Upload folder using huggingface_hub

README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: Qwen/Qwen-VL-Chat
+---
+
+# 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 0.8.2

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen-VL-Chat",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "attn.c_proj",
+    "c_attn",
+    "w1",
+    "w2"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:166159c1b725cd16b6e568fe357a4d22ff97530acbfa7cfac9aabe9fb36e62f7
+size 224482573

special_tokens_map.json

@@ -0,0 +1,3 @@
+{
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "auto_map": {
+    "AutoTokenizer": [
+      "Qwen/Qwen-VL-Chat--tokenization_qwen.QWenTokenizer",
+      null
+    ]
+  },
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 1024,
+  "padding_side": "right",
+  "tokenizer_class": "QWenTokenizer"
+}

trainer_state.json

@@ -0,0 +1,952 @@
+{
+  "best_metric": 0.9140611886978149,
+  "best_model_checkpoint": "ckpt/origin/pedes_environment_v2/checkpoint-91",
+  "epoch": 4.90566037735849,
+  "eval_steps": 7,
+  "global_step": 130,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 5e-06,
+      "loss": 1.1312,
+      "step": 1
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1e-05,
+      "loss": 1.0024,
+      "step": 2
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.998494093481022e-06,
+      "loss": 1.1562,
+      "step": 3
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.993977281025862e-06,
+      "loss": 1.1379,
+      "step": 4
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.986452283393452e-06,
+      "loss": 1.0642,
+      "step": 5
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.975923633360985e-06,
+      "loss": 1.1291,
+      "step": 6
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 9.962397672993552e-06,
+      "loss": 1.0684,
+      "step": 7
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 1.0384804010391235,
+      "eval_runtime": 36.0334,
+      "eval_samples_per_second": 1.915,
+      "eval_steps_per_second": 1.915,
+      "step": 7
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.945882549823906e-06,
+      "loss": 0.9229,
+      "step": 8
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.926388211944707e-06,
+      "loss": 1.0811,
+      "step": 9
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.903926402016153e-06,
+      "loss": 0.9438,
+      "step": 10
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.878510650192644e-06,
+      "loss": 1.0043,
+      "step": 11
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.850156265972722e-06,
+      "loss": 0.9032,
+      "step": 12
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.8188803289772e-06,
+      "loss": 1.0192,
+      "step": 13
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.784701678661045e-06,
+      "loss": 1.0098,
+      "step": 14
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 0.9786658883094788,
+      "eval_runtime": 35.9159,
+      "eval_samples_per_second": 1.921,
+      "eval_steps_per_second": 1.921,
+      "step": 14
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.747640902965185e-06,
+      "loss": 0.9059,
+      "step": 15
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.707720325915105e-06,
+      "loss": 0.9866,
+      "step": 16
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 9.664963994173695e-06,
+      "loss": 0.9917,
+      "step": 17
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 9.619397662556434e-06,
+      "loss": 0.9275,
+      "step": 18
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.571048778517655e-06,
+      "loss": 0.9052,
+      "step": 19
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 9.519946465617217e-06,
+      "loss": 0.8874,
+      "step": 20
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 9.466121505977577e-06,
+      "loss": 0.978,
+      "step": 21
+    },
+    {
+      "epoch": 0.79,
+      "eval_loss": 0.9512829780578613,
+      "eval_runtime": 35.9114,
+      "eval_samples_per_second": 1.921,
+      "eval_steps_per_second": 1.921,
+      "step": 21
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.409606321741776e-06,
+      "loss": 0.9062,
+      "step": 22
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.350434955543557e-06,
+      "loss": 1.0455,
+      "step": 23
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.288643050001362e-06,
+      "loss": 0.8784,
+      "step": 24
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 9.224267826248536e-06,
+      "loss": 0.924,
+      "step": 25
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 9.157348061512728e-06,
+      "loss": 0.9133,
+      "step": 26
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 9.08792406575792e-06,
+      "loss": 0.8332,
+      "step": 27
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 9.016037657403225e-06,
+      "loss": 0.9772,
+      "step": 28
+    },
+    {
+      "epoch": 1.06,
+      "eval_loss": 0.9353252649307251,
+      "eval_runtime": 36.0706,
+      "eval_samples_per_second": 1.913,
+      "eval_steps_per_second": 1.913,
+      "step": 28
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 8.941732138133032e-06,
+      "loss": 0.8295,
+      "step": 29
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 8.865052266813686e-06,
+      "loss": 0.9754,
+      "step": 30
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 8.786044232532423e-06,
+      "loss": 0.9305,
+      "step": 31
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 8.704755626774796e-06,
+      "loss": 0.8728,
+      "step": 32
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 8.621235414757337e-06,
+      "loss": 0.9236,
+      "step": 33
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 0.9223,
+      "step": 34
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 8.447702723685335e-06,
+      "loss": 0.9838,
+      "step": 35
+    },
+    {
+      "epoch": 1.32,
+      "eval_loss": 0.9286850690841675,
+      "eval_runtime": 35.9219,
+      "eval_samples_per_second": 1.921,
+      "eval_steps_per_second": 1.921,
+      "step": 35
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 8.357794774235094e-06,
+      "loss": 0.8317,
+      "step": 36
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 8.265864214768883e-06,
+      "loss": 0.7946,
+      "step": 37
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 8.171966420818227e-06,
+      "loss": 0.9288,
+      "step": 38
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 8.076157952903134e-06,
+      "loss": 0.8589,
+      "step": 39
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 7.978496522462167e-06,
+      "loss": 0.8974,
+      "step": 40
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 7.879040957089229e-06,
+      "loss": 0.9479,
+      "step": 41
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 7.777851165098012e-06,
+      "loss": 0.8649,
+      "step": 42
+    },
+    {
+      "epoch": 1.58,
+      "eval_loss": 0.9226968288421631,
+      "eval_runtime": 36.0309,
+      "eval_samples_per_second": 1.915,
+      "eval_steps_per_second": 1.915,
+      "step": 42
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 7.674988099435487e-06,
+      "loss": 0.9145,
+      "step": 43
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 7.570513720966108e-06,
+      "loss": 0.9756,
+      "step": 44
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 7.464490961148921e-06,
+      "loss": 0.8617,
+      "step": 45
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 7.3569836841299905e-06,
+      "loss": 0.8243,
+      "step": 46
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.248056648273034e-06,
+      "loss": 0.8681,
+      "step": 47
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 7.137775467151411e-06,
+      "loss": 0.801,
+      "step": 48
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 7.026206570024949e-06,
+      "loss": 0.8676,
+      "step": 49
+    },
+    {
+      "epoch": 1.85,
+      "eval_loss": 0.9197350144386292,
+      "eval_runtime": 35.9615,
+      "eval_samples_per_second": 1.919,
+      "eval_steps_per_second": 1.919,
+      "step": 49
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 6.913417161825449e-06,
+      "loss": 0.8457,
+      "step": 50
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 6.799475182674942e-06,
+      "loss": 0.8894,
+      "step": 51
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 6.684449266961101e-06,
+      "loss": 0.8995,
+      "step": 52
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.568408701994459e-06,
+      "loss": 0.9544,
+      "step": 53
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 6.451423386272312e-06,
+      "loss": 0.8938,
+      "step": 54
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 6.333563787374493e-06,
+      "loss": 0.8898,
+      "step": 55
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 6.21490089951632e-06,
+      "loss": 0.8327,
+      "step": 56
+    },
+    {
+      "epoch": 2.11,
+      "eval_loss": 0.9180477261543274,
+      "eval_runtime": 35.9929,
+      "eval_samples_per_second": 1.917,
+      "eval_steps_per_second": 1.917,
+      "step": 56
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 6.095506200784349e-06,
+      "loss": 0.8413,
+      "step": 57
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 5.975451610080643e-06,
+      "loss": 0.9434,
+      "step": 58
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 5.8548094438015065e-06,
+      "loss": 0.9523,
+      "step": 59
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 5.733652372276809e-06,
+      "loss": 0.8919,
+      "step": 60
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 5.612053375996082e-06,
+      "loss": 0.85,
+      "step": 61
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 5.490085701647805e-06,
+      "loss": 0.8806,
+      "step": 62
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 5.367822817998338e-06,
+      "loss": 0.8033,
+      "step": 63
+    },
+    {
+      "epoch": 2.38,
+      "eval_loss": 0.9181221127510071,
+      "eval_runtime": 36.0174,
+      "eval_samples_per_second": 1.916,
+      "eval_steps_per_second": 1.916,
+      "step": 63
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 5.245338371637091e-06,
+      "loss": 0.9186,
+      "step": 64
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 5.122706142614562e-06,
+      "loss": 0.8516,
+      "step": 65
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 5e-06,
+      "loss": 0.8434,
+      "step": 66
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 4.87729385738544e-06,
+      "loss": 0.8888,
+      "step": 67
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 4.75466162836291e-06,
+      "loss": 0.8871,
+      "step": 68
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 4.6321771820016635e-06,
+      "loss": 0.8806,
+      "step": 69
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 4.509914298352197e-06,
+      "loss": 0.8538,
+      "step": 70
+    },
+    {
+      "epoch": 2.64,
+      "eval_loss": 0.9172544479370117,
+      "eval_runtime": 35.8611,
+      "eval_samples_per_second": 1.924,
+      "eval_steps_per_second": 1.924,
+      "step": 70
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 4.38794662400392e-06,
+      "loss": 0.8353,
+      "step": 71
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.266347627723192e-06,
+      "loss": 0.8561,
+      "step": 72
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 4.145190556198494e-06,
+      "loss": 0.9676,
+      "step": 73
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 4.02454838991936e-06,
+      "loss": 0.8629,
+      "step": 74
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 3.904493799215652e-06,
+      "loss": 0.7983,
+      "step": 75
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 3.7850991004836813e-06,
+      "loss": 0.9275,
+      "step": 76
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 3.6664362126255087e-06,
+      "loss": 0.9481,
+      "step": 77
+    },
+    {
+      "epoch": 2.91,
+      "eval_loss": 0.9153242707252502,
+      "eval_runtime": 35.946,
+      "eval_samples_per_second": 1.92,
+      "eval_steps_per_second": 1.92,
+      "step": 77
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 3.5485766137276894e-06,
+      "loss": 0.8156,
+      "step": 78
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 3.4315912980055433e-06,
+      "loss": 0.7228,
+      "step": 79
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 3.3155507330389004e-06,
+      "loss": 0.9645,
+      "step": 80
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 3.2005248173250593e-06,
+      "loss": 0.7754,
+      "step": 81
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 3.0865828381745515e-06,
+      "loss": 0.8191,
+      "step": 82
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 2.9737934299750514e-06,
+      "loss": 0.8938,
+      "step": 83
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 2.862224532848591e-06,
+      "loss": 0.8995,
+      "step": 84
+    },
+    {
+      "epoch": 3.17,
+      "eval_loss": 0.9135288596153259,
+      "eval_runtime": 35.9776,
+      "eval_samples_per_second": 1.918,
+      "eval_steps_per_second": 1.918,
+      "step": 84
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 2.7519433517269665e-06,
+      "loss": 0.8728,
+      "step": 85
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 2.6430163158700116e-06,
+      "loss": 0.9105,
+      "step": 86
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 2.5355090388510806e-06,
+      "loss": 0.7815,
+      "step": 87
+    },
+    {
+      "epoch": 3.32,
+      "learning_rate": 2.429486279033892e-06,
+      "loss": 0.8562,
+      "step": 88
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 2.325011900564515e-06,
+      "loss": 0.8367,
+      "step": 89
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 2.2221488349019903e-06,
+      "loss": 0.8954,
+      "step": 90
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 2.1209590429107734e-06,
+      "loss": 0.8555,
+      "step": 91
+    },
+    {
+      "epoch": 3.43,
+      "eval_loss": 0.9140611886978149,
+      "eval_runtime": 35.9673,
+      "eval_samples_per_second": 1.918,
+      "eval_steps_per_second": 1.918,
+      "step": 91
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 2.0215034775378336e-06,
+      "loss": 0.8164,
+      "step": 92
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 1.9238420470968665e-06,
+      "loss": 0.8467,
+      "step": 93
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 1.8280335791817733e-06,
+      "loss": 0.8462,
+      "step": 94
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 1.7341357852311175e-06,
+      "loss": 0.8948,
+      "step": 95
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 1.642205225764908e-06,
+      "loss": 0.836,
+      "step": 96
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 1.5522972763146653e-06,
+      "loss": 0.8551,
+      "step": 97
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 1.4644660940672628e-06,
+      "loss": 0.884,
+      "step": 98
+    },
+    {
+      "epoch": 3.7,
+      "eval_loss": 0.9140763282775879,
+      "eval_runtime": 35.972,
+      "eval_samples_per_second": 1.918,
+      "eval_steps_per_second": 1.918,
+      "step": 98
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 1.3787645852426663e-06,
+      "loss": 0.8857,
+      "step": 99
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 1.2952443732252058e-06,
+      "loss": 0.7897,
+      "step": 100
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 1.2139557674675773e-06,
+      "loss": 0.8527,
+      "step": 101
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 1.134947733186315e-06,
+      "loss": 0.9348,
+      "step": 102
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 1.058267861866969e-06,
+      "loss": 0.9066,
+      "step": 103
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 9.83962342596776e-07,
+      "loss": 0.8794,
+      "step": 104
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 9.120759342420821e-07,
+      "loss": 0.878,
+      "step": 105
+    },
+    {
+      "epoch": 3.96,
+      "eval_loss": 0.9139989614486694,
+      "eval_runtime": 36.0023,
+      "eval_samples_per_second": 1.917,
+      "eval_steps_per_second": 1.917,
+      "step": 105
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 8.426519384872733e-07,
+      "loss": 0.8052,
+      "step": 106
+    },
+    {
+      "epoch": 4.04,
+      "learning_rate": 7.757321737514645e-07,
+      "loss": 0.8845,
+      "step": 107
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 7.113569499986401e-07,
+      "loss": 0.8134,
+      "step": 108
+    },
+    {
+      "epoch": 4.11,
+      "learning_rate": 6.495650444564433e-07,
+      "loss": 0.8164,
+      "step": 109
+    },
+    {
+      "epoch": 4.15,
+      "learning_rate": 5.903936782582253e-07,
+      "loss": 0.7922,
+      "step": 110
+    },
+    {
+      "epoch": 4.19,
+      "learning_rate": 5.338784940224239e-07,
+      "loss": 0.7529,
+      "step": 111
+    },
+    {
+      "epoch": 4.23,
+      "learning_rate": 4.800535343827834e-07,
+      "loss": 0.8288,
+      "step": 112
+    },
+    {
+      "epoch": 4.23,
+      "eval_loss": 0.9135251641273499,
+      "eval_runtime": 35.8899,
+      "eval_samples_per_second": 1.923,
+      "eval_steps_per_second": 1.923,
+      "step": 112
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 4.289512214823466e-07,
+      "loss": 0.8892,
+      "step": 113
+    },
+    {
+      "epoch": 4.3,
+      "learning_rate": 3.8060233744356634e-07,
+      "loss": 0.8427,
+      "step": 114
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 3.350360058263058e-07,
+      "loss": 0.9283,
+      "step": 115
+    },
+    {
+      "epoch": 4.38,
+      "learning_rate": 2.9227967408489653e-07,
+      "loss": 0.8674,
+      "step": 116
+    },
+    {
+      "epoch": 4.42,
+      "learning_rate": 2.523590970348166e-07,
+      "loss": 0.924,
+      "step": 117
+    },
+    {
+      "epoch": 4.45,
+      "learning_rate": 2.152983213389559e-07,
+      "loss": 0.8693,
+      "step": 118
+    },
+    {
+      "epoch": 4.49,
+      "learning_rate": 1.8111967102280082e-07,
+      "loss": 0.8456,
+      "step": 119
+    },
+    {
+      "epoch": 4.49,
+      "eval_loss": 0.9141875505447388,
+      "eval_runtime": 35.8271,
+      "eval_samples_per_second": 1.926,
+      "eval_steps_per_second": 1.926,
+      "step": 119
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 1.4984373402728014e-07,
+      "loss": 0.8763,
+      "step": 120
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 1.2148934980735772e-07,
+      "loss": 0.8042,
+      "step": 121
+    },
+    {
+      "epoch": 4.6,
+      "learning_rate": 9.607359798384785e-08,
+      "loss": 0.8456,
+      "step": 122
+    },
+    {
+      "epoch": 4.64,
+      "learning_rate": 7.36117880552939e-08,
+      "loss": 0.8505,
+      "step": 123
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 5.411745017609493e-08,
+      "loss": 0.8404,
+      "step": 124
+    },
+    {
+      "epoch": 4.72,
+      "learning_rate": 3.7602327006450166e-08,
+      "loss": 0.8483,
+      "step": 125
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 2.4076366639015914e-08,
+      "loss": 0.9049,
+      "step": 126
+    },
+    {
+      "epoch": 4.75,
+      "eval_loss": 0.9144126176834106,
+      "eval_runtime": 35.948,
+      "eval_samples_per_second": 1.919,
+      "eval_steps_per_second": 1.919,
+      "step": 126
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 1.3547716606548967e-08,
+      "loss": 0.8482,
+      "step": 127
+    },
+    {
+      "epoch": 4.83,
+      "learning_rate": 6.022718974137976e-09,
+      "loss": 0.9232,
+      "step": 128
+    },
+    {
+      "epoch": 4.87,
+      "learning_rate": 1.5059065189787502e-09,
+      "loss": 0.8653,
+      "step": 129
+    },
+    {
+      "epoch": 4.91,
+      "learning_rate": 0.0,
+      "loss": 0.9167,
+      "step": 130
+    },
+    {
+      "epoch": 4.91,
+      "step": 130,
+      "total_flos": 3.500008779892654e+17,
+      "train_loss": 0.8952723305958968,
+      "train_runtime": 7687.2741,
+      "train_samples_per_second": 0.825,
+      "train_steps_per_second": 0.017
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 130,
+  "num_train_epochs": 5,
+  "save_steps": 13,
+  "total_flos": 3.500008779892654e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9999d0ac6d9aee60648d04b52c128f6eb86db10e75de9eeb5feec8f3ffeaaa9
+size 4155