_samples_per_second": 38.87,
+      "eval_steps_per_second": 4.859,
+      "step": 180
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 8.402061855670104e-06,
+      "loss": 2.0424,
+      "step": 185
+    },
+    {
+      "epoch": 3.7,
+      "eval_loss": 1.915299654006958,
+      "eval_runtime": 5.1477,
+      "eval_samples_per_second": 38.852,
+      "eval_steps_per_second": 4.857,
+      "step": 185
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 8.350515463917526e-06,
+      "loss": 1.918,
+      "step": 190
+    },
+    {
+      "epoch": 3.8,
+      "eval_loss": 1.8873623609542847,
+      "eval_runtime": 5.1508,
+      "eval_samples_per_second": 38.829,
+      "eval_steps_per_second": 4.854,
+      "step": 190
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 8.29896907216495e-06,
+      "loss": 1.9694,
+      "step": 195
+    },
+    {
+      "epoch": 3.9,
+      "eval_loss": 1.8603157997131348,
+      "eval_runtime": 5.1519,
+      "eval_samples_per_second": 38.821,
+      "eval_steps_per_second": 4.853,
+      "step": 195
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 8.247422680412371e-06,
+      "loss": 2.0038,
+      "step": 200
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.8306643962860107,
+      "eval_runtime": 5.1498,
+      "eval_samples_per_second": 38.837,
+      "eval_steps_per_second": 4.855,
+      "step": 200
+    },
+    {
+      "epoch": 4.1,
+      "learning_rate": 8.195876288659794e-06,
+      "loss": 1.8293,
+      "step": 205
+    },
+    {
+      "epoch": 4.1,
+      "eval_loss": 1.8058170080184937,
+      "eval_runtime": 5.1492,
+      "eval_samples_per_second": 38.841,
+      "eval_steps_per_second": 4.855,
+      "step": 205
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 8.144329896907216e-06,
+      "loss": 1.8531,
+      "step": 210
+    },
+    {
+      "epoch": 4.2,
+      "eval_loss": 1.782442331314087,
+      "eval_runtime": 5.1474,
+      "eval_samples_per_second": 38.855,
+      "eval_steps_per_second": 4.857,
+      "step": 210
+    },
+    {
+      "epoch": 4.3,
+      "learning_rate": 8.09278350515464e-06,
+      "loss": 1.773,
+      "step": 215
+    },
+    {
+      "epoch": 4.3,
+      "eval_loss": 1.7570624351501465,
+      "eval_runtime": 5.1491,
+      "eval_samples_per_second": 38.842,
+      "eval_steps_per_second": 4.855,
+      "step": 215
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 8.041237113402063e-06,
+      "loss": 1.7922,
+      "step": 220
+    },
+    {
+      "epoch": 4.4,
+      "eval_loss": 1.733828067779541,
+      "eval_runtime": 5.148,
+      "eval_samples_per_second": 38.85,
+      "eval_steps_per_second": 4.856,
+      "step": 220
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 7.989690721649486e-06,
+      "loss": 1.7672,
+      "step": 225
+    },
+    {
+      "epoch": 4.5,
+      "eval_loss": 1.7087085247039795,
+      "eval_runtime": 5.1536,
+      "eval_samples_per_second": 38.808,
+      "eval_steps_per_second": 4.851,
+      "step": 225
+    },
+    {
+      "epoch": 4.6,
+      "learning_rate": 7.938144329896907e-06,
+      "loss": 1.6826,
+      "step": 230
+    },
+    {
+      "epoch": 4.6,
+      "eval_loss": 1.6879255771636963,
+      "eval_runtime": 5.1553,
+      "eval_samples_per_second": 38.795,
+      "eval_steps_per_second": 4.849,
+      "step": 230
+    },
+    {
+      "epoch": 4.7,
+      "learning_rate": 7.886597938144331e-06,
+      "loss": 1.6726,
+      "step": 235
+    },
+    {
+      "epoch": 4.7,
+      "eval_loss": 1.6709604263305664,
+      "eval_runtime": 5.151,
+      "eval_samples_per_second": 38.827,
+      "eval_steps_per_second": 4.853,
+      "step": 235
+    },
+    {
+      "epoch": 4.8,
+      "learning_rate": 7.835051546391754e-06,
+      "loss": 1.5631,
+      "step": 240
+    },
+    {
+      "epoch": 4.8,
+      "eval_loss": 1.6577242612838745,
+      "eval_runtime": 5.1498,
+      "eval_samples_per_second": 38.836,
+      "eval_steps_per_second": 4.855,
+      "step": 240
+    },
+    {
+      "epoch": 4.9,
+      "learning_rate": 7.783505154639176e-06,
+      "loss": 1.6535,
+      "step": 245
+    },
+    {
+      "epoch": 4.9,
+      "eval_loss": 1.648335576057434,
+      "eval_runtime": 5.1527,
+      "eval_samples_per_second": 38.815,
+      "eval_steps_per_second": 4.852,
+      "step": 245
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 7.731958762886599e-06,
+      "loss": 1.6678,
+      "step": 250
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.6402533054351807,
+      "eval_runtime": 5.1556,
+      "eval_samples_per_second": 38.793,
+      "eval_steps_per_second": 4.849,
+      "step": 250
+    },
+    {
+      "epoch": 5.1,
+      "learning_rate": 7.680412371134021e-06,
+      "loss": 1.6544,
+      "step": 255
+    },
+    {
+      "epoch": 5.1,
+      "eval_loss": 1.633925437927246,
+      "eval_runtime": 5.1527,
+      "eval_samples_per_second": 38.814,
+      "eval_steps_per_second": 4.852,
+      "step": 255
+    },
+    {
+      "epoch": 5.2,
+      "learning_rate": 7.628865979381444e-06,
+      "loss": 1.6815,
+      "step": 260
+    },
+    {
+      "epoch": 5.2,
+      "eval_loss": 1.6283142566680908,
+      "eval_runtime": 5.1532,
+      "eval_samples_per_second": 38.811,
+      "eval_steps_per_second": 4.851,
+      "step": 260
+    },
+    {
+      "epoch": 5.3,
+      "learning_rate": 7.577319587628866e-06,
+      "loss": 1.5864,
+      "step": 265
+    },
+    {
+      "epoch": 5.3,
+      "eval_loss": 1.6227909326553345,
+      "eval_runtime": 5.151,
+      "eval_samples_per_second": 38.827,
+      "eval_steps_per_second": 4.853,
+      "step": 265
+    },
+    {
+      "epoch": 5.4,
+      "learning_rate": 7.525773195876289e-06,
+      "loss": 1.6057,
+      "step": 270
+    },
+    {
+      "epoch": 5.4,
+      "eval_loss": 1.617853045463562,
+      "eval_runtime": 5.1532,
+      "eval_samples_per_second": 38.811,
+      "eval_steps_per_second": 4.851,
+      "step": 270
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 7.474226804123712e-06,
+      "loss": 1.6311,
+      "step": 275
+    },
+    {
+      "epoch": 5.5,
+      "eval_loss": 1.612758755683899,
+      "eval_runtime": 5.153,
+      "eval_samples_per_second": 38.813,
+      "eval_steps_per_second": 4.852,
+      "step": 275
+    },
+    {
+      "epoch": 5.6,
+      "learning_rate": 7.422680412371135e-06,
+      "loss": 1.6224,
+      "step": 280
+    },
+    {
+      "epoch": 5.6,
+      "eval_loss": 1.6080013513565063,
+      "eval_runtime": 5.1535,
+      "eval_samples_per_second": 38.808,
+      "eval_steps_per_second": 4.851,
+      "step": 280
+    },
+    {
+      "epoch": 5.7,
+      "learning_rate": 7.3711340206185574e-06,
+      "loss": 1.6039,
+      "step": 285
+    },
+    {
+      "epoch": 5.7,
+      "eval_loss": 1.6029901504516602,
+      "eval_runtime": 5.152,
+      "eval_samples_per_second": 38.82,
+      "eval_steps_per_second": 4.853,
+      "step": 285
+    },
+    {
+      "epoch": 5.8,
+      "learning_rate": 7.319587628865979e-06,
+      "loss": 1.5567,
+      "step": 290
+    },
+    {
+      "epoch": 5.8,
+      "eval_loss": 1.597578763961792,
+      "eval_runtime": 5.1528,
+      "eval_samples_per_second": 38.814,
+      "eval_steps_per_second": 4.852,
+      "step": 290
+    },
+    {
+      "epoch": 5.9,
+      "learning_rate": 7.2680412371134026e-06,
+      "loss": 1.577,
+      "step": 295
+    },
+    {
+      "epoch": 5.9,
+      "eval_loss": 1.5921249389648438,
+      "eval_runtime": 5.152,
+      "eval_samples_per_second": 38.82,
+      "eval_steps_per_second": 4.853,
+      "step": 295
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 7.216494845360825e-06,
+      "loss": 1.5508,
+      "step": 300
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.5858511924743652,
+      "eval_runtime": 5.1516,
+      "eval_samples_per_second": 38.823,
+      "eval_steps_per_second": 4.853,
+      "step": 300
+    },
+    {
+      "epoch": 6.1,
+      "learning_rate": 7.164948453608248e-06,
+      "loss": 1.5157,
+      "step": 305
+    },
+    {
+      "epoch": 6.1,
+      "eval_loss": 1.5796844959259033,
+      "eval_runtime": 5.1529,
+      "eval_samples_per_second": 38.813,
+      "eval_steps_per_second": 4.852,
+      "step": 305
+    },
+    {
+      "epoch": 6.2,
+      "learning_rate": 7.113402061855671e-06,
+      "loss": 1.5272,
+      "step": 310
+    },
+    {
+      "epoch": 6.2,
+      "eval_loss": 1.573445439338684,
+      "eval_runtime": 5.1521,
+      "eval_samples_per_second": 38.819,
+      "eval_steps_per_second": 4.852,
+      "step": 310
+    },
+    {
+      "epoch": 6.3,
+      "learning_rate": 7.061855670103094e-06,
+      "loss": 1.5893,
+      "step": 315
+    },
+    {
+      "epoch": 6.3,
+      "eval_loss": 1.5679742097854614,
+      "eval_runtime": 5.1524,
+      "eval_samples_per_second": 38.817,
+      "eval_steps_per_second": 4.852,
+      "step": 315
+    },
+    {
+      "epoch": 6.4,
+      "learning_rate": 7.010309278350515e-06,
+      "loss": 1.5978,
+      "step": 320
+    },
+    {
+      "epoch": 6.4,
+      "eval_loss": 1.5638006925582886,
+      "eval_runtime": 5.1534,
+      "eval_samples_per_second": 38.809,
+      "eval_steps_per_second": 4.851,
+      "step": 320
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 6.958762886597939e-06,
+      "loss": 1.5482,
+      "step": 325
+    },
+    {
+      "epoch": 6.5,
+      "eval_loss": 1.560308814048767,
+      "eval_runtime": 5.1556,
+      "eval_samples_per_second": 38.793,
+      "eval_steps_per_second": 4.849,
+      "step": 325
+    },
+    {
+      "epoch": 6.6,
+      "learning_rate": 6.907216494845361e-06,
+      "loss": 1.5961,
+      "step": 330
+    },
+    {
+      "epoch": 6.6,
+      "eval_loss": 1.5574184656143188,
+      "eval_runtime": 5.156,
+      "eval_samples_per_second": 38.789,
+      "eval_steps_per_second": 4.849,
+      "step": 330
+    },
+    {
+      "epoch": 6.7,
+      "learning_rate": 6.855670103092784e-06,
+      "loss": 1.5593,
+      "step": 335
+    },
+    {
+      "epoch": 6.7,
+      "eval_loss": 1.554602861404419,
+      "eval_runtime": 5.1518,
+      "eval_samples_per_second": 38.821,
+      "eval_steps_per_second": 4.853,
+      "step": 335
+    },
+    {
+      "epoch": 6.8,
+      "learning_rate": 6.804123711340207e-06,
+      "loss": 1.5423,
+      "step": 340
+    },
+    {
+      "epoch": 6.8,
+      "eval_loss": 1.5518602132797241,
+      "eval_runtime": 5.1532,
+      "eval_samples_per_second": 38.811,
+      "eval_steps_per_second": 4.851,
+      "step": 340
+    },
+    {
+      "epoch": 6.9,
+      "learning_rate": 6.75257731958763e-06,
+      "loss": 1.5401,
+      "step": 345
+    },
+    {
+      "epoch": 6.9,
+      "eval_loss": 1.5492786169052124,
+      "eval_runtime": 5.1507,
+      "eval_samples_per_second": 38.83,
+      "eval_steps_per_second": 4.854,
+      "step": 345
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 6.701030927835052e-06,
+      "loss": 1.4929,
+      "step": 350
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.5464287996292114,
+      "eval_runtime": 5.1542,
+      "eval_samples_per_second": 38.804,
+      "eval_steps_per_second": 4.85,
+      "step": 350
+    },
+    {
+      "epoch": 7.1,
+      "learning_rate": 6.649484536082474e-06,
+      "loss": 1.5584,
+      "step": 355
+    },
+    {
+      "epoch": 7.1,
+      "eval_loss": 1.5436272621154785,
+      "eval_runtime": 5.1525,
+      "eval_samples_per_second": 38.816,
+      "eval_steps_per_second": 4.852,
+      "step": 355
+    },
+    {
+      "epoch": 7.2,
+      "learning_rate": 6.597938144329898e-06,
+      "loss": 1.5636,
+      "step": 360
+    },
+    {
+      "epoch": 7.2,
+      "eval_loss": 1.5407922267913818,
+      "eval_runtime": 5.1541,
+      "eval_samples_per_second": 38.804,
+      "eval_steps_per_second": 4.85,
+      "step": 360
+    },
+    {
+      "epoch": 7.3,
+      "learning_rate": 6.54639175257732e-06,
+      "loss": 1.4561,
+      "step": 365
+    },
+    {
+      "epoch": 7.3,
+      "eval_loss": 1.537742018699646,
+      "eval_runtime": 5.1529,
+      "eval_samples_per_second": 38.813,
+      "eval_steps_per_second": 4.852,
+      "step": 365
+    },
+    {
+      "epoch": 7.4,
+      "learning_rate": 6.494845360824743e-06,
+      "loss": 1.4441,
+      "step": 370
+    },
+    {
+      "epoch": 7.4,
+      "eval_loss": 1.5347923040390015,
+      "eval_runtime": 5.1516,
+      "eval_samples_per_second": 38.823,
+      "eval_steps_per_second": 4.853,
+      "step": 370
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 6.443298969072166e-06,
+      "loss": 1.484,
+      "step": 375
+    },
+    {
+      "epoch": 7.5,
+      "eval_loss": 1.5315654277801514,
+      "eval_runtime": 5.1519,
+      "eval_samples_per_second": 38.82,
+      "eval_steps_per_second": 4.853,
+      "step": 375
+    },
+    {
+      "epoch": 7.6,
+      "learning_rate": 6.391752577319588e-06,
+      "loss": 1.5692,
+      "step": 380
+    },
+    {
+      "epoch": 7.6,
+      "eval_loss": 1.5285476446151733,
+      "eval_runtime": 5.1526,
+      "eval_samples_per_second": 38.815,
+      "eval_steps_per_second": 4.852,
+      "step": 380
+    },
+    {
+      "epoch": 7.7,
+      "learning_rate": 6.34020618556701e-06,
+      "loss": 1.5412,
+      "step": 385
+    },
+    {
+      "epoch": 7.7,
+      "eval_loss": 1.5255026817321777,
+      "eval_runtime": 5.1513,
+      "eval_samples_per_second": 38.825,
+      "eval_steps_per_second": 4.853,
+      "step": 385
+    },
+    {
+      "epoch": 7.8,
+      "learning_rate": 6.288659793814433e-06,
+      "loss": 1.5279,
+      "step": 390
+    },
+    {
+      "epoch": 7.8,
+      "eval_loss": 1.5224711894989014,
+      "eval_runtime": 5.1532,
+      "eval_samples_per_second": 38.811,
+      "eval_steps_per_second": 4.851,
+      "step": 390
+    },
+    {
+      "epoch": 7.9,
+      "learning_rate": 6.237113402061856e-06,
+      "loss": 1.5237,
+      "step": 395
+    },
+    {
+      "epoch": 7.9,
+      "eval_loss": 1.519749402999878,
+      "eval_runtime": 5.1512,
+      "eval_samples_per_second": 38.826,
+      "eval_steps_per_second": 4.853,
+      "step": 395
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 6.185567010309279e-06,
+      "loss": 1.4892,
+      "step": 400
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.5169061422348022,
+      "eval_runtime": 5.1546,
+      "eval_samples_per_second": 38.801,
+      "eval_steps_per_second": 4.85,
+      "step": 400
+    },
+    {
+      "epoch": 8.1,
+      "learning_rate": 6.134020618556702e-06,
+      "loss": 1.5646,
+      "step": 405
+    },
+    {
+      "epoch": 8.1,
+      "eval_loss": 1.514501690864563,
+      "eval_runtime": 5.152,
+      "eval_samples_per_second": 38.82,
+      "eval_steps_per_second": 4.852,
+      "step": 405
+    },
+    {
+      "epoch": 8.2,
+      "learning_rate": 6.082474226804124e-06,
+      "loss": 1.5126,
+      "step": 410
+    },
+    {
+      "epoch": 8.2,
+      "eval_loss": 1.512241244316101,
+      "eval_runtime": 5.1565,
+      "eval_samples_per_second": 38.786,
+      "eval_steps_per_second": 4.848,
+      "step": 410
+    },
+    {
+      "epoch": 8.3,
+      "learning_rate": 6.030927835051547e-06,
+      "loss": 1.4663,
+      "step": 415
+    },
+    {
+      "epoch": 8.3,
+      "eval_loss": 1.5100592374801636,
+      "eval_runtime": 5.1535,
+      "eval_samples_per_second": 38.809,
+      "eval_steps_per_second": 4.851,
+      "step": 415
+    },
+    {
+      "epoch": 8.4,
+      "learning_rate": 5.979381443298969e-06,
+      "loss": 1.4908,
+      "step": 420
+    },
+    {
+      "epoch": 8.4,
+      "eval_loss": 1.508164644241333,
+      "eval_runtime": 5.1536,
+      "eval_samples_per_second": 38.808,
+      "eval_steps_per_second": 4.851,
+      "step": 420
+    },
+    {
+      "epoch": 8.5,
+      "learning_rate": 5.927835051546393e-06,
+      "loss": 1.462,
+      "step": 425
+    },
+    {
+      "epoch": 8.5,
+      "eval_loss": 1.5060806274414062,
+      "eval_runtime": 5.153,
+      "eval_samples_per_second": 38.813,
+      "eval_steps_per_second": 4.852,
+      "step": 425
+    },
+    {
+      "epoch": 8.6,
+      "learning_rate": 5.876288659793815e-06,
+      "loss": 1.549,
+      "step": 430
+    },
+    {
+      "epoch": 8.6,
+      "eval_loss": 1.504152536392212,
+      "eval_runtime": 5.1558,
+      "eval_samples_per_second": 38.791,
+      "eval_steps_per_second": 4.849,
+      "step": 430
+    },
+    {
+      "epoch": 8.7,
+      "learning_rate": 5.824742268041238e-06,
+      "loss": 1.4515,
+      "step": 435
+    },
+    {
+      "epoch": 8.7,
+      "eval_loss": 1.5021499395370483,
+      "eval_runtime": 5.1564,
+      "eval_samples_per_second": 38.787,
+      "eval_steps_per_second": 4.848,
+      "step": 435
+    },
+    {
+      "epoch": 8.8,
+      "learning_rate": 5.7731958762886594e-06,
+      "loss": 1.396,
+      "step": 440
+    },
+    {
+      "epoch": 8.8,
+      "eval_loss": 1.5001071691513062,
+      "eval_runtime": 5.1553,
+      "eval_samples_per_second": 38.795,
+      "eval_steps_per_second": 4.849,
+      "step": 440
+    },
+    {
+      "epoch": 8.9,
+      "learning_rate": 5.721649484536083e-06,
+      "loss": 1.5242,
+      "step": 445
+    },
+    {
+      "epoch": 8.9,
+      "eval_loss": 1.498133897781372,
+      "eval_runtime": 5.1532,
+      "eval_samples_per_second": 38.811,
+      "eval_steps_per_second": 4.851,
+      "step": 445
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 5.670103092783505e-06,
+      "loss": 1.4559,
+      "step": 450
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.4960052967071533,
+      "eval_runtime": 5.1548,
+      "eval_samples_per_second": 38.799,
+      "eval_steps_per_second": 4.85,
+      "step": 450
+    },
+    {
+      "epoch": 9.1,
+      "learning_rate": 5.618556701030928e-06,
+      "loss": 1.4769,
+      "step": 455
+    },
+    {
+      "epoch": 9.1,
+      "eval_loss": 1.4939426183700562,
+      "eval_runtime": 5.1523,
+      "eval_samples_per_second": 38.818,
+      "eval_steps_per_second": 4.852,
+      "step": 455
+    },
+    {
+      "epoch": 9.2,
+      "learning_rate": 5.567010309278351e-06,
+      "loss": 1.4452,
+      "step": 460
+    },
+    {
+      "epoch": 9.2,
+      "eval_loss": 1.4920403957366943,
+      "eval_runtime": 5.1554,
+      "eval_samples_per_second": 38.794,
+      "eval_steps_per_second": 4.849,
+      "step": 460
+    },
+    {
+      "epoch": 9.3,
+      "learning_rate": 5.515463917525774e-06,
+      "loss": 1.4912,
+      "step": 465
+    },
+    {
+      "epoch": 9.3,
+      "eval_loss": 1.4899413585662842,
+      "eval_runtime": 5.1551,
+      "eval_samples_per_second": 38.796,
+      "eval_steps_per_second": 4.85,
+      "step": 465
+    },
+    {
+      "epoch": 9.4,
+      "learning_rate": 5.463917525773196e-06,
+      "loss": 1.4724,
+      "step": 470
+    },
+    {
+      "epoch": 9.4,
+      "eval_loss": 1.4880609512329102,
+      "eval_runtime": 5.1536,
+      "eval_samples_per_second": 38.808,
+      "eval_steps_per_second": 4.851,
+      "step": 470
+    },
+    {
+      "epoch": 9.5,
+      "learning_rate": 5.412371134020619e-06,
+      "loss": 1.4435,
+      "step": 475
+    },
+    {
+      "epoch": 9.5,
+      "eval_loss": 1.4861160516738892,
+      "eval_runtime": 5.1542,
+      "eval_samples_per_second": 38.803,
+      "eval_steps_per_second": 4.85,
+      "step": 475
+    },
+    {
+      "epoch": 9.6,
+      "learning_rate": 5.360824742268042e-06,
+      "loss": 1.4529,
+      "step": 480
+    },
+    {
+      "epoch": 9.6,
+      "eval_loss": 1.4843745231628418,
+      "eval_runtime": 5.1528,
+      "eval_samples_per_second": 38.814,
+      "eval_steps_per_second": 4.852,
+      "step": 480
+    },
+    {
+      "epoch": 9.7,
+      "learning_rate": 5.309278350515464e-06,
+      "loss": 1.4757,
+      "step": 485
+    },
+    {
+      "epoch": 9.7,
+      "eval_loss": 1.4827232360839844,
+      "eval_runtime": 5.1532,
+      "eval_samples_per_second": 38.81,
+      "eval_steps_per_second": 4.851,
+      "step": 485
+    },
+    {
+      "epoch": 9.8,
+      "learning_rate": 5.257731958762888e-06,
+      "loss": 1.4765,
+      "step": 490
+    },
+    {
+      "epoch": 9.8,
+      "eval_loss": 1.4811526536941528,
+      "eval_runtime": 5.1549,
+      "eval_samples_per_second": 38.798,
+      "eval_steps_per_second": 4.85,
+      "step": 490
+    },
+    {
+      "epoch": 9.9,
+      "learning_rate": 5.20618556701031e-06,
+      "loss": 1.4903,
+      "step": 495
+    },
+    {
+      "epoch": 9.9,
+      "eval_loss": 1.4798364639282227,
+      "eval_runtime": 5.155,
+      "eval_samples_per_second": 38.797,
+      "eval_steps_per_second": 4.85,
+      "step": 495
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 5.154639175257732e-06,
+      "loss": 1.4216,
+      "step": 500
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.4785280227661133,
+      "eval_runtime": 5.1555,
+      "eval_samples_per_second": 38.793,
+      "eval_steps_per_second": 4.849,
+      "step": 500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1000,
+  "num_train_epochs": 20,
+  "save_steps": 10,
+  "total_flos": 1.6467958322823168e+16,
+  "trial_name": null,
+  "trial_params": null
+}

lora_li_V4/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:682680722ea73dfeecdb65ef4dbb5fbb672093b6e16e38495cd84e8d965b2ae1
+size 4472