Upload 11 files

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: sarvamai/OpenHathi-7B-Hi-v0.1-Base
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.10.0

adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "sarvamai/OpenHathi-7B-Hi-v0.1-Base",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a79365868e96dbd30865018cc8e0ec6ae00dd78c422c7155b448a0f25ea5785f
+size 92824216

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd62859726d46c7cab01c6b8c28886ac32364304c4811b5be12790acd36300ed
+size 47209298

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46290c18c3b3920166595e51bd3f5c6fc1585185680dcfaaf67a05fc1901e325
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50875594b892047c8e46a61b82a18becc1a9e9c9af6ce75ec5a292af0d5a8cd2
+size 1064

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,771 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.572701541042038,
+  "eval_steps": 100,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.49666959047317505,
+      "learning_rate": 0.0001,
+      "loss": 3.1694,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 2.1809041500091553,
+      "eval_runtime": 688.5742,
+      "eval_samples_per_second": 49.254,
+      "eval_steps_per_second": 1.539,
+      "step": 100
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.5750323534011841,
+      "learning_rate": 9.655172413793105e-05,
+      "loss": 2.0372,
+      "step": 200
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 1.9693516492843628,
+      "eval_runtime": 688.4711,
+      "eval_samples_per_second": 49.261,
+      "eval_steps_per_second": 1.54,
+      "step": 200
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.6069626808166504,
+      "learning_rate": 9.310344827586207e-05,
+      "loss": 1.9397,
+      "step": 300
+    },
+    {
+      "epoch": 0.09,
+      "eval_loss": 1.914998173713684,
+      "eval_runtime": 688.3078,
+      "eval_samples_per_second": 49.273,
+      "eval_steps_per_second": 1.54,
+      "step": 300
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.6587632894515991,
+      "learning_rate": 8.96551724137931e-05,
+      "loss": 1.9029,
+      "step": 400
+    },
+    {
+      "epoch": 0.13,
+      "eval_loss": 1.887677550315857,
+      "eval_runtime": 688.3053,
+      "eval_samples_per_second": 49.273,
+      "eval_steps_per_second": 1.54,
+      "step": 400
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.6251624226570129,
+      "learning_rate": 8.620689655172413e-05,
+      "loss": 1.8749,
+      "step": 500
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 1.8642584085464478,
+      "eval_runtime": 688.2945,
+      "eval_samples_per_second": 49.274,
+      "eval_steps_per_second": 1.54,
+      "step": 500
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.6488652229309082,
+      "learning_rate": 8.275862068965517e-05,
+      "loss": 1.8444,
+      "step": 600
+    },
+    {
+      "epoch": 0.19,
+      "eval_loss": 1.8471214771270752,
+      "eval_runtime": 688.3193,
+      "eval_samples_per_second": 49.272,
+      "eval_steps_per_second": 1.54,
+      "step": 600
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.5931334495544434,
+      "learning_rate": 7.931034482758621e-05,
+      "loss": 1.8316,
+      "step": 700
+    },
+    {
+      "epoch": 0.22,
+      "eval_loss": 1.8358324766159058,
+      "eval_runtime": 688.2994,
+      "eval_samples_per_second": 49.274,
+      "eval_steps_per_second": 1.54,
+      "step": 700
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.5620170831680298,
+      "learning_rate": 7.586206896551724e-05,
+      "loss": 1.8312,
+      "step": 800
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 1.824582815170288,
+      "eval_runtime": 688.296,
+      "eval_samples_per_second": 49.274,
+      "eval_steps_per_second": 1.54,
+      "step": 800
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.5843664407730103,
+      "learning_rate": 7.241379310344828e-05,
+      "loss": 1.8203,
+      "step": 900
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 1.8139162063598633,
+      "eval_runtime": 688.4311,
+      "eval_samples_per_second": 49.264,
+      "eval_steps_per_second": 1.54,
+      "step": 900
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.6241691708564758,
+      "learning_rate": 6.896551724137931e-05,
+      "loss": 1.8057,
+      "step": 1000
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 1.8063077926635742,
+      "eval_runtime": 688.4241,
+      "eval_samples_per_second": 49.265,
+      "eval_steps_per_second": 1.54,
+      "step": 1000
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.639207661151886,
+      "learning_rate": 6.551724137931034e-05,
+      "loss": 1.7986,
+      "step": 1100
+    },
+    {
+      "epoch": 0.35,
+      "eval_loss": 1.7982680797576904,
+      "eval_runtime": 688.2656,
+      "eval_samples_per_second": 49.276,
+      "eval_steps_per_second": 1.54,
+      "step": 1100
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.6417416930198669,
+      "learning_rate": 6.206896551724138e-05,
+      "loss": 1.7969,
+      "step": 1200
+    },
+    {
+      "epoch": 0.38,
+      "eval_loss": 1.7924365997314453,
+      "eval_runtime": 688.2797,
+      "eval_samples_per_second": 49.275,
+      "eval_steps_per_second": 1.54,
+      "step": 1200
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.6295751333236694,
+      "learning_rate": 5.862068965517241e-05,
+      "loss": 1.779,
+      "step": 1300
+    },
+    {
+      "epoch": 0.41,
+      "eval_loss": 1.785871148109436,
+      "eval_runtime": 688.4975,
+      "eval_samples_per_second": 49.259,
+      "eval_steps_per_second": 1.54,
+      "step": 1300
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.6242513656616211,
+      "learning_rate": 5.517241379310345e-05,
+      "loss": 1.7743,
+      "step": 1400
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 1.780082106590271,
+      "eval_runtime": 688.2673,
+      "eval_samples_per_second": 49.276,
+      "eval_steps_per_second": 1.54,
+      "step": 1400
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.6389493942260742,
+      "learning_rate": 5.172413793103449e-05,
+      "loss": 1.769,
+      "step": 1500
+    },
+    {
+      "epoch": 0.47,
+      "eval_loss": 1.7744983434677124,
+      "eval_runtime": 687.8653,
+      "eval_samples_per_second": 49.305,
+      "eval_steps_per_second": 1.541,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.669941246509552,
+      "learning_rate": 4.827586206896552e-05,
+      "loss": 1.7734,
+      "step": 1600
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 1.7702207565307617,
+      "eval_runtime": 688.2155,
+      "eval_samples_per_second": 49.28,
+      "eval_steps_per_second": 1.54,
+      "step": 1600
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.6194856762886047,
+      "learning_rate": 4.482758620689655e-05,
+      "loss": 1.7666,
+      "step": 1700
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.7659046649932861,
+      "eval_runtime": 688.2457,
+      "eval_samples_per_second": 49.277,
+      "eval_steps_per_second": 1.54,
+      "step": 1700
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.6265833377838135,
+      "learning_rate": 4.1379310344827587e-05,
+      "loss": 1.7578,
+      "step": 1800
+    },
+    {
+      "epoch": 0.57,
+      "eval_loss": 1.7620124816894531,
+      "eval_runtime": 688.4272,
+      "eval_samples_per_second": 49.264,
+      "eval_steps_per_second": 1.54,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.6443737745285034,
+      "learning_rate": 3.793103448275862e-05,
+      "loss": 1.7321,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 1.7327184677124023,
+      "eval_runtime": 679.9956,
+      "eval_samples_per_second": 49.875,
+      "eval_steps_per_second": 1.559,
+      "step": 1900
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.6571601033210754,
+      "learning_rate": 3.4482758620689657e-05,
+      "loss": 1.7336,
+      "step": 2000
+    },
+    {
+      "epoch": 0.63,
+      "eval_loss": 1.730404019355774,
+      "eval_runtime": 679.76,
+      "eval_samples_per_second": 49.893,
+      "eval_steps_per_second": 1.559,
+      "step": 2000
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.651569128036499,
+      "learning_rate": 3.103448275862069e-05,
+      "loss": 1.7216,
+      "step": 2100
+    },
+    {
+      "epoch": 0.66,
+      "eval_loss": 1.7281814813613892,
+      "eval_runtime": 679.7835,
+      "eval_samples_per_second": 49.891,
+      "eval_steps_per_second": 1.559,
+      "step": 2100
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.6475515365600586,
+      "learning_rate": 2.7586206896551727e-05,
+      "loss": 1.7263,
+      "step": 2200
+    },
+    {
+      "epoch": 0.69,
+      "eval_loss": 1.726309061050415,
+      "eval_runtime": 679.7496,
+      "eval_samples_per_second": 49.893,
+      "eval_steps_per_second": 1.559,
+      "step": 2200
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.6775307059288025,
+      "learning_rate": 2.413793103448276e-05,
+      "loss": 1.728,
+      "step": 2300
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 1.7238056659698486,
+      "eval_runtime": 679.9872,
+      "eval_samples_per_second": 49.876,
+      "eval_steps_per_second": 1.559,
+      "step": 2300
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.7065313458442688,
+      "learning_rate": 2.0689655172413793e-05,
+      "loss": 1.7222,
+      "step": 2400
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 1.7217180728912354,
+      "eval_runtime": 679.9742,
+      "eval_samples_per_second": 49.877,
+      "eval_steps_per_second": 1.559,
+      "step": 2400
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.6938297748565674,
+      "learning_rate": 1.7241379310344828e-05,
+      "loss": 1.7249,
+      "step": 2500
+    },
+    {
+      "epoch": 0.79,
+      "eval_loss": 1.719938039779663,
+      "eval_runtime": 679.7345,
+      "eval_samples_per_second": 49.894,
+      "eval_steps_per_second": 1.559,
+      "step": 2500
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.6739135980606079,
+      "learning_rate": 1.3793103448275863e-05,
+      "loss": 1.7116,
+      "step": 2600
+    },
+    {
+      "epoch": 0.82,
+      "eval_loss": 1.7181174755096436,
+      "eval_runtime": 679.9623,
+      "eval_samples_per_second": 49.878,
+      "eval_steps_per_second": 1.559,
+      "step": 2600
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.6775588989257812,
+      "learning_rate": 1.0344827586206897e-05,
+      "loss": 1.7146,
+      "step": 2700
+    },
+    {
+      "epoch": 0.85,
+      "eval_loss": 1.7168805599212646,
+      "eval_runtime": 679.7273,
+      "eval_samples_per_second": 49.895,
+      "eval_steps_per_second": 1.559,
+      "step": 2700
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.6750255823135376,
+      "learning_rate": 6.896551724137932e-06,
+      "loss": 1.712,
+      "step": 2800
+    },
+    {
+      "epoch": 0.88,
+      "eval_loss": 1.715585708618164,
+      "eval_runtime": 679.7333,
+      "eval_samples_per_second": 49.895,
+      "eval_steps_per_second": 1.559,
+      "step": 2800
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.68208247423172,
+      "learning_rate": 3.448275862068966e-06,
+      "loss": 1.7184,
+      "step": 2900
+    },
+    {
+      "epoch": 0.91,
+      "eval_loss": 1.7148162126541138,
+      "eval_runtime": 679.6399,
+      "eval_samples_per_second": 49.901,
+      "eval_steps_per_second": 1.56,
+      "step": 2900
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.6982720494270325,
+      "learning_rate": 0.0,
+      "loss": 1.7137,
+      "step": 3000
+    },
+    {
+      "epoch": 0.94,
+      "eval_loss": 1.7144192457199097,
+      "eval_runtime": 679.8535,
+      "eval_samples_per_second": 49.886,
+      "eval_steps_per_second": 1.559,
+      "step": 3000
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.7738541960716248,
+      "learning_rate": 3.8775510204081634e-05,
+      "loss": 1.7029,
+      "step": 3100
+    },
+    {
+      "epoch": 0.97,
+      "eval_loss": 1.7050038576126099,
+      "eval_runtime": 687.1983,
+      "eval_samples_per_second": 49.353,
+      "eval_steps_per_second": 1.542,
+      "step": 3100
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.6895627379417419,
+      "learning_rate": 3.673469387755102e-05,
+      "loss": 1.7094,
+      "step": 3200
+    },
+    {
+      "epoch": 1.01,
+      "eval_loss": 1.7042526006698608,
+      "eval_runtime": 687.1845,
+      "eval_samples_per_second": 49.354,
+      "eval_steps_per_second": 1.543,
+      "step": 3200
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.8041057586669922,
+      "learning_rate": 3.469387755102041e-05,
+      "loss": 1.7049,
+      "step": 3300
+    },
+    {
+      "epoch": 1.04,
+      "eval_loss": 1.7035516500473022,
+      "eval_runtime": 687.4035,
+      "eval_samples_per_second": 49.338,
+      "eval_steps_per_second": 1.542,
+      "step": 3300
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.7259939908981323,
+      "learning_rate": 3.265306122448979e-05,
+      "loss": 1.7098,
+      "step": 3400
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.7024834156036377,
+      "eval_runtime": 687.1647,
+      "eval_samples_per_second": 49.355,
+      "eval_steps_per_second": 1.543,
+      "step": 3400
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.7912746667861938,
+      "learning_rate": 3.061224489795919e-05,
+      "loss": 1.7015,
+      "step": 3500
+    },
+    {
+      "epoch": 1.1,
+      "eval_loss": 1.7005605697631836,
+      "eval_runtime": 687.1366,
+      "eval_samples_per_second": 49.357,
+      "eval_steps_per_second": 1.543,
+      "step": 3500
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.8287527561187744,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 1.6876,
+      "step": 3600
+    },
+    {
+      "epoch": 1.13,
+      "eval_loss": 1.6933950185775757,
+      "eval_runtime": 683.5096,
+      "eval_samples_per_second": 49.619,
+      "eval_steps_per_second": 1.551,
+      "step": 3600
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.736217737197876,
+      "learning_rate": 2.6530612244897963e-05,
+      "loss": 1.6958,
+      "step": 3700
+    },
+    {
+      "epoch": 1.16,
+      "eval_loss": 1.692893624305725,
+      "eval_runtime": 683.433,
+      "eval_samples_per_second": 49.624,
+      "eval_steps_per_second": 1.551,
+      "step": 3700
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.7109358906745911,
+      "learning_rate": 2.448979591836735e-05,
+      "loss": 1.6885,
+      "step": 3800
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 1.6916097402572632,
+      "eval_runtime": 683.3969,
+      "eval_samples_per_second": 49.627,
+      "eval_steps_per_second": 1.551,
+      "step": 3800
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.7234348654747009,
+      "learning_rate": 2.2448979591836737e-05,
+      "loss": 1.6934,
+      "step": 3900
+    },
+    {
+      "epoch": 1.23,
+      "eval_loss": 1.6902754306793213,
+      "eval_runtime": 683.1628,
+      "eval_samples_per_second": 49.644,
+      "eval_steps_per_second": 1.552,
+      "step": 3900
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.7684239149093628,
+      "learning_rate": 2.0408163265306123e-05,
+      "loss": 1.6909,
+      "step": 4000
+    },
+    {
+      "epoch": 1.26,
+      "eval_loss": 1.689305067062378,
+      "eval_runtime": 683.1661,
+      "eval_samples_per_second": 49.644,
+      "eval_steps_per_second": 1.552,
+      "step": 4000
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.7669008374214172,
+      "learning_rate": 1.836734693877551e-05,
+      "loss": 1.6907,
+      "step": 4100
+    },
+    {
+      "epoch": 1.29,
+      "eval_loss": 1.688330888748169,
+      "eval_runtime": 683.1804,
+      "eval_samples_per_second": 49.643,
+      "eval_steps_per_second": 1.552,
+      "step": 4100
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.7422395348548889,
+      "learning_rate": 1.6326530612244897e-05,
+      "loss": 1.6912,
+      "step": 4200
+    },
+    {
+      "epoch": 1.32,
+      "eval_loss": 1.687252163887024,
+      "eval_runtime": 683.2129,
+      "eval_samples_per_second": 49.64,
+      "eval_steps_per_second": 1.551,
+      "step": 4200
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.7352548837661743,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 1.6873,
+      "step": 4300
+    },
+    {
+      "epoch": 1.35,
+      "eval_loss": 1.6862083673477173,
+      "eval_runtime": 683.1788,
+      "eval_samples_per_second": 49.643,
+      "eval_steps_per_second": 1.552,
+      "step": 4300
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.7130007147789001,
+      "learning_rate": 1.2244897959183674e-05,
+      "loss": 1.6858,
+      "step": 4400
+    },
+    {
+      "epoch": 1.38,
+      "eval_loss": 1.6853961944580078,
+      "eval_runtime": 683.1786,
+      "eval_samples_per_second": 49.643,
+      "eval_steps_per_second": 1.552,
+      "step": 4400
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.7947734594345093,
+      "learning_rate": 1.0204081632653061e-05,
+      "loss": 1.6813,
+      "step": 4500
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 1.6845451593399048,
+      "eval_runtime": 683.4171,
+      "eval_samples_per_second": 49.626,
+      "eval_steps_per_second": 1.551,
+      "step": 4500
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.7227717041969299,
+      "learning_rate": 8.163265306122448e-06,
+      "loss": 1.6867,
+      "step": 4600
+    },
+    {
+      "epoch": 1.45,
+      "eval_loss": 1.6836014986038208,
+      "eval_runtime": 683.3718,
+      "eval_samples_per_second": 49.629,
+      "eval_steps_per_second": 1.551,
+      "step": 4600
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.746582567691803,
+      "learning_rate": 6.122448979591837e-06,
+      "loss": 1.6882,
+      "step": 4700
+    },
+    {
+      "epoch": 1.48,
+      "eval_loss": 1.682924509048462,
+      "eval_runtime": 683.3662,
+      "eval_samples_per_second": 49.629,
+      "eval_steps_per_second": 1.551,
+      "step": 4700
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.7279271483421326,
+      "learning_rate": 4.081632653061224e-06,
+      "loss": 1.6872,
+      "step": 4800
+    },
+    {
+      "epoch": 1.51,
+      "eval_loss": 1.682388186454773,
+      "eval_runtime": 683.1514,
+      "eval_samples_per_second": 49.645,
+      "eval_steps_per_second": 1.552,
+      "step": 4800
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.7303986549377441,
+      "learning_rate": 2.040816326530612e-06,
+      "loss": 1.6898,
+      "step": 4900
+    },
+    {
+      "epoch": 1.54,
+      "eval_loss": 1.682073950767517,
+      "eval_runtime": 683.3608,
+      "eval_samples_per_second": 49.63,
+      "eval_steps_per_second": 1.551,
+      "step": 4900
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.763130784034729,
+      "learning_rate": 0.0,
+      "loss": 1.6845,
+      "step": 5000
+    },
+    {
+      "epoch": 1.57,
+      "eval_loss": 1.6819010972976685,
+      "eval_runtime": 683.1778,
+      "eval_samples_per_second": 49.643,
+      "eval_steps_per_second": 1.552,
+      "step": 5000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "total_flos": 2.03873794720034e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc19869896809aeeb998276dffc5c796ca8ce160e5c5b0e576340e801ae8fa90
+size 4856