Upload full trainer checkpoint step=1466 (profile=llama3_1_8b_base, run_type=sft)

.gitattributes

@@ -131,3 +131,4 @@ meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-1013/tokenizer.json filter=
 meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-2026/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-3039/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-4052/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-1466/tokenizer.json filter=lfs diff=lfs merge=lfs -text

meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-1466/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Meta-Llama-3.1-8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Meta-Llama-3.1-8B
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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 0.18.1

meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-1466/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "LlamaForCausalLM",
+    "parent_library": "transformers.models.llama.modeling_llama",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Meta-Llama-3.1-8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-1466/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeae5e07a8d9b92052b6418ada0aeec6c226839a6e77f2fffb796f75c14516a9
+size 83945296

meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-1466/chat_template.jinja

@@ -0,0 +1,12 @@
+{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ messages[0]['content'] + '
+
+' }}{% set loop_messages = messages[1:] %}{% else %}{{ '' + '
+
+' }}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}{{ '### Instruction:
+' + message['content'] + '
+
+' }}{% elif message['role'] == 'assistant' %}{{ '### Response:
+' + message['content'] + eos_token + '
+
+' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '### Response:
+' }}{% endif %}

meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-1466/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b584a4e97475ef1d99387db902af3f22c6d714a86d5800599a9c5b4a696a072
+size 43127973

meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-1466/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ccb8eeb935749fc43744e0a5eeacdf6f0f10253be15266a497cbca0ffaa2573
+size 14645

meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-1466/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adf5bf1180c4073f3c778c1ab49bbe225838d3c7885b46f176a1b30b405c7f03
+size 1465

meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-1466/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-1466/tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "from_slow": true,
+  "is_local": false,
+  "legacy": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null
+}

meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-1466/trainer_state.json

@@ -0,0 +1,2101 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.24995737425404946,
+  "eval_steps": 1466,
+  "global_step": 1466,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008525149190110827,
+      "grad_norm": 1.6653118133544922,
+      "learning_rate": 6.382978723404255e-07,
+      "loss": 0.6878558158874511,
+      "step": 5
+    },
+    {
+      "epoch": 0.0017050298380221654,
+      "grad_norm": 1.6072094440460205,
+      "learning_rate": 1.4361702127659573e-06,
+      "loss": 0.7222867965698242,
+      "step": 10
+    },
+    {
+      "epoch": 0.0025575447570332483,
+      "grad_norm": 1.8327608108520508,
+      "learning_rate": 2.2340425531914894e-06,
+      "loss": 0.6977188110351562,
+      "step": 15
+    },
+    {
+      "epoch": 0.0034100596760443308,
+      "grad_norm": 1.7263766527175903,
+      "learning_rate": 3.0319148936170214e-06,
+      "loss": 0.6928215026855469,
+      "step": 20
+    },
+    {
+      "epoch": 0.004262574595055414,
+      "grad_norm": 1.8482989072799683,
+      "learning_rate": 3.829787234042553e-06,
+      "loss": 0.6887872695922852,
+      "step": 25
+    },
+    {
+      "epoch": 0.005115089514066497,
+      "grad_norm": 2.0272440910339355,
+      "learning_rate": 4.627659574468085e-06,
+      "loss": 0.6714544296264648,
+      "step": 30
+    },
+    {
+      "epoch": 0.005967604433077579,
+      "grad_norm": 2.4286959171295166,
+      "learning_rate": 5.425531914893616e-06,
+      "loss": 0.6025971412658692,
+      "step": 35
+    },
+    {
+      "epoch": 0.0068201193520886615,
+      "grad_norm": 2.26863694190979,
+      "learning_rate": 6.223404255319148e-06,
+      "loss": 0.5200423240661621,
+      "step": 40
+    },
+    {
+      "epoch": 0.0076726342710997444,
+      "grad_norm": 2.0572476387023926,
+      "learning_rate": 7.02127659574468e-06,
+      "loss": 0.3741515874862671,
+      "step": 45
+    },
+    {
+      "epoch": 0.008525149190110827,
+      "grad_norm": 0.9048103094100952,
+      "learning_rate": 7.819148936170211e-06,
+      "loss": 0.25923154354095457,
+      "step": 50
+    },
+    {
+      "epoch": 0.00937766410912191,
+      "grad_norm": 0.5942133069038391,
+      "learning_rate": 8.617021276595744e-06,
+      "loss": 0.18589640855789186,
+      "step": 55
+    },
+    {
+      "epoch": 0.010230179028132993,
+      "grad_norm": 0.40469691157341003,
+      "learning_rate": 9.414893617021275e-06,
+      "loss": 0.14508966207504273,
+      "step": 60
+    },
+    {
+      "epoch": 0.011082693947144074,
+      "grad_norm": 0.319180428981781,
+      "learning_rate": 1.0212765957446808e-05,
+      "loss": 0.1287898302078247,
+      "step": 65
+    },
+    {
+      "epoch": 0.011935208866155157,
+      "grad_norm": 0.2620982229709625,
+      "learning_rate": 1.101063829787234e-05,
+      "loss": 0.10825083255767823,
+      "step": 70
+    },
+    {
+      "epoch": 0.01278772378516624,
+      "grad_norm": 0.2702063024044037,
+      "learning_rate": 1.1808510638297872e-05,
+      "loss": 0.09140915870666504,
+      "step": 75
+    },
+    {
+      "epoch": 0.013640238704177323,
+      "grad_norm": 0.21019567549228668,
+      "learning_rate": 1.2606382978723403e-05,
+      "loss": 0.07847741842269898,
+      "step": 80
+    },
+    {
+      "epoch": 0.014492753623188406,
+      "grad_norm": 0.27865487337112427,
+      "learning_rate": 1.3404255319148936e-05,
+      "loss": 0.0681579053401947,
+      "step": 85
+    },
+    {
+      "epoch": 0.015345268542199489,
+      "grad_norm": 0.2561706006526947,
+      "learning_rate": 1.4202127659574466e-05,
+      "loss": 0.06208043098449707,
+      "step": 90
+    },
+    {
+      "epoch": 0.01619778346121057,
+      "grad_norm": 0.33415308594703674,
+      "learning_rate": 1.4999999999999999e-05,
+      "loss": 0.05436077117919922,
+      "step": 95
+    },
+    {
+      "epoch": 0.017050298380221655,
+      "grad_norm": 0.20705723762512207,
+      "learning_rate": 1.579787234042553e-05,
+      "loss": 0.061427068710327146,
+      "step": 100
+    },
+    {
+      "epoch": 0.017902813299232736,
+      "grad_norm": 0.26269420981407166,
+      "learning_rate": 1.659574468085106e-05,
+      "loss": 0.04944279193878174,
+      "step": 105
+    },
+    {
+      "epoch": 0.01875532821824382,
+      "grad_norm": 0.256533682346344,
+      "learning_rate": 1.7393617021276596e-05,
+      "loss": 0.0463131994009018,
+      "step": 110
+    },
+    {
+      "epoch": 0.0196078431372549,
+      "grad_norm": 0.25077348947525024,
+      "learning_rate": 1.8191489361702127e-05,
+      "loss": 0.036723154783248904,
+      "step": 115
+    },
+    {
+      "epoch": 0.020460358056265986,
+      "grad_norm": 0.2801378071308136,
+      "learning_rate": 1.8989361702127655e-05,
+      "loss": 0.04308137893676758,
+      "step": 120
+    },
+    {
+      "epoch": 0.021312872975277068,
+      "grad_norm": 0.23140908777713776,
+      "learning_rate": 1.978723404255319e-05,
+      "loss": 0.0391487717628479,
+      "step": 125
+    },
+    {
+      "epoch": 0.02216538789428815,
+      "grad_norm": 0.4250975251197815,
+      "learning_rate": 2.0585106382978724e-05,
+      "loss": 0.03745899498462677,
+      "step": 130
+    },
+    {
+      "epoch": 0.023017902813299233,
+      "grad_norm": 0.24533668160438538,
+      "learning_rate": 2.1382978723404255e-05,
+      "loss": 0.03649275898933411,
+      "step": 135
+    },
+    {
+      "epoch": 0.023870417732310314,
+      "grad_norm": 0.2309182733297348,
+      "learning_rate": 2.2180851063829783e-05,
+      "loss": 0.036090463399887085,
+      "step": 140
+    },
+    {
+      "epoch": 0.0247229326513214,
+      "grad_norm": 0.28087928891181946,
+      "learning_rate": 2.2978723404255317e-05,
+      "loss": 0.03179733753204346,
+      "step": 145
+    },
+    {
+      "epoch": 0.02557544757033248,
+      "grad_norm": 0.2785134017467499,
+      "learning_rate": 2.377659574468085e-05,
+      "loss": 0.02794267237186432,
+      "step": 150
+    },
+    {
+      "epoch": 0.026427962489343565,
+      "grad_norm": 0.20468176901340485,
+      "learning_rate": 2.457446808510638e-05,
+      "loss": 0.025854837894439698,
+      "step": 155
+    },
+    {
+      "epoch": 0.027280477408354646,
+      "grad_norm": 0.4069538116455078,
+      "learning_rate": 2.537234042553191e-05,
+      "loss": 0.03182780146598816,
+      "step": 160
+    },
+    {
+      "epoch": 0.028132992327365727,
+      "grad_norm": 0.3025060296058655,
+      "learning_rate": 2.6170212765957446e-05,
+      "loss": 0.027975103259086607,
+      "step": 165
+    },
+    {
+      "epoch": 0.028985507246376812,
+      "grad_norm": 0.22387781739234924,
+      "learning_rate": 2.6968085106382977e-05,
+      "loss": 0.025766396522521974,
+      "step": 170
+    },
+    {
+      "epoch": 0.029838022165387893,
+      "grad_norm": 0.15060213208198547,
+      "learning_rate": 2.7765957446808508e-05,
+      "loss": 0.025661858916282653,
+      "step": 175
+    },
+    {
+      "epoch": 0.030690537084398978,
+      "grad_norm": 0.2912445366382599,
+      "learning_rate": 2.856382978723404e-05,
+      "loss": 0.02397846579551697,
+      "step": 180
+    },
+    {
+      "epoch": 0.03154305200341006,
+      "grad_norm": 0.19390830397605896,
+      "learning_rate": 2.9361702127659574e-05,
+      "loss": 0.023744897544384004,
+      "step": 185
+    },
+    {
+      "epoch": 0.03239556692242114,
+      "grad_norm": 0.24036464095115662,
+      "learning_rate": 3.0159574468085105e-05,
+      "loss": 0.0238590270280838,
+      "step": 190
+    },
+    {
+      "epoch": 0.03324808184143223,
+      "grad_norm": 0.2793026566505432,
+      "learning_rate": 3.0957446808510636e-05,
+      "loss": 0.025464403629302978,
+      "step": 195
+    },
+    {
+      "epoch": 0.03410059676044331,
+      "grad_norm": 0.21164429187774658,
+      "learning_rate": 3.175531914893617e-05,
+      "loss": 0.020692554116249085,
+      "step": 200
+    },
+    {
+      "epoch": 0.03495311167945439,
+      "grad_norm": 0.3742266297340393,
+      "learning_rate": 3.25531914893617e-05,
+      "loss": 0.02315486818552017,
+      "step": 205
+    },
+    {
+      "epoch": 0.03580562659846547,
+      "grad_norm": 0.2690248191356659,
+      "learning_rate": 3.3351063829787226e-05,
+      "loss": 0.0174571692943573,
+      "step": 210
+    },
+    {
+      "epoch": 0.03665814151747655,
+      "grad_norm": 0.3727855980396271,
+      "learning_rate": 3.414893617021276e-05,
+      "loss": 0.021705827116966246,
+      "step": 215
+    },
+    {
+      "epoch": 0.03751065643648764,
+      "grad_norm": 0.27461397647857666,
+      "learning_rate": 3.4946808510638296e-05,
+      "loss": 0.028134092688560486,
+      "step": 220
+    },
+    {
+      "epoch": 0.03836317135549872,
+      "grad_norm": 0.1723722219467163,
+      "learning_rate": 3.574468085106383e-05,
+      "loss": 0.02093944847583771,
+      "step": 225
+    },
+    {
+      "epoch": 0.0392156862745098,
+      "grad_norm": 0.17161321640014648,
+      "learning_rate": 3.654255319148936e-05,
+      "loss": 0.021984823048114777,
+      "step": 230
+    },
+    {
+      "epoch": 0.040068201193520885,
+      "grad_norm": 0.203886479139328,
+      "learning_rate": 3.734042553191489e-05,
+      "loss": 0.02234097272157669,
+      "step": 235
+    },
+    {
+      "epoch": 0.04092071611253197,
+      "grad_norm": 0.2021923065185547,
+      "learning_rate": 3.813829787234042e-05,
+      "loss": 0.02671273946762085,
+      "step": 240
+    },
+    {
+      "epoch": 0.041773231031543054,
+      "grad_norm": 0.24510027468204498,
+      "learning_rate": 3.8936170212765955e-05,
+      "loss": 0.016925157606601716,
+      "step": 245
+    },
+    {
+      "epoch": 0.042625745950554135,
+      "grad_norm": 0.191350057721138,
+      "learning_rate": 3.973404255319149e-05,
+      "loss": 0.02067229151725769,
+      "step": 250
+    },
+    {
+      "epoch": 0.043478260869565216,
+      "grad_norm": 0.20248189568519592,
+      "learning_rate": 4.053191489361702e-05,
+      "loss": 0.01805101931095123,
+      "step": 255
+    },
+    {
+      "epoch": 0.0443307757885763,
+      "grad_norm": 0.22623269259929657,
+      "learning_rate": 4.1329787234042545e-05,
+      "loss": 0.019811727106571198,
+      "step": 260
+    },
+    {
+      "epoch": 0.045183290707587385,
+      "grad_norm": 0.2050849199295044,
+      "learning_rate": 4.2127659574468086e-05,
+      "loss": 0.017767781019210817,
+      "step": 265
+    },
+    {
+      "epoch": 0.04603580562659847,
+      "grad_norm": 0.24867363274097443,
+      "learning_rate": 4.2925531914893614e-05,
+      "loss": 0.02127009928226471,
+      "step": 270
+    },
+    {
+      "epoch": 0.04688832054560955,
+      "grad_norm": 0.20721694827079773,
+      "learning_rate": 4.372340425531914e-05,
+      "loss": 0.022770658135414124,
+      "step": 275
+    },
+    {
+      "epoch": 0.04774083546462063,
+      "grad_norm": 0.19511370360851288,
+      "learning_rate": 4.452127659574468e-05,
+      "loss": 0.02165296971797943,
+      "step": 280
+    },
+    {
+      "epoch": 0.04859335038363171,
+      "grad_norm": 0.19066740572452545,
+      "learning_rate": 4.5319148936170204e-05,
+      "loss": 0.020857495069503785,
+      "step": 285
+    },
+    {
+      "epoch": 0.0494458653026428,
+      "grad_norm": 0.14217901229858398,
+      "learning_rate": 4.6117021276595746e-05,
+      "loss": 0.016413891315460206,
+      "step": 290
+    },
+    {
+      "epoch": 0.05029838022165388,
+      "grad_norm": 0.24177870154380798,
+      "learning_rate": 4.6914893617021274e-05,
+      "loss": 0.01902117133140564,
+      "step": 295
+    },
+    {
+      "epoch": 0.05115089514066496,
+      "grad_norm": 0.2742858827114105,
+      "learning_rate": 4.77127659574468e-05,
+      "loss": 0.016554126143455507,
+      "step": 300
+    },
+    {
+      "epoch": 0.05200341005967604,
+      "grad_norm": 0.24519385397434235,
+      "learning_rate": 4.851063829787234e-05,
+      "loss": 0.022036357223987578,
+      "step": 305
+    },
+    {
+      "epoch": 0.05285592497868713,
+      "grad_norm": 0.296572208404541,
+      "learning_rate": 4.930851063829787e-05,
+      "loss": 0.0196581095457077,
+      "step": 310
+    },
+    {
+      "epoch": 0.05370843989769821,
+      "grad_norm": 0.17092008888721466,
+      "learning_rate": 5.01063829787234e-05,
+      "loss": 0.015453743934631347,
+      "step": 315
+    },
+    {
+      "epoch": 0.05456095481670929,
+      "grad_norm": 0.17074067890644073,
+      "learning_rate": 5.090425531914893e-05,
+      "loss": 0.013983796536922454,
+      "step": 320
+    },
+    {
+      "epoch": 0.05541346973572037,
+      "grad_norm": 0.27302470803260803,
+      "learning_rate": 5.170212765957446e-05,
+      "loss": 0.015387402474880218,
+      "step": 325
+    },
+    {
+      "epoch": 0.056265984654731455,
+      "grad_norm": 0.2603592872619629,
+      "learning_rate": 5.2499999999999995e-05,
+      "loss": 0.013557825982570649,
+      "step": 330
+    },
+    {
+      "epoch": 0.05711849957374254,
+      "grad_norm": 0.23079948127269745,
+      "learning_rate": 5.329787234042553e-05,
+      "loss": 0.014809322357177735,
+      "step": 335
+    },
+    {
+      "epoch": 0.057971014492753624,
+      "grad_norm": 0.15029627084732056,
+      "learning_rate": 5.409574468085106e-05,
+      "loss": 0.018204084038734435,
+      "step": 340
+    },
+    {
+      "epoch": 0.058823529411764705,
+      "grad_norm": 0.2930934429168701,
+      "learning_rate": 5.4893617021276586e-05,
+      "loss": 0.02035558819770813,
+      "step": 345
+    },
+    {
+      "epoch": 0.059676044330775786,
+      "grad_norm": 0.19710905849933624,
+      "learning_rate": 5.569148936170213e-05,
+      "loss": 0.015025021135807037,
+      "step": 350
+    },
+    {
+      "epoch": 0.060528559249786874,
+      "grad_norm": 0.13316969573497772,
+      "learning_rate": 5.6489361702127655e-05,
+      "loss": 0.01258893460035324,
+      "step": 355
+    },
+    {
+      "epoch": 0.061381074168797956,
+      "grad_norm": 0.30591729283332825,
+      "learning_rate": 5.728723404255319e-05,
+      "loss": 0.0187319278717041,
+      "step": 360
+    },
+    {
+      "epoch": 0.06223358908780904,
+      "grad_norm": 0.22696663439273834,
+      "learning_rate": 5.808510638297872e-05,
+      "loss": 0.015805599093437196,
+      "step": 365
+    },
+    {
+      "epoch": 0.06308610400682012,
+      "grad_norm": 0.2800130546092987,
+      "learning_rate": 5.8882978723404245e-05,
+      "loss": 0.01719983071088791,
+      "step": 370
+    },
+    {
+      "epoch": 0.0639386189258312,
+      "grad_norm": 0.20671235024929047,
+      "learning_rate": 5.9680851063829786e-05,
+      "loss": 0.014449423551559449,
+      "step": 375
+    },
+    {
+      "epoch": 0.06479113384484228,
+      "grad_norm": 0.1630883365869522,
+      "learning_rate": 6.0478723404255314e-05,
+      "loss": 0.017153808474540712,
+      "step": 380
+    },
+    {
+      "epoch": 0.06564364876385337,
+      "grad_norm": 0.18699344992637634,
+      "learning_rate": 6.127659574468084e-05,
+      "loss": 0.015558701753616334,
+      "step": 385
+    },
+    {
+      "epoch": 0.06649616368286446,
+      "grad_norm": 0.15257929265499115,
+      "learning_rate": 6.207446808510638e-05,
+      "loss": 0.018240168690681458,
+      "step": 390
+    },
+    {
+      "epoch": 0.06734867860187553,
+      "grad_norm": 0.19658304750919342,
+      "learning_rate": 6.287234042553191e-05,
+      "loss": 0.015907022356987,
+      "step": 395
+    },
+    {
+      "epoch": 0.06820119352088662,
+      "grad_norm": 0.3743384778499603,
+      "learning_rate": 6.367021276595743e-05,
+      "loss": 0.014921861886978149,
+      "step": 400
+    },
+    {
+      "epoch": 0.06905370843989769,
+      "grad_norm": 0.254724383354187,
+      "learning_rate": 6.446808510638298e-05,
+      "loss": 0.018739913403987885,
+      "step": 405
+    },
+    {
+      "epoch": 0.06990622335890878,
+      "grad_norm": 0.19365151226520538,
+      "learning_rate": 6.52659574468085e-05,
+      "loss": 0.018984711170196532,
+      "step": 410
+    },
+    {
+      "epoch": 0.07075873827791987,
+      "grad_norm": 0.20728597044944763,
+      "learning_rate": 6.606382978723404e-05,
+      "loss": 0.01524859368801117,
+      "step": 415
+    },
+    {
+      "epoch": 0.07161125319693094,
+      "grad_norm": 0.1415344476699829,
+      "learning_rate": 6.686170212765957e-05,
+      "loss": 0.014004582166671753,
+      "step": 420
+    },
+    {
+      "epoch": 0.07246376811594203,
+      "grad_norm": 0.14169375598430634,
+      "learning_rate": 6.765957446808509e-05,
+      "loss": 0.013503608107566834,
+      "step": 425
+    },
+    {
+      "epoch": 0.0733162830349531,
+      "grad_norm": 0.22518369555473328,
+      "learning_rate": 6.845744680851064e-05,
+      "loss": 0.017587104439735414,
+      "step": 430
+    },
+    {
+      "epoch": 0.0741687979539642,
+      "grad_norm": 0.1091267541050911,
+      "learning_rate": 6.925531914893616e-05,
+      "loss": 0.013890406489372254,
+      "step": 435
+    },
+    {
+      "epoch": 0.07502131287297528,
+      "grad_norm": 0.24982722103595734,
+      "learning_rate": 7.00531914893617e-05,
+      "loss": 0.01599075198173523,
+      "step": 440
+    },
+    {
+      "epoch": 0.07587382779198636,
+      "grad_norm": 0.22311007976531982,
+      "learning_rate": 7.085106382978723e-05,
+      "loss": 0.014870230853557587,
+      "step": 445
+    },
+    {
+      "epoch": 0.07672634271099744,
+      "grad_norm": 0.27064985036849976,
+      "learning_rate": 7.164893617021276e-05,
+      "loss": 0.019213163852691652,
+      "step": 450
+    },
+    {
+      "epoch": 0.07757885763000852,
+      "grad_norm": 0.16876882314682007,
+      "learning_rate": 7.244680851063829e-05,
+      "loss": 0.014935044944286347,
+      "step": 455
+    },
+    {
+      "epoch": 0.0784313725490196,
+      "grad_norm": 0.18644963204860687,
+      "learning_rate": 7.324468085106382e-05,
+      "loss": 0.013823372125625611,
+      "step": 460
+    },
+    {
+      "epoch": 0.0792838874680307,
+      "grad_norm": 0.13067972660064697,
+      "learning_rate": 7.404255319148935e-05,
+      "loss": 0.013839980959892273,
+      "step": 465
+    },
+    {
+      "epoch": 0.08013640238704177,
+      "grad_norm": 0.0976850613951683,
+      "learning_rate": 7.484042553191489e-05,
+      "loss": 0.012782379984855652,
+      "step": 470
+    },
+    {
+      "epoch": 0.08098891730605286,
+      "grad_norm": 0.2523496150970459,
+      "learning_rate": 7.499999439800074e-05,
+      "loss": 0.013075053691864014,
+      "step": 475
+    },
+    {
+      "epoch": 0.08184143222506395,
+      "grad_norm": 0.18349343538284302,
+      "learning_rate": 7.499997163988164e-05,
+      "loss": 0.01753528565168381,
+      "step": 480
+    },
+    {
+      "epoch": 0.08269394714407502,
+      "grad_norm": 0.16528834402561188,
+      "learning_rate": 7.499993137552834e-05,
+      "loss": 0.012987489998340606,
+      "step": 485
+    },
+    {
+      "epoch": 0.08354646206308611,
+      "grad_norm": 0.1918938159942627,
+      "learning_rate": 7.499987360495964e-05,
+      "loss": 0.018496687710285186,
+      "step": 490
+    },
+    {
+      "epoch": 0.08439897698209718,
+      "grad_norm": 0.11452502012252808,
+      "learning_rate": 7.499979832820255e-05,
+      "loss": 0.015578755736351013,
+      "step": 495
+    },
+    {
+      "epoch": 0.08525149190110827,
+      "grad_norm": 0.2084985226392746,
+      "learning_rate": 7.499970554529216e-05,
+      "loss": 0.014264023303985596,
+      "step": 500
+    },
+    {
+      "epoch": 0.08610400682011936,
+      "grad_norm": 0.13777600228786469,
+      "learning_rate": 7.49995952562718e-05,
+      "loss": 0.014527246356010437,
+      "step": 505
+    },
+    {
+      "epoch": 0.08695652173913043,
+      "grad_norm": 0.2515336275100708,
+      "learning_rate": 7.499946746119296e-05,
+      "loss": 0.019042417407035828,
+      "step": 510
+    },
+    {
+      "epoch": 0.08780903665814152,
+      "grad_norm": 0.12859591841697693,
+      "learning_rate": 7.499932216011531e-05,
+      "loss": 0.01340993344783783,
+      "step": 515
+    },
+    {
+      "epoch": 0.0886615515771526,
+      "grad_norm": 0.15603038668632507,
+      "learning_rate": 7.499915935310667e-05,
+      "loss": 0.01645509898662567,
+      "step": 520
+    },
+    {
+      "epoch": 0.08951406649616368,
+      "grad_norm": 0.1493784785270691,
+      "learning_rate": 7.499897904024303e-05,
+      "loss": 0.016503919661045075,
+      "step": 525
+    },
+    {
+      "epoch": 0.09036658141517477,
+      "grad_norm": 0.14551150798797607,
+      "learning_rate": 7.499878122160858e-05,
+      "loss": 0.013891169428825378,
+      "step": 530
+    },
+    {
+      "epoch": 0.09121909633418585,
+      "grad_norm": 0.12197990715503693,
+      "learning_rate": 7.499856589729569e-05,
+      "loss": 0.01531532108783722,
+      "step": 535
+    },
+    {
+      "epoch": 0.09207161125319693,
+      "grad_norm": 0.24787496030330658,
+      "learning_rate": 7.499833306740485e-05,
+      "loss": 0.016374409198760986,
+      "step": 540
+    },
+    {
+      "epoch": 0.09292412617220801,
+      "grad_norm": 0.10902808606624603,
+      "learning_rate": 7.499808273204476e-05,
+      "loss": 0.013505718111991883,
+      "step": 545
+    },
+    {
+      "epoch": 0.0937766410912191,
+      "grad_norm": 0.16540755331516266,
+      "learning_rate": 7.499781489133228e-05,
+      "loss": 0.016257329285144805,
+      "step": 550
+    },
+    {
+      "epoch": 0.09462915601023018,
+      "grad_norm": 0.1228717565536499,
+      "learning_rate": 7.499752954539245e-05,
+      "loss": 0.011345921456813813,
+      "step": 555
+    },
+    {
+      "epoch": 0.09548167092924126,
+      "grad_norm": 0.12704797089099884,
+      "learning_rate": 7.49972266943585e-05,
+      "loss": 0.014449910819530487,
+      "step": 560
+    },
+    {
+      "epoch": 0.09633418584825235,
+      "grad_norm": 0.2014201581478119,
+      "learning_rate": 7.499690633837178e-05,
+      "loss": 0.01456935852766037,
+      "step": 565
+    },
+    {
+      "epoch": 0.09718670076726342,
+      "grad_norm": 0.17480657994747162,
+      "learning_rate": 7.499656847758187e-05,
+      "loss": 0.014413098990917205,
+      "step": 570
+    },
+    {
+      "epoch": 0.09803921568627451,
+      "grad_norm": 0.18946893513202667,
+      "learning_rate": 7.499621311214646e-05,
+      "loss": 0.0139508917927742,
+      "step": 575
+    },
+    {
+      "epoch": 0.0988917306052856,
+      "grad_norm": 0.15367820858955383,
+      "learning_rate": 7.499584024223149e-05,
+      "loss": 0.014091435074806213,
+      "step": 580
+    },
+    {
+      "epoch": 0.09974424552429667,
+      "grad_norm": 0.15018688142299652,
+      "learning_rate": 7.499544986801099e-05,
+      "loss": 0.016737687587738036,
+      "step": 585
+    },
+    {
+      "epoch": 0.10059676044330776,
+      "grad_norm": 0.17522579431533813,
+      "learning_rate": 7.499504198966722e-05,
+      "loss": 0.015822765231132508,
+      "step": 590
+    },
+    {
+      "epoch": 0.10144927536231885,
+      "grad_norm": 0.12634818255901337,
+      "learning_rate": 7.499461660739059e-05,
+      "loss": 0.015363042056560517,
+      "step": 595
+    },
+    {
+      "epoch": 0.10230179028132992,
+      "grad_norm": 0.12466495484113693,
+      "learning_rate": 7.499417372137968e-05,
+      "loss": 0.013208043575286866,
+      "step": 600
+    },
+    {
+      "epoch": 0.10315430520034101,
+      "grad_norm": 0.18877951800823212,
+      "learning_rate": 7.499371333184125e-05,
+      "loss": 0.016261917352676392,
+      "step": 605
+    },
+    {
+      "epoch": 0.10400682011935208,
+      "grad_norm": 0.21521399915218353,
+      "learning_rate": 7.49932354389902e-05,
+      "loss": 0.013861049711704255,
+      "step": 610
+    },
+    {
+      "epoch": 0.10485933503836317,
+      "grad_norm": 0.1375613659620285,
+      "learning_rate": 7.499274004304964e-05,
+      "loss": 0.015597744286060334,
+      "step": 615
+    },
+    {
+      "epoch": 0.10571184995737426,
+      "grad_norm": 0.16078200936317444,
+      "learning_rate": 7.499222714425087e-05,
+      "loss": 0.018308353424072266,
+      "step": 620
+    },
+    {
+      "epoch": 0.10656436487638533,
+      "grad_norm": 0.15485632419586182,
+      "learning_rate": 7.499169674283328e-05,
+      "loss": 0.015836401283740996,
+      "step": 625
+    },
+    {
+      "epoch": 0.10741687979539642,
+      "grad_norm": 0.14019452035427094,
+      "learning_rate": 7.499114883904451e-05,
+      "loss": 0.014591602981090546,
+      "step": 630
+    },
+    {
+      "epoch": 0.1082693947144075,
+      "grad_norm": 0.2042212039232254,
+      "learning_rate": 7.499058343314031e-05,
+      "loss": 0.01718664914369583,
+      "step": 635
+    },
+    {
+      "epoch": 0.10912190963341858,
+      "grad_norm": 0.13801656663417816,
+      "learning_rate": 7.499000052538467e-05,
+      "loss": 0.015579727292060853,
+      "step": 640
+    },
+    {
+      "epoch": 0.10997442455242967,
+      "grad_norm": 0.12787523865699768,
+      "learning_rate": 7.498940011604968e-05,
+      "loss": 0.012525486946105956,
+      "step": 645
+    },
+    {
+      "epoch": 0.11082693947144075,
+      "grad_norm": 0.1752539724111557,
+      "learning_rate": 7.498878220541564e-05,
+      "loss": 0.014286568760871888,
+      "step": 650
+    },
+    {
+      "epoch": 0.11167945439045183,
+      "grad_norm": 0.12485212087631226,
+      "learning_rate": 7.498814679377101e-05,
+      "loss": 0.01482405811548233,
+      "step": 655
+    },
+    {
+      "epoch": 0.11253196930946291,
+      "grad_norm": 0.10980220139026642,
+      "learning_rate": 7.498749388141243e-05,
+      "loss": 0.01597980558872223,
+      "step": 660
+    },
+    {
+      "epoch": 0.113384484228474,
+      "grad_norm": 0.09144977480173111,
+      "learning_rate": 7.498682346864469e-05,
+      "loss": 0.011583130061626434,
+      "step": 665
+    },
+    {
+      "epoch": 0.11423699914748509,
+      "grad_norm": 0.11955336481332779,
+      "learning_rate": 7.498613555578076e-05,
+      "loss": 0.013009116053581238,
+      "step": 670
+    },
+    {
+      "epoch": 0.11508951406649616,
+      "grad_norm": 0.14505070447921753,
+      "learning_rate": 7.49854301431418e-05,
+      "loss": 0.013878281414508819,
+      "step": 675
+    },
+    {
+      "epoch": 0.11594202898550725,
+      "grad_norm": 0.15674598515033722,
+      "learning_rate": 7.49847072310571e-05,
+      "loss": 0.014717698097229004,
+      "step": 680
+    },
+    {
+      "epoch": 0.11679454390451834,
+      "grad_norm": 0.16684003174304962,
+      "learning_rate": 7.498396681986413e-05,
+      "loss": 0.015567027032375336,
+      "step": 685
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 0.13314439356327057,
+      "learning_rate": 7.498320890990857e-05,
+      "loss": 0.017679129540920258,
+      "step": 690
+    },
+    {
+      "epoch": 0.1184995737425405,
+      "grad_norm": 0.1099700927734375,
+      "learning_rate": 7.498243350154423e-05,
+      "loss": 0.015660777688026428,
+      "step": 695
+    },
+    {
+      "epoch": 0.11935208866155157,
+      "grad_norm": 0.09305288642644882,
+      "learning_rate": 7.498164059513307e-05,
+      "loss": 0.011864218115806579,
+      "step": 700
+    },
+    {
+      "epoch": 0.12020460358056266,
+      "grad_norm": 0.1284978687763214,
+      "learning_rate": 7.498083019104527e-05,
+      "loss": 0.013128276169300079,
+      "step": 705
+    },
+    {
+      "epoch": 0.12105711849957375,
+      "grad_norm": 0.19205476343631744,
+      "learning_rate": 7.498000228965913e-05,
+      "loss": 0.014518238604068756,
+      "step": 710
+    },
+    {
+      "epoch": 0.12190963341858482,
+      "grad_norm": 0.25064221024513245,
+      "learning_rate": 7.497915689136119e-05,
+      "loss": 0.014235696196556092,
+      "step": 715
+    },
+    {
+      "epoch": 0.12276214833759591,
+      "grad_norm": 0.11866044998168945,
+      "learning_rate": 7.497829399654607e-05,
+      "loss": 0.013622967898845673,
+      "step": 720
+    },
+    {
+      "epoch": 0.12361466325660699,
+      "grad_norm": 0.1366252452135086,
+      "learning_rate": 7.49774136056166e-05,
+      "loss": 0.013592693209648132,
+      "step": 725
+    },
+    {
+      "epoch": 0.12446717817561807,
+      "grad_norm": 0.12722773849964142,
+      "learning_rate": 7.497651571898379e-05,
+      "loss": 0.02055167257785797,
+      "step": 730
+    },
+    {
+      "epoch": 0.12531969309462915,
+      "grad_norm": 0.07723517715930939,
+      "learning_rate": 7.49756003370668e-05,
+      "loss": 0.012377069890499115,
+      "step": 735
+    },
+    {
+      "epoch": 0.12617220801364024,
+      "grad_norm": 0.11081967502832413,
+      "learning_rate": 7.497466746029293e-05,
+      "loss": 0.013797640800476074,
+      "step": 740
+    },
+    {
+      "epoch": 0.12702472293265132,
+      "grad_norm": 0.1117677390575409,
+      "learning_rate": 7.497371708909771e-05,
+      "loss": 0.01338990479707718,
+      "step": 745
+    },
+    {
+      "epoch": 0.1278772378516624,
+      "grad_norm": 0.24659112095832825,
+      "learning_rate": 7.497274922392483e-05,
+      "loss": 0.012844511866569519,
+      "step": 750
+    },
+    {
+      "epoch": 0.1287297527706735,
+      "grad_norm": 0.24900244176387787,
+      "learning_rate": 7.497176386522606e-05,
+      "loss": 0.015656352043151855,
+      "step": 755
+    },
+    {
+      "epoch": 0.12958226768968456,
+      "grad_norm": 0.1331390142440796,
+      "learning_rate": 7.497076101346144e-05,
+      "loss": 0.013722085952758789,
+      "step": 760
+    },
+    {
+      "epoch": 0.13043478260869565,
+      "grad_norm": 0.1224697008728981,
+      "learning_rate": 7.496974066909913e-05,
+      "loss": 0.011186304688453674,
+      "step": 765
+    },
+    {
+      "epoch": 0.13128729752770674,
+      "grad_norm": 0.11053820699453354,
+      "learning_rate": 7.496870283261546e-05,
+      "loss": 0.012894454598426818,
+      "step": 770
+    },
+    {
+      "epoch": 0.13213981244671782,
+      "grad_norm": 0.09663277864456177,
+      "learning_rate": 7.49676475044949e-05,
+      "loss": 0.015331995487213135,
+      "step": 775
+    },
+    {
+      "epoch": 0.1329923273657289,
+      "grad_norm": 0.1483219712972641,
+      "learning_rate": 7.496657468523014e-05,
+      "loss": 0.015070399641990662,
+      "step": 780
+    },
+    {
+      "epoch": 0.13384484228473997,
+      "grad_norm": 0.12375539541244507,
+      "learning_rate": 7.496548437532202e-05,
+      "loss": 0.013722005486488342,
+      "step": 785
+    },
+    {
+      "epoch": 0.13469735720375106,
+      "grad_norm": 0.14662130177021027,
+      "learning_rate": 7.496437657527949e-05,
+      "loss": 0.012852996587753296,
+      "step": 790
+    },
+    {
+      "epoch": 0.13554987212276215,
+      "grad_norm": 0.1740300953388214,
+      "learning_rate": 7.496325128561975e-05,
+      "loss": 0.014796209335327149,
+      "step": 795
+    },
+    {
+      "epoch": 0.13640238704177324,
+      "grad_norm": 0.10670243203639984,
+      "learning_rate": 7.496210850686809e-05,
+      "loss": 0.013983005285263061,
+      "step": 800
+    },
+    {
+      "epoch": 0.13725490196078433,
+      "grad_norm": 0.1362515240907669,
+      "learning_rate": 7.496094823955801e-05,
+      "loss": 0.014472618699073792,
+      "step": 805
+    },
+    {
+      "epoch": 0.13810741687979539,
+      "grad_norm": 0.11403689533472061,
+      "learning_rate": 7.495977048423117e-05,
+      "loss": 0.01294848918914795,
+      "step": 810
+    },
+    {
+      "epoch": 0.13895993179880647,
+      "grad_norm": 0.11532565206289291,
+      "learning_rate": 7.495857524143738e-05,
+      "loss": 0.011346425861120224,
+      "step": 815
+    },
+    {
+      "epoch": 0.13981244671781756,
+      "grad_norm": 0.1506761759519577,
+      "learning_rate": 7.495736251173463e-05,
+      "loss": 0.016532811522483825,
+      "step": 820
+    },
+    {
+      "epoch": 0.14066496163682865,
+      "grad_norm": 0.10915899276733398,
+      "learning_rate": 7.495613229568903e-05,
+      "loss": 0.01278679072856903,
+      "step": 825
+    },
+    {
+      "epoch": 0.14151747655583974,
+      "grad_norm": 0.10394130647182465,
+      "learning_rate": 7.49548845938749e-05,
+      "loss": 0.011449626088142395,
+      "step": 830
+    },
+    {
+      "epoch": 0.1423699914748508,
+      "grad_norm": 0.08730677515268326,
+      "learning_rate": 7.495361940687475e-05,
+      "loss": 0.011916645616292954,
+      "step": 835
+    },
+    {
+      "epoch": 0.1432225063938619,
+      "grad_norm": 0.08257348835468292,
+      "learning_rate": 7.495233673527914e-05,
+      "loss": 0.013689276576042176,
+      "step": 840
+    },
+    {
+      "epoch": 0.14407502131287298,
+      "grad_norm": 0.182078555226326,
+      "learning_rate": 7.495103657968692e-05,
+      "loss": 0.019141729176044463,
+      "step": 845
+    },
+    {
+      "epoch": 0.14492753623188406,
+      "grad_norm": 0.105568528175354,
+      "learning_rate": 7.494971894070501e-05,
+      "loss": 0.015522226691246033,
+      "step": 850
+    },
+    {
+      "epoch": 0.14578005115089515,
+      "grad_norm": 0.09030122309923172,
+      "learning_rate": 7.494838381894856e-05,
+      "loss": 0.012900182604789734,
+      "step": 855
+    },
+    {
+      "epoch": 0.1466325660699062,
+      "grad_norm": 0.11199921369552612,
+      "learning_rate": 7.494703121504082e-05,
+      "loss": 0.013011230528354645,
+      "step": 860
+    },
+    {
+      "epoch": 0.1474850809889173,
+      "grad_norm": 0.11342430859804153,
+      "learning_rate": 7.494566112961325e-05,
+      "loss": 0.015477502346038818,
+      "step": 865
+    },
+    {
+      "epoch": 0.1483375959079284,
+      "grad_norm": 0.07956613600254059,
+      "learning_rate": 7.494427356330544e-05,
+      "loss": 0.011270551383495331,
+      "step": 870
+    },
+    {
+      "epoch": 0.14919011082693948,
+      "grad_norm": 0.13356897234916687,
+      "learning_rate": 7.494286851676515e-05,
+      "loss": 0.012481572479009629,
+      "step": 875
+    },
+    {
+      "epoch": 0.15004262574595056,
+      "grad_norm": 0.14493827521800995,
+      "learning_rate": 7.494144599064833e-05,
+      "loss": 0.015318951010704041,
+      "step": 880
+    },
+    {
+      "epoch": 0.15089514066496162,
+      "grad_norm": 0.13254614174365997,
+      "learning_rate": 7.494000598561902e-05,
+      "loss": 0.012697519361972808,
+      "step": 885
+    },
+    {
+      "epoch": 0.1517476555839727,
+      "grad_norm": 0.12164720892906189,
+      "learning_rate": 7.49385485023495e-05,
+      "loss": 0.011361779272556305,
+      "step": 890
+    },
+    {
+      "epoch": 0.1526001705029838,
+      "grad_norm": 0.10743863880634308,
+      "learning_rate": 7.493707354152015e-05,
+      "loss": 0.012824115157127381,
+      "step": 895
+    },
+    {
+      "epoch": 0.1534526854219949,
+      "grad_norm": 0.0933203473687172,
+      "learning_rate": 7.493558110381954e-05,
+      "loss": 0.012234293669462205,
+      "step": 900
+    },
+    {
+      "epoch": 0.15430520034100598,
+      "grad_norm": 0.10252948850393295,
+      "learning_rate": 7.493407118994437e-05,
+      "loss": 0.01874733567237854,
+      "step": 905
+    },
+    {
+      "epoch": 0.15515771526001704,
+      "grad_norm": 0.1184248998761177,
+      "learning_rate": 7.493254380059954e-05,
+      "loss": 0.012014241516590118,
+      "step": 910
+    },
+    {
+      "epoch": 0.15601023017902813,
+      "grad_norm": 0.10140799731016159,
+      "learning_rate": 7.49309989364981e-05,
+      "loss": 0.013288506865501403,
+      "step": 915
+    },
+    {
+      "epoch": 0.1568627450980392,
+      "grad_norm": 0.15704941749572754,
+      "learning_rate": 7.492943659836121e-05,
+      "loss": 0.012907981872558594,
+      "step": 920
+    },
+    {
+      "epoch": 0.1577152600170503,
+      "grad_norm": 0.10368761420249939,
+      "learning_rate": 7.492785678691822e-05,
+      "loss": 0.01384827345609665,
+      "step": 925
+    },
+    {
+      "epoch": 0.1585677749360614,
+      "grad_norm": 0.13517284393310547,
+      "learning_rate": 7.492625950290668e-05,
+      "loss": 0.014644764363765717,
+      "step": 930
+    },
+    {
+      "epoch": 0.15942028985507245,
+      "grad_norm": 0.08189263194799423,
+      "learning_rate": 7.492464474707222e-05,
+      "loss": 0.011974713951349258,
+      "step": 935
+    },
+    {
+      "epoch": 0.16027280477408354,
+      "grad_norm": 0.11737149208784103,
+      "learning_rate": 7.492301252016867e-05,
+      "loss": 0.014023615419864655,
+      "step": 940
+    },
+    {
+      "epoch": 0.16112531969309463,
+      "grad_norm": 0.15778031945228577,
+      "learning_rate": 7.492136282295801e-05,
+      "loss": 0.01533726304769516,
+      "step": 945
+    },
+    {
+      "epoch": 0.16197783461210571,
+      "grad_norm": 0.14194118976593018,
+      "learning_rate": 7.491969565621036e-05,
+      "loss": 0.01569782793521881,
+      "step": 950
+    },
+    {
+      "epoch": 0.1628303495311168,
+      "grad_norm": 0.12579558789730072,
+      "learning_rate": 7.491801102070403e-05,
+      "loss": 0.012844063341617584,
+      "step": 955
+    },
+    {
+      "epoch": 0.1636828644501279,
+      "grad_norm": 0.10578597337007523,
+      "learning_rate": 7.491630891722547e-05,
+      "loss": 0.011186198890209198,
+      "step": 960
+    },
+    {
+      "epoch": 0.16453537936913895,
+      "grad_norm": 0.12398207187652588,
+      "learning_rate": 7.491458934656925e-05,
+      "loss": 0.014328254759311676,
+      "step": 965
+    },
+    {
+      "epoch": 0.16538789428815004,
+      "grad_norm": 0.09390626102685928,
+      "learning_rate": 7.491285230953814e-05,
+      "loss": 0.013881708681583404,
+      "step": 970
+    },
+    {
+      "epoch": 0.16624040920716113,
+      "grad_norm": 0.17196106910705566,
+      "learning_rate": 7.491109780694303e-05,
+      "loss": 0.014424234628677368,
+      "step": 975
+    },
+    {
+      "epoch": 0.16709292412617222,
+      "grad_norm": 0.06994624435901642,
+      "learning_rate": 7.490932583960302e-05,
+      "loss": 0.010434426367282867,
+      "step": 980
+    },
+    {
+      "epoch": 0.1679454390451833,
+      "grad_norm": 0.09414499998092651,
+      "learning_rate": 7.490753640834527e-05,
+      "loss": 0.010483803600072861,
+      "step": 985
+    },
+    {
+      "epoch": 0.16879795396419436,
+      "grad_norm": 0.11002875864505768,
+      "learning_rate": 7.490572951400518e-05,
+      "loss": 0.009266073256731034,
+      "step": 990
+    },
+    {
+      "epoch": 0.16965046888320545,
+      "grad_norm": 0.14956022799015045,
+      "learning_rate": 7.490390515742626e-05,
+      "loss": 0.015529079735279084,
+      "step": 995
+    },
+    {
+      "epoch": 0.17050298380221654,
+      "grad_norm": 0.13828666508197784,
+      "learning_rate": 7.490206333946019e-05,
+      "loss": 0.011511271446943283,
+      "step": 1000
+    },
+    {
+      "epoch": 0.17135549872122763,
+      "grad_norm": 0.1265997439622879,
+      "learning_rate": 7.490020406096678e-05,
+      "loss": 0.010465707629919052,
+      "step": 1005
+    },
+    {
+      "epoch": 0.17220801364023872,
+      "grad_norm": 0.07772056013345718,
+      "learning_rate": 7.489832732281401e-05,
+      "loss": 0.013828210532665253,
+      "step": 1010
+    },
+    {
+      "epoch": 0.17306052855924978,
+      "grad_norm": 0.08055376261472702,
+      "learning_rate": 7.489643312587799e-05,
+      "loss": 0.013010218739509583,
+      "step": 1015
+    },
+    {
+      "epoch": 0.17391304347826086,
+      "grad_norm": 0.09059367328882217,
+      "learning_rate": 7.489452147104301e-05,
+      "loss": 0.013864235579967498,
+      "step": 1020
+    },
+    {
+      "epoch": 0.17476555839727195,
+      "grad_norm": 0.15273553133010864,
+      "learning_rate": 7.489259235920149e-05,
+      "loss": 0.013432112336158753,
+      "step": 1025
+    },
+    {
+      "epoch": 0.17561807331628304,
+      "grad_norm": 0.11343793570995331,
+      "learning_rate": 7.489064579125399e-05,
+      "loss": 0.01213686615228653,
+      "step": 1030
+    },
+    {
+      "epoch": 0.17647058823529413,
+      "grad_norm": 0.11880069226026535,
+      "learning_rate": 7.488868176810926e-05,
+      "loss": 0.012188264727592468,
+      "step": 1035
+    },
+    {
+      "epoch": 0.1773231031543052,
+      "grad_norm": 0.16270127892494202,
+      "learning_rate": 7.488670029068415e-05,
+      "loss": 0.015294317901134492,
+      "step": 1040
+    },
+    {
+      "epoch": 0.17817561807331628,
+      "grad_norm": 0.11542797088623047,
+      "learning_rate": 7.488470135990369e-05,
+      "loss": 0.013500772416591644,
+      "step": 1045
+    },
+    {
+      "epoch": 0.17902813299232737,
+      "grad_norm": 0.09579882025718689,
+      "learning_rate": 7.488268497670103e-05,
+      "loss": 0.013453315198421478,
+      "step": 1050
+    },
+    {
+      "epoch": 0.17988064791133845,
+      "grad_norm": 0.08847666531801224,
+      "learning_rate": 7.488065114201752e-05,
+      "loss": 0.0153861403465271,
+      "step": 1055
+    },
+    {
+      "epoch": 0.18073316283034954,
+      "grad_norm": 0.11167823523283005,
+      "learning_rate": 7.487859985680257e-05,
+      "loss": 0.011502107977867127,
+      "step": 1060
+    },
+    {
+      "epoch": 0.1815856777493606,
+      "grad_norm": 0.11255413293838501,
+      "learning_rate": 7.487653112201385e-05,
+      "loss": 0.012194579839706421,
+      "step": 1065
+    },
+    {
+      "epoch": 0.1824381926683717,
+      "grad_norm": 0.10929680615663528,
+      "learning_rate": 7.487444493861705e-05,
+      "loss": 0.015874122083187104,
+      "step": 1070
+    },
+    {
+      "epoch": 0.18329070758738278,
+      "grad_norm": 0.10753592848777771,
+      "learning_rate": 7.487234130758613e-05,
+      "loss": 0.009445396810770034,
+      "step": 1075
+    },
+    {
+      "epoch": 0.18414322250639387,
+      "grad_norm": 0.11368737369775772,
+      "learning_rate": 7.487022022990309e-05,
+      "loss": 0.011674505472183228,
+      "step": 1080
+    },
+    {
+      "epoch": 0.18499573742540495,
+      "grad_norm": 0.12944836914539337,
+      "learning_rate": 7.486808170655813e-05,
+      "loss": 0.011856313049793243,
+      "step": 1085
+    },
+    {
+      "epoch": 0.18584825234441602,
+      "grad_norm": 0.0833214819431305,
+      "learning_rate": 7.48659257385496e-05,
+      "loss": 0.014119544625282287,
+      "step": 1090
+    },
+    {
+      "epoch": 0.1867007672634271,
+      "grad_norm": 0.11955790221691132,
+      "learning_rate": 7.486375232688397e-05,
+      "loss": 0.012977911531925202,
+      "step": 1095
+    },
+    {
+      "epoch": 0.1875532821824382,
+      "grad_norm": 0.1452455222606659,
+      "learning_rate": 7.486156147257584e-05,
+      "loss": 0.015410827100276947,
+      "step": 1100
+    },
+    {
+      "epoch": 0.18840579710144928,
+      "grad_norm": 0.09630092978477478,
+      "learning_rate": 7.485935317664801e-05,
+      "loss": 0.013698874413967133,
+      "step": 1105
+    },
+    {
+      "epoch": 0.18925831202046037,
+      "grad_norm": 0.11687257140874863,
+      "learning_rate": 7.485712744013137e-05,
+      "loss": 0.013196484744548797,
+      "step": 1110
+    },
+    {
+      "epoch": 0.19011082693947143,
+      "grad_norm": 0.08894632011651993,
+      "learning_rate": 7.485488426406495e-05,
+      "loss": 0.01540881097316742,
+      "step": 1115
+    },
+    {
+      "epoch": 0.19096334185848252,
+      "grad_norm": 0.09196458756923676,
+      "learning_rate": 7.485262364949597e-05,
+      "loss": 0.012018527090549468,
+      "step": 1120
+    },
+    {
+      "epoch": 0.1918158567774936,
+      "grad_norm": 0.12328553944826126,
+      "learning_rate": 7.485034559747974e-05,
+      "loss": 0.014925773441791534,
+      "step": 1125
+    },
+    {
+      "epoch": 0.1926683716965047,
+      "grad_norm": 0.12566202878952026,
+      "learning_rate": 7.484805010907975e-05,
+      "loss": 0.01104198843240738,
+      "step": 1130
+    },
+    {
+      "epoch": 0.19352088661551578,
+      "grad_norm": 0.1022765263915062,
+      "learning_rate": 7.484573718536758e-05,
+      "loss": 0.0118367500603199,
+      "step": 1135
+    },
+    {
+      "epoch": 0.19437340153452684,
+      "grad_norm": 0.09682224690914154,
+      "learning_rate": 7.4843406827423e-05,
+      "loss": 0.011423001438379288,
+      "step": 1140
+    },
+    {
+      "epoch": 0.19522591645353793,
+      "grad_norm": 0.15166254341602325,
+      "learning_rate": 7.484105903633388e-05,
+      "loss": 0.014048118889331818,
+      "step": 1145
+    },
+    {
+      "epoch": 0.19607843137254902,
+      "grad_norm": 0.09285032004117966,
+      "learning_rate": 7.483869381319627e-05,
+      "loss": 0.012882034480571746,
+      "step": 1150
+    },
+    {
+      "epoch": 0.1969309462915601,
+      "grad_norm": 0.09011214971542358,
+      "learning_rate": 7.483631115911434e-05,
+      "loss": 0.01419239491224289,
+      "step": 1155
+    },
+    {
+      "epoch": 0.1977834612105712,
+      "grad_norm": 0.14540383219718933,
+      "learning_rate": 7.483391107520037e-05,
+      "loss": 0.014623096585273743,
+      "step": 1160
+    },
+    {
+      "epoch": 0.19863597612958228,
+      "grad_norm": 0.12326448410749435,
+      "learning_rate": 7.483149356257479e-05,
+      "loss": 0.013109591603279114,
+      "step": 1165
+    },
+    {
+      "epoch": 0.19948849104859334,
+      "grad_norm": 0.07067535817623138,
+      "learning_rate": 7.482905862236622e-05,
+      "loss": 0.013740380108356477,
+      "step": 1170
+    },
+    {
+      "epoch": 0.20034100596760443,
+      "grad_norm": 0.10170529782772064,
+      "learning_rate": 7.482660625571134e-05,
+      "loss": 0.011151721328496933,
+      "step": 1175
+    },
+    {
+      "epoch": 0.20119352088661552,
+      "grad_norm": 0.10074683278799057,
+      "learning_rate": 7.482413646375498e-05,
+      "loss": 0.01180294007062912,
+      "step": 1180
+    },
+    {
+      "epoch": 0.2020460358056266,
+      "grad_norm": 0.047992780804634094,
+      "learning_rate": 7.482164924765016e-05,
+      "loss": 0.01065710186958313,
+      "step": 1185
+    },
+    {
+      "epoch": 0.2028985507246377,
+      "grad_norm": 0.1279197484254837,
+      "learning_rate": 7.481914460855796e-05,
+      "loss": 0.012219739705324173,
+      "step": 1190
+    },
+    {
+      "epoch": 0.20375106564364875,
+      "grad_norm": 0.11339649558067322,
+      "learning_rate": 7.481662254764765e-05,
+      "loss": 0.012664712965488434,
+      "step": 1195
+    },
+    {
+      "epoch": 0.20460358056265984,
+      "grad_norm": 0.10576959699392319,
+      "learning_rate": 7.481408306609662e-05,
+      "loss": 0.010009048134088516,
+      "step": 1200
+    },
+    {
+      "epoch": 0.20545609548167093,
+      "grad_norm": 0.08073283731937408,
+      "learning_rate": 7.481152616509037e-05,
+      "loss": 0.011126396805047989,
+      "step": 1205
+    },
+    {
+      "epoch": 0.20630861040068202,
+      "grad_norm": 0.09888558834791183,
+      "learning_rate": 7.480895184582253e-05,
+      "loss": 0.013096305727958679,
+      "step": 1210
+    },
+    {
+      "epoch": 0.2071611253196931,
+      "grad_norm": 0.09703118354082108,
+      "learning_rate": 7.48063601094949e-05,
+      "loss": 0.010653502494096755,
+      "step": 1215
+    },
+    {
+      "epoch": 0.20801364023870417,
+      "grad_norm": 0.10693266987800598,
+      "learning_rate": 7.48037509573174e-05,
+      "loss": 0.012283077836036682,
+      "step": 1220
+    },
+    {
+      "epoch": 0.20886615515771526,
+      "grad_norm": 0.1024889275431633,
+      "learning_rate": 7.480112439050804e-05,
+      "loss": 0.012971282005310059,
+      "step": 1225
+    },
+    {
+      "epoch": 0.20971867007672634,
+      "grad_norm": 0.10043203830718994,
+      "learning_rate": 7.4798480410293e-05,
+      "loss": 0.011451539397239686,
+      "step": 1230
+    },
+    {
+      "epoch": 0.21057118499573743,
+      "grad_norm": 0.11248672753572464,
+      "learning_rate": 7.47958190179066e-05,
+      "loss": 0.012805460393428803,
+      "step": 1235
+    },
+    {
+      "epoch": 0.21142369991474852,
+      "grad_norm": 0.08651525527238846,
+      "learning_rate": 7.479314021459123e-05,
+      "loss": 0.013016811013221741,
+      "step": 1240
+    },
+    {
+      "epoch": 0.21227621483375958,
+      "grad_norm": 0.06062095984816551,
+      "learning_rate": 7.479044400159746e-05,
+      "loss": 0.01299230456352234,
+      "step": 1245
+    },
+    {
+      "epoch": 0.21312872975277067,
+      "grad_norm": 0.1589215248823166,
+      "learning_rate": 7.478773038018397e-05,
+      "loss": 0.012607543170452118,
+      "step": 1250
+    },
+    {
+      "epoch": 0.21398124467178176,
+      "grad_norm": 0.12105076014995575,
+      "learning_rate": 7.478499935161758e-05,
+      "loss": 0.012772174179553985,
+      "step": 1255
+    },
+    {
+      "epoch": 0.21483375959079284,
+      "grad_norm": 0.0846070721745491,
+      "learning_rate": 7.478225091717323e-05,
+      "loss": 0.009387130290269852,
+      "step": 1260
+    },
+    {
+      "epoch": 0.21568627450980393,
+      "grad_norm": 0.054560381919145584,
+      "learning_rate": 7.477948507813396e-05,
+      "loss": 0.013299009203910828,
+      "step": 1265
+    },
+    {
+      "epoch": 0.216538789428815,
+      "grad_norm": 0.10125566273927689,
+      "learning_rate": 7.477670183579094e-05,
+      "loss": 0.013010343909263611,
+      "step": 1270
+    },
+    {
+      "epoch": 0.21739130434782608,
+      "grad_norm": 0.10493458807468414,
+      "learning_rate": 7.477390119144353e-05,
+      "loss": 0.013531042635440827,
+      "step": 1275
+    },
+    {
+      "epoch": 0.21824381926683717,
+      "grad_norm": 0.07453935593366623,
+      "learning_rate": 7.477108314639913e-05,
+      "loss": 0.01330820918083191,
+      "step": 1280
+    },
+    {
+      "epoch": 0.21909633418584826,
+      "grad_norm": 0.14430643618106842,
+      "learning_rate": 7.47682477019733e-05,
+      "loss": 0.015061555802822113,
+      "step": 1285
+    },
+    {
+      "epoch": 0.21994884910485935,
+      "grad_norm": 0.1073407456278801,
+      "learning_rate": 7.476539485948973e-05,
+      "loss": 0.011137319356203079,
+      "step": 1290
+    },
+    {
+      "epoch": 0.2208013640238704,
+      "grad_norm": 0.16794899106025696,
+      "learning_rate": 7.476252462028021e-05,
+      "loss": 0.013223762810230254,
+      "step": 1295
+    },
+    {
+      "epoch": 0.2216538789428815,
+      "grad_norm": 0.11509175598621368,
+      "learning_rate": 7.475963698568468e-05,
+      "loss": 0.012790821492671967,
+      "step": 1300
+    },
+    {
+      "epoch": 0.22250639386189258,
+      "grad_norm": 0.08615118265151978,
+      "learning_rate": 7.475673195705116e-05,
+      "loss": 0.011050455272197723,
+      "step": 1305
+    },
+    {
+      "epoch": 0.22335890878090367,
+      "grad_norm": 0.1186874732375145,
+      "learning_rate": 7.475380953573583e-05,
+      "loss": 0.011253353953361512,
+      "step": 1310
+    },
+    {
+      "epoch": 0.22421142369991476,
+      "grad_norm": 0.08680208027362823,
+      "learning_rate": 7.475086972310297e-05,
+      "loss": 0.010736887156963349,
+      "step": 1315
+    },
+    {
+      "epoch": 0.22506393861892582,
+      "grad_norm": 0.08204677700996399,
+      "learning_rate": 7.474791252052498e-05,
+      "loss": 0.011695361882448196,
+      "step": 1320
+    },
+    {
+      "epoch": 0.2259164535379369,
+      "grad_norm": 0.08945680409669876,
+      "learning_rate": 7.47449379293824e-05,
+      "loss": 0.01684057414531708,
+      "step": 1325
+    },
+    {
+      "epoch": 0.226768968456948,
+      "grad_norm": 0.12350911647081375,
+      "learning_rate": 7.474194595106384e-05,
+      "loss": 0.012560060620307923,
+      "step": 1330
+    },
+    {
+      "epoch": 0.22762148337595908,
+      "grad_norm": 0.09201455116271973,
+      "learning_rate": 7.473893658696605e-05,
+      "loss": 0.01128845140337944,
+      "step": 1335
+    },
+    {
+      "epoch": 0.22847399829497017,
+      "grad_norm": 0.12938448786735535,
+      "learning_rate": 7.473590983849396e-05,
+      "loss": 0.011510471999645232,
+      "step": 1340
+    },
+    {
+      "epoch": 0.22932651321398123,
+      "grad_norm": 0.0837291032075882,
+      "learning_rate": 7.473286570706047e-05,
+      "loss": 0.011677465587854385,
+      "step": 1345
+    },
+    {
+      "epoch": 0.23017902813299232,
+      "grad_norm": 0.12514546513557434,
+      "learning_rate": 7.472980419408675e-05,
+      "loss": 0.01308433711528778,
+      "step": 1350
+    },
+    {
+      "epoch": 0.2310315430520034,
+      "grad_norm": 0.05483829975128174,
+      "learning_rate": 7.472672530100199e-05,
+      "loss": 0.007203156501054764,
+      "step": 1355
+    },
+    {
+      "epoch": 0.2318840579710145,
+      "grad_norm": 0.13903425633907318,
+      "learning_rate": 7.472362902924352e-05,
+      "loss": 0.013231572508811951,
+      "step": 1360
+    },
+    {
+      "epoch": 0.23273657289002558,
+      "grad_norm": 0.09622041881084442,
+      "learning_rate": 7.472051538025678e-05,
+      "loss": 0.013325902819633483,
+      "step": 1365
+    },
+    {
+      "epoch": 0.23358908780903667,
+      "grad_norm": 0.0792275071144104,
+      "learning_rate": 7.471738435549533e-05,
+      "loss": 0.011098403483629227,
+      "step": 1370
+    },
+    {
+      "epoch": 0.23444160272804773,
+      "grad_norm": 0.11833506077528,
+      "learning_rate": 7.471423595642084e-05,
+      "loss": 0.014845246076583862,
+      "step": 1375
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 0.07531571388244629,
+      "learning_rate": 7.471107018450309e-05,
+      "loss": 0.011498528718948364,
+      "step": 1380
+    },
+    {
+      "epoch": 0.2361466325660699,
+      "grad_norm": 0.08739249408245087,
+      "learning_rate": 7.470788704121995e-05,
+      "loss": 0.013241058588027954,
+      "step": 1385
+    },
+    {
+      "epoch": 0.236999147485081,
+      "grad_norm": 0.07113732397556305,
+      "learning_rate": 7.470468652805743e-05,
+      "loss": 0.009632241725921632,
+      "step": 1390
+    },
+    {
+      "epoch": 0.23785166240409208,
+      "grad_norm": 0.07838430255651474,
+      "learning_rate": 7.470146864650965e-05,
+      "loss": 0.009344339370727539,
+      "step": 1395
+    },
+    {
+      "epoch": 0.23870417732310314,
+      "grad_norm": 0.1086372509598732,
+      "learning_rate": 7.46982333980788e-05,
+      "loss": 0.014708395302295684,
+      "step": 1400
+    },
+    {
+      "epoch": 0.23955669224211423,
+      "grad_norm": 0.06628046184778214,
+      "learning_rate": 7.469498078427519e-05,
+      "loss": 0.011472882330417633,
+      "step": 1405
+    },
+    {
+      "epoch": 0.24040920716112532,
+      "grad_norm": 0.13003386557102203,
+      "learning_rate": 7.46917108066173e-05,
+      "loss": 0.011933800578117371,
+      "step": 1410
+    },
+    {
+      "epoch": 0.2412617220801364,
+      "grad_norm": 0.07365831732749939,
+      "learning_rate": 7.468842346663162e-05,
+      "loss": 0.0102902352809906,
+      "step": 1415
+    },
+    {
+      "epoch": 0.2421142369991475,
+      "grad_norm": 0.11540158838033676,
+      "learning_rate": 7.468511876585279e-05,
+      "loss": 0.012016136944293977,
+      "step": 1420
+    },
+    {
+      "epoch": 0.24296675191815856,
+      "grad_norm": 0.11687944084405899,
+      "learning_rate": 7.468179670582359e-05,
+      "loss": 0.01773642897605896,
+      "step": 1425
+    },
+    {
+      "epoch": 0.24381926683716965,
+      "grad_norm": 0.10464506596326828,
+      "learning_rate": 7.467845728809483e-05,
+      "loss": 0.009476778656244278,
+      "step": 1430
+    },
+    {
+      "epoch": 0.24467178175618073,
+      "grad_norm": 0.11479093879461288,
+      "learning_rate": 7.46751005142255e-05,
+      "loss": 0.014100676774978638,
+      "step": 1435
+    },
+    {
+      "epoch": 0.24552429667519182,
+      "grad_norm": 0.1388610154390335,
+      "learning_rate": 7.46717263857826e-05,
+      "loss": 0.012735754251480103,
+      "step": 1440
+    },
+    {
+      "epoch": 0.2463768115942029,
+      "grad_norm": 0.08022485673427582,
+      "learning_rate": 7.466833490434132e-05,
+      "loss": 0.014391189813613892,
+      "step": 1445
+    },
+    {
+      "epoch": 0.24722932651321397,
+      "grad_norm": 0.12174725532531738,
+      "learning_rate": 7.466492607148492e-05,
+      "loss": 0.013387931883335114,
+      "step": 1450
+    },
+    {
+      "epoch": 0.24808184143222506,
+      "grad_norm": 0.1102161779999733,
+      "learning_rate": 7.466149988880474e-05,
+      "loss": 0.01143224760890007,
+      "step": 1455
+    },
+    {
+      "epoch": 0.24893435635123615,
+      "grad_norm": 0.14878468215465546,
+      "learning_rate": 7.465805635790024e-05,
+      "loss": 0.010428830236196517,
+      "step": 1460
+    },
+    {
+      "epoch": 0.24978687127024723,
+      "grad_norm": 0.3046579658985138,
+      "learning_rate": 7.4654595480379e-05,
+      "loss": 0.012648795545101166,
+      "step": 1465
+    },
+    {
+      "epoch": 0.24995737425404946,
+      "eval_loss": 0.036103956401348114,
+      "eval_runtime": 3.6524,
+      "eval_samples_per_second": 68.995,
+      "eval_steps_per_second": 1.095,
+      "step": 1466
+    },
+    {
+      "eval_cer_subset": 0.01393977885257381,
+      "eval_cer_subset_edit_distance": 856,
+      "eval_cer_subset_groups": 250,
+      "eval_cer_subset_items": 250,
+      "eval_cer_subset_ref_chars": 61407,
+      "step": 1466
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 23460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 2932,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.941642367710904e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-1466/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6adec376d54028ef57ef3dc856a5cba12bab9c0d580369637fa983b6072064f7
+size 5841

meta-llama__meta-llama-3.1-8b/sft/run_manifest.json

@@ -0,0 +1,25 @@
+{
+  "schema_version": 1,
+  "run_id": "aacb0b6c-2b10-48da-90bc-ca77fd7cac31",
+  "run_type": "sft",
+  "profile_name": "llama3_1_8b_base",
+  "model_name": "meta-llama/Meta-Llama-3.1-8B",
+  "status": "running",
+  "best_metric_name": "eval_loss",
+  "best_metric_value": 0.036103956401348114,
+  "best_step": 1466,
+  "best_checkpoint_step": 1466,
+  "latest_checkpoint_step": 1466,
+  "checkpoints": [
+    {
+      "step": 1466,
+      "epoch": 0.24995737425404946,
+      "repo_path": "meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-1466",
+      "timestamp": "2026-04-09T06:43:22.133396+00:00"
+    }
+  ],
+  "epoch_artifacts": [],
+  "resume_history": [],
+  "created_at": "2026-04-09T06:12:43.688637+00:00",
+  "updated_at": "2026-04-09T06:43:22.133410+00:00"
+}