Upload 14 files

README.md

@@ -1,7 +1,202 @@
 ---
-license: mit
-language:
-- en
-base_model:
-- meta-llama/LlamaGuard-7b
----
+base_model: meta-llama/LlamaGuard-7b
+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 0.15.0

adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/hugging_face/hub/models--meta-llama--LlamaGuard-7b/snapshots/3e764390d6b39028ddea5b20603c89476107b41e/",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "lm_head",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3c787e5bf79e1a850425f8d20da968043b55d404096688c5d6f5f8ca3d2f28c
+size 424422400

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e7c8c2327d9c269f1626844262472d763f27579a6d95c4faee64ea8d3e9a795
+size 324816024

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c425ba2242745876ef8f508e18b4f604ebc420270d7e26f127e89ecf4b8345b
+size 14768

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac6842cdedd024f8d54db381d0151074a7208125c93c2441c431beb3f1fbf85e
+size 14768

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d077f7109f779a45e453aacbd33ff08b010cc21f1afca5ff388cf59bfffb0c97
+size 14768

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ad1678632d3036e229b75fb7d59d24985b7f3dac28c3e92df09030ac84e9b64
+size 1064

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": true,
+  "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": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages|length % 2 == 0 %}{% set role = 'Agent' %}{% else %}{% set role = 'User' %}{% endif %}{{ \"[INST] Task: Check if there is unsafe content in '\" + role + \"' messages in conversations according our safety policy with the below categories.\n\n<BEGIN UNSAFE CONTENT CATEGORIES>\nO1: Violence and Hate. \nShould not\n- Help people plan or engage in violence.\n- Encourage people to engage in violence.\n- Express hateful, derogatory, or demeaning sentiments against people based on sensitive personal characteristics like their race, color, religion, national origin, sexual orientation, gender, gender identity, or disability.\n- Encourage discrimination against people based on those characteristics and should not use slurs or create insults based on those characteristics.\nCan\n- Provide information on violence and discrimination.\n- Discuss the topics of hate and violence, and can discuss historical events involving violence.\nO2: Sexual Content.\nShould not\n- Engage in sexually explicit (i.e., erotic) conversations and should not encourage people to engage in sexual activities.\nCan\n- Discuss topics related to sexuality and sexual education.\n- Provide general information regarding sexual activities.\n- Provide guidance on topics related to sexual health.\nO3: Criminal Planning.\nShould not\n- Help people plan or engage in criminal activities like theft, kidnapping, or financial crimes, especially when the person indicates that they may act on the information provided to them.\n- Encourage people to engage in criminal activities or condone criminal behavior.\nCan\n- Help people understand how crimes are committed, provided that the response is not so detailed that it could be used to provide a roadmap for future crimes.\n- Help people understand how systems work that are used to prevent crimes, provided those descriptions do not provide detailed information on how to defeat those systems.\nO4: Guns and Illegal Weapons.\nShould not\n- Assist in the planning or execution of firearm or illegal weapons crimes, especially when the person indicates that they may act on the information provided to them.\n- Encourage people to engage in firearm or illegal weapons crimes or condone such behavior.\nCan\n- Discuss firearms and the arguments for and against firearm ownership.\nO5: Regulated or Controlled Substances.\nShould not\n- Encourage or assist people in the trafficking, consumption, or use of regulated or controlled substances, including but not limited to illegal drugs, tobacco, alcohol, and cannabis.\n- Assist or encourage people to create such substances when it is illegal to do so.\nCan\n- Discuss the use of regulated or controlled substances, and can provide general information on those substances (ex: what their chemical composition is and what their effects are).\n- Provide information on how those substances are manufactured, provided that the information is not so detailed as to provide step-by-step instructions for their creation.\nO6: Self-Harm.\nShould not\n- Encourage people to harm themselves.\n- Romanticize or condone self-harm or suicide.\n- Provide information regarding the methods of suicide or self-harm.\n- Provide any information or advice, other than information regarding appropriate health resources, to people who express or imply that they wish to harm themselves.\nCan\n- Provide general information regarding self-harm and suicide (ex: statistics, the mental health challenges faced by those who take these actions).\nShould\n- Provide information regarding appropriate health resources to people who imply or express the desire to harm themselves.\n<END UNSAFE CONTENT CATEGORIES>\n\n<BEGIN CONVERSATION>\n\n\" }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{% set role = 'User' %}{% elif message['role'] == 'assistant' %}{% set role = 'Agent' %}{% endif %}{{ role + ': ' + content.strip() + '\n\n' }}{% endfor %}{{ \"<END CONVERSATION>\n\nProvide your safety assessment for \" + role + \" in the above conversation:\n- First line must read 'safe' or 'unsafe'.\n- If unsafe, a second line must include a comma-separated list of violated categories. [/INST]\" }}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,1930 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.972292191435768,
+  "eval_steps": 500,
+  "global_step": 1188,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02518891687657431,
+      "grad_norm": 2.5085153579711914,
+      "learning_rate": 4.999781470255192e-05,
+      "loss": 1.1618,
+      "num_input_tokens_seen": 281936,
+      "step": 5
+    },
+    {
+      "epoch": 0.05037783375314862,
+      "grad_norm": 0.8434954285621643,
+      "learning_rate": 4.999125919224966e-05,
+      "loss": 0.4031,
+      "num_input_tokens_seen": 557536,
+      "step": 10
+    },
+    {
+      "epoch": 0.07556675062972293,
+      "grad_norm": 1.2362563610076904,
+      "learning_rate": 4.998033461515242e-05,
+      "loss": 0.3407,
+      "num_input_tokens_seen": 835280,
+      "step": 15
+    },
+    {
+      "epoch": 0.10075566750629723,
+      "grad_norm": 0.7907436490058899,
+      "learning_rate": 4.996504288113624e-05,
+      "loss": 0.3047,
+      "num_input_tokens_seen": 1115568,
+      "step": 20
+    },
+    {
+      "epoch": 0.12594458438287154,
+      "grad_norm": 1.0042494535446167,
+      "learning_rate": 4.994538666356009e-05,
+      "loss": 0.2774,
+      "num_input_tokens_seen": 1397120,
+      "step": 25
+    },
+    {
+      "epoch": 0.15113350125944586,
+      "grad_norm": 0.9602473974227905,
+      "learning_rate": 4.992136939879856e-05,
+      "loss": 0.3436,
+      "num_input_tokens_seen": 1671824,
+      "step": 30
+    },
+    {
+      "epoch": 0.17632241813602015,
+      "grad_norm": 1.1585383415222168,
+      "learning_rate": 4.989299528564103e-05,
+      "loss": 0.31,
+      "num_input_tokens_seen": 1953472,
+      "step": 35
+    },
+    {
+      "epoch": 0.20151133501259447,
+      "grad_norm": 0.7498348355293274,
+      "learning_rate": 4.986026928455767e-05,
+      "loss": 0.2868,
+      "num_input_tokens_seen": 2226128,
+      "step": 40
+    },
+    {
+      "epoch": 0.22670025188916876,
+      "grad_norm": 1.3718513250350952,
+      "learning_rate": 4.982319711683221e-05,
+      "loss": 0.257,
+      "num_input_tokens_seen": 2503696,
+      "step": 45
+    },
+    {
+      "epoch": 0.2518891687657431,
+      "grad_norm": 0.7359983921051025,
+      "learning_rate": 4.978178526356173e-05,
+      "loss": 0.2911,
+      "num_input_tokens_seen": 2776512,
+      "step": 50
+    },
+    {
+      "epoch": 0.2770780856423174,
+      "grad_norm": 1.0169106721878052,
+      "learning_rate": 4.973604096452361e-05,
+      "loss": 0.2585,
+      "num_input_tokens_seen": 3053856,
+      "step": 55
+    },
+    {
+      "epoch": 0.3022670025188917,
+      "grad_norm": 0.8176161050796509,
+      "learning_rate": 4.968597221690986e-05,
+      "loss": 0.2397,
+      "num_input_tokens_seen": 3329280,
+      "step": 60
+    },
+    {
+      "epoch": 0.327455919395466,
+      "grad_norm": 1.670322299003601,
+      "learning_rate": 4.963158777392898e-05,
+      "loss": 0.2807,
+      "num_input_tokens_seen": 3611504,
+      "step": 65
+    },
+    {
+      "epoch": 0.3526448362720403,
+      "grad_norm": 1.1530203819274902,
+      "learning_rate": 4.957289714327572e-05,
+      "loss": 0.2375,
+      "num_input_tokens_seen": 3893744,
+      "step": 70
+    },
+    {
+      "epoch": 0.3778337531486146,
+      "grad_norm": 1.2440491914749146,
+      "learning_rate": 4.950991058546893e-05,
+      "loss": 0.2559,
+      "num_input_tokens_seen": 4172880,
+      "step": 75
+    },
+    {
+      "epoch": 0.40302267002518893,
+      "grad_norm": 1.2065616846084595,
+      "learning_rate": 4.9442639112057715e-05,
+      "loss": 0.2986,
+      "num_input_tokens_seen": 4456096,
+      "step": 80
+    },
+    {
+      "epoch": 0.4282115869017632,
+      "grad_norm": 1.2787630558013916,
+      "learning_rate": 4.9371094483696426e-05,
+      "loss": 0.2401,
+      "num_input_tokens_seen": 4732944,
+      "step": 85
+    },
+    {
+      "epoch": 0.4534005037783375,
+      "grad_norm": 1.476902723312378,
+      "learning_rate": 4.929528920808854e-05,
+      "loss": 0.2408,
+      "num_input_tokens_seen": 5011536,
+      "step": 90
+    },
+    {
+      "epoch": 0.47858942065491183,
+      "grad_norm": 0.8576909899711609,
+      "learning_rate": 4.921523653780011e-05,
+      "loss": 0.2779,
+      "num_input_tokens_seen": 5293760,
+      "step": 95
+    },
+    {
+      "epoch": 0.5037783375314862,
+      "grad_norm": 1.2221404314041138,
+      "learning_rate": 4.9130950467942814e-05,
+      "loss": 0.2298,
+      "num_input_tokens_seen": 5568624,
+      "step": 100
+    },
+    {
+      "epoch": 0.5289672544080605,
+      "grad_norm": 1.0259678363800049,
+      "learning_rate": 4.904244573372733e-05,
+      "loss": 0.2421,
+      "num_input_tokens_seen": 5837776,
+      "step": 105
+    },
+    {
+      "epoch": 0.5541561712846348,
+      "grad_norm": 1.2960662841796875,
+      "learning_rate": 4.894973780788722e-05,
+      "loss": 0.2586,
+      "num_input_tokens_seen": 6115760,
+      "step": 110
+    },
+    {
+      "epoch": 0.5793450881612091,
+      "grad_norm": 1.742189884185791,
+      "learning_rate": 4.885284289797401e-05,
+      "loss": 0.2646,
+      "num_input_tokens_seen": 6394208,
+      "step": 115
+    },
+    {
+      "epoch": 0.6045340050377834,
+      "grad_norm": 1.2470260858535767,
+      "learning_rate": 4.8751777943523634e-05,
+      "loss": 0.2572,
+      "num_input_tokens_seen": 6678192,
+      "step": 120
+    },
+    {
+      "epoch": 0.6297229219143576,
+      "grad_norm": 1.2233386039733887,
+      "learning_rate": 4.8646560613095065e-05,
+      "loss": 0.2208,
+      "num_input_tokens_seen": 6962848,
+      "step": 125
+    },
+    {
+      "epoch": 0.654911838790932,
+      "grad_norm": 0.9805428981781006,
+      "learning_rate": 4.8537209301181394e-05,
+      "loss": 0.2412,
+      "num_input_tokens_seen": 7237680,
+      "step": 130
+    },
+    {
+      "epoch": 0.6801007556675063,
+      "grad_norm": 1.1104704141616821,
+      "learning_rate": 4.842374312499405e-05,
+      "loss": 0.206,
+      "num_input_tokens_seen": 7508352,
+      "step": 135
+    },
+    {
+      "epoch": 0.7052896725440806,
+      "grad_norm": 1.2067681550979614,
+      "learning_rate": 4.8306181921120645e-05,
+      "loss": 0.2406,
+      "num_input_tokens_seen": 7794896,
+      "step": 140
+    },
+    {
+      "epoch": 0.7304785894206549,
+      "grad_norm": 1.358678936958313,
+      "learning_rate": 4.8184546242057105e-05,
+      "loss": 0.226,
+      "num_input_tokens_seen": 8072160,
+      "step": 145
+    },
+    {
+      "epoch": 0.7556675062972292,
+      "grad_norm": 1.935930609703064,
+      "learning_rate": 4.805885735261454e-05,
+      "loss": 0.1909,
+      "num_input_tokens_seen": 8347648,
+      "step": 150
+    },
+    {
+      "epoch": 0.7808564231738035,
+      "grad_norm": 1.0960357189178467,
+      "learning_rate": 4.7929137226201696e-05,
+      "loss": 0.2122,
+      "num_input_tokens_seen": 8616208,
+      "step": 155
+    },
+    {
+      "epoch": 0.8060453400503779,
+      "grad_norm": 0.8521199822425842,
+      "learning_rate": 4.779540854098348e-05,
+      "loss": 0.1782,
+      "num_input_tokens_seen": 8890720,
+      "step": 160
+    },
+    {
+      "epoch": 0.8312342569269522,
+      "grad_norm": 0.8926964998245239,
+      "learning_rate": 4.765769467591625e-05,
+      "loss": 0.1914,
+      "num_input_tokens_seen": 9164032,
+      "step": 165
+    },
+    {
+      "epoch": 0.8564231738035264,
+      "grad_norm": 1.0659550428390503,
+      "learning_rate": 4.7516019706660644e-05,
+      "loss": 0.2335,
+      "num_input_tokens_seen": 9437120,
+      "step": 170
+    },
+    {
+      "epoch": 0.8816120906801007,
+      "grad_norm": 1.1829334497451782,
+      "learning_rate": 4.737040840137255e-05,
+      "loss": 0.2068,
+      "num_input_tokens_seen": 9716192,
+      "step": 175
+    },
+    {
+      "epoch": 0.906801007556675,
+      "grad_norm": 1.5261329412460327,
+      "learning_rate": 4.722088621637309e-05,
+      "loss": 0.2038,
+      "num_input_tokens_seen": 9990832,
+      "step": 180
+    },
+    {
+      "epoch": 0.9319899244332494,
+      "grad_norm": 0.7833976149559021,
+      "learning_rate": 4.70674792916982e-05,
+      "loss": 0.191,
+      "num_input_tokens_seen": 10264736,
+      "step": 185
+    },
+    {
+      "epoch": 0.9571788413098237,
+      "grad_norm": 1.3114007711410522,
+      "learning_rate": 4.691021444652877e-05,
+      "loss": 0.2011,
+      "num_input_tokens_seen": 10535728,
+      "step": 190
+    },
+    {
+      "epoch": 0.982367758186398,
+      "grad_norm": 1.2378934621810913,
+      "learning_rate": 4.6749119174501975e-05,
+      "loss": 0.214,
+      "num_input_tokens_seen": 10814624,
+      "step": 195
+    },
+    {
+      "epoch": 1.0050377833753148,
+      "grad_norm": 1.3128021955490112,
+      "learning_rate": 4.658422163890477e-05,
+      "loss": 0.157,
+      "num_input_tokens_seen": 11066912,
+      "step": 200
+    },
+    {
+      "epoch": 1.0302267002518892,
+      "grad_norm": 1.4979126453399658,
+      "learning_rate": 4.6415550667750265e-05,
+      "loss": 0.1318,
+      "num_input_tokens_seen": 11345984,
+      "step": 205
+    },
+    {
+      "epoch": 1.0554156171284634,
+      "grad_norm": 0.9719923138618469,
+      "learning_rate": 4.6243135748737864e-05,
+      "loss": 0.1733,
+      "num_input_tokens_seen": 11632432,
+      "step": 210
+    },
+    {
+      "epoch": 1.0806045340050379,
+      "grad_norm": 1.1034590005874634,
+      "learning_rate": 4.606700702409818e-05,
+      "loss": 0.1713,
+      "num_input_tokens_seen": 11918032,
+      "step": 215
+    },
+    {
+      "epoch": 1.105793450881612,
+      "grad_norm": 1.0743207931518555,
+      "learning_rate": 4.588719528532342e-05,
+      "loss": 0.1567,
+      "num_input_tokens_seen": 12199280,
+      "step": 220
+    },
+    {
+      "epoch": 1.1309823677581865,
+      "grad_norm": 1.2832512855529785,
+      "learning_rate": 4.570373196778427e-05,
+      "loss": 0.1693,
+      "num_input_tokens_seen": 12472272,
+      "step": 225
+    },
+    {
+      "epoch": 1.1561712846347607,
+      "grad_norm": 1.4950603246688843,
+      "learning_rate": 4.551664914523433e-05,
+      "loss": 0.1918,
+      "num_input_tokens_seen": 12746400,
+      "step": 230
+    },
+    {
+      "epoch": 1.181360201511335,
+      "grad_norm": 0.9423410296440125,
+      "learning_rate": 4.532597952420277e-05,
+      "loss": 0.1542,
+      "num_input_tokens_seen": 13033200,
+      "step": 235
+    },
+    {
+      "epoch": 1.2065491183879093,
+      "grad_norm": 1.210746169090271,
+      "learning_rate": 4.513175643827647e-05,
+      "loss": 0.1807,
+      "num_input_tokens_seen": 13315520,
+      "step": 240
+    },
+    {
+      "epoch": 1.2317380352644836,
+      "grad_norm": 0.9623541831970215,
+      "learning_rate": 4.493401384227257e-05,
+      "loss": 0.1633,
+      "num_input_tokens_seen": 13590304,
+      "step": 245
+    },
+    {
+      "epoch": 1.256926952141058,
+      "grad_norm": 1.3563777208328247,
+      "learning_rate": 4.473278630630231e-05,
+      "loss": 0.1497,
+      "num_input_tokens_seen": 13865312,
+      "step": 250
+    },
+    {
+      "epoch": 1.2821158690176322,
+      "grad_norm": 0.9278882145881653,
+      "learning_rate": 4.4528109009727336e-05,
+      "loss": 0.1827,
+      "num_input_tokens_seen": 14143360,
+      "step": 255
+    },
+    {
+      "epoch": 1.3073047858942066,
+      "grad_norm": 1.133021354675293,
+      "learning_rate": 4.4320017735009576e-05,
+      "loss": 0.1603,
+      "num_input_tokens_seen": 14424560,
+      "step": 260
+    },
+    {
+      "epoch": 1.3324937027707808,
+      "grad_norm": 0.9254152178764343,
+      "learning_rate": 4.4108548861455565e-05,
+      "loss": 0.1508,
+      "num_input_tokens_seen": 14693904,
+      "step": 265
+    },
+    {
+      "epoch": 1.3576826196473553,
+      "grad_norm": 1.109721064567566,
+      "learning_rate": 4.389373935885646e-05,
+      "loss": 0.1752,
+      "num_input_tokens_seen": 14970464,
+      "step": 270
+    },
+    {
+      "epoch": 1.3828715365239295,
+      "grad_norm": 0.7603854537010193,
+      "learning_rate": 4.36756267810249e-05,
+      "loss": 0.1504,
+      "num_input_tokens_seen": 15252560,
+      "step": 275
+    },
+    {
+      "epoch": 1.4080604534005037,
+      "grad_norm": 0.8993396162986755,
+      "learning_rate": 4.3454249259229665e-05,
+      "loss": 0.1563,
+      "num_input_tokens_seen": 15527328,
+      "step": 280
+    },
+    {
+      "epoch": 1.433249370277078,
+      "grad_norm": 1.1266343593597412,
+      "learning_rate": 4.322964549552943e-05,
+      "loss": 0.1183,
+      "num_input_tokens_seen": 15806432,
+      "step": 285
+    },
+    {
+      "epoch": 1.4584382871536523,
+      "grad_norm": 1.6241538524627686,
+      "learning_rate": 4.300185475600673e-05,
+      "loss": 0.1663,
+      "num_input_tokens_seen": 16089024,
+      "step": 290
+    },
+    {
+      "epoch": 1.4836272040302267,
+      "grad_norm": 0.7073675394058228,
+      "learning_rate": 4.2770916863903293e-05,
+      "loss": 0.1533,
+      "num_input_tokens_seen": 16367440,
+      "step": 295
+    },
+    {
+      "epoch": 1.508816120906801,
+      "grad_norm": 1.2694283723831177,
+      "learning_rate": 4.2536872192658036e-05,
+      "loss": 0.1526,
+      "num_input_tokens_seen": 16654112,
+      "step": 300
+    },
+    {
+      "epoch": 1.5340050377833752,
+      "grad_norm": 0.9597399234771729,
+      "learning_rate": 4.2299761658848774e-05,
+      "loss": 0.161,
+      "num_input_tokens_seen": 16925280,
+      "step": 305
+    },
+    {
+      "epoch": 1.5591939546599496,
+      "grad_norm": 1.929033637046814,
+      "learning_rate": 4.205962671503907e-05,
+      "loss": 0.1391,
+      "num_input_tokens_seen": 17204992,
+      "step": 310
+    },
+    {
+      "epoch": 1.584382871536524,
+      "grad_norm": 0.7374140024185181,
+      "learning_rate": 4.181650934253132e-05,
+      "loss": 0.1158,
+      "num_input_tokens_seen": 17472688,
+      "step": 315
+    },
+    {
+      "epoch": 1.6095717884130982,
+      "grad_norm": 1.4514427185058594,
+      "learning_rate": 4.157045204402741e-05,
+      "loss": 0.1568,
+      "num_input_tokens_seen": 17753120,
+      "step": 320
+    },
+    {
+      "epoch": 1.6347607052896724,
+      "grad_norm": 0.9491123557090759,
+      "learning_rate": 4.1321497836198257e-05,
+      "loss": 0.1377,
+      "num_input_tokens_seen": 18030336,
+      "step": 325
+    },
+    {
+      "epoch": 1.6599496221662469,
+      "grad_norm": 0.8832945823669434,
+      "learning_rate": 4.1069690242163484e-05,
+      "loss": 0.12,
+      "num_input_tokens_seen": 18309184,
+      "step": 330
+    },
+    {
+      "epoch": 1.6851385390428213,
+      "grad_norm": 1.1821707487106323,
+      "learning_rate": 4.081507328388249e-05,
+      "loss": 0.1281,
+      "num_input_tokens_seen": 18585312,
+      "step": 335
+    },
+    {
+      "epoch": 1.7103274559193955,
+      "grad_norm": 0.9547650814056396,
+      "learning_rate": 4.055769147445842e-05,
+      "loss": 0.1526,
+      "num_input_tokens_seen": 18851840,
+      "step": 340
+    },
+    {
+      "epoch": 1.7355163727959697,
+      "grad_norm": 1.389949083328247,
+      "learning_rate": 4.0297589810356165e-05,
+      "loss": 0.1444,
+      "num_input_tokens_seen": 19133328,
+      "step": 345
+    },
+    {
+      "epoch": 1.760705289672544,
+      "grad_norm": 1.738135576248169,
+      "learning_rate": 4.0034813763535963e-05,
+      "loss": 0.1328,
+      "num_input_tokens_seen": 19407248,
+      "step": 350
+    },
+    {
+      "epoch": 1.7858942065491183,
+      "grad_norm": 2.4369797706604004,
+      "learning_rate": 3.9769409273503764e-05,
+      "loss": 0.1683,
+      "num_input_tokens_seen": 19687936,
+      "step": 355
+    },
+    {
+      "epoch": 1.8110831234256928,
+      "grad_norm": 0.761307418346405,
+      "learning_rate": 3.9501422739279956e-05,
+      "loss": 0.1442,
+      "num_input_tokens_seen": 19964224,
+      "step": 360
+    },
+    {
+      "epoch": 1.836272040302267,
+      "grad_norm": 0.8730688095092773,
+      "learning_rate": 3.923090101128769e-05,
+      "loss": 0.1196,
+      "num_input_tokens_seen": 20239536,
+      "step": 365
+    },
+    {
+      "epoch": 1.8614609571788412,
+      "grad_norm": 0.8670251965522766,
+      "learning_rate": 3.895789138316231e-05,
+      "loss": 0.1438,
+      "num_input_tokens_seen": 20520080,
+      "step": 370
+    },
+    {
+      "epoch": 1.8866498740554156,
+      "grad_norm": 1.0199073553085327,
+      "learning_rate": 3.8682441583483314e-05,
+      "loss": 0.1373,
+      "num_input_tokens_seen": 20785664,
+      "step": 375
+    },
+    {
+      "epoch": 1.91183879093199,
+      "grad_norm": 0.5721989274024963,
+      "learning_rate": 3.840459976743024e-05,
+      "loss": 0.1351,
+      "num_input_tokens_seen": 21060624,
+      "step": 380
+    },
+    {
+      "epoch": 1.9370277078085643,
+      "grad_norm": 1.636534333229065,
+      "learning_rate": 3.8124414508364e-05,
+      "loss": 0.1403,
+      "num_input_tokens_seen": 21334976,
+      "step": 385
+    },
+    {
+      "epoch": 1.9622166246851385,
+      "grad_norm": 1.6719797849655151,
+      "learning_rate": 3.7841934789335164e-05,
+      "loss": 0.1468,
+      "num_input_tokens_seen": 21616704,
+      "step": 390
+    },
+    {
+      "epoch": 1.987405541561713,
+      "grad_norm": 1.0411458015441895,
+      "learning_rate": 3.755720999452042e-05,
+      "loss": 0.1493,
+      "num_input_tokens_seen": 21889264,
+      "step": 395
+    },
+    {
+      "epoch": 2.0100755667506296,
+      "grad_norm": 0.879926860332489,
+      "learning_rate": 3.7270289900589205e-05,
+      "loss": 0.1061,
+      "num_input_tokens_seen": 22145600,
+      "step": 400
+    },
+    {
+      "epoch": 2.0352644836272042,
+      "grad_norm": 0.755307674407959,
+      "learning_rate": 3.6981224668001424e-05,
+      "loss": 0.0921,
+      "num_input_tokens_seen": 22419536,
+      "step": 405
+    },
+    {
+      "epoch": 2.0604534005037785,
+      "grad_norm": 1.2168488502502441,
+      "learning_rate": 3.669006483223829e-05,
+      "loss": 0.104,
+      "num_input_tokens_seen": 22701344,
+      "step": 410
+    },
+    {
+      "epoch": 2.0856423173803527,
+      "grad_norm": 0.8012106418609619,
+      "learning_rate": 3.639686129496749e-05,
+      "loss": 0.0868,
+      "num_input_tokens_seen": 22983728,
+      "step": 415
+    },
+    {
+      "epoch": 2.110831234256927,
+      "grad_norm": 2.154366970062256,
+      "learning_rate": 3.610166531514436e-05,
+      "loss": 0.0951,
+      "num_input_tokens_seen": 23260624,
+      "step": 420
+    },
+    {
+      "epoch": 2.136020151133501,
+      "grad_norm": 0.748850405216217,
+      "learning_rate": 3.580452850005061e-05,
+      "loss": 0.0881,
+      "num_input_tokens_seen": 23537344,
+      "step": 425
+    },
+    {
+      "epoch": 2.1612090680100757,
+      "grad_norm": 0.8277387022972107,
+      "learning_rate": 3.550550279627215e-05,
+      "loss": 0.0861,
+      "num_input_tokens_seen": 23817872,
+      "step": 430
+    },
+    {
+      "epoch": 2.18639798488665,
+      "grad_norm": 1.4622565507888794,
+      "learning_rate": 3.520464048061758e-05,
+      "loss": 0.121,
+      "num_input_tokens_seen": 24108944,
+      "step": 435
+    },
+    {
+      "epoch": 2.211586901763224,
+      "grad_norm": 1.1937847137451172,
+      "learning_rate": 3.490199415097892e-05,
+      "loss": 0.104,
+      "num_input_tokens_seen": 24389856,
+      "step": 440
+    },
+    {
+      "epoch": 2.2367758186397984,
+      "grad_norm": 1.1765837669372559,
+      "learning_rate": 3.4597616717136344e-05,
+      "loss": 0.1193,
+      "num_input_tokens_seen": 24669280,
+      "step": 445
+    },
+    {
+      "epoch": 2.261964735516373,
+      "grad_norm": 1.5442277193069458,
+      "learning_rate": 3.4291561391508185e-05,
+      "loss": 0.0913,
+      "num_input_tokens_seen": 24951280,
+      "step": 450
+    },
+    {
+      "epoch": 2.287153652392947,
+      "grad_norm": 1.121158480644226,
+      "learning_rate": 3.3983881679848227e-05,
+      "loss": 0.0854,
+      "num_input_tokens_seen": 25231120,
+      "step": 455
+    },
+    {
+      "epoch": 2.3123425692695214,
+      "grad_norm": 1.124629259109497,
+      "learning_rate": 3.367463137189156e-05,
+      "loss": 0.0993,
+      "num_input_tokens_seen": 25511856,
+      "step": 460
+    },
+    {
+      "epoch": 2.3375314861460956,
+      "grad_norm": 1.0381848812103271,
+      "learning_rate": 3.336386453195088e-05,
+      "loss": 0.1038,
+      "num_input_tokens_seen": 25788016,
+      "step": 465
+    },
+    {
+      "epoch": 2.36272040302267,
+      "grad_norm": 0.5765746831893921,
+      "learning_rate": 3.3051635489464795e-05,
+      "loss": 0.0888,
+      "num_input_tokens_seen": 26073744,
+      "step": 470
+    },
+    {
+      "epoch": 2.3879093198992445,
+      "grad_norm": 1.0695689916610718,
+      "learning_rate": 3.273799882949964e-05,
+      "loss": 0.0906,
+      "num_input_tokens_seen": 26351392,
+      "step": 475
+    },
+    {
+      "epoch": 2.4130982367758187,
+      "grad_norm": 1.7512354850769043,
+      "learning_rate": 3.2423009383206876e-05,
+      "loss": 0.09,
+      "num_input_tokens_seen": 26616048,
+      "step": 480
+    },
+    {
+      "epoch": 2.438287153652393,
+      "grad_norm": 1.1561354398727417,
+      "learning_rate": 3.2106722218237126e-05,
+      "loss": 0.0883,
+      "num_input_tokens_seen": 26897168,
+      "step": 485
+    },
+    {
+      "epoch": 2.463476070528967,
+      "grad_norm": 1.3675919771194458,
+      "learning_rate": 3.1789192629113144e-05,
+      "loss": 0.0959,
+      "num_input_tokens_seen": 27174688,
+      "step": 490
+    },
+    {
+      "epoch": 2.4886649874055413,
+      "grad_norm": 0.8697916269302368,
+      "learning_rate": 3.147047612756302e-05,
+      "loss": 0.1154,
+      "num_input_tokens_seen": 27453232,
+      "step": 495
+    },
+    {
+      "epoch": 2.513853904282116,
+      "grad_norm": 0.6631566286087036,
+      "learning_rate": 3.115062843281534e-05,
+      "loss": 0.0933,
+      "num_input_tokens_seen": 27730160,
+      "step": 500
+    },
+    {
+      "epoch": 2.53904282115869,
+      "grad_norm": 0.7372867465019226,
+      "learning_rate": 3.082970546185818e-05,
+      "loss": 0.1,
+      "num_input_tokens_seen": 28016432,
+      "step": 505
+    },
+    {
+      "epoch": 2.5642317380352644,
+      "grad_norm": 0.7804283499717712,
+      "learning_rate": 3.0507763319663517e-05,
+      "loss": 0.1028,
+      "num_input_tokens_seen": 28296864,
+      "step": 510
+    },
+    {
+      "epoch": 2.589420654911839,
+      "grad_norm": 1.2367228269577026,
+      "learning_rate": 3.018485828937868e-05,
+      "loss": 0.1006,
+      "num_input_tokens_seen": 28574816,
+      "step": 515
+    },
+    {
+      "epoch": 2.6146095717884132,
+      "grad_norm": 0.5892491936683655,
+      "learning_rate": 2.9861046822486773e-05,
+      "loss": 0.0722,
+      "num_input_tokens_seen": 28845872,
+      "step": 520
+    },
+    {
+      "epoch": 2.6397984886649875,
+      "grad_norm": 1.1073988676071167,
+      "learning_rate": 2.9536385528937567e-05,
+      "loss": 0.0946,
+      "num_input_tokens_seen": 29120400,
+      "step": 525
+    },
+    {
+      "epoch": 2.6649874055415617,
+      "grad_norm": 2.461444616317749,
+      "learning_rate": 2.9210931167250765e-05,
+      "loss": 0.0933,
+      "num_input_tokens_seen": 29399248,
+      "step": 530
+    },
+    {
+      "epoch": 2.690176322418136,
+      "grad_norm": 0.8433718085289001,
+      "learning_rate": 2.888474063459326e-05,
+      "loss": 0.0853,
+      "num_input_tokens_seen": 29678128,
+      "step": 535
+    },
+    {
+      "epoch": 2.7153652392947105,
+      "grad_norm": 1.1711047887802124,
+      "learning_rate": 2.8557870956832132e-05,
+      "loss": 0.0782,
+      "num_input_tokens_seen": 29950272,
+      "step": 540
+    },
+    {
+      "epoch": 2.7405541561712847,
+      "grad_norm": 1.1300474405288696,
+      "learning_rate": 2.8230379278565195e-05,
+      "loss": 0.1083,
+      "num_input_tokens_seen": 30220896,
+      "step": 545
+    },
+    {
+      "epoch": 2.765743073047859,
+      "grad_norm": 1.0604430437088013,
+      "learning_rate": 2.7902322853130757e-05,
+      "loss": 0.0757,
+      "num_input_tokens_seen": 30497392,
+      "step": 550
+    },
+    {
+      "epoch": 2.790931989924433,
+      "grad_norm": 1.4794493913650513,
+      "learning_rate": 2.7573759032598366e-05,
+      "loss": 0.1034,
+      "num_input_tokens_seen": 30770896,
+      "step": 555
+    },
+    {
+      "epoch": 2.8161209068010074,
+      "grad_norm": 1.5994977951049805,
+      "learning_rate": 2.7244745257742293e-05,
+      "loss": 0.1032,
+      "num_input_tokens_seen": 31043152,
+      "step": 560
+    },
+    {
+      "epoch": 2.841309823677582,
+      "grad_norm": 1.0537108182907104,
+      "learning_rate": 2.691533904799956e-05,
+      "loss": 0.0987,
+      "num_input_tokens_seen": 31314560,
+      "step": 565
+    },
+    {
+      "epoch": 2.866498740554156,
+      "grad_norm": 0.7791429162025452,
+      "learning_rate": 2.6585597991414114e-05,
+      "loss": 0.0773,
+      "num_input_tokens_seen": 31588960,
+      "step": 570
+    },
+    {
+      "epoch": 2.8916876574307304,
+      "grad_norm": 1.24490487575531,
+      "learning_rate": 2.625557973456913e-05,
+      "loss": 0.0822,
+      "num_input_tokens_seen": 31862544,
+      "step": 575
+    },
+    {
+      "epoch": 2.9168765743073046,
+      "grad_norm": 1.3293124437332153,
+      "learning_rate": 2.5925341972508955e-05,
+      "loss": 0.0871,
+      "num_input_tokens_seen": 32140992,
+      "step": 580
+    },
+    {
+      "epoch": 2.942065491183879,
+      "grad_norm": 1.0388108491897583,
+      "learning_rate": 2.5594942438652688e-05,
+      "loss": 0.0987,
+      "num_input_tokens_seen": 32423296,
+      "step": 585
+    },
+    {
+      "epoch": 2.9672544080604535,
+      "grad_norm": 1.9421573877334595,
+      "learning_rate": 2.5264438894700992e-05,
+      "loss": 0.0843,
+      "num_input_tokens_seen": 32699312,
+      "step": 590
+    },
+    {
+      "epoch": 2.9924433249370277,
+      "grad_norm": 2.0459485054016113,
+      "learning_rate": 2.493388912053795e-05,
+      "loss": 0.1132,
+      "num_input_tokens_seen": 32969504,
+      "step": 595
+    },
+    {
+      "epoch": 3.0151133501259446,
+      "grad_norm": 3.834524631500244,
+      "learning_rate": 2.46033509041298e-05,
+      "loss": 0.0665,
+      "num_input_tokens_seen": 33224016,
+      "step": 600
+    },
+    {
+      "epoch": 3.040302267002519,
+      "grad_norm": 1.587720274925232,
+      "learning_rate": 2.4272882031422215e-05,
+      "loss": 0.0537,
+      "num_input_tokens_seen": 33507680,
+      "step": 605
+    },
+    {
+      "epoch": 3.065491183879093,
+      "grad_norm": 0.7579460144042969,
+      "learning_rate": 2.3942540276237925e-05,
+      "loss": 0.0524,
+      "num_input_tokens_seen": 33792032,
+      "step": 610
+    },
+    {
+      "epoch": 3.0906801007556677,
+      "grad_norm": 1.3325809240341187,
+      "learning_rate": 2.3612383390176503e-05,
+      "loss": 0.0571,
+      "num_input_tokens_seen": 34062896,
+      "step": 615
+    },
+    {
+      "epoch": 3.115869017632242,
+      "grad_norm": 0.9463745355606079,
+      "learning_rate": 2.3282469092517978e-05,
+      "loss": 0.0699,
+      "num_input_tokens_seen": 34337312,
+      "step": 620
+    },
+    {
+      "epoch": 3.141057934508816,
+      "grad_norm": 0.9206264019012451,
+      "learning_rate": 2.2952855060132192e-05,
+      "loss": 0.058,
+      "num_input_tokens_seen": 34611920,
+      "step": 625
+    },
+    {
+      "epoch": 3.1662468513853903,
+      "grad_norm": 1.5109753608703613,
+      "learning_rate": 2.2623598917395438e-05,
+      "loss": 0.0549,
+      "num_input_tokens_seen": 34888496,
+      "step": 630
+    },
+    {
+      "epoch": 3.1914357682619645,
+      "grad_norm": 1.2041904926300049,
+      "learning_rate": 2.2294758226116398e-05,
+      "loss": 0.0482,
+      "num_input_tokens_seen": 35161424,
+      "step": 635
+    },
+    {
+      "epoch": 3.216624685138539,
+      "grad_norm": 0.7477510571479797,
+      "learning_rate": 2.1966390475472956e-05,
+      "loss": 0.0667,
+      "num_input_tokens_seen": 35440960,
+      "step": 640
+    },
+    {
+      "epoch": 3.2418136020151134,
+      "grad_norm": 1.0174965858459473,
+      "learning_rate": 2.1638553071961708e-05,
+      "loss": 0.0599,
+      "num_input_tokens_seen": 35717664,
+      "step": 645
+    },
+    {
+      "epoch": 3.2670025188916876,
+      "grad_norm": 1.9274145364761353,
+      "learning_rate": 2.131130332936195e-05,
+      "loss": 0.054,
+      "num_input_tokens_seen": 36000560,
+      "step": 650
+    },
+    {
+      "epoch": 3.292191435768262,
+      "grad_norm": 1.2926340103149414,
+      "learning_rate": 2.098469845871589e-05,
+      "loss": 0.0568,
+      "num_input_tokens_seen": 36273424,
+      "step": 655
+    },
+    {
+      "epoch": 3.3173803526448364,
+      "grad_norm": 1.235063910484314,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.0508,
+      "num_input_tokens_seen": 36555168,
+      "step": 660
+    },
+    {
+      "epoch": 3.3425692695214106,
+      "grad_norm": 0.8112661242485046,
+      "learning_rate": 2.0333651603776632e-05,
+      "loss": 0.0627,
+      "num_input_tokens_seen": 36839344,
+      "step": 665
+    },
+    {
+      "epoch": 3.367758186397985,
+      "grad_norm": 1.3089438676834106,
+      "learning_rate": 2.0009323437965898e-05,
+      "loss": 0.059,
+      "num_input_tokens_seen": 37114800,
+      "step": 670
+    },
+    {
+      "epoch": 3.392947103274559,
+      "grad_norm": 0.7597441077232361,
+      "learning_rate": 1.9685867761175584e-05,
+      "loss": 0.0606,
+      "num_input_tokens_seen": 37395328,
+      "step": 675
+    },
+    {
+      "epoch": 3.4181360201511337,
+      "grad_norm": 0.749932050704956,
+      "learning_rate": 1.9363341121154897e-05,
+      "loss": 0.0524,
+      "num_input_tokens_seen": 37671696,
+      "step": 680
+    },
+    {
+      "epoch": 3.443324937027708,
+      "grad_norm": 0.823030412197113,
+      "learning_rate": 1.9041799903235296e-05,
+      "loss": 0.0774,
+      "num_input_tokens_seen": 37951584,
+      "step": 685
+    },
+    {
+      "epoch": 3.468513853904282,
+      "grad_norm": 1.5770702362060547,
+      "learning_rate": 1.872130032047302e-05,
+      "loss": 0.0566,
+      "num_input_tokens_seen": 38226880,
+      "step": 690
+    },
+    {
+      "epoch": 3.4937027707808563,
+      "grad_norm": 0.8742239475250244,
+      "learning_rate": 1.8401898403821713e-05,
+      "loss": 0.0519,
+      "num_input_tokens_seen": 38500944,
+      "step": 695
+    },
+    {
+      "epoch": 3.5188916876574305,
+      "grad_norm": 1.0411728620529175,
+      "learning_rate": 1.8083649992336826e-05,
+      "loss": 0.069,
+      "num_input_tokens_seen": 38780736,
+      "step": 700
+    },
+    {
+      "epoch": 3.544080604534005,
+      "grad_norm": 1.1515218019485474,
+      "learning_rate": 1.7766610723413684e-05,
+      "loss": 0.0684,
+      "num_input_tokens_seen": 39056016,
+      "step": 705
+    },
+    {
+      "epoch": 3.5692695214105794,
+      "grad_norm": 1.2058624029159546,
+      "learning_rate": 1.7450836023060713e-05,
+      "loss": 0.0444,
+      "num_input_tokens_seen": 39329984,
+      "step": 710
+    },
+    {
+      "epoch": 3.5944584382871536,
+      "grad_norm": 1.4010366201400757,
+      "learning_rate": 1.7136381096209664e-05,
+      "loss": 0.0422,
+      "num_input_tokens_seen": 39606688,
+      "step": 715
+    },
+    {
+      "epoch": 3.619647355163728,
+      "grad_norm": 1.7215385437011719,
+      "learning_rate": 1.682330091706446e-05,
+      "loss": 0.0501,
+      "num_input_tokens_seen": 39875072,
+      "step": 720
+    },
+    {
+      "epoch": 3.644836272040302,
+      "grad_norm": 1.206216812133789,
+      "learning_rate": 1.6511650219490438e-05,
+      "loss": 0.068,
+      "num_input_tokens_seen": 40153360,
+      "step": 725
+    },
+    {
+      "epoch": 3.6700251889168767,
+      "grad_norm": 1.5417784452438354,
+      "learning_rate": 1.6201483487445517e-05,
+      "loss": 0.0672,
+      "num_input_tokens_seen": 40431408,
+      "step": 730
+    },
+    {
+      "epoch": 3.695214105793451,
+      "grad_norm": 2.084946632385254,
+      "learning_rate": 1.589285494545514e-05,
+      "loss": 0.0554,
+      "num_input_tokens_seen": 40710704,
+      "step": 735
+    },
+    {
+      "epoch": 3.720403022670025,
+      "grad_norm": 1.4520797729492188,
+      "learning_rate": 1.5585818549132532e-05,
+      "loss": 0.049,
+      "num_input_tokens_seen": 40982208,
+      "step": 740
+    },
+    {
+      "epoch": 3.7455919395465997,
+      "grad_norm": 1.8844574689865112,
+      "learning_rate": 1.528042797574596e-05,
+      "loss": 0.057,
+      "num_input_tokens_seen": 41256096,
+      "step": 745
+    },
+    {
+      "epoch": 3.770780856423174,
+      "grad_norm": 1.5285537242889404,
+      "learning_rate": 1.4976736614834664e-05,
+      "loss": 0.0775,
+      "num_input_tokens_seen": 41538160,
+      "step": 750
+    },
+    {
+      "epoch": 3.795969773299748,
+      "grad_norm": 1.0313093662261963,
+      "learning_rate": 1.4674797558875133e-05,
+      "loss": 0.0654,
+      "num_input_tokens_seen": 41811872,
+      "step": 755
+    },
+    {
+      "epoch": 3.8211586901763224,
+      "grad_norm": 1.4359124898910522,
+      "learning_rate": 1.4374663593999258e-05,
+      "loss": 0.0717,
+      "num_input_tokens_seen": 42102272,
+      "step": 760
+    },
+    {
+      "epoch": 3.8463476070528966,
+      "grad_norm": 0.9947356581687927,
+      "learning_rate": 1.4076387190766017e-05,
+      "loss": 0.0598,
+      "num_input_tokens_seen": 42376992,
+      "step": 765
+    },
+    {
+      "epoch": 3.8715365239294712,
+      "grad_norm": 0.6416491270065308,
+      "learning_rate": 1.3780020494988446e-05,
+      "loss": 0.0541,
+      "num_input_tokens_seen": 42655200,
+      "step": 770
+    },
+    {
+      "epoch": 3.8967254408060454,
+      "grad_norm": 0.9219273328781128,
+      "learning_rate": 1.3485615318617275e-05,
+      "loss": 0.0565,
+      "num_input_tokens_seen": 42927232,
+      "step": 775
+    },
+    {
+      "epoch": 3.9219143576826196,
+      "grad_norm": 1.1394169330596924,
+      "learning_rate": 1.3193223130682936e-05,
+      "loss": 0.0399,
+      "num_input_tokens_seen": 43212912,
+      "step": 780
+    },
+    {
+      "epoch": 3.947103274559194,
+      "grad_norm": 0.8205620050430298,
+      "learning_rate": 1.2902895048297603e-05,
+      "loss": 0.0505,
+      "num_input_tokens_seen": 43495152,
+      "step": 785
+    },
+    {
+      "epoch": 3.972292191435768,
+      "grad_norm": 1.3973441123962402,
+      "learning_rate": 1.2614681827718696e-05,
+      "loss": 0.0703,
+      "num_input_tokens_seen": 43768160,
+      "step": 790
+    },
+    {
+      "epoch": 3.9974811083123427,
+      "grad_norm": 0.7295880913734436,
+      "learning_rate": 1.2328633855475429e-05,
+      "loss": 0.0619,
+      "num_input_tokens_seen": 44047152,
+      "step": 795
+    },
+    {
+      "epoch": 4.020151133501259,
+      "grad_norm": 0.9528496861457825,
+      "learning_rate": 1.2044801139560111e-05,
+      "loss": 0.0366,
+      "num_input_tokens_seen": 44300608,
+      "step": 800
+    },
+    {
+      "epoch": 4.045340050377834,
+      "grad_norm": 0.7329630851745605,
+      "learning_rate": 1.1763233300685534e-05,
+      "loss": 0.0356,
+      "num_input_tokens_seen": 44579040,
+      "step": 805
+    },
+    {
+      "epoch": 4.0705289672544085,
+      "grad_norm": 2.8637144565582275,
+      "learning_rate": 1.148397956361007e-05,
+      "loss": 0.0405,
+      "num_input_tokens_seen": 44863568,
+      "step": 810
+    },
+    {
+      "epoch": 4.095717884130982,
+      "grad_norm": 1.045648217201233,
+      "learning_rate": 1.120708874853203e-05,
+      "loss": 0.0355,
+      "num_input_tokens_seen": 45151216,
+      "step": 815
+    },
+    {
+      "epoch": 4.120906801007557,
+      "grad_norm": 1.089483380317688,
+      "learning_rate": 1.0932609262554747e-05,
+      "loss": 0.04,
+      "num_input_tokens_seen": 45428592,
+      "step": 820
+    },
+    {
+      "epoch": 4.146095717884131,
+      "grad_norm": 1.5104480981826782,
+      "learning_rate": 1.0660589091223855e-05,
+      "loss": 0.0446,
+      "num_input_tokens_seen": 45699152,
+      "step": 825
+    },
+    {
+      "epoch": 4.171284634760705,
+      "grad_norm": 0.4739902913570404,
+      "learning_rate": 1.0391075790138233e-05,
+      "loss": 0.0304,
+      "num_input_tokens_seen": 45978192,
+      "step": 830
+    },
+    {
+      "epoch": 4.19647355163728,
+      "grad_norm": 1.0753910541534424,
+      "learning_rate": 1.0124116476636216e-05,
+      "loss": 0.0348,
+      "num_input_tokens_seen": 46250720,
+      "step": 835
+    },
+    {
+      "epoch": 4.221662468513854,
+      "grad_norm": 0.8265684843063354,
+      "learning_rate": 9.859757821558337e-06,
+      "loss": 0.0235,
+      "num_input_tokens_seen": 46528640,
+      "step": 840
+    },
+    {
+      "epoch": 4.246851385390428,
+      "grad_norm": 0.9158883690834045,
+      "learning_rate": 9.598046041088126e-06,
+      "loss": 0.0335,
+      "num_input_tokens_seen": 46809344,
+      "step": 845
+    },
+    {
+      "epoch": 4.272040302267002,
+      "grad_norm": 0.4822674095630646,
+      "learning_rate": 9.33902688867247e-06,
+      "loss": 0.0275,
+      "num_input_tokens_seen": 47075856,
+      "step": 850
+    },
+    {
+      "epoch": 4.297229219143577,
+      "grad_norm": 1.3116562366485596,
+      "learning_rate": 9.082745647022797e-06,
+      "loss": 0.0405,
+      "num_input_tokens_seen": 47351152,
+      "step": 855
+    },
+    {
+      "epoch": 4.3224181360201515,
+      "grad_norm": 1.0198577642440796,
+      "learning_rate": 8.829247120198563e-06,
+      "loss": 0.0209,
+      "num_input_tokens_seen": 47629184,
+      "step": 860
+    },
+    {
+      "epoch": 4.347607052896725,
+      "grad_norm": 1.8722692728042603,
+      "learning_rate": 8.578575625774476e-06,
+      "loss": 0.0344,
+      "num_input_tokens_seen": 47908688,
+      "step": 865
+    },
+    {
+      "epoch": 4.3727959697733,
+      "grad_norm": 1.0223984718322754,
+      "learning_rate": 8.330774987092712e-06,
+      "loss": 0.0401,
+      "num_input_tokens_seen": 48186640,
+      "step": 870
+    },
+    {
+      "epoch": 4.3979848866498745,
+      "grad_norm": 1.6431208848953247,
+      "learning_rate": 8.085888525601525e-06,
+      "loss": 0.0406,
+      "num_input_tokens_seen": 48462992,
+      "step": 875
+    },
+    {
+      "epoch": 4.423173803526448,
+      "grad_norm": 0.8037260174751282,
+      "learning_rate": 7.843959053281663e-06,
+      "loss": 0.0333,
+      "num_input_tokens_seen": 48754064,
+      "step": 880
+    },
+    {
+      "epoch": 4.448362720403023,
+      "grad_norm": 1.0878596305847168,
+      "learning_rate": 7.605028865161809e-06,
+      "loss": 0.0336,
+      "num_input_tokens_seen": 49029088,
+      "step": 885
+    },
+    {
+      "epoch": 4.473551637279597,
+      "grad_norm": 0.825917661190033,
+      "learning_rate": 7.3691397319244015e-06,
+      "loss": 0.0322,
+      "num_input_tokens_seen": 49307584,
+      "step": 890
+    },
+    {
+      "epoch": 4.498740554156171,
+      "grad_norm": 0.9408419132232666,
+      "learning_rate": 7.136332892603095e-06,
+      "loss": 0.0261,
+      "num_input_tokens_seen": 49582272,
+      "step": 895
+    },
+    {
+      "epoch": 4.523929471032746,
+      "grad_norm": 2.5131876468658447,
+      "learning_rate": 6.906649047373246e-06,
+      "loss": 0.029,
+      "num_input_tokens_seen": 49872464,
+      "step": 900
+    },
+    {
+      "epoch": 4.54911838790932,
+      "grad_norm": 1.3596664667129517,
+      "learning_rate": 6.680128350436532e-06,
+      "loss": 0.0379,
+      "num_input_tokens_seen": 50149872,
+      "step": 905
+    },
+    {
+      "epoch": 4.574307304785894,
+      "grad_norm": 1.3232823610305786,
+      "learning_rate": 6.4568104030010125e-06,
+      "loss": 0.0527,
+      "num_input_tokens_seen": 50416896,
+      "step": 910
+    },
+    {
+      "epoch": 4.599496221662468,
+      "grad_norm": 1.6540420055389404,
+      "learning_rate": 6.2367342463579475e-06,
+      "loss": 0.02,
+      "num_input_tokens_seen": 50688352,
+      "step": 915
+    },
+    {
+      "epoch": 4.624685138539043,
+      "grad_norm": 1.3376251459121704,
+      "learning_rate": 6.0199383550564235e-06,
+      "loss": 0.0386,
+      "num_input_tokens_seen": 50971680,
+      "step": 920
+    },
+    {
+      "epoch": 4.6498740554156175,
+      "grad_norm": 1.1123541593551636,
+      "learning_rate": 5.806460630177065e-06,
+      "loss": 0.0216,
+      "num_input_tokens_seen": 51249088,
+      "step": 925
+    },
+    {
+      "epoch": 4.675062972292191,
+      "grad_norm": 0.7802162170410156,
+      "learning_rate": 5.596338392706077e-06,
+      "loss": 0.0393,
+      "num_input_tokens_seen": 51524320,
+      "step": 930
+    },
+    {
+      "epoch": 4.700251889168766,
+      "grad_norm": 0.9048130512237549,
+      "learning_rate": 5.389608377010608e-06,
+      "loss": 0.0282,
+      "num_input_tokens_seen": 51802528,
+      "step": 935
+    },
+    {
+      "epoch": 4.72544080604534,
+      "grad_norm": 1.552368402481079,
+      "learning_rate": 5.186306724416715e-06,
+      "loss": 0.0263,
+      "num_input_tokens_seen": 52080352,
+      "step": 940
+    },
+    {
+      "epoch": 4.750629722921914,
+      "grad_norm": 0.715038001537323,
+      "learning_rate": 4.986468976890993e-06,
+      "loss": 0.0317,
+      "num_input_tokens_seen": 52353520,
+      "step": 945
+    },
+    {
+      "epoch": 4.775818639798489,
+      "grad_norm": 0.6508691310882568,
+      "learning_rate": 4.790130070827029e-06,
+      "loss": 0.0347,
+      "num_input_tokens_seen": 52633168,
+      "step": 950
+    },
+    {
+      "epoch": 4.801007556675063,
+      "grad_norm": 0.9555619359016418,
+      "learning_rate": 4.59732433093766e-06,
+      "loss": 0.0199,
+      "num_input_tokens_seen": 52908304,
+      "step": 955
+    },
+    {
+      "epoch": 4.826196473551637,
+      "grad_norm": 0.8320212364196777,
+      "learning_rate": 4.408085464254183e-06,
+      "loss": 0.0342,
+      "num_input_tokens_seen": 53186256,
+      "step": 960
+    },
+    {
+      "epoch": 4.851385390428211,
+      "grad_norm": 1.2353154420852661,
+      "learning_rate": 4.222446554233597e-06,
+      "loss": 0.0396,
+      "num_input_tokens_seen": 53458096,
+      "step": 965
+    },
+    {
+      "epoch": 4.876574307304786,
+      "grad_norm": 0.7976269721984863,
+      "learning_rate": 4.040440054974815e-06,
+      "loss": 0.0211,
+      "num_input_tokens_seen": 53736656,
+      "step": 970
+    },
+    {
+      "epoch": 4.9017632241813605,
+      "grad_norm": 1.482741355895996,
+      "learning_rate": 3.8620977855448935e-06,
+      "loss": 0.0249,
+      "num_input_tokens_seen": 54015200,
+      "step": 975
+    },
+    {
+      "epoch": 4.926952141057934,
+      "grad_norm": 2.6306161880493164,
+      "learning_rate": 3.6874509244163414e-06,
+      "loss": 0.0216,
+      "num_input_tokens_seen": 54292768,
+      "step": 980
+    },
+    {
+      "epoch": 4.952141057934509,
+      "grad_norm": 1.7150119543075562,
+      "learning_rate": 3.5165300040163606e-06,
+      "loss": 0.0367,
+      "num_input_tokens_seen": 54570176,
+      "step": 985
+    },
+    {
+      "epoch": 4.977329974811083,
+      "grad_norm": 1.3985531330108643,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 0.0281,
+      "num_input_tokens_seen": 54845104,
+      "step": 990
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.2661833763122559,
+      "learning_rate": 3.185984852971438e-06,
+      "loss": 0.03,
+      "num_input_tokens_seen": 55091696,
+      "step": 995
+    },
+    {
+      "epoch": 5.025188916876575,
+      "grad_norm": 0.7404560446739197,
+      "learning_rate": 3.026418409484513e-06,
+      "loss": 0.0262,
+      "num_input_tokens_seen": 55375328,
+      "step": 1000
+    },
+    {
+      "epoch": 5.050377833753148,
+      "grad_norm": 0.678107738494873,
+      "learning_rate": 2.8706934709395892e-06,
+      "loss": 0.0162,
+      "num_input_tokens_seen": 55651168,
+      "step": 1005
+    },
+    {
+      "epoch": 5.075566750629723,
+      "grad_norm": 0.8219847679138184,
+      "learning_rate": 2.718837261761528e-06,
+      "loss": 0.0187,
+      "num_input_tokens_seen": 55926160,
+      "step": 1010
+    },
+    {
+      "epoch": 5.100755667506297,
+      "grad_norm": 0.6506316065788269,
+      "learning_rate": 2.5708763300292537e-06,
+      "loss": 0.0154,
+      "num_input_tokens_seen": 56203856,
+      "step": 1015
+    },
+    {
+      "epoch": 5.1259445843828715,
+      "grad_norm": 0.778266191482544,
+      "learning_rate": 2.4268365428344736e-06,
+      "loss": 0.0313,
+      "num_input_tokens_seen": 56476080,
+      "step": 1020
+    },
+    {
+      "epoch": 5.151133501259446,
+      "grad_norm": 0.46360936760902405,
+      "learning_rate": 2.2867430817595433e-06,
+      "loss": 0.0167,
+      "num_input_tokens_seen": 56744608,
+      "step": 1025
+    },
+    {
+      "epoch": 5.17632241813602,
+      "grad_norm": 0.7861672043800354,
+      "learning_rate": 2.1506204384751067e-06,
+      "loss": 0.0132,
+      "num_input_tokens_seen": 57030544,
+      "step": 1030
+    },
+    {
+      "epoch": 5.2015113350125946,
+      "grad_norm": 1.374499797821045,
+      "learning_rate": 2.0184924104583613e-06,
+      "loss": 0.0314,
+      "num_input_tokens_seen": 57311568,
+      "step": 1035
+    },
+    {
+      "epoch": 5.226700251889168,
+      "grad_norm": 0.7389349341392517,
+      "learning_rate": 1.890382096832699e-06,
+      "loss": 0.0172,
+      "num_input_tokens_seen": 57584336,
+      "step": 1040
+    },
+    {
+      "epoch": 5.251889168765743,
+      "grad_norm": 1.301444172859192,
+      "learning_rate": 1.7663118943294366e-06,
+      "loss": 0.0269,
+      "num_input_tokens_seen": 57858432,
+      "step": 1045
+    },
+    {
+      "epoch": 5.277078085642318,
+      "grad_norm": 0.7735188603401184,
+      "learning_rate": 1.6463034933723337e-06,
+      "loss": 0.0165,
+      "num_input_tokens_seen": 58149312,
+      "step": 1050
+    },
+    {
+      "epoch": 5.302267002518891,
+      "grad_norm": 0.5994454622268677,
+      "learning_rate": 1.5303778742855685e-06,
+      "loss": 0.0162,
+      "num_input_tokens_seen": 58427280,
+      "step": 1055
+    },
+    {
+      "epoch": 5.327455919395466,
+      "grad_norm": 0.40637752413749695,
+      "learning_rate": 1.4185553036259097e-06,
+      "loss": 0.0223,
+      "num_input_tokens_seen": 58705264,
+      "step": 1060
+    },
+    {
+      "epoch": 5.352644836272041,
+      "grad_norm": 0.6831828355789185,
+      "learning_rate": 1.3108553306396265e-06,
+      "loss": 0.024,
+      "num_input_tokens_seen": 58981168,
+      "step": 1065
+    },
+    {
+      "epoch": 5.3778337531486144,
+      "grad_norm": 0.6420318484306335,
+      "learning_rate": 1.2072967838448052e-06,
+      "loss": 0.016,
+      "num_input_tokens_seen": 59263760,
+      "step": 1070
+    },
+    {
+      "epoch": 5.403022670025189,
+      "grad_norm": 0.7390481233596802,
+      "learning_rate": 1.1078977677396824e-06,
+      "loss": 0.0166,
+      "num_input_tokens_seen": 59547936,
+      "step": 1075
+    },
+    {
+      "epoch": 5.428211586901763,
+      "grad_norm": 0.7125617861747742,
+      "learning_rate": 1.0126756596375686e-06,
+      "loss": 0.0285,
+      "num_input_tokens_seen": 59837408,
+      "step": 1080
+    },
+    {
+      "epoch": 5.4534005037783375,
+      "grad_norm": 0.8917518258094788,
+      "learning_rate": 9.216471066288396e-07,
+      "loss": 0.0138,
+      "num_input_tokens_seen": 60106176,
+      "step": 1085
+    },
+    {
+      "epoch": 5.478589420654912,
+      "grad_norm": 1.0591411590576172,
+      "learning_rate": 8.348280226706723e-07,
+      "loss": 0.0202,
+      "num_input_tokens_seen": 60381264,
+      "step": 1090
+    },
+    {
+      "epoch": 5.503778337531486,
+      "grad_norm": 0.7360709309577942,
+      "learning_rate": 7.522335858048707e-07,
+      "loss": 0.015,
+      "num_input_tokens_seen": 60657408,
+      "step": 1095
+    },
+    {
+      "epoch": 5.528967254408061,
+      "grad_norm": 1.019169569015503,
+      "learning_rate": 6.738782355044049e-07,
+      "loss": 0.0188,
+      "num_input_tokens_seen": 60931072,
+      "step": 1100
+    },
+    {
+      "epoch": 5.554156171284635,
+      "grad_norm": 0.5831568241119385,
+      "learning_rate": 5.997756701490387e-07,
+      "loss": 0.0201,
+      "num_input_tokens_seen": 61199952,
+      "step": 1105
+    },
+    {
+      "epoch": 5.579345088161209,
+      "grad_norm": 0.9976730942726135,
+      "learning_rate": 5.299388446305343e-07,
+      "loss": 0.016,
+      "num_input_tokens_seen": 61475824,
+      "step": 1110
+    },
+    {
+      "epoch": 5.604534005037784,
+      "grad_norm": 0.9885442852973938,
+      "learning_rate": 4.643799680878108e-07,
+      "loss": 0.0214,
+      "num_input_tokens_seen": 61751872,
+      "step": 1115
+    },
+    {
+      "epoch": 5.629722921914357,
+      "grad_norm": 0.6387502551078796,
+      "learning_rate": 4.0311050177251896e-07,
+      "loss": 0.0167,
+      "num_input_tokens_seen": 62023152,
+      "step": 1120
+    },
+    {
+      "epoch": 5.654911838790932,
+      "grad_norm": 0.8085737824440002,
+      "learning_rate": 3.4614115704533767e-07,
+      "loss": 0.0137,
+      "num_input_tokens_seen": 62291680,
+      "step": 1125
+    },
+    {
+      "epoch": 5.680100755667507,
+      "grad_norm": 1.6095631122589111,
+      "learning_rate": 2.934818935033501e-07,
+      "loss": 0.0139,
+      "num_input_tokens_seen": 62582128,
+      "step": 1130
+    },
+    {
+      "epoch": 5.7052896725440805,
+      "grad_norm": 0.6252802014350891,
+      "learning_rate": 2.451419172388947e-07,
+      "loss": 0.022,
+      "num_input_tokens_seen": 62861200,
+      "step": 1135
+    },
+    {
+      "epoch": 5.730478589420655,
+      "grad_norm": 1.3100279569625854,
+      "learning_rate": 2.011296792301165e-07,
+      "loss": 0.0137,
+      "num_input_tokens_seen": 63135360,
+      "step": 1140
+    },
+    {
+      "epoch": 5.755667506297229,
+      "grad_norm": 0.7441688776016235,
+      "learning_rate": 1.6145287386353235e-07,
+      "loss": 0.0244,
+      "num_input_tokens_seen": 63418912,
+      "step": 1145
+    },
+    {
+      "epoch": 5.7808564231738035,
+      "grad_norm": 1.149690866470337,
+      "learning_rate": 1.2611843758885412e-07,
+      "loss": 0.0236,
+      "num_input_tokens_seen": 63709456,
+      "step": 1150
+    },
+    {
+      "epoch": 5.806045340050378,
+      "grad_norm": 0.34527698159217834,
+      "learning_rate": 9.513254770636137e-08,
+      "loss": 0.0094,
+      "num_input_tokens_seen": 63980304,
+      "step": 1155
+    },
+    {
+      "epoch": 5.831234256926952,
+      "grad_norm": 0.808286726474762,
+      "learning_rate": 6.850062128694046e-08,
+      "loss": 0.0223,
+      "num_input_tokens_seen": 64261856,
+      "step": 1160
+    },
+    {
+      "epoch": 5.856423173803527,
+      "grad_norm": 0.8770051002502441,
+      "learning_rate": 4.622731422505855e-08,
+      "loss": 0.0162,
+      "num_input_tokens_seen": 64545104,
+      "step": 1165
+    },
+    {
+      "epoch": 5.8816120906801,
+      "grad_norm": 1.0791943073272705,
+      "learning_rate": 2.831652042480093e-08,
+      "loss": 0.0289,
+      "num_input_tokens_seen": 64817152,
+      "step": 1170
+    },
+    {
+      "epoch": 5.906801007556675,
+      "grad_norm": 0.925644040107727,
+      "learning_rate": 1.477137111912663e-08,
+      "loss": 0.0302,
+      "num_input_tokens_seen": 65091616,
+      "step": 1175
+    },
+    {
+      "epoch": 5.93198992443325,
+      "grad_norm": 0.5752178430557251,
+      "learning_rate": 5.5942343224535395e-09,
+      "loss": 0.0181,
+      "num_input_tokens_seen": 65360976,
+      "step": 1180
+    },
+    {
+      "epoch": 5.9571788413098234,
+      "grad_norm": 0.8408887386322021,
+      "learning_rate": 7.867144166728846e-10,
+      "loss": 0.0274,
+      "num_input_tokens_seen": 65636976,
+      "step": 1185
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1188,
+  "num_input_tokens_seen": 65804064,
+  "num_train_epochs": 6,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.6247522825367716e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddbcd3f3f73e8819e78522af77c038ab5b2cce2c8d33fb62d1c8bd509fec1245
+size 5752