Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: HuggingFaceM4/idefics-9b
+---
+
+# 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 0.10.1.dev0

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "PeftModel",
+    "parent_library": "peft.peft_model"
+  },
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dcdff3b1cd5502f37fbc49bd5b56164a756b0b21281ba40b23f36847ee050d4
+size 79111656

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:004e4492dd5e5219c50b76a69f86589a588bca017a740d3dcc174147e719869c
+size 40107172

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8972cc07f8b502c4f3c2a744b9c92b835c2deeea6669dc944b2584b396010860
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f4fe8e328be6e10e053e14666b2e571c45c73d9a8291556b08910e3da67b3e6
+size 1064

trainer_state.json

@@ -0,0 +1,1133 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9092975676290066,
+  "eval_steps": 10,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009092975676290065,
+      "grad_norm": 1.0088555812835693,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 2.2722,
+      "step": 5
+    },
+    {
+      "epoch": 0.01818595135258013,
+      "grad_norm": 0.9372844099998474,
+      "learning_rate": 0.000196,
+      "loss": 1.6351,
+      "step": 10
+    },
+    {
+      "epoch": 0.01818595135258013,
+      "eval_loss": 1.5618833303451538,
+      "eval_runtime": 7.6668,
+      "eval_samples_per_second": 3.913,
+      "eval_steps_per_second": 1.956,
+      "step": 10
+    },
+    {
+      "epoch": 0.0272789270288702,
+      "grad_norm": 1.3525443077087402,
+      "learning_rate": 0.000194,
+      "loss": 1.5293,
+      "step": 15
+    },
+    {
+      "epoch": 0.03637190270516026,
+      "grad_norm": 0.8991140723228455,
+      "learning_rate": 0.000192,
+      "loss": 1.4111,
+      "step": 20
+    },
+    {
+      "epoch": 0.03637190270516026,
+      "eval_loss": 1.3718944787979126,
+      "eval_runtime": 7.8196,
+      "eval_samples_per_second": 3.837,
+      "eval_steps_per_second": 1.918,
+      "step": 20
+    },
+    {
+      "epoch": 0.04546487838145033,
+      "grad_norm": 1.98069429397583,
+      "learning_rate": 0.00019,
+      "loss": 1.3139,
+      "step": 25
+    },
+    {
+      "epoch": 0.0545578540577404,
+      "grad_norm": 0.6621396541595459,
+      "learning_rate": 0.000188,
+      "loss": 1.4428,
+      "step": 30
+    },
+    {
+      "epoch": 0.0545578540577404,
+      "eval_loss": 1.2937129735946655,
+      "eval_runtime": 7.4563,
+      "eval_samples_per_second": 4.023,
+      "eval_steps_per_second": 2.012,
+      "step": 30
+    },
+    {
+      "epoch": 0.06365082973403047,
+      "grad_norm": 0.896124005317688,
+      "learning_rate": 0.00018600000000000002,
+      "loss": 1.3239,
+      "step": 35
+    },
+    {
+      "epoch": 0.07274380541032052,
+      "grad_norm": 1.9882720708847046,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 1.279,
+      "step": 40
+    },
+    {
+      "epoch": 0.07274380541032052,
+      "eval_loss": 1.2551789283752441,
+      "eval_runtime": 7.9884,
+      "eval_samples_per_second": 3.755,
+      "eval_steps_per_second": 1.878,
+      "step": 40
+    },
+    {
+      "epoch": 0.08183678108661059,
+      "grad_norm": 0.7292985320091248,
+      "learning_rate": 0.000182,
+      "loss": 1.2615,
+      "step": 45
+    },
+    {
+      "epoch": 0.09092975676290066,
+      "grad_norm": 0.7677621245384216,
+      "learning_rate": 0.00018,
+      "loss": 1.2903,
+      "step": 50
+    },
+    {
+      "epoch": 0.09092975676290066,
+      "eval_loss": 1.2139209508895874,
+      "eval_runtime": 7.6731,
+      "eval_samples_per_second": 3.91,
+      "eval_steps_per_second": 1.955,
+      "step": 50
+    },
+    {
+      "epoch": 0.10002273243919073,
+      "grad_norm": 0.781851589679718,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 1.1273,
+      "step": 55
+    },
+    {
+      "epoch": 0.1091157081154808,
+      "grad_norm": 0.7166887521743774,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 1.3067,
+      "step": 60
+    },
+    {
+      "epoch": 0.1091157081154808,
+      "eval_loss": 1.2027504444122314,
+      "eval_runtime": 7.6999,
+      "eval_samples_per_second": 3.896,
+      "eval_steps_per_second": 1.948,
+      "step": 60
+    },
+    {
+      "epoch": 0.11820868379177085,
+      "grad_norm": 0.7799960970878601,
+      "learning_rate": 0.000174,
+      "loss": 1.1987,
+      "step": 65
+    },
+    {
+      "epoch": 0.12730165946806093,
+      "grad_norm": 0.6864632964134216,
+      "learning_rate": 0.000172,
+      "loss": 1.2013,
+      "step": 70
+    },
+    {
+      "epoch": 0.12730165946806093,
+      "eval_loss": 1.1920855045318604,
+      "eval_runtime": 7.8738,
+      "eval_samples_per_second": 3.81,
+      "eval_steps_per_second": 1.905,
+      "step": 70
+    },
+    {
+      "epoch": 0.136394635144351,
+      "grad_norm": 0.774085283279419,
+      "learning_rate": 0.00017,
+      "loss": 1.1184,
+      "step": 75
+    },
+    {
+      "epoch": 0.14548761082064104,
+      "grad_norm": 0.6681156158447266,
+      "learning_rate": 0.000168,
+      "loss": 1.2931,
+      "step": 80
+    },
+    {
+      "epoch": 0.14548761082064104,
+      "eval_loss": 1.1745468378067017,
+      "eval_runtime": 7.4956,
+      "eval_samples_per_second": 4.002,
+      "eval_steps_per_second": 2.001,
+      "step": 80
+    },
+    {
+      "epoch": 0.15458058649693113,
+      "grad_norm": 0.7310240864753723,
+      "learning_rate": 0.000166,
+      "loss": 1.1426,
+      "step": 85
+    },
+    {
+      "epoch": 0.16367356217322118,
+      "grad_norm": 0.8338828682899475,
+      "learning_rate": 0.000164,
+      "loss": 1.1719,
+      "step": 90
+    },
+    {
+      "epoch": 0.16367356217322118,
+      "eval_loss": 1.1653213500976562,
+      "eval_runtime": 7.8929,
+      "eval_samples_per_second": 3.801,
+      "eval_steps_per_second": 1.9,
+      "step": 90
+    },
+    {
+      "epoch": 0.17276653784951126,
+      "grad_norm": 0.732770562171936,
+      "learning_rate": 0.000162,
+      "loss": 1.2321,
+      "step": 95
+    },
+    {
+      "epoch": 0.18185951352580132,
+      "grad_norm": 0.7523607611656189,
+      "learning_rate": 0.00016,
+      "loss": 1.2331,
+      "step": 100
+    },
+    {
+      "epoch": 0.18185951352580132,
+      "eval_loss": 1.1490192413330078,
+      "eval_runtime": 7.6199,
+      "eval_samples_per_second": 3.937,
+      "eval_steps_per_second": 1.969,
+      "step": 100
+    },
+    {
+      "epoch": 0.19095248920209137,
+      "grad_norm": 0.7681267261505127,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 1.1277,
+      "step": 105
+    },
+    {
+      "epoch": 0.20004546487838146,
+      "grad_norm": 0.7249591946601868,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 1.142,
+      "step": 110
+    },
+    {
+      "epoch": 0.20004546487838146,
+      "eval_loss": 1.137698769569397,
+      "eval_runtime": 7.8436,
+      "eval_samples_per_second": 3.825,
+      "eval_steps_per_second": 1.912,
+      "step": 110
+    },
+    {
+      "epoch": 0.2091384405546715,
+      "grad_norm": 0.6904309391975403,
+      "learning_rate": 0.000154,
+      "loss": 1.2033,
+      "step": 115
+    },
+    {
+      "epoch": 0.2182314162309616,
+      "grad_norm": 0.7456697821617126,
+      "learning_rate": 0.000152,
+      "loss": 1.1777,
+      "step": 120
+    },
+    {
+      "epoch": 0.2182314162309616,
+      "eval_loss": 1.1293922662734985,
+      "eval_runtime": 7.2963,
+      "eval_samples_per_second": 4.112,
+      "eval_steps_per_second": 2.056,
+      "step": 120
+    },
+    {
+      "epoch": 0.22732439190725165,
+      "grad_norm": 0.6743273735046387,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.1582,
+      "step": 125
+    },
+    {
+      "epoch": 0.2364173675835417,
+      "grad_norm": 0.6429440379142761,
+      "learning_rate": 0.000148,
+      "loss": 1.1064,
+      "step": 130
+    },
+    {
+      "epoch": 0.2364173675835417,
+      "eval_loss": 1.119972825050354,
+      "eval_runtime": 7.7787,
+      "eval_samples_per_second": 3.857,
+      "eval_steps_per_second": 1.928,
+      "step": 130
+    },
+    {
+      "epoch": 0.2455103432598318,
+      "grad_norm": 0.6626828908920288,
+      "learning_rate": 0.000146,
+      "loss": 1.1741,
+      "step": 135
+    },
+    {
+      "epoch": 0.25460331893612187,
+      "grad_norm": 0.8786306381225586,
+      "learning_rate": 0.000144,
+      "loss": 0.9836,
+      "step": 140
+    },
+    {
+      "epoch": 0.25460331893612187,
+      "eval_loss": 1.1226236820220947,
+      "eval_runtime": 7.3222,
+      "eval_samples_per_second": 4.097,
+      "eval_steps_per_second": 2.049,
+      "step": 140
+    },
+    {
+      "epoch": 0.2636962946124119,
+      "grad_norm": 0.7686639428138733,
+      "learning_rate": 0.000142,
+      "loss": 1.0945,
+      "step": 145
+    },
+    {
+      "epoch": 0.272789270288702,
+      "grad_norm": 0.795609712600708,
+      "learning_rate": 0.00014,
+      "loss": 0.9761,
+      "step": 150
+    },
+    {
+      "epoch": 0.272789270288702,
+      "eval_loss": 1.0910608768463135,
+      "eval_runtime": 7.8761,
+      "eval_samples_per_second": 3.809,
+      "eval_steps_per_second": 1.905,
+      "step": 150
+    },
+    {
+      "epoch": 0.28188224596499206,
+      "grad_norm": 0.8161769509315491,
+      "learning_rate": 0.000138,
+      "loss": 1.0516,
+      "step": 155
+    },
+    {
+      "epoch": 0.2909752216412821,
+      "grad_norm": 0.7441025972366333,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 1.0843,
+      "step": 160
+    },
+    {
+      "epoch": 0.2909752216412821,
+      "eval_loss": 1.0994905233383179,
+      "eval_runtime": 7.3248,
+      "eval_samples_per_second": 4.096,
+      "eval_steps_per_second": 2.048,
+      "step": 160
+    },
+    {
+      "epoch": 0.30006819731757217,
+      "grad_norm": 0.8015936613082886,
+      "learning_rate": 0.000134,
+      "loss": 1.2283,
+      "step": 165
+    },
+    {
+      "epoch": 0.30916117299386225,
+      "grad_norm": 0.7653372287750244,
+      "learning_rate": 0.000132,
+      "loss": 1.0927,
+      "step": 170
+    },
+    {
+      "epoch": 0.30916117299386225,
+      "eval_loss": 1.0781885385513306,
+      "eval_runtime": 7.7433,
+      "eval_samples_per_second": 3.874,
+      "eval_steps_per_second": 1.937,
+      "step": 170
+    },
+    {
+      "epoch": 0.3182541486701523,
+      "grad_norm": 0.7825664281845093,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 1.106,
+      "step": 175
+    },
+    {
+      "epoch": 0.32734712434644236,
+      "grad_norm": 0.7554489970207214,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 1.0999,
+      "step": 180
+    },
+    {
+      "epoch": 0.32734712434644236,
+      "eval_loss": 1.0733944177627563,
+      "eval_runtime": 7.5964,
+      "eval_samples_per_second": 3.949,
+      "eval_steps_per_second": 1.975,
+      "step": 180
+    },
+    {
+      "epoch": 0.33644010002273245,
+      "grad_norm": 0.8089460730552673,
+      "learning_rate": 0.000126,
+      "loss": 1.2226,
+      "step": 185
+    },
+    {
+      "epoch": 0.34553307569902253,
+      "grad_norm": 0.7402002215385437,
+      "learning_rate": 0.000124,
+      "loss": 1.1182,
+      "step": 190
+    },
+    {
+      "epoch": 0.34553307569902253,
+      "eval_loss": 1.0658830404281616,
+      "eval_runtime": 7.8865,
+      "eval_samples_per_second": 3.804,
+      "eval_steps_per_second": 1.902,
+      "step": 190
+    },
+    {
+      "epoch": 0.35462605137531256,
+      "grad_norm": 0.6649179458618164,
+      "learning_rate": 0.000122,
+      "loss": 1.0671,
+      "step": 195
+    },
+    {
+      "epoch": 0.36371902705160264,
+      "grad_norm": 0.7573872804641724,
+      "learning_rate": 0.00012,
+      "loss": 1.0291,
+      "step": 200
+    },
+    {
+      "epoch": 0.36371902705160264,
+      "eval_loss": 1.0471783876419067,
+      "eval_runtime": 7.9526,
+      "eval_samples_per_second": 3.772,
+      "eval_steps_per_second": 1.886,
+      "step": 200
+    },
+    {
+      "epoch": 0.3728120027278927,
+      "grad_norm": 0.8243398666381836,
+      "learning_rate": 0.000118,
+      "loss": 1.1096,
+      "step": 205
+    },
+    {
+      "epoch": 0.38190497840418275,
+      "grad_norm": 0.721502423286438,
+      "learning_rate": 0.000116,
+      "loss": 1.2158,
+      "step": 210
+    },
+    {
+      "epoch": 0.38190497840418275,
+      "eval_loss": 1.0554709434509277,
+      "eval_runtime": 7.3409,
+      "eval_samples_per_second": 4.087,
+      "eval_steps_per_second": 2.043,
+      "step": 210
+    },
+    {
+      "epoch": 0.39099795408047283,
+      "grad_norm": 0.7591432332992554,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 1.0817,
+      "step": 215
+    },
+    {
+      "epoch": 0.4000909297567629,
+      "grad_norm": 0.7596343755722046,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 1.0873,
+      "step": 220
+    },
+    {
+      "epoch": 0.4000909297567629,
+      "eval_loss": 1.0482908487319946,
+      "eval_runtime": 7.8536,
+      "eval_samples_per_second": 3.82,
+      "eval_steps_per_second": 1.91,
+      "step": 220
+    },
+    {
+      "epoch": 0.40918390543305294,
+      "grad_norm": 0.8296840190887451,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 1.0252,
+      "step": 225
+    },
+    {
+      "epoch": 0.418276881109343,
+      "grad_norm": 0.9094285368919373,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 1.0978,
+      "step": 230
+    },
+    {
+      "epoch": 0.418276881109343,
+      "eval_loss": 1.046170711517334,
+      "eval_runtime": 7.4472,
+      "eval_samples_per_second": 4.028,
+      "eval_steps_per_second": 2.014,
+      "step": 230
+    },
+    {
+      "epoch": 0.4273698567856331,
+      "grad_norm": 0.8471206426620483,
+      "learning_rate": 0.00010600000000000002,
+      "loss": 1.0371,
+      "step": 235
+    },
+    {
+      "epoch": 0.4364628324619232,
+      "grad_norm": 0.8168342113494873,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 1.0352,
+      "step": 240
+    },
+    {
+      "epoch": 0.4364628324619232,
+      "eval_loss": 1.0409115552902222,
+      "eval_runtime": 7.8502,
+      "eval_samples_per_second": 3.822,
+      "eval_steps_per_second": 1.911,
+      "step": 240
+    },
+    {
+      "epoch": 0.4455558081382132,
+      "grad_norm": 0.7482770681381226,
+      "learning_rate": 0.00010200000000000001,
+      "loss": 1.0812,
+      "step": 245
+    },
+    {
+      "epoch": 0.4546487838145033,
+      "grad_norm": 0.7300863862037659,
+      "learning_rate": 0.0001,
+      "loss": 1.1762,
+      "step": 250
+    },
+    {
+      "epoch": 0.4546487838145033,
+      "eval_loss": 1.0410172939300537,
+      "eval_runtime": 7.4872,
+      "eval_samples_per_second": 4.007,
+      "eval_steps_per_second": 2.003,
+      "step": 250
+    },
+    {
+      "epoch": 0.4637417594907934,
+      "grad_norm": 0.7066290378570557,
+      "learning_rate": 9.8e-05,
+      "loss": 1.1054,
+      "step": 255
+    },
+    {
+      "epoch": 0.4728347351670834,
+      "grad_norm": 0.8214625716209412,
+      "learning_rate": 9.6e-05,
+      "loss": 1.0563,
+      "step": 260
+    },
+    {
+      "epoch": 0.4728347351670834,
+      "eval_loss": 1.03702974319458,
+      "eval_runtime": 7.8723,
+      "eval_samples_per_second": 3.811,
+      "eval_steps_per_second": 1.905,
+      "step": 260
+    },
+    {
+      "epoch": 0.4819277108433735,
+      "grad_norm": 0.8834312558174133,
+      "learning_rate": 9.4e-05,
+      "loss": 1.1071,
+      "step": 265
+    },
+    {
+      "epoch": 0.4910206865196636,
+      "grad_norm": 0.768332302570343,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 1.0537,
+      "step": 270
+    },
+    {
+      "epoch": 0.4910206865196636,
+      "eval_loss": 1.033887267112732,
+      "eval_runtime": 7.7503,
+      "eval_samples_per_second": 3.871,
+      "eval_steps_per_second": 1.935,
+      "step": 270
+    },
+    {
+      "epoch": 0.5001136621959537,
+      "grad_norm": 0.805924654006958,
+      "learning_rate": 9e-05,
+      "loss": 1.1193,
+      "step": 275
+    },
+    {
+      "epoch": 0.5092066378722437,
+      "grad_norm": 0.8571528792381287,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 1.0951,
+      "step": 280
+    },
+    {
+      "epoch": 0.5092066378722437,
+      "eval_loss": 1.0283806324005127,
+      "eval_runtime": 7.6361,
+      "eval_samples_per_second": 3.929,
+      "eval_steps_per_second": 1.964,
+      "step": 280
+    },
+    {
+      "epoch": 0.5182996135485337,
+      "grad_norm": 0.8743025064468384,
+      "learning_rate": 8.6e-05,
+      "loss": 0.9861,
+      "step": 285
+    },
+    {
+      "epoch": 0.5273925892248238,
+      "grad_norm": 0.8119250535964966,
+      "learning_rate": 8.4e-05,
+      "loss": 1.0458,
+      "step": 290
+    },
+    {
+      "epoch": 0.5273925892248238,
+      "eval_loss": 1.0257965326309204,
+      "eval_runtime": 7.8945,
+      "eval_samples_per_second": 3.8,
+      "eval_steps_per_second": 1.9,
+      "step": 290
+    },
+    {
+      "epoch": 0.5364855649011139,
+      "grad_norm": 0.9032679796218872,
+      "learning_rate": 8.2e-05,
+      "loss": 1.0145,
+      "step": 295
+    },
+    {
+      "epoch": 0.545578540577404,
+      "grad_norm": 0.8125148415565491,
+      "learning_rate": 8e-05,
+      "loss": 1.0212,
+      "step": 300
+    },
+    {
+      "epoch": 0.545578540577404,
+      "eval_loss": 1.018557071685791,
+      "eval_runtime": 7.5438,
+      "eval_samples_per_second": 3.977,
+      "eval_steps_per_second": 1.988,
+      "step": 300
+    },
+    {
+      "epoch": 0.554671516253694,
+      "grad_norm": 0.77150958776474,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 1.0901,
+      "step": 305
+    },
+    {
+      "epoch": 0.5637644919299841,
+      "grad_norm": 0.8303976058959961,
+      "learning_rate": 7.6e-05,
+      "loss": 1.0535,
+      "step": 310
+    },
+    {
+      "epoch": 0.5637644919299841,
+      "eval_loss": 1.019250750541687,
+      "eval_runtime": 7.9264,
+      "eval_samples_per_second": 3.785,
+      "eval_steps_per_second": 1.892,
+      "step": 310
+    },
+    {
+      "epoch": 0.5728574676062742,
+      "grad_norm": 0.8433631658554077,
+      "learning_rate": 7.4e-05,
+      "loss": 1.1187,
+      "step": 315
+    },
+    {
+      "epoch": 0.5819504432825642,
+      "grad_norm": 0.8279653787612915,
+      "learning_rate": 7.2e-05,
+      "loss": 1.1483,
+      "step": 320
+    },
+    {
+      "epoch": 0.5819504432825642,
+      "eval_loss": 1.0166659355163574,
+      "eval_runtime": 7.3093,
+      "eval_samples_per_second": 4.104,
+      "eval_steps_per_second": 2.052,
+      "step": 320
+    },
+    {
+      "epoch": 0.5910434189588543,
+      "grad_norm": 0.6873704791069031,
+      "learning_rate": 7e-05,
+      "loss": 1.0573,
+      "step": 325
+    },
+    {
+      "epoch": 0.6001363946351443,
+      "grad_norm": 0.7217792868614197,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 1.0225,
+      "step": 330
+    },
+    {
+      "epoch": 0.6001363946351443,
+      "eval_loss": 1.0203421115875244,
+      "eval_runtime": 7.9938,
+      "eval_samples_per_second": 3.753,
+      "eval_steps_per_second": 1.876,
+      "step": 330
+    },
+    {
+      "epoch": 0.6092293703114344,
+      "grad_norm": 0.828619122505188,
+      "learning_rate": 6.6e-05,
+      "loss": 1.0272,
+      "step": 335
+    },
+    {
+      "epoch": 0.6183223459877245,
+      "grad_norm": 0.7822660207748413,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.9776,
+      "step": 340
+    },
+    {
+      "epoch": 0.6183223459877245,
+      "eval_loss": 1.0186898708343506,
+      "eval_runtime": 7.3434,
+      "eval_samples_per_second": 4.085,
+      "eval_steps_per_second": 2.043,
+      "step": 340
+    },
+    {
+      "epoch": 0.6274153216640146,
+      "grad_norm": 0.7307916283607483,
+      "learning_rate": 6.2e-05,
+      "loss": 1.0637,
+      "step": 345
+    },
+    {
+      "epoch": 0.6365082973403046,
+      "grad_norm": 0.8595789670944214,
+      "learning_rate": 6e-05,
+      "loss": 1.0571,
+      "step": 350
+    },
+    {
+      "epoch": 0.6365082973403046,
+      "eval_loss": 1.008802056312561,
+      "eval_runtime": 7.6422,
+      "eval_samples_per_second": 3.926,
+      "eval_steps_per_second": 1.963,
+      "step": 350
+    },
+    {
+      "epoch": 0.6456012730165946,
+      "grad_norm": 1.0007542371749878,
+      "learning_rate": 5.8e-05,
+      "loss": 1.1277,
+      "step": 355
+    },
+    {
+      "epoch": 0.6546942486928847,
+      "grad_norm": 0.8014799356460571,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 1.2342,
+      "step": 360
+    },
+    {
+      "epoch": 0.6546942486928847,
+      "eval_loss": 1.0054609775543213,
+      "eval_runtime": 7.5443,
+      "eval_samples_per_second": 3.977,
+      "eval_steps_per_second": 1.988,
+      "step": 360
+    },
+    {
+      "epoch": 0.6637872243691748,
+      "grad_norm": 0.8301798105239868,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 1.0886,
+      "step": 365
+    },
+    {
+      "epoch": 0.6728802000454649,
+      "grad_norm": 0.8582270741462708,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 1.0834,
+      "step": 370
+    },
+    {
+      "epoch": 0.6728802000454649,
+      "eval_loss": 0.9980356693267822,
+      "eval_runtime": 7.3182,
+      "eval_samples_per_second": 4.099,
+      "eval_steps_per_second": 2.05,
+      "step": 370
+    },
+    {
+      "epoch": 0.681973175721755,
+      "grad_norm": 0.9084227085113525,
+      "learning_rate": 5e-05,
+      "loss": 1.0517,
+      "step": 375
+    },
+    {
+      "epoch": 0.6910661513980451,
+      "grad_norm": 0.8120643496513367,
+      "learning_rate": 4.8e-05,
+      "loss": 1.0931,
+      "step": 380
+    },
+    {
+      "epoch": 0.6910661513980451,
+      "eval_loss": 0.9912369847297668,
+      "eval_runtime": 7.8444,
+      "eval_samples_per_second": 3.824,
+      "eval_steps_per_second": 1.912,
+      "step": 380
+    },
+    {
+      "epoch": 0.700159127074335,
+      "grad_norm": 0.8523077964782715,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.0883,
+      "step": 385
+    },
+    {
+      "epoch": 0.7092521027506251,
+      "grad_norm": 0.8379296660423279,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 1.1041,
+      "step": 390
+    },
+    {
+      "epoch": 0.7092521027506251,
+      "eval_loss": 0.9924930334091187,
+      "eval_runtime": 7.364,
+      "eval_samples_per_second": 4.074,
+      "eval_steps_per_second": 2.037,
+      "step": 390
+    },
+    {
+      "epoch": 0.7183450784269152,
+      "grad_norm": 0.9272042512893677,
+      "learning_rate": 4.2e-05,
+      "loss": 1.0839,
+      "step": 395
+    },
+    {
+      "epoch": 0.7274380541032053,
+      "grad_norm": 0.8774125576019287,
+      "learning_rate": 4e-05,
+      "loss": 0.9889,
+      "step": 400
+    },
+    {
+      "epoch": 0.7274380541032053,
+      "eval_loss": 0.9954690337181091,
+      "eval_runtime": 7.8404,
+      "eval_samples_per_second": 3.826,
+      "eval_steps_per_second": 1.913,
+      "step": 400
+    },
+    {
+      "epoch": 0.7365310297794954,
+      "grad_norm": 0.7553389072418213,
+      "learning_rate": 3.8e-05,
+      "loss": 1.0906,
+      "step": 405
+    },
+    {
+      "epoch": 0.7456240054557854,
+      "grad_norm": 0.7866451740264893,
+      "learning_rate": 3.6e-05,
+      "loss": 1.0219,
+      "step": 410
+    },
+    {
+      "epoch": 0.7456240054557854,
+      "eval_loss": 0.994717001914978,
+      "eval_runtime": 7.8266,
+      "eval_samples_per_second": 3.833,
+      "eval_steps_per_second": 1.917,
+      "step": 410
+    },
+    {
+      "epoch": 0.7547169811320755,
+      "grad_norm": 0.8554181456565857,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 1.0598,
+      "step": 415
+    },
+    {
+      "epoch": 0.7638099568083655,
+      "grad_norm": 0.9773761034011841,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 1.033,
+      "step": 420
+    },
+    {
+      "epoch": 0.7638099568083655,
+      "eval_loss": 0.9926409125328064,
+      "eval_runtime": 7.2819,
+      "eval_samples_per_second": 4.12,
+      "eval_steps_per_second": 2.06,
+      "step": 420
+    },
+    {
+      "epoch": 0.7729029324846556,
+      "grad_norm": 0.8768495917320251,
+      "learning_rate": 3e-05,
+      "loss": 1.054,
+      "step": 425
+    },
+    {
+      "epoch": 0.7819959081609457,
+      "grad_norm": 0.787002682685852,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 1.0548,
+      "step": 430
+    },
+    {
+      "epoch": 0.7819959081609457,
+      "eval_loss": 0.9910202622413635,
+      "eval_runtime": 7.8704,
+      "eval_samples_per_second": 3.812,
+      "eval_steps_per_second": 1.906,
+      "step": 430
+    },
+    {
+      "epoch": 0.7910888838372357,
+      "grad_norm": 0.843839704990387,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 1.0936,
+      "step": 435
+    },
+    {
+      "epoch": 0.8001818595135258,
+      "grad_norm": 0.9202592968940735,
+      "learning_rate": 2.4e-05,
+      "loss": 1.0684,
+      "step": 440
+    },
+    {
+      "epoch": 0.8001818595135258,
+      "eval_loss": 0.9879806637763977,
+      "eval_runtime": 7.292,
+      "eval_samples_per_second": 4.114,
+      "eval_steps_per_second": 2.057,
+      "step": 440
+    },
+    {
+      "epoch": 0.8092748351898159,
+      "grad_norm": 0.8747548460960388,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 1.0185,
+      "step": 445
+    },
+    {
+      "epoch": 0.8183678108661059,
+      "grad_norm": 0.8311501145362854,
+      "learning_rate": 2e-05,
+      "loss": 1.0874,
+      "step": 450
+    },
+    {
+      "epoch": 0.8183678108661059,
+      "eval_loss": 0.9860556125640869,
+      "eval_runtime": 7.7936,
+      "eval_samples_per_second": 3.849,
+      "eval_steps_per_second": 1.925,
+      "step": 450
+    },
+    {
+      "epoch": 0.827460786542396,
+      "grad_norm": 0.8813076615333557,
+      "learning_rate": 1.8e-05,
+      "loss": 1.0209,
+      "step": 455
+    },
+    {
+      "epoch": 0.836553762218686,
+      "grad_norm": 0.9480300545692444,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.0878,
+      "step": 460
+    },
+    {
+      "epoch": 0.836553762218686,
+      "eval_loss": 0.9852551817893982,
+      "eval_runtime": 7.2978,
+      "eval_samples_per_second": 4.111,
+      "eval_steps_per_second": 2.055,
+      "step": 460
+    },
+    {
+      "epoch": 0.8456467378949761,
+      "grad_norm": 0.8942534923553467,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 0.9746,
+      "step": 465
+    },
+    {
+      "epoch": 0.8547397135712662,
+      "grad_norm": 0.9491382837295532,
+      "learning_rate": 1.2e-05,
+      "loss": 0.9443,
+      "step": 470
+    },
+    {
+      "epoch": 0.8547397135712662,
+      "eval_loss": 0.9845015406608582,
+      "eval_runtime": 7.7967,
+      "eval_samples_per_second": 3.848,
+      "eval_steps_per_second": 1.924,
+      "step": 470
+    },
+    {
+      "epoch": 0.8638326892475563,
+      "grad_norm": 0.9191480278968811,
+      "learning_rate": 1e-05,
+      "loss": 1.0311,
+      "step": 475
+    },
+    {
+      "epoch": 0.8729256649238464,
+      "grad_norm": 0.8474745750427246,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.1006,
+      "step": 480
+    },
+    {
+      "epoch": 0.8729256649238464,
+      "eval_loss": 0.9836694002151489,
+      "eval_runtime": 7.3154,
+      "eval_samples_per_second": 4.101,
+      "eval_steps_per_second": 2.05,
+      "step": 480
+    },
+    {
+      "epoch": 0.8820186406001363,
+      "grad_norm": 0.8463994860649109,
+      "learning_rate": 6e-06,
+      "loss": 1.0196,
+      "step": 485
+    },
+    {
+      "epoch": 0.8911116162764264,
+      "grad_norm": 0.8902223706245422,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.0447,
+      "step": 490
+    },
+    {
+      "epoch": 0.8911116162764264,
+      "eval_loss": 0.9838915467262268,
+      "eval_runtime": 7.7764,
+      "eval_samples_per_second": 3.858,
+      "eval_steps_per_second": 1.929,
+      "step": 490
+    },
+    {
+      "epoch": 0.9002045919527165,
+      "grad_norm": 0.8993239998817444,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.0981,
+      "step": 495
+    },
+    {
+      "epoch": 0.9092975676290066,
+      "grad_norm": 0.8118588924407959,
+      "learning_rate": 0.0,
+      "loss": 1.0078,
+      "step": 500
+    },
+    {
+      "epoch": 0.9092975676290066,
+      "eval_loss": 0.9837616086006165,
+      "eval_runtime": 7.456,
+      "eval_samples_per_second": 4.024,
+      "eval_steps_per_second": 2.012,
+      "step": 500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.068977650017795e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:153ab890898c4154c7fb7f39e62f25c87434e7d88e70ab096f33348a8a48fdc7
+size 5176