Upload folder using huggingface_hub

README.md

@@ -0,0 +1,164 @@
+---
+license: bigcode-openrail-m
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: bigcode/starcoder
+model-index:
+- name: lora-out
+ results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.3.0`
+```yaml
+base_model: bigcode/starcoder
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+is_llama_derived_model: false
+
+load_in_8bit: true
+load_in_4bit: false
+strict: false
+
+datasets:
+ - path: /workspace/axolotl-mdel/mathematica.txt
+ type: completion
+
+lora_modules_to_save:
+ - embed_tokens
+ - lm_head
+
+dataset_prepared_path:
+val_set_size: 0.05
+output_dir: ./lora-out
+
+sequence_len: 2048
+sample_packing: true
+pad_to_sequence_len: true
+
+adapter: lora
+lora_model_dir:
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+wandb_project: starcoder-mathematica
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 2
+micro_batch_size: 1
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16: false
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+s2_attention:
+
+warmup_steps: 10
+evals_per_epoch: 4
+eval_table_size:
+eval_table_max_new_tokens: 128
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+ pad_token: "[PAD]"
+ bos_token: "<s>"
+ eos_token: "</s>"
+ unk_token: "<unk>"
+
+```
+
+</details><br>
+
+# lora-out
+
+This model is a fine-tuned version of [bigcode/starcoder](https://huggingface.co/bigcode/starcoder) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.0968
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 2
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.8529 | 0.0 | 1 | 3.1576 |
+| 0.4365 | 0.25 | 127 | 3.1416 |
+| 2.953 | 0.5 | 254 | 3.1146 |
+| 0.35 | 0.75 | 381 | 3.0968 |
+
+
+### Framework versions
+
+- PEFT 0.7.0
+- Transformers 4.37.0.dev0
+- Pytorch 2.0.1+cu118
+- Datasets 2.16.1
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,30 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "bigcode/starcoder",
+ "bias": "none",
+ "fan_in_fan_out": null,
+ "inference_mode": true,
+ "init_lora_weights": true,
+ "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": [
+ "embed_tokens",
+ "lm_head"
+ ],
+ "peft_type": "LORA",
+ "r": 32,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "c_proj",
+ "c_fc",
+ "c_attn"
+ ],
+ "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fdd5d4e5abc47b7801925fa4319a27dafffe3e26c99c08dec6388e846d06382
+size 1045856081

added_tokens.json

@@ -0,0 +1,6 @@
+{
+ "</s>": 49154,
+ "<s>": 49153,
+ "<unk>": 49155,
+ "[PAD]": 49152
+}

checkpoint-492/README.md

@@ -0,0 +1,218 @@
+---
+library_name: peft
+base_model: bigcode/starcoder
+---
+
+# 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]
+
+
+## Training procedure
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+### Framework versions
+
+- PEFT 0.7.0

checkpoint-492/adapter_config.json

@@ -0,0 +1,30 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "bigcode/starcoder",
+ "bias": "none",
+ "fan_in_fan_out": null,
+ "inference_mode": true,
+ "init_lora_weights": true,
+ "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": [
+ "embed_tokens",
+ "lm_head"
+ ],
+ "peft_type": "LORA",
+ "r": 32,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "c_proj",
+ "c_fc",
+ "c_attn"
+ ],
+ "task_type": "CAUSAL_LM"
+}

checkpoint-492/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7313054df98f87bd9be10494c1b522b160a13ba59900885414bc4904fca0099
+size 1045783792

checkpoint-492/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:999968e8507c4b291fb95454907a11256d5d7a19cd2a0e8ff6f63b25718551bf
+size 826871587

checkpoint-492/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed2751b99f5cff795e81a257377695a49576d09777ea32cc6b0169b19e658d9b
+size 14575

checkpoint-492/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a235c7e05aad6920288b6dca5aed5dcfbfbee009cf9d05cf53f56475bacc1288
+size 627

checkpoint-492/trainer_state.json

@@ -0,0 +1,3005 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 0.9713721618953604,
+ "eval_steps": 127,
+ "global_step": 492,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.0,
+ "learning_rate": 2e-05,
+ "loss": 2.8529,
+ "step": 1
+ },
+ {
+ "epoch": 0.0,
+ "eval_loss": 3.1576027870178223,
+ "eval_runtime": 37.0517,
+ "eval_samples_per_second": 1.403,
+ "eval_steps_per_second": 1.403,
+ "step": 1
+ },
+ {
+ "epoch": 0.0,
+ "learning_rate": 4e-05,
+ "loss": 0.7839,
+ "step": 2
+ },
+ {
+ "epoch": 0.01,
+ "learning_rate": 6e-05,
+ "loss": 0.5453,
+ "step": 3
+ },
+ {
+ "epoch": 0.01,
+ "learning_rate": 8e-05,
+ "loss": 0.0492,
+ "step": 4
+ },
+ {
+ "epoch": 0.01,
+ "learning_rate": 0.0001,
+ "loss": 0.766,
+ "step": 5
+ },
+ {
+ "epoch": 0.01,
+ "learning_rate": 0.00012,
+ "loss": 0.8575,
+ "step": 6
+ },
+ {
+ "epoch": 0.01,
+ "learning_rate": 0.00014,
+ "loss": 0.5194,
+ "step": 7
+ },
+ {
+ "epoch": 0.02,
+ "learning_rate": 0.00016,
+ "loss": 0.2592,
+ "step": 8
+ },
+ {
+ "epoch": 0.02,
+ "learning_rate": 0.00018,
+ "loss": 2.9974,
+ "step": 9
+ },
+ {
+ "epoch": 0.02,
+ "learning_rate": 0.0002,
+ "loss": 0.1871,
+ "step": 10
+ },
+ {
+ "epoch": 0.02,
+ "learning_rate": 0.00019999799412001546,
+ "loss": 0.213,
+ "step": 11
+ },
+ {
+ "epoch": 0.02,
+ "learning_rate": 0.00019999197656053288,
+ "loss": 0.7832,
+ "step": 12
+ },
+ {
+ "epoch": 0.03,
+ "learning_rate": 0.0001999819475629623,
+ "loss": 2.6674,
+ "step": 13
+ },
+ {
+ "epoch": 0.03,
+ "learning_rate": 0.00019996790752964305,
+ "loss": 0.1479,
+ "step": 14
+ },
+ {
+ "epoch": 0.03,
+ "learning_rate": 0.00019994985702382758,
+ "loss": 0.1546,
+ "step": 15
+ },
+ {
+ "epoch": 0.03,
+ "learning_rate": 0.00019992779676965885,
+ "loss": 3.1039,
+ "step": 16
+ },
+ {
+ "epoch": 0.03,
+ "learning_rate": 0.00019990172765214128,
+ "loss": 2.2049,
+ "step": 17
+ },
+ {
+ "epoch": 0.04,
+ "learning_rate": 0.00019987165071710527,
+ "loss": 3.6854,
+ "step": 18
+ },
+ {
+ "epoch": 0.04,
+ "learning_rate": 0.00019983756717116536,
+ "loss": 0.1398,
+ "step": 19
+ },
+ {
+ "epoch": 0.04,
+ "learning_rate": 0.0001997994783816715,
+ "loss": 0.3254,
+ "step": 20
+ },
+ {
+ "epoch": 0.04,
+ "learning_rate": 0.00019975738587665456,
+ "loss": 0.6154,
+ "step": 21
+ },
+ {
+ "epoch": 0.04,
+ "learning_rate": 0.00019971129134476473,
+ "loss": 0.8228,
+ "step": 22
+ },
+ {
+ "epoch": 0.05,
+ "learning_rate": 0.00019966119663520412,
+ "loss": 0.3039,
+ "step": 23
+ },
+ {
+ "epoch": 0.05,
+ "learning_rate": 0.0001996071037576521,
+ "loss": 1.0781,
+ "step": 24
+ },
+ {
+ "epoch": 0.05,
+ "learning_rate": 0.00019954901488218515,
+ "loss": 0.6851,
+ "step": 25
+ },
+ {
+ "epoch": 0.05,
+ "learning_rate": 0.00019948693233918952,
+ "loss": 0.6144,
+ "step": 26
+ },
+ {
+ "epoch": 0.05,
+ "learning_rate": 0.0001994208586192678,
+ "loss": 0.8485,
+ "step": 27
+ },
+ {
+ "epoch": 0.06,
+ "learning_rate": 0.00019935079637313906,
+ "loss": 0.6133,
+ "step": 28
+ },
+ {
+ "epoch": 0.06,
+ "learning_rate": 0.00019927674841153237,
+ "loss": 2.9564,
+ "step": 29
+ },
+ {
+ "epoch": 0.06,
+ "learning_rate": 0.0001991987177050743,
+ "loss": 1.506,
+ "step": 30
+ },
+ {
+ "epoch": 0.06,
+ "learning_rate": 0.00019911670738416947,
+ "loss": 0.168,
+ "step": 31
+ },
+ {
+ "epoch": 0.06,
+ "learning_rate": 0.00019903072073887507,
+ "loss": 0.7176,
+ "step": 32
+ },
+ {
+ "epoch": 0.07,
+ "learning_rate": 0.000198940761218769,
+ "loss": 0.4638,
+ "step": 33
+ },
+ {
+ "epoch": 0.07,
+ "learning_rate": 0.00019884683243281116,
+ "loss": 0.7248,
+ "step": 34
+ },
+ {
+ "epoch": 0.07,
+ "learning_rate": 0.00019874893814919906,
+ "loss": 0.3349,
+ "step": 35
+ },
+ {
+ "epoch": 0.07,
+ "learning_rate": 0.00019864708229521636,
+ "loss": 0.3917,
+ "step": 36
+ },
+ {
+ "epoch": 0.07,
+ "learning_rate": 0.0001985412689570754,
+ "loss": 1.2308,
+ "step": 37
+ },
+ {
+ "epoch": 0.08,
+ "learning_rate": 0.00019843150237975344,
+ "loss": 0.9945,
+ "step": 38
+ },
+ {
+ "epoch": 0.08,
+ "learning_rate": 0.00019831778696682194,
+ "loss": 1.3547,
+ "step": 39
+ },
+ {
+ "epoch": 0.08,
+ "learning_rate": 0.00019820012728027044,
+ "loss": 0.9227,
+ "step": 40
+ },
+ {
+ "epoch": 0.08,
+ "learning_rate": 0.00019807852804032305,
+ "loss": 1.0954,
+ "step": 41
+ },
+ {
+ "epoch": 0.08,
+ "learning_rate": 0.00019795299412524945,
+ "loss": 0.6762,
+ "step": 42
+ },
+ {
+ "epoch": 0.08,
+ "learning_rate": 0.000197823530571169,
+ "loss": 1.3553,
+ "step": 43
+ },
+ {
+ "epoch": 0.09,
+ "learning_rate": 0.0001976901425718487,
+ "loss": 0.3896,
+ "step": 44
+ },
+ {
+ "epoch": 0.09,
+ "learning_rate": 0.00019755283547849494,
+ "loss": 0.3207,
+ "step": 45
+ },
+ {
+ "epoch": 0.09,
+ "learning_rate": 0.0001974116147995387,
+ "loss": 3.249,
+ "step": 46
+ },
+ {
+ "epoch": 0.09,
+ "learning_rate": 0.00019726648620041468,
+ "loss": 0.9758,
+ "step": 47
+ },
+ {
+ "epoch": 0.09,
+ "learning_rate": 0.0001971174555033339,
+ "loss": 0.5544,
+ "step": 48
+ },
+ {
+ "epoch": 0.1,
+ "learning_rate": 0.00019696452868705024,
+ "loss": 0.332,
+ "step": 49
+ },
+ {
+ "epoch": 0.1,
+ "learning_rate": 0.00019680771188662044,
+ "loss": 0.6672,
+ "step": 50
+ },
+ {
+ "epoch": 0.1,
+ "learning_rate": 0.0001966470113931582,
+ "loss": 0.7634,
+ "step": 51
+ },
+ {
+ "epoch": 0.1,
+ "learning_rate": 0.00019648243365358146,
+ "loss": 0.5081,
+ "step": 52
+ },
+ {
+ "epoch": 0.1,
+ "learning_rate": 0.00019631398527035422,
+ "loss": 0.7995,
+ "step": 53
+ },
+ {
+ "epoch": 0.11,
+ "learning_rate": 0.00019614167300122126,
+ "loss": 1.1439,
+ "step": 54
+ },
+ {
+ "epoch": 0.11,
+ "learning_rate": 0.0001959655037589372,
+ "loss": 0.4855,
+ "step": 55
+ },
+ {
+ "epoch": 0.11,
+ "learning_rate": 0.00019578548461098914,
+ "loss": 5.2893,
+ "step": 56
+ },
+ {
+ "epoch": 0.11,
+ "learning_rate": 0.00019560162277931325,
+ "loss": 0.1765,
+ "step": 57
+ },
+ {
+ "epoch": 0.11,
+ "learning_rate": 0.00019541392564000488,
+ "loss": 0.4805,
+ "step": 58
+ },
+ {
+ "epoch": 0.12,
+ "learning_rate": 0.00019522240072302274,
+ "loss": 1.668,
+ "step": 59
+ },
+ {
+ "epoch": 0.12,
+ "learning_rate": 0.00019502705571188672,
+ "loss": 0.1239,
+ "step": 60
+ },
+ {
+ "epoch": 0.12,
+ "learning_rate": 0.0001948278984433699,
+ "loss": 3.1256,
+ "step": 61
+ },
+ {
+ "epoch": 0.12,
+ "learning_rate": 0.0001946249369071837,
+ "loss": 0.2337,
+ "step": 62
+ },
+ {
+ "epoch": 0.12,
+ "learning_rate": 0.00019441817924565786,
+ "loss": 0.1279,
+ "step": 63
+ },
+ {
+ "epoch": 0.13,
+ "learning_rate": 0.0001942076337534135,
+ "loss": 3.1412,
+ "step": 64
+ },
+ {
+ "epoch": 0.13,
+ "learning_rate": 0.00019399330887703037,
+ "loss": 0.4809,
+ "step": 65
+ },
+ {
+ "epoch": 0.13,
+ "learning_rate": 0.00019377521321470805,
+ "loss": 0.5192,
+ "step": 66
+ },
+ {
+ "epoch": 0.13,
+ "learning_rate": 0.00019355335551592105,
+ "loss": 0.5328,
+ "step": 67
+ },
+ {
+ "epoch": 0.13,
+ "learning_rate": 0.00019332774468106768,
+ "loss": 0.1569,
+ "step": 68
+ },
+ {
+ "epoch": 0.14,
+ "learning_rate": 0.00019309838976111311,
+ "loss": 3.1561,
+ "step": 69
+ },
+ {
+ "epoch": 0.14,
+ "learning_rate": 0.00019286529995722623,
+ "loss": 4.205,
+ "step": 70
+ },
+ {
+ "epoch": 0.14,
+ "learning_rate": 0.00019262848462041045,
+ "loss": 0.0668,
+ "step": 71
+ },
+ {
+ "epoch": 0.14,
+ "learning_rate": 0.0001923879532511287,
+ "loss": 0.4921,
+ "step": 72
+ },
+ {
+ "epoch": 0.14,
+ "learning_rate": 0.0001921437154989221,
+ "loss": 3.1048,
+ "step": 73
+ },
+ {
+ "epoch": 0.15,
+ "learning_rate": 0.00019189578116202307,
+ "loss": 0.2369,
+ "step": 74
+ },
+ {
+ "epoch": 0.15,
+ "learning_rate": 0.00019164416018696207,
+ "loss": 0.7976,
+ "step": 75
+ },
+ {
+ "epoch": 0.15,
+ "learning_rate": 0.00019138886266816866,
+ "loss": 0.4052,
+ "step": 76
+ },
+ {
+ "epoch": 0.15,
+ "learning_rate": 0.00019112989884756653,
+ "loss": 0.3292,
+ "step": 77
+ },
+ {
+ "epoch": 0.15,
+ "learning_rate": 0.0001908672791141625,
+ "loss": 0.4974,
+ "step": 78
+ },
+ {
+ "epoch": 0.16,
+ "learning_rate": 0.00019060101400362998,
+ "loss": 0.1235,
+ "step": 79
+ },
+ {
+ "epoch": 0.16,
+ "learning_rate": 0.00019033111419788597,
+ "loss": 1.8426,
+ "step": 80
+ },
+ {
+ "epoch": 0.16,
+ "learning_rate": 0.000190057590524663,
+ "loss": 1.1387,
+ "step": 81
+ },
+ {
+ "epoch": 0.16,
+ "learning_rate": 0.00018978045395707418,
+ "loss": 0.1255,
+ "step": 82
+ },
+ {
+ "epoch": 0.16,
+ "learning_rate": 0.0001894997156131734,
+ "loss": 0.3632,
+ "step": 83
+ },
+ {
+ "epoch": 0.17,
+ "learning_rate": 0.0001892153867555092,
+ "loss": 0.5894,
+ "step": 84
+ },
+ {
+ "epoch": 0.17,
+ "learning_rate": 0.00018892747879067286,
+ "loss": 0.9053,
+ "step": 85
+ },
+ {
+ "epoch": 0.17,
+ "learning_rate": 0.00018863600326884082,
+ "loss": 0.6213,
+ "step": 86
+ },
+ {
+ "epoch": 0.17,
+ "learning_rate": 0.00018834097188331143,
+ "loss": 0.4491,
+ "step": 87
+ },
+ {
+ "epoch": 0.17,
+ "learning_rate": 0.00018804239647003573,
+ "loss": 0.3181,
+ "step": 88
+ },
+ {
+ "epoch": 0.18,
+ "learning_rate": 0.00018774028900714256,
+ "loss": 0.6545,
+ "step": 89
+ },
+ {
+ "epoch": 0.18,
+ "learning_rate": 0.00018743466161445823,
+ "loss": 0.4294,
+ "step": 90
+ },
+ {
+ "epoch": 0.18,
+ "learning_rate": 0.0001871255265530201,
+ "loss": 2.9904,
+ "step": 91
+ },
+ {
+ "epoch": 0.18,
+ "learning_rate": 0.00018681289622458485,
+ "loss": 0.6953,
+ "step": 92
+ },
+ {
+ "epoch": 0.18,
+ "learning_rate": 0.00018649678317113084,
+ "loss": 3.2506,
+ "step": 93
+ },
+ {
+ "epoch": 0.19,
+ "learning_rate": 0.00018617720007435497,
+ "loss": 0.7977,
+ "step": 94
+ },
+ {
+ "epoch": 0.19,
+ "learning_rate": 0.000185854159755164,
+ "loss": 2.8863,
+ "step": 95
+ },
+ {
+ "epoch": 0.19,
+ "learning_rate": 0.00018552767517316022,
+ "loss": 0.6639,
+ "step": 96
+ },
+ {
+ "epoch": 0.19,
+ "learning_rate": 0.00018519775942612128,
+ "loss": 0.3403,
+ "step": 97
+ },
+ {
+ "epoch": 0.19,
+ "learning_rate": 0.00018486442574947511,
+ "loss": 0.084,
+ "step": 98
+ },
+ {
+ "epoch": 0.2,
+ "learning_rate": 0.0001845276875157687,
+ "loss": 0.8301,
+ "step": 99
+ },
+ {
+ "epoch": 0.2,
+ "learning_rate": 0.0001841875582341317,
+ "loss": 0.3861,
+ "step": 100
+ },
+ {
+ "epoch": 0.2,
+ "learning_rate": 0.0001838440515497345,
+ "loss": 0.9388,
+ "step": 101
+ },
+ {
+ "epoch": 0.2,
+ "learning_rate": 0.00018349718124324076,
+ "loss": 0.4805,
+ "step": 102
+ },
+ {
+ "epoch": 0.2,
+ "learning_rate": 0.00018314696123025454,
+ "loss": 0.9507,
+ "step": 103
+ },
+ {
+ "epoch": 0.21,
+ "learning_rate": 0.00018279340556076216,
+ "loss": 0.9377,
+ "step": 104
+ },
+ {
+ "epoch": 0.21,
+ "learning_rate": 0.0001824365284185684,
+ "loss": 3.8316,
+ "step": 105
+ },
+ {
+ "epoch": 0.21,
+ "learning_rate": 0.00018207634412072764,
+ "loss": 2.9745,
+ "step": 106
+ },
+ {
+ "epoch": 0.21,
+ "learning_rate": 0.00018171286711696934,
+ "loss": 1.9168,
+ "step": 107
+ },
+ {
+ "epoch": 0.21,
+ "learning_rate": 0.0001813461119891184,
+ "loss": 0.9356,
+ "step": 108
+ },
+ {
+ "epoch": 0.22,
+ "learning_rate": 0.00018097609345051025,
+ "loss": 5.7176,
+ "step": 109
+ },
+ {
+ "epoch": 0.22,
+ "learning_rate": 0.00018060282634540053,
+ "loss": 1.141,
+ "step": 110
+ },
+ {
+ "epoch": 0.22,
+ "learning_rate": 0.00018022632564836948,
+ "loss": 0.2181,
+ "step": 111
+ },
+ {
+ "epoch": 0.22,
+ "learning_rate": 0.0001798466064637214,
+ "loss": 0.8319,
+ "step": 112
+ },
+ {
+ "epoch": 0.22,
+ "learning_rate": 0.00017946368402487845,
+ "loss": 0.6727,
+ "step": 113
+ },
+ {
+ "epoch": 0.23,
+ "learning_rate": 0.00017907757369376985,
+ "loss": 1.0776,
+ "step": 114
+ },
+ {
+ "epoch": 0.23,
+ "learning_rate": 0.00017868829096021527,
+ "loss": 0.5182,
+ "step": 115
+ },
+ {
+ "epoch": 0.23,
+ "learning_rate": 0.00017829585144130356,
+ "loss": 0.7924,
+ "step": 116
+ },
+ {
+ "epoch": 0.23,
+ "learning_rate": 0.0001779002708807662,
+ "loss": 0.4007,
+ "step": 117
+ },
+ {
+ "epoch": 0.23,
+ "learning_rate": 0.0001775015651483459,
+ "loss": 0.2954,
+ "step": 118
+ },
+ {
+ "epoch": 0.23,
+ "learning_rate": 0.00017709975023915949,
+ "loss": 1.4825,
+ "step": 119
+ },
+ {
+ "epoch": 0.24,
+ "learning_rate": 0.0001766948422730567,
+ "loss": 0.8667,
+ "step": 120
+ },
+ {
+ "epoch": 0.24,
+ "learning_rate": 0.0001762868574939732,
+ "loss": 0.0204,
+ "step": 121
+ },
+ {
+ "epoch": 0.24,
+ "learning_rate": 0.0001758758122692791,
+ "loss": 0.0491,
+ "step": 122
+ },
+ {
+ "epoch": 0.24,
+ "learning_rate": 0.00017546172308912213,
+ "loss": 3.2544,
+ "step": 123
+ },
+ {
+ "epoch": 0.24,
+ "learning_rate": 0.00017504460656576627,
+ "loss": 0.7571,
+ "step": 124
+ },
+ {
+ "epoch": 0.25,
+ "learning_rate": 0.0001746244794329252,
+ "loss": 3.2652,
+ "step": 125
+ },
+ {
+ "epoch": 0.25,
+ "learning_rate": 0.0001742013585450911,
+ "loss": 0.565,
+ "step": 126
+ },
+ {
+ "epoch": 0.25,
+ "learning_rate": 0.00017377526087685832,
+ "loss": 0.4365,
+ "step": 127
+ },
+ {
+ "epoch": 0.25,
+ "eval_loss": 3.1416423320770264,
+ "eval_runtime": 38.7051,
+ "eval_samples_per_second": 1.343,
+ "eval_steps_per_second": 1.343,
+ "step": 127
+ },
+ {
+ "epoch": 0.25,
+ "learning_rate": 0.0001733462035222426,
+ "loss": 3.5766,
+ "step": 128
+ },
+ {
+ "epoch": 0.25,
+ "learning_rate": 0.0001729142036939951,
+ "loss": 0.2136,
+ "step": 129
+ },
+ {
+ "epoch": 0.26,
+ "learning_rate": 0.000172479278722912,
+ "loss": 0.8068,
+ "step": 130
+ },
+ {
+ "epoch": 0.26,
+ "learning_rate": 0.0001720414460571392,
+ "loss": 0.3899,
+ "step": 131
+ },
+ {
+ "epoch": 0.26,
+ "learning_rate": 0.0001716007232614723,
+ "loss": 0.5877,
+ "step": 132
+ },
+ {
+ "epoch": 0.26,
+ "learning_rate": 0.000171157128016652,
+ "loss": 0.1575,
+ "step": 133
+ },
+ {
+ "epoch": 0.26,
+ "learning_rate": 0.00017071067811865476,
+ "loss": 3.0165,
+ "step": 134
+ },
+ {
+ "epoch": 0.27,
+ "learning_rate": 0.0001702613914779789,
+ "loss": 3.3047,
+ "step": 135
+ },
+ {
+ "epoch": 0.27,
+ "learning_rate": 0.0001698092861189259,
+ "loss": 0.4127,
+ "step": 136
+ },
+ {
+ "epoch": 0.27,
+ "learning_rate": 0.00016935438017887772,
+ "loss": 0.7031,
+ "step": 137
+ },
+ {
+ "epoch": 0.27,
+ "learning_rate": 0.00016889669190756868,
+ "loss": 2.9221,
+ "step": 138
+ },
+ {
+ "epoch": 0.27,
+ "learning_rate": 0.00016843623966635366,
+ "loss": 0.1674,
+ "step": 139
+ },
+ {
+ "epoch": 0.28,
+ "learning_rate": 0.0001679730419274713,
+ "loss": 0.4934,
+ "step": 140
+ },
+ {
+ "epoch": 0.28,
+ "learning_rate": 0.0001675071172733031,
+ "loss": 0.6168,
+ "step": 141
+ },
+ {
+ "epoch": 0.28,
+ "learning_rate": 0.00016703848439562785,
+ "loss": 0.3576,
+ "step": 142
+ },
+ {
+ "epoch": 0.28,
+ "learning_rate": 0.00016656716209487174,
+ "loss": 0.5786,
+ "step": 143
+ },
+ {
+ "epoch": 0.28,
+ "learning_rate": 0.0001660931692793541,
+ "loss": 1.2878,
+ "step": 144
+ },
+ {
+ "epoch": 0.29,
+ "learning_rate": 0.000165616524964529,
+ "loss": 0.4301,
+ "step": 145
+ },
+ {
+ "epoch": 0.29,
+ "learning_rate": 0.00016513724827222227,
+ "loss": 0.3353,
+ "step": 146
+ },
+ {
+ "epoch": 0.29,
+ "learning_rate": 0.00016465535842986434,
+ "loss": 0.9216,
+ "step": 147
+ },
+ {
+ "epoch": 0.29,
+ "learning_rate": 0.000164170874769719,
+ "loss": 0.4037,
+ "step": 148
+ },
+ {
+ "epoch": 0.29,
+ "learning_rate": 0.00016368381672810786,
+ "loss": 3.7759,
+ "step": 149
+ },
+ {
+ "epoch": 0.3,
+ "learning_rate": 0.0001631942038446304,
+ "loss": 0.3816,
+ "step": 150
+ },
+ {
+ "epoch": 0.3,
+ "learning_rate": 0.00016270205576138032,
+ "loss": 0.167,
+ "step": 151
+ },
+ {
+ "epoch": 0.3,
+ "learning_rate": 0.00016220739222215738,
+ "loss": 2.676,
+ "step": 152
+ },
+ {
+ "epoch": 0.3,
+ "learning_rate": 0.00016171023307167545,
+ "loss": 0.0795,
+ "step": 153
+ },
+ {
+ "epoch": 0.3,
+ "learning_rate": 0.0001612105982547663,
+ "loss": 0.1744,
+ "step": 154
+ },
+ {
+ "epoch": 0.31,
+ "learning_rate": 0.00016070850781557948,
+ "loss": 0.4056,
+ "step": 155
+ },
+ {
+ "epoch": 0.31,
+ "learning_rate": 0.0001602039818967783,
+ "loss": 0.7392,
+ "step": 156
+ },
+ {
+ "epoch": 0.31,
+ "learning_rate": 0.00015969704073873157,
+ "loss": 5.6689,
+ "step": 157
+ },
+ {
+ "epoch": 0.31,
+ "learning_rate": 0.0001591877046787017,
+ "loss": 0.7629,
+ "step": 158
+ },
+ {
+ "epoch": 0.31,
+ "learning_rate": 0.00015867599415002895,
+ "loss": 0.069,
+ "step": 159
+ },
+ {
+ "epoch": 0.32,
+ "learning_rate": 0.00015816192968131138,
+ "loss": 2.9564,
+ "step": 160
+ },
+ {
+ "epoch": 0.32,
+ "learning_rate": 0.0001576455318955816,
+ "loss": 0.3949,
+ "step": 161
+ },
+ {
+ "epoch": 0.32,
+ "learning_rate": 0.00015712682150947923,
+ "loss": 0.4876,
+ "step": 162
+ },
+ {
+ "epoch": 0.32,
+ "learning_rate": 0.00015660581933241993,
+ "loss": 0.9095,
+ "step": 163
+ },
+ {
+ "epoch": 0.32,
+ "learning_rate": 0.00015608254626576048,
+ "loss": 0.1195,
+ "step": 164
+ },
+ {
+ "epoch": 0.33,
+ "learning_rate": 0.00015555702330196023,
+ "loss": 0.182,
+ "step": 165
+ },
+ {
+ "epoch": 0.33,
+ "learning_rate": 0.00015502927152373914,
+ "loss": 0.3554,
+ "step": 166
+ },
+ {
+ "epoch": 0.33,
+ "learning_rate": 0.0001544993121032318,
+ "loss": 0.5072,
+ "step": 167
+ },
+ {
+ "epoch": 0.33,
+ "learning_rate": 0.000153967166301138,
+ "loss": 0.7807,
+ "step": 168
+ },
+ {
+ "epoch": 0.33,
+ "learning_rate": 0.00015343285546587013,
+ "loss": 0.1042,
+ "step": 169
+ },
+ {
+ "epoch": 0.34,
+ "learning_rate": 0.00015289640103269625,
+ "loss": 0.3438,
+ "step": 170
+ },
+ {
+ "epoch": 0.34,
+ "learning_rate": 0.00015235782452288068,
+ "loss": 0.3308,
+ "step": 171
+ },
+ {
+ "epoch": 0.34,
+ "learning_rate": 0.0001518171475428202,
+ "loss": 0.5366,
+ "step": 172
+ },
+ {
+ "epoch": 0.34,
+ "learning_rate": 0.00015127439178317745,
+ "loss": 0.509,
+ "step": 173
+ },
+ {
+ "epoch": 0.34,
+ "learning_rate": 0.00015072957901801076,
+ "loss": 0.4237,
+ "step": 174
+ },
+ {
+ "epoch": 0.35,
+ "learning_rate": 0.0001501827311039005,
+ "loss": 0.2678,
+ "step": 175
+ },
+ {
+ "epoch": 0.35,
+ "learning_rate": 0.0001496338699790724,
+ "loss": 0.5321,
+ "step": 176
+ },
+ {
+ "epoch": 0.35,
+ "learning_rate": 0.00014908301766251739,
+ "loss": 0.1806,
+ "step": 177
+ },
+ {
+ "epoch": 0.35,
+ "learning_rate": 0.00014853019625310813,
+ "loss": 0.469,
+ "step": 178
+ },
+ {
+ "epoch": 0.35,
+ "learning_rate": 0.00014797542792871265,
+ "loss": 0.4509,
+ "step": 179
+ },
+ {
+ "epoch": 0.36,
+ "learning_rate": 0.0001474187349453045,
+ "loss": 0.4466,
+ "step": 180
+ },
+ {
+ "epoch": 0.36,
+ "learning_rate": 0.00014686013963607,
+ "loss": 0.9026,
+ "step": 181
+ },
+ {
+ "epoch": 0.36,
+ "learning_rate": 0.00014629966441051208,
+ "loss": 0.6483,
+ "step": 182
+ },
+ {
+ "epoch": 0.36,
+ "learning_rate": 0.0001457373317535515,
+ "loss": 0.1891,
+ "step": 183
+ },
+ {
+ "epoch": 0.36,
+ "learning_rate": 0.0001451731642246247,
+ "loss": 2.834,
+ "step": 184
+ },
+ {
+ "epoch": 0.37,
+ "learning_rate": 0.00014460718445677876,
+ "loss": 0.3445,
+ "step": 185
+ },
+ {
+ "epoch": 0.37,
+ "learning_rate": 0.00014403941515576344,
+ "loss": 0.3603,
+ "step": 186
+ },
+ {
+ "epoch": 0.37,
+ "learning_rate": 0.00014346987909912023,
+ "loss": 0.388,
+ "step": 187
+ },
+ {
+ "epoch": 0.37,
+ "learning_rate": 0.00014289859913526874,
+ "loss": 0.4124,
+ "step": 188
+ },
+ {
+ "epoch": 0.37,
+ "learning_rate": 0.00014232559818258984,
+ "loss": 1.4459,
+ "step": 189
+ },
+ {
+ "epoch": 0.38,
+ "learning_rate": 0.00014175089922850633,
+ "loss": 0.1114,
+ "step": 190
+ },
+ {
+ "epoch": 0.38,
+ "learning_rate": 0.00014117452532856083,
+ "loss": 3.2592,
+ "step": 191
+ },
+ {
+ "epoch": 0.38,
+ "learning_rate": 0.0001405964996054907,
+ "loss": 0.4387,
+ "step": 192
+ },
+ {
+ "epoch": 0.38,
+ "learning_rate": 0.00014001684524830057,
+ "loss": 3.0681,
+ "step": 193
+ },
+ {
+ "epoch": 0.38,
+ "learning_rate": 0.00013943558551133186,
+ "loss": 2.8873,
+ "step": 194
+ },
+ {
+ "epoch": 0.38,
+ "learning_rate": 0.00013885274371333,
+ "loss": 0.0514,
+ "step": 195
+ },
+ {
+ "epoch": 0.39,
+ "learning_rate": 0.000138268343236509,
+ "loss": 0.2656,
+ "step": 196
+ },
+ {
+ "epoch": 0.39,
+ "learning_rate": 0.00013768240752561314,
+ "loss": 0.5523,
+ "step": 197
+ },
+ {
+ "epoch": 0.39,
+ "learning_rate": 0.0001370949600869768,
+ "loss": 0.3376,
+ "step": 198
+ },
+ {
+ "epoch": 0.39,
+ "learning_rate": 0.00013650602448758112,
+ "loss": 0.397,
+ "step": 199
+ },
+ {
+ "epoch": 0.39,
+ "learning_rate": 0.0001359156243541087,
+ "loss": 0.306,
+ "step": 200
+ },
+ {
+ "epoch": 0.4,
+ "learning_rate": 0.00013532378337199582,
+ "loss": 0.3834,
+ "step": 201
+ },
+ {
+ "epoch": 0.4,
+ "learning_rate": 0.00013473052528448201,
+ "loss": 0.351,
+ "step": 202
+ },
+ {
+ "epoch": 0.4,
+ "learning_rate": 0.00013413587389165784,
+ "loss": 0.3581,
+ "step": 203
+ },
+ {
+ "epoch": 0.4,
+ "learning_rate": 0.00013353985304950973,
+ "loss": 0.3167,
+ "step": 204
+ },
+ {
+ "epoch": 0.4,
+ "learning_rate": 0.00013294248666896328,
+ "loss": 1.2743,
+ "step": 205
+ },
+ {
+ "epoch": 0.41,
+ "learning_rate": 0.0001323437987149238,
+ "loss": 1.1231,
+ "step": 206
+ },
+ {
+ "epoch": 0.41,
+ "learning_rate": 0.00013174381320531505,
+ "loss": 0.2232,
+ "step": 207
+ },
+ {
+ "epoch": 0.41,
+ "learning_rate": 0.0001311425542101154,
+ "loss": 0.2116,
+ "step": 208
+ },
+ {
+ "epoch": 0.41,
+ "learning_rate": 0.00013054004585039258,
+ "loss": 3.3701,
+ "step": 209
+ },
+ {
+ "epoch": 0.41,
+ "learning_rate": 0.00012993631229733582,
+ "loss": 0.1044,
+ "step": 210
+ },
+ {
+ "epoch": 0.42,
+ "learning_rate": 0.00012933137777128607,
+ "loss": 0.8717,
+ "step": 211
+ },
+ {
+ "epoch": 0.42,
+ "learning_rate": 0.0001287252665407645,
+ "loss": 0.1707,
+ "step": 212
+ },
+ {
+ "epoch": 0.42,
+ "learning_rate": 0.0001281180029214988,
+ "loss": 0.3714,
+ "step": 213
+ },
+ {
+ "epoch": 0.42,
+ "learning_rate": 0.0001275096112754478,
+ "loss": 0.5697,
+ "step": 214
+ },
+ {
+ "epoch": 0.42,
+ "learning_rate": 0.000126900116009824,
+ "loss": 0.8001,
+ "step": 215
+ },
+ {
+ "epoch": 0.43,
+ "learning_rate": 0.0001262895415761145,
+ "loss": 0.8647,
+ "step": 216
+ },
+ {
+ "epoch": 0.43,
+ "learning_rate": 0.00012567791246909994,
+ "loss": 0.31,
+ "step": 217
+ },
+ {
+ "epoch": 0.43,
+ "learning_rate": 0.00012506525322587207,
+ "loss": 2.5493,
+ "step": 218
+ },
+ {
+ "epoch": 0.43,
+ "learning_rate": 0.0001244515884248491,
+ "loss": 3.1865,
+ "step": 219
+ },
+ {
+ "epoch": 0.43,
+ "learning_rate": 0.00012383694268478993,
+ "loss": 2.7346,
+ "step": 220
+ },
+ {
+ "epoch": 0.44,
+ "learning_rate": 0.0001232213406638062,
+ "loss": 2.9121,
+ "step": 221
+ },
+ {
+ "epoch": 0.44,
+ "learning_rate": 0.0001226048070583735,
+ "loss": 3.3936,
+ "step": 222
+ },
+ {
+ "epoch": 0.44,
+ "learning_rate": 0.00012198736660234009,
+ "loss": 0.7656,
+ "step": 223
+ },
+ {
+ "epoch": 0.44,
+ "learning_rate": 0.00012136904406593507,
+ "loss": 0.2102,
+ "step": 224
+ },
+ {
+ "epoch": 0.44,
+ "learning_rate": 0.00012074986425477445,
+ "loss": 0.0982,
+ "step": 225
+ },
+ {
+ "epoch": 0.45,
+ "learning_rate": 0.00012012985200886602,
+ "loss": 0.5801,
+ "step": 226
+ },
+ {
+ "epoch": 0.45,
+ "learning_rate": 0.00011950903220161285,
+ "loss": 0.1236,
+ "step": 227
+ },
+ {
+ "epoch": 0.45,
+ "learning_rate": 0.00011888742973881543,
+ "loss": 1.401,
+ "step": 228
+ },
+ {
+ "epoch": 0.45,
+ "learning_rate": 0.00011826506955767258,
+ "loss": 0.5149,
+ "step": 229
+ },
+ {
+ "epoch": 0.45,
+ "learning_rate": 0.00011764197662578086,
+ "loss": 0.6567,
+ "step": 230
+ },
+ {
+ "epoch": 0.46,
+ "learning_rate": 0.00011701817594013312,
+ "loss": 0.1937,
+ "step": 231
+ },
+ {
+ "epoch": 0.46,
+ "learning_rate": 0.00011639369252611552,
+ "loss": 0.1336,
+ "step": 232
+ },
+ {
+ "epoch": 0.46,
+ "learning_rate": 0.00011576855143650371,
+ "loss": 2.8677,
+ "step": 233
+ },
+ {
+ "epoch": 0.46,
+ "learning_rate": 0.00011514277775045768,
+ "loss": 0.3171,
+ "step": 234
+ },
+ {
+ "epoch": 0.46,
+ "learning_rate": 0.00011451639657251563,
+ "loss": 0.7903,
+ "step": 235
+ },
+ {
+ "epoch": 0.47,
+ "learning_rate": 0.00011388943303158693,
+ "loss": 2.6568,
+ "step": 236
+ },
+ {
+ "epoch": 0.47,
+ "learning_rate": 0.00011326191227994391,
+ "loss": 0.2808,
+ "step": 237
+ },
+ {
+ "epoch": 0.47,
+ "learning_rate": 0.00011263385949221295,
+ "loss": 0.1951,
+ "step": 238
+ },
+ {
+ "epoch": 0.47,
+ "learning_rate": 0.0001120052998643643,
+ "loss": 0.0974,
+ "step": 239
+ },
+ {
+ "epoch": 0.47,
+ "learning_rate": 0.00011137625861270151,
+ "loss": 0.1154,
+ "step": 240
+ },
+ {
+ "epoch": 0.48,
+ "learning_rate": 0.00011074676097284973,
+ "loss": 0.2559,
+ "step": 241
+ },
+ {
+ "epoch": 0.48,
+ "learning_rate": 0.00011011683219874323,
+ "loss": 0.6843,
+ "step": 242
+ },
+ {
+ "epoch": 0.48,
+ "learning_rate": 0.00010948649756161246,
+ "loss": 1.8828,
+ "step": 243
+ },
+ {
+ "epoch": 0.48,
+ "learning_rate": 0.00010885578234897003,
+ "loss": 0.0511,
+ "step": 244
+ },
+ {
+ "epoch": 0.48,
+ "learning_rate": 0.00010822471186359639,
+ "loss": 0.4992,
+ "step": 245
+ },
+ {
+ "epoch": 0.49,
+ "learning_rate": 0.00010759331142252462,
+ "loss": 0.1157,
+ "step": 246
+ },
+ {
+ "epoch": 0.49,
+ "learning_rate": 0.00010696160635602487,
+ "loss": 0.937,
+ "step": 247
+ },
+ {
+ "epoch": 0.49,
+ "learning_rate": 0.00010632962200658815,
+ "loss": 0.052,
+ "step": 248
+ },
+ {
+ "epoch": 0.49,
+ "learning_rate": 0.00010569738372790956,
+ "loss": 0.1229,
+ "step": 249
+ },
+ {
+ "epoch": 0.49,
+ "learning_rate": 0.00010506491688387127,
+ "loss": 0.1599,
+ "step": 250
+ },
+ {
+ "epoch": 0.5,
+ "learning_rate": 0.000104432246847525,
+ "loss": 0.7171,
+ "step": 251
+ },
+ {
+ "epoch": 0.5,
+ "learning_rate": 0.00010379939900007393,
+ "loss": 0.0594,
+ "step": 252
+ },
+ {
+ "epoch": 0.5,
+ "learning_rate": 0.00010316639872985472,
+ "loss": 2.7738,
+ "step": 253
+ },
+ {
+ "epoch": 0.5,
+ "learning_rate": 0.00010253327143131879,
+ "loss": 2.953,
+ "step": 254
+ },
+ {
+ "epoch": 0.5,
+ "eval_loss": 3.1145544052124023,
+ "eval_runtime": 38.0064,
+ "eval_samples_per_second": 1.368,
+ "eval_steps_per_second": 1.368,
+ "step": 254
+ },
+ {
+ "epoch": 0.5,
+ "learning_rate": 0.00010190004250401368,
+ "loss": 1.0087,
+ "step": 255
+ },
+ {
+ "epoch": 0.51,
+ "learning_rate": 0.00010126673735156402,
+ "loss": 0.1579,
+ "step": 256
+ },
+ {
+ "epoch": 0.51,
+ "learning_rate": 0.00010063338138065234,
+ "loss": 0.7859,
+ "step": 257
+ },
+ {
+ "epoch": 0.51,
+ "learning_rate": 0.0001,
+ "loss": 3.0133,
+ "step": 258
+ },
+ {
+ "epoch": 0.51,
+ "learning_rate": 9.936661861934765e-05,
+ "loss": 0.2415,
+ "step": 259
+ },
+ {
+ "epoch": 0.51,
+ "learning_rate": 9.8733262648436e-05,
+ "loss": 0.1456,
+ "step": 260
+ },
+ {
+ "epoch": 0.52,
+ "learning_rate": 9.809995749598632e-05,
+ "loss": 0.1532,
+ "step": 261
+ },
+ {
+ "epoch": 0.52,
+ "learning_rate": 9.746672856868123e-05,
+ "loss": 0.407,
+ "step": 262
+ },
+ {
+ "epoch": 0.52,
+ "learning_rate": 9.683360127014529e-05,
+ "loss": 0.3275,
+ "step": 263
+ },
+ {
+ "epoch": 0.52,
+ "learning_rate": 9.620060099992609e-05,
+ "loss": 0.3738,
+ "step": 264
+ },
+ {
+ "epoch": 0.52,
+ "learning_rate": 9.556775315247501e-05,
+ "loss": 0.283,
+ "step": 265
+ },
+ {
+ "epoch": 0.53,
+ "learning_rate": 9.493508311612874e-05,
+ "loss": 0.6886,
+ "step": 266
+ },
+ {
+ "epoch": 0.53,
+ "learning_rate": 9.430261627209044e-05,
+ "loss": 0.2551,
+ "step": 267
+ },
+ {
+ "epoch": 0.53,
+ "learning_rate": 9.367037799341187e-05,
+ "loss": 0.8632,
+ "step": 268
+ },
+ {
+ "epoch": 0.53,
+ "learning_rate": 9.303839364397511e-05,
+ "loss": 0.4109,
+ "step": 269
+ },
+ {
+ "epoch": 0.53,
+ "learning_rate": 9.24066885774754e-05,
+ "loss": 0.122,
+ "step": 270
+ },
+ {
+ "epoch": 0.54,
+ "learning_rate": 9.177528813640362e-05,
+ "loss": 0.1055,
+ "step": 271
+ },
+ {
+ "epoch": 0.54,
+ "learning_rate": 9.114421765102999e-05,
+ "loss": 0.3906,
+ "step": 272
+ },
+ {
+ "epoch": 0.54,
+ "learning_rate": 9.051350243838756e-05,
+ "loss": 0.0687,
+ "step": 273
+ },
+ {
+ "epoch": 0.54,
+ "learning_rate": 8.98831678012568e-05,
+ "loss": 2.9347,
+ "step": 274
+ },
+ {
+ "epoch": 0.54,
+ "learning_rate": 8.925323902715031e-05,
+ "loss": 0.1194,
+ "step": 275
+ },
+ {
+ "epoch": 0.54,
+ "learning_rate": 8.862374138729853e-05,
+ "loss": 0.5719,
+ "step": 276
+ },
+ {
+ "epoch": 0.55,
+ "learning_rate": 8.799470013563573e-05,
+ "loss": 2.7415,
+ "step": 277
+ },
+ {
+ "epoch": 0.55,
+ "learning_rate": 8.73661405077871e-05,
+ "loss": 0.1243,
+ "step": 278
+ },
+ {
+ "epoch": 0.55,
+ "learning_rate": 8.67380877200561e-05,
+ "loss": 2.9093,
+ "step": 279
+ },
+ {
+ "epoch": 0.55,
+ "learning_rate": 8.611056696841312e-05,
+ "loss": 1.2619,
+ "step": 280
+ },
+ {
+ "epoch": 0.55,
+ "learning_rate": 8.54836034274844e-05,
+ "loss": 0.5068,
+ "step": 281
+ },
+ {
+ "epoch": 0.56,
+ "learning_rate": 8.485722224954237e-05,
+ "loss": 2.9148,
+ "step": 282
+ },
+ {
+ "epoch": 0.56,
+ "learning_rate": 8.423144856349631e-05,
+ "loss": 1.1471,
+ "step": 283
+ },
+ {
+ "epoch": 0.56,
+ "learning_rate": 8.36063074738845e-05,
+ "loss": 1.91,
+ "step": 284
+ },
+ {
+ "epoch": 0.56,
+ "learning_rate": 8.298182405986689e-05,
+ "loss": 0.0886,
+ "step": 285
+ },
+ {
+ "epoch": 0.56,
+ "learning_rate": 8.235802337421919e-05,
+ "loss": 0.3945,
+ "step": 286
+ },
+ {
+ "epoch": 0.57,
+ "learning_rate": 8.173493044232745e-05,
+ "loss": 0.4341,
+ "step": 287
+ },
+ {
+ "epoch": 0.57,
+ "learning_rate": 8.11125702611846e-05,
+ "loss": 1.4804,
+ "step": 288
+ },
+ {
+ "epoch": 0.57,
+ "learning_rate": 8.049096779838719e-05,
+ "loss": 2.9338,
+ "step": 289
+ },
+ {
+ "epoch": 0.57,
+ "learning_rate": 7.987014799113397e-05,
+ "loss": 0.4612,
+ "step": 290
+ },
+ {
+ "epoch": 0.57,
+ "learning_rate": 7.925013574522557e-05,
+ "loss": 0.9304,
+ "step": 291
+ },
+ {
+ "epoch": 0.58,
+ "learning_rate": 7.863095593406491e-05,
+ "loss": 2.9119,
+ "step": 292
+ },
+ {
+ "epoch": 0.58,
+ "learning_rate": 7.801263339765994e-05,
+ "loss": 2.8254,
+ "step": 293
+ },
+ {
+ "epoch": 0.58,
+ "learning_rate": 7.739519294162652e-05,
+ "loss": 0.0828,
+ "step": 294
+ },
+ {
+ "epoch": 0.58,
+ "learning_rate": 7.677865933619379e-05,
+ "loss": 2.9986,
+ "step": 295
+ },
+ {
+ "epoch": 0.58,
+ "learning_rate": 7.616305731521008e-05,
+ "loss": 3.1021,
+ "step": 296
+ },
+ {
+ "epoch": 0.59,
+ "learning_rate": 7.554841157515092e-05,
+ "loss": 0.6816,
+ "step": 297
+ },
+ {
+ "epoch": 0.59,
+ "learning_rate": 7.493474677412794e-05,
+ "loss": 0.1559,
+ "step": 298
+ },
+ {
+ "epoch": 0.59,
+ "learning_rate": 7.432208753090009e-05,
+ "loss": 0.0844,
+ "step": 299
+ },
+ {
+ "epoch": 0.59,
+ "learning_rate": 7.371045842388552e-05,
+ "loss": 2.7568,
+ "step": 300
+ },
+ {
+ "epoch": 0.59,
+ "learning_rate": 7.309988399017602e-05,
+ "loss": 1.1267,
+ "step": 301
+ },
+ {
+ "epoch": 0.6,
+ "learning_rate": 7.24903887245522e-05,
+ "loss": 0.2277,
+ "step": 302
+ },
+ {
+ "epoch": 0.6,
+ "learning_rate": 7.188199707850122e-05,
+ "loss": 0.0967,
+ "step": 303
+ },
+ {
+ "epoch": 0.6,
+ "learning_rate": 7.127473345923554e-05,
+ "loss": 3.2755,
+ "step": 304
+ },
+ {
+ "epoch": 0.6,
+ "learning_rate": 7.066862222871397e-05,
+ "loss": 1.1044,
+ "step": 305
+ },
+ {
+ "epoch": 0.6,
+ "learning_rate": 7.006368770266421e-05,
+ "loss": 0.0781,
+ "step": 306
+ },
+ {
+ "epoch": 0.61,
+ "learning_rate": 6.945995414960744e-05,
+ "loss": 0.064,
+ "step": 307
+ },
+ {
+ "epoch": 0.61,
+ "learning_rate": 6.885744578988463e-05,
+ "loss": 0.831,
+ "step": 308
+ },
+ {
+ "epoch": 0.61,
+ "learning_rate": 6.825618679468502e-05,
+ "loss": 0.1206,
+ "step": 309
+ },
+ {
+ "epoch": 0.61,
+ "learning_rate": 6.765620128507619e-05,
+ "loss": 0.6853,
+ "step": 310
+ },
+ {
+ "epoch": 0.61,
+ "learning_rate": 6.705751333103675e-05,
+ "loss": 0.2435,
+ "step": 311
+ },
+ {
+ "epoch": 0.62,
+ "learning_rate": 6.64601469504903e-05,
+ "loss": 0.753,
+ "step": 312
+ },
+ {
+ "epoch": 0.62,
+ "learning_rate": 6.586412610834221e-05,
+ "loss": 0.0688,
+ "step": 313
+ },
+ {
+ "epoch": 0.62,
+ "learning_rate": 6.526947471551798e-05,
+ "loss": 0.2185,
+ "step": 314
+ },
+ {
+ "epoch": 0.62,
+ "learning_rate": 6.46762166280042e-05,
+ "loss": 0.0895,
+ "step": 315
+ },
+ {
+ "epoch": 0.62,
+ "learning_rate": 6.40843756458913e-05,
+ "loss": 2.5166,
+ "step": 316
+ },
+ {
+ "epoch": 0.63,
+ "learning_rate": 6.349397551241894e-05,
+ "loss": 0.7716,
+ "step": 317
+ },
+ {
+ "epoch": 0.63,
+ "learning_rate": 6.290503991302324e-05,
+ "loss": 0.7076,
+ "step": 318
+ },
+ {
+ "epoch": 0.63,
+ "learning_rate": 6.231759247438689e-05,
+ "loss": 0.3317,
+ "step": 319
+ },
+ {
+ "epoch": 0.63,
+ "learning_rate": 6.173165676349103e-05,
+ "loss": 0.3898,
+ "step": 320
+ },
+ {
+ "epoch": 0.63,
+ "learning_rate": 6.114725628666998e-05,
+ "loss": 1.9533,
+ "step": 321
+ },
+ {
+ "epoch": 0.64,
+ "learning_rate": 6.0564414488668165e-05,
+ "loss": 0.646,
+ "step": 322
+ },
+ {
+ "epoch": 0.64,
+ "learning_rate": 5.998315475169942e-05,
+ "loss": 2.9357,
+ "step": 323
+ },
+ {
+ "epoch": 0.64,
+ "learning_rate": 5.94035003945093e-05,
+ "loss": 5.7477,
+ "step": 324
+ },
+ {
+ "epoch": 0.64,
+ "learning_rate": 5.88254746714392e-05,
+ "loss": 1.0008,
+ "step": 325
+ },
+ {
+ "epoch": 0.64,
+ "learning_rate": 5.824910077149371e-05,
+ "loss": 0.3179,
+ "step": 326
+ },
+ {
+ "epoch": 0.65,
+ "learning_rate": 5.767440181741019e-05,
+ "loss": 0.9338,
+ "step": 327
+ },
+ {
+ "epoch": 0.65,
+ "learning_rate": 5.710140086473129e-05,
+ "loss": 0.1536,
+ "step": 328
+ },
+ {
+ "epoch": 0.65,
+ "learning_rate": 5.653012090087977e-05,
+ "loss": 0.61,
+ "step": 329
+ },
+ {
+ "epoch": 0.65,
+ "learning_rate": 5.596058484423656e-05,
+ "loss": 1.2369,
+ "step": 330
+ },
+ {
+ "epoch": 0.65,
+ "learning_rate": 5.5392815543221254e-05,
+ "loss": 0.1902,
+ "step": 331
+ },
+ {
+ "epoch": 0.66,
+ "learning_rate": 5.4826835775375285e-05,
+ "loss": 0.2775,
+ "step": 332
+ },
+ {
+ "epoch": 0.66,
+ "learning_rate": 5.4262668246448475e-05,
+ "loss": 0.2029,
+ "step": 333
+ },
+ {
+ "epoch": 0.66,
+ "learning_rate": 5.3700335589487925e-05,
+ "loss": 0.0906,
+ "step": 334
+ },
+ {
+ "epoch": 0.66,
+ "learning_rate": 5.3139860363929996e-05,
+ "loss": 0.1297,
+ "step": 335
+ },
+ {
+ "epoch": 0.66,
+ "learning_rate": 5.2581265054695494e-05,
+ "loss": 0.3453,
+ "step": 336
+ },
+ {
+ "epoch": 0.67,
+ "learning_rate": 5.202457207128736e-05,
+ "loss": 0.156,
+ "step": 337
+ },
+ {
+ "epoch": 0.67,
+ "learning_rate": 5.146980374689192e-05,
+ "loss": 0.2555,
+ "step": 338
+ },
+ {
+ "epoch": 0.67,
+ "learning_rate": 5.0916982337482644e-05,
+ "loss": 0.3003,
+ "step": 339
+ },
+ {
+ "epoch": 0.67,
+ "learning_rate": 5.0366130020927624e-05,
+ "loss": 0.7925,
+ "step": 340
+ },
+ {
+ "epoch": 0.67,
+ "learning_rate": 4.981726889609952e-05,
+ "loss": 1.2376,
+ "step": 341
+ },
+ {
+ "epoch": 0.68,
+ "learning_rate": 4.9270420981989294e-05,
+ "loss": 2.9298,
+ "step": 342
+ },
+ {
+ "epoch": 0.68,
+ "learning_rate": 4.872560821682256e-05,
+ "loss": 0.1811,
+ "step": 343
+ },
+ {
+ "epoch": 0.68,
+ "learning_rate": 4.818285245717984e-05,
+ "loss": 0.1007,
+ "step": 344
+ },
+ {
+ "epoch": 0.68,
+ "learning_rate": 4.764217547711934e-05,
+ "loss": 5.1643,
+ "step": 345
+ },
+ {
+ "epoch": 0.68,
+ "learning_rate": 4.710359896730379e-05,
+ "loss": 0.6855,
+ "step": 346
+ },
+ {
+ "epoch": 0.69,
+ "learning_rate": 4.656714453412993e-05,
+ "loss": 1.6421,
+ "step": 347
+ },
+ {
+ "epoch": 0.69,
+ "learning_rate": 4.6032833698862044e-05,
+ "loss": 0.0813,
+ "step": 348
+ },
+ {
+ "epoch": 0.69,
+ "learning_rate": 4.5500687896768256e-05,
+ "loss": 2.8098,
+ "step": 349
+ },
+ {
+ "epoch": 0.69,
+ "learning_rate": 4.497072847626087e-05,
+ "loss": 2.9227,
+ "step": 350
+ },
+ {
+ "epoch": 0.69,
+ "learning_rate": 4.444297669803981e-05,
+ "loss": 0.0877,
+ "step": 351
+ },
+ {
+ "epoch": 0.69,
+ "learning_rate": 4.3917453734239566e-05,
+ "loss": 0.1996,
+ "step": 352
+ },
+ {
+ "epoch": 0.7,
+ "learning_rate": 4.339418066758008e-05,
+ "loss": 0.8809,
+ "step": 353
+ },
+ {
+ "epoch": 0.7,
+ "learning_rate": 4.287317849052075e-05,
+ "loss": 2.7009,
+ "step": 354
+ },
+ {
+ "epoch": 0.7,
+ "learning_rate": 4.235446810441841e-05,
+ "loss": 0.067,
+ "step": 355
+ },
+ {
+ "epoch": 0.7,
+ "learning_rate": 4.1838070318688604e-05,
+ "loss": 1.6842,
+ "step": 356
+ },
+ {
+ "epoch": 0.7,
+ "learning_rate": 4.132400584997106e-05,
+ "loss": 0.7324,
+ "step": 357
+ },
+ {
+ "epoch": 0.71,
+ "learning_rate": 4.081229532129827e-05,
+ "loss": 0.1683,
+ "step": 358
+ },
+ {
+ "epoch": 0.71,
+ "learning_rate": 4.030295926126845e-05,
+ "loss": 0.7423,
+ "step": 359
+ },
+ {
+ "epoch": 0.71,
+ "learning_rate": 3.979601810322169e-05,
+ "loss": 0.2521,
+ "step": 360
+ },
+ {
+ "epoch": 0.71,
+ "learning_rate": 3.929149218442052e-05,
+ "loss": 0.3601,
+ "step": 361
+ },
+ {
+ "epoch": 0.71,
+ "learning_rate": 3.878940174523371e-05,
+ "loss": 0.1575,
+ "step": 362
+ },
+ {
+ "epoch": 0.72,
+ "learning_rate": 3.828976692832458e-05,
+ "loss": 0.572,
+ "step": 363
+ },
+ {
+ "epoch": 0.72,
+ "learning_rate": 3.779260777784263e-05,
+ "loss": 2.8984,
+ "step": 364
+ },
+ {
+ "epoch": 0.72,
+ "learning_rate": 3.7297944238619706e-05,
+ "loss": 0.0589,
+ "step": 365
+ },
+ {
+ "epoch": 0.72,
+ "learning_rate": 3.680579615536961e-05,
+ "loss": 0.0536,
+ "step": 366
+ },
+ {
+ "epoch": 0.72,
+ "learning_rate": 3.631618327189218e-05,
+ "loss": 0.0897,
+ "step": 367
+ },
+ {
+ "epoch": 0.73,
+ "learning_rate": 3.582912523028101e-05,
+ "loss": 0.7315,
+ "step": 368
+ },
+ {
+ "epoch": 0.73,
+ "learning_rate": 3.534464157013574e-05,
+ "loss": 0.1946,
+ "step": 369
+ },
+ {
+ "epoch": 0.73,
+ "learning_rate": 3.4862751727777797e-05,
+ "loss": 1.2387,
+ "step": 370
+ },
+ {
+ "epoch": 0.73,
+ "learning_rate": 3.438347503547102e-05,
+ "loss": 0.0964,
+ "step": 371
+ },
+ {
+ "epoch": 0.73,
+ "learning_rate": 3.390683072064594e-05,
+ "loss": 1.1282,
+ "step": 372
+ },
+ {
+ "epoch": 0.74,
+ "learning_rate": 3.343283790512829e-05,
+ "loss": 0.3648,
+ "step": 373
+ },
+ {
+ "epoch": 0.74,
+ "learning_rate": 3.296151560437214e-05,
+ "loss": 0.1887,
+ "step": 374
+ },
+ {
+ "epoch": 0.74,
+ "learning_rate": 3.249288272669691e-05,
+ "loss": 0.1734,
+ "step": 375
+ },
+ {
+ "epoch": 0.74,
+ "learning_rate": 3.202695807252871e-05,
+ "loss": 2.8517,
+ "step": 376
+ },
+ {
+ "epoch": 0.74,
+ "learning_rate": 3.1563760333646395e-05,
+ "loss": 0.1988,
+ "step": 377
+ },
+ {
+ "epoch": 0.75,
+ "learning_rate": 3.110330809243134e-05,
+ "loss": 2.929,
+ "step": 378
+ },
+ {
+ "epoch": 0.75,
+ "learning_rate": 3.064561982112232e-05,
+ "loss": 0.1981,
+ "step": 379
+ },
+ {
+ "epoch": 0.75,
+ "learning_rate": 3.0190713881074105e-05,
+ "loss": 0.0902,
+ "step": 380
+ },
+ {
+ "epoch": 0.75,
+ "learning_rate": 2.9738608522021173e-05,
+ "loss": 0.35,
+ "step": 381
+ },
+ {
+ "epoch": 0.75,
+ "eval_loss": 3.096834897994995,
+ "eval_runtime": 37.8467,
+ "eval_samples_per_second": 1.374,
+ "eval_steps_per_second": 1.374,
+ "step": 381
+ },
+ {
+ "epoch": 0.75,
+ "learning_rate": 2.9289321881345254e-05,
+ "loss": 0.4055,
+ "step": 382
+ },
+ {
+ "epoch": 0.76,
+ "learning_rate": 2.8842871983347998e-05,
+ "loss": 0.0914,
+ "step": 383
+ },
+ {
+ "epoch": 0.76,
+ "learning_rate": 2.8399276738527714e-05,
+ "loss": 0.6584,
+ "step": 384
+ },
+ {
+ "epoch": 0.76,
+ "learning_rate": 2.795855394286081e-05,
+ "loss": 0.1345,
+ "step": 385
+ },
+ {
+ "epoch": 0.76,
+ "learning_rate": 2.7520721277088024e-05,
+ "loss": 0.1762,
+ "step": 386
+ },
+ {
+ "epoch": 0.76,
+ "learning_rate": 2.7085796306004906e-05,
+ "loss": 0.0956,
+ "step": 387
+ },
+ {
+ "epoch": 0.77,
+ "learning_rate": 2.6653796477757432e-05,
+ "loss": 0.0985,
+ "step": 388
+ },
+ {
+ "epoch": 0.77,
+ "learning_rate": 2.6224739123141684e-05,
+ "loss": 0.768,
+ "step": 389
+ },
+ {
+ "epoch": 0.77,
+ "learning_rate": 2.5798641454908944e-05,
+ "loss": 3.141,
+ "step": 390
+ },
+ {
+ "epoch": 0.77,
+ "learning_rate": 2.537552056707483e-05,
+ "loss": 3.1468,
+ "step": 391
+ },
+ {
+ "epoch": 0.77,
+ "learning_rate": 2.4955393434233754e-05,
+ "loss": 2.8864,
+ "step": 392
+ },
+ {
+ "epoch": 0.78,
+ "learning_rate": 2.45382769108779e-05,
+ "loss": 0.774,
+ "step": 393
+ },
+ {
+ "epoch": 0.78,
+ "learning_rate": 2.4124187730720917e-05,
+ "loss": 0.1578,
+ "step": 394
+ },
+ {
+ "epoch": 0.78,
+ "learning_rate": 2.3713142506026786e-05,
+ "loss": 2.4016,
+ "step": 395
+ },
+ {
+ "epoch": 0.78,
+ "learning_rate": 2.3305157726943327e-05,
+ "loss": 3.0549,
+ "step": 396
+ },
+ {
+ "epoch": 0.78,
+ "learning_rate": 2.290024976084052e-05,
+ "loss": 0.3476,
+ "step": 397
+ },
+ {
+ "epoch": 0.79,
+ "learning_rate": 2.2498434851654126e-05,
+ "loss": 1.6223,
+ "step": 398
+ },
+ {
+ "epoch": 0.79,
+ "learning_rate": 2.209972911923377e-05,
+ "loss": 0.139,
+ "step": 399
+ },
+ {
+ "epoch": 0.79,
+ "learning_rate": 2.170414855869647e-05,
+ "loss": 3.1515,
+ "step": 400
+ },
+ {
+ "epoch": 0.79,
+ "learning_rate": 2.1311709039784734e-05,
+ "loss": 1.0012,
+ "step": 401
+ },
+ {
+ "epoch": 0.79,
+ "learning_rate": 2.092242630623016e-05,
+ "loss": 0.4592,
+ "step": 402
+ },
+ {
+ "epoch": 0.8,
+ "learning_rate": 2.0536315975121544e-05,
+ "loss": 0.4305,
+ "step": 403
+ },
+ {
+ "epoch": 0.8,
+ "learning_rate": 2.0153393536278653e-05,
+ "loss": 0.9412,
+ "step": 404
+ },
+ {
+ "epoch": 0.8,
+ "learning_rate": 1.9773674351630545e-05,
+ "loss": 0.1606,
+ "step": 405
+ },
+ {
+ "epoch": 0.8,
+ "learning_rate": 1.939717365459952e-05,
+ "loss": 0.1445,
+ "step": 406
+ },
+ {
+ "epoch": 0.8,
+ "learning_rate": 1.9023906549489767e-05,
+ "loss": 5.7603,
+ "step": 407
+ },
+ {
+ "epoch": 0.81,
+ "learning_rate": 1.8653888010881637e-05,
+ "loss": 0.037,
+ "step": 408
+ },
+ {
+ "epoch": 0.81,
+ "learning_rate": 1.82871328830307e-05,
+ "loss": 0.1551,
+ "step": 409
+ },
+ {
+ "epoch": 0.81,
+ "learning_rate": 1.7923655879272393e-05,
+ "loss": 0.542,
+ "step": 410
+ },
+ {
+ "epoch": 0.81,
+ "learning_rate": 1.7563471581431624e-05,
+ "loss": 0.1888,
+ "step": 411
+ },
+ {
+ "epoch": 0.81,
+ "learning_rate": 1.7206594439237865e-05,
+ "loss": 1.0623,
+ "step": 412
+ },
+ {
+ "epoch": 0.82,
+ "learning_rate": 1.6853038769745467e-05,
+ "loss": 0.0943,
+ "step": 413
+ },
+ {
+ "epoch": 0.82,
+ "learning_rate": 1.6502818756759276e-05,
+ "loss": 0.1562,
+ "step": 414
+ },
+ {
+ "epoch": 0.82,
+ "learning_rate": 1.61559484502655e-05,
+ "loss": 2.9172,
+ "step": 415
+ },
+ {
+ "epoch": 0.82,
+ "learning_rate": 1.5812441765868292e-05,
+ "loss": 0.0865,
+ "step": 416
+ },
+ {
+ "epoch": 0.82,
+ "learning_rate": 1.547231248423132e-05,
+ "loss": 2.3386,
+ "step": 417
+ },
+ {
+ "epoch": 0.83,
+ "learning_rate": 1.5135574250524897e-05,
+ "loss": 2.3205,
+ "step": 418
+ },
+ {
+ "epoch": 0.83,
+ "learning_rate": 1.4802240573878733e-05,
+ "loss": 0.9576,
+ "step": 419
+ },
+ {
+ "epoch": 0.83,
+ "learning_rate": 1.447232482683979e-05,
+ "loss": 0.1757,
+ "step": 420
+ },
+ {
+ "epoch": 0.83,
+ "learning_rate": 1.4145840244835983e-05,
+ "loss": 0.5404,
+ "step": 421
+ },
+ {
+ "epoch": 0.83,
+ "learning_rate": 1.3822799925645036e-05,
+ "loss": 0.8805,
+ "step": 422
+ },
+ {
+ "epoch": 0.84,
+ "learning_rate": 1.3503216828869192e-05,
+ "loss": 0.1249,
+ "step": 423
+ },
+ {
+ "epoch": 0.84,
+ "learning_rate": 1.3187103775415156e-05,
+ "loss": 0.3596,
+ "step": 424
+ },
+ {
+ "epoch": 0.84,
+ "learning_rate": 1.2874473446979918e-05,
+ "loss": 1.6876,
+ "step": 425
+ },
+ {
+ "epoch": 0.84,
+ "learning_rate": 1.2565338385541792e-05,
+ "loss": 0.1585,
+ "step": 426
+ },
+ {
+ "epoch": 0.84,
+ "learning_rate": 1.2259710992857465e-05,
+ "loss": 2.8895,
+ "step": 427
+ },
+ {
+ "epoch": 0.85,
+ "learning_rate": 1.195760352996429e-05,
+ "loss": 2.9701,
+ "step": 428
+ },
+ {
+ "epoch": 0.85,
+ "learning_rate": 1.1659028116688575e-05,
+ "loss": 0.3456,
+ "step": 429
+ },
+ {
+ "epoch": 0.85,
+ "learning_rate": 1.1363996731159188e-05,
+ "loss": 0.3992,
+ "step": 430
+ },
+ {
+ "epoch": 0.85,
+ "learning_rate": 1.107252120932717e-05,
+ "loss": 0.4428,
+ "step": 431
+ },
+ {
+ "epoch": 0.85,
+ "learning_rate": 1.0784613244490816e-05,
+ "loss": 0.0964,
+ "step": 432
+ },
+ {
+ "epoch": 0.85,
+ "learning_rate": 1.0500284386826597e-05,
+ "loss": 0.4612,
+ "step": 433
+ },
+ {
+ "epoch": 0.86,
+ "learning_rate": 1.0219546042925843e-05,
+ "loss": 1.0988,
+ "step": 434
+ },
+ {
+ "epoch": 0.86,
+ "learning_rate": 9.942409475337012e-06,
+ "loss": 0.2646,
+ "step": 435
+ },
+ {
+ "epoch": 0.86,
+ "learning_rate": 9.668885802114003e-06,
+ "loss": 0.1104,
+ "step": 436
+ },
+ {
+ "epoch": 0.86,
+ "learning_rate": 9.398985996370058e-06,
+ "loss": 2.9026,
+ "step": 437
+ },
+ {
+ "epoch": 0.86,
+ "learning_rate": 9.13272088583751e-06,
+ "loss": 2.5969,
+ "step": 438
+ },
+ {
+ "epoch": 0.87,
+ "learning_rate": 8.870101152433497e-06,
+ "loss": 0.204,
+ "step": 439
+ },
+ {
+ "epoch": 0.87,
+ "learning_rate": 8.611137331831331e-06,
+ "loss": 2.8929,
+ "step": 440
+ },
+ {
+ "epoch": 0.87,
+ "learning_rate": 8.355839813037936e-06,
+ "loss": 0.4752,
+ "step": 441
+ },
+ {
+ "epoch": 0.87,
+ "learning_rate": 8.10421883797694e-06,
+ "loss": 0.0708,
+ "step": 442
+ },
+ {
+ "epoch": 0.87,
+ "learning_rate": 7.856284501077926e-06,
+ "loss": 0.2817,
+ "step": 443
+ },
+ {
+ "epoch": 0.88,
+ "learning_rate": 7.612046748871327e-06,
+ "loss": 0.3538,
+ "step": 444
+ },
+ {
+ "epoch": 0.88,
+ "learning_rate": 7.371515379589555e-06,
+ "loss": 3.0355,
+ "step": 445
+ },
+ {
+ "epoch": 0.88,
+ "learning_rate": 7.13470004277379e-06,
+ "loss": 1.7098,
+ "step": 446
+ },
+ {
+ "epoch": 0.88,
+ "learning_rate": 6.901610238886891e-06,
+ "loss": 0.0538,
+ "step": 447
+ },
+ {
+ "epoch": 0.88,
+ "learning_rate": 6.672255318932341e-06,
+ "loss": 0.1649,
+ "step": 448
+ },
+ {
+ "epoch": 0.89,
+ "learning_rate": 6.4466444840789674e-06,
+ "loss": 0.1586,
+ "step": 449
+ },
+ {
+ "epoch": 0.89,
+ "learning_rate": 6.22478678529197e-06,
+ "loss": 3.0296,
+ "step": 450
+ },
+ {
+ "epoch": 0.89,
+ "learning_rate": 6.006691122969643e-06,
+ "loss": 2.9251,
+ "step": 451
+ },
+ {
+ "epoch": 0.89,
+ "learning_rate": 5.792366246586511e-06,
+ "loss": 0.5227,
+ "step": 452
+ },
+ {
+ "epoch": 0.89,
+ "learning_rate": 5.581820754342137e-06,
+ "loss": 0.1688,
+ "step": 453
+ },
+ {
+ "epoch": 0.9,
+ "learning_rate": 5.375063092816313e-06,
+ "loss": 0.6017,
+ "step": 454
+ },
+ {
+ "epoch": 0.9,
+ "learning_rate": 5.172101556630149e-06,
+ "loss": 0.0826,
+ "step": 455
+ },
+ {
+ "epoch": 0.9,
+ "learning_rate": 4.972944288113268e-06,
+ "loss": 0.7591,
+ "step": 456
+ },
+ {
+ "epoch": 0.9,
+ "learning_rate": 4.777599276977263e-06,
+ "loss": 0.1292,
+ "step": 457
+ },
+ {
+ "epoch": 0.9,
+ "learning_rate": 4.586074359995119e-06,
+ "loss": 0.8982,
+ "step": 458
+ },
+ {
+ "epoch": 0.91,
+ "learning_rate": 4.398377220686745e-06,
+ "loss": 2.735,
+ "step": 459
+ },
+ {
+ "epoch": 0.91,
+ "learning_rate": 4.214515389010865e-06,
+ "loss": 0.242,
+ "step": 460
+ },
+ {
+ "epoch": 0.91,
+ "learning_rate": 4.034496241062824e-06,
+ "loss": 0.097,
+ "step": 461
+ },
+ {
+ "epoch": 0.91,
+ "learning_rate": 3.858326998778761e-06,
+ "loss": 0.1028,
+ "step": 462
+ },
+ {
+ "epoch": 0.91,
+ "learning_rate": 3.6860147296457816e-06,
+ "loss": 0.1689,
+ "step": 463
+ },
+ {
+ "epoch": 0.92,
+ "learning_rate": 3.5175663464185436e-06,
+ "loss": 0.1873,
+ "step": 464
+ },
+ {
+ "epoch": 0.92,
+ "learning_rate": 3.3529886068418447e-06,
+ "loss": 3.074,
+ "step": 465
+ },
+ {
+ "epoch": 0.92,
+ "learning_rate": 3.1922881133795825e-06,
+ "loss": 0.2985,
+ "step": 466
+ },
+ {
+ "epoch": 0.92,
+ "learning_rate": 3.035471312949778e-06,
+ "loss": 0.0815,
+ "step": 467
+ },
+ {
+ "epoch": 0.92,
+ "learning_rate": 2.8825444966661063e-06,
+ "loss": 0.1297,
+ "step": 468
+ },
+ {
+ "epoch": 0.93,
+ "learning_rate": 2.7335137995853188e-06,
+ "loss": 1.8928,
+ "step": 469
+ },
+ {
+ "epoch": 0.93,
+ "learning_rate": 2.5883852004613074e-06,
+ "loss": 0.0399,
+ "step": 470
+ },
+ {
+ "epoch": 0.93,
+ "learning_rate": 2.4471645215050743e-06,
+ "loss": 2.4668,
+ "step": 471
+ },
+ {
+ "epoch": 0.93,
+ "learning_rate": 2.3098574281513185e-06,
+ "loss": 1.3717,
+ "step": 472
+ },
+ {
+ "epoch": 0.93,
+ "learning_rate": 2.1764694288310184e-06,
+ "loss": 0.5464,
+ "step": 473
+ },
+ {
+ "epoch": 0.94,
+ "learning_rate": 2.0470058747505516e-06,
+ "loss": 5.7381,
+ "step": 474
+ },
+ {
+ "epoch": 0.94,
+ "learning_rate": 1.921471959676957e-06,
+ "loss": 0.0523,
+ "step": 475
+ },
+ {
+ "epoch": 0.94,
+ "learning_rate": 1.7998727197295784e-06,
+ "loss": 2.0947,
+ "step": 476
+ },
+ {
+ "epoch": 0.94,
+ "learning_rate": 1.6822130331780484e-06,
+ "loss": 0.3609,
+ "step": 477
+ },
+ {
+ "epoch": 0.94,
+ "learning_rate": 1.5684976202465784e-06,
+ "loss": 0.3193,
+ "step": 478
+ },
+ {
+ "epoch": 0.95,
+ "learning_rate": 1.4587310429245882e-06,
+ "loss": 0.5045,
+ "step": 479
+ },
+ {
+ "epoch": 0.95,
+ "learning_rate": 1.3529177047836627e-06,
+ "loss": 0.0842,
+ "step": 480
+ },
+ {
+ "epoch": 0.95,
+ "learning_rate": 1.2510618508009608e-06,
+ "loss": 1.3106,
+ "step": 481
+ },
+ {
+ "epoch": 0.95,
+ "learning_rate": 1.1531675671888619e-06,
+ "loss": 2.8808,
+ "step": 482
+ },
+ {
+ "epoch": 0.95,
+ "learning_rate": 1.0592387812310311e-06,
+ "loss": 2.9172,
+ "step": 483
+ },
+ {
+ "epoch": 0.96,
+ "learning_rate": 9.692792611249224e-07,
+ "loss": 0.6062,
+ "step": 484
+ },
+ {
+ "epoch": 0.96,
+ "learning_rate": 8.832926158305444e-07,
+ "loss": 0.1825,
+ "step": 485
+ },
+ {
+ "epoch": 0.96,
+ "learning_rate": 8.012822949256982e-07,
+ "loss": 0.2575,
+ "step": 486
+ },
+ {
+ "epoch": 0.96,
+ "learning_rate": 7.232515884676328e-07,
+ "loss": 0.1746,
+ "step": 487
+ },
+ {
+ "epoch": 0.96,
+ "learning_rate": 6.492036268609725e-07,
+ "loss": 0.264,
+ "step": 488
+ },
+ {
+ "epoch": 0.97,
+ "learning_rate": 5.791413807322066e-07,
+ "loss": 0.0955,
+ "step": 489
+ },
+ {
+ "epoch": 0.97,
+ "learning_rate": 5.130676608104845e-07,
+ "loss": 0.1896,
+ "step": 490
+ },
+ {
+ "epoch": 0.97,
+ "learning_rate": 4.509851178148505e-07,
+ "loss": 0.402,
+ "step": 491
+ },
+ {
+ "epoch": 0.97,
+ "learning_rate": 3.9289624234790656e-07,
+ "loss": 0.3264,
+ "step": 492
+ }
+ ],
+ "logging_steps": 1,
+ "max_steps": 506,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 1,
+ "save_steps": 500,
+ "total_flos": 1.8835459562432102e+17,
+ "train_batch_size": 1,
+ "trial_name": null,
+ "trial_params": null
+}

checkpoint-492/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0bbf07f85ca03d460e0939878b710e57c14395472419b3516802b1c1ba6510a
+size 4795

config.json

@@ -0,0 +1,51 @@
+{
+ "_name_or_path": "bigcode/starcoder",
+ "activation_function": "gelu",
+ "architectures": [
+ "GPTBigCodeForCausalLM"
+ ],
+ "attention_softmax_in_fp32": true,
+ "attn_pdrop": 0.1,
+ "bos_token_id": 0,
+ "embd_pdrop": 0.1,
+ "eos_token_id": 0,
+ "inference_runner": 0,
+ "initializer_range": 0.02,
+ "layer_norm_epsilon": 1e-05,
+ "max_batch_size": null,
+ "max_sequence_length": null,
+ "model_type": "gpt_bigcode",
+ "multi_query": true,
+ "n_embd": 6144,
+ "n_head": 48,
+ "n_inner": 24576,
+ "n_layer": 40,
+ "n_positions": 8192,
+ "pad_key_length": true,
+ "pre_allocate_kv_cache": false,
+ "quantization_config": {
+ "bnb_4bit_compute_dtype": "float32",
+ "bnb_4bit_quant_type": "fp4",
+ "bnb_4bit_use_double_quant": false,
+ "llm_int8_enable_fp32_cpu_offload": false,
+ "llm_int8_has_fp16_weight": false,
+ "llm_int8_skip_modules": null,
+ "llm_int8_threshold": 6.0,
+ "load_in_4bit": false,
+ "load_in_8bit": true,
+ "quant_method": "bitsandbytes"
+ },
+ "resid_pdrop": 0.1,
+ "scale_attention_softmax_in_fp32": true,
+ "scale_attn_weights": true,
+ "summary_activation": null,
+ "summary_first_dropout": 0.1,
+ "summary_proj_to_labels": true,
+ "summary_type": "cls_index",
+ "summary_use_proj": true,
+ "torch_dtype": "float32",
+ "transformers_version": "4.37.0.dev0",
+ "use_cache": false,
+ "validate_runner_input": true,
+ "vocab_size": 49156
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+ "additional_special_tokens": [
+ "<|endoftext|>",
+ "<fim_prefix>",
+ "<fim_middle>",
+ "<fim_suffix>",
+ "<fim_pad>",
+ "<filename>",
+ "<gh_stars>",
+ "<issue_start>",
+ "<issue_comment>",
+ "<issue_closed>",
+ "<jupyter_start>",
+ "<jupyter_text>",
+ "<jupyter_code>",
+ "<jupyter_output>",
+ "<empty_output>",
+ "<commit_before>",
+ "<commit_msg>",
+ "<commit_after>",
+ "<reponame>"
+ ],
+ "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": {
+ "content": "[PAD]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}

tokenizer_config.json

@@ -0,0 +1,218 @@
+{
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "<fim_prefix>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "<fim_middle>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "3": {
+ "content": "<fim_suffix>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "4": {
+ "content": "<fim_pad>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "5": {
+ "content": "<filename>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "6": {
+ "content": "<gh_stars>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "7": {
+ "content": "<issue_start>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "8": {
+ "content": "<issue_comment>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "9": {
+ "content": "<issue_closed>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "10": {
+ "content": "<jupyter_start>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "11": {
+ "content": "<jupyter_text>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "12": {
+ "content": "<jupyter_code>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "13": {
+ "content": "<jupyter_output>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "14": {
+ "content": "<empty_output>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "15": {
+ "content": "<commit_before>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "16": {
+ "content": "<commit_msg>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "17": {
+ "content": "<commit_after>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "18": {
+ "content": "<reponame>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "49152": {
+ "content": "[PAD]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "49153": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "49154": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "49155": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "additional_special_tokens": [
+ "<|endoftext|>",
+ "<fim_prefix>",
+ "<fim_middle>",
+ "<fim_suffix>",
+ "<fim_pad>",
+ "<filename>",
+ "<gh_stars>",
+ "<issue_start>",
+ "<issue_comment>",
+ "<issue_closed>",
+ "<jupyter_start>",
+ "<jupyter_text>",
+ "<jupyter_code>",
+ "<jupyter_output>",
+ "<empty_output>",
+ "<commit_before>",
+ "<commit_msg>",
+ "<commit_after>",
+ "<reponame>"
+ ],
+ "bos_token": "<s>",
+ "clean_up_tokenization_spaces": true,
+ "eos_token": "</s>",
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "[PAD]",
+ "tokenizer_class": "GPT2Tokenizer",
+ "unk_token": "<unk>",
+ "vocab_size": 49152
+}