Upload 15 files

README.md

@@ -1,3 +1,238 @@
 ---
-license: mit
+library_name: peft
+base_model: HuggingFaceH4/zephyr-7b-beta
 ---
+
+# 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]
+- **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 Data 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 Data 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: QuantizationMethod.BITS_AND_BYTES
+- load_in_8bit: False
+- load_in_4bit: True
+- 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: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.2
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- load_in_8bit: False
+- load_in_4bit: True
+- 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: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.2

adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42f2b9791a38bca4cab66df0b594b134df08068e68d11d6ef95b217f9013cbc1
+size 109098378

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f46722242703fad2f636f7be221a05a7aa8636f5eb699f22a281ab0609775d4
+size 218211962

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
+size 888

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e18a37b92d8480fc7a2ebab431f1aafd151a854413733ca47354bc77b1e06e6
+size 14768

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24d1d70a3d1500b0aa278bd5164952bd7a26a3c26fe2d134b2e2bb5a7742794e
+size 14768

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47cdf404d57c885d338f40209feb89ea11ba38642c0d4be28a92c90d20453a55
+size 14768

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:112a137ea22fe0bd6309f54c81308456c7645deffb96cfa7de06c9946947656e
+size 1064

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1024,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

trainer_state.json

@@ -0,0 +1,1073 @@
+{
+  "best_metric": 0.4947710931301117,
+  "best_model_checkpoint": "zephyr_7B_ruPython/checkpoint-3466",
+  "epoch": 1.9997115245925285,
+  "eval_steps": 500,
+  "global_step": 3466,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 1.0975,
+      "step": 20
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 1.083,
+      "step": 40
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.307692307692308e-05,
+      "loss": 1.0227,
+      "step": 60
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3.0769230769230774e-05,
+      "loss": 0.9524,
+      "step": 80
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 3.846153846153846e-05,
+      "loss": 0.8904,
+      "step": 100
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.615384615384616e-05,
+      "loss": 0.8482,
+      "step": 120
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 5.384615384615385e-05,
+      "loss": 0.8015,
+      "step": 140
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 6.153846153846155e-05,
+      "loss": 0.8032,
+      "step": 160
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 6.923076923076924e-05,
+      "loss": 0.7839,
+      "step": 180
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 7.692307692307693e-05,
+      "loss": 0.7964,
+      "step": 200
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 8.461538461538461e-05,
+      "loss": 0.7531,
+      "step": 220
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.230769230769232e-05,
+      "loss": 0.7508,
+      "step": 240
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0001,
+      "loss": 0.7531,
+      "step": 260
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0001076923076923077,
+      "loss": 0.7543,
+      "step": 280
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00011538461538461538,
+      "loss": 0.7426,
+      "step": 300
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0001230769230769231,
+      "loss": 0.7222,
+      "step": 320
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00013076923076923077,
+      "loss": 0.7456,
+      "step": 340
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00013846153846153847,
+      "loss": 0.7447,
+      "step": 360
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00014615384615384615,
+      "loss": 0.7297,
+      "step": 380
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00015384615384615385,
+      "loss": 0.7339,
+      "step": 400
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00016153846153846155,
+      "loss": 0.7418,
+      "step": 420
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00016923076923076923,
+      "loss": 0.7315,
+      "step": 440
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00017692307692307693,
+      "loss": 0.7104,
+      "step": 460
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00018461538461538463,
+      "loss": 0.717,
+      "step": 480
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00019230769230769233,
+      "loss": 0.7307,
+      "step": 500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0002,
+      "loss": 0.728,
+      "step": 520
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0001991451164778799,
+      "loss": 0.7171,
+      "step": 540
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0001982902329557598,
+      "loss": 0.7137,
+      "step": 560
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0001974353494336397,
+      "loss": 0.6911,
+      "step": 580
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00019658046591151956,
+      "loss": 0.6992,
+      "step": 600
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00019572558238939946,
+      "loss": 0.6959,
+      "step": 620
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00019487069886727932,
+      "loss": 0.7046,
+      "step": 640
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00019401581534515922,
+      "loss": 0.6976,
+      "step": 660
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0001931609318230391,
+      "loss": 0.7042,
+      "step": 680
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.000192306048300919,
+      "loss": 0.6908,
+      "step": 700
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0001914511647787989,
+      "loss": 0.6984,
+      "step": 720
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0001905962812566788,
+      "loss": 0.6999,
+      "step": 740
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0001897413977345587,
+      "loss": 0.7094,
+      "step": 760
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00018888651421243856,
+      "loss": 0.7003,
+      "step": 780
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00018803163069031845,
+      "loss": 0.6809,
+      "step": 800
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00018717674716819835,
+      "loss": 0.7135,
+      "step": 820
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00018632186364607822,
+      "loss": 0.6913,
+      "step": 840
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0001854669801239581,
+      "loss": 0.6932,
+      "step": 860
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.000184612096601838,
+      "loss": 0.6832,
+      "step": 880
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0001837572130797179,
+      "loss": 0.6927,
+      "step": 900
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0001829023295575978,
+      "loss": 0.6729,
+      "step": 920
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00018204744603547766,
+      "loss": 0.6742,
+      "step": 940
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00018119256251335756,
+      "loss": 0.6718,
+      "step": 960
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018033767899123745,
+      "loss": 0.6868,
+      "step": 980
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00017948279546911735,
+      "loss": 0.6869,
+      "step": 1000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00017862791194699724,
+      "loss": 0.6633,
+      "step": 1020
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0001777730284248771,
+      "loss": 0.6967,
+      "step": 1040
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.000176918144902757,
+      "loss": 0.6758,
+      "step": 1060
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0001760632613806369,
+      "loss": 0.6918,
+      "step": 1080
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0001752083778585168,
+      "loss": 0.6718,
+      "step": 1100
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00017435349433639666,
+      "loss": 0.6722,
+      "step": 1120
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00017349861081427656,
+      "loss": 0.684,
+      "step": 1140
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00017264372729215645,
+      "loss": 0.6619,
+      "step": 1160
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00017178884377003635,
+      "loss": 0.6789,
+      "step": 1180
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00017093396024791624,
+      "loss": 0.677,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00017007907672579614,
+      "loss": 0.6836,
+      "step": 1220
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.000169266937379782,
+      "loss": 0.6823,
+      "step": 1240
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0001684120538576619,
+      "loss": 0.6936,
+      "step": 1260
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0001675571703355418,
+      "loss": 0.6646,
+      "step": 1280
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0001667022868134217,
+      "loss": 0.6733,
+      "step": 1300
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00016584740329130159,
+      "loss": 0.6753,
+      "step": 1320
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00016499251976918145,
+      "loss": 0.677,
+      "step": 1340
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00016413763624706135,
+      "loss": 0.6692,
+      "step": 1360
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00016328275272494122,
+      "loss": 0.656,
+      "step": 1380
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0001624278692028211,
+      "loss": 0.6767,
+      "step": 1400
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.000161572985680701,
+      "loss": 0.6485,
+      "step": 1420
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0001607181021585809,
+      "loss": 0.679,
+      "step": 1440
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0001598632186364608,
+      "loss": 0.6701,
+      "step": 1460
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0001590083351143407,
+      "loss": 0.6632,
+      "step": 1480
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00015815345159222056,
+      "loss": 0.6707,
+      "step": 1500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00015729856807010045,
+      "loss": 0.6738,
+      "step": 1520
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00015644368454798035,
+      "loss": 0.68,
+      "step": 1540
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00015558880102586024,
+      "loss": 0.6748,
+      "step": 1560
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00015473391750374014,
+      "loss": 0.6628,
+      "step": 1580
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00015387903398162,
+      "loss": 0.6674,
+      "step": 1600
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0001530241504594999,
+      "loss": 0.6572,
+      "step": 1620
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0001521692669373798,
+      "loss": 0.6547,
+      "step": 1640
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0001513143834152597,
+      "loss": 0.6599,
+      "step": 1660
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00015045949989313955,
+      "loss": 0.6665,
+      "step": 1680
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00014960461637101945,
+      "loss": 0.6687,
+      "step": 1700
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00014874973284889934,
+      "loss": 0.6655,
+      "step": 1720
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5166412591934204,
+      "eval_runtime": 3665.2848,
+      "eval_samples_per_second": 1.081,
+      "eval_steps_per_second": 0.36,
+      "step": 1733
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00014789484932677924,
+      "loss": 0.673,
+      "step": 1740
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00014703996580465913,
+      "loss": 0.6603,
+      "step": 1760
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00014618508228253903,
+      "loss": 0.6548,
+      "step": 1780
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0001453301987604189,
+      "loss": 0.6708,
+      "step": 1800
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0001444753152382988,
+      "loss": 0.6668,
+      "step": 1820
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00014362043171617866,
+      "loss": 0.6901,
+      "step": 1840
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00014276554819405855,
+      "loss": 0.6648,
+      "step": 1860
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00014191066467193845,
+      "loss": 0.6431,
+      "step": 1880
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00014105578114981834,
+      "loss": 0.6653,
+      "step": 1900
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00014020089762769824,
+      "loss": 0.6693,
+      "step": 1920
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00013934601410557813,
+      "loss": 0.6732,
+      "step": 1940
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00013849113058345803,
+      "loss": 0.6434,
+      "step": 1960
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00013763624706133792,
+      "loss": 0.6429,
+      "step": 1980
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0001367813635392178,
+      "loss": 0.6619,
+      "step": 2000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00013592648001709766,
+      "loss": 0.6561,
+      "step": 2020
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00013507159649497755,
+      "loss": 0.6518,
+      "step": 2040
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00013421671297285745,
+      "loss": 0.6358,
+      "step": 2060
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00013336182945073734,
+      "loss": 0.6711,
+      "step": 2080
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00013250694592861724,
+      "loss": 0.6543,
+      "step": 2100
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00013165206240649713,
+      "loss": 0.6517,
+      "step": 2120
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00013079717888437703,
+      "loss": 0.6549,
+      "step": 2140
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0001299422953622569,
+      "loss": 0.6558,
+      "step": 2160
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0001290874118401368,
+      "loss": 0.6585,
+      "step": 2180
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00012823252831801668,
+      "loss": 0.6444,
+      "step": 2200
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00012737764479589655,
+      "loss": 0.642,
+      "step": 2220
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00012652276127377645,
+      "loss": 0.6708,
+      "step": 2240
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00012566787775165634,
+      "loss": 0.653,
+      "step": 2260
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00012481299422953623,
+      "loss": 0.6438,
+      "step": 2280
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00012395811070741613,
+      "loss": 0.6296,
+      "step": 2300
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00012310322718529602,
+      "loss": 0.6376,
+      "step": 2320
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0001222483436631759,
+      "loss": 0.6284,
+      "step": 2340
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00012139346014105579,
+      "loss": 0.6373,
+      "step": 2360
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00012053857661893568,
+      "loss": 0.6289,
+      "step": 2380
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00011968369309681558,
+      "loss": 0.6421,
+      "step": 2400
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00011882880957469544,
+      "loss": 0.6385,
+      "step": 2420
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00011797392605257534,
+      "loss": 0.6312,
+      "step": 2440
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00011711904253045522,
+      "loss": 0.6454,
+      "step": 2460
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00011626415900833511,
+      "loss": 0.6476,
+      "step": 2480
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00011540927548621501,
+      "loss": 0.6373,
+      "step": 2500
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.0001145543919640949,
+      "loss": 0.647,
+      "step": 2520
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00011369950844197479,
+      "loss": 0.6319,
+      "step": 2540
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00011284462491985468,
+      "loss": 0.6506,
+      "step": 2560
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00011198974139773457,
+      "loss": 0.637,
+      "step": 2580
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00011113485787561446,
+      "loss": 0.6339,
+      "step": 2600
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00011027997435349434,
+      "loss": 0.6316,
+      "step": 2620
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00010942509083137422,
+      "loss": 0.6325,
+      "step": 2640
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00010857020730925411,
+      "loss": 0.6202,
+      "step": 2660
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.00010771532378713401,
+      "loss": 0.6219,
+      "step": 2680
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00010686044026501389,
+      "loss": 0.6367,
+      "step": 2700
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.00010600555674289378,
+      "loss": 0.6374,
+      "step": 2720
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00010515067322077368,
+      "loss": 0.6235,
+      "step": 2740
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00010429578969865357,
+      "loss": 0.626,
+      "step": 2760
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00010344090617653345,
+      "loss": 0.6325,
+      "step": 2780
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00010258602265441335,
+      "loss": 0.6425,
+      "step": 2800
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00010173113913229324,
+      "loss": 0.6344,
+      "step": 2820
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00010087625561017311,
+      "loss": 0.6208,
+      "step": 2840
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.000100021372088053,
+      "loss": 0.6339,
+      "step": 2860
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 9.916648856593289e-05,
+      "loss": 0.6348,
+      "step": 2880
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 9.831160504381278e-05,
+      "loss": 0.6193,
+      "step": 2900
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 9.745672152169268e-05,
+      "loss": 0.6283,
+      "step": 2920
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 9.660183799957256e-05,
+      "loss": 0.6314,
+      "step": 2940
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 9.574695447745245e-05,
+      "loss": 0.6373,
+      "step": 2960
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 9.489207095533233e-05,
+      "loss": 0.6437,
+      "step": 2980
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 9.403718743321223e-05,
+      "loss": 0.6433,
+      "step": 3000
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 9.318230391109212e-05,
+      "loss": 0.6238,
+      "step": 3020
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 9.2327420388972e-05,
+      "loss": 0.6237,
+      "step": 3040
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 9.14725368668519e-05,
+      "loss": 0.6388,
+      "step": 3060
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 9.06176533447318e-05,
+      "loss": 0.6422,
+      "step": 3080
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 8.976276982261168e-05,
+      "loss": 0.5997,
+      "step": 3100
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 8.890788630049156e-05,
+      "loss": 0.6265,
+      "step": 3120
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 8.805300277837145e-05,
+      "loss": 0.6298,
+      "step": 3140
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 8.719811925625135e-05,
+      "loss": 0.622,
+      "step": 3160
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 8.634323573413123e-05,
+      "loss": 0.6232,
+      "step": 3180
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 8.548835221201111e-05,
+      "loss": 0.6337,
+      "step": 3200
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 8.4633468689891e-05,
+      "loss": 0.6187,
+      "step": 3220
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 8.37785851677709e-05,
+      "loss": 0.6446,
+      "step": 3240
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 8.292370164565079e-05,
+      "loss": 0.6298,
+      "step": 3260
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 8.206881812353067e-05,
+      "loss": 0.6364,
+      "step": 3280
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 8.121393460141055e-05,
+      "loss": 0.6314,
+      "step": 3300
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 8.035905107929045e-05,
+      "loss": 0.633,
+      "step": 3320
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 7.950416755717034e-05,
+      "loss": 0.6163,
+      "step": 3340
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 7.864928403505023e-05,
+      "loss": 0.6351,
+      "step": 3360
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 7.779440051293012e-05,
+      "loss": 0.6038,
+      "step": 3380
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 7.693951699081e-05,
+      "loss": 0.6245,
+      "step": 3400
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 7.60846334686899e-05,
+      "loss": 0.6311,
+      "step": 3420
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 7.522974994656978e-05,
+      "loss": 0.6391,
+      "step": 3440
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 7.437486642444967e-05,
+      "loss": 0.6205,
+      "step": 3460
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.4947710931301117,
+      "eval_runtime": 3649.3488,
+      "eval_samples_per_second": 1.086,
+      "eval_steps_per_second": 0.362,
+      "step": 3466
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 5199,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 3.6485939432993587e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c1edc5b1bcd0355612749d7e505a9d98a74ee9056b118b0b815148f2817a927
+size 4472