Upload checkpoint-2000

MS_Marco_ep10/checkpoint-2000/README.md

@@ -0,0 +1,206 @@
+---
+base_model: Qwen/Qwen3-Embedding-4B
+library_name: peft
+tags:
+- base_model:adapter:Qwen/Qwen3-Embedding-4B
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.16.0

MS_Marco_ep10/checkpoint-2000/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-Embedding-4B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "FEATURE_EXTRACTION",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

MS_Marco_ep10/checkpoint-2000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03db742c5e8ec82c043ea008fa43194a72b4d0fc10d21422bc1d1930e949242c
+size 264305872

MS_Marco_ep10/checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f84cdda05f753ba99c72b7671a9ff3491b4ddbd7b0618e91e1bd2706b762acd4
+size 530221329

MS_Marco_ep10/checkpoint-2000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8357a2e555543ada794103cd18bf163ee600e2457092894bb0e5762412b8944
+size 14917

MS_Marco_ep10/checkpoint-2000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7c9fbac4632c9b8b5d2a0cd9bb372b1ab766227545cd534ef6772fc3a9433ec
+size 14917

MS_Marco_ep10/checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1bc32749fe0b8fed3019b3ad3f9be44802ea81d489f6945bf04443aa220c7f9
+size 1465

MS_Marco_ep10/checkpoint-2000/trainer_state.json

@@ -0,0 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.2544853034737244,
+  "eval_steps": 1000000,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001272426517368622,
+      "grad_norm": 3.5877323150634766,
+      "learning_rate": 5.725919328158799e-08,
+      "loss": 0.1624,
+      "step": 10
+    },
+    {
+      "epoch": 0.002544853034737244,
+      "grad_norm": 2.085402488708496,
+      "learning_rate": 1.2088051915001908e-07,
+      "loss": 0.1406,
+      "step": 20
+    },
+    {
+      "epoch": 0.003817279552105866,
+      "grad_norm": 2.65560245513916,
+      "learning_rate": 1.845018450184502e-07,
+      "loss": 0.1539,
+      "step": 30
+    },
+    {
+      "epoch": 0.005089706069474488,
+      "grad_norm": 4.92278528213501,
+      "learning_rate": 2.4812317088688133e-07,
+      "loss": 0.1836,
+      "step": 40
+    },
+    {
+      "epoch": 0.00636213258684311,
+      "grad_norm": 3.515843152999878,
+      "learning_rate": 3.117444967553124e-07,
+      "loss": 0.1567,
+      "step": 50
+    },
+    {
+      "epoch": 0.007634559104211732,
+      "grad_norm": 2.803701877593994,
+      "learning_rate": 3.7536582262374346e-07,
+      "loss": 0.1596,
+      "step": 60
+    },
+    {
+      "epoch": 0.008906985621580354,
+      "grad_norm": 2.529664993286133,
+      "learning_rate": 4.389871484921746e-07,
+      "loss": 0.1436,
+      "step": 70
+    },
+    {
+      "epoch": 0.010179412138948976,
+      "grad_norm": 4.315010070800781,
+      "learning_rate": 5.026084743606057e-07,
+      "loss": 0.175,
+      "step": 80
+    },
+    {
+      "epoch": 0.011451838656317598,
+      "grad_norm": 3.158771276473999,
+      "learning_rate": 5.662298002290368e-07,
+      "loss": 0.1337,
+      "step": 90
+    },
+    {
+      "epoch": 0.01272426517368622,
+      "grad_norm": 1.9685556888580322,
+      "learning_rate": 6.298511260974679e-07,
+      "loss": 0.1563,
+      "step": 100
+    },
+    {
+      "epoch": 0.013996691691054842,
+      "grad_norm": 1.7232635021209717,
+      "learning_rate": 6.93472451965899e-07,
+      "loss": 0.1262,
+      "step": 110
+    },
+    {
+      "epoch": 0.015269118208423464,
+      "grad_norm": 3.527454137802124,
+      "learning_rate": 7.570937778343301e-07,
+      "loss": 0.1413,
+      "step": 120
+    },
+    {
+      "epoch": 0.016541544725792084,
+      "grad_norm": 3.0089797973632812,
+      "learning_rate": 8.207151037027612e-07,
+      "loss": 0.1524,
+      "step": 130
+    },
+    {
+      "epoch": 0.017813971243160708,
+      "grad_norm": 1.7723190784454346,
+      "learning_rate": 8.843364295711924e-07,
+      "loss": 0.1307,
+      "step": 140
+    },
+    {
+      "epoch": 0.01908639776052933,
+      "grad_norm": 1.957555890083313,
+      "learning_rate": 9.479577554396234e-07,
+      "loss": 0.123,
+      "step": 150
+    },
+    {
+      "epoch": 0.020358824277897952,
+      "grad_norm": 1.7378482818603516,
+      "learning_rate": 1.0115790813080545e-06,
+      "loss": 0.1708,
+      "step": 160
+    },
+    {
+      "epoch": 0.021631250795266573,
+      "grad_norm": 1.664908766746521,
+      "learning_rate": 1.0752004071764857e-06,
+      "loss": 0.1132,
+      "step": 170
+    },
+    {
+      "epoch": 0.022903677312635196,
+      "grad_norm": 2.3183891773223877,
+      "learning_rate": 1.1388217330449168e-06,
+      "loss": 0.1107,
+      "step": 180
+    },
+    {
+      "epoch": 0.024176103830003817,
+      "grad_norm": 2.1844465732574463,
+      "learning_rate": 1.2024430589133478e-06,
+      "loss": 0.0953,
+      "step": 190
+    },
+    {
+      "epoch": 0.02544853034737244,
+      "grad_norm": 4.4184417724609375,
+      "learning_rate": 1.266064384781779e-06,
+      "loss": 0.0922,
+      "step": 200
+    },
+    {
+      "epoch": 0.02672095686474106,
+      "grad_norm": 2.0239903926849365,
+      "learning_rate": 1.32968571065021e-06,
+      "loss": 0.0699,
+      "step": 210
+    },
+    {
+      "epoch": 0.027993383382109684,
+      "grad_norm": 1.2873213291168213,
+      "learning_rate": 1.3933070365186412e-06,
+      "loss": 0.0717,
+      "step": 220
+    },
+    {
+      "epoch": 0.029265809899478305,
+      "grad_norm": 1.9870949983596802,
+      "learning_rate": 1.4569283623870722e-06,
+      "loss": 0.055,
+      "step": 230
+    },
+    {
+      "epoch": 0.03053823641684693,
+      "grad_norm": 0.75453120470047,
+      "learning_rate": 1.5205496882555034e-06,
+      "loss": 0.0558,
+      "step": 240
+    },
+    {
+      "epoch": 0.03181066293421555,
+      "grad_norm": 2.1326417922973633,
+      "learning_rate": 1.5841710141239346e-06,
+      "loss": 0.0428,
+      "step": 250
+    },
+    {
+      "epoch": 0.03308308945158417,
+      "grad_norm": 0.530195951461792,
+      "learning_rate": 1.6477923399923656e-06,
+      "loss": 0.0344,
+      "step": 260
+    },
+    {
+      "epoch": 0.034355515968952796,
+      "grad_norm": 0.25554534792900085,
+      "learning_rate": 1.7114136658607965e-06,
+      "loss": 0.0342,
+      "step": 270
+    },
+    {
+      "epoch": 0.035627942486321416,
+      "grad_norm": 2.5654115676879883,
+      "learning_rate": 1.7750349917292275e-06,
+      "loss": 0.0464,
+      "step": 280
+    },
+    {
+      "epoch": 0.03690036900369004,
+      "grad_norm": 0.8986497521400452,
+      "learning_rate": 1.838656317597659e-06,
+      "loss": 0.0359,
+      "step": 290
+    },
+    {
+      "epoch": 0.03817279552105866,
+      "grad_norm": 0.4290733337402344,
+      "learning_rate": 1.90227764346609e-06,
+      "loss": 0.0269,
+      "step": 300
+    },
+    {
+      "epoch": 0.039445222038427284,
+      "grad_norm": 1.9061795473098755,
+      "learning_rate": 1.965898969334521e-06,
+      "loss": 0.0336,
+      "step": 310
+    },
+    {
+      "epoch": 0.040717648555795904,
+      "grad_norm": 2.097940444946289,
+      "learning_rate": 2.029520295202952e-06,
+      "loss": 0.0527,
+      "step": 320
+    },
+    {
+      "epoch": 0.041990075073164525,
+      "grad_norm": 2.3401193618774414,
+      "learning_rate": 2.093141621071383e-06,
+      "loss": 0.0254,
+      "step": 330
+    },
+    {
+      "epoch": 0.043262501590533145,
+      "grad_norm": 0.4466155171394348,
+      "learning_rate": 2.1567629469398143e-06,
+      "loss": 0.0365,
+      "step": 340
+    },
+    {
+      "epoch": 0.044534928107901765,
+      "grad_norm": 1.4632848501205444,
+      "learning_rate": 2.2203842728082453e-06,
+      "loss": 0.037,
+      "step": 350
+    },
+    {
+      "epoch": 0.04580735462527039,
+      "grad_norm": 1.3355021476745605,
+      "learning_rate": 2.2840055986766767e-06,
+      "loss": 0.0409,
+      "step": 360
+    },
+    {
+      "epoch": 0.04707978114263901,
+      "grad_norm": 2.0859885215759277,
+      "learning_rate": 2.3476269245451077e-06,
+      "loss": 0.0305,
+      "step": 370
+    },
+    {
+      "epoch": 0.04835220766000763,
+      "grad_norm": 1.3638544082641602,
+      "learning_rate": 2.4112482504135386e-06,
+      "loss": 0.0331,
+      "step": 380
+    },
+    {
+      "epoch": 0.04962463417737625,
+      "grad_norm": 0.41071686148643494,
+      "learning_rate": 2.47486957628197e-06,
+      "loss": 0.03,
+      "step": 390
+    },
+    {
+      "epoch": 0.05089706069474488,
+      "grad_norm": 0.8771544098854065,
+      "learning_rate": 2.538490902150401e-06,
+      "loss": 0.0306,
+      "step": 400
+    },
+    {
+      "epoch": 0.0521694872121135,
+      "grad_norm": 0.6460317373275757,
+      "learning_rate": 2.602112228018832e-06,
+      "loss": 0.0311,
+      "step": 410
+    },
+    {
+      "epoch": 0.05344191372948212,
+      "grad_norm": 0.19301742315292358,
+      "learning_rate": 2.6657335538872634e-06,
+      "loss": 0.0138,
+      "step": 420
+    },
+    {
+      "epoch": 0.05471434024685074,
+      "grad_norm": 2.0089757442474365,
+      "learning_rate": 2.7293548797556944e-06,
+      "loss": 0.0255,
+      "step": 430
+    },
+    {
+      "epoch": 0.05598676676421937,
+      "grad_norm": 0.8393608927726746,
+      "learning_rate": 2.7929762056241254e-06,
+      "loss": 0.0206,
+      "step": 440
+    },
+    {
+      "epoch": 0.05725919328158799,
+      "grad_norm": 0.8323113322257996,
+      "learning_rate": 2.8565975314925564e-06,
+      "loss": 0.0148,
+      "step": 450
+    },
+    {
+      "epoch": 0.05853161979895661,
+      "grad_norm": 1.5697057247161865,
+      "learning_rate": 2.9202188573609878e-06,
+      "loss": 0.0258,
+      "step": 460
+    },
+    {
+      "epoch": 0.05980404631632523,
+      "grad_norm": 0.22127273678779602,
+      "learning_rate": 2.9838401832294188e-06,
+      "loss": 0.0195,
+      "step": 470
+    },
+    {
+      "epoch": 0.06107647283369386,
+      "grad_norm": 1.421794056892395,
+      "learning_rate": 3.0474615090978497e-06,
+      "loss": 0.0202,
+      "step": 480
+    },
+    {
+      "epoch": 0.06234889935106248,
+      "grad_norm": 2.1492910385131836,
+      "learning_rate": 3.1110828349662807e-06,
+      "loss": 0.0244,
+      "step": 490
+    },
+    {
+      "epoch": 0.0636213258684311,
+      "grad_norm": 0.09726544469594955,
+      "learning_rate": 3.174704160834712e-06,
+      "loss": 0.0257,
+      "step": 500
+    },
+    {
+      "epoch": 0.06489375238579972,
+      "grad_norm": 0.5567276477813721,
+      "learning_rate": 3.2383254867031427e-06,
+      "loss": 0.0103,
+      "step": 510
+    },
+    {
+      "epoch": 0.06616617890316834,
+      "grad_norm": 0.857915997505188,
+      "learning_rate": 3.301946812571574e-06,
+      "loss": 0.0198,
+      "step": 520
+    },
+    {
+      "epoch": 0.06743860542053697,
+      "grad_norm": 2.1099727153778076,
+      "learning_rate": 3.3655681384400055e-06,
+      "loss": 0.0169,
+      "step": 530
+    },
+    {
+      "epoch": 0.06871103193790559,
+      "grad_norm": 0.35235458612442017,
+      "learning_rate": 3.429189464308436e-06,
+      "loss": 0.0169,
+      "step": 540
+    },
+    {
+      "epoch": 0.0699834584552742,
+      "grad_norm": 0.27329525351524353,
+      "learning_rate": 3.4928107901768675e-06,
+      "loss": 0.025,
+      "step": 550
+    },
+    {
+      "epoch": 0.07125588497264283,
+      "grad_norm": 1.0509276390075684,
+      "learning_rate": 3.556432116045299e-06,
+      "loss": 0.0143,
+      "step": 560
+    },
+    {
+      "epoch": 0.07252831149001145,
+      "grad_norm": 2.021751880645752,
+      "learning_rate": 3.6200534419137294e-06,
+      "loss": 0.0248,
+      "step": 570
+    },
+    {
+      "epoch": 0.07380073800738007,
+      "grad_norm": 0.9538995027542114,
+      "learning_rate": 3.683674767782161e-06,
+      "loss": 0.0234,
+      "step": 580
+    },
+    {
+      "epoch": 0.0750731645247487,
+      "grad_norm": 1.5769826173782349,
+      "learning_rate": 3.7472960936505914e-06,
+      "loss": 0.0173,
+      "step": 590
+    },
+    {
+      "epoch": 0.07634559104211731,
+      "grad_norm": 1.1721569299697876,
+      "learning_rate": 3.810917419519023e-06,
+      "loss": 0.0283,
+      "step": 600
+    },
+    {
+      "epoch": 0.07761801755948594,
+      "grad_norm": 0.1278325915336609,
+      "learning_rate": 3.874538745387454e-06,
+      "loss": 0.01,
+      "step": 610
+    },
+    {
+      "epoch": 0.07889044407685457,
+      "grad_norm": 1.5084667205810547,
+      "learning_rate": 3.938160071255885e-06,
+      "loss": 0.0152,
+      "step": 620
+    },
+    {
+      "epoch": 0.08016287059422318,
+      "grad_norm": 0.1045418232679367,
+      "learning_rate": 4.001781397124316e-06,
+      "loss": 0.0196,
+      "step": 630
+    },
+    {
+      "epoch": 0.08143529711159181,
+      "grad_norm": 0.1617429554462433,
+      "learning_rate": 4.065402722992747e-06,
+      "loss": 0.0215,
+      "step": 640
+    },
+    {
+      "epoch": 0.08270772362896042,
+      "grad_norm": 0.11483286321163177,
+      "learning_rate": 4.129024048861178e-06,
+      "loss": 0.0206,
+      "step": 650
+    },
+    {
+      "epoch": 0.08398015014632905,
+      "grad_norm": 0.3859212100505829,
+      "learning_rate": 4.1926453747296096e-06,
+      "loss": 0.0067,
+      "step": 660
+    },
+    {
+      "epoch": 0.08525257666369768,
+      "grad_norm": 0.23510600626468658,
+      "learning_rate": 4.25626670059804e-06,
+      "loss": 0.0213,
+      "step": 670
+    },
+    {
+      "epoch": 0.08652500318106629,
+      "grad_norm": 1.86430823802948,
+      "learning_rate": 4.3198880264664715e-06,
+      "loss": 0.0217,
+      "step": 680
+    },
+    {
+      "epoch": 0.08779742969843492,
+      "grad_norm": 1.0131075382232666,
+      "learning_rate": 4.383509352334903e-06,
+      "loss": 0.0143,
+      "step": 690
+    },
+    {
+      "epoch": 0.08906985621580353,
+      "grad_norm": 0.29921114444732666,
+      "learning_rate": 4.4471306782033335e-06,
+      "loss": 0.0169,
+      "step": 700
+    },
+    {
+      "epoch": 0.09034228273317216,
+      "grad_norm": 0.39632511138916016,
+      "learning_rate": 4.510752004071765e-06,
+      "loss": 0.0091,
+      "step": 710
+    },
+    {
+      "epoch": 0.09161470925054079,
+      "grad_norm": 0.1986786276102066,
+      "learning_rate": 4.5743733299401955e-06,
+      "loss": 0.0077,
+      "step": 720
+    },
+    {
+      "epoch": 0.0928871357679094,
+      "grad_norm": 1.939620852470398,
+      "learning_rate": 4.637994655808627e-06,
+      "loss": 0.0182,
+      "step": 730
+    },
+    {
+      "epoch": 0.09415956228527803,
+      "grad_norm": 2.1149661540985107,
+      "learning_rate": 4.701615981677058e-06,
+      "loss": 0.0235,
+      "step": 740
+    },
+    {
+      "epoch": 0.09543198880264665,
+      "grad_norm": 0.03329145163297653,
+      "learning_rate": 4.765237307545489e-06,
+      "loss": 0.0172,
+      "step": 750
+    },
+    {
+      "epoch": 0.09670441532001527,
+      "grad_norm": 1.470470905303955,
+      "learning_rate": 4.82885863341392e-06,
+      "loss": 0.0178,
+      "step": 760
+    },
+    {
+      "epoch": 0.0979768418373839,
+      "grad_norm": 1.055908441543579,
+      "learning_rate": 4.892479959282352e-06,
+      "loss": 0.0133,
+      "step": 770
+    },
+    {
+      "epoch": 0.0992492683547525,
+      "grad_norm": 2.2330827713012695,
+      "learning_rate": 4.956101285150783e-06,
+      "loss": 0.0102,
+      "step": 780
+    },
+    {
+      "epoch": 0.10052169487212113,
+      "grad_norm": 0.20729655027389526,
+      "learning_rate": 5.019722611019214e-06,
+      "loss": 0.0081,
+      "step": 790
+    },
+    {
+      "epoch": 0.10179412138948976,
+      "grad_norm": 0.1920371800661087,
+      "learning_rate": 5.083343936887645e-06,
+      "loss": 0.0081,
+      "step": 800
+    },
+    {
+      "epoch": 0.10306654790685837,
+      "grad_norm": 0.5931546092033386,
+      "learning_rate": 5.1469652627560764e-06,
+      "loss": 0.0313,
+      "step": 810
+    },
+    {
+      "epoch": 0.104338974424227,
+      "grad_norm": 1.6505730152130127,
+      "learning_rate": 5.210586588624507e-06,
+      "loss": 0.01,
+      "step": 820
+    },
+    {
+      "epoch": 0.10561140094159563,
+      "grad_norm": 1.3409397602081299,
+      "learning_rate": 5.274207914492938e-06,
+      "loss": 0.0182,
+      "step": 830
+    },
+    {
+      "epoch": 0.10688382745896424,
+      "grad_norm": 0.2508680820465088,
+      "learning_rate": 5.33782924036137e-06,
+      "loss": 0.0108,
+      "step": 840
+    },
+    {
+      "epoch": 0.10815625397633287,
+      "grad_norm": 0.7329053282737732,
+      "learning_rate": 5.401450566229801e-06,
+      "loss": 0.0168,
+      "step": 850
+    },
+    {
+      "epoch": 0.10942868049370148,
+      "grad_norm": 0.12235169112682343,
+      "learning_rate": 5.465071892098232e-06,
+      "loss": 0.0149,
+      "step": 860
+    },
+    {
+      "epoch": 0.11070110701107011,
+      "grad_norm": 0.058564718812704086,
+      "learning_rate": 5.528693217966663e-06,
+      "loss": 0.0148,
+      "step": 870
+    },
+    {
+      "epoch": 0.11197353352843874,
+      "grad_norm": 0.6761524081230164,
+      "learning_rate": 5.592314543835094e-06,
+      "loss": 0.0131,
+      "step": 880
+    },
+    {
+      "epoch": 0.11324596004580735,
+      "grad_norm": 0.7170369029045105,
+      "learning_rate": 5.655935869703525e-06,
+      "loss": 0.0121,
+      "step": 890
+    },
+    {
+      "epoch": 0.11451838656317598,
+      "grad_norm": 0.5446187257766724,
+      "learning_rate": 5.7195571955719566e-06,
+      "loss": 0.0126,
+      "step": 900
+    },
+    {
+      "epoch": 0.1157908130805446,
+      "grad_norm": 0.03237615525722504,
+      "learning_rate": 5.783178521440387e-06,
+      "loss": 0.0043,
+      "step": 910
+    },
+    {
+      "epoch": 0.11706323959791322,
+      "grad_norm": 0.4705624580383301,
+      "learning_rate": 5.8467998473088185e-06,
+      "loss": 0.0122,
+      "step": 920
+    },
+    {
+      "epoch": 0.11833566611528185,
+      "grad_norm": 0.8848108053207397,
+      "learning_rate": 5.91042117317725e-06,
+      "loss": 0.0184,
+      "step": 930
+    },
+    {
+      "epoch": 0.11960809263265046,
+      "grad_norm": 0.5390125513076782,
+      "learning_rate": 5.9740424990456805e-06,
+      "loss": 0.0093,
+      "step": 940
+    },
+    {
+      "epoch": 0.12088051915001909,
+      "grad_norm": 0.38235408067703247,
+      "learning_rate": 6.037663824914112e-06,
+      "loss": 0.0264,
+      "step": 950
+    },
+    {
+      "epoch": 0.12215294566738771,
+      "grad_norm": 0.07413897663354874,
+      "learning_rate": 6.1012851507825425e-06,
+      "loss": 0.0154,
+      "step": 960
+    },
+    {
+      "epoch": 0.12342537218475633,
+      "grad_norm": 0.08041392266750336,
+      "learning_rate": 6.164906476650974e-06,
+      "loss": 0.0094,
+      "step": 970
+    },
+    {
+      "epoch": 0.12469779870212495,
+      "grad_norm": 0.4950060546398163,
+      "learning_rate": 6.228527802519405e-06,
+      "loss": 0.0078,
+      "step": 980
+    },
+    {
+      "epoch": 0.12597022521949358,
+      "grad_norm": 0.028932543471455574,
+      "learning_rate": 6.292149128387837e-06,
+      "loss": 0.0115,
+      "step": 990
+    },
+    {
+      "epoch": 0.1272426517368622,
+      "grad_norm": 1.5096838474273682,
+      "learning_rate": 6.355770454256267e-06,
+      "loss": 0.0165,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1285150782542308,
+      "grad_norm": 0.11332298815250397,
+      "learning_rate": 6.419391780124698e-06,
+      "loss": 0.0095,
+      "step": 1010
+    },
+    {
+      "epoch": 0.12978750477159945,
+      "grad_norm": 0.6465795040130615,
+      "learning_rate": 6.48301310599313e-06,
+      "loss": 0.0195,
+      "step": 1020
+    },
+    {
+      "epoch": 0.13105993128896806,
+      "grad_norm": 0.25017666816711426,
+      "learning_rate": 6.546634431861561e-06,
+      "loss": 0.0061,
+      "step": 1030
+    },
+    {
+      "epoch": 0.13233235780633668,
+      "grad_norm": 1.8187178373336792,
+      "learning_rate": 6.610255757729991e-06,
+      "loss": 0.0138,
+      "step": 1040
+    },
+    {
+      "epoch": 0.13360478432370532,
+      "grad_norm": 3.078958749771118,
+      "learning_rate": 6.673877083598422e-06,
+      "loss": 0.0141,
+      "step": 1050
+    },
+    {
+      "epoch": 0.13487721084107393,
+      "grad_norm": 0.8495808839797974,
+      "learning_rate": 6.737498409466854e-06,
+      "loss": 0.0277,
+      "step": 1060
+    },
+    {
+      "epoch": 0.13614963735844254,
+      "grad_norm": 0.30749642848968506,
+      "learning_rate": 6.8011197353352845e-06,
+      "loss": 0.0062,
+      "step": 1070
+    },
+    {
+      "epoch": 0.13742206387581118,
+      "grad_norm": 0.13450919091701508,
+      "learning_rate": 6.864741061203715e-06,
+      "loss": 0.0162,
+      "step": 1080
+    },
+    {
+      "epoch": 0.1386944903931798,
+      "grad_norm": 0.32650208473205566,
+      "learning_rate": 6.928362387072147e-06,
+      "loss": 0.0111,
+      "step": 1090
+    },
+    {
+      "epoch": 0.1399669169105484,
+      "grad_norm": 0.04899647459387779,
+      "learning_rate": 6.991983712940578e-06,
+      "loss": 0.0027,
+      "step": 1100
+    },
+    {
+      "epoch": 0.14123934342791702,
+      "grad_norm": 0.06836508959531784,
+      "learning_rate": 7.0556050388090085e-06,
+      "loss": 0.0089,
+      "step": 1110
+    },
+    {
+      "epoch": 0.14251176994528567,
+      "grad_norm": 0.7668923139572144,
+      "learning_rate": 7.119226364677441e-06,
+      "loss": 0.0035,
+      "step": 1120
+    },
+    {
+      "epoch": 0.14378419646265428,
+      "grad_norm": 0.05036250501871109,
+      "learning_rate": 7.182847690545871e-06,
+      "loss": 0.0063,
+      "step": 1130
+    },
+    {
+      "epoch": 0.1450566229800229,
+      "grad_norm": 0.08341695368289948,
+      "learning_rate": 7.246469016414302e-06,
+      "loss": 0.0044,
+      "step": 1140
+    },
+    {
+      "epoch": 0.14632904949739153,
+      "grad_norm": 2.2805428504943848,
+      "learning_rate": 7.310090342282734e-06,
+      "loss": 0.0151,
+      "step": 1150
+    },
+    {
+      "epoch": 0.14760147601476015,
+      "grad_norm": 0.007249306421726942,
+      "learning_rate": 7.373711668151165e-06,
+      "loss": 0.006,
+      "step": 1160
+    },
+    {
+      "epoch": 0.14887390253212876,
+      "grad_norm": 0.09136034548282623,
+      "learning_rate": 7.437332994019595e-06,
+      "loss": 0.0117,
+      "step": 1170
+    },
+    {
+      "epoch": 0.1501463290494974,
+      "grad_norm": 0.3426164984703064,
+      "learning_rate": 7.5009543198880275e-06,
+      "loss": 0.0146,
+      "step": 1180
+    },
+    {
+      "epoch": 0.15141875556686601,
+      "grad_norm": 0.11082851141691208,
+      "learning_rate": 7.564575645756458e-06,
+      "loss": 0.027,
+      "step": 1190
+    },
+    {
+      "epoch": 0.15269118208423463,
+      "grad_norm": 0.05444815009832382,
+      "learning_rate": 7.628196971624889e-06,
+      "loss": 0.0184,
+      "step": 1200
+    },
+    {
+      "epoch": 0.15396360860160327,
+      "grad_norm": 0.7797910571098328,
+      "learning_rate": 7.69181829749332e-06,
+      "loss": 0.0058,
+      "step": 1210
+    },
+    {
+      "epoch": 0.15523603511897188,
+      "grad_norm": 0.05821133777499199,
+      "learning_rate": 7.755439623361751e-06,
+      "loss": 0.0113,
+      "step": 1220
+    },
+    {
+      "epoch": 0.1565084616363405,
+      "grad_norm": 0.03613057732582092,
+      "learning_rate": 7.819060949230183e-06,
+      "loss": 0.0075,
+      "step": 1230
+    },
+    {
+      "epoch": 0.15778088815370914,
+      "grad_norm": 0.21981610357761383,
+      "learning_rate": 7.882682275098613e-06,
+      "loss": 0.0101,
+      "step": 1240
+    },
+    {
+      "epoch": 0.15905331467107775,
+      "grad_norm": 0.20088253915309906,
+      "learning_rate": 7.946303600967046e-06,
+      "loss": 0.0042,
+      "step": 1250
+    },
+    {
+      "epoch": 0.16032574118844636,
+      "grad_norm": 0.07598040997982025,
+      "learning_rate": 8.009924926835475e-06,
+      "loss": 0.0072,
+      "step": 1260
+    },
+    {
+      "epoch": 0.16159816770581498,
+      "grad_norm": 0.12485750019550323,
+      "learning_rate": 8.073546252703907e-06,
+      "loss": 0.005,
+      "step": 1270
+    },
+    {
+      "epoch": 0.16287059422318362,
+      "grad_norm": 0.23695872724056244,
+      "learning_rate": 8.137167578572338e-06,
+      "loss": 0.0058,
+      "step": 1280
+    },
+    {
+      "epoch": 0.16414302074055223,
+      "grad_norm": 0.5497035384178162,
+      "learning_rate": 8.20078890444077e-06,
+      "loss": 0.0048,
+      "step": 1290
+    },
+    {
+      "epoch": 0.16541544725792084,
+      "grad_norm": 0.11535526812076569,
+      "learning_rate": 8.2644102303092e-06,
+      "loss": 0.0162,
+      "step": 1300
+    },
+    {
+      "epoch": 0.16668787377528949,
+      "grad_norm": 0.24588041007518768,
+      "learning_rate": 8.328031556177632e-06,
+      "loss": 0.0167,
+      "step": 1310
+    },
+    {
+      "epoch": 0.1679603002926581,
+      "grad_norm": 0.02810610644519329,
+      "learning_rate": 8.391652882046062e-06,
+      "loss": 0.015,
+      "step": 1320
+    },
+    {
+      "epoch": 0.1692327268100267,
+      "grad_norm": 1.970468282699585,
+      "learning_rate": 8.455274207914494e-06,
+      "loss": 0.0086,
+      "step": 1330
+    },
+    {
+      "epoch": 0.17050515332739535,
+      "grad_norm": 1.3369934558868408,
+      "learning_rate": 8.518895533782923e-06,
+      "loss": 0.0047,
+      "step": 1340
+    },
+    {
+      "epoch": 0.17177757984476397,
+      "grad_norm": 1.4428670406341553,
+      "learning_rate": 8.582516859651356e-06,
+      "loss": 0.0055,
+      "step": 1350
+    },
+    {
+      "epoch": 0.17305000636213258,
+      "grad_norm": 1.5606224536895752,
+      "learning_rate": 8.646138185519786e-06,
+      "loss": 0.0124,
+      "step": 1360
+    },
+    {
+      "epoch": 0.17432243287950122,
+      "grad_norm": 0.1116681918501854,
+      "learning_rate": 8.709759511388217e-06,
+      "loss": 0.0065,
+      "step": 1370
+    },
+    {
+      "epoch": 0.17559485939686983,
+      "grad_norm": 1.1111221313476562,
+      "learning_rate": 8.773380837256649e-06,
+      "loss": 0.0118,
+      "step": 1380
+    },
+    {
+      "epoch": 0.17686728591423845,
+      "grad_norm": 0.028176436200737953,
+      "learning_rate": 8.83700216312508e-06,
+      "loss": 0.004,
+      "step": 1390
+    },
+    {
+      "epoch": 0.17813971243160706,
+      "grad_norm": 0.046109430491924286,
+      "learning_rate": 8.90062348899351e-06,
+      "loss": 0.0065,
+      "step": 1400
+    },
+    {
+      "epoch": 0.1794121389489757,
+      "grad_norm": 0.23842725157737732,
+      "learning_rate": 8.964244814861943e-06,
+      "loss": 0.0039,
+      "step": 1410
+    },
+    {
+      "epoch": 0.18068456546634432,
+      "grad_norm": 0.07986653596162796,
+      "learning_rate": 9.027866140730373e-06,
+      "loss": 0.0062,
+      "step": 1420
+    },
+    {
+      "epoch": 0.18195699198371293,
+      "grad_norm": 0.028882242739200592,
+      "learning_rate": 9.091487466598804e-06,
+      "loss": 0.0104,
+      "step": 1430
+    },
+    {
+      "epoch": 0.18322941850108157,
+      "grad_norm": 0.054946914315223694,
+      "learning_rate": 9.155108792467236e-06,
+      "loss": 0.0107,
+      "step": 1440
+    },
+    {
+      "epoch": 0.18450184501845018,
+      "grad_norm": 0.15618978440761566,
+      "learning_rate": 9.218730118335667e-06,
+      "loss": 0.0122,
+      "step": 1450
+    },
+    {
+      "epoch": 0.1857742715358188,
+      "grad_norm": 0.1851753294467926,
+      "learning_rate": 9.282351444204097e-06,
+      "loss": 0.0065,
+      "step": 1460
+    },
+    {
+      "epoch": 0.18704669805318744,
+      "grad_norm": 0.2444417029619217,
+      "learning_rate": 9.34597277007253e-06,
+      "loss": 0.0092,
+      "step": 1470
+    },
+    {
+      "epoch": 0.18831912457055605,
+      "grad_norm": 1.1832714080810547,
+      "learning_rate": 9.40959409594096e-06,
+      "loss": 0.0041,
+      "step": 1480
+    },
+    {
+      "epoch": 0.18959155108792466,
+      "grad_norm": 0.20352864265441895,
+      "learning_rate": 9.473215421809391e-06,
+      "loss": 0.0138,
+      "step": 1490
+    },
+    {
+      "epoch": 0.1908639776052933,
+      "grad_norm": 0.43454509973526,
+      "learning_rate": 9.53683674767782e-06,
+      "loss": 0.0127,
+      "step": 1500
+    },
+    {
+      "epoch": 0.19213640412266192,
+      "grad_norm": 0.8199312686920166,
+      "learning_rate": 9.600458073546254e-06,
+      "loss": 0.0123,
+      "step": 1510
+    },
+    {
+      "epoch": 0.19340883064003053,
+      "grad_norm": 0.016706250607967377,
+      "learning_rate": 9.664079399414683e-06,
+      "loss": 0.0127,
+      "step": 1520
+    },
+    {
+      "epoch": 0.19468125715739917,
+      "grad_norm": 1.3700906038284302,
+      "learning_rate": 9.727700725283115e-06,
+      "loss": 0.0082,
+      "step": 1530
+    },
+    {
+      "epoch": 0.1959536836747678,
+      "grad_norm": 0.05637359619140625,
+      "learning_rate": 9.791322051151546e-06,
+      "loss": 0.0229,
+      "step": 1540
+    },
+    {
+      "epoch": 0.1972261101921364,
+      "grad_norm": 0.05423460528254509,
+      "learning_rate": 9.854943377019978e-06,
+      "loss": 0.0067,
+      "step": 1550
+    },
+    {
+      "epoch": 0.198498536709505,
+      "grad_norm": 0.4112365245819092,
+      "learning_rate": 9.918564702888407e-06,
+      "loss": 0.0145,
+      "step": 1560
+    },
+    {
+      "epoch": 0.19977096322687365,
+      "grad_norm": 0.3613516092300415,
+      "learning_rate": 9.98218602875684e-06,
+      "loss": 0.0045,
+      "step": 1570
+    },
+    {
+      "epoch": 0.20104338974424227,
+      "grad_norm": 0.20391610264778137,
+      "learning_rate": 1.004580735462527e-05,
+      "loss": 0.0159,
+      "step": 1580
+    },
+    {
+      "epoch": 0.20231581626161088,
+      "grad_norm": 0.5387713313102722,
+      "learning_rate": 1.0109428680493702e-05,
+      "loss": 0.0136,
+      "step": 1590
+    },
+    {
+      "epoch": 0.20358824277897952,
+      "grad_norm": 0.14269393682479858,
+      "learning_rate": 1.0173050006362133e-05,
+      "loss": 0.0065,
+      "step": 1600
+    },
+    {
+      "epoch": 0.20486066929634814,
+      "grad_norm": 1.532262921333313,
+      "learning_rate": 1.0236671332230564e-05,
+      "loss": 0.0275,
+      "step": 1610
+    },
+    {
+      "epoch": 0.20613309581371675,
+      "grad_norm": 2.2569189071655273,
+      "learning_rate": 1.0300292658098996e-05,
+      "loss": 0.0165,
+      "step": 1620
+    },
+    {
+      "epoch": 0.2074055223310854,
+      "grad_norm": 0.21518416702747345,
+      "learning_rate": 1.0363913983967426e-05,
+      "loss": 0.0158,
+      "step": 1630
+    },
+    {
+      "epoch": 0.208677948848454,
+      "grad_norm": 0.041043154895305634,
+      "learning_rate": 1.0427535309835857e-05,
+      "loss": 0.0101,
+      "step": 1640
+    },
+    {
+      "epoch": 0.20995037536582262,
+      "grad_norm": 0.030664950609207153,
+      "learning_rate": 1.0491156635704288e-05,
+      "loss": 0.003,
+      "step": 1650
+    },
+    {
+      "epoch": 0.21122280188319126,
+      "grad_norm": 0.03374583646655083,
+      "learning_rate": 1.055477796157272e-05,
+      "loss": 0.0115,
+      "step": 1660
+    },
+    {
+      "epoch": 0.21249522840055987,
+      "grad_norm": 0.020480433478951454,
+      "learning_rate": 1.0618399287441151e-05,
+      "loss": 0.0039,
+      "step": 1670
+    },
+    {
+      "epoch": 0.21376765491792848,
+      "grad_norm": 0.04108405113220215,
+      "learning_rate": 1.0682020613309583e-05,
+      "loss": 0.0142,
+      "step": 1680
+    },
+    {
+      "epoch": 0.2150400814352971,
+      "grad_norm": 0.0639573484659195,
+      "learning_rate": 1.0745641939178012e-05,
+      "loss": 0.0053,
+      "step": 1690
+    },
+    {
+      "epoch": 0.21631250795266574,
+      "grad_norm": 1.848137378692627,
+      "learning_rate": 1.0809263265046444e-05,
+      "loss": 0.0071,
+      "step": 1700
+    },
+    {
+      "epoch": 0.21758493447003435,
+      "grad_norm": 0.271002858877182,
+      "learning_rate": 1.0872884590914875e-05,
+      "loss": 0.0096,
+      "step": 1710
+    },
+    {
+      "epoch": 0.21885736098740297,
+      "grad_norm": 0.02884743921458721,
+      "learning_rate": 1.0936505916783307e-05,
+      "loss": 0.0064,
+      "step": 1720
+    },
+    {
+      "epoch": 0.2201297875047716,
+      "grad_norm": 0.033135417848825455,
+      "learning_rate": 1.1000127242651738e-05,
+      "loss": 0.0122,
+      "step": 1730
+    },
+    {
+      "epoch": 0.22140221402214022,
+      "grad_norm": 0.10254822671413422,
+      "learning_rate": 1.106374856852017e-05,
+      "loss": 0.0095,
+      "step": 1740
+    },
+    {
+      "epoch": 0.22267464053950883,
+      "grad_norm": 0.023600544780492783,
+      "learning_rate": 1.1127369894388599e-05,
+      "loss": 0.0046,
+      "step": 1750
+    },
+    {
+      "epoch": 0.22394706705687747,
+      "grad_norm": 0.24926574528217316,
+      "learning_rate": 1.1190991220257032e-05,
+      "loss": 0.0034,
+      "step": 1760
+    },
+    {
+      "epoch": 0.2252194935742461,
+      "grad_norm": 0.11188559979200363,
+      "learning_rate": 1.1254612546125462e-05,
+      "loss": 0.0075,
+      "step": 1770
+    },
+    {
+      "epoch": 0.2264919200916147,
+      "grad_norm": 1.826882004737854,
+      "learning_rate": 1.1318233871993893e-05,
+      "loss": 0.0072,
+      "step": 1780
+    },
+    {
+      "epoch": 0.22776434660898334,
+      "grad_norm": 0.21881231665611267,
+      "learning_rate": 1.1381855197862323e-05,
+      "loss": 0.0079,
+      "step": 1790
+    },
+    {
+      "epoch": 0.22903677312635196,
+      "grad_norm": 0.031731124967336655,
+      "learning_rate": 1.1445476523730756e-05,
+      "loss": 0.0021,
+      "step": 1800
+    },
+    {
+      "epoch": 0.23030919964372057,
+      "grad_norm": 0.017091596499085426,
+      "learning_rate": 1.1509097849599186e-05,
+      "loss": 0.0041,
+      "step": 1810
+    },
+    {
+      "epoch": 0.2315816261610892,
+      "grad_norm": 2.5410568714141846,
+      "learning_rate": 1.1572719175467617e-05,
+      "loss": 0.0083,
+      "step": 1820
+    },
+    {
+      "epoch": 0.23285405267845782,
+      "grad_norm": 0.5720783472061157,
+      "learning_rate": 1.1636340501336049e-05,
+      "loss": 0.0065,
+      "step": 1830
+    },
+    {
+      "epoch": 0.23412647919582644,
+      "grad_norm": 0.1771746128797531,
+      "learning_rate": 1.169996182720448e-05,
+      "loss": 0.0051,
+      "step": 1840
+    },
+    {
+      "epoch": 0.23539890571319505,
+      "grad_norm": 0.3735668659210205,
+      "learning_rate": 1.176358315307291e-05,
+      "loss": 0.0037,
+      "step": 1850
+    },
+    {
+      "epoch": 0.2366713322305637,
+      "grad_norm": 0.025163499638438225,
+      "learning_rate": 1.1827204478941343e-05,
+      "loss": 0.0039,
+      "step": 1860
+    },
+    {
+      "epoch": 0.2379437587479323,
+      "grad_norm": 0.3122095465660095,
+      "learning_rate": 1.1890825804809773e-05,
+      "loss": 0.0026,
+      "step": 1870
+    },
+    {
+      "epoch": 0.23921618526530092,
+      "grad_norm": 0.5866298079490662,
+      "learning_rate": 1.1954447130678204e-05,
+      "loss": 0.0027,
+      "step": 1880
+    },
+    {
+      "epoch": 0.24048861178266956,
+      "grad_norm": 0.18981511890888214,
+      "learning_rate": 1.2018068456546635e-05,
+      "loss": 0.0111,
+      "step": 1890
+    },
+    {
+      "epoch": 0.24176103830003817,
+      "grad_norm": 0.4353330135345459,
+      "learning_rate": 1.2081689782415067e-05,
+      "loss": 0.0053,
+      "step": 1900
+    },
+    {
+      "epoch": 0.24303346481740679,
+      "grad_norm": 1.369036316871643,
+      "learning_rate": 1.2145311108283496e-05,
+      "loss": 0.0193,
+      "step": 1910
+    },
+    {
+      "epoch": 0.24430589133477543,
+      "grad_norm": 0.13712532818317413,
+      "learning_rate": 1.220893243415193e-05,
+      "loss": 0.0169,
+      "step": 1920
+    },
+    {
+      "epoch": 0.24557831785214404,
+      "grad_norm": 0.05920857936143875,
+      "learning_rate": 1.227255376002036e-05,
+      "loss": 0.0184,
+      "step": 1930
+    },
+    {
+      "epoch": 0.24685074436951265,
+      "grad_norm": 0.021631982177495956,
+      "learning_rate": 1.233617508588879e-05,
+      "loss": 0.0066,
+      "step": 1940
+    },
+    {
+      "epoch": 0.2481231708868813,
+      "grad_norm": 0.16193988919258118,
+      "learning_rate": 1.239979641175722e-05,
+      "loss": 0.0121,
+      "step": 1950
+    },
+    {
+      "epoch": 0.2493955974042499,
+      "grad_norm": 0.02966451644897461,
+      "learning_rate": 1.2463417737625654e-05,
+      "loss": 0.0113,
+      "step": 1960
+    },
+    {
+      "epoch": 0.2506680239216185,
+      "grad_norm": 0.1511862426996231,
+      "learning_rate": 1.2527039063494083e-05,
+      "loss": 0.0044,
+      "step": 1970
+    },
+    {
+      "epoch": 0.25194045043898716,
+      "grad_norm": 0.06729118525981903,
+      "learning_rate": 1.2590660389362516e-05,
+      "loss": 0.004,
+      "step": 1980
+    },
+    {
+      "epoch": 0.25321287695635575,
+      "grad_norm": 0.023136969655752182,
+      "learning_rate": 1.2654281715230944e-05,
+      "loss": 0.0033,
+      "step": 1990
+    },
+    {
+      "epoch": 0.2544853034737244,
+      "grad_norm": 0.4016958177089691,
+      "learning_rate": 1.2717903041099377e-05,
+      "loss": 0.0073,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 78590,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.900242344210596e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

MS_Marco_ep10/checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7c3a81dbd821ff62fe2820db3a336ec894be47026ddefd26dc3159ee1f50881
+size 5841