Upload 12 files

Yi-1.5-9B-Chat-LoRA/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: ../../model/Yi-1.5-9B-Chat
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.10.0

Yi-1.5-9B-Chat-LoRA/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "../../model/Yi-1.5-9B-Chat",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Yi-1.5-9B-Chat-LoRA/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb59628946cf46f6da675e0a3c8cf755403db49a54e85e3af20ac31bc729241f
+size 19686264

Yi-1.5-9B-Chat-LoRA/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d17f5c1baca039db59602a5ca935d32ffa8a4a88bd76291f4635d8fda23c713
+size 39482810

Yi-1.5-9B-Chat-LoRA/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55f6ef5fd81f87dc8a69f1b9a751ba37cc49c37318322e45ba4733ff23a92208
+size 14512

Yi-1.5-9B-Chat-LoRA/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f510db96e40d7f66609c96cf485c13417fc4eaf253603d2b6591466c3fb5f63a
+size 14512

Yi-1.5-9B-Chat-LoRA/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e147b5d4cbad0fb2ad49d465222adf18aab8e828f7d056a3874291f92779ae3d
+size 1064

Yi-1.5-9B-Chat-LoRA/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Yi-1.5-9B-Chat-LoRA/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

Yi-1.5-9B-Chat-LoRA/tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

Yi-1.5-9B-Chat-LoRA/trainer_state.json

@@ -0,0 +1,2093 @@
+{
+  "best_metric": 2.2857470512390137,
+  "best_model_checkpoint": "../../saves/Yi-1.5-9B-Chat/lora/sft/checkpoint-2800",
+  "epoch": 4.148148148148148,
+  "eval_steps": 200,
+  "global_step": 2800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "grad_norm": 11.507218360900879,
+      "learning_rate": 2e-05,
+      "loss": 3.995,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 7.0516510009765625,
+      "learning_rate": 4.5e-05,
+      "loss": 3.8373,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 5.1662492752075195,
+      "learning_rate": 4.999929854041747e-05,
+      "loss": 3.4376,
+      "step": 30
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.265901565551758,
+      "learning_rate": 4.999644892832738e-05,
+      "loss": 3.0327,
+      "step": 40
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.507016658782959,
+      "learning_rate": 4.999140757217391e-05,
+      "loss": 2.7494,
+      "step": 50
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 3.204484462738037,
+      "learning_rate": 4.9984174913994355e-05,
+      "loss": 2.6219,
+      "step": 60
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.585574746131897,
+      "learning_rate": 4.9974751587964214e-05,
+      "loss": 2.6297,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.005038261413574,
+      "learning_rate": 4.9963138420341604e-05,
+      "loss": 2.6139,
+      "step": 80
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 2.9263103008270264,
+      "learning_rate": 4.994933642939482e-05,
+      "loss": 2.6403,
+      "step": 90
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 2.398559331893921,
+      "learning_rate": 4.993334682531302e-05,
+      "loss": 2.7009,
+      "step": 100
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.3030171394348145,
+      "learning_rate": 4.991517101010015e-05,
+      "loss": 2.9349,
+      "step": 110
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.3386640548706055,
+      "learning_rate": 4.9894810577451975e-05,
+      "loss": 2.2748,
+      "step": 120
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.8978828191757202,
+      "learning_rate": 4.9872267312616384e-05,
+      "loss": 2.3982,
+      "step": 130
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 2.644758939743042,
+      "learning_rate": 4.9847543192236815e-05,
+      "loss": 2.4243,
+      "step": 140
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.887523889541626,
+      "learning_rate": 4.9820640384178954e-05,
+      "loss": 2.5096,
+      "step": 150
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.8633583784103394,
+      "learning_rate": 4.9791561247340674e-05,
+      "loss": 2.3775,
+      "step": 160
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 2.8847458362579346,
+      "learning_rate": 4.976030833144516e-05,
+      "loss": 2.2988,
+      "step": 170
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.756564974784851,
+      "learning_rate": 4.972688437681736e-05,
+      "loss": 2.3573,
+      "step": 180
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 4.001959800720215,
+      "learning_rate": 4.969129231414374e-05,
+      "loss": 2.5404,
+      "step": 190
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.489682674407959,
+      "learning_rate": 4.9653535264215256e-05,
+      "loss": 2.5707,
+      "step": 200
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 2.391483783721924,
+      "eval_runtime": 96.186,
+      "eval_samples_per_second": 6.238,
+      "eval_steps_per_second": 3.119,
+      "step": 200
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 2.316711187362671,
+      "learning_rate": 4.961361653765377e-05,
+      "loss": 2.5629,
+      "step": 210
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 2.2436294555664062,
+      "learning_rate": 4.957153963462172e-05,
+      "loss": 2.3062,
+      "step": 220
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.6833086013793945,
+      "learning_rate": 4.952730824451527e-05,
+      "loss": 2.4841,
+      "step": 230
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.4797868728637695,
+      "learning_rate": 4.9480926245640754e-05,
+      "loss": 2.4149,
+      "step": 240
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 2.539104700088501,
+      "learning_rate": 4.943239770487469e-05,
+      "loss": 2.5375,
+      "step": 250
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 2.656684637069702,
+      "learning_rate": 4.9381726877307124e-05,
+      "loss": 2.58,
+      "step": 260
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.8903274536132812,
+      "learning_rate": 4.9328918205868556e-05,
+      "loss": 2.36,
+      "step": 270
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 3.5389297008514404,
+      "learning_rate": 4.927397632094039e-05,
+      "loss": 2.4487,
+      "step": 280
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 2.3600199222564697,
+      "learning_rate": 4.9216906039948896e-05,
+      "loss": 2.5569,
+      "step": 290
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.797351837158203,
+      "learning_rate": 4.915771236694286e-05,
+      "loss": 2.5081,
+      "step": 300
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.2043402194976807,
+      "learning_rate": 4.909640049215478e-05,
+      "loss": 2.6873,
+      "step": 310
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 2.070732831954956,
+      "learning_rate": 4.903297579154577e-05,
+      "loss": 2.4935,
+      "step": 320
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 2.1852307319641113,
+      "learning_rate": 4.896744382633419e-05,
+      "loss": 2.4865,
+      "step": 330
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.5772058963775635,
+      "learning_rate": 4.889981034250807e-05,
+      "loss": 2.3605,
+      "step": 340
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.855281114578247,
+      "learning_rate": 4.883008127032121e-05,
+      "loss": 2.6443,
+      "step": 350
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 2.7813808917999268,
+      "learning_rate": 4.8758262723773255e-05,
+      "loss": 2.2597,
+      "step": 360
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 3.336205244064331,
+      "learning_rate": 4.86843610000736e-05,
+      "loss": 2.4404,
+      "step": 370
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.562402367591858,
+      "learning_rate": 4.860838257908925e-05,
+      "loss": 2.3216,
+      "step": 380
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.9673439264297485,
+      "learning_rate": 4.85303341227766e-05,
+      "loss": 2.3308,
+      "step": 390
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 2.689194440841675,
+      "learning_rate": 4.845022247459736e-05,
+      "loss": 2.5978,
+      "step": 400
+    },
+    {
+      "epoch": 0.59,
+      "eval_loss": 2.3469619750976562,
+      "eval_runtime": 96.7403,
+      "eval_samples_per_second": 6.202,
+      "eval_steps_per_second": 3.101,
+      "step": 400
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 2.1179988384246826,
+      "learning_rate": 4.836805465891844e-05,
+      "loss": 2.679,
+      "step": 410
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.770677089691162,
+      "learning_rate": 4.828383788039611e-05,
+      "loss": 2.3037,
+      "step": 420
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.4875175952911377,
+      "learning_rate": 4.819757952334425e-05,
+      "loss": 2.1605,
+      "step": 430
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 2.146296501159668,
+      "learning_rate": 4.810928715108683e-05,
+      "loss": 2.4998,
+      "step": 440
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.9566316604614258,
+      "learning_rate": 4.801896850529482e-05,
+      "loss": 2.6092,
+      "step": 450
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.384901285171509,
+      "learning_rate": 4.792663150530733e-05,
+      "loss": 2.5815,
+      "step": 460
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.225851535797119,
+      "learning_rate": 4.783228424743726e-05,
+      "loss": 2.3677,
+      "step": 470
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 2.222594976425171,
+      "learning_rate": 4.773593500426134e-05,
+      "loss": 2.3782,
+      "step": 480
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.6287986040115356,
+      "learning_rate": 4.763759222389487e-05,
+      "loss": 2.4165,
+      "step": 490
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.4728448390960693,
+      "learning_rate": 4.7537264529250835e-05,
+      "loss": 2.3643,
+      "step": 500
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.7345590591430664,
+      "learning_rate": 4.743496071728396e-05,
+      "loss": 2.4526,
+      "step": 510
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.9642170667648315,
+      "learning_rate": 4.7330689758219314e-05,
+      "loss": 2.3306,
+      "step": 520
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 2.757434368133545,
+      "learning_rate": 4.722446079476576e-05,
+      "loss": 2.5495,
+      "step": 530
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.5214667320251465,
+      "learning_rate": 4.711628314131436e-05,
+      "loss": 2.5145,
+      "step": 540
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 2.977623462677002,
+      "learning_rate": 4.700616628312158e-05,
+      "loss": 2.4552,
+      "step": 550
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 3.109473466873169,
+      "learning_rate": 4.689411987547773e-05,
+      "loss": 2.4047,
+      "step": 560
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.7021738290786743,
+      "learning_rate": 4.678015374286025e-05,
+      "loss": 2.5649,
+      "step": 570
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 2.258920669555664,
+      "learning_rate": 4.666427787807232e-05,
+      "loss": 2.5556,
+      "step": 580
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 2.1758129596710205,
+      "learning_rate": 4.654650244136669e-05,
+      "loss": 2.4234,
+      "step": 590
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 2.581289529800415,
+      "learning_rate": 4.642683775955476e-05,
+      "loss": 2.5284,
+      "step": 600
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 2.327061414718628,
+      "eval_runtime": 96.1253,
+      "eval_samples_per_second": 6.242,
+      "eval_steps_per_second": 3.121,
+      "step": 600
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 3.0182411670684814,
+      "learning_rate": 4.630529432510118e-05,
+      "loss": 2.3928,
+      "step": 610
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.1703760623931885,
+      "learning_rate": 4.618188279520374e-05,
+      "loss": 2.675,
+      "step": 620
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 2.2590174674987793,
+      "learning_rate": 4.6056613990859024e-05,
+      "loss": 2.4192,
+      "step": 630
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 3.697880744934082,
+      "learning_rate": 4.5929498895913514e-05,
+      "loss": 2.1851,
+      "step": 640
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.6290298700332642,
+      "learning_rate": 4.580054865610059e-05,
+      "loss": 2.452,
+      "step": 650
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 2.1037967205047607,
+      "learning_rate": 4.5669774578063174e-05,
+      "loss": 2.368,
+      "step": 660
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 3.8899028301239014,
+      "learning_rate": 4.5537188128362384e-05,
+      "loss": 2.4681,
+      "step": 670
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 2.6862452030181885,
+      "learning_rate": 4.54028009324721e-05,
+      "loss": 2.5741,
+      "step": 680
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 2.2980988025665283,
+      "learning_rate": 4.52666247737596e-05,
+      "loss": 2.3131,
+      "step": 690
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 2.9786365032196045,
+      "learning_rate": 4.512867159245242e-05,
+      "loss": 2.4059,
+      "step": 700
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 2.39225435256958,
+      "learning_rate": 4.498895348459135e-05,
+      "loss": 2.3781,
+      "step": 710
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 1.9918076992034912,
+      "learning_rate": 4.484748270096988e-05,
+      "loss": 2.399,
+      "step": 720
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 2.9783575534820557,
+      "learning_rate": 4.470427164605997e-05,
+      "loss": 2.4341,
+      "step": 730
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 1.9173182249069214,
+      "learning_rate": 4.455933287692444e-05,
+      "loss": 2.3917,
+      "step": 740
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 5.648810863494873,
+      "learning_rate": 4.441267910211594e-05,
+      "loss": 2.6513,
+      "step": 750
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 4.045050144195557,
+      "learning_rate": 4.4264323180562574e-05,
+      "loss": 2.5065,
+      "step": 760
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 3.8237059116363525,
+      "learning_rate": 4.411427812044049e-05,
+      "loss": 2.3481,
+      "step": 770
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 2.632697582244873,
+      "learning_rate": 4.396255707803323e-05,
+      "loss": 2.445,
+      "step": 780
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 3.1144275665283203,
+      "learning_rate": 4.3809173356578184e-05,
+      "loss": 2.3096,
+      "step": 790
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 1.7161847352981567,
+      "learning_rate": 4.3654140405100116e-05,
+      "loss": 2.4712,
+      "step": 800
+    },
+    {
+      "epoch": 1.19,
+      "eval_loss": 2.317145824432373,
+      "eval_runtime": 96.3893,
+      "eval_samples_per_second": 6.225,
+      "eval_steps_per_second": 3.112,
+      "step": 800
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 2.709351062774658,
+      "learning_rate": 4.349747181723197e-05,
+      "loss": 2.4706,
+      "step": 810
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 2.301166534423828,
+      "learning_rate": 4.3339181330022876e-05,
+      "loss": 2.5085,
+      "step": 820
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 2.3112149238586426,
+      "learning_rate": 4.3179282822733706e-05,
+      "loss": 2.3204,
+      "step": 830
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 1.850696325302124,
+      "learning_rate": 4.301779031562011e-05,
+      "loss": 2.4174,
+      "step": 840
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 2.511995315551758,
+      "learning_rate": 4.285471796870316e-05,
+      "loss": 2.3967,
+      "step": 850
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 3.4540021419525146,
+      "learning_rate": 4.26900800805278e-05,
+      "loss": 2.2189,
+      "step": 860
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 3.0399599075317383,
+      "learning_rate": 4.252389108690909e-05,
+      "loss": 2.4208,
+      "step": 870
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 2.1426591873168945,
+      "learning_rate": 4.235616555966645e-05,
+      "loss": 2.479,
+      "step": 880
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 2.262714147567749,
+      "learning_rate": 4.218691820534601e-05,
+      "loss": 2.5144,
+      "step": 890
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 2.40321683883667,
+      "learning_rate": 4.201616386393102e-05,
+      "loss": 2.332,
+      "step": 900
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 2.4343059062957764,
+      "learning_rate": 4.184391750754075e-05,
+      "loss": 2.4799,
+      "step": 910
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 2.6487956047058105,
+      "learning_rate": 4.167019423911761e-05,
+      "loss": 2.4492,
+      "step": 920
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 3.0731077194213867,
+      "learning_rate": 4.149500929110295e-05,
+      "loss": 2.4789,
+      "step": 930
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 2.791496515274048,
+      "learning_rate": 4.1318378024101435e-05,
+      "loss": 2.2895,
+      "step": 940
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 2.860171318054199,
+      "learning_rate": 4.114031592553417e-05,
+      "loss": 2.3098,
+      "step": 950
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 2.6719272136688232,
+      "learning_rate": 4.096083860828076e-05,
+      "loss": 2.2381,
+      "step": 960
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 3.2551610469818115,
+      "learning_rate": 4.07799618093103e-05,
+      "loss": 2.4553,
+      "step": 970
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 2.201517105102539,
+      "learning_rate": 4.059770138830157e-05,
+      "loss": 2.4248,
+      "step": 980
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 3.5828166007995605,
+      "learning_rate": 4.041407332625238e-05,
+      "loss": 2.3741,
+      "step": 990
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 2.608720064163208,
+      "learning_rate": 4.022909372407835e-05,
+      "loss": 2.4542,
+      "step": 1000
+    },
+    {
+      "epoch": 1.48,
+      "eval_loss": 2.308347463607788,
+      "eval_runtime": 96.2879,
+      "eval_samples_per_second": 6.231,
+      "eval_steps_per_second": 3.116,
+      "step": 1000
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 2.607658624649048,
+      "learning_rate": 4.004277880120113e-05,
+      "loss": 2.5501,
+      "step": 1010
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 2.599700450897217,
+      "learning_rate": 3.9855144894126235e-05,
+      "loss": 2.2606,
+      "step": 1020
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 2.6854465007781982,
+      "learning_rate": 3.966620845501067e-05,
+      "loss": 2.3407,
+      "step": 1030
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 2.488729476928711,
+      "learning_rate": 3.9475986050220314e-05,
+      "loss": 2.4184,
+      "step": 1040
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 2.6692395210266113,
+      "learning_rate": 3.928449435887737e-05,
+      "loss": 2.4879,
+      "step": 1050
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 2.208466053009033,
+      "learning_rate": 3.909175017139791e-05,
+      "loss": 2.2039,
+      "step": 1060
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 2.5494725704193115,
+      "learning_rate": 3.889777038801964e-05,
+      "loss": 2.3029,
+      "step": 1070
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.0070173740386963,
+      "learning_rate": 3.870257201732005e-05,
+      "loss": 2.3363,
+      "step": 1080
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 2.75435209274292,
+      "learning_rate": 3.8506172174725066e-05,
+      "loss": 2.2523,
+      "step": 1090
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 2.6911637783050537,
+      "learning_rate": 3.830858808100834e-05,
+      "loss": 2.4057,
+      "step": 1100
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 3.0497798919677734,
+      "learning_rate": 3.810983706078131e-05,
+      "loss": 2.2635,
+      "step": 1110
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 3.2239983081817627,
+      "learning_rate": 3.790993654097405e-05,
+      "loss": 2.3918,
+      "step": 1120
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 2.4736838340759277,
+      "learning_rate": 3.770890404930738e-05,
+      "loss": 2.3823,
+      "step": 1130
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 2.585200548171997,
+      "learning_rate": 3.7506757212755886e-05,
+      "loss": 2.3349,
+      "step": 1140
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 2.8950488567352295,
+      "learning_rate": 3.730351375600239e-05,
+      "loss": 2.2586,
+      "step": 1150
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 2.7123405933380127,
+      "learning_rate": 3.7099191499883806e-05,
+      "loss": 2.309,
+      "step": 1160
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 2.049273729324341,
+      "learning_rate": 3.6893808359828565e-05,
+      "loss": 2.3608,
+      "step": 1170
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 2.6950619220733643,
+      "learning_rate": 3.668738234428575e-05,
+      "loss": 2.4085,
+      "step": 1180
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 3.231593370437622,
+      "learning_rate": 3.64799315531461e-05,
+      "loss": 2.2365,
+      "step": 1190
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 3.310612201690674,
+      "learning_rate": 3.627147417615493e-05,
+      "loss": 2.3518,
+      "step": 1200
+    },
+    {
+      "epoch": 1.78,
+      "eval_loss": 2.2971346378326416,
+      "eval_runtime": 96.9315,
+      "eval_samples_per_second": 6.19,
+      "eval_steps_per_second": 3.095,
+      "step": 1200
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 2.5581092834472656,
+      "learning_rate": 3.606202849131723e-05,
+      "loss": 2.2343,
+      "step": 1210
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 2.7495291233062744,
+      "learning_rate": 3.585161286329503e-05,
+      "loss": 2.3144,
+      "step": 1220
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 1.433355689048767,
+      "learning_rate": 3.564024574179713e-05,
+      "loss": 2.4354,
+      "step": 1230
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 1.7245852947235107,
+      "learning_rate": 3.542794565996137e-05,
+      "loss": 2.405,
+      "step": 1240
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 2.598426103591919,
+      "learning_rate": 3.5214731232729626e-05,
+      "loss": 2.4057,
+      "step": 1250
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 2.4231202602386475,
+      "learning_rate": 3.500062115521562e-05,
+      "loss": 2.233,
+      "step": 1260
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 2.9336726665496826,
+      "learning_rate": 3.478563420106565e-05,
+      "loss": 2.5745,
+      "step": 1270
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 2.057365655899048,
+      "learning_rate": 3.4569789220812544e-05,
+      "loss": 2.4635,
+      "step": 1280
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 1.8743510246276855,
+      "learning_rate": 3.435310514022272e-05,
+      "loss": 2.3892,
+      "step": 1290
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 2.422725200653076,
+      "learning_rate": 3.4135600958636794e-05,
+      "loss": 2.4463,
+      "step": 1300
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 2.9806418418884277,
+      "learning_rate": 3.391729574730365e-05,
+      "loss": 2.2907,
+      "step": 1310
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 2.656452178955078,
+      "learning_rate": 3.369820864770822e-05,
+      "loss": 2.55,
+      "step": 1320
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 1.4007813930511475,
+      "learning_rate": 3.347835886989318e-05,
+      "loss": 2.4001,
+      "step": 1330
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 2.9661433696746826,
+      "learning_rate": 3.3257765690774474e-05,
+      "loss": 2.2728,
+      "step": 1340
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.8605289459228516,
+      "learning_rate": 3.303644845245114e-05,
+      "loss": 2.4102,
+      "step": 1350
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 2.4378559589385986,
+      "learning_rate": 3.2814426560509335e-05,
+      "loss": 2.3268,
+      "step": 1360
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 2.231828212738037,
+      "learning_rate": 3.259171948232081e-05,
+      "loss": 2.265,
+      "step": 1370
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 3.6883370876312256,
+      "learning_rate": 3.236834674533595e-05,
+      "loss": 2.3077,
+      "step": 1380
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 2.531064510345459,
+      "learning_rate": 3.214432793537159e-05,
+      "loss": 2.2186,
+      "step": 1390
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 3.7311625480651855,
+      "learning_rate": 3.1919682694893676e-05,
+      "loss": 2.3739,
+      "step": 1400
+    },
+    {
+      "epoch": 2.07,
+      "eval_loss": 2.2983055114746094,
+      "eval_runtime": 97.4749,
+      "eval_samples_per_second": 6.155,
+      "eval_steps_per_second": 3.078,
+      "step": 1400
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 2.1773197650909424,
+      "learning_rate": 3.169443072129498e-05,
+      "loss": 2.3585,
+      "step": 1410
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 3.2135908603668213,
+      "learning_rate": 3.146859176516795e-05,
+      "loss": 2.4114,
+      "step": 1420
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 2.469650983810425,
+      "learning_rate": 3.1242185628573e-05,
+      "loss": 2.4616,
+      "step": 1430
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 3.1853158473968506,
+      "learning_rate": 3.101523216330216e-05,
+      "loss": 2.4351,
+      "step": 1440
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 3.484740972518921,
+      "learning_rate": 3.0787751269138454e-05,
+      "loss": 2.4084,
+      "step": 1450
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 2.925419330596924,
+      "learning_rate": 3.055976289211105e-05,
+      "loss": 2.3629,
+      "step": 1460
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 2.416266918182373,
+      "learning_rate": 3.033128702274634e-05,
+      "loss": 2.3339,
+      "step": 1470
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 2.828092575073242,
+      "learning_rate": 3.010234369431511e-05,
+      "loss": 2.2583,
+      "step": 1480
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 2.0409436225891113,
+      "learning_rate": 2.9872952981076008e-05,
+      "loss": 2.0624,
+      "step": 1490
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 2.849675416946411,
+      "learning_rate": 2.9643134996515364e-05,
+      "loss": 2.3726,
+      "step": 1500
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 4.13971471786499,
+      "learning_rate": 2.9412909891583613e-05,
+      "loss": 2.2965,
+      "step": 1510
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 3.702918529510498,
+      "learning_rate": 2.9182297852928407e-05,
+      "loss": 2.4658,
+      "step": 1520
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 3.2200419902801514,
+      "learning_rate": 2.8951319101124598e-05,
+      "loss": 2.4594,
+      "step": 1530
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 2.465409517288208,
+      "learning_rate": 2.8719993888901258e-05,
+      "loss": 2.4301,
+      "step": 1540
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 2.5337352752685547,
+      "learning_rate": 2.848834249936589e-05,
+      "loss": 2.3253,
+      "step": 1550
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 3.3071987628936768,
+      "learning_rate": 2.8256385244225926e-05,
+      "loss": 2.6393,
+      "step": 1560
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 2.4905800819396973,
+      "learning_rate": 2.802414246200781e-05,
+      "loss": 2.1755,
+      "step": 1570
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 2.8511528968811035,
+      "learning_rate": 2.7791634516273574e-05,
+      "loss": 2.2376,
+      "step": 1580
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 2.7542080879211426,
+      "learning_rate": 2.755888179383543e-05,
+      "loss": 2.3509,
+      "step": 1590
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 3.257232189178467,
+      "learning_rate": 2.7325904702968137e-05,
+      "loss": 2.2619,
+      "step": 1600
+    },
+    {
+      "epoch": 2.37,
+      "eval_loss": 2.294617176055908,
+      "eval_runtime": 98.0772,
+      "eval_samples_per_second": 6.118,
+      "eval_steps_per_second": 3.059,
+      "step": 1600
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 2.707037925720215,
+      "learning_rate": 2.7092723671619565e-05,
+      "loss": 2.4258,
+      "step": 1610
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 3.6930806636810303,
+      "learning_rate": 2.685935914561954e-05,
+      "loss": 2.3555,
+      "step": 1620
+    },
+    {
+      "epoch": 2.41,
+      "grad_norm": 1.9949381351470947,
+      "learning_rate": 2.6625831586887116e-05,
+      "loss": 2.3908,
+      "step": 1630
+    },
+    {
+      "epoch": 2.43,
+      "grad_norm": 2.457606554031372,
+      "learning_rate": 2.6392161471636413e-05,
+      "loss": 2.2989,
+      "step": 1640
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 2.2386317253112793,
+      "learning_rate": 2.615836928858122e-05,
+      "loss": 2.6807,
+      "step": 1650
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 2.672177791595459,
+      "learning_rate": 2.5924475537138497e-05,
+      "loss": 2.1579,
+      "step": 1660
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 4.241297721862793,
+      "learning_rate": 2.569050072563097e-05,
+      "loss": 2.0706,
+      "step": 1670
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 2.5108397006988525,
+      "learning_rate": 2.5456465369488864e-05,
+      "loss": 2.4219,
+      "step": 1680
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 2.7684569358825684,
+      "learning_rate": 2.5222389989451096e-05,
+      "loss": 2.2234,
+      "step": 1690
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 3.104278087615967,
+      "learning_rate": 2.4988295109765972e-05,
+      "loss": 2.3018,
+      "step": 1700
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 3.235226631164551,
+      "learning_rate": 2.4754201256391585e-05,
+      "loss": 2.364,
+      "step": 1710
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 2.1415085792541504,
+      "learning_rate": 2.4520128955196008e-05,
+      "loss": 2.3683,
+      "step": 1720
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 2.5002896785736084,
+      "learning_rate": 2.42860987301576e-05,
+      "loss": 2.4247,
+      "step": 1730
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 2.8159451484680176,
+      "learning_rate": 2.4052131101565364e-05,
+      "loss": 2.3574,
+      "step": 1740
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 3.0876357555389404,
+      "learning_rate": 2.3818246584219726e-05,
+      "loss": 2.2649,
+      "step": 1750
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 2.8891026973724365,
+      "learning_rate": 2.3584465685633738e-05,
+      "loss": 2.4012,
+      "step": 1760
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 2.3504886627197266,
+      "learning_rate": 2.335080890423491e-05,
+      "loss": 2.3263,
+      "step": 1770
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 2.84779691696167,
+      "learning_rate": 2.3117296727567897e-05,
+      "loss": 2.4177,
+      "step": 1780
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 2.4880871772766113,
+      "learning_rate": 2.288394963049807e-05,
+      "loss": 2.3029,
+      "step": 1790
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 2.4965240955352783,
+      "learning_rate": 2.2650788073416293e-05,
+      "loss": 2.2876,
+      "step": 1800
+    },
+    {
+      "epoch": 2.67,
+      "eval_loss": 2.287304401397705,
+      "eval_runtime": 97.8793,
+      "eval_samples_per_second": 6.13,
+      "eval_steps_per_second": 3.065,
+      "step": 1800
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 3.6506803035736084,
+      "learning_rate": 2.2417832500444827e-05,
+      "loss": 2.2686,
+      "step": 1810
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 2.156888008117676,
+      "learning_rate": 2.2185103337644833e-05,
+      "loss": 2.4572,
+      "step": 1820
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 2.9049007892608643,
+      "learning_rate": 2.1952620991225285e-05,
+      "loss": 2.4824,
+      "step": 1830
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 3.4357845783233643,
+      "learning_rate": 2.1720405845753792e-05,
+      "loss": 2.3334,
+      "step": 1840
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 2.405451774597168,
+      "learning_rate": 2.148847826236914e-05,
+      "loss": 2.4271,
+      "step": 1850
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 2.0909016132354736,
+      "learning_rate": 2.125685857699609e-05,
+      "loss": 2.3499,
+      "step": 1860
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 3.3600564002990723,
+      "learning_rate": 2.1025567098562177e-05,
+      "loss": 2.2665,
+      "step": 1870
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 3.0894439220428467,
+      "learning_rate": 2.0794624107217056e-05,
+      "loss": 2.3211,
+      "step": 1880
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 2.564870834350586,
+      "learning_rate": 2.056404985255424e-05,
+      "loss": 2.3905,
+      "step": 1890
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 2.177769422531128,
+      "learning_rate": 2.0333864551835602e-05,
+      "loss": 2.4703,
+      "step": 1900
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 2.499175548553467,
+      "learning_rate": 2.010408838821866e-05,
+      "loss": 2.3287,
+      "step": 1910
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 3.076934337615967,
+      "learning_rate": 1.987474150898691e-05,
+      "loss": 2.3857,
+      "step": 1920
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 5.456985950469971,
+      "learning_rate": 1.9645844023783206e-05,
+      "loss": 2.3238,
+      "step": 1930
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 2.502319574356079,
+      "learning_rate": 1.941741600284656e-05,
+      "loss": 2.3027,
+      "step": 1940
+    },
+    {
+      "epoch": 2.89,
+      "grad_norm": 3.1800990104675293,
+      "learning_rate": 1.918947747525232e-05,
+      "loss": 2.086,
+      "step": 1950
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 3.400146245956421,
+      "learning_rate": 1.896204842715596e-05,
+      "loss": 2.5469,
+      "step": 1960
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 2.4540586471557617,
+      "learning_rate": 1.873514880004065e-05,
+      "loss": 2.2501,
+      "step": 1970
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 3.094639778137207,
+      "learning_rate": 1.8508798488968803e-05,
+      "loss": 2.3037,
+      "step": 1980
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 2.7142815589904785,
+      "learning_rate": 1.8283017340837517e-05,
+      "loss": 2.2974,
+      "step": 1990
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 2.40388560295105,
+      "learning_rate": 1.8057825152638478e-05,
+      "loss": 2.2484,
+      "step": 2000
+    },
+    {
+      "epoch": 2.96,
+      "eval_loss": 2.2887699604034424,
+      "eval_runtime": 100.5569,
+      "eval_samples_per_second": 5.967,
+      "eval_steps_per_second": 2.983,
+      "step": 2000
+    },
+    {
+      "epoch": 2.98,
+      "grad_norm": 3.5946638584136963,
+      "learning_rate": 1.7833241669722015e-05,
+      "loss": 2.2191,
+      "step": 2010
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 3.1359758377075195,
+      "learning_rate": 1.760928658406587e-05,
+      "loss": 2.4429,
+      "step": 2020
+    },
+    {
+      "epoch": 3.01,
+      "grad_norm": 3.105003833770752,
+      "learning_rate": 1.738597953254848e-05,
+      "loss": 2.3241,
+      "step": 2030
+    },
+    {
+      "epoch": 3.02,
+      "grad_norm": 2.3050458431243896,
+      "learning_rate": 1.716334009522726e-05,
+      "loss": 2.3608,
+      "step": 2040
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 2.2272346019744873,
+      "learning_rate": 1.6941387793621673e-05,
+      "loss": 2.3107,
+      "step": 2050
+    },
+    {
+      "epoch": 3.05,
+      "grad_norm": 2.0482161045074463,
+      "learning_rate": 1.672014208900165e-05,
+      "loss": 2.1823,
+      "step": 2060
+    },
+    {
+      "epoch": 3.07,
+      "grad_norm": 2.0835390090942383,
+      "learning_rate": 1.6499622380681096e-05,
+      "loss": 2.1622,
+      "step": 2070
+    },
+    {
+      "epoch": 3.08,
+      "grad_norm": 3.687225103378296,
+      "learning_rate": 1.6279848004316972e-05,
+      "loss": 2.3643,
+      "step": 2080
+    },
+    {
+      "epoch": 3.1,
+      "grad_norm": 3.2139699459075928,
+      "learning_rate": 1.6060838230213883e-05,
+      "loss": 2.2241,
+      "step": 2090
+    },
+    {
+      "epoch": 3.11,
+      "grad_norm": 3.513046979904175,
+      "learning_rate": 1.5842612261634392e-05,
+      "loss": 2.311,
+      "step": 2100
+    },
+    {
+      "epoch": 3.13,
+      "grad_norm": 2.698282241821289,
+      "learning_rate": 1.5625189233115282e-05,
+      "loss": 2.4009,
+      "step": 2110
+    },
+    {
+      "epoch": 3.14,
+      "grad_norm": 2.889256238937378,
+      "learning_rate": 1.5408588208789733e-05,
+      "loss": 2.2708,
+      "step": 2120
+    },
+    {
+      "epoch": 3.16,
+      "grad_norm": 2.4953372478485107,
+      "learning_rate": 1.5192828180715824e-05,
+      "loss": 2.2726,
+      "step": 2130
+    },
+    {
+      "epoch": 3.17,
+      "grad_norm": 3.368839740753174,
+      "learning_rate": 1.4977928067211178e-05,
+      "loss": 2.0851,
+      "step": 2140
+    },
+    {
+      "epoch": 3.19,
+      "grad_norm": 3.3648414611816406,
+      "learning_rate": 1.4763906711194229e-05,
+      "loss": 2.11,
+      "step": 2150
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 2.7509853839874268,
+      "learning_rate": 1.4550782878531972e-05,
+      "loss": 2.3487,
+      "step": 2160
+    },
+    {
+      "epoch": 3.21,
+      "grad_norm": 3.071002721786499,
+      "learning_rate": 1.4338575256394612e-05,
+      "loss": 2.2536,
+      "step": 2170
+    },
+    {
+      "epoch": 3.23,
+      "grad_norm": 2.7192609310150146,
+      "learning_rate": 1.4127302451616936e-05,
+      "loss": 2.2367,
+      "step": 2180
+    },
+    {
+      "epoch": 3.24,
+      "grad_norm": 5.182852268218994,
+      "learning_rate": 1.3916982989066915e-05,
+      "loss": 2.0933,
+      "step": 2190
+    },
+    {
+      "epoch": 3.26,
+      "grad_norm": 2.816575527191162,
+      "learning_rate": 1.370763531002132e-05,
+      "loss": 2.4534,
+      "step": 2200
+    },
+    {
+      "epoch": 3.26,
+      "eval_loss": 2.2867271900177,
+      "eval_runtime": 98.3879,
+      "eval_samples_per_second": 6.098,
+      "eval_steps_per_second": 3.049,
+      "step": 2200
+    },
+    {
+      "epoch": 3.27,
+      "grad_norm": 2.238353967666626,
+      "learning_rate": 1.3499277770548823e-05,
+      "loss": 2.3927,
+      "step": 2210
+    },
+    {
+      "epoch": 3.29,
+      "grad_norm": 3.0616304874420166,
+      "learning_rate": 1.3291928639900436e-05,
+      "loss": 2.3978,
+      "step": 2220
+    },
+    {
+      "epoch": 3.3,
+      "grad_norm": 3.807537317276001,
+      "learning_rate": 1.3085606098907682e-05,
+      "loss": 2.1303,
+      "step": 2230
+    },
+    {
+      "epoch": 3.32,
+      "grad_norm": 3.6472954750061035,
+      "learning_rate": 1.2880328238388393e-05,
+      "loss": 2.3277,
+      "step": 2240
+    },
+    {
+      "epoch": 3.33,
+      "grad_norm": 3.634000301361084,
+      "learning_rate": 1.2676113057560515e-05,
+      "loss": 2.358,
+      "step": 2250
+    },
+    {
+      "epoch": 3.35,
+      "grad_norm": 5.468724727630615,
+      "learning_rate": 1.2472978462463874e-05,
+      "loss": 2.4583,
+      "step": 2260
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 3.201179265975952,
+      "learning_rate": 1.2270942264390174e-05,
+      "loss": 2.2543,
+      "step": 2270
+    },
+    {
+      "epoch": 3.38,
+      "grad_norm": 2.4082183837890625,
+      "learning_rate": 1.2070022178321186e-05,
+      "loss": 2.2401,
+      "step": 2280
+    },
+    {
+      "epoch": 3.39,
+      "grad_norm": 3.068176031112671,
+      "learning_rate": 1.1870235821375553e-05,
+      "loss": 2.3446,
+      "step": 2290
+    },
+    {
+      "epoch": 3.41,
+      "grad_norm": 2.7859139442443848,
+      "learning_rate": 1.1671600711263991e-05,
+      "loss": 2.3761,
+      "step": 2300
+    },
+    {
+      "epoch": 3.42,
+      "grad_norm": 2.423513650894165,
+      "learning_rate": 1.1474134264753384e-05,
+      "loss": 2.2563,
+      "step": 2310
+    },
+    {
+      "epoch": 3.44,
+      "grad_norm": 3.0830302238464355,
+      "learning_rate": 1.1277853796139554e-05,
+      "loss": 2.2455,
+      "step": 2320
+    },
+    {
+      "epoch": 3.45,
+      "grad_norm": 3.237128734588623,
+      "learning_rate": 1.1082776515729201e-05,
+      "loss": 2.3861,
+      "step": 2330
+    },
+    {
+      "epoch": 3.47,
+      "grad_norm": 2.9493908882141113,
+      "learning_rate": 1.0888919528330777e-05,
+      "loss": 2.0657,
+      "step": 2340
+    },
+    {
+      "epoch": 3.48,
+      "grad_norm": 3.7209978103637695,
+      "learning_rate": 1.0696299831754753e-05,
+      "loss": 2.4492,
+      "step": 2350
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 2.332671880722046,
+      "learning_rate": 1.0504934315323181e-05,
+      "loss": 2.3108,
+      "step": 2360
+    },
+    {
+      "epoch": 3.51,
+      "grad_norm": 3.0048203468322754,
+      "learning_rate": 1.0314839758388859e-05,
+      "loss": 2.5104,
+      "step": 2370
+    },
+    {
+      "epoch": 3.53,
+      "grad_norm": 3.380918502807617,
+      "learning_rate": 1.0126032828863982e-05,
+      "loss": 2.3024,
+      "step": 2380
+    },
+    {
+      "epoch": 3.54,
+      "grad_norm": 2.693096876144409,
+      "learning_rate": 9.938530081758764e-06,
+      "loss": 2.3422,
+      "step": 2390
+    },
+    {
+      "epoch": 3.56,
+      "grad_norm": 2.64311146736145,
+      "learning_rate": 9.752347957729804e-06,
+      "loss": 2.3934,
+      "step": 2400
+    },
+    {
+      "epoch": 3.56,
+      "eval_loss": 2.2875092029571533,
+      "eval_runtime": 98.3803,
+      "eval_samples_per_second": 6.099,
+      "eval_steps_per_second": 3.049,
+      "step": 2400
+    },
+    {
+      "epoch": 3.57,
+      "grad_norm": 2.693216562271118,
+      "learning_rate": 9.567502781638516e-06,
+      "loss": 2.3249,
+      "step": 2410
+    },
+    {
+      "epoch": 3.59,
+      "grad_norm": 2.68764066696167,
+      "learning_rate": 9.384010761119787e-06,
+      "loss": 2.2552,
+      "step": 2420
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 4.221546649932861,
+      "learning_rate": 9.201887985160804e-06,
+      "loss": 2.3362,
+      "step": 2430
+    },
+    {
+      "epoch": 3.61,
+      "grad_norm": 2.777925729751587,
+      "learning_rate": 9.039161391719244e-06,
+      "loss": 2.3256,
+      "step": 2440
+    },
+    {
+      "epoch": 3.63,
+      "grad_norm": 2.7611911296844482,
+      "learning_rate": 8.859684074465835e-06,
+      "loss": 2.2209,
+      "step": 2450
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 2.7354393005371094,
+      "learning_rate": 8.681621975898577e-06,
+      "loss": 2.1957,
+      "step": 2460
+    },
+    {
+      "epoch": 3.66,
+      "grad_norm": 2.901160478591919,
+      "learning_rate": 8.504990708897056e-06,
+      "loss": 2.2935,
+      "step": 2470
+    },
+    {
+      "epoch": 3.67,
+      "grad_norm": 2.4266469478607178,
+      "learning_rate": 8.329805760882403e-06,
+      "loss": 2.307,
+      "step": 2480
+    },
+    {
+      "epoch": 3.69,
+      "grad_norm": 2.3984947204589844,
+      "learning_rate": 8.156082492459257e-06,
+      "loss": 2.3943,
+      "step": 2490
+    },
+    {
+      "epoch": 3.7,
+      "grad_norm": 2.6705055236816406,
+      "learning_rate": 7.983836136068984e-06,
+      "loss": 2.3774,
+      "step": 2500
+    },
+    {
+      "epoch": 3.72,
+      "grad_norm": 3.173973321914673,
+      "learning_rate": 7.813081794653995e-06,
+      "loss": 2.2757,
+      "step": 2510
+    },
+    {
+      "epoch": 3.73,
+      "grad_norm": 3.104217529296875,
+      "learning_rate": 7.643834440333553e-06,
+      "loss": 2.2961,
+      "step": 2520
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 3.088330030441284,
+      "learning_rate": 7.476108913090915e-06,
+      "loss": 2.2001,
+      "step": 2530
+    },
+    {
+      "epoch": 3.76,
+      "grad_norm": 3.717886447906494,
+      "learning_rate": 7.309919919472208e-06,
+      "loss": 2.1859,
+      "step": 2540
+    },
+    {
+      "epoch": 3.78,
+      "grad_norm": 3.12146258354187,
+      "learning_rate": 7.145282031296841e-06,
+      "loss": 2.2422,
+      "step": 2550
+    },
+    {
+      "epoch": 3.79,
+      "grad_norm": 3.212069272994995,
+      "learning_rate": 6.982209684379892e-06,
+      "loss": 2.1191,
+      "step": 2560
+    },
+    {
+      "epoch": 3.81,
+      "grad_norm": 3.0071327686309814,
+      "learning_rate": 6.8207171772662976e-06,
+      "loss": 2.1472,
+      "step": 2570
+    },
+    {
+      "epoch": 3.82,
+      "grad_norm": 3.0386757850646973,
+      "learning_rate": 6.660818669977134e-06,
+      "loss": 2.3547,
+      "step": 2580
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 2.2448551654815674,
+      "learning_rate": 6.5025281827680335e-06,
+      "loss": 2.2866,
+      "step": 2590
+    },
+    {
+      "epoch": 3.85,
+      "grad_norm": 3.914092779159546,
+      "learning_rate": 6.345859594899886e-06,
+      "loss": 2.3713,
+      "step": 2600
+    },
+    {
+      "epoch": 3.85,
+      "eval_loss": 2.2858927249908447,
+      "eval_runtime": 98.5519,
+      "eval_samples_per_second": 6.088,
+      "eval_steps_per_second": 3.044,
+      "step": 2600
+    },
+    {
+      "epoch": 3.87,
+      "grad_norm": 2.350407600402832,
+      "learning_rate": 6.1908266434218235e-06,
+      "loss": 2.2876,
+      "step": 2610
+    },
+    {
+      "epoch": 3.88,
+      "grad_norm": 2.7468740940093994,
+      "learning_rate": 6.037442921966771e-06,
+      "loss": 2.3253,
+      "step": 2620
+    },
+    {
+      "epoch": 3.9,
+      "grad_norm": 3.026620626449585,
+      "learning_rate": 5.885721879559514e-06,
+      "loss": 2.2033,
+      "step": 2630
+    },
+    {
+      "epoch": 3.91,
+      "grad_norm": 2.2398440837860107,
+      "learning_rate": 5.735676819437425e-06,
+      "loss": 2.317,
+      "step": 2640
+    },
+    {
+      "epoch": 3.93,
+      "grad_norm": 2.4124555587768555,
+      "learning_rate": 5.587320897884066e-06,
+      "loss": 2.284,
+      "step": 2650
+    },
+    {
+      "epoch": 3.94,
+      "grad_norm": 2.4340391159057617,
+      "learning_rate": 5.440667123075558e-06,
+      "loss": 2.3012,
+      "step": 2660
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 2.7486612796783447,
+      "learning_rate": 5.295728353940038e-06,
+      "loss": 2.5206,
+      "step": 2670
+    },
+    {
+      "epoch": 3.97,
+      "grad_norm": 2.5270161628723145,
+      "learning_rate": 5.152517299030127e-06,
+      "loss": 2.5541,
+      "step": 2680
+    },
+    {
+      "epoch": 3.99,
+      "grad_norm": 3.589616298675537,
+      "learning_rate": 5.011046515408657e-06,
+      "loss": 2.3475,
+      "step": 2690
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.27154541015625,
+      "learning_rate": 4.871328407547587e-06,
+      "loss": 2.4889,
+      "step": 2700
+    },
+    {
+      "epoch": 4.01,
+      "grad_norm": 2.9212470054626465,
+      "learning_rate": 4.733375226240408e-06,
+      "loss": 2.4318,
+      "step": 2710
+    },
+    {
+      "epoch": 4.03,
+      "grad_norm": 3.5055928230285645,
+      "learning_rate": 4.597199067527907e-06,
+      "loss": 2.1628,
+      "step": 2720
+    },
+    {
+      "epoch": 4.04,
+      "grad_norm": 2.520705223083496,
+      "learning_rate": 4.462811871637618e-06,
+      "loss": 2.0723,
+      "step": 2730
+    },
+    {
+      "epoch": 4.06,
+      "grad_norm": 3.2816295623779297,
+      "learning_rate": 4.330225421936823e-06,
+      "loss": 2.2386,
+      "step": 2740
+    },
+    {
+      "epoch": 4.07,
+      "grad_norm": 3.64699649810791,
+      "learning_rate": 4.1994513438994156e-06,
+      "loss": 2.1135,
+      "step": 2750
+    },
+    {
+      "epoch": 4.09,
+      "grad_norm": 3.278775930404663,
+      "learning_rate": 4.070501104086488e-06,
+      "loss": 2.2199,
+      "step": 2760
+    },
+    {
+      "epoch": 4.1,
+      "grad_norm": 1.8690662384033203,
+      "learning_rate": 3.943386009140984e-06,
+      "loss": 2.2364,
+      "step": 2770
+    },
+    {
+      "epoch": 4.12,
+      "grad_norm": 3.0856454372406006,
+      "learning_rate": 3.818117204796262e-06,
+      "loss": 2.0439,
+      "step": 2780
+    },
+    {
+      "epoch": 4.13,
+      "grad_norm": 3.822516679763794,
+      "learning_rate": 3.694705674898827e-06,
+      "loss": 2.2703,
+      "step": 2790
+    },
+    {
+      "epoch": 4.15,
+      "grad_norm": 5.145390510559082,
+      "learning_rate": 3.573162240445238e-06,
+      "loss": 2.3365,
+      "step": 2800
+    },
+    {
+      "epoch": 4.15,
+      "eval_loss": 2.2857470512390137,
+      "eval_runtime": 98.4481,
+      "eval_samples_per_second": 6.095,
+      "eval_steps_per_second": 3.047,
+      "step": 2800
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 200,
+  "total_flos": 7.882780555954094e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

Yi-1.5-9B-Chat-LoRA/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63f70fe831711cdfd1f28877e724899c1779d7deea9ba996bb7d43de2c0034eb
+size 5112