Forced push from Callback: Step 5000

checkpoint-5000/README.md

@@ -0,0 +1,206 @@
+---
+base_model: mohammed525671/final_arabic_grammarly_2
+library_name: peft
+tags:
+- base_model:adapter:mohammed525671/final_arabic_grammarly_2
+- 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 0.19.1

checkpoint-5000/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "mohammed525671/final_arabic_grammarly_2",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q",
+    "v"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_2_SEQ_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-5000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8f0d86708f4b8e985c3f61818ed0c86a2ac5e94f277b68f46e32cbce8e4ef1d
+size 7098016

checkpoint-5000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b07d0a74c09f4c412a15e114e2ce88f4b8919617ff0970dcf071afc62406f77d
+size 14279243

checkpoint-5000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67d15f0bbd2c71ec574bb1d7b2c633e4e374002332e1ac7de5631b73736c9812
+size 14645

checkpoint-5000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9eefe8f48812a0946379983776b850099bd0c97bf44f570d8bd4587584ff3dd
+size 1465

checkpoint-5000/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "backend": "tokenizers",
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "extra_special_tokens": [
+    "<pad>",
+    "</s>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_id": 2,
+  "unk_token": "<unk>"
+}

checkpoint-5000/trainer_state.json

@@ -0,0 +1,439 @@
+{
+  "best_global_step": 5000,
+  "best_metric": 0.2988842723825056,
+  "best_model_checkpoint": "/content/lora_checkpoints/checkpoint-5000",
+  "epoch": 0.584932147870847,
+  "eval_steps": 1000,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01169864295741694,
+      "grad_norm": 0.17465531826019287,
+      "learning_rate": 3.960000000000001e-05,
+      "loss": 0.8288492584228515,
+      "step": 100
+    },
+    {
+      "epoch": 0.02339728591483388,
+      "grad_norm": 0.10292098671197891,
+      "learning_rate": 7.960000000000001e-05,
+      "loss": 0.8100727844238281,
+      "step": 200
+    },
+    {
+      "epoch": 0.03509592887225082,
+      "grad_norm": 0.7526177763938904,
+      "learning_rate": 0.00011960000000000001,
+      "loss": 0.6363310241699218,
+      "step": 300
+    },
+    {
+      "epoch": 0.04679457182966776,
+      "grad_norm": 0.13997608423233032,
+      "learning_rate": 0.0001596,
+      "loss": 0.667275161743164,
+      "step": 400
+    },
+    {
+      "epoch": 0.0584932147870847,
+      "grad_norm": 0.435800701379776,
+      "learning_rate": 0.0001996,
+      "loss": 0.666079330444336,
+      "step": 500
+    },
+    {
+      "epoch": 0.07019185774450164,
+      "grad_norm": 0.29729676246643066,
+      "learning_rate": 0.0001988069414316703,
+      "loss": 0.7561639404296875,
+      "step": 600
+    },
+    {
+      "epoch": 0.08189050070191858,
+      "grad_norm": 0.5007213354110718,
+      "learning_rate": 0.00019760183176669078,
+      "loss": 0.9136177825927735,
+      "step": 700
+    },
+    {
+      "epoch": 0.09358914365933552,
+      "grad_norm": 0.3354756832122803,
+      "learning_rate": 0.00019639672210171127,
+      "loss": 0.7920448303222656,
+      "step": 800
+    },
+    {
+      "epoch": 0.10528778661675246,
+      "grad_norm": 0.2753271460533142,
+      "learning_rate": 0.00019519161243673175,
+      "loss": 0.7825648498535156,
+      "step": 900
+    },
+    {
+      "epoch": 0.1169864295741694,
+      "grad_norm": 0.2488747239112854,
+      "learning_rate": 0.00019398650277175223,
+      "loss": 0.8908327484130859,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1169864295741694,
+      "eval_bleu": 14.159322048476906,
+      "eval_chrf++": 37.25199978938141,
+      "eval_gleu": 0.29527796770330317,
+      "eval_loss": 0.13655707240104675,
+      "eval_runtime": 3076.623,
+      "eval_samples_per_second": 8.126,
+      "eval_steps_per_second": 1.016,
+      "step": 1000
+    },
+    {
+      "epoch": 0.12868507253158634,
+      "grad_norm": 0.30232590436935425,
+      "learning_rate": 0.00019278139310677272,
+      "loss": 0.7722515106201172,
+      "step": 1100
+    },
+    {
+      "epoch": 0.14038371548900327,
+      "grad_norm": 0.38113218545913696,
+      "learning_rate": 0.00019157628344179323,
+      "loss": 0.761008529663086,
+      "step": 1200
+    },
+    {
+      "epoch": 0.1520823584464202,
+      "grad_norm": 0.833577036857605,
+      "learning_rate": 0.0001903711737768137,
+      "loss": 0.729088134765625,
+      "step": 1300
+    },
+    {
+      "epoch": 0.16378100140383717,
+      "grad_norm": 0.27296575903892517,
+      "learning_rate": 0.0001891660641118342,
+      "loss": 0.7132440948486328,
+      "step": 1400
+    },
+    {
+      "epoch": 0.1754796443612541,
+      "grad_norm": 0.43808019161224365,
+      "learning_rate": 0.00018796095444685468,
+      "loss": 0.7673744964599609,
+      "step": 1500
+    },
+    {
+      "epoch": 0.18717828731867103,
+      "grad_norm": 0.5978686213493347,
+      "learning_rate": 0.00018675584478187516,
+      "loss": 0.7649851989746094,
+      "step": 1600
+    },
+    {
+      "epoch": 0.19887693027608797,
+      "grad_norm": 0.27942633628845215,
+      "learning_rate": 0.00018555073511689564,
+      "loss": 0.73284912109375,
+      "step": 1700
+    },
+    {
+      "epoch": 0.21057557323350493,
+      "grad_norm": 0.7221409678459167,
+      "learning_rate": 0.00018434562545191613,
+      "loss": 0.8051951599121093,
+      "step": 1800
+    },
+    {
+      "epoch": 0.22227421619092186,
+      "grad_norm": 0.5762982964515686,
+      "learning_rate": 0.00018314051578693664,
+      "loss": 0.7878440856933594,
+      "step": 1900
+    },
+    {
+      "epoch": 0.2339728591483388,
+      "grad_norm": 0.5500592589378357,
+      "learning_rate": 0.0001819354061219571,
+      "loss": 0.7237545013427734,
+      "step": 2000
+    },
+    {
+      "epoch": 0.2339728591483388,
+      "eval_bleu": 14.170822767293767,
+      "eval_chrf++": 37.26464042738157,
+      "eval_gleu": 0.29572456761353044,
+      "eval_loss": 0.1321471929550171,
+      "eval_runtime": 3046.6444,
+      "eval_samples_per_second": 8.206,
+      "eval_steps_per_second": 1.026,
+      "step": 2000
+    },
+    {
+      "epoch": 0.24567150210575572,
+      "grad_norm": 0.24421566724777222,
+      "learning_rate": 0.00018073029645697758,
+      "loss": 0.8127301025390625,
+      "step": 2100
+    },
+    {
+      "epoch": 0.2573701450631727,
+      "grad_norm": 0.4300897419452667,
+      "learning_rate": 0.0001795251867919981,
+      "loss": 0.7431999206542969,
+      "step": 2200
+    },
+    {
+      "epoch": 0.2690687880205896,
+      "grad_norm": 0.4674065411090851,
+      "learning_rate": 0.00017832007712701857,
+      "loss": 0.7770858764648437,
+      "step": 2300
+    },
+    {
+      "epoch": 0.28076743097800655,
+      "grad_norm": 0.3334859311580658,
+      "learning_rate": 0.00017711496746203905,
+      "loss": 0.7566382598876953,
+      "step": 2400
+    },
+    {
+      "epoch": 0.2924660739354235,
+      "grad_norm": 0.5279520153999329,
+      "learning_rate": 0.00017590985779705954,
+      "loss": 0.7609191131591797,
+      "step": 2500
+    },
+    {
+      "epoch": 0.3041647168928404,
+      "grad_norm": 0.40749409794807434,
+      "learning_rate": 0.00017470474813208002,
+      "loss": 0.8018978118896485,
+      "step": 2600
+    },
+    {
+      "epoch": 0.3158633598502574,
+      "grad_norm": 0.5021436214447021,
+      "learning_rate": 0.0001734996384671005,
+      "loss": 0.704549560546875,
+      "step": 2700
+    },
+    {
+      "epoch": 0.32756200280767434,
+      "grad_norm": 0.21254391968250275,
+      "learning_rate": 0.00017229452880212102,
+      "loss": 0.6860762786865234,
+      "step": 2800
+    },
+    {
+      "epoch": 0.33926064576509124,
+      "grad_norm": 0.5828664898872375,
+      "learning_rate": 0.0001710894191371415,
+      "loss": 0.7940917205810547,
+      "step": 2900
+    },
+    {
+      "epoch": 0.3509592887225082,
+      "grad_norm": 0.6279259920120239,
+      "learning_rate": 0.00016988430947216198,
+      "loss": 0.7563919830322265,
+      "step": 3000
+    },
+    {
+      "epoch": 0.3509592887225082,
+      "eval_bleu": 14.190561307729688,
+      "eval_chrf++": 37.282843281422906,
+      "eval_gleu": 0.2959946351903762,
+      "eval_loss": 0.1300257444381714,
+      "eval_runtime": 3028.8248,
+      "eval_samples_per_second": 8.254,
+      "eval_steps_per_second": 1.032,
+      "step": 3000
+    },
+    {
+      "epoch": 0.3626579316799251,
+      "grad_norm": 0.49756914377212524,
+      "learning_rate": 0.00016867919980718247,
+      "loss": 0.7388571929931641,
+      "step": 3100
+    },
+    {
+      "epoch": 0.37435657463734207,
+      "grad_norm": 0.2790064513683319,
+      "learning_rate": 0.00016747409014220295,
+      "loss": 0.8041506958007812,
+      "step": 3200
+    },
+    {
+      "epoch": 0.386055217594759,
+      "grad_norm": 0.4176758825778961,
+      "learning_rate": 0.00016626898047722343,
+      "loss": 0.7459670257568359,
+      "step": 3300
+    },
+    {
+      "epoch": 0.39775386055217593,
+      "grad_norm": 0.643490731716156,
+      "learning_rate": 0.00016506387081224392,
+      "loss": 0.7993578338623046,
+      "step": 3400
+    },
+    {
+      "epoch": 0.4094525035095929,
+      "grad_norm": 0.4160093665122986,
+      "learning_rate": 0.00016385876114726443,
+      "loss": 0.7083788299560547,
+      "step": 3500
+    },
+    {
+      "epoch": 0.42115114646700985,
+      "grad_norm": 0.5131481289863586,
+      "learning_rate": 0.00016265365148228488,
+      "loss": 0.7386051177978515,
+      "step": 3600
+    },
+    {
+      "epoch": 0.43284978942442676,
+      "grad_norm": 0.34466978907585144,
+      "learning_rate": 0.00016144854181730537,
+      "loss": 0.7423291778564454,
+      "step": 3700
+    },
+    {
+      "epoch": 0.4445484323818437,
+      "grad_norm": 0.3849602937698364,
+      "learning_rate": 0.00016024343215232588,
+      "loss": 0.7886087799072266,
+      "step": 3800
+    },
+    {
+      "epoch": 0.4562470753392606,
+      "grad_norm": 1.0863958597183228,
+      "learning_rate": 0.00015903832248734636,
+      "loss": 0.7084539031982422,
+      "step": 3900
+    },
+    {
+      "epoch": 0.4679457182966776,
+      "grad_norm": 0.5512566566467285,
+      "learning_rate": 0.00015783321282236684,
+      "loss": 0.7262689208984375,
+      "step": 4000
+    },
+    {
+      "epoch": 0.4679457182966776,
+      "eval_bleu": 14.223643604859138,
+      "eval_chrf++": 37.31221944095716,
+      "eval_gleu": 0.29643493674629917,
+      "eval_loss": 0.13029149174690247,
+      "eval_runtime": 3029.0038,
+      "eval_samples_per_second": 8.254,
+      "eval_steps_per_second": 1.032,
+      "step": 4000
+    },
+    {
+      "epoch": 0.47964436125409454,
+      "grad_norm": 0.5066221356391907,
+      "learning_rate": 0.00015662810315738733,
+      "loss": 0.7101921844482422,
+      "step": 4100
+    },
+    {
+      "epoch": 0.49134300421151145,
+      "grad_norm": 0.25377070903778076,
+      "learning_rate": 0.0001554229934924078,
+      "loss": 0.8036322021484374,
+      "step": 4200
+    },
+    {
+      "epoch": 0.5030416471689284,
+      "grad_norm": 0.36515700817108154,
+      "learning_rate": 0.0001542178838274283,
+      "loss": 0.7672134399414062,
+      "step": 4300
+    },
+    {
+      "epoch": 0.5147402901263454,
+      "grad_norm": 0.5217819213867188,
+      "learning_rate": 0.00015301277416244878,
+      "loss": 0.7055610656738281,
+      "step": 4400
+    },
+    {
+      "epoch": 0.5264389330837623,
+      "grad_norm": 0.5822096467018127,
+      "learning_rate": 0.0001518076644974693,
+      "loss": 0.7314647674560547,
+      "step": 4500
+    },
+    {
+      "epoch": 0.5381375760411792,
+      "grad_norm": 0.35088884830474854,
+      "learning_rate": 0.00015060255483248977,
+      "loss": 0.7090898132324219,
+      "step": 4600
+    },
+    {
+      "epoch": 0.5498362189985961,
+      "grad_norm": 0.32798826694488525,
+      "learning_rate": 0.00014939744516751023,
+      "loss": 0.7123609161376954,
+      "step": 4700
+    },
+    {
+      "epoch": 0.5615348619560131,
+      "grad_norm": 0.36279675364494324,
+      "learning_rate": 0.00014819233550253074,
+      "loss": 0.6808916473388672,
+      "step": 4800
+    },
+    {
+      "epoch": 0.5732335049134301,
+      "grad_norm": 0.2988830506801605,
+      "learning_rate": 0.00014698722583755122,
+      "loss": 0.7374357604980468,
+      "step": 4900
+    },
+    {
+      "epoch": 0.584932147870847,
+      "grad_norm": 0.3163226246833801,
+      "learning_rate": 0.0001457821161725717,
+      "loss": 0.7219663238525391,
+      "step": 5000
+    },
+    {
+      "epoch": 0.584932147870847,
+      "eval_bleu": 14.478830100713067,
+      "eval_chrf++": 37.47970478737833,
+      "eval_gleu": 0.2988842723825056,
+      "eval_loss": 0.11943691223859787,
+      "eval_runtime": 1205.6734,
+      "eval_samples_per_second": 8.294,
+      "eval_steps_per_second": 1.037,
+      "step": 5000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 17096,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 1.4853509406978048e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2f1adfeab5b878e23075d9ce65374fe908112ad4fdc3ea083b3fff413cae702
+size 5393