Training in progress, step 300, checkpoint

checkpoint-300/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/Phi-3-mini-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 0.11.1

checkpoint-300/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 512,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "qkv_proj",
+    "down_proj",
+    "gate_up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b9cdcb49729016a59ca73af1c5e74131f06ee3fbc9aa15777c1cdecd77f3f54
+size 2004651224

checkpoint-300/added_tokens.json

@@ -0,0 +1,17 @@
+{
+  "</plan>": 32014,
+  "</thinking>": 32012,
+  "<plan>": 32013,
+  "<thinking>": 32011,
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:409894f652d7264a0ffb916a1618168dbf624bb4ca17499ed18da0672ff9cfcf
+size 4009448634

checkpoint-300/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:155980f8ca2dac19c15298068a5d564e9fd9c2a6bd699727a9b4b40f7225aea8
+size 15984

checkpoint-300/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30ea79ff98d65e758d55a9c807a84b989e6778620c1defa590dfb3b94c528f89
+size 15984

checkpoint-300/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7c6a62653ba5ce15530de6cbcf4a3f2987c8606143149a33ce36863ec226ad2
+size 15984

checkpoint-300/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68635ed424947443fbd736471d033e55ff35e7ef9d6845d0e0cfc6812e5ac0b1
+size 15984

checkpoint-300/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1d77e8c21d7b489ba8ca2962081f4b8843db515a5e66e029424ee3ea8dd7f45
+size 15984

checkpoint-300/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:814d24d9c622cfa0d389d4cb35079aacc55b1a54c781ee1d7730330960b9e04e
+size 15984

checkpoint-300/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9726aa6d0c3640facdba38f39cdcb21ae0c854e68b6529717aef135454833fa
+size 15984

checkpoint-300/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c201a8194443543b2d67b8fd0c6bdbc2c200e0265d8f356ec3cf94990d559e06
+size 15984

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f09c8348bb59de6a4274cfa62ab86a9d92397402dc26ad8598fd8f4160fb3f82
+size 1064

checkpoint-300/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
+  }
+}

checkpoint-300/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-300/tokenizer_config.json

@@ -0,0 +1,163 @@
+{
+  "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
+    },
+    "32011": {
+      "content": "<thinking>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "</thinking>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<plan>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32014": {
+      "content": "</plan>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|system|>' + '\n' + message['content'] + '<|end|>' + '\n'}}{% elif (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
+}

checkpoint-300/trainer_state.json

@@ -0,0 +1,2197 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0101010101010102,
+  "eval_steps": 38,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003367003367003367,
+      "grad_norm": 2.0,
+      "learning_rate": 4.5454545454545457e-07,
+      "loss": 1.0833,
+      "step": 1
+    },
+    {
+      "epoch": 0.003367003367003367,
+      "eval_loss": 1.032954454421997,
+      "eval_runtime": 8.7786,
+      "eval_samples_per_second": 56.957,
+      "eval_steps_per_second": 3.645,
+      "step": 1
+    },
+    {
+      "epoch": 0.006734006734006734,
+      "grad_norm": 2.265625,
+      "learning_rate": 9.090909090909091e-07,
+      "loss": 0.996,
+      "step": 2
+    },
+    {
+      "epoch": 0.010101010101010102,
+      "grad_norm": 1.6484375,
+      "learning_rate": 1.3636363636363636e-06,
+      "loss": 1.0487,
+      "step": 3
+    },
+    {
+      "epoch": 0.013468013468013467,
+      "grad_norm": 2.046875,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 1.0554,
+      "step": 4
+    },
+    {
+      "epoch": 0.016835016835016835,
+      "grad_norm": 2.4375,
+      "learning_rate": 2.2727272727272728e-06,
+      "loss": 1.0341,
+      "step": 5
+    },
+    {
+      "epoch": 0.020202020202020204,
+      "grad_norm": 1.9609375,
+      "learning_rate": 2.7272727272727272e-06,
+      "loss": 1.0132,
+      "step": 6
+    },
+    {
+      "epoch": 0.02356902356902357,
+      "grad_norm": 2.625,
+      "learning_rate": 3.181818181818182e-06,
+      "loss": 1.0298,
+      "step": 7
+    },
+    {
+      "epoch": 0.026936026936026935,
+      "grad_norm": 2.296875,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 1.0216,
+      "step": 8
+    },
+    {
+      "epoch": 0.030303030303030304,
+      "grad_norm": 2.234375,
+      "learning_rate": 4.0909090909090915e-06,
+      "loss": 1.0736,
+      "step": 9
+    },
+    {
+      "epoch": 0.03367003367003367,
+      "grad_norm": 2.1875,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 1.0216,
+      "step": 10
+    },
+    {
+      "epoch": 0.037037037037037035,
+      "grad_norm": 2.359375,
+      "learning_rate": 5e-06,
+      "loss": 1.0075,
+      "step": 11
+    },
+    {
+      "epoch": 0.04040404040404041,
+      "grad_norm": 1.890625,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 1.051,
+      "step": 12
+    },
+    {
+      "epoch": 0.04377104377104377,
+      "grad_norm": 1.90625,
+      "learning_rate": 5.90909090909091e-06,
+      "loss": 1.0655,
+      "step": 13
+    },
+    {
+      "epoch": 0.04713804713804714,
+      "grad_norm": 1.6484375,
+      "learning_rate": 6.363636363636364e-06,
+      "loss": 1.0297,
+      "step": 14
+    },
+    {
+      "epoch": 0.050505050505050504,
+      "grad_norm": 1.6953125,
+      "learning_rate": 6.818181818181818e-06,
+      "loss": 1.0411,
+      "step": 15
+    },
+    {
+      "epoch": 0.05387205387205387,
+      "grad_norm": 1.9921875,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 1.0618,
+      "step": 16
+    },
+    {
+      "epoch": 0.05723905723905724,
+      "grad_norm": 1.4453125,
+      "learning_rate": 7.727272727272727e-06,
+      "loss": 1.0052,
+      "step": 17
+    },
+    {
+      "epoch": 0.06060606060606061,
+      "grad_norm": 1.390625,
+      "learning_rate": 8.181818181818183e-06,
+      "loss": 1.0053,
+      "step": 18
+    },
+    {
+      "epoch": 0.06397306397306397,
+      "grad_norm": 1.2734375,
+      "learning_rate": 8.636363636363637e-06,
+      "loss": 0.9786,
+      "step": 19
+    },
+    {
+      "epoch": 0.06734006734006734,
+      "grad_norm": 1.234375,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 1.0419,
+      "step": 20
+    },
+    {
+      "epoch": 0.0707070707070707,
+      "grad_norm": 1.1484375,
+      "learning_rate": 9.545454545454547e-06,
+      "loss": 1.0356,
+      "step": 21
+    },
+    {
+      "epoch": 0.07407407407407407,
+      "grad_norm": 1.28125,
+      "learning_rate": 1e-05,
+      "loss": 0.9778,
+      "step": 22
+    },
+    {
+      "epoch": 0.07744107744107744,
+      "grad_norm": 1.1875,
+      "learning_rate": 1.0454545454545455e-05,
+      "loss": 0.9691,
+      "step": 23
+    },
+    {
+      "epoch": 0.08080808080808081,
+      "grad_norm": 1.1953125,
+      "learning_rate": 1.0909090909090909e-05,
+      "loss": 1.0408,
+      "step": 24
+    },
+    {
+      "epoch": 0.08417508417508418,
+      "grad_norm": 1.078125,
+      "learning_rate": 1.1363636363636366e-05,
+      "loss": 0.9799,
+      "step": 25
+    },
+    {
+      "epoch": 0.08754208754208755,
+      "grad_norm": 1.0390625,
+      "learning_rate": 1.181818181818182e-05,
+      "loss": 0.9756,
+      "step": 26
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 1.1875,
+      "learning_rate": 1.2272727272727274e-05,
+      "loss": 1.0451,
+      "step": 27
+    },
+    {
+      "epoch": 0.09427609427609428,
+      "grad_norm": 1.0546875,
+      "learning_rate": 1.2727272727272728e-05,
+      "loss": 1.0093,
+      "step": 28
+    },
+    {
+      "epoch": 0.09764309764309764,
+      "grad_norm": 0.96484375,
+      "learning_rate": 1.3181818181818183e-05,
+      "loss": 0.99,
+      "step": 29
+    },
+    {
+      "epoch": 0.10101010101010101,
+      "grad_norm": 1.0703125,
+      "learning_rate": 1.3636363636363637e-05,
+      "loss": 1.0079,
+      "step": 30
+    },
+    {
+      "epoch": 0.10437710437710437,
+      "grad_norm": 0.89453125,
+      "learning_rate": 1.4090909090909092e-05,
+      "loss": 0.9653,
+      "step": 31
+    },
+    {
+      "epoch": 0.10774410774410774,
+      "grad_norm": 1.0546875,
+      "learning_rate": 1.4545454545454546e-05,
+      "loss": 0.9926,
+      "step": 32
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 0.96875,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.9857,
+      "step": 33
+    },
+    {
+      "epoch": 0.11447811447811448,
+      "grad_norm": 1.1484375,
+      "learning_rate": 1.5454545454545454e-05,
+      "loss": 0.9676,
+      "step": 34
+    },
+    {
+      "epoch": 0.11784511784511785,
+      "grad_norm": 1.078125,
+      "learning_rate": 1.590909090909091e-05,
+      "loss": 0.9686,
+      "step": 35
+    },
+    {
+      "epoch": 0.12121212121212122,
+      "grad_norm": 0.8203125,
+      "learning_rate": 1.6363636363636366e-05,
+      "loss": 0.9182,
+      "step": 36
+    },
+    {
+      "epoch": 0.12457912457912458,
+      "grad_norm": 0.8515625,
+      "learning_rate": 1.681818181818182e-05,
+      "loss": 0.9506,
+      "step": 37
+    },
+    {
+      "epoch": 0.12794612794612795,
+      "grad_norm": 0.86328125,
+      "learning_rate": 1.7272727272727274e-05,
+      "loss": 0.9533,
+      "step": 38
+    },
+    {
+      "epoch": 0.12794612794612795,
+      "eval_loss": 0.9329763054847717,
+      "eval_runtime": 8.7095,
+      "eval_samples_per_second": 57.409,
+      "eval_steps_per_second": 3.674,
+      "step": 38
+    },
+    {
+      "epoch": 0.13131313131313133,
+      "grad_norm": 0.7890625,
+      "learning_rate": 1.772727272727273e-05,
+      "loss": 0.9225,
+      "step": 39
+    },
+    {
+      "epoch": 0.13468013468013468,
+      "grad_norm": 0.890625,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 0.9378,
+      "step": 40
+    },
+    {
+      "epoch": 0.13804713804713806,
+      "grad_norm": 1.046875,
+      "learning_rate": 1.8636363636363638e-05,
+      "loss": 0.8982,
+      "step": 41
+    },
+    {
+      "epoch": 0.1414141414141414,
+      "grad_norm": 0.94921875,
+      "learning_rate": 1.9090909090909094e-05,
+      "loss": 0.8958,
+      "step": 42
+    },
+    {
+      "epoch": 0.1447811447811448,
+      "grad_norm": 0.9765625,
+      "learning_rate": 1.9545454545454546e-05,
+      "loss": 0.8796,
+      "step": 43
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.92578125,
+      "learning_rate": 2e-05,
+      "loss": 0.8808,
+      "step": 44
+    },
+    {
+      "epoch": 0.15151515151515152,
+      "grad_norm": 0.94921875,
+      "learning_rate": 1.9999931213623708e-05,
+      "loss": 0.8638,
+      "step": 45
+    },
+    {
+      "epoch": 0.15488215488215487,
+      "grad_norm": 1.0390625,
+      "learning_rate": 1.999972485544114e-05,
+      "loss": 0.9124,
+      "step": 46
+    },
+    {
+      "epoch": 0.15824915824915825,
+      "grad_norm": 1.046875,
+      "learning_rate": 1.999938092829122e-05,
+      "loss": 0.8757,
+      "step": 47
+    },
+    {
+      "epoch": 0.16161616161616163,
+      "grad_norm": 0.73046875,
+      "learning_rate": 1.999889943690545e-05,
+      "loss": 0.885,
+      "step": 48
+    },
+    {
+      "epoch": 0.16498316498316498,
+      "grad_norm": 0.86328125,
+      "learning_rate": 1.9998280387907845e-05,
+      "loss": 0.8664,
+      "step": 49
+    },
+    {
+      "epoch": 0.16835016835016836,
+      "grad_norm": 0.87109375,
+      "learning_rate": 1.9997523789814827e-05,
+      "loss": 0.8512,
+      "step": 50
+    },
+    {
+      "epoch": 0.1717171717171717,
+      "grad_norm": 0.80859375,
+      "learning_rate": 1.9996629653035128e-05,
+      "loss": 0.8428,
+      "step": 51
+    },
+    {
+      "epoch": 0.1750841750841751,
+      "grad_norm": 0.71875,
+      "learning_rate": 1.9995597989869625e-05,
+      "loss": 0.8536,
+      "step": 52
+    },
+    {
+      "epoch": 0.17845117845117844,
+      "grad_norm": 0.6171875,
+      "learning_rate": 1.9994428814511205e-05,
+      "loss": 0.82,
+      "step": 53
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 0.71875,
+      "learning_rate": 1.999312214304453e-05,
+      "loss": 0.8043,
+      "step": 54
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "grad_norm": 0.8046875,
+      "learning_rate": 1.9991677993445832e-05,
+      "loss": 0.8525,
+      "step": 55
+    },
+    {
+      "epoch": 0.18855218855218855,
+      "grad_norm": 0.6015625,
+      "learning_rate": 1.9990096385582682e-05,
+      "loss": 0.7958,
+      "step": 56
+    },
+    {
+      "epoch": 0.1919191919191919,
+      "grad_norm": 0.79296875,
+      "learning_rate": 1.998837734121369e-05,
+      "loss": 0.8001,
+      "step": 57
+    },
+    {
+      "epoch": 0.19528619528619529,
+      "grad_norm": 0.7109375,
+      "learning_rate": 1.9986520883988233e-05,
+      "loss": 0.805,
+      "step": 58
+    },
+    {
+      "epoch": 0.19865319865319866,
+      "grad_norm": 0.84375,
+      "learning_rate": 1.9984527039446093e-05,
+      "loss": 0.7821,
+      "step": 59
+    },
+    {
+      "epoch": 0.20202020202020202,
+      "grad_norm": 1.1015625,
+      "learning_rate": 1.998239583501714e-05,
+      "loss": 0.7932,
+      "step": 60
+    },
+    {
+      "epoch": 0.2053872053872054,
+      "grad_norm": 0.6953125,
+      "learning_rate": 1.9980127300020946e-05,
+      "loss": 0.7925,
+      "step": 61
+    },
+    {
+      "epoch": 0.20875420875420875,
+      "grad_norm": 0.60546875,
+      "learning_rate": 1.9977721465666365e-05,
+      "loss": 0.7846,
+      "step": 62
+    },
+    {
+      "epoch": 0.21212121212121213,
+      "grad_norm": 0.7265625,
+      "learning_rate": 1.9975178365051123e-05,
+      "loss": 0.7671,
+      "step": 63
+    },
+    {
+      "epoch": 0.21548821548821548,
+      "grad_norm": 0.70703125,
+      "learning_rate": 1.997249803316136e-05,
+      "loss": 0.8194,
+      "step": 64
+    },
+    {
+      "epoch": 0.21885521885521886,
+      "grad_norm": 0.81640625,
+      "learning_rate": 1.9969680506871138e-05,
+      "loss": 0.7607,
+      "step": 65
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.61328125,
+      "learning_rate": 1.9966725824941933e-05,
+      "loss": 0.7858,
+      "step": 66
+    },
+    {
+      "epoch": 0.2255892255892256,
+      "grad_norm": 0.66015625,
+      "learning_rate": 1.9963634028022133e-05,
+      "loss": 0.7546,
+      "step": 67
+    },
+    {
+      "epoch": 0.22895622895622897,
+      "grad_norm": 0.6875,
+      "learning_rate": 1.9960405158646425e-05,
+      "loss": 0.7915,
+      "step": 68
+    },
+    {
+      "epoch": 0.23232323232323232,
+      "grad_norm": 0.59765625,
+      "learning_rate": 1.9957039261235263e-05,
+      "loss": 0.7324,
+      "step": 69
+    },
+    {
+      "epoch": 0.2356902356902357,
+      "grad_norm": 0.65625,
+      "learning_rate": 1.9953536382094218e-05,
+      "loss": 0.7735,
+      "step": 70
+    },
+    {
+      "epoch": 0.23905723905723905,
+      "grad_norm": 0.984375,
+      "learning_rate": 1.9949896569413368e-05,
+      "loss": 0.7356,
+      "step": 71
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 0.8125,
+      "learning_rate": 1.9946119873266615e-05,
+      "loss": 0.7407,
+      "step": 72
+    },
+    {
+      "epoch": 0.24579124579124578,
+      "grad_norm": 0.76953125,
+      "learning_rate": 1.9942206345611008e-05,
+      "loss": 0.7124,
+      "step": 73
+    },
+    {
+      "epoch": 0.24915824915824916,
+      "grad_norm": 0.6640625,
+      "learning_rate": 1.9938156040286027e-05,
+      "loss": 0.7295,
+      "step": 74
+    },
+    {
+      "epoch": 0.25252525252525254,
+      "grad_norm": 0.5546875,
+      "learning_rate": 1.993396901301283e-05,
+      "loss": 0.733,
+      "step": 75
+    },
+    {
+      "epoch": 0.2558922558922559,
+      "grad_norm": 0.5703125,
+      "learning_rate": 1.9929645321393505e-05,
+      "loss": 0.779,
+      "step": 76
+    },
+    {
+      "epoch": 0.2558922558922559,
+      "eval_loss": 0.7325140237808228,
+      "eval_runtime": 8.7635,
+      "eval_samples_per_second": 57.055,
+      "eval_steps_per_second": 3.652,
+      "step": 76
+    },
+    {
+      "epoch": 0.25925925925925924,
+      "grad_norm": 0.67578125,
+      "learning_rate": 1.992518502491028e-05,
+      "loss": 0.7345,
+      "step": 77
+    },
+    {
+      "epoch": 0.26262626262626265,
+      "grad_norm": 0.5,
+      "learning_rate": 1.9920588184924664e-05,
+      "loss": 0.7102,
+      "step": 78
+    },
+    {
+      "epoch": 0.265993265993266,
+      "grad_norm": 0.51953125,
+      "learning_rate": 1.9915854864676665e-05,
+      "loss": 0.7433,
+      "step": 79
+    },
+    {
+      "epoch": 0.26936026936026936,
+      "grad_norm": 0.48828125,
+      "learning_rate": 1.991098512928386e-05,
+      "loss": 0.7628,
+      "step": 80
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 0.55859375,
+      "learning_rate": 1.990597904574055e-05,
+      "loss": 0.6858,
+      "step": 81
+    },
+    {
+      "epoch": 0.2760942760942761,
+      "grad_norm": 0.5390625,
+      "learning_rate": 1.9900836682916796e-05,
+      "loss": 0.7169,
+      "step": 82
+    },
+    {
+      "epoch": 0.27946127946127947,
+      "grad_norm": 0.494140625,
+      "learning_rate": 1.9895558111557503e-05,
+      "loss": 0.6995,
+      "step": 83
+    },
+    {
+      "epoch": 0.2828282828282828,
+      "grad_norm": 0.4765625,
+      "learning_rate": 1.989014340428143e-05,
+      "loss": 0.7234,
+      "step": 84
+    },
+    {
+      "epoch": 0.28619528619528617,
+      "grad_norm": 0.5546875,
+      "learning_rate": 1.98845926355802e-05,
+      "loss": 0.7182,
+      "step": 85
+    },
+    {
+      "epoch": 0.2895622895622896,
+      "grad_norm": 0.51171875,
+      "learning_rate": 1.9878905881817254e-05,
+      "loss": 0.6837,
+      "step": 86
+    },
+    {
+      "epoch": 0.29292929292929293,
+      "grad_norm": 0.54296875,
+      "learning_rate": 1.9873083221226833e-05,
+      "loss": 0.6759,
+      "step": 87
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.52734375,
+      "learning_rate": 1.986712473391289e-05,
+      "loss": 0.7275,
+      "step": 88
+    },
+    {
+      "epoch": 0.2996632996632997,
+      "grad_norm": 0.51171875,
+      "learning_rate": 1.986103050184797e-05,
+      "loss": 0.728,
+      "step": 89
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 0.4609375,
+      "learning_rate": 1.9854800608872096e-05,
+      "loss": 0.6865,
+      "step": 90
+    },
+    {
+      "epoch": 0.3063973063973064,
+      "grad_norm": 0.44921875,
+      "learning_rate": 1.9848435140691627e-05,
+      "loss": 0.6816,
+      "step": 91
+    },
+    {
+      "epoch": 0.30976430976430974,
+      "grad_norm": 0.4453125,
+      "learning_rate": 1.9841934184878056e-05,
+      "loss": 0.6767,
+      "step": 92
+    },
+    {
+      "epoch": 0.31313131313131315,
+      "grad_norm": 0.546875,
+      "learning_rate": 1.9835297830866827e-05,
+      "loss": 0.7623,
+      "step": 93
+    },
+    {
+      "epoch": 0.3164983164983165,
+      "grad_norm": 0.45703125,
+      "learning_rate": 1.9828526169956083e-05,
+      "loss": 0.7193,
+      "step": 94
+    },
+    {
+      "epoch": 0.31986531986531985,
+      "grad_norm": 0.482421875,
+      "learning_rate": 1.9821619295305432e-05,
+      "loss": 0.6573,
+      "step": 95
+    },
+    {
+      "epoch": 0.32323232323232326,
+      "grad_norm": 0.43359375,
+      "learning_rate": 1.9814577301934647e-05,
+      "loss": 0.7,
+      "step": 96
+    },
+    {
+      "epoch": 0.3265993265993266,
+      "grad_norm": 0.56640625,
+      "learning_rate": 1.980740028672237e-05,
+      "loss": 0.7111,
+      "step": 97
+    },
+    {
+      "epoch": 0.32996632996632996,
+      "grad_norm": 0.47265625,
+      "learning_rate": 1.9800088348404778e-05,
+      "loss": 0.7025,
+      "step": 98
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.51953125,
+      "learning_rate": 1.9792641587574212e-05,
+      "loss": 0.6925,
+      "step": 99
+    },
+    {
+      "epoch": 0.3367003367003367,
+      "grad_norm": 0.484375,
+      "learning_rate": 1.9785060106677818e-05,
+      "loss": 0.6715,
+      "step": 100
+    },
+    {
+      "epoch": 0.3400673400673401,
+      "grad_norm": 0.443359375,
+      "learning_rate": 1.977734401001611e-05,
+      "loss": 0.6929,
+      "step": 101
+    },
+    {
+      "epoch": 0.3434343434343434,
+      "grad_norm": 0.5703125,
+      "learning_rate": 1.9769493403741556e-05,
+      "loss": 0.7126,
+      "step": 102
+    },
+    {
+      "epoch": 0.3468013468013468,
+      "grad_norm": 0.490234375,
+      "learning_rate": 1.9761508395857106e-05,
+      "loss": 0.7012,
+      "step": 103
+    },
+    {
+      "epoch": 0.3501683501683502,
+      "grad_norm": 0.54296875,
+      "learning_rate": 1.9753389096214716e-05,
+      "loss": 0.6819,
+      "step": 104
+    },
+    {
+      "epoch": 0.35353535353535354,
+      "grad_norm": 0.412109375,
+      "learning_rate": 1.974513561651382e-05,
+      "loss": 0.7073,
+      "step": 105
+    },
+    {
+      "epoch": 0.3569023569023569,
+      "grad_norm": 0.4296875,
+      "learning_rate": 1.9736748070299813e-05,
+      "loss": 0.6743,
+      "step": 106
+    },
+    {
+      "epoch": 0.3602693602693603,
+      "grad_norm": 0.4140625,
+      "learning_rate": 1.9728226572962474e-05,
+      "loss": 0.6746,
+      "step": 107
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.5078125,
+      "learning_rate": 1.9719571241734395e-05,
+      "loss": 0.6729,
+      "step": 108
+    },
+    {
+      "epoch": 0.367003367003367,
+      "grad_norm": 0.74609375,
+      "learning_rate": 1.9710782195689343e-05,
+      "loss": 0.6781,
+      "step": 109
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.462890625,
+      "learning_rate": 1.9701859555740647e-05,
+      "loss": 0.6976,
+      "step": 110
+    },
+    {
+      "epoch": 0.37373737373737376,
+      "grad_norm": 0.396484375,
+      "learning_rate": 1.9692803444639517e-05,
+      "loss": 0.6464,
+      "step": 111
+    },
+    {
+      "epoch": 0.3771043771043771,
+      "grad_norm": 0.58203125,
+      "learning_rate": 1.9683613986973373e-05,
+      "loss": 0.6614,
+      "step": 112
+    },
+    {
+      "epoch": 0.38047138047138046,
+      "grad_norm": 0.416015625,
+      "learning_rate": 1.967429130916411e-05,
+      "loss": 0.6087,
+      "step": 113
+    },
+    {
+      "epoch": 0.3838383838383838,
+      "grad_norm": 0.431640625,
+      "learning_rate": 1.966483553946637e-05,
+      "loss": 0.6894,
+      "step": 114
+    },
+    {
+      "epoch": 0.3838383838383838,
+      "eval_loss": 0.6650684475898743,
+      "eval_runtime": 8.7352,
+      "eval_samples_per_second": 57.24,
+      "eval_steps_per_second": 3.663,
+      "step": 114
+    },
+    {
+      "epoch": 0.3872053872053872,
+      "grad_norm": 0.396484375,
+      "learning_rate": 1.9655246807965786e-05,
+      "loss": 0.6962,
+      "step": 115
+    },
+    {
+      "epoch": 0.39057239057239057,
+      "grad_norm": 0.39453125,
+      "learning_rate": 1.9645525246577168e-05,
+      "loss": 0.6614,
+      "step": 116
+    },
+    {
+      "epoch": 0.3939393939393939,
+      "grad_norm": 0.427734375,
+      "learning_rate": 1.963567098904272e-05,
+      "loss": 0.6889,
+      "step": 117
+    },
+    {
+      "epoch": 0.39730639730639733,
+      "grad_norm": 0.357421875,
+      "learning_rate": 1.9625684170930172e-05,
+      "loss": 0.642,
+      "step": 118
+    },
+    {
+      "epoch": 0.4006734006734007,
+      "grad_norm": 0.3828125,
+      "learning_rate": 1.9615564929630925e-05,
+      "loss": 0.6185,
+      "step": 119
+    },
+    {
+      "epoch": 0.40404040404040403,
+      "grad_norm": 0.396484375,
+      "learning_rate": 1.9605313404358176e-05,
+      "loss": 0.6624,
+      "step": 120
+    },
+    {
+      "epoch": 0.4074074074074074,
+      "grad_norm": 0.390625,
+      "learning_rate": 1.9594929736144978e-05,
+      "loss": 0.6632,
+      "step": 121
+    },
+    {
+      "epoch": 0.4107744107744108,
+      "grad_norm": 0.51953125,
+      "learning_rate": 1.9584414067842304e-05,
+      "loss": 0.6504,
+      "step": 122
+    },
+    {
+      "epoch": 0.41414141414141414,
+      "grad_norm": 0.44140625,
+      "learning_rate": 1.957376654411711e-05,
+      "loss": 0.6543,
+      "step": 123
+    },
+    {
+      "epoch": 0.4175084175084175,
+      "grad_norm": 0.48828125,
+      "learning_rate": 1.9562987311450298e-05,
+      "loss": 0.626,
+      "step": 124
+    },
+    {
+      "epoch": 0.4208754208754209,
+      "grad_norm": 0.38671875,
+      "learning_rate": 1.955207651813475e-05,
+      "loss": 0.7022,
+      "step": 125
+    },
+    {
+      "epoch": 0.42424242424242425,
+      "grad_norm": 0.34765625,
+      "learning_rate": 1.954103431427325e-05,
+      "loss": 0.6574,
+      "step": 126
+    },
+    {
+      "epoch": 0.4276094276094276,
+      "grad_norm": 0.3984375,
+      "learning_rate": 1.952986085177643e-05,
+      "loss": 0.6068,
+      "step": 127
+    },
+    {
+      "epoch": 0.43097643097643096,
+      "grad_norm": 0.380859375,
+      "learning_rate": 1.9518556284360696e-05,
+      "loss": 0.6538,
+      "step": 128
+    },
+    {
+      "epoch": 0.43434343434343436,
+      "grad_norm": 0.42578125,
+      "learning_rate": 1.950712076754609e-05,
+      "loss": 0.7139,
+      "step": 129
+    },
+    {
+      "epoch": 0.4377104377104377,
+      "grad_norm": 0.42578125,
+      "learning_rate": 1.949555445865417e-05,
+      "loss": 0.6362,
+      "step": 130
+    },
+    {
+      "epoch": 0.44107744107744107,
+      "grad_norm": 0.357421875,
+      "learning_rate": 1.9483857516805823e-05,
+      "loss": 0.6382,
+      "step": 131
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.337890625,
+      "learning_rate": 1.9472030102919102e-05,
+      "loss": 0.6522,
+      "step": 132
+    },
+    {
+      "epoch": 0.4478114478114478,
+      "grad_norm": 0.390625,
+      "learning_rate": 1.9460072379706995e-05,
+      "loss": 0.6583,
+      "step": 133
+    },
+    {
+      "epoch": 0.4511784511784512,
+      "grad_norm": 0.373046875,
+      "learning_rate": 1.9447984511675192e-05,
+      "loss": 0.6343,
+      "step": 134
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.392578125,
+      "learning_rate": 1.9435766665119823e-05,
+      "loss": 0.6442,
+      "step": 135
+    },
+    {
+      "epoch": 0.45791245791245794,
+      "grad_norm": 0.375,
+      "learning_rate": 1.942341900812516e-05,
+      "loss": 0.6286,
+      "step": 136
+    },
+    {
+      "epoch": 0.4612794612794613,
+      "grad_norm": 0.427734375,
+      "learning_rate": 1.9410941710561323e-05,
+      "loss": 0.6596,
+      "step": 137
+    },
+    {
+      "epoch": 0.46464646464646464,
+      "grad_norm": 0.423828125,
+      "learning_rate": 1.939833494408193e-05,
+      "loss": 0.6632,
+      "step": 138
+    },
+    {
+      "epoch": 0.468013468013468,
+      "grad_norm": 0.349609375,
+      "learning_rate": 1.9385598882121735e-05,
+      "loss": 0.6525,
+      "step": 139
+    },
+    {
+      "epoch": 0.4713804713804714,
+      "grad_norm": 0.431640625,
+      "learning_rate": 1.9372733699894253e-05,
+      "loss": 0.6136,
+      "step": 140
+    },
+    {
+      "epoch": 0.47474747474747475,
+      "grad_norm": 0.37109375,
+      "learning_rate": 1.935973957438933e-05,
+      "loss": 0.6908,
+      "step": 141
+    },
+    {
+      "epoch": 0.4781144781144781,
+      "grad_norm": 0.341796875,
+      "learning_rate": 1.934661668437073e-05,
+      "loss": 0.6374,
+      "step": 142
+    },
+    {
+      "epoch": 0.48148148148148145,
+      "grad_norm": 0.37890625,
+      "learning_rate": 1.9333365210373668e-05,
+      "loss": 0.6386,
+      "step": 143
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 0.3828125,
+      "learning_rate": 1.9319985334702315e-05,
+      "loss": 0.6775,
+      "step": 144
+    },
+    {
+      "epoch": 0.4882154882154882,
+      "grad_norm": 0.400390625,
+      "learning_rate": 1.9306477241427303e-05,
+      "loss": 0.6006,
+      "step": 145
+    },
+    {
+      "epoch": 0.49158249158249157,
+      "grad_norm": 0.37890625,
+      "learning_rate": 1.9292841116383192e-05,
+      "loss": 0.6123,
+      "step": 146
+    },
+    {
+      "epoch": 0.494949494949495,
+      "grad_norm": 0.416015625,
+      "learning_rate": 1.9279077147165903e-05,
+      "loss": 0.6198,
+      "step": 147
+    },
+    {
+      "epoch": 0.4983164983164983,
+      "grad_norm": 0.365234375,
+      "learning_rate": 1.9265185523130156e-05,
+      "loss": 0.624,
+      "step": 148
+    },
+    {
+      "epoch": 0.5016835016835017,
+      "grad_norm": 0.337890625,
+      "learning_rate": 1.9251166435386837e-05,
+      "loss": 0.6348,
+      "step": 149
+    },
+    {
+      "epoch": 0.5050505050505051,
+      "grad_norm": 0.361328125,
+      "learning_rate": 1.9237020076800407e-05,
+      "loss": 0.6379,
+      "step": 150
+    },
+    {
+      "epoch": 0.5084175084175084,
+      "grad_norm": 0.3828125,
+      "learning_rate": 1.9222746641986207e-05,
+      "loss": 0.6065,
+      "step": 151
+    },
+    {
+      "epoch": 0.5117845117845118,
+      "grad_norm": 0.419921875,
+      "learning_rate": 1.920834632730781e-05,
+      "loss": 0.6137,
+      "step": 152
+    },
+    {
+      "epoch": 0.5117845117845118,
+      "eval_loss": 0.6364830732345581,
+      "eval_runtime": 8.689,
+      "eval_samples_per_second": 57.544,
+      "eval_steps_per_second": 3.683,
+      "step": 152
+    },
+    {
+      "epoch": 0.5151515151515151,
+      "grad_norm": 0.365234375,
+      "learning_rate": 1.919381933087431e-05,
+      "loss": 0.6596,
+      "step": 153
+    },
+    {
+      "epoch": 0.5185185185185185,
+      "grad_norm": 0.38671875,
+      "learning_rate": 1.9179165852537596e-05,
+      "loss": 0.6292,
+      "step": 154
+    },
+    {
+      "epoch": 0.5218855218855218,
+      "grad_norm": 0.345703125,
+      "learning_rate": 1.9164386093889598e-05,
+      "loss": 0.6555,
+      "step": 155
+    },
+    {
+      "epoch": 0.5252525252525253,
+      "grad_norm": 0.376953125,
+      "learning_rate": 1.9149480258259535e-05,
+      "loss": 0.632,
+      "step": 156
+    },
+    {
+      "epoch": 0.5286195286195287,
+      "grad_norm": 0.3515625,
+      "learning_rate": 1.9134448550711077e-05,
+      "loss": 0.644,
+      "step": 157
+    },
+    {
+      "epoch": 0.531986531986532,
+      "grad_norm": 0.353515625,
+      "learning_rate": 1.9119291178039573e-05,
+      "loss": 0.6549,
+      "step": 158
+    },
+    {
+      "epoch": 0.5353535353535354,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.9104008348769164e-05,
+      "loss": 0.6572,
+      "step": 159
+    },
+    {
+      "epoch": 0.5387205387205387,
+      "grad_norm": 0.3515625,
+      "learning_rate": 1.9088600273149947e-05,
+      "loss": 0.6284,
+      "step": 160
+    },
+    {
+      "epoch": 0.5420875420875421,
+      "grad_norm": 0.5,
+      "learning_rate": 1.907306716315505e-05,
+      "loss": 0.6495,
+      "step": 161
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 0.357421875,
+      "learning_rate": 1.905740923247775e-05,
+      "loss": 0.6357,
+      "step": 162
+    },
+    {
+      "epoch": 0.5488215488215489,
+      "grad_norm": 0.349609375,
+      "learning_rate": 1.9041626696528503e-05,
+      "loss": 0.6188,
+      "step": 163
+    },
+    {
+      "epoch": 0.5521885521885522,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.9025719772432006e-05,
+      "loss": 0.6142,
+      "step": 164
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.337890625,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 0.6339,
+      "step": 165
+    },
+    {
+      "epoch": 0.5589225589225589,
+      "grad_norm": 0.412109375,
+      "learning_rate": 1.8993533636849223e-05,
+      "loss": 0.6067,
+      "step": 166
+    },
+    {
+      "epoch": 0.5622895622895623,
+      "grad_norm": 0.494140625,
+      "learning_rate": 1.8977254868156465e-05,
+      "loss": 0.5849,
+      "step": 167
+    },
+    {
+      "epoch": 0.5656565656565656,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.896085259689741e-05,
+      "loss": 0.6083,
+      "step": 168
+    },
+    {
+      "epoch": 0.569023569023569,
+      "grad_norm": 0.3984375,
+      "learning_rate": 1.8944327048722634e-05,
+      "loss": 0.6319,
+      "step": 169
+    },
+    {
+      "epoch": 0.5723905723905723,
+      "grad_norm": 0.4375,
+      "learning_rate": 1.892767845097864e-05,
+      "loss": 0.6299,
+      "step": 170
+    },
+    {
+      "epoch": 0.5757575757575758,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.891090703270477e-05,
+      "loss": 0.5819,
+      "step": 171
+    },
+    {
+      "epoch": 0.5791245791245792,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.889401302463005e-05,
+      "loss": 0.6166,
+      "step": 172
+    },
+    {
+      "epoch": 0.5824915824915825,
+      "grad_norm": 0.392578125,
+      "learning_rate": 1.887699665916999e-05,
+      "loss": 0.605,
+      "step": 173
+    },
+    {
+      "epoch": 0.5858585858585859,
+      "grad_norm": 0.33984375,
+      "learning_rate": 1.8859858170423423e-05,
+      "loss": 0.6573,
+      "step": 174
+    },
+    {
+      "epoch": 0.5892255892255892,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.8842597794169245e-05,
+      "loss": 0.5891,
+      "step": 175
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.359375,
+      "learning_rate": 1.8825215767863215e-05,
+      "loss": 0.6383,
+      "step": 176
+    },
+    {
+      "epoch": 0.5959595959595959,
+      "grad_norm": 0.30859375,
+      "learning_rate": 1.8807712330634645e-05,
+      "loss": 0.5958,
+      "step": 177
+    },
+    {
+      "epoch": 0.5993265993265994,
+      "grad_norm": 0.3671875,
+      "learning_rate": 1.879008772328314e-05,
+      "loss": 0.5791,
+      "step": 178
+    },
+    {
+      "epoch": 0.6026936026936027,
+      "grad_norm": 0.37890625,
+      "learning_rate": 1.877234218827528e-05,
+      "loss": 0.6294,
+      "step": 179
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 0.40625,
+      "learning_rate": 1.8754475969741272e-05,
+      "loss": 0.5971,
+      "step": 180
+    },
+    {
+      "epoch": 0.6094276094276094,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.87364893134716e-05,
+      "loss": 0.6078,
+      "step": 181
+    },
+    {
+      "epoch": 0.6127946127946128,
+      "grad_norm": 0.326171875,
+      "learning_rate": 1.8718382466913642e-05,
+      "loss": 0.6115,
+      "step": 182
+    },
+    {
+      "epoch": 0.6161616161616161,
+      "grad_norm": 0.3515625,
+      "learning_rate": 1.8700155679168277e-05,
+      "loss": 0.6263,
+      "step": 183
+    },
+    {
+      "epoch": 0.6195286195286195,
+      "grad_norm": 0.365234375,
+      "learning_rate": 1.868180920098644e-05,
+      "loss": 0.5933,
+      "step": 184
+    },
+    {
+      "epoch": 0.622895622895623,
+      "grad_norm": 0.419921875,
+      "learning_rate": 1.866334328476568e-05,
+      "loss": 0.6371,
+      "step": 185
+    },
+    {
+      "epoch": 0.6262626262626263,
+      "grad_norm": 0.333984375,
+      "learning_rate": 1.864475818454669e-05,
+      "loss": 0.6314,
+      "step": 186
+    },
+    {
+      "epoch": 0.6296296296296297,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.8626054156009807e-05,
+      "loss": 0.6802,
+      "step": 187
+    },
+    {
+      "epoch": 0.632996632996633,
+      "grad_norm": 0.359375,
+      "learning_rate": 1.8607231456471505e-05,
+      "loss": 0.6189,
+      "step": 188
+    },
+    {
+      "epoch": 0.6363636363636364,
+      "grad_norm": 0.337890625,
+      "learning_rate": 1.858829034488084e-05,
+      "loss": 0.5987,
+      "step": 189
+    },
+    {
+      "epoch": 0.6397306397306397,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.8569231081815895e-05,
+      "loss": 0.6492,
+      "step": 190
+    },
+    {
+      "epoch": 0.6397306397306397,
+      "eval_loss": 0.6246641874313354,
+      "eval_runtime": 8.7145,
+      "eval_samples_per_second": 57.375,
+      "eval_steps_per_second": 3.672,
+      "step": 190
+    },
+    {
+      "epoch": 0.6430976430976431,
+      "grad_norm": 0.326171875,
+      "learning_rate": 1.8550053929480202e-05,
+      "loss": 0.6198,
+      "step": 191
+    },
+    {
+      "epoch": 0.6464646464646465,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.8530759151699122e-05,
+      "loss": 0.6253,
+      "step": 192
+    },
+    {
+      "epoch": 0.6498316498316499,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.8511347013916228e-05,
+      "loss": 0.5804,
+      "step": 193
+    },
+    {
+      "epoch": 0.6531986531986532,
+      "grad_norm": 0.3671875,
+      "learning_rate": 1.8491817783189636e-05,
+      "loss": 0.5909,
+      "step": 194
+    },
+    {
+      "epoch": 0.6565656565656566,
+      "grad_norm": 0.3359375,
+      "learning_rate": 1.8472171728188356e-05,
+      "loss": 0.5996,
+      "step": 195
+    },
+    {
+      "epoch": 0.6599326599326599,
+      "grad_norm": 0.357421875,
+      "learning_rate": 1.845240911918857e-05,
+      "loss": 0.6401,
+      "step": 196
+    },
+    {
+      "epoch": 0.6632996632996633,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.843253022806993e-05,
+      "loss": 0.6576,
+      "step": 197
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.30859375,
+      "learning_rate": 1.8412535328311813e-05,
+      "loss": 0.5715,
+      "step": 198
+    },
+    {
+      "epoch": 0.67003367003367,
+      "grad_norm": 0.3203125,
+      "learning_rate": 1.839242469498956e-05,
+      "loss": 0.5988,
+      "step": 199
+    },
+    {
+      "epoch": 0.6734006734006734,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.837219860477069e-05,
+      "loss": 0.5796,
+      "step": 200
+    },
+    {
+      "epoch": 0.6767676767676768,
+      "grad_norm": 0.33984375,
+      "learning_rate": 1.8351857335911094e-05,
+      "loss": 0.6329,
+      "step": 201
+    },
+    {
+      "epoch": 0.6801346801346801,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.83314011682512e-05,
+      "loss": 0.6374,
+      "step": 202
+    },
+    {
+      "epoch": 0.6835016835016835,
+      "grad_norm": 0.3125,
+      "learning_rate": 1.831083038321215e-05,
+      "loss": 0.6235,
+      "step": 203
+    },
+    {
+      "epoch": 0.6868686868686869,
+      "grad_norm": 0.349609375,
+      "learning_rate": 1.8290145263791883e-05,
+      "loss": 0.621,
+      "step": 204
+    },
+    {
+      "epoch": 0.6902356902356902,
+      "grad_norm": 0.359375,
+      "learning_rate": 1.826934609456129e-05,
+      "loss": 0.6396,
+      "step": 205
+    },
+    {
+      "epoch": 0.6936026936026936,
+      "grad_norm": 0.337890625,
+      "learning_rate": 1.824843316166026e-05,
+      "loss": 0.6197,
+      "step": 206
+    },
+    {
+      "epoch": 0.696969696969697,
+      "grad_norm": 0.361328125,
+      "learning_rate": 1.822740675279377e-05,
+      "loss": 0.6473,
+      "step": 207
+    },
+    {
+      "epoch": 0.7003367003367004,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.8206267157227918e-05,
+      "loss": 0.6227,
+      "step": 208
+    },
+    {
+      "epoch": 0.7037037037037037,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.8185014665785936e-05,
+      "loss": 0.6009,
+      "step": 209
+    },
+    {
+      "epoch": 0.7070707070707071,
+      "grad_norm": 0.353515625,
+      "learning_rate": 1.8163649570844198e-05,
+      "loss": 0.592,
+      "step": 210
+    },
+    {
+      "epoch": 0.7104377104377104,
+      "grad_norm": 0.376953125,
+      "learning_rate": 1.8142172166328198e-05,
+      "loss": 0.6063,
+      "step": 211
+    },
+    {
+      "epoch": 0.7138047138047138,
+      "grad_norm": 0.34765625,
+      "learning_rate": 1.8120582747708503e-05,
+      "loss": 0.6315,
+      "step": 212
+    },
+    {
+      "epoch": 0.7171717171717171,
+      "grad_norm": 0.36328125,
+      "learning_rate": 1.809888161199668e-05,
+      "loss": 0.6297,
+      "step": 213
+    },
+    {
+      "epoch": 0.7205387205387206,
+      "grad_norm": 0.349609375,
+      "learning_rate": 1.8077069057741235e-05,
+      "loss": 0.6079,
+      "step": 214
+    },
+    {
+      "epoch": 0.7239057239057239,
+      "grad_norm": 0.318359375,
+      "learning_rate": 1.8055145385023477e-05,
+      "loss": 0.6192,
+      "step": 215
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.326171875,
+      "learning_rate": 1.803311089545341e-05,
+      "loss": 0.6104,
+      "step": 216
+    },
+    {
+      "epoch": 0.7306397306397306,
+      "grad_norm": 0.3359375,
+      "learning_rate": 1.8010965892165568e-05,
+      "loss": 0.6166,
+      "step": 217
+    },
+    {
+      "epoch": 0.734006734006734,
+      "grad_norm": 0.361328125,
+      "learning_rate": 1.7988710679814857e-05,
+      "loss": 0.6145,
+      "step": 218
+    },
+    {
+      "epoch": 0.7373737373737373,
+      "grad_norm": 0.32421875,
+      "learning_rate": 1.796634556457236e-05,
+      "loss": 0.5994,
+      "step": 219
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.34765625,
+      "learning_rate": 1.7943870854121126e-05,
+      "loss": 0.586,
+      "step": 220
+    },
+    {
+      "epoch": 0.7441077441077442,
+      "grad_norm": 0.32421875,
+      "learning_rate": 1.792128685765193e-05,
+      "loss": 0.582,
+      "step": 221
+    },
+    {
+      "epoch": 0.7474747474747475,
+      "grad_norm": 0.337890625,
+      "learning_rate": 1.789859388585903e-05,
+      "loss": 0.6017,
+      "step": 222
+    },
+    {
+      "epoch": 0.7508417508417509,
+      "grad_norm": 0.36328125,
+      "learning_rate": 1.7875792250935883e-05,
+      "loss": 0.5864,
+      "step": 223
+    },
+    {
+      "epoch": 0.7542087542087542,
+      "grad_norm": 0.373046875,
+      "learning_rate": 1.785288226657086e-05,
+      "loss": 0.5869,
+      "step": 224
+    },
+    {
+      "epoch": 0.7575757575757576,
+      "grad_norm": 0.3203125,
+      "learning_rate": 1.782986424794292e-05,
+      "loss": 0.6448,
+      "step": 225
+    },
+    {
+      "epoch": 0.7609427609427609,
+      "grad_norm": 0.3203125,
+      "learning_rate": 1.780673851171728e-05,
+      "loss": 0.5895,
+      "step": 226
+    },
+    {
+      "epoch": 0.7643097643097643,
+      "grad_norm": 0.326171875,
+      "learning_rate": 1.7783505376041063e-05,
+      "loss": 0.6289,
+      "step": 227
+    },
+    {
+      "epoch": 0.7676767676767676,
+      "grad_norm": 0.33984375,
+      "learning_rate": 1.7760165160538907e-05,
+      "loss": 0.6231,
+      "step": 228
+    },
+    {
+      "epoch": 0.7676767676767676,
+      "eval_loss": 0.6190042495727539,
+      "eval_runtime": 8.7179,
+      "eval_samples_per_second": 57.353,
+      "eval_steps_per_second": 3.671,
+      "step": 228
+    },
+    {
+      "epoch": 0.7710437710437711,
+      "grad_norm": 0.384765625,
+      "learning_rate": 1.7736718186308585e-05,
+      "loss": 0.6327,
+      "step": 229
+    },
+    {
+      "epoch": 0.7744107744107744,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.7713164775916573e-05,
+      "loss": 0.5811,
+      "step": 230
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.314453125,
+      "learning_rate": 1.768950525339362e-05,
+      "loss": 0.5816,
+      "step": 231
+    },
+    {
+      "epoch": 0.7811447811447811,
+      "grad_norm": 0.345703125,
+      "learning_rate": 1.7665739944230296e-05,
+      "loss": 0.6046,
+      "step": 232
+    },
+    {
+      "epoch": 0.7845117845117845,
+      "grad_norm": 0.361328125,
+      "learning_rate": 1.7641869175372493e-05,
+      "loss": 0.5985,
+      "step": 233
+    },
+    {
+      "epoch": 0.7878787878787878,
+      "grad_norm": 0.36328125,
+      "learning_rate": 1.7617893275216953e-05,
+      "loss": 0.6226,
+      "step": 234
+    },
+    {
+      "epoch": 0.7912457912457912,
+      "grad_norm": 0.353515625,
+      "learning_rate": 1.759381257360673e-05,
+      "loss": 0.6361,
+      "step": 235
+    },
+    {
+      "epoch": 0.7946127946127947,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.7569627401826673e-05,
+      "loss": 0.665,
+      "step": 236
+    },
+    {
+      "epoch": 0.797979797979798,
+      "grad_norm": 0.3671875,
+      "learning_rate": 1.754533809259884e-05,
+      "loss": 0.6078,
+      "step": 237
+    },
+    {
+      "epoch": 0.8013468013468014,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.7520944980077948e-05,
+      "loss": 0.6043,
+      "step": 238
+    },
+    {
+      "epoch": 0.8047138047138047,
+      "grad_norm": 0.3125,
+      "learning_rate": 1.7496448399846757e-05,
+      "loss": 0.614,
+      "step": 239
+    },
+    {
+      "epoch": 0.8080808080808081,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.7471848688911465e-05,
+      "loss": 0.5756,
+      "step": 240
+    },
+    {
+      "epoch": 0.8114478114478114,
+      "grad_norm": 0.40234375,
+      "learning_rate": 1.744714618569707e-05,
+      "loss": 0.5982,
+      "step": 241
+    },
+    {
+      "epoch": 0.8148148148148148,
+      "grad_norm": 0.359375,
+      "learning_rate": 1.74223412300427e-05,
+      "loss": 0.6126,
+      "step": 242
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 0.296875,
+      "learning_rate": 1.7397434163196967e-05,
+      "loss": 0.6281,
+      "step": 243
+    },
+    {
+      "epoch": 0.8215488215488216,
+      "grad_norm": 0.294921875,
+      "learning_rate": 1.737242532781324e-05,
+      "loss": 0.5821,
+      "step": 244
+    },
+    {
+      "epoch": 0.8249158249158249,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.7347315067944955e-05,
+      "loss": 0.6546,
+      "step": 245
+    },
+    {
+      "epoch": 0.8282828282828283,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.7322103729040868e-05,
+      "loss": 0.6301,
+      "step": 246
+    },
+    {
+      "epoch": 0.8316498316498316,
+      "grad_norm": 0.396484375,
+      "learning_rate": 1.72967916579403e-05,
+      "loss": 0.585,
+      "step": 247
+    },
+    {
+      "epoch": 0.835016835016835,
+      "grad_norm": 0.33203125,
+      "learning_rate": 1.7271379202868394e-05,
+      "loss": 0.6277,
+      "step": 248
+    },
+    {
+      "epoch": 0.8383838383838383,
+      "grad_norm": 0.37109375,
+      "learning_rate": 1.7245866713431278e-05,
+      "loss": 0.6536,
+      "step": 249
+    },
+    {
+      "epoch": 0.8417508417508418,
+      "grad_norm": 0.33984375,
+      "learning_rate": 1.72202545406113e-05,
+      "loss": 0.6231,
+      "step": 250
+    },
+    {
+      "epoch": 0.8451178451178452,
+      "grad_norm": 0.30078125,
+      "learning_rate": 1.7194543036762165e-05,
+      "loss": 0.6102,
+      "step": 251
+    },
+    {
+      "epoch": 0.8484848484848485,
+      "grad_norm": 0.33203125,
+      "learning_rate": 1.7168732555604114e-05,
+      "loss": 0.6118,
+      "step": 252
+    },
+    {
+      "epoch": 0.8518518518518519,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.7142823452219036e-05,
+      "loss": 0.6323,
+      "step": 253
+    },
+    {
+      "epoch": 0.8552188552188552,
+      "grad_norm": 0.32421875,
+      "learning_rate": 1.7116816083045603e-05,
+      "loss": 0.6393,
+      "step": 254
+    },
+    {
+      "epoch": 0.8585858585858586,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.709071080587435e-05,
+      "loss": 0.5845,
+      "step": 255
+    },
+    {
+      "epoch": 0.8619528619528619,
+      "grad_norm": 0.33203125,
+      "learning_rate": 1.7064507979842755e-05,
+      "loss": 0.6026,
+      "step": 256
+    },
+    {
+      "epoch": 0.8653198653198653,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.7038207965430316e-05,
+      "loss": 0.5665,
+      "step": 257
+    },
+    {
+      "epoch": 0.8686868686868687,
+      "grad_norm": 0.3203125,
+      "learning_rate": 1.7011811124453567e-05,
+      "loss": 0.5787,
+      "step": 258
+    },
+    {
+      "epoch": 0.8720538720538721,
+      "grad_norm": 0.359375,
+      "learning_rate": 1.6985317820061116e-05,
+      "loss": 0.5506,
+      "step": 259
+    },
+    {
+      "epoch": 0.8754208754208754,
+      "grad_norm": 0.35546875,
+      "learning_rate": 1.6958728416728644e-05,
+      "loss": 0.5902,
+      "step": 260
+    },
+    {
+      "epoch": 0.8787878787878788,
+      "grad_norm": 0.404296875,
+      "learning_rate": 1.6932043280253892e-05,
+      "loss": 0.6037,
+      "step": 261
+    },
+    {
+      "epoch": 0.8821548821548821,
+      "grad_norm": 0.314453125,
+      "learning_rate": 1.6905262777751627e-05,
+      "loss": 0.5533,
+      "step": 262
+    },
+    {
+      "epoch": 0.8855218855218855,
+      "grad_norm": 0.296875,
+      "learning_rate": 1.6878387277648593e-05,
+      "loss": 0.5924,
+      "step": 263
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.310546875,
+      "learning_rate": 1.6851417149678442e-05,
+      "loss": 0.5834,
+      "step": 264
+    },
+    {
+      "epoch": 0.8922558922558923,
+      "grad_norm": 0.345703125,
+      "learning_rate": 1.6824352764876653e-05,
+      "loss": 0.6527,
+      "step": 265
+    },
+    {
+      "epoch": 0.8956228956228957,
+      "grad_norm": 0.3359375,
+      "learning_rate": 1.6797194495575412e-05,
+      "loss": 0.6428,
+      "step": 266
+    },
+    {
+      "epoch": 0.8956228956228957,
+      "eval_loss": 0.6151465773582458,
+      "eval_runtime": 8.6578,
+      "eval_samples_per_second": 57.751,
+      "eval_steps_per_second": 3.696,
+      "step": 266
+    },
+    {
+      "epoch": 0.898989898989899,
+      "grad_norm": 0.298828125,
+      "learning_rate": 1.676994271539851e-05,
+      "loss": 0.5817,
+      "step": 267
+    },
+    {
+      "epoch": 0.9023569023569024,
+      "grad_norm": 0.33203125,
+      "learning_rate": 1.6742597799256182e-05,
+      "loss": 0.6313,
+      "step": 268
+    },
+    {
+      "epoch": 0.9057239057239057,
+      "grad_norm": 0.353515625,
+      "learning_rate": 1.671516012333997e-05,
+      "loss": 0.5895,
+      "step": 269
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.36328125,
+      "learning_rate": 1.6687630065117536e-05,
+      "loss": 0.6106,
+      "step": 270
+    },
+    {
+      "epoch": 0.9124579124579124,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.666000800332747e-05,
+      "loss": 0.567,
+      "step": 271
+    },
+    {
+      "epoch": 0.9158249158249159,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.663229431797407e-05,
+      "loss": 0.6024,
+      "step": 272
+    },
+    {
+      "epoch": 0.9191919191919192,
+      "grad_norm": 0.359375,
+      "learning_rate": 1.660448939032214e-05,
+      "loss": 0.6348,
+      "step": 273
+    },
+    {
+      "epoch": 0.9225589225589226,
+      "grad_norm": 0.3125,
+      "learning_rate": 1.6576593602891727e-05,
+      "loss": 0.6119,
+      "step": 274
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 0.314453125,
+      "learning_rate": 1.6548607339452853e-05,
+      "loss": 0.599,
+      "step": 275
+    },
+    {
+      "epoch": 0.9292929292929293,
+      "grad_norm": 0.3203125,
+      "learning_rate": 1.6520530985020243e-05,
+      "loss": 0.587,
+      "step": 276
+    },
+    {
+      "epoch": 0.9326599326599326,
+      "grad_norm": 0.318359375,
+      "learning_rate": 1.6492364925848045e-05,
+      "loss": 0.6113,
+      "step": 277
+    },
+    {
+      "epoch": 0.936026936026936,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.6464109549424477e-05,
+      "loss": 0.594,
+      "step": 278
+    },
+    {
+      "epoch": 0.9393939393939394,
+      "grad_norm": 0.283203125,
+      "learning_rate": 1.6435765244466536e-05,
+      "loss": 0.5823,
+      "step": 279
+    },
+    {
+      "epoch": 0.9427609427609428,
+      "grad_norm": 0.3203125,
+      "learning_rate": 1.6407332400914625e-05,
+      "loss": 0.5871,
+      "step": 280
+    },
+    {
+      "epoch": 0.9461279461279462,
+      "grad_norm": 0.32421875,
+      "learning_rate": 1.63788114099272e-05,
+      "loss": 0.6126,
+      "step": 281
+    },
+    {
+      "epoch": 0.9494949494949495,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.6350202663875385e-05,
+      "loss": 0.6343,
+      "step": 282
+    },
+    {
+      "epoch": 0.9528619528619529,
+      "grad_norm": 0.30078125,
+      "learning_rate": 1.6321506556337575e-05,
+      "loss": 0.6033,
+      "step": 283
+    },
+    {
+      "epoch": 0.9562289562289562,
+      "grad_norm": 0.400390625,
+      "learning_rate": 1.6292723482094013e-05,
+      "loss": 0.6216,
+      "step": 284
+    },
+    {
+      "epoch": 0.9595959595959596,
+      "grad_norm": 0.296875,
+      "learning_rate": 1.6263853837121384e-05,
+      "loss": 0.5599,
+      "step": 285
+    },
+    {
+      "epoch": 0.9629629629629629,
+      "grad_norm": 0.349609375,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 0.632,
+      "step": 286
+    },
+    {
+      "epoch": 0.9663299663299664,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.6205856424845038e-05,
+      "loss": 0.5824,
+      "step": 287
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 0.3359375,
+      "learning_rate": 1.617672945542768e-05,
+      "loss": 0.628,
+      "step": 288
+    },
+    {
+      "epoch": 0.9730639730639731,
+      "grad_norm": 0.275390625,
+      "learning_rate": 1.614751751104301e-05,
+      "loss": 0.5691,
+      "step": 289
+    },
+    {
+      "epoch": 0.9764309764309764,
+      "grad_norm": 0.310546875,
+      "learning_rate": 1.6118220993567783e-05,
+      "loss": 0.5816,
+      "step": 290
+    },
+    {
+      "epoch": 0.9797979797979798,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.6088840306042247e-05,
+      "loss": 0.5907,
+      "step": 291
+    },
+    {
+      "epoch": 0.9831649831649831,
+      "grad_norm": 0.341796875,
+      "learning_rate": 1.605937585266462e-05,
+      "loss": 0.6129,
+      "step": 292
+    },
+    {
+      "epoch": 0.9865319865319865,
+      "grad_norm": 0.333984375,
+      "learning_rate": 1.6029828038785486e-05,
+      "loss": 0.5916,
+      "step": 293
+    },
+    {
+      "epoch": 0.98989898989899,
+      "grad_norm": 0.38671875,
+      "learning_rate": 1.600019727090226e-05,
+      "loss": 0.5984,
+      "step": 294
+    },
+    {
+      "epoch": 0.9932659932659933,
+      "grad_norm": 0.345703125,
+      "learning_rate": 1.5970483956653572e-05,
+      "loss": 0.5549,
+      "step": 295
+    },
+    {
+      "epoch": 0.9966329966329966,
+      "grad_norm": 0.3671875,
+      "learning_rate": 1.5940688504813664e-05,
+      "loss": 0.6102,
+      "step": 296
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4140625,
+      "learning_rate": 1.5910811325286768e-05,
+      "loss": 0.6109,
+      "step": 297
+    },
+    {
+      "epoch": 1.0033670033670035,
+      "grad_norm": 0.3671875,
+      "learning_rate": 1.5880852829101464e-05,
+      "loss": 0.6281,
+      "step": 298
+    },
+    {
+      "epoch": 1.0067340067340067,
+      "grad_norm": 0.32421875,
+      "learning_rate": 1.5850813428405036e-05,
+      "loss": 0.6149,
+      "step": 299
+    },
+    {
+      "epoch": 1.0101010101010102,
+      "grad_norm": 0.3359375,
+      "learning_rate": 1.5820693536457787e-05,
+      "loss": 0.6244,
+      "step": 300
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 891,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 75,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.45750689775616e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fe3399e1833e4baeabfb150d83c5b0e5f796c95cfa06424bda5f2c881c0a1e7
+size 6392