Upload 14 files

README.md

@@ -1,3 +1,202 @@
----
-license: apache-2.0
----
+---
+base_model: Qwen/Qwen2-1.5B
+library_name: peft
+---
+
+# 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 0.11.1

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-1.5B",
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "lm_head",
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "q_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 sha256:5a00964968e6d0a5dff2413128626581089973918056ec3d6a35bc4c3de30ffc
+size 1017229528

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f78d23e80b412492bb23e7f77c42dc58a5421d56d226af3bfb96ded4984901c
+size 167693808

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6e37e1ce471c56982fb53ecc021031588a46b2ad8c358491def6bf222b39b2c
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82bae41031bb9a3e20f8500051e9b275b0c0fa328ed27a9d8750a01556e2e224
+size 1064

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "max_length": 512,
+  "model_max_length": 32768,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,828 @@
+{
+  "best_metric": 0.8609164953231812,
+  "best_model_checkpoint": "/home/coder/qwen2/checkpoint-15900",
+  "epoch": 0.9999803783832573,
+  "eval_steps": 300,
+  "global_step": 15926,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.018836752073023807,
+      "grad_norm": 0.2832883298397064,
+      "learning_rate": 0.00019629420262546324,
+      "loss": 1.1403,
+      "step": 300
+    },
+    {
+      "epoch": 0.018836752073023807,
+      "eval_loss": 1.0671226978302002,
+      "eval_runtime": 300.1436,
+      "eval_samples_per_second": 17.155,
+      "eval_steps_per_second": 2.146,
+      "step": 300
+    },
+    {
+      "epoch": 0.037673504146047615,
+      "grad_norm": 0.33913707733154297,
+      "learning_rate": 0.00019252559512593432,
+      "loss": 1.0551,
+      "step": 600
+    },
+    {
+      "epoch": 0.037673504146047615,
+      "eval_loss": 1.0309056043624878,
+      "eval_runtime": 300.0852,
+      "eval_samples_per_second": 17.158,
+      "eval_steps_per_second": 2.146,
+      "step": 600
+    },
+    {
+      "epoch": 0.05651025621907143,
+      "grad_norm": 0.30800801515579224,
+      "learning_rate": 0.0001887569876264054,
+      "loss": 1.0185,
+      "step": 900
+    },
+    {
+      "epoch": 0.05651025621907143,
+      "eval_loss": 1.0096280574798584,
+      "eval_runtime": 299.931,
+      "eval_samples_per_second": 17.167,
+      "eval_steps_per_second": 2.147,
+      "step": 900
+    },
+    {
+      "epoch": 0.07534700829209523,
+      "grad_norm": 0.317748099565506,
+      "learning_rate": 0.00018498838012687648,
+      "loss": 0.9952,
+      "step": 1200
+    },
+    {
+      "epoch": 0.07534700829209523,
+      "eval_loss": 0.9937332272529602,
+      "eval_runtime": 299.9997,
+      "eval_samples_per_second": 17.163,
+      "eval_steps_per_second": 2.147,
+      "step": 1200
+    },
+    {
+      "epoch": 0.09418376036511904,
+      "grad_norm": 0.36215266585350037,
+      "learning_rate": 0.00018121977262734753,
+      "loss": 0.9931,
+      "step": 1500
+    },
+    {
+      "epoch": 0.09418376036511904,
+      "eval_loss": 0.9828254580497742,
+      "eval_runtime": 299.9242,
+      "eval_samples_per_second": 17.168,
+      "eval_steps_per_second": 2.147,
+      "step": 1500
+    },
+    {
+      "epoch": 0.11302051243814286,
+      "grad_norm": 0.3347627520561218,
+      "learning_rate": 0.0001774511651278186,
+      "loss": 0.9763,
+      "step": 1800
+    },
+    {
+      "epoch": 0.11302051243814286,
+      "eval_loss": 0.972442626953125,
+      "eval_runtime": 299.8563,
+      "eval_samples_per_second": 17.172,
+      "eval_steps_per_second": 2.148,
+      "step": 1800
+    },
+    {
+      "epoch": 0.13185726451116667,
+      "grad_norm": 0.319148451089859,
+      "learning_rate": 0.0001736825576282897,
+      "loss": 0.9727,
+      "step": 2100
+    },
+    {
+      "epoch": 0.13185726451116667,
+      "eval_loss": 0.965033769607544,
+      "eval_runtime": 299.797,
+      "eval_samples_per_second": 17.175,
+      "eval_steps_per_second": 2.148,
+      "step": 2100
+    },
+    {
+      "epoch": 0.15069401658419046,
+      "grad_norm": 0.2830144166946411,
+      "learning_rate": 0.00016991395012876077,
+      "loss": 0.9674,
+      "step": 2400
+    },
+    {
+      "epoch": 0.15069401658419046,
+      "eval_loss": 0.9570498466491699,
+      "eval_runtime": 300.0087,
+      "eval_samples_per_second": 17.163,
+      "eval_steps_per_second": 2.147,
+      "step": 2400
+    },
+    {
+      "epoch": 0.16953076865721428,
+      "grad_norm": 0.30889859795570374,
+      "learning_rate": 0.00016614534262923185,
+      "loss": 0.9601,
+      "step": 2700
+    },
+    {
+      "epoch": 0.16953076865721428,
+      "eval_loss": 0.9515209197998047,
+      "eval_runtime": 299.9801,
+      "eval_samples_per_second": 17.164,
+      "eval_steps_per_second": 2.147,
+      "step": 2700
+    },
+    {
+      "epoch": 0.18836752073023807,
+      "grad_norm": 0.33287131786346436,
+      "learning_rate": 0.0001623767351297029,
+      "loss": 0.944,
+      "step": 3000
+    },
+    {
+      "epoch": 0.18836752073023807,
+      "eval_loss": 0.9454107284545898,
+      "eval_runtime": 299.9554,
+      "eval_samples_per_second": 17.166,
+      "eval_steps_per_second": 2.147,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2072042728032619,
+      "grad_norm": 0.31519943475723267,
+      "learning_rate": 0.00015860812763017398,
+      "loss": 0.9462,
+      "step": 3300
+    },
+    {
+      "epoch": 0.2072042728032619,
+      "eval_loss": 0.9404099583625793,
+      "eval_runtime": 299.9447,
+      "eval_samples_per_second": 17.166,
+      "eval_steps_per_second": 2.147,
+      "step": 3300
+    },
+    {
+      "epoch": 0.22604102487628572,
+      "grad_norm": 0.315909743309021,
+      "learning_rate": 0.00015483952013064506,
+      "loss": 0.9326,
+      "step": 3600
+    },
+    {
+      "epoch": 0.22604102487628572,
+      "eval_loss": 0.9352145195007324,
+      "eval_runtime": 299.9991,
+      "eval_samples_per_second": 17.163,
+      "eval_steps_per_second": 2.147,
+      "step": 3600
+    },
+    {
+      "epoch": 0.2448777769493095,
+      "grad_norm": 0.2997918128967285,
+      "learning_rate": 0.00015107091263111613,
+      "loss": 0.9298,
+      "step": 3900
+    },
+    {
+      "epoch": 0.2448777769493095,
+      "eval_loss": 0.9315630793571472,
+      "eval_runtime": 299.95,
+      "eval_samples_per_second": 17.166,
+      "eval_steps_per_second": 2.147,
+      "step": 3900
+    },
+    {
+      "epoch": 0.26371452902233333,
+      "grad_norm": 0.2730711102485657,
+      "learning_rate": 0.0001473023051315872,
+      "loss": 0.9345,
+      "step": 4200
+    },
+    {
+      "epoch": 0.26371452902233333,
+      "eval_loss": 0.9274590015411377,
+      "eval_runtime": 300.1027,
+      "eval_samples_per_second": 17.157,
+      "eval_steps_per_second": 2.146,
+      "step": 4200
+    },
+    {
+      "epoch": 0.28255128109535715,
+      "grad_norm": 0.27338674664497375,
+      "learning_rate": 0.0001435336976320583,
+      "loss": 0.9378,
+      "step": 4500
+    },
+    {
+      "epoch": 0.28255128109535715,
+      "eval_loss": 0.9236754775047302,
+      "eval_runtime": 299.988,
+      "eval_samples_per_second": 17.164,
+      "eval_steps_per_second": 2.147,
+      "step": 4500
+    },
+    {
+      "epoch": 0.3013880331683809,
+      "grad_norm": 0.3145460784435272,
+      "learning_rate": 0.00013976509013252937,
+      "loss": 0.9235,
+      "step": 4800
+    },
+    {
+      "epoch": 0.3013880331683809,
+      "eval_loss": 0.9199886322021484,
+      "eval_runtime": 299.9923,
+      "eval_samples_per_second": 17.164,
+      "eval_steps_per_second": 2.147,
+      "step": 4800
+    },
+    {
+      "epoch": 0.32022478524140474,
+      "grad_norm": 0.2656671702861786,
+      "learning_rate": 0.00013599648263300045,
+      "loss": 0.9207,
+      "step": 5100
+    },
+    {
+      "epoch": 0.32022478524140474,
+      "eval_loss": 0.9165565371513367,
+      "eval_runtime": 299.8304,
+      "eval_samples_per_second": 17.173,
+      "eval_steps_per_second": 2.148,
+      "step": 5100
+    },
+    {
+      "epoch": 0.33906153731442856,
+      "grad_norm": 0.2907351851463318,
+      "learning_rate": 0.00013222787513347153,
+      "loss": 0.9149,
+      "step": 5400
+    },
+    {
+      "epoch": 0.33906153731442856,
+      "eval_loss": 0.9132035374641418,
+      "eval_runtime": 299.8597,
+      "eval_samples_per_second": 17.171,
+      "eval_steps_per_second": 2.148,
+      "step": 5400
+    },
+    {
+      "epoch": 0.3578982893874524,
+      "grad_norm": 0.39790818095207214,
+      "learning_rate": 0.0001284592676339426,
+      "loss": 0.9063,
+      "step": 5700
+    },
+    {
+      "epoch": 0.3578982893874524,
+      "eval_loss": 0.9105966687202454,
+      "eval_runtime": 300.0175,
+      "eval_samples_per_second": 17.162,
+      "eval_steps_per_second": 2.147,
+      "step": 5700
+    },
+    {
+      "epoch": 0.37673504146047615,
+      "grad_norm": 0.3338871896266937,
+      "learning_rate": 0.00012469066013441369,
+      "loss": 0.9046,
+      "step": 6000
+    },
+    {
+      "epoch": 0.37673504146047615,
+      "eval_loss": 0.9074862003326416,
+      "eval_runtime": 299.8956,
+      "eval_samples_per_second": 17.169,
+      "eval_steps_per_second": 2.147,
+      "step": 6000
+    },
+    {
+      "epoch": 0.39557179353349997,
+      "grad_norm": 0.2925800383090973,
+      "learning_rate": 0.00012092205263488474,
+      "loss": 0.907,
+      "step": 6300
+    },
+    {
+      "epoch": 0.39557179353349997,
+      "eval_loss": 0.9044873118400574,
+      "eval_runtime": 300.0697,
+      "eval_samples_per_second": 17.159,
+      "eval_steps_per_second": 2.146,
+      "step": 6300
+    },
+    {
+      "epoch": 0.4144085456065238,
+      "grad_norm": 0.34801357984542847,
+      "learning_rate": 0.00011715344513535582,
+      "loss": 0.9042,
+      "step": 6600
+    },
+    {
+      "epoch": 0.4144085456065238,
+      "eval_loss": 0.9019830822944641,
+      "eval_runtime": 299.9421,
+      "eval_samples_per_second": 17.167,
+      "eval_steps_per_second": 2.147,
+      "step": 6600
+    },
+    {
+      "epoch": 0.4332452976795476,
+      "grad_norm": 0.3444356918334961,
+      "learning_rate": 0.0001133848376358269,
+      "loss": 0.9019,
+      "step": 6900
+    },
+    {
+      "epoch": 0.4332452976795476,
+      "eval_loss": 0.8995754718780518,
+      "eval_runtime": 299.921,
+      "eval_samples_per_second": 17.168,
+      "eval_steps_per_second": 2.147,
+      "step": 6900
+    },
+    {
+      "epoch": 0.45208204975257144,
+      "grad_norm": 0.3366526961326599,
+      "learning_rate": 0.00010961623013629799,
+      "loss": 0.9041,
+      "step": 7200
+    },
+    {
+      "epoch": 0.45208204975257144,
+      "eval_loss": 0.8974488973617554,
+      "eval_runtime": 299.9169,
+      "eval_samples_per_second": 17.168,
+      "eval_steps_per_second": 2.147,
+      "step": 7200
+    },
+    {
+      "epoch": 0.4709188018255952,
+      "grad_norm": 0.34138697385787964,
+      "learning_rate": 0.00010584762263676907,
+      "loss": 0.9001,
+      "step": 7500
+    },
+    {
+      "epoch": 0.4709188018255952,
+      "eval_loss": 0.8951303958892822,
+      "eval_runtime": 299.8867,
+      "eval_samples_per_second": 17.17,
+      "eval_steps_per_second": 2.147,
+      "step": 7500
+    },
+    {
+      "epoch": 0.489755553898619,
+      "grad_norm": 0.35338446497917175,
+      "learning_rate": 0.00010207901513724012,
+      "loss": 0.8962,
+      "step": 7800
+    },
+    {
+      "epoch": 0.489755553898619,
+      "eval_loss": 0.8931267261505127,
+      "eval_runtime": 300.0707,
+      "eval_samples_per_second": 17.159,
+      "eval_steps_per_second": 2.146,
+      "step": 7800
+    },
+    {
+      "epoch": 0.5085923059716428,
+      "grad_norm": 0.33024904131889343,
+      "learning_rate": 9.83104076377112e-05,
+      "loss": 0.901,
+      "step": 8100
+    },
+    {
+      "epoch": 0.5085923059716428,
+      "eval_loss": 0.8908406496047974,
+      "eval_runtime": 300.0908,
+      "eval_samples_per_second": 17.158,
+      "eval_steps_per_second": 2.146,
+      "step": 8100
+    },
+    {
+      "epoch": 0.5274290580446667,
+      "grad_norm": 0.30269181728363037,
+      "learning_rate": 9.454180013818228e-05,
+      "loss": 0.8886,
+      "step": 8400
+    },
+    {
+      "epoch": 0.5274290580446667,
+      "eval_loss": 0.8892831802368164,
+      "eval_runtime": 299.9819,
+      "eval_samples_per_second": 17.164,
+      "eval_steps_per_second": 2.147,
+      "step": 8400
+    },
+    {
+      "epoch": 0.5462658101176905,
+      "grad_norm": 0.32455185055732727,
+      "learning_rate": 9.077319263865335e-05,
+      "loss": 0.8823,
+      "step": 8700
+    },
+    {
+      "epoch": 0.5462658101176905,
+      "eval_loss": 0.887444019317627,
+      "eval_runtime": 300.1485,
+      "eval_samples_per_second": 17.155,
+      "eval_steps_per_second": 2.146,
+      "step": 8700
+    },
+    {
+      "epoch": 0.5651025621907143,
+      "grad_norm": 0.32726097106933594,
+      "learning_rate": 8.700458513912443e-05,
+      "loss": 0.8773,
+      "step": 9000
+    },
+    {
+      "epoch": 0.5651025621907143,
+      "eval_loss": 0.885347306728363,
+      "eval_runtime": 300.0218,
+      "eval_samples_per_second": 17.162,
+      "eval_steps_per_second": 2.147,
+      "step": 9000
+    },
+    {
+      "epoch": 0.5839393142637381,
+      "grad_norm": 0.3211737275123596,
+      "learning_rate": 8.323597763959551e-05,
+      "loss": 0.8876,
+      "step": 9300
+    },
+    {
+      "epoch": 0.5839393142637381,
+      "eval_loss": 0.8837311267852783,
+      "eval_runtime": 299.8508,
+      "eval_samples_per_second": 17.172,
+      "eval_steps_per_second": 2.148,
+      "step": 9300
+    },
+    {
+      "epoch": 0.6027760663367618,
+      "grad_norm": 0.3470586836338043,
+      "learning_rate": 7.946737014006658e-05,
+      "loss": 0.888,
+      "step": 9600
+    },
+    {
+      "epoch": 0.6027760663367618,
+      "eval_loss": 0.8818086981773376,
+      "eval_runtime": 299.9724,
+      "eval_samples_per_second": 17.165,
+      "eval_steps_per_second": 2.147,
+      "step": 9600
+    },
+    {
+      "epoch": 0.6216128184097857,
+      "grad_norm": 0.3012458384037018,
+      "learning_rate": 7.569876264053766e-05,
+      "loss": 0.8833,
+      "step": 9900
+    },
+    {
+      "epoch": 0.6216128184097857,
+      "eval_loss": 0.8803924322128296,
+      "eval_runtime": 300.0969,
+      "eval_samples_per_second": 17.158,
+      "eval_steps_per_second": 2.146,
+      "step": 9900
+    },
+    {
+      "epoch": 0.6404495704828095,
+      "grad_norm": 0.32445794343948364,
+      "learning_rate": 7.194271716600717e-05,
+      "loss": 0.8841,
+      "step": 10200
+    },
+    {
+      "epoch": 0.6404495704828095,
+      "eval_loss": 0.8785931468009949,
+      "eval_runtime": 299.8302,
+      "eval_samples_per_second": 17.173,
+      "eval_steps_per_second": 2.148,
+      "step": 10200
+    },
+    {
+      "epoch": 0.6592863225558333,
+      "grad_norm": 0.33264926075935364,
+      "learning_rate": 6.817410966647824e-05,
+      "loss": 0.8852,
+      "step": 10500
+    },
+    {
+      "epoch": 0.6592863225558333,
+      "eval_loss": 0.8771566152572632,
+      "eval_runtime": 300.0665,
+      "eval_samples_per_second": 17.16,
+      "eval_steps_per_second": 2.146,
+      "step": 10500
+    },
+    {
+      "epoch": 0.6781230746288571,
+      "grad_norm": 0.3084549307823181,
+      "learning_rate": 6.440550216694932e-05,
+      "loss": 0.8793,
+      "step": 10800
+    },
+    {
+      "epoch": 0.6781230746288571,
+      "eval_loss": 0.8756351470947266,
+      "eval_runtime": 300.155,
+      "eval_samples_per_second": 17.154,
+      "eval_steps_per_second": 2.146,
+      "step": 10800
+    },
+    {
+      "epoch": 0.696959826701881,
+      "grad_norm": 0.3315499722957611,
+      "learning_rate": 6.0636894667420396e-05,
+      "loss": 0.8687,
+      "step": 11100
+    },
+    {
+      "epoch": 0.696959826701881,
+      "eval_loss": 0.8744714260101318,
+      "eval_runtime": 300.5183,
+      "eval_samples_per_second": 17.134,
+      "eval_steps_per_second": 2.143,
+      "step": 11100
+    },
+    {
+      "epoch": 0.7157965787749048,
+      "grad_norm": 0.35962772369384766,
+      "learning_rate": 5.686828716789147e-05,
+      "loss": 0.8631,
+      "step": 11400
+    },
+    {
+      "epoch": 0.7157965787749048,
+      "eval_loss": 0.8730462789535522,
+      "eval_runtime": 299.7837,
+      "eval_samples_per_second": 17.176,
+      "eval_steps_per_second": 2.148,
+      "step": 11400
+    },
+    {
+      "epoch": 0.7346333308479286,
+      "grad_norm": 0.33538639545440674,
+      "learning_rate": 5.3099679668362547e-05,
+      "loss": 0.879,
+      "step": 11700
+    },
+    {
+      "epoch": 0.7346333308479286,
+      "eval_loss": 0.8714411854743958,
+      "eval_runtime": 299.9502,
+      "eval_samples_per_second": 17.166,
+      "eval_steps_per_second": 2.147,
+      "step": 11700
+    },
+    {
+      "epoch": 0.7534700829209523,
+      "grad_norm": 0.3434339165687561,
+      "learning_rate": 4.933107216883362e-05,
+      "loss": 0.8616,
+      "step": 12000
+    },
+    {
+      "epoch": 0.7534700829209523,
+      "eval_loss": 0.8703322410583496,
+      "eval_runtime": 300.0139,
+      "eval_samples_per_second": 17.163,
+      "eval_steps_per_second": 2.147,
+      "step": 12000
+    },
+    {
+      "epoch": 0.7723068349939761,
+      "grad_norm": 0.34114760160446167,
+      "learning_rate": 4.55624646693047e-05,
+      "loss": 0.8708,
+      "step": 12300
+    },
+    {
+      "epoch": 0.7723068349939761,
+      "eval_loss": 0.8692737817764282,
+      "eval_runtime": 299.9274,
+      "eval_samples_per_second": 17.167,
+      "eval_steps_per_second": 2.147,
+      "step": 12300
+    },
+    {
+      "epoch": 0.7911435870669999,
+      "grad_norm": 0.40352341532707214,
+      "learning_rate": 4.18064191947742e-05,
+      "loss": 0.8724,
+      "step": 12600
+    },
+    {
+      "epoch": 0.7911435870669999,
+      "eval_loss": 0.8681650161743164,
+      "eval_runtime": 300.4231,
+      "eval_samples_per_second": 17.139,
+      "eval_steps_per_second": 2.144,
+      "step": 12600
+    },
+    {
+      "epoch": 0.8099803391400238,
+      "grad_norm": 0.36962220072746277,
+      "learning_rate": 3.8037811695245274e-05,
+      "loss": 0.8672,
+      "step": 12900
+    },
+    {
+      "epoch": 0.8099803391400238,
+      "eval_loss": 0.8672531247138977,
+      "eval_runtime": 299.8101,
+      "eval_samples_per_second": 17.174,
+      "eval_steps_per_second": 2.148,
+      "step": 12900
+    },
+    {
+      "epoch": 0.8288170912130476,
+      "grad_norm": 0.4042891561985016,
+      "learning_rate": 3.426920419571635e-05,
+      "loss": 0.8643,
+      "step": 13200
+    },
+    {
+      "epoch": 0.8288170912130476,
+      "eval_loss": 0.8664665818214417,
+      "eval_runtime": 299.8585,
+      "eval_samples_per_second": 17.171,
+      "eval_steps_per_second": 2.148,
+      "step": 13200
+    },
+    {
+      "epoch": 0.8476538432860714,
+      "grad_norm": 0.2992730140686035,
+      "learning_rate": 3.0500596696187428e-05,
+      "loss": 0.8632,
+      "step": 13500
+    },
+    {
+      "epoch": 0.8476538432860714,
+      "eval_loss": 0.8653113842010498,
+      "eval_runtime": 299.946,
+      "eval_samples_per_second": 17.166,
+      "eval_steps_per_second": 2.147,
+      "step": 13500
+    },
+    {
+      "epoch": 0.8664905953590952,
+      "grad_norm": 0.31725963950157166,
+      "learning_rate": 2.6731989196658503e-05,
+      "loss": 0.8564,
+      "step": 13800
+    },
+    {
+      "epoch": 0.8664905953590952,
+      "eval_loss": 0.8644812107086182,
+      "eval_runtime": 299.8536,
+      "eval_samples_per_second": 17.172,
+      "eval_steps_per_second": 2.148,
+      "step": 13800
+    },
+    {
+      "epoch": 0.885327347432119,
+      "grad_norm": 0.3101350963115692,
+      "learning_rate": 2.296338169712958e-05,
+      "loss": 0.861,
+      "step": 14100
+    },
+    {
+      "epoch": 0.885327347432119,
+      "eval_loss": 0.8637036085128784,
+      "eval_runtime": 300.356,
+      "eval_samples_per_second": 17.143,
+      "eval_steps_per_second": 2.144,
+      "step": 14100
+    },
+    {
+      "epoch": 0.9041640995051429,
+      "grad_norm": 0.33058223128318787,
+      "learning_rate": 1.9194774197600654e-05,
+      "loss": 0.8543,
+      "step": 14400
+    },
+    {
+      "epoch": 0.9041640995051429,
+      "eval_loss": 0.8630216121673584,
+      "eval_runtime": 299.9507,
+      "eval_samples_per_second": 17.166,
+      "eval_steps_per_second": 2.147,
+      "step": 14400
+    },
+    {
+      "epoch": 0.9230008515781666,
+      "grad_norm": 0.35784465074539185,
+      "learning_rate": 1.5438728723070158e-05,
+      "loss": 0.868,
+      "step": 14700
+    },
+    {
+      "epoch": 0.9230008515781666,
+      "eval_loss": 0.8623820543289185,
+      "eval_runtime": 299.933,
+      "eval_samples_per_second": 17.167,
+      "eval_steps_per_second": 2.147,
+      "step": 14700
+    },
+    {
+      "epoch": 0.9418376036511904,
+      "grad_norm": 0.3938862383365631,
+      "learning_rate": 1.1670121223541235e-05,
+      "loss": 0.8607,
+      "step": 15000
+    },
+    {
+      "epoch": 0.9418376036511904,
+      "eval_loss": 0.861863911151886,
+      "eval_runtime": 299.8746,
+      "eval_samples_per_second": 17.171,
+      "eval_steps_per_second": 2.148,
+      "step": 15000
+    },
+    {
+      "epoch": 0.9606743557242142,
+      "grad_norm": 0.3867338001728058,
+      "learning_rate": 7.90151372401231e-06,
+      "loss": 0.8491,
+      "step": 15300
+    },
+    {
+      "epoch": 0.9606743557242142,
+      "eval_loss": 0.8613755106925964,
+      "eval_runtime": 299.919,
+      "eval_samples_per_second": 17.168,
+      "eval_steps_per_second": 2.147,
+      "step": 15300
+    },
+    {
+      "epoch": 0.979511107797238,
+      "grad_norm": 0.3372841477394104,
+      "learning_rate": 4.132906224483387e-06,
+      "loss": 0.8643,
+      "step": 15600
+    },
+    {
+      "epoch": 0.979511107797238,
+      "eval_loss": 0.8610811829566956,
+      "eval_runtime": 299.8287,
+      "eval_samples_per_second": 17.173,
+      "eval_steps_per_second": 2.148,
+      "step": 15600
+    },
+    {
+      "epoch": 0.9983478598702619,
+      "grad_norm": 0.3431134819984436,
+      "learning_rate": 3.642987249544627e-07,
+      "loss": 0.8633,
+      "step": 15900
+    },
+    {
+      "epoch": 0.9983478598702619,
+      "eval_loss": 0.8609164953231812,
+      "eval_runtime": 299.9008,
+      "eval_samples_per_second": 17.169,
+      "eval_steps_per_second": 2.147,
+      "step": 15900
+    }
+  ],
+  "logging_steps": 300,
+  "max_steps": 15926,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.1684162719241994e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f203c239c4cec4ae0f20b8df027141ae6e9dc293c497c04f5b902ecf835d5f65
+size 5432