Upload folder using huggingface_hub

adapter_config.json

@@ -20,11 +20,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "down_proj",
     "up_proj",
     "gate_proj",
-    "Wqkv"
+    "o_proj",
+    "Wqkv",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2d43d47b46d25c72215b5d4ffd66d7a49c408c465c4eee0e1c6a5dac531ca3e
+oid sha256:99ddf450976c0bbf44df8dccdf9ec4cab646e80e2111ea19b896753af0d94c4a
 size 681596224

phi_sft/checkpoint-290/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/Phi-3-medium-4k-instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.2

phi_sft/checkpoint-290/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3-medium-4k-instruct",
+  "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": 128,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "Wqkv",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

phi_sft/checkpoint-290/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99ddf450976c0bbf44df8dccdf9ec4cab646e80e2111ea19b896753af0d94c4a
+size 681596224

phi_sft/checkpoint-290/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b80b85fee4568e0bea183b9c166f2909796faa2b7e05c9070fe8b63529fafbe5
+size 346305594

phi_sft/checkpoint-290/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:440dc2adc75ca65d4b90a198fa0e417fb477d22789c46cfdc32d65da4da32dc8
+size 14244

phi_sft/checkpoint-290/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adadf38b18962211e1ec1e333d9be8fa24b2c8a37782971f9db54aa771f3b761
+size 1064

phi_sft/checkpoint-290/special_tokens_map.json

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

phi_sft/checkpoint-290/tokenizer_config.json

@@ -0,0 +1,131 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

phi_sft/checkpoint-290/trainer_state.json

@@ -0,0 +1,2063 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 290,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.034482758620689655,
+      "grad_norm": 0.17807579040527344,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.1722,
+      "step": 1
+    },
+    {
+      "epoch": 0.06896551724137931,
+      "grad_norm": 0.14334461092948914,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.1382,
+      "step": 2
+    },
+    {
+      "epoch": 0.10344827586206896,
+      "grad_norm": 1.1039605140686035,
+      "learning_rate": 6e-06,
+      "loss": 1.0634,
+      "step": 3
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 0.20950548350811005,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.076,
+      "step": 4
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 0.22060707211494446,
+      "learning_rate": 1e-05,
+      "loss": 1.1275,
+      "step": 5
+    },
+    {
+      "epoch": 0.20689655172413793,
+      "grad_norm": 0.5935385227203369,
+      "learning_rate": 1.2e-05,
+      "loss": 1.0849,
+      "step": 6
+    },
+    {
+      "epoch": 0.2413793103448276,
+      "grad_norm": 0.21441376209259033,
+      "learning_rate": 1.4e-05,
+      "loss": 1.0646,
+      "step": 7
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 0.1888943761587143,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.332,
+      "step": 8
+    },
+    {
+      "epoch": 0.3103448275862069,
+      "grad_norm": 0.2495911568403244,
+      "learning_rate": 1.8e-05,
+      "loss": 1.2492,
+      "step": 9
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 0.15021701157093048,
+      "learning_rate": 2e-05,
+      "loss": 1.0421,
+      "step": 10
+    },
+    {
+      "epoch": 0.3793103448275862,
+      "grad_norm": 0.2735109031200409,
+      "learning_rate": 1.9999370567547008e-05,
+      "loss": 0.9769,
+      "step": 11
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 0.31325650215148926,
+      "learning_rate": 1.999748234942507e-05,
+      "loss": 1.0283,
+      "step": 12
+    },
+    {
+      "epoch": 0.4482758620689655,
+      "grad_norm": 0.27598780393600464,
+      "learning_rate": 1.9994335583335336e-05,
+      "loss": 1.0617,
+      "step": 13
+    },
+    {
+      "epoch": 0.4827586206896552,
+      "grad_norm": 0.36362579464912415,
+      "learning_rate": 1.9989930665413148e-05,
+      "loss": 1.0484,
+      "step": 14
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 0.3282495141029358,
+      "learning_rate": 1.998426815017817e-05,
+      "loss": 1.1508,
+      "step": 15
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.26612451672554016,
+      "learning_rate": 1.997734875046456e-05,
+      "loss": 1.1086,
+      "step": 16
+    },
+    {
+      "epoch": 0.5862068965517241,
+      "grad_norm": 0.234268918633461,
+      "learning_rate": 1.9969173337331283e-05,
+      "loss": 1.0223,
+      "step": 17
+    },
+    {
+      "epoch": 0.6206896551724138,
+      "grad_norm": 0.2058275192975998,
+      "learning_rate": 1.9959742939952393e-05,
+      "loss": 1.1502,
+      "step": 18
+    },
+    {
+      "epoch": 0.6551724137931034,
+      "grad_norm": 0.22659699618816376,
+      "learning_rate": 1.9949058745487524e-05,
+      "loss": 1.0664,
+      "step": 19
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.23868638277053833,
+      "learning_rate": 1.9937122098932428e-05,
+      "loss": 0.9078,
+      "step": 20
+    },
+    {
+      "epoch": 0.7241379310344828,
+      "grad_norm": 0.4853997826576233,
+      "learning_rate": 1.9923934502949645e-05,
+      "loss": 1.1411,
+      "step": 21
+    },
+    {
+      "epoch": 0.7586206896551724,
+      "grad_norm": 0.27940553426742554,
+      "learning_rate": 1.990949761767935e-05,
+      "loss": 1.018,
+      "step": 22
+    },
+    {
+      "epoch": 0.7931034482758621,
+      "grad_norm": 0.21220554411411285,
+      "learning_rate": 1.9893813260530368e-05,
+      "loss": 1.04,
+      "step": 23
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.24021866917610168,
+      "learning_rate": 1.9876883405951378e-05,
+      "loss": 1.1487,
+      "step": 24
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 0.24674388766288757,
+      "learning_rate": 1.985871018518236e-05,
+      "loss": 0.9219,
+      "step": 25
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 0.27987539768218994,
+      "learning_rate": 1.98392958859863e-05,
+      "loss": 0.9854,
+      "step": 26
+    },
+    {
+      "epoch": 0.9310344827586207,
+      "grad_norm": 0.19086048007011414,
+      "learning_rate": 1.9818642952361188e-05,
+      "loss": 1.0212,
+      "step": 27
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 0.2220487892627716,
+      "learning_rate": 1.9796753984232357e-05,
+      "loss": 0.9409,
+      "step": 28
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.32672297954559326,
+      "learning_rate": 1.9773631737125192e-05,
+      "loss": 0.9612,
+      "step": 29
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 0.27398526668548584,
+      "learning_rate": 1.9749279121818235e-05,
+      "loss": 0.9294,
+      "step": 30
+    },
+    {
+      "epoch": 1.0689655172413792,
+      "grad_norm": 0.21060261130332947,
+      "learning_rate": 1.9723699203976768e-05,
+      "loss": 0.9595,
+      "step": 31
+    },
+    {
+      "epoch": 1.103448275862069,
+      "grad_norm": 0.21103355288505554,
+      "learning_rate": 1.969689520376687e-05,
+      "loss": 1.0846,
+      "step": 32
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "grad_norm": 0.22356903553009033,
+      "learning_rate": 1.9668870495450064e-05,
+      "loss": 0.8991,
+      "step": 33
+    },
+    {
+      "epoch": 1.1724137931034484,
+      "grad_norm": 0.2682551145553589,
+      "learning_rate": 1.9639628606958535e-05,
+      "loss": 0.9837,
+      "step": 34
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 0.2573905885219574,
+      "learning_rate": 1.9609173219450998e-05,
+      "loss": 1.0286,
+      "step": 35
+    },
+    {
+      "epoch": 1.2413793103448276,
+      "grad_norm": 0.2607196271419525,
+      "learning_rate": 1.9577508166849308e-05,
+      "loss": 0.9029,
+      "step": 36
+    },
+    {
+      "epoch": 1.2758620689655173,
+      "grad_norm": 0.20472170412540436,
+      "learning_rate": 1.954463743535581e-05,
+      "loss": 0.8581,
+      "step": 37
+    },
+    {
+      "epoch": 1.3103448275862069,
+      "grad_norm": 0.22384370863437653,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 0.8642,
+      "step": 38
+    },
+    {
+      "epoch": 1.3448275862068966,
+      "grad_norm": 0.23026607930660248,
+      "learning_rate": 1.947529563887529e-05,
+      "loss": 0.868,
+      "step": 39
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.27446794509887695,
+      "learning_rate": 1.9438833303083677e-05,
+      "loss": 1.0613,
+      "step": 40
+    },
+    {
+      "epoch": 1.4137931034482758,
+      "grad_norm": 0.211438849568367,
+      "learning_rate": 1.940118274569219e-05,
+      "loss": 0.8051,
+      "step": 41
+    },
+    {
+      "epoch": 1.4482758620689655,
+      "grad_norm": 0.2091425359249115,
+      "learning_rate": 1.9362348706397374e-05,
+      "loss": 0.8515,
+      "step": 42
+    },
+    {
+      "epoch": 1.4827586206896552,
+      "grad_norm": 0.25555312633514404,
+      "learning_rate": 1.9322336073880143e-05,
+      "loss": 0.8974,
+      "step": 43
+    },
+    {
+      "epoch": 1.5172413793103448,
+      "grad_norm": 0.23694130778312683,
+      "learning_rate": 1.928114988519039e-05,
+      "loss": 0.9187,
+      "step": 44
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 0.2148314267396927,
+      "learning_rate": 1.9238795325112867e-05,
+      "loss": 0.9458,
+      "step": 45
+    },
+    {
+      "epoch": 1.5862068965517242,
+      "grad_norm": 0.23585829138755798,
+      "learning_rate": 1.919527772551451e-05,
+      "loss": 1.0475,
+      "step": 46
+    },
+    {
+      "epoch": 1.6206896551724137,
+      "grad_norm": 0.22569262981414795,
+      "learning_rate": 1.91506025646732e-05,
+      "loss": 0.987,
+      "step": 47
+    },
+    {
+      "epoch": 1.6551724137931034,
+      "grad_norm": 0.19846168160438538,
+      "learning_rate": 1.9104775466588162e-05,
+      "loss": 0.9255,
+      "step": 48
+    },
+    {
+      "epoch": 1.6896551724137931,
+      "grad_norm": 0.3316393196582794,
+      "learning_rate": 1.9057802200271943e-05,
+      "loss": 0.9647,
+      "step": 49
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 0.24265407025814056,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 0.9569,
+      "step": 50
+    },
+    {
+      "epoch": 1.7586206896551724,
+      "grad_norm": 0.2276720106601715,
+      "learning_rate": 1.8960440959687254e-05,
+      "loss": 0.921,
+      "step": 51
+    },
+    {
+      "epoch": 1.793103448275862,
+      "grad_norm": 0.2314290851354599,
+      "learning_rate": 1.891006524188368e-05,
+      "loss": 0.9175,
+      "step": 52
+    },
+    {
+      "epoch": 1.8275862068965516,
+      "grad_norm": 0.21895094215869904,
+      "learning_rate": 1.88585678672358e-05,
+      "loss": 0.8467,
+      "step": 53
+    },
+    {
+      "epoch": 1.8620689655172413,
+      "grad_norm": 0.21930821239948273,
+      "learning_rate": 1.880595531856738e-05,
+      "loss": 0.8175,
+      "step": 54
+    },
+    {
+      "epoch": 1.896551724137931,
+      "grad_norm": 0.2337353378534317,
+      "learning_rate": 1.8752234219087538e-05,
+      "loss": 0.9402,
+      "step": 55
+    },
+    {
+      "epoch": 1.9310344827586206,
+      "grad_norm": 0.28663069009780884,
+      "learning_rate": 1.8697411331556958e-05,
+      "loss": 1.0676,
+      "step": 56
+    },
+    {
+      "epoch": 1.9655172413793105,
+      "grad_norm": 0.29483750462532043,
+      "learning_rate": 1.864149355743655e-05,
+      "loss": 0.9589,
+      "step": 57
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.3743893504142761,
+      "learning_rate": 1.8584487936018663e-05,
+      "loss": 0.9082,
+      "step": 58
+    },
+    {
+      "epoch": 2.0344827586206895,
+      "grad_norm": 0.23090603947639465,
+      "learning_rate": 1.8526401643540924e-05,
+      "loss": 0.9417,
+      "step": 59
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 0.2298315465450287,
+      "learning_rate": 1.8467241992282842e-05,
+      "loss": 0.874,
+      "step": 60
+    },
+    {
+      "epoch": 2.103448275862069,
+      "grad_norm": 0.2441719025373459,
+      "learning_rate": 1.8407016429645305e-05,
+      "loss": 0.8965,
+      "step": 61
+    },
+    {
+      "epoch": 2.1379310344827585,
+      "grad_norm": 0.22642402350902557,
+      "learning_rate": 1.834573253721303e-05,
+      "loss": 0.8604,
+      "step": 62
+    },
+    {
+      "epoch": 2.1724137931034484,
+      "grad_norm": 0.23399463295936584,
+      "learning_rate": 1.8283398029800167e-05,
+      "loss": 0.8852,
+      "step": 63
+    },
+    {
+      "epoch": 2.206896551724138,
+      "grad_norm": 0.2652157247066498,
+      "learning_rate": 1.8220020754479104e-05,
+      "loss": 0.7388,
+      "step": 64
+    },
+    {
+      "epoch": 2.2413793103448274,
+      "grad_norm": 0.23206576704978943,
+      "learning_rate": 1.8155608689592604e-05,
+      "loss": 0.9001,
+      "step": 65
+    },
+    {
+      "epoch": 2.2758620689655173,
+      "grad_norm": 0.2772204279899597,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.8994,
+      "step": 66
+    },
+    {
+      "epoch": 2.310344827586207,
+      "grad_norm": 0.23800912499427795,
+      "learning_rate": 1.8023712754803783e-05,
+      "loss": 0.8184,
+      "step": 67
+    },
+    {
+      "epoch": 2.344827586206897,
+      "grad_norm": 0.2611038386821747,
+      "learning_rate": 1.795624548881781e-05,
+      "loss": 1.0151,
+      "step": 68
+    },
+    {
+      "epoch": 2.3793103448275863,
+      "grad_norm": 0.2740626931190491,
+      "learning_rate": 1.7887776639008912e-05,
+      "loss": 0.8608,
+      "step": 69
+    },
+    {
+      "epoch": 2.413793103448276,
+      "grad_norm": 0.2342958301305771,
+      "learning_rate": 1.78183148246803e-05,
+      "loss": 0.8971,
+      "step": 70
+    },
+    {
+      "epoch": 2.4482758620689653,
+      "grad_norm": 0.2934868335723877,
+      "learning_rate": 1.7747868790136012e-05,
+      "loss": 0.8794,
+      "step": 71
+    },
+    {
+      "epoch": 2.4827586206896552,
+      "grad_norm": 0.27324584126472473,
+      "learning_rate": 1.7676447403580114e-05,
+      "loss": 0.8423,
+      "step": 72
+    },
+    {
+      "epoch": 2.5172413793103448,
+      "grad_norm": 0.3090510368347168,
+      "learning_rate": 1.7604059656000313e-05,
+      "loss": 0.9163,
+      "step": 73
+    },
+    {
+      "epoch": 2.5517241379310347,
+      "grad_norm": 0.2825857400894165,
+      "learning_rate": 1.7530714660036112e-05,
+      "loss": 0.7595,
+      "step": 74
+    },
+    {
+      "epoch": 2.586206896551724,
+      "grad_norm": 0.29138025641441345,
+      "learning_rate": 1.7456421648831658e-05,
+      "loss": 0.8515,
+      "step": 75
+    },
+    {
+      "epoch": 2.6206896551724137,
+      "grad_norm": 0.24783280491828918,
+      "learning_rate": 1.738118997487341e-05,
+      "loss": 0.7475,
+      "step": 76
+    },
+    {
+      "epoch": 2.655172413793103,
+      "grad_norm": 0.28366154432296753,
+      "learning_rate": 1.7305029108812777e-05,
+      "loss": 0.761,
+      "step": 77
+    },
+    {
+      "epoch": 2.689655172413793,
+      "grad_norm": 0.29896560311317444,
+      "learning_rate": 1.7227948638273918e-05,
+      "loss": 1.0103,
+      "step": 78
+    },
+    {
+      "epoch": 2.7241379310344827,
+      "grad_norm": 0.25055158138275146,
+      "learning_rate": 1.7149958266646756e-05,
+      "loss": 0.9047,
+      "step": 79
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "grad_norm": 0.30915355682373047,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.869,
+      "step": 80
+    },
+    {
+      "epoch": 2.793103448275862,
+      "grad_norm": 0.3037479519844055,
+      "learning_rate": 1.6991287205172575e-05,
+      "loss": 1.1759,
+      "step": 81
+    },
+    {
+      "epoch": 2.8275862068965516,
+      "grad_norm": 0.27288734912872314,
+      "learning_rate": 1.691062648986865e-05,
+      "loss": 0.7851,
+      "step": 82
+    },
+    {
+      "epoch": 2.862068965517241,
+      "grad_norm": 0.2524704933166504,
+      "learning_rate": 1.682909582004807e-05,
+      "loss": 0.9823,
+      "step": 83
+    },
+    {
+      "epoch": 2.896551724137931,
+      "grad_norm": 0.2636321187019348,
+      "learning_rate": 1.6746705459320746e-05,
+      "loss": 1.0698,
+      "step": 84
+    },
+    {
+      "epoch": 2.9310344827586206,
+      "grad_norm": 0.2754139304161072,
+      "learning_rate": 1.6663465779520042e-05,
+      "loss": 0.8199,
+      "step": 85
+    },
+    {
+      "epoch": 2.9655172413793105,
+      "grad_norm": 0.4758215844631195,
+      "learning_rate": 1.657938725939713e-05,
+      "loss": 0.7468,
+      "step": 86
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.31884345412254333,
+      "learning_rate": 1.6494480483301836e-05,
+      "loss": 0.7877,
+      "step": 87
+    },
+    {
+      "epoch": 3.0344827586206895,
+      "grad_norm": 0.24241481721401215,
+      "learning_rate": 1.6408756139850243e-05,
+      "loss": 0.8371,
+      "step": 88
+    },
+    {
+      "epoch": 3.0689655172413794,
+      "grad_norm": 0.26576536893844604,
+      "learning_rate": 1.63222250205791e-05,
+      "loss": 0.75,
+      "step": 89
+    },
+    {
+      "epoch": 3.103448275862069,
+      "grad_norm": 0.30096766352653503,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 0.9242,
+      "step": 90
+    },
+    {
+      "epoch": 3.1379310344827585,
+      "grad_norm": 0.26124823093414307,
+      "learning_rate": 1.6146786127164773e-05,
+      "loss": 0.9695,
+      "step": 91
+    },
+    {
+      "epoch": 3.1724137931034484,
+      "grad_norm": 0.2820647656917572,
+      "learning_rate": 1.60579004384082e-05,
+      "loss": 0.7924,
+      "step": 92
+    },
+    {
+      "epoch": 3.206896551724138,
+      "grad_norm": 0.26848721504211426,
+      "learning_rate": 1.5968252141825038e-05,
+      "loss": 0.8045,
+      "step": 93
+    },
+    {
+      "epoch": 3.2413793103448274,
+      "grad_norm": 0.25865674018859863,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 0.782,
+      "step": 94
+    },
+    {
+      "epoch": 3.2758620689655173,
+      "grad_norm": 0.2408091127872467,
+      "learning_rate": 1.578671296179806e-05,
+      "loss": 0.6853,
+      "step": 95
+    },
+    {
+      "epoch": 3.310344827586207,
+      "grad_norm": 0.3063780665397644,
+      "learning_rate": 1.569484493168452e-05,
+      "loss": 0.8486,
+      "step": 96
+    },
+    {
+      "epoch": 3.344827586206897,
+      "grad_norm": 0.29873567819595337,
+      "learning_rate": 1.5602259997528028e-05,
+      "loss": 0.9433,
+      "step": 97
+    },
+    {
+      "epoch": 3.3793103448275863,
+      "grad_norm": 0.27373233437538147,
+      "learning_rate": 1.5508969814521026e-05,
+      "loss": 0.7435,
+      "step": 98
+    },
+    {
+      "epoch": 3.413793103448276,
+      "grad_norm": 0.2671841084957123,
+      "learning_rate": 1.541498612663726e-05,
+      "loss": 0.7966,
+      "step": 99
+    },
+    {
+      "epoch": 3.4482758620689653,
+      "grad_norm": 0.30250269174575806,
+      "learning_rate": 1.5320320765153367e-05,
+      "loss": 0.7771,
+      "step": 100
+    },
+    {
+      "epoch": 3.4827586206896552,
+      "grad_norm": 0.3080671727657318,
+      "learning_rate": 1.5224985647159489e-05,
+      "loss": 0.7749,
+      "step": 101
+    },
+    {
+      "epoch": 3.5172413793103448,
+      "grad_norm": 0.3227786421775818,
+      "learning_rate": 1.5128992774059063e-05,
+      "loss": 0.8247,
+      "step": 102
+    },
+    {
+      "epoch": 3.5517241379310347,
+      "grad_norm": 0.2906538248062134,
+      "learning_rate": 1.5032354230058004e-05,
+      "loss": 0.7864,
+      "step": 103
+    },
+    {
+      "epoch": 3.586206896551724,
+      "grad_norm": 0.31295332312583923,
+      "learning_rate": 1.493508218064347e-05,
+      "loss": 0.8499,
+      "step": 104
+    },
+    {
+      "epoch": 3.6206896551724137,
+      "grad_norm": 0.31619223952293396,
+      "learning_rate": 1.4837188871052399e-05,
+      "loss": 0.8852,
+      "step": 105
+    },
+    {
+      "epoch": 3.655172413793103,
+      "grad_norm": 0.2794528901576996,
+      "learning_rate": 1.4738686624729987e-05,
+      "loss": 0.7642,
+      "step": 106
+    },
+    {
+      "epoch": 3.689655172413793,
+      "grad_norm": 0.33145707845687866,
+      "learning_rate": 1.4639587841778342e-05,
+      "loss": 0.8132,
+      "step": 107
+    },
+    {
+      "epoch": 3.7241379310344827,
+      "grad_norm": 0.33101916313171387,
+      "learning_rate": 1.4539904997395468e-05,
+      "loss": 0.9102,
+      "step": 108
+    },
+    {
+      "epoch": 3.7586206896551726,
+      "grad_norm": 0.305571973323822,
+      "learning_rate": 1.4439650640304822e-05,
+      "loss": 0.9019,
+      "step": 109
+    },
+    {
+      "epoch": 3.793103448275862,
+      "grad_norm": 0.3403263986110687,
+      "learning_rate": 1.4338837391175582e-05,
+      "loss": 0.8448,
+      "step": 110
+    },
+    {
+      "epoch": 3.8275862068965516,
+      "grad_norm": 0.2603549063205719,
+      "learning_rate": 1.4237477941033888e-05,
+      "loss": 0.932,
+      "step": 111
+    },
+    {
+      "epoch": 3.862068965517241,
+      "grad_norm": 0.31784287095069885,
+      "learning_rate": 1.4135585049665207e-05,
+      "loss": 1.0628,
+      "step": 112
+    },
+    {
+      "epoch": 3.896551724137931,
+      "grad_norm": 0.3544517755508423,
+      "learning_rate": 1.4033171544008053e-05,
+      "loss": 0.8902,
+      "step": 113
+    },
+    {
+      "epoch": 3.9310344827586206,
+      "grad_norm": 0.28407877683639526,
+      "learning_rate": 1.3930250316539237e-05,
+      "loss": 0.8418,
+      "step": 114
+    },
+    {
+      "epoch": 3.9655172413793105,
+      "grad_norm": 0.3233966529369354,
+      "learning_rate": 1.3826834323650899e-05,
+      "loss": 1.0213,
+      "step": 115
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.5007153749465942,
+      "learning_rate": 1.3722936584019453e-05,
+      "loss": 0.849,
+      "step": 116
+    },
+    {
+      "epoch": 4.0344827586206895,
+      "grad_norm": 0.29051631689071655,
+      "learning_rate": 1.3618570176966723e-05,
+      "loss": 0.9174,
+      "step": 117
+    },
+    {
+      "epoch": 4.068965517241379,
+      "grad_norm": 0.32139936089515686,
+      "learning_rate": 1.3513748240813429e-05,
+      "loss": 0.8534,
+      "step": 118
+    },
+    {
+      "epoch": 4.103448275862069,
+      "grad_norm": 0.3164803087711334,
+      "learning_rate": 1.340848397122525e-05,
+      "loss": 0.7836,
+      "step": 119
+    },
+    {
+      "epoch": 4.137931034482759,
+      "grad_norm": 0.3631249666213989,
+      "learning_rate": 1.3302790619551673e-05,
+      "loss": 0.7273,
+      "step": 120
+    },
+    {
+      "epoch": 4.172413793103448,
+      "grad_norm": 0.2703869640827179,
+      "learning_rate": 1.3196681491157816e-05,
+      "loss": 0.7809,
+      "step": 121
+    },
+    {
+      "epoch": 4.206896551724138,
+      "grad_norm": 0.2911336123943329,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.8687,
+      "step": 122
+    },
+    {
+      "epoch": 4.241379310344827,
+      "grad_norm": 0.31598594784736633,
+      "learning_rate": 1.2983269385691562e-05,
+      "loss": 0.8602,
+      "step": 123
+    },
+    {
+      "epoch": 4.275862068965517,
+      "grad_norm": 0.31362679600715637,
+      "learning_rate": 1.2875993274320173e-05,
+      "loss": 0.6573,
+      "step": 124
+    },
+    {
+      "epoch": 4.310344827586207,
+      "grad_norm": 0.29367008805274963,
+      "learning_rate": 1.2768355114248493e-05,
+      "loss": 0.7656,
+      "step": 125
+    },
+    {
+      "epoch": 4.344827586206897,
+      "grad_norm": 0.3383594751358032,
+      "learning_rate": 1.2660368455666752e-05,
+      "loss": 0.7799,
+      "step": 126
+    },
+    {
+      "epoch": 4.379310344827586,
+      "grad_norm": 0.4282345175743103,
+      "learning_rate": 1.2552046892636427e-05,
+      "loss": 0.7991,
+      "step": 127
+    },
+    {
+      "epoch": 4.413793103448276,
+      "grad_norm": 0.368530809879303,
+      "learning_rate": 1.2443404061378941e-05,
+      "loss": 0.8792,
+      "step": 128
+    },
+    {
+      "epoch": 4.448275862068965,
+      "grad_norm": 0.36611831188201904,
+      "learning_rate": 1.2334453638559057e-05,
+      "loss": 0.8577,
+      "step": 129
+    },
+    {
+      "epoch": 4.482758620689655,
+      "grad_norm": 0.30029138922691345,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 0.7704,
+      "step": 130
+    },
+    {
+      "epoch": 4.517241379310345,
+      "grad_norm": 0.33511656522750854,
+      "learning_rate": 1.211568491677263e-05,
+      "loss": 0.7999,
+      "step": 131
+    },
+    {
+      "epoch": 4.551724137931035,
+      "grad_norm": 0.3483274579048157,
+      "learning_rate": 1.200589415783273e-05,
+      "loss": 0.7363,
+      "step": 132
+    },
+    {
+      "epoch": 4.586206896551724,
+      "grad_norm": 0.4255923330783844,
+      "learning_rate": 1.1895850883916786e-05,
+      "loss": 1.0776,
+      "step": 133
+    },
+    {
+      "epoch": 4.620689655172414,
+      "grad_norm": 0.37267133593559265,
+      "learning_rate": 1.1785568947986368e-05,
+      "loss": 0.8634,
+      "step": 134
+    },
+    {
+      "epoch": 4.655172413793103,
+      "grad_norm": 0.399506151676178,
+      "learning_rate": 1.1675062233047365e-05,
+      "loss": 0.9234,
+      "step": 135
+    },
+    {
+      "epoch": 4.689655172413794,
+      "grad_norm": 0.32030320167541504,
+      "learning_rate": 1.156434465040231e-05,
+      "loss": 0.7586,
+      "step": 136
+    },
+    {
+      "epoch": 4.724137931034483,
+      "grad_norm": 0.3084131181240082,
+      "learning_rate": 1.1453430137899129e-05,
+      "loss": 0.7435,
+      "step": 137
+    },
+    {
+      "epoch": 4.758620689655173,
+      "grad_norm": 0.31277623772621155,
+      "learning_rate": 1.1342332658176556e-05,
+      "loss": 0.732,
+      "step": 138
+    },
+    {
+      "epoch": 4.793103448275862,
+      "grad_norm": 0.3215080201625824,
+      "learning_rate": 1.123106619690643e-05,
+      "loss": 0.7813,
+      "step": 139
+    },
+    {
+      "epoch": 4.827586206896552,
+      "grad_norm": 0.3149239122867584,
+      "learning_rate": 1.1119644761033079e-05,
+      "loss": 0.8421,
+      "step": 140
+    },
+    {
+      "epoch": 4.862068965517241,
+      "grad_norm": 0.3260899484157562,
+      "learning_rate": 1.1008082377010045e-05,
+      "loss": 0.9099,
+      "step": 141
+    },
+    {
+      "epoch": 4.896551724137931,
+      "grad_norm": 0.3588120639324188,
+      "learning_rate": 1.0896393089034336e-05,
+      "loss": 0.8573,
+      "step": 142
+    },
+    {
+      "epoch": 4.931034482758621,
+      "grad_norm": 0.36314326524734497,
+      "learning_rate": 1.0784590957278452e-05,
+      "loss": 0.7753,
+      "step": 143
+    },
+    {
+      "epoch": 4.9655172413793105,
+      "grad_norm": 0.3441053628921509,
+      "learning_rate": 1.0672690056120398e-05,
+      "loss": 0.9387,
+      "step": 144
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.5082918405532837,
+      "learning_rate": 1.0560704472371919e-05,
+      "loss": 0.789,
+      "step": 145
+    },
+    {
+      "epoch": 5.0344827586206895,
+      "grad_norm": 0.3376893699169159,
+      "learning_rate": 1.044864830350515e-05,
+      "loss": 0.7638,
+      "step": 146
+    },
+    {
+      "epoch": 5.068965517241379,
+      "grad_norm": 0.31075963377952576,
+      "learning_rate": 1.0336535655877942e-05,
+      "loss": 1.042,
+      "step": 147
+    },
+    {
+      "epoch": 5.103448275862069,
+      "grad_norm": 0.3507033884525299,
+      "learning_rate": 1.0224380642958052e-05,
+      "loss": 0.7219,
+      "step": 148
+    },
+    {
+      "epoch": 5.137931034482759,
+      "grad_norm": 0.37355339527130127,
+      "learning_rate": 1.011219738354646e-05,
+      "loss": 0.7958,
+      "step": 149
+    },
+    {
+      "epoch": 5.172413793103448,
+      "grad_norm": 0.3259904682636261,
+      "learning_rate": 1e-05,
+      "loss": 0.7245,
+      "step": 150
+    },
+    {
+      "epoch": 5.206896551724138,
+      "grad_norm": 0.26023536920547485,
+      "learning_rate": 9.887802616453543e-06,
+      "loss": 0.6982,
+      "step": 151
+    },
+    {
+      "epoch": 5.241379310344827,
+      "grad_norm": 0.34935978055000305,
+      "learning_rate": 9.775619357041952e-06,
+      "loss": 0.858,
+      "step": 152
+    },
+    {
+      "epoch": 5.275862068965517,
+      "grad_norm": 0.3716798424720764,
+      "learning_rate": 9.663464344122064e-06,
+      "loss": 0.7607,
+      "step": 153
+    },
+    {
+      "epoch": 5.310344827586207,
+      "grad_norm": 0.32676616311073303,
+      "learning_rate": 9.551351696494854e-06,
+      "loss": 0.8896,
+      "step": 154
+    },
+    {
+      "epoch": 5.344827586206897,
+      "grad_norm": 0.305982381105423,
+      "learning_rate": 9.439295527628083e-06,
+      "loss": 0.8338,
+      "step": 155
+    },
+    {
+      "epoch": 5.379310344827586,
+      "grad_norm": 0.42595145106315613,
+      "learning_rate": 9.327309943879604e-06,
+      "loss": 0.8285,
+      "step": 156
+    },
+    {
+      "epoch": 5.413793103448276,
+      "grad_norm": 0.3462941348552704,
+      "learning_rate": 9.215409042721553e-06,
+      "loss": 0.8321,
+      "step": 157
+    },
+    {
+      "epoch": 5.448275862068965,
+      "grad_norm": 0.44463250041007996,
+      "learning_rate": 9.103606910965666e-06,
+      "loss": 0.7191,
+      "step": 158
+    },
+    {
+      "epoch": 5.482758620689655,
+      "grad_norm": 0.3701193630695343,
+      "learning_rate": 8.991917622989957e-06,
+      "loss": 0.7042,
+      "step": 159
+    },
+    {
+      "epoch": 5.517241379310345,
+      "grad_norm": 0.4350188374519348,
+      "learning_rate": 8.880355238966923e-06,
+      "loss": 0.8192,
+      "step": 160
+    },
+    {
+      "epoch": 5.551724137931035,
+      "grad_norm": 0.3398708403110504,
+      "learning_rate": 8.768933803093573e-06,
+      "loss": 0.7338,
+      "step": 161
+    },
+    {
+      "epoch": 5.586206896551724,
+      "grad_norm": 0.32399433851242065,
+      "learning_rate": 8.657667341823449e-06,
+      "loss": 0.729,
+      "step": 162
+    },
+    {
+      "epoch": 5.620689655172414,
+      "grad_norm": 0.4222228527069092,
+      "learning_rate": 8.546569862100876e-06,
+      "loss": 0.7907,
+      "step": 163
+    },
+    {
+      "epoch": 5.655172413793103,
+      "grad_norm": 0.34937605261802673,
+      "learning_rate": 8.43565534959769e-06,
+      "loss": 0.7824,
+      "step": 164
+    },
+    {
+      "epoch": 5.689655172413794,
+      "grad_norm": 0.4491080343723297,
+      "learning_rate": 8.324937766952638e-06,
+      "loss": 1.0042,
+      "step": 165
+    },
+    {
+      "epoch": 5.724137931034483,
+      "grad_norm": 0.3659018874168396,
+      "learning_rate": 8.214431052013636e-06,
+      "loss": 0.7599,
+      "step": 166
+    },
+    {
+      "epoch": 5.758620689655173,
+      "grad_norm": 0.38442462682724,
+      "learning_rate": 8.104149116083216e-06,
+      "loss": 0.7906,
+      "step": 167
+    },
+    {
+      "epoch": 5.793103448275862,
+      "grad_norm": 0.36882272362709045,
+      "learning_rate": 7.994105842167274e-06,
+      "loss": 0.745,
+      "step": 168
+    },
+    {
+      "epoch": 5.827586206896552,
+      "grad_norm": 0.38902854919433594,
+      "learning_rate": 7.884315083227373e-06,
+      "loss": 0.8323,
+      "step": 169
+    },
+    {
+      "epoch": 5.862068965517241,
+      "grad_norm": 0.39629384875297546,
+      "learning_rate": 7.774790660436857e-06,
+      "loss": 0.822,
+      "step": 170
+    },
+    {
+      "epoch": 5.896551724137931,
+      "grad_norm": 0.4170951843261719,
+      "learning_rate": 7.66554636144095e-06,
+      "loss": 0.8574,
+      "step": 171
+    },
+    {
+      "epoch": 5.931034482758621,
+      "grad_norm": 0.3711739778518677,
+      "learning_rate": 7.556595938621058e-06,
+      "loss": 0.7577,
+      "step": 172
+    },
+    {
+      "epoch": 5.9655172413793105,
+      "grad_norm": 0.37948688864707947,
+      "learning_rate": 7.447953107363574e-06,
+      "loss": 0.7528,
+      "step": 173
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.5917400121688843,
+      "learning_rate": 7.33963154433325e-06,
+      "loss": 0.8559,
+      "step": 174
+    },
+    {
+      "epoch": 6.0344827586206895,
+      "grad_norm": 0.34915852546691895,
+      "learning_rate": 7.2316448857515076e-06,
+      "loss": 0.7615,
+      "step": 175
+    },
+    {
+      "epoch": 6.068965517241379,
+      "grad_norm": 0.34217187762260437,
+      "learning_rate": 7.124006725679828e-06,
+      "loss": 0.7841,
+      "step": 176
+    },
+    {
+      "epoch": 6.103448275862069,
+      "grad_norm": 0.3473447859287262,
+      "learning_rate": 7.01673061430844e-06,
+      "loss": 0.7879,
+      "step": 177
+    },
+    {
+      "epoch": 6.137931034482759,
+      "grad_norm": 0.4143597483634949,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.84,
+      "step": 178
+    },
+    {
+      "epoch": 6.172413793103448,
+      "grad_norm": 0.384921133518219,
+      "learning_rate": 6.8033185088421874e-06,
+      "loss": 0.6566,
+      "step": 179
+    },
+    {
+      "epoch": 6.206896551724138,
+      "grad_norm": 0.3714582920074463,
+      "learning_rate": 6.697209380448333e-06,
+      "loss": 0.6852,
+      "step": 180
+    },
+    {
+      "epoch": 6.241379310344827,
+      "grad_norm": 0.3736112117767334,
+      "learning_rate": 6.59151602877475e-06,
+      "loss": 0.7115,
+      "step": 181
+    },
+    {
+      "epoch": 6.275862068965517,
+      "grad_norm": 0.30986639857292175,
+      "learning_rate": 6.486251759186573e-06,
+      "loss": 0.7566,
+      "step": 182
+    },
+    {
+      "epoch": 6.310344827586207,
+      "grad_norm": 0.4025953710079193,
+      "learning_rate": 6.381429823033281e-06,
+      "loss": 0.6718,
+      "step": 183
+    },
+    {
+      "epoch": 6.344827586206897,
+      "grad_norm": 0.4431048035621643,
+      "learning_rate": 6.277063415980549e-06,
+      "loss": 0.8241,
+      "step": 184
+    },
+    {
+      "epoch": 6.379310344827586,
+      "grad_norm": 0.372121125459671,
+      "learning_rate": 6.173165676349103e-06,
+      "loss": 0.8447,
+      "step": 185
+    },
+    {
+      "epoch": 6.413793103448276,
+      "grad_norm": 0.4210289418697357,
+      "learning_rate": 6.069749683460765e-06,
+      "loss": 0.7478,
+      "step": 186
+    },
+    {
+      "epoch": 6.448275862068965,
+      "grad_norm": 0.3632698357105255,
+      "learning_rate": 5.966828455991951e-06,
+      "loss": 0.9466,
+      "step": 187
+    },
+    {
+      "epoch": 6.482758620689655,
+      "grad_norm": 0.4597689211368561,
+      "learning_rate": 5.864414950334796e-06,
+      "loss": 0.925,
+      "step": 188
+    },
+    {
+      "epoch": 6.517241379310345,
+      "grad_norm": 0.41018036007881165,
+      "learning_rate": 5.7625220589661136e-06,
+      "loss": 0.8247,
+      "step": 189
+    },
+    {
+      "epoch": 6.551724137931035,
+      "grad_norm": 0.3755370080471039,
+      "learning_rate": 5.66116260882442e-06,
+      "loss": 0.9044,
+      "step": 190
+    },
+    {
+      "epoch": 6.586206896551724,
+      "grad_norm": 0.379211962223053,
+      "learning_rate": 5.560349359695181e-06,
+      "loss": 0.8281,
+      "step": 191
+    },
+    {
+      "epoch": 6.620689655172414,
+      "grad_norm": 0.4033229649066925,
+      "learning_rate": 5.460095002604533e-06,
+      "loss": 0.6582,
+      "step": 192
+    },
+    {
+      "epoch": 6.655172413793103,
+      "grad_norm": 0.3888568580150604,
+      "learning_rate": 5.360412158221661e-06,
+      "loss": 0.7206,
+      "step": 193
+    },
+    {
+      "epoch": 6.689655172413794,
+      "grad_norm": 0.4054708778858185,
+      "learning_rate": 5.2613133752700145e-06,
+      "loss": 0.6688,
+      "step": 194
+    },
+    {
+      "epoch": 6.724137931034483,
+      "grad_norm": 0.3875979781150818,
+      "learning_rate": 5.1628111289476025e-06,
+      "loss": 0.754,
+      "step": 195
+    },
+    {
+      "epoch": 6.758620689655173,
+      "grad_norm": 0.4415038824081421,
+      "learning_rate": 5.064917819356532e-06,
+      "loss": 1.0078,
+      "step": 196
+    },
+    {
+      "epoch": 6.793103448275862,
+      "grad_norm": 0.40458041429519653,
+      "learning_rate": 4.967645769942e-06,
+      "loss": 0.7884,
+      "step": 197
+    },
+    {
+      "epoch": 6.827586206896552,
+      "grad_norm": 0.39093512296676636,
+      "learning_rate": 4.87100722594094e-06,
+      "loss": 0.8759,
+      "step": 198
+    },
+    {
+      "epoch": 6.862068965517241,
+      "grad_norm": 0.4464360475540161,
+      "learning_rate": 4.775014352840512e-06,
+      "loss": 0.7639,
+      "step": 199
+    },
+    {
+      "epoch": 6.896551724137931,
+      "grad_norm": 0.3683170974254608,
+      "learning_rate": 4.679679234846636e-06,
+      "loss": 0.7306,
+      "step": 200
+    },
+    {
+      "epoch": 6.931034482758621,
+      "grad_norm": 0.39194703102111816,
+      "learning_rate": 4.5850138733627435e-06,
+      "loss": 0.826,
+      "step": 201
+    },
+    {
+      "epoch": 6.9655172413793105,
+      "grad_norm": 0.4512757360935211,
+      "learning_rate": 4.491030185478976e-06,
+      "loss": 0.6949,
+      "step": 202
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.555197536945343,
+      "learning_rate": 4.397740002471973e-06,
+      "loss": 0.7691,
+      "step": 203
+    },
+    {
+      "epoch": 7.0344827586206895,
+      "grad_norm": 0.38228851556777954,
+      "learning_rate": 4.305155068315481e-06,
+      "loss": 0.8514,
+      "step": 204
+    },
+    {
+      "epoch": 7.068965517241379,
+      "grad_norm": 0.37993335723876953,
+      "learning_rate": 4.213287038201943e-06,
+      "loss": 0.6894,
+      "step": 205
+    },
+    {
+      "epoch": 7.103448275862069,
+      "grad_norm": 0.3587632179260254,
+      "learning_rate": 4.12214747707527e-06,
+      "loss": 0.8874,
+      "step": 206
+    },
+    {
+      "epoch": 7.137931034482759,
+      "grad_norm": 0.4013674557209015,
+      "learning_rate": 4.0317478581749644e-06,
+      "loss": 0.6651,
+      "step": 207
+    },
+    {
+      "epoch": 7.172413793103448,
+      "grad_norm": 0.44422778487205505,
+      "learning_rate": 3.942099561591802e-06,
+      "loss": 0.817,
+      "step": 208
+    },
+    {
+      "epoch": 7.206896551724138,
+      "grad_norm": 0.39651286602020264,
+      "learning_rate": 3.853213872835229e-06,
+      "loss": 0.7115,
+      "step": 209
+    },
+    {
+      "epoch": 7.241379310344827,
+      "grad_norm": 0.45297321677207947,
+      "learning_rate": 3.7651019814126656e-06,
+      "loss": 0.8083,
+      "step": 210
+    },
+    {
+      "epoch": 7.275862068965517,
+      "grad_norm": 0.33265623450279236,
+      "learning_rate": 3.677774979420904e-06,
+      "loss": 0.7737,
+      "step": 211
+    },
+    {
+      "epoch": 7.310344827586207,
+      "grad_norm": 0.36475762724876404,
+      "learning_rate": 3.591243860149759e-06,
+      "loss": 0.7406,
+      "step": 212
+    },
+    {
+      "epoch": 7.344827586206897,
+      "grad_norm": 0.4376261532306671,
+      "learning_rate": 3.505519516698165e-06,
+      "loss": 0.7463,
+      "step": 213
+    },
+    {
+      "epoch": 7.379310344827586,
+      "grad_norm": 0.46567025780677795,
+      "learning_rate": 3.4206127406028744e-06,
+      "loss": 0.7571,
+      "step": 214
+    },
+    {
+      "epoch": 7.413793103448276,
+      "grad_norm": 0.38137590885162354,
+      "learning_rate": 3.3365342204799613e-06,
+      "loss": 0.733,
+      "step": 215
+    },
+    {
+      "epoch": 7.448275862068965,
+      "grad_norm": 0.37629345059394836,
+      "learning_rate": 3.2532945406792573e-06,
+      "loss": 0.7534,
+      "step": 216
+    },
+    {
+      "epoch": 7.482758620689655,
+      "grad_norm": 0.433769553899765,
+      "learning_rate": 3.1709041799519312e-06,
+      "loss": 0.7588,
+      "step": 217
+    },
+    {
+      "epoch": 7.517241379310345,
+      "grad_norm": 0.353617399930954,
+      "learning_rate": 3.089373510131354e-06,
+      "loss": 0.6982,
+      "step": 218
+    },
+    {
+      "epoch": 7.551724137931035,
+      "grad_norm": 0.3998333513736725,
+      "learning_rate": 3.0087127948274264e-06,
+      "loss": 0.8379,
+      "step": 219
+    },
+    {
+      "epoch": 7.586206896551724,
+      "grad_norm": 0.3798607289791107,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.8405,
+      "step": 220
+    },
+    {
+      "epoch": 7.620689655172414,
+      "grad_norm": 0.4249820411205292,
+      "learning_rate": 2.850041733353247e-06,
+      "loss": 0.7697,
+      "step": 221
+    },
+    {
+      "epoch": 7.655172413793103,
+      "grad_norm": 0.4408404231071472,
+      "learning_rate": 2.7720513617260857e-06,
+      "loss": 0.7761,
+      "step": 222
+    },
+    {
+      "epoch": 7.689655172413794,
+      "grad_norm": 0.4564493000507355,
+      "learning_rate": 2.694970891187225e-06,
+      "loss": 0.7459,
+      "step": 223
+    },
+    {
+      "epoch": 7.724137931034483,
+      "grad_norm": 0.45804357528686523,
+      "learning_rate": 2.6188100251265947e-06,
+      "loss": 0.9882,
+      "step": 224
+    },
+    {
+      "epoch": 7.758620689655173,
+      "grad_norm": 0.38965076208114624,
+      "learning_rate": 2.5435783511683444e-06,
+      "loss": 0.6766,
+      "step": 225
+    },
+    {
+      "epoch": 7.793103448275862,
+      "grad_norm": 0.40751808881759644,
+      "learning_rate": 2.469285339963892e-06,
+      "loss": 0.8678,
+      "step": 226
+    },
+    {
+      "epoch": 7.827586206896552,
+      "grad_norm": 0.4756832718849182,
+      "learning_rate": 2.395940343999691e-06,
+      "loss": 0.9249,
+      "step": 227
+    },
+    {
+      "epoch": 7.862068965517241,
+      "grad_norm": 0.4479880928993225,
+      "learning_rate": 2.323552596419889e-06,
+      "loss": 0.9394,
+      "step": 228
+    },
+    {
+      "epoch": 7.896551724137931,
+      "grad_norm": 0.40543538331985474,
+      "learning_rate": 2.2521312098639914e-06,
+      "loss": 0.6536,
+      "step": 229
+    },
+    {
+      "epoch": 7.931034482758621,
+      "grad_norm": 0.4100518226623535,
+      "learning_rate": 2.1816851753197023e-06,
+      "loss": 0.7255,
+      "step": 230
+    },
+    {
+      "epoch": 7.9655172413793105,
+      "grad_norm": 0.4805466830730438,
+      "learning_rate": 2.1122233609910903e-06,
+      "loss": 0.6486,
+      "step": 231
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.5520636439323425,
+      "learning_rate": 2.043754511182191e-06,
+      "loss": 0.5854,
+      "step": 232
+    },
+    {
+      "epoch": 8.03448275862069,
+      "grad_norm": 0.357243150472641,
+      "learning_rate": 1.9762872451962214e-06,
+      "loss": 0.7409,
+      "step": 233
+    },
+    {
+      "epoch": 8.068965517241379,
+      "grad_norm": 0.3809254467487335,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.873,
+      "step": 234
+    },
+    {
+      "epoch": 8.10344827586207,
+      "grad_norm": 0.36205536127090454,
+      "learning_rate": 1.8443913104073984e-06,
+      "loss": 0.8273,
+      "step": 235
+    },
+    {
+      "epoch": 8.137931034482758,
+      "grad_norm": 0.429328978061676,
+      "learning_rate": 1.7799792455209019e-06,
+      "loss": 0.9069,
+      "step": 236
+    },
+    {
+      "epoch": 8.172413793103448,
+      "grad_norm": 0.42592883110046387,
+      "learning_rate": 1.716601970199836e-06,
+      "loss": 0.8012,
+      "step": 237
+    },
+    {
+      "epoch": 8.206896551724139,
+      "grad_norm": 0.5000731348991394,
+      "learning_rate": 1.6542674627869738e-06,
+      "loss": 0.7902,
+      "step": 238
+    },
+    {
+      "epoch": 8.241379310344827,
+      "grad_norm": 0.473174512386322,
+      "learning_rate": 1.5929835703546992e-06,
+      "loss": 0.999,
+      "step": 239
+    },
+    {
+      "epoch": 8.275862068965518,
+      "grad_norm": 0.4019586741924286,
+      "learning_rate": 1.5327580077171589e-06,
+      "loss": 0.7231,
+      "step": 240
+    },
+    {
+      "epoch": 8.310344827586206,
+      "grad_norm": 0.4227881133556366,
+      "learning_rate": 1.4735983564590784e-06,
+      "loss": 0.7377,
+      "step": 241
+    },
+    {
+      "epoch": 8.344827586206897,
+      "grad_norm": 0.4504655599594116,
+      "learning_rate": 1.4155120639813392e-06,
+      "loss": 0.6787,
+      "step": 242
+    },
+    {
+      "epoch": 8.379310344827585,
+      "grad_norm": 0.43115106225013733,
+      "learning_rate": 1.3585064425634542e-06,
+      "loss": 0.7101,
+      "step": 243
+    },
+    {
+      "epoch": 8.413793103448276,
+      "grad_norm": 0.4861285090446472,
+      "learning_rate": 1.3025886684430467e-06,
+      "loss": 0.8464,
+      "step": 244
+    },
+    {
+      "epoch": 8.448275862068966,
+      "grad_norm": 0.45497927069664,
+      "learning_rate": 1.2477657809124632e-06,
+      "loss": 0.7153,
+      "step": 245
+    },
+    {
+      "epoch": 8.482758620689655,
+      "grad_norm": 0.4058876037597656,
+      "learning_rate": 1.19404468143262e-06,
+      "loss": 0.7608,
+      "step": 246
+    },
+    {
+      "epoch": 8.517241379310345,
+      "grad_norm": 0.406684011220932,
+      "learning_rate": 1.1414321327642019e-06,
+      "loss": 0.8353,
+      "step": 247
+    },
+    {
+      "epoch": 8.551724137931034,
+      "grad_norm": 0.3937000632286072,
+      "learning_rate": 1.0899347581163222e-06,
+      "loss": 0.7998,
+      "step": 248
+    },
+    {
+      "epoch": 8.586206896551724,
+      "grad_norm": 0.368868887424469,
+      "learning_rate": 1.0395590403127487e-06,
+      "loss": 0.7146,
+      "step": 249
+    },
+    {
+      "epoch": 8.620689655172415,
+      "grad_norm": 0.41563382744789124,
+      "learning_rate": 9.903113209758098e-07,
+      "loss": 0.8536,
+      "step": 250
+    },
+    {
+      "epoch": 8.655172413793103,
+      "grad_norm": 0.4131675362586975,
+      "learning_rate": 9.421977997280596e-07,
+      "loss": 0.6459,
+      "step": 251
+    },
+    {
+      "epoch": 8.689655172413794,
+      "grad_norm": 0.4058147668838501,
+      "learning_rate": 8.952245334118415e-07,
+      "loss": 0.7364,
+      "step": 252
+    },
+    {
+      "epoch": 8.724137931034482,
+      "grad_norm": 0.42709603905677795,
+      "learning_rate": 8.493974353268019e-07,
+      "loss": 0.7259,
+      "step": 253
+    },
+    {
+      "epoch": 8.758620689655173,
+      "grad_norm": 0.4050786793231964,
+      "learning_rate": 8.047222744854943e-07,
+      "loss": 0.7467,
+      "step": 254
+    },
+    {
+      "epoch": 8.793103448275861,
+      "grad_norm": 0.45394542813301086,
+      "learning_rate": 7.612046748871327e-07,
+      "loss": 0.6898,
+      "step": 255
+    },
+    {
+      "epoch": 8.827586206896552,
+      "grad_norm": 0.4538683295249939,
+      "learning_rate": 7.188501148096117e-07,
+      "loss": 0.6845,
+      "step": 256
+    },
+    {
+      "epoch": 8.862068965517242,
+      "grad_norm": 0.430452436208725,
+      "learning_rate": 6.776639261198581e-07,
+      "loss": 0.77,
+      "step": 257
+    },
+    {
+      "epoch": 8.89655172413793,
+      "grad_norm": 0.41714251041412354,
+      "learning_rate": 6.37651293602628e-07,
+      "loss": 0.7057,
+      "step": 258
+    },
+    {
+      "epoch": 8.931034482758621,
+      "grad_norm": 0.4864565432071686,
+      "learning_rate": 5.988172543078097e-07,
+      "loss": 0.6911,
+      "step": 259
+    },
+    {
+      "epoch": 8.96551724137931,
+      "grad_norm": 0.38794228434562683,
+      "learning_rate": 5.611666969163243e-07,
+      "loss": 0.7606,
+      "step": 260
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.5385807752609253,
+      "learning_rate": 5.247043611247127e-07,
+      "loss": 0.7045,
+      "step": 261
+    },
+    {
+      "epoch": 9.03448275862069,
+      "grad_norm": 0.42163336277008057,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 0.8221,
+      "step": 262
+    },
+    {
+      "epoch": 9.068965517241379,
+      "grad_norm": 0.4152377247810364,
+      "learning_rate": 4.553625646441928e-07,
+      "loss": 0.7311,
+      "step": 263
+    },
+    {
+      "epoch": 9.10344827586207,
+      "grad_norm": 0.39403805136680603,
+      "learning_rate": 4.224918331506955e-07,
+      "loss": 0.7236,
+      "step": 264
+    },
+    {
+      "epoch": 9.137931034482758,
+      "grad_norm": 0.40883564949035645,
+      "learning_rate": 3.908267805490051e-07,
+      "loss": 0.7725,
+      "step": 265
+    },
+    {
+      "epoch": 9.172413793103448,
+      "grad_norm": 0.37636932730674744,
+      "learning_rate": 3.603713930414676e-07,
+      "loss": 0.7272,
+      "step": 266
+    },
+    {
+      "epoch": 9.206896551724139,
+      "grad_norm": 0.44501543045043945,
+      "learning_rate": 3.3112950454993633e-07,
+      "loss": 0.7091,
+      "step": 267
+    },
+    {
+      "epoch": 9.241379310344827,
+      "grad_norm": 0.36911624670028687,
+      "learning_rate": 3.0310479623313125e-07,
+      "loss": 0.7032,
+      "step": 268
+    },
+    {
+      "epoch": 9.275862068965518,
+      "grad_norm": 0.44340014457702637,
+      "learning_rate": 2.7630079602323447e-07,
+      "loss": 0.7774,
+      "step": 269
+    },
+    {
+      "epoch": 9.310344827586206,
+      "grad_norm": 0.4391462206840515,
+      "learning_rate": 2.507208781817638e-07,
+      "loss": 0.706,
+      "step": 270
+    },
+    {
+      "epoch": 9.344827586206897,
+      "grad_norm": 0.3953486680984497,
+      "learning_rate": 2.2636826287480872e-07,
+      "loss": 0.7653,
+      "step": 271
+    },
+    {
+      "epoch": 9.379310344827585,
+      "grad_norm": 0.450130820274353,
+      "learning_rate": 2.0324601576764525e-07,
+      "loss": 0.783,
+      "step": 272
+    },
+    {
+      "epoch": 9.413793103448276,
+      "grad_norm": 0.4283774495124817,
+      "learning_rate": 1.81357047638816e-07,
+      "loss": 0.6993,
+      "step": 273
+    },
+    {
+      "epoch": 9.448275862068966,
+      "grad_norm": 0.46512722969055176,
+      "learning_rate": 1.6070411401370335e-07,
+      "loss": 0.6359,
+      "step": 274
+    },
+    {
+      "epoch": 9.482758620689655,
+      "grad_norm": 0.45328933000564575,
+      "learning_rate": 1.4128981481764115e-07,
+      "loss": 0.9826,
+      "step": 275
+    },
+    {
+      "epoch": 9.517241379310345,
+      "grad_norm": 0.342708557844162,
+      "learning_rate": 1.231165940486234e-07,
+      "loss": 0.7167,
+      "step": 276
+    },
+    {
+      "epoch": 9.551724137931034,
+      "grad_norm": 0.5037355422973633,
+      "learning_rate": 1.0618673946963365e-07,
+      "loss": 0.7886,
+      "step": 277
+    },
+    {
+      "epoch": 9.586206896551724,
+      "grad_norm": 0.4170833230018616,
+      "learning_rate": 9.0502382320653e-08,
+      "loss": 0.759,
+      "step": 278
+    },
+    {
+      "epoch": 9.620689655172415,
+      "grad_norm": 0.44028815627098083,
+      "learning_rate": 7.606549705035937e-08,
+      "loss": 0.8782,
+      "step": 279
+    },
+    {
+      "epoch": 9.655172413793103,
+      "grad_norm": 0.420846551656723,
+      "learning_rate": 6.287790106757396e-08,
+      "loss": 0.7216,
+      "step": 280
+    },
+    {
+      "epoch": 9.689655172413794,
+      "grad_norm": 0.4208323061466217,
+      "learning_rate": 5.094125451247656e-08,
+      "loss": 0.776,
+      "step": 281
+    },
+    {
+      "epoch": 9.724137931034482,
+      "grad_norm": 0.42419716715812683,
+      "learning_rate": 4.025706004760932e-08,
+      "loss": 0.6682,
+      "step": 282
+    },
+    {
+      "epoch": 9.758620689655173,
+      "grad_norm": 0.43146654963493347,
+      "learning_rate": 3.082666266872036e-08,
+      "loss": 0.7483,
+      "step": 283
+    },
+    {
+      "epoch": 9.793103448275861,
+      "grad_norm": 0.43936026096343994,
+      "learning_rate": 2.265124953543918e-08,
+      "loss": 0.9118,
+      "step": 284
+    },
+    {
+      "epoch": 9.827586206896552,
+      "grad_norm": 0.4402799606323242,
+      "learning_rate": 1.5731849821833955e-08,
+      "loss": 0.8107,
+      "step": 285
+    },
+    {
+      "epoch": 9.862068965517242,
+      "grad_norm": 0.377135306596756,
+      "learning_rate": 1.0069334586854106e-08,
+      "loss": 0.6527,
+      "step": 286
+    },
+    {
+      "epoch": 9.89655172413793,
+      "grad_norm": 0.452321857213974,
+      "learning_rate": 5.664416664666883e-09,
+      "loss": 0.8356,
+      "step": 287
+    },
+    {
+      "epoch": 9.931034482758621,
+      "grad_norm": 0.42655467987060547,
+      "learning_rate": 2.5176505749346937e-09,
+      "loss": 0.7422,
+      "step": 288
+    },
+    {
+      "epoch": 9.96551724137931,
+      "grad_norm": 0.41591566801071167,
+      "learning_rate": 6.294324529942942e-10,
+      "loss": 0.872,
+      "step": 289
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.5666583180427551,
+      "learning_rate": 0.0,
+      "loss": 0.8514,
+      "step": 290
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 290,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.501590410496e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

phi_sft/checkpoint-290/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6db4f317e6d2367337aa35eee1a071337d4c606da344355f0b63dd098c044fc
+size 5432

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6a6acde7c9c646707b9822328c2133636a7e7784d24cdb1e849387e4d2d708e
+oid sha256:b6db4f317e6d2367337aa35eee1a071337d4c606da344355f0b63dd098c044fc
 size 5432