Training in progress, step 800, checkpoint

checkpoint-800/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen3.6-27B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.6-27B
+- 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 0.20.0

checkpoint-800/adapter_config.json

@@ -0,0 +1,53 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.6-27B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "out_proj",
+    "up_proj",
+    "in_proj_qkv",
+    "down_proj",
+    "in_proj_z",
+    "v_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true,
+  "velora_config": null
+}

checkpoint-800/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e37ebd29de3b3b07d068d2217fe41065f8bcb06edbb17798d3936d83703f293
+size 1740746640

checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7254aef74fc12d169f036163c390b9f72ea8a06bb9cd793b73c6e6fce32cae9
+size 3481950275

checkpoint-800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:363c5df1543d2c82b2f13164f35bdd0367ceb32e7fa1b2f67c19df073a08b17b
+size 14645

checkpoint-800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a519034a962cca96ddd3586bd53bebb01c25b993c57ea68ba94d5cceb36d8b0
+size 1529

checkpoint-800/trainer_state.json

@@ -0,0 +1,1218 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8321414640488883,
+  "eval_steps": 100,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005200884150305552,
+      "grad_norm": 4.82585334777832,
+      "learning_rate": 5.6140350877192985e-06,
+      "loss": 0.7676299571990967,
+      "step": 5
+    },
+    {
+      "epoch": 0.010401768300611104,
+      "grad_norm": 3.292309522628784,
+      "learning_rate": 1.263157894736842e-05,
+      "loss": 0.631245470046997,
+      "step": 10
+    },
+    {
+      "epoch": 0.015602652450916656,
+      "grad_norm": 3.0301995277404785,
+      "learning_rate": 1.9649122807017544e-05,
+      "loss": 0.6749040126800537,
+      "step": 15
+    },
+    {
+      "epoch": 0.02080353660122221,
+      "grad_norm": 2.853067398071289,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.7889204978942871,
+      "step": 20
+    },
+    {
+      "epoch": 0.02600442075152776,
+      "grad_norm": 2.4595491886138916,
+      "learning_rate": 3.368421052631579e-05,
+      "loss": 0.8261689186096192,
+      "step": 25
+    },
+    {
+      "epoch": 0.031205304901833313,
+      "grad_norm": 3.285839319229126,
+      "learning_rate": 4.070175438596492e-05,
+      "loss": 0.8855669021606445,
+      "step": 30
+    },
+    {
+      "epoch": 0.03640618905213886,
+      "grad_norm": 2.9381635189056396,
+      "learning_rate": 4.771929824561404e-05,
+      "loss": 0.8640634536743164,
+      "step": 35
+    },
+    {
+      "epoch": 0.04160707320244442,
+      "grad_norm": 2.142974376678467,
+      "learning_rate": 5.4736842105263165e-05,
+      "loss": 0.8938538551330566,
+      "step": 40
+    },
+    {
+      "epoch": 0.046807957352749965,
+      "grad_norm": 3.4374115467071533,
+      "learning_rate": 6.175438596491228e-05,
+      "loss": 0.9762144088745117,
+      "step": 45
+    },
+    {
+      "epoch": 0.05200884150305552,
+      "grad_norm": 2.2888057231903076,
+      "learning_rate": 6.87719298245614e-05,
+      "loss": 1.0100465774536134,
+      "step": 50
+    },
+    {
+      "epoch": 0.05720972565336107,
+      "grad_norm": 2.101193428039551,
+      "learning_rate": 7.578947368421052e-05,
+      "loss": 1.0064237594604493,
+      "step": 55
+    },
+    {
+      "epoch": 0.062410609803666625,
+      "grad_norm": 2.3019754886627197,
+      "learning_rate": 7.999977348305978e-05,
+      "loss": 1.0382986068725586,
+      "step": 60
+    },
+    {
+      "epoch": 0.06761149395397217,
+      "grad_norm": 2.0822298526763916,
+      "learning_rate": 7.999722519694521e-05,
+      "loss": 1.1403823852539063,
+      "step": 65
+    },
+    {
+      "epoch": 0.07281237810427772,
+      "grad_norm": 2.109672784805298,
+      "learning_rate": 7.999184565952555e-05,
+      "loss": 1.0954228401184083,
+      "step": 70
+    },
+    {
+      "epoch": 0.07801326225458328,
+      "grad_norm": 1.9484328031539917,
+      "learning_rate": 7.998363525159777e-05,
+      "loss": 1.125577735900879,
+      "step": 75
+    },
+    {
+      "epoch": 0.08321414640488883,
+      "grad_norm": 2.0304486751556396,
+      "learning_rate": 7.997259455434539e-05,
+      "loss": 1.078431987762451,
+      "step": 80
+    },
+    {
+      "epoch": 0.08841503055519438,
+      "grad_norm": 1.8764644861221313,
+      "learning_rate": 7.995872434929734e-05,
+      "loss": 1.0825774192810058,
+      "step": 85
+    },
+    {
+      "epoch": 0.09361591470549993,
+      "grad_norm": 2.521047353744507,
+      "learning_rate": 7.994202561827263e-05,
+      "loss": 1.0628202438354493,
+      "step": 90
+    },
+    {
+      "epoch": 0.0988167988558055,
+      "grad_norm": 1.7737245559692383,
+      "learning_rate": 7.992249954331088e-05,
+      "loss": 1.0672310829162597,
+      "step": 95
+    },
+    {
+      "epoch": 0.10401768300611104,
+      "grad_norm": 2.0016262531280518,
+      "learning_rate": 7.990014750658856e-05,
+      "loss": 1.0844260215759278,
+      "step": 100
+    },
+    {
+      "epoch": 0.10401768300611104,
+      "eval_loss": 1.090377688407898,
+      "eval_runtime": 131.495,
+      "eval_samples_per_second": 1.947,
+      "eval_steps_per_second": 1.947,
+      "step": 100
+    },
+    {
+      "epoch": 0.10921856715641659,
+      "grad_norm": 2.2041330337524414,
+      "learning_rate": 7.987497109032128e-05,
+      "loss": 1.095380973815918,
+      "step": 105
+    },
+    {
+      "epoch": 0.11441945130672214,
+      "grad_norm": 1.7770912647247314,
+      "learning_rate": 7.98469720766517e-05,
+      "loss": 1.076313304901123,
+      "step": 110
+    },
+    {
+      "epoch": 0.11962033545702769,
+      "grad_norm": 2.0055956840515137,
+      "learning_rate": 7.98161524475234e-05,
+      "loss": 1.069803810119629,
+      "step": 115
+    },
+    {
+      "epoch": 0.12482121960733325,
+      "grad_norm": 1.9808892011642456,
+      "learning_rate": 7.978251438454063e-05,
+      "loss": 1.062901496887207,
+      "step": 120
+    },
+    {
+      "epoch": 0.13002210375763879,
+      "grad_norm": 1.7519869804382324,
+      "learning_rate": 7.974606026881378e-05,
+      "loss": 1.03425931930542,
+      "step": 125
+    },
+    {
+      "epoch": 0.13522298790794435,
+      "grad_norm": 1.8879916667938232,
+      "learning_rate": 7.970679268079092e-05,
+      "loss": 1.085061264038086,
+      "step": 130
+    },
+    {
+      "epoch": 0.1404238720582499,
+      "grad_norm": 1.855212926864624,
+      "learning_rate": 7.966471440007514e-05,
+      "loss": 1.0653216361999511,
+      "step": 135
+    },
+    {
+      "epoch": 0.14562475620855544,
+      "grad_norm": 1.9829131364822388,
+      "learning_rate": 7.961982840522773e-05,
+      "loss": 1.0679091453552245,
+      "step": 140
+    },
+    {
+      "epoch": 0.150825640358861,
+      "grad_norm": 1.8631235361099243,
+      "learning_rate": 7.957213787355738e-05,
+      "loss": 1.0336699485778809,
+      "step": 145
+    },
+    {
+      "epoch": 0.15602652450916657,
+      "grad_norm": 1.7199710607528687,
+      "learning_rate": 7.95216461808953e-05,
+      "loss": 1.085853385925293,
+      "step": 150
+    },
+    {
+      "epoch": 0.1612274086594721,
+      "grad_norm": 1.8429338932037354,
+      "learning_rate": 7.946835690135617e-05,
+      "loss": 1.039409065246582,
+      "step": 155
+    },
+    {
+      "epoch": 0.16642829280977767,
+      "grad_norm": 1.9319918155670166,
+      "learning_rate": 7.941227380708522e-05,
+      "loss": 1.0467087745666503,
+      "step": 160
+    },
+    {
+      "epoch": 0.1716291769600832,
+      "grad_norm": 2.0441744327545166,
+      "learning_rate": 7.93534008679912e-05,
+      "loss": 1.0675994873046875,
+      "step": 165
+    },
+    {
+      "epoch": 0.17683006111038876,
+      "grad_norm": 1.847270131111145,
+      "learning_rate": 7.929174225146534e-05,
+      "loss": 1.0682602882385255,
+      "step": 170
+    },
+    {
+      "epoch": 0.18203094526069433,
+      "grad_norm": 1.8770182132720947,
+      "learning_rate": 7.922730232208637e-05,
+      "loss": 1.0655933380126954,
+      "step": 175
+    },
+    {
+      "epoch": 0.18723182941099986,
+      "grad_norm": 1.9199661016464233,
+      "learning_rate": 7.916008564131158e-05,
+      "loss": 1.0514616012573241,
+      "step": 180
+    },
+    {
+      "epoch": 0.19243271356130542,
+      "grad_norm": 1.7040131092071533,
+      "learning_rate": 7.909009696715391e-05,
+      "loss": 1.0357669830322265,
+      "step": 185
+    },
+    {
+      "epoch": 0.197633597711611,
+      "grad_norm": 1.7878484725952148,
+      "learning_rate": 7.901734125384515e-05,
+      "loss": 1.034726905822754,
+      "step": 190
+    },
+    {
+      "epoch": 0.20283448186191652,
+      "grad_norm": 1.7647621631622314,
+      "learning_rate": 7.89418236514853e-05,
+      "loss": 1.0258402824401855,
+      "step": 195
+    },
+    {
+      "epoch": 0.20803536601222208,
+      "grad_norm": 1.7211089134216309,
+      "learning_rate": 7.886354950567789e-05,
+      "loss": 1.0237075805664062,
+      "step": 200
+    },
+    {
+      "epoch": 0.20803536601222208,
+      "eval_loss": 1.0211308002471924,
+      "eval_runtime": 130.7508,
+      "eval_samples_per_second": 1.958,
+      "eval_steps_per_second": 1.958,
+      "step": 200
+    },
+    {
+      "epoch": 0.21323625016252762,
+      "grad_norm": 1.9167125225067139,
+      "learning_rate": 7.878252435715178e-05,
+      "loss": 1.0424039840698243,
+      "step": 205
+    },
+    {
+      "epoch": 0.21843713431283318,
+      "grad_norm": 1.6589795351028442,
+      "learning_rate": 7.869875394136873e-05,
+      "loss": 0.985629940032959,
+      "step": 210
+    },
+    {
+      "epoch": 0.22363801846313874,
+      "grad_norm": 1.7960469722747803,
+      "learning_rate": 7.861224418811757e-05,
+      "loss": 1.0503170013427734,
+      "step": 215
+    },
+    {
+      "epoch": 0.22883890261344428,
+      "grad_norm": 1.876910924911499,
+      "learning_rate": 7.852300122109443e-05,
+      "loss": 1.0263469696044922,
+      "step": 220
+    },
+    {
+      "epoch": 0.23403978676374984,
+      "grad_norm": 1.7034902572631836,
+      "learning_rate": 7.843103135746916e-05,
+      "loss": 1.0396705627441407,
+      "step": 225
+    },
+    {
+      "epoch": 0.23924067091405538,
+      "grad_norm": 1.7886664867401123,
+      "learning_rate": 7.833634110743832e-05,
+      "loss": 1.0125335693359374,
+      "step": 230
+    },
+    {
+      "epoch": 0.24444155506436094,
+      "grad_norm": 1.7878754138946533,
+      "learning_rate": 7.823893717376422e-05,
+      "loss": 0.9978487968444825,
+      "step": 235
+    },
+    {
+      "epoch": 0.2496424392146665,
+      "grad_norm": 1.6163357496261597,
+      "learning_rate": 7.813882645130049e-05,
+      "loss": 1.0093013763427734,
+      "step": 240
+    },
+    {
+      "epoch": 0.25484332336497206,
+      "grad_norm": 1.7179474830627441,
+      "learning_rate": 7.80360160265041e-05,
+      "loss": 0.9946321487426758,
+      "step": 245
+    },
+    {
+      "epoch": 0.26004420751527757,
+      "grad_norm": 1.828262209892273,
+      "learning_rate": 7.793051317693359e-05,
+      "loss": 1.0461179733276367,
+      "step": 250
+    },
+    {
+      "epoch": 0.26524509166558313,
+      "grad_norm": 1.837222933769226,
+      "learning_rate": 7.782232537073406e-05,
+      "loss": 1.0099411964416505,
+      "step": 255
+    },
+    {
+      "epoch": 0.2704459758158887,
+      "grad_norm": 1.9459391832351685,
+      "learning_rate": 7.771146026610844e-05,
+      "loss": 0.9811776161193848,
+      "step": 260
+    },
+    {
+      "epoch": 0.27564685996619426,
+      "grad_norm": 1.8060634136199951,
+      "learning_rate": 7.759792571077545e-05,
+      "loss": 0.9858491897583008,
+      "step": 265
+    },
+    {
+      "epoch": 0.2808477441164998,
+      "grad_norm": 1.8257906436920166,
+      "learning_rate": 7.748172974141401e-05,
+      "loss": 1.0260663032531738,
+      "step": 270
+    },
+    {
+      "epoch": 0.2860486282668054,
+      "grad_norm": 1.7271229028701782,
+      "learning_rate": 7.736288058309448e-05,
+      "loss": 1.0253376007080077,
+      "step": 275
+    },
+    {
+      "epoch": 0.2912495124171109,
+      "grad_norm": 1.6389424800872803,
+      "learning_rate": 7.724138664869628e-05,
+      "loss": 0.9872174263000488,
+      "step": 280
+    },
+    {
+      "epoch": 0.29645039656741645,
+      "grad_norm": 1.7230466604232788,
+      "learning_rate": 7.711725653831255e-05,
+      "loss": 1.0354929924011231,
+      "step": 285
+    },
+    {
+      "epoch": 0.301651280717722,
+      "grad_norm": 1.7749247550964355,
+      "learning_rate": 7.699049903864125e-05,
+      "loss": 0.9916903495788574,
+      "step": 290
+    },
+    {
+      "epoch": 0.3068521648680276,
+      "grad_norm": 1.7340270280838013,
+      "learning_rate": 7.68611231223632e-05,
+      "loss": 1.0025782585144043,
+      "step": 295
+    },
+    {
+      "epoch": 0.31205304901833314,
+      "grad_norm": 1.5753134489059448,
+      "learning_rate": 7.672913794750699e-05,
+      "loss": 0.9782845497131347,
+      "step": 300
+    },
+    {
+      "epoch": 0.31205304901833314,
+      "eval_loss": 1.01508629322052,
+      "eval_runtime": 130.89,
+      "eval_samples_per_second": 1.956,
+      "eval_steps_per_second": 1.956,
+      "step": 300
+    },
+    {
+      "epoch": 0.31725393316863865,
+      "grad_norm": 1.6529031991958618,
+      "learning_rate": 7.659455285680071e-05,
+      "loss": 0.9918001174926758,
+      "step": 305
+    },
+    {
+      "epoch": 0.3224548173189442,
+      "grad_norm": 1.6655994653701782,
+      "learning_rate": 7.645737737701054e-05,
+      "loss": 0.9847027778625488,
+      "step": 310
+    },
+    {
+      "epoch": 0.32765570146924977,
+      "grad_norm": 1.7864056825637817,
+      "learning_rate": 7.631762121826653e-05,
+      "loss": 0.9591518402099609,
+      "step": 315
+    },
+    {
+      "epoch": 0.33285658561955533,
+      "grad_norm": 1.7958587408065796,
+      "learning_rate": 7.617529427337507e-05,
+      "loss": 0.9712434768676758,
+      "step": 320
+    },
+    {
+      "epoch": 0.3380574697698609,
+      "grad_norm": 1.7462350130081177,
+      "learning_rate": 7.603040661711879e-05,
+      "loss": 1.0182976722717285,
+      "step": 325
+    },
+    {
+      "epoch": 0.3432583539201664,
+      "grad_norm": 1.73703932762146,
+      "learning_rate": 7.588296850554326e-05,
+      "loss": 0.978699779510498,
+      "step": 330
+    },
+    {
+      "epoch": 0.34845923807047197,
+      "grad_norm": 1.781213402748108,
+      "learning_rate": 7.573299037523115e-05,
+      "loss": 1.0263344764709472,
+      "step": 335
+    },
+    {
+      "epoch": 0.35366012222077753,
+      "grad_norm": 1.7940926551818848,
+      "learning_rate": 7.558048284256334e-05,
+      "loss": 1.039241409301758,
+      "step": 340
+    },
+    {
+      "epoch": 0.3588610063710831,
+      "grad_norm": 1.725530982017517,
+      "learning_rate": 7.542545670296747e-05,
+      "loss": 0.9716745376586914,
+      "step": 345
+    },
+    {
+      "epoch": 0.36406189052138865,
+      "grad_norm": 1.665209174156189,
+      "learning_rate": 7.526792293015382e-05,
+      "loss": 0.9396204948425293,
+      "step": 350
+    },
+    {
+      "epoch": 0.36926277467169416,
+      "grad_norm": 1.8031824827194214,
+      "learning_rate": 7.51078926753384e-05,
+      "loss": 0.9682992935180664,
+      "step": 355
+    },
+    {
+      "epoch": 0.3744636588219997,
+      "grad_norm": 1.7742233276367188,
+      "learning_rate": 7.494537726645375e-05,
+      "loss": 0.9833150863647461,
+      "step": 360
+    },
+    {
+      "epoch": 0.3796645429723053,
+      "grad_norm": 1.7864766120910645,
+      "learning_rate": 7.478038820734698e-05,
+      "loss": 0.9690051078796387,
+      "step": 365
+    },
+    {
+      "epoch": 0.38486542712261085,
+      "grad_norm": 1.7735403776168823,
+      "learning_rate": 7.461293717696549e-05,
+      "loss": 0.9864785194396972,
+      "step": 370
+    },
+    {
+      "epoch": 0.3900663112729164,
+      "grad_norm": 1.6049963235855103,
+      "learning_rate": 7.444303602853024e-05,
+      "loss": 0.9804511070251465,
+      "step": 375
+    },
+    {
+      "epoch": 0.395267195423222,
+      "grad_norm": 1.6558054685592651,
+      "learning_rate": 7.427069678869672e-05,
+      "loss": 0.9362913131713867,
+      "step": 380
+    },
+    {
+      "epoch": 0.4004680795735275,
+      "grad_norm": 1.6555157899856567,
+      "learning_rate": 7.409593165670364e-05,
+      "loss": 0.948128604888916,
+      "step": 385
+    },
+    {
+      "epoch": 0.40566896372383304,
+      "grad_norm": 1.812888741493225,
+      "learning_rate": 7.391875300350937e-05,
+      "loss": 0.9553811073303222,
+      "step": 390
+    },
+    {
+      "epoch": 0.4108698478741386,
+      "grad_norm": 1.6602718830108643,
+      "learning_rate": 7.373917337091626e-05,
+      "loss": 0.940127944946289,
+      "step": 395
+    },
+    {
+      "epoch": 0.41607073202444417,
+      "grad_norm": 1.7474323511123657,
+      "learning_rate": 7.355720547068288e-05,
+      "loss": 0.9683933258056641,
+      "step": 400
+    },
+    {
+      "epoch": 0.41607073202444417,
+      "eval_loss": 0.9856516122817993,
+      "eval_runtime": 130.2348,
+      "eval_samples_per_second": 1.966,
+      "eval_steps_per_second": 1.966,
+      "step": 400
+    },
+    {
+      "epoch": 0.42127161617474973,
+      "grad_norm": 1.7211471796035767,
+      "learning_rate": 7.337286218362413e-05,
+      "loss": 0.9713785171508789,
+      "step": 405
+    },
+    {
+      "epoch": 0.42647250032505524,
+      "grad_norm": 1.839705467224121,
+      "learning_rate": 7.31861565586995e-05,
+      "loss": 0.9828580856323242,
+      "step": 410
+    },
+    {
+      "epoch": 0.4316733844753608,
+      "grad_norm": 1.6094111204147339,
+      "learning_rate": 7.299710181208943e-05,
+      "loss": 0.9652169227600098,
+      "step": 415
+    },
+    {
+      "epoch": 0.43687426862566636,
+      "grad_norm": 1.8238450288772583,
+      "learning_rate": 7.280571132625971e-05,
+      "loss": 0.9175550460815429,
+      "step": 420
+    },
+    {
+      "epoch": 0.4420751527759719,
+      "grad_norm": 1.7738935947418213,
+      "learning_rate": 7.261199864901423e-05,
+      "loss": 0.959293270111084,
+      "step": 425
+    },
+    {
+      "epoch": 0.4472760369262775,
+      "grad_norm": 1.7823359966278076,
+      "learning_rate": 7.241597749253593e-05,
+      "loss": 0.9460945129394531,
+      "step": 430
+    },
+    {
+      "epoch": 0.452476921076583,
+      "grad_norm": 1.852073073387146,
+      "learning_rate": 7.221766173241629e-05,
+      "loss": 0.9572076797485352,
+      "step": 435
+    },
+    {
+      "epoch": 0.45767780522688856,
+      "grad_norm": 1.7884498834609985,
+      "learning_rate": 7.201706540667293e-05,
+      "loss": 0.980253028869629,
+      "step": 440
+    },
+    {
+      "epoch": 0.4628786893771941,
+      "grad_norm": 1.6045715808868408,
+      "learning_rate": 7.181420271475616e-05,
+      "loss": 0.9448029518127441,
+      "step": 445
+    },
+    {
+      "epoch": 0.4680795735274997,
+      "grad_norm": 1.703908920288086,
+      "learning_rate": 7.160908801654358e-05,
+      "loss": 0.9464167594909668,
+      "step": 450
+    },
+    {
+      "epoch": 0.47328045767780524,
+      "grad_norm": 1.5748329162597656,
+      "learning_rate": 7.14017358313239e-05,
+      "loss": 0.9481819152832032,
+      "step": 455
+    },
+    {
+      "epoch": 0.47848134182811075,
+      "grad_norm": 1.62021803855896,
+      "learning_rate": 7.11921608367689e-05,
+      "loss": 0.9535123825073242,
+      "step": 460
+    },
+    {
+      "epoch": 0.4836822259784163,
+      "grad_norm": 1.6786726713180542,
+      "learning_rate": 7.09803778678946e-05,
+      "loss": 0.9362807273864746,
+      "step": 465
+    },
+    {
+      "epoch": 0.4888831101287219,
+      "grad_norm": 1.602408528327942,
+      "learning_rate": 7.076640191601113e-05,
+      "loss": 0.9352068901062012,
+      "step": 470
+    },
+    {
+      "epoch": 0.49408399427902744,
+      "grad_norm": 1.710305094718933,
+      "learning_rate": 7.055024812766153e-05,
+      "loss": 0.9479847908020019,
+      "step": 475
+    },
+    {
+      "epoch": 0.499284878429333,
+      "grad_norm": 1.7393652200698853,
+      "learning_rate": 7.03319318035496e-05,
+      "loss": 0.9210905075073242,
+      "step": 480
+    },
+    {
+      "epoch": 0.5044857625796385,
+      "grad_norm": 1.6267069578170776,
+      "learning_rate": 7.011146839745681e-05,
+      "loss": 0.935267448425293,
+      "step": 485
+    },
+    {
+      "epoch": 0.5096866467299441,
+      "grad_norm": 1.5649526119232178,
+      "learning_rate": 6.98888735151484e-05,
+      "loss": 0.950043773651123,
+      "step": 490
+    },
+    {
+      "epoch": 0.5148875308802496,
+      "grad_norm": 1.7210514545440674,
+      "learning_rate": 6.966416291326867e-05,
+      "loss": 0.9338683128356934,
+      "step": 495
+    },
+    {
+      "epoch": 0.5200884150305551,
+      "grad_norm": 1.7836523056030273,
+      "learning_rate": 6.943735249822567e-05,
+      "loss": 0.9206833839416504,
+      "step": 500
+    },
+    {
+      "epoch": 0.5200884150305551,
+      "eval_loss": 0.9551063776016235,
+      "eval_runtime": 130.2472,
+      "eval_samples_per_second": 1.965,
+      "eval_steps_per_second": 1.965,
+      "step": 500
+    },
+    {
+      "epoch": 0.5252892991808608,
+      "grad_norm": 1.6640737056732178,
+      "learning_rate": 6.920845832506523e-05,
+      "loss": 0.9343124389648437,
+      "step": 505
+    },
+    {
+      "epoch": 0.5304901833311663,
+      "grad_norm": 1.5780658721923828,
+      "learning_rate": 6.897749659633448e-05,
+      "loss": 0.9712604522705078,
+      "step": 510
+    },
+    {
+      "epoch": 0.5356910674814719,
+      "grad_norm": 1.6826986074447632,
+      "learning_rate": 6.874448366093497e-05,
+      "loss": 0.9570392608642578,
+      "step": 515
+    },
+    {
+      "epoch": 0.5408919516317774,
+      "grad_norm": 1.6517504453659058,
+      "learning_rate": 6.850943601296529e-05,
+      "loss": 0.9325905799865722,
+      "step": 520
+    },
+    {
+      "epoch": 0.546092835782083,
+      "grad_norm": 1.8107248544692993,
+      "learning_rate": 6.827237029055364e-05,
+      "loss": 0.9377958297729492,
+      "step": 525
+    },
+    {
+      "epoch": 0.5512937199323885,
+      "grad_norm": 1.6924495697021484,
+      "learning_rate": 6.803330327468006e-05,
+      "loss": 0.9227448463439941,
+      "step": 530
+    },
+    {
+      "epoch": 0.556494604082694,
+      "grad_norm": 1.6941320896148682,
+      "learning_rate": 6.779225188798846e-05,
+      "loss": 0.9221724510192871,
+      "step": 535
+    },
+    {
+      "epoch": 0.5616954882329996,
+      "grad_norm": 1.605466604232788,
+      "learning_rate": 6.754923319358883e-05,
+      "loss": 0.9474879264831543,
+      "step": 540
+    },
+    {
+      "epoch": 0.5668963723833051,
+      "grad_norm": 1.6994117498397827,
+      "learning_rate": 6.730426439384939e-05,
+      "loss": 0.9544130325317383,
+      "step": 545
+    },
+    {
+      "epoch": 0.5720972565336108,
+      "grad_norm": 1.6269444227218628,
+      "learning_rate": 6.705736282917892e-05,
+      "loss": 0.8944686889648438,
+      "step": 550
+    },
+    {
+      "epoch": 0.5772981406839163,
+      "grad_norm": 1.7221931219100952,
+      "learning_rate": 6.680854597679924e-05,
+      "loss": 0.9075075149536133,
+      "step": 555
+    },
+    {
+      "epoch": 0.5824990248342218,
+      "grad_norm": 1.7379156351089478,
+      "learning_rate": 6.655783144950809e-05,
+      "loss": 0.9554330825805664,
+      "step": 560
+    },
+    {
+      "epoch": 0.5876999089845274,
+      "grad_norm": 1.7438715696334839,
+      "learning_rate": 6.63052369944324e-05,
+      "loss": 0.9195778846740723,
+      "step": 565
+    },
+    {
+      "epoch": 0.5929007931348329,
+      "grad_norm": 1.6393606662750244,
+      "learning_rate": 6.605078049177205e-05,
+      "loss": 0.915708065032959,
+      "step": 570
+    },
+    {
+      "epoch": 0.5981016772851385,
+      "grad_norm": 1.7054882049560547,
+      "learning_rate": 6.579447995353416e-05,
+      "loss": 0.9384199142456054,
+      "step": 575
+    },
+    {
+      "epoch": 0.603302561435444,
+      "grad_norm": 1.5726091861724854,
+      "learning_rate": 6.553635352225812e-05,
+      "loss": 0.9182180404663086,
+      "step": 580
+    },
+    {
+      "epoch": 0.6085034455857495,
+      "grad_norm": 1.827543020248413,
+      "learning_rate": 6.52764194697313e-05,
+      "loss": 0.9172782897949219,
+      "step": 585
+    },
+    {
+      "epoch": 0.6137043297360552,
+      "grad_norm": 1.541303038597107,
+      "learning_rate": 6.501469619569579e-05,
+      "loss": 0.9366864204406739,
+      "step": 590
+    },
+    {
+      "epoch": 0.6189052138863607,
+      "grad_norm": 1.6896532773971558,
+      "learning_rate": 6.475120222654573e-05,
+      "loss": 0.91693115234375,
+      "step": 595
+    },
+    {
+      "epoch": 0.6241060980366663,
+      "grad_norm": 1.8263614177703857,
+      "learning_rate": 6.448595621401615e-05,
+      "loss": 0.9207332611083985,
+      "step": 600
+    },
+    {
+      "epoch": 0.6241060980366663,
+      "eval_loss": 0.9301373958587646,
+      "eval_runtime": 129.9867,
+      "eval_samples_per_second": 1.969,
+      "eval_steps_per_second": 1.969,
+      "step": 600
+    },
+    {
+      "epoch": 0.6293069821869718,
+      "grad_norm": 2.5737788677215576,
+      "learning_rate": 6.421897693386245e-05,
+      "loss": 1.8008251190185547,
+      "step": 605
+    },
+    {
+      "epoch": 0.6345078663372773,
+      "grad_norm": 2.3786563873291016,
+      "learning_rate": 6.395028328453154e-05,
+      "loss": 1.0148398399353027,
+      "step": 610
+    },
+    {
+      "epoch": 0.6397087504875829,
+      "grad_norm": 2.1619725227355957,
+      "learning_rate": 6.367989428582395e-05,
+      "loss": 0.9035258293151855,
+      "step": 615
+    },
+    {
+      "epoch": 0.6449096346378884,
+      "grad_norm": 1.8177882432937622,
+      "learning_rate": 6.340782907754754e-05,
+      "loss": 0.9431497573852539,
+      "step": 620
+    },
+    {
+      "epoch": 0.650110518788194,
+      "grad_norm": 2.0389435291290283,
+      "learning_rate": 6.313410691816269e-05,
+      "loss": 0.9617778778076171,
+      "step": 625
+    },
+    {
+      "epoch": 0.6553114029384995,
+      "grad_norm": 1.8454713821411133,
+      "learning_rate": 6.285874718341898e-05,
+      "loss": 0.9618912696838379,
+      "step": 630
+    },
+    {
+      "epoch": 0.660512287088805,
+      "grad_norm": 1.9317169189453125,
+      "learning_rate": 6.25817693649838e-05,
+      "loss": 1.020989227294922,
+      "step": 635
+    },
+    {
+      "epoch": 0.6657131712391107,
+      "grad_norm": 2.249952554702759,
+      "learning_rate": 6.230319306906246e-05,
+      "loss": 1.0368837356567382,
+      "step": 640
+    },
+    {
+      "epoch": 0.6709140553894162,
+      "grad_norm": 1.8525416851043701,
+      "learning_rate": 6.202303801501045e-05,
+      "loss": 0.9958114624023438,
+      "step": 645
+    },
+    {
+      "epoch": 0.6761149395397218,
+      "grad_norm": 1.99785578250885,
+      "learning_rate": 6.174132403393749e-05,
+      "loss": 1.0103933334350585,
+      "step": 650
+    },
+    {
+      "epoch": 0.6813158236900273,
+      "grad_norm": 2.1036858558654785,
+      "learning_rate": 6.145807106730384e-05,
+      "loss": 1.009110927581787,
+      "step": 655
+    },
+    {
+      "epoch": 0.6865167078403328,
+      "grad_norm": 1.8276114463806152,
+      "learning_rate": 6.11732991655087e-05,
+      "loss": 1.0265812873840332,
+      "step": 660
+    },
+    {
+      "epoch": 0.6917175919906384,
+      "grad_norm": 1.8524454832077026,
+      "learning_rate": 6.088702848647087e-05,
+      "loss": 1.0076023101806642,
+      "step": 665
+    },
+    {
+      "epoch": 0.6969184761409439,
+      "grad_norm": 2.044529914855957,
+      "learning_rate": 6.059927929420191e-05,
+      "loss": 1.0623496055603028,
+      "step": 670
+    },
+    {
+      "epoch": 0.7021193602912496,
+      "grad_norm": 1.9014661312103271,
+      "learning_rate": 6.031007195737173e-05,
+      "loss": 1.0505518913269043,
+      "step": 675
+    },
+    {
+      "epoch": 0.7073202444415551,
+      "grad_norm": 1.7579931020736694,
+      "learning_rate": 6.0019426947866685e-05,
+      "loss": 1.0260109901428223,
+      "step": 680
+    },
+    {
+      "epoch": 0.7125211285918606,
+      "grad_norm": 1.9789166450500488,
+      "learning_rate": 5.972736483934053e-05,
+      "loss": 1.0057721138000488,
+      "step": 685
+    },
+    {
+      "epoch": 0.7177220127421662,
+      "grad_norm": 1.7603486776351929,
+      "learning_rate": 5.943390630575808e-05,
+      "loss": 0.9560928344726562,
+      "step": 690
+    },
+    {
+      "epoch": 0.7229228968924717,
+      "grad_norm": 1.723509669303894,
+      "learning_rate": 5.9139072119931735e-05,
+      "loss": 1.0287532806396484,
+      "step": 695
+    },
+    {
+      "epoch": 0.7281237810427773,
+      "grad_norm": 1.880836844444275,
+      "learning_rate": 5.884288315205113e-05,
+      "loss": 1.0159936904907227,
+      "step": 700
+    },
+    {
+      "epoch": 0.7281237810427773,
+      "eval_loss": 1.0172600746154785,
+      "eval_runtime": 130.5328,
+      "eval_samples_per_second": 1.961,
+      "eval_steps_per_second": 1.961,
+      "step": 700
+    },
+    {
+      "epoch": 0.7333246651930828,
+      "grad_norm": 1.7332347631454468,
+      "learning_rate": 5.8545360368205704e-05,
+      "loss": 0.9914582252502442,
+      "step": 705
+    },
+    {
+      "epoch": 0.7385255493433883,
+      "grad_norm": 1.6425188779830933,
+      "learning_rate": 5.824652482890067e-05,
+      "loss": 0.9969341278076171,
+      "step": 710
+    },
+    {
+      "epoch": 0.7437264334936939,
+      "grad_norm": 1.868652105331421,
+      "learning_rate": 5.794639768756625e-05,
+      "loss": 0.9733437538146973,
+      "step": 715
+    },
+    {
+      "epoch": 0.7489273176439994,
+      "grad_norm": 1.7285988330841064,
+      "learning_rate": 5.764500018906019e-05,
+      "loss": 0.992225170135498,
+      "step": 720
+    },
+    {
+      "epoch": 0.7541282017943051,
+      "grad_norm": 1.7920562028884888,
+      "learning_rate": 5.734235366816398e-05,
+      "loss": 0.9502806663513184,
+      "step": 725
+    },
+    {
+      "epoch": 0.7593290859446106,
+      "grad_norm": 1.7255525588989258,
+      "learning_rate": 5.703847954807273e-05,
+      "loss": 0.9720046997070313,
+      "step": 730
+    },
+    {
+      "epoch": 0.7645299700949162,
+      "grad_norm": 1.8702120780944824,
+      "learning_rate": 5.673339933887854e-05,
+      "loss": 1.0045533180236816,
+      "step": 735
+    },
+    {
+      "epoch": 0.7697308542452217,
+      "grad_norm": 1.7282917499542236,
+      "learning_rate": 5.642713463604804e-05,
+      "loss": 0.998747444152832,
+      "step": 740
+    },
+    {
+      "epoch": 0.7749317383955272,
+      "grad_norm": 1.6850981712341309,
+      "learning_rate": 5.6119707118893566e-05,
+      "loss": 0.9491232872009278,
+      "step": 745
+    },
+    {
+      "epoch": 0.7801326225458328,
+      "grad_norm": 1.8323360681533813,
+      "learning_rate": 5.581113854903873e-05,
+      "loss": 0.9483734130859375,
+      "step": 750
+    },
+    {
+      "epoch": 0.7853335066961383,
+      "grad_norm": 1.7287927865982056,
+      "learning_rate": 5.5501450768877895e-05,
+      "loss": 0.9630053520202637,
+      "step": 755
+    },
+    {
+      "epoch": 0.790534390846444,
+      "grad_norm": 1.8735415935516357,
+      "learning_rate": 5.519066570003006e-05,
+      "loss": 0.9625276565551758,
+      "step": 760
+    },
+    {
+      "epoch": 0.7957352749967495,
+      "grad_norm": 1.7333344221115112,
+      "learning_rate": 5.4878805341787106e-05,
+      "loss": 0.956482982635498,
+      "step": 765
+    },
+    {
+      "epoch": 0.800936159147055,
+      "grad_norm": 1.7283087968826294,
+      "learning_rate": 5.456589176955656e-05,
+      "loss": 0.9767995834350586,
+      "step": 770
+    },
+    {
+      "epoch": 0.8061370432973606,
+      "grad_norm": 1.6415756940841675,
+      "learning_rate": 5.4251947133298954e-05,
+      "loss": 0.9446447372436524,
+      "step": 775
+    },
+    {
+      "epoch": 0.8113379274476661,
+      "grad_norm": 1.6519927978515625,
+      "learning_rate": 5.393699365595995e-05,
+      "loss": 0.9424878120422363,
+      "step": 780
+    },
+    {
+      "epoch": 0.8165388115979717,
+      "grad_norm": 1.647696852684021,
+      "learning_rate": 5.3621053631897175e-05,
+      "loss": 0.9464174270629883,
+      "step": 785
+    },
+    {
+      "epoch": 0.8217396957482772,
+      "grad_norm": 1.8417209386825562,
+      "learning_rate": 5.330414942530217e-05,
+      "loss": 0.9534976959228516,
+      "step": 790
+    },
+    {
+      "epoch": 0.8269405798985827,
+      "grad_norm": 1.8787815570831299,
+      "learning_rate": 5.298630346861732e-05,
+      "loss": 0.902367115020752,
+      "step": 795
+    },
+    {
+      "epoch": 0.8321414640488883,
+      "grad_norm": 1.68453848361969,
+      "learning_rate": 5.266753826094787e-05,
+      "loss": 0.9392575263977051,
+      "step": 800
+    },
+    {
+      "epoch": 0.8321414640488883,
+      "eval_loss": 0.9664498567581177,
+      "eval_runtime": 129.775,
+      "eval_samples_per_second": 1.973,
+      "eval_steps_per_second": 1.973,
+      "step": 800
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1924,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.1727071894491873e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14fd1411109c0eee6413d22d6af96a8f8643991c4f44679b65cf8291ea6222b1
+size 5201