Upload full trainer checkpoint step=1466 (profile=llama3_2_1b_base, run_type=sft)

.gitattributes

@@ -64,3 +64,4 @@ meta-llama__llama-3.2-1b/epoch_0003/tokenizer.json filter=lfs diff=lfs merge=lfs
 meta-llama__llama-3.2-1b/epoch_0004/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 meta-llama__llama-3.2-1b/epoch_0005/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 meta-llama__llama-3.2-1b/epoch_0006/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+meta-llama__llama-3.2-1b/sft/checkpoints/checkpoint-1466/tokenizer.json filter=lfs diff=lfs merge=lfs -text

meta-llama__llama-3.2-1b/sft/checkpoints/checkpoint-1466/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Llama-3.2-1B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Llama-3.2-1B
+- 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__llama-3.2-1b/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/Llama-3.2-1B",
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

meta-llama__llama-3.2-1b/sft/checkpoints/checkpoint-1466/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8905a6c2198f3eeb51bacd845709c1a9bd7773d97ab4ef76c686db7bbe522801
+size 45118424

meta-llama__llama-3.2-1b/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__llama-3.2-1b/sft/checkpoints/checkpoint-1466/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e48227cdedb276b8390f527946f0087285f2308d084b490a19592e6bf7541ff4
+size 23162187

meta-llama__llama-3.2-1b/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__llama-3.2-1b/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__llama-3.2-1b/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__llama-3.2-1b/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__llama-3.2-1b/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": 0.8702483177185059,
+      "learning_rate": 6.382978723404255e-07,
+      "loss": 0.7270183563232422,
+      "step": 5
+    },
+    {
+      "epoch": 0.0017050298380221654,
+      "grad_norm": 0.8312188982963562,
+      "learning_rate": 1.4361702127659573e-06,
+      "loss": 0.7593235015869141,
+      "step": 10
+    },
+    {
+      "epoch": 0.0025575447570332483,
+      "grad_norm": 0.9371886253356934,
+      "learning_rate": 2.2340425531914894e-06,
+      "loss": 0.7415130615234375,
+      "step": 15
+    },
+    {
+      "epoch": 0.0034100596760443308,
+      "grad_norm": 0.8715710043907166,
+      "learning_rate": 3.0319148936170214e-06,
+      "loss": 0.7387494087219239,
+      "step": 20
+    },
+    {
+      "epoch": 0.004262574595055414,
+      "grad_norm": 0.869061291217804,
+      "learning_rate": 3.829787234042553e-06,
+      "loss": 0.732928466796875,
+      "step": 25
+    },
+    {
+      "epoch": 0.005115089514066497,
+      "grad_norm": 0.9074509143829346,
+      "learning_rate": 4.627659574468085e-06,
+      "loss": 0.7359912872314454,
+      "step": 30
+    },
+    {
+      "epoch": 0.005967604433077579,
+      "grad_norm": 1.0012825727462769,
+      "learning_rate": 5.425531914893616e-06,
+      "loss": 0.6921219825744629,
+      "step": 35
+    },
+    {
+      "epoch": 0.0068201193520886615,
+      "grad_norm": 0.9422137141227722,
+      "learning_rate": 6.223404255319148e-06,
+      "loss": 0.6865067958831788,
+      "step": 40
+    },
+    {
+      "epoch": 0.0076726342710997444,
+      "grad_norm": 0.9773287773132324,
+      "learning_rate": 7.02127659574468e-06,
+      "loss": 0.6299760341644287,
+      "step": 45
+    },
+    {
+      "epoch": 0.008525149190110827,
+      "grad_norm": 1.1514697074890137,
+      "learning_rate": 7.819148936170211e-06,
+      "loss": 0.6246551513671875,
+      "step": 50
+    },
+    {
+      "epoch": 0.00937766410912191,
+      "grad_norm": 1.1929924488067627,
+      "learning_rate": 8.617021276595744e-06,
+      "loss": 0.5671340942382812,
+      "step": 55
+    },
+    {
+      "epoch": 0.010230179028132993,
+      "grad_norm": 1.2087507247924805,
+      "learning_rate": 9.414893617021275e-06,
+      "loss": 0.466497802734375,
+      "step": 60
+    },
+    {
+      "epoch": 0.011082693947144074,
+      "grad_norm": 1.3783831596374512,
+      "learning_rate": 1.0212765957446808e-05,
+      "loss": 0.3536498546600342,
+      "step": 65
+    },
+    {
+      "epoch": 0.011935208866155157,
+      "grad_norm": 0.7981624007225037,
+      "learning_rate": 1.101063829787234e-05,
+      "loss": 0.22803339958190919,
+      "step": 70
+    },
+    {
+      "epoch": 0.01278772378516624,
+      "grad_norm": 0.3521866798400879,
+      "learning_rate": 1.1808510638297872e-05,
+      "loss": 0.1623826026916504,
+      "step": 75
+    },
+    {
+      "epoch": 0.013640238704177323,
+      "grad_norm": 0.27423161268234253,
+      "learning_rate": 1.2606382978723403e-05,
+      "loss": 0.1479944944381714,
+      "step": 80
+    },
+    {
+      "epoch": 0.014492753623188406,
+      "grad_norm": 0.2307504117488861,
+      "learning_rate": 1.3404255319148936e-05,
+      "loss": 0.13179465532302856,
+      "step": 85
+    },
+    {
+      "epoch": 0.015345268542199489,
+      "grad_norm": 0.2505638301372528,
+      "learning_rate": 1.4202127659574466e-05,
+      "loss": 0.12060884237289429,
+      "step": 90
+    },
+    {
+      "epoch": 0.01619778346121057,
+      "grad_norm": 0.23193876445293427,
+      "learning_rate": 1.4999999999999999e-05,
+      "loss": 0.10533099174499512,
+      "step": 95
+    },
+    {
+      "epoch": 0.017050298380221655,
+      "grad_norm": 0.2267618179321289,
+      "learning_rate": 1.579787234042553e-05,
+      "loss": 0.11999905109405518,
+      "step": 100
+    },
+    {
+      "epoch": 0.017902813299232736,
+      "grad_norm": 0.22980229556560516,
+      "learning_rate": 1.659574468085106e-05,
+      "loss": 0.10567227602005005,
+      "step": 105
+    },
+    {
+      "epoch": 0.01875532821824382,
+      "grad_norm": 0.2573573589324951,
+      "learning_rate": 1.7393617021276596e-05,
+      "loss": 0.09509810209274291,
+      "step": 110
+    },
+    {
+      "epoch": 0.0196078431372549,
+      "grad_norm": 0.22669287025928497,
+      "learning_rate": 1.8191489361702127e-05,
+      "loss": 0.09332407712936401,
+      "step": 115
+    },
+    {
+      "epoch": 0.020460358056265986,
+      "grad_norm": 0.2708875834941864,
+      "learning_rate": 1.8989361702127655e-05,
+      "loss": 0.09526345729827881,
+      "step": 120
+    },
+    {
+      "epoch": 0.021312872975277068,
+      "grad_norm": 0.2242223024368286,
+      "learning_rate": 1.978723404255319e-05,
+      "loss": 0.09162800312042237,
+      "step": 125
+    },
+    {
+      "epoch": 0.02216538789428815,
+      "grad_norm": 0.28643250465393066,
+      "learning_rate": 2.0585106382978724e-05,
+      "loss": 0.08713340759277344,
+      "step": 130
+    },
+    {
+      "epoch": 0.023017902813299233,
+      "grad_norm": 0.2659653425216675,
+      "learning_rate": 2.1382978723404255e-05,
+      "loss": 0.08405932188034057,
+      "step": 135
+    },
+    {
+      "epoch": 0.023870417732310314,
+      "grad_norm": 0.23080135881900787,
+      "learning_rate": 2.2180851063829783e-05,
+      "loss": 0.07873657941818238,
+      "step": 140
+    },
+    {
+      "epoch": 0.0247229326513214,
+      "grad_norm": 0.21435977518558502,
+      "learning_rate": 2.2978723404255317e-05,
+      "loss": 0.06758193373680114,
+      "step": 145
+    },
+    {
+      "epoch": 0.02557544757033248,
+      "grad_norm": 0.20372840762138367,
+      "learning_rate": 2.377659574468085e-05,
+      "loss": 0.06967071890830993,
+      "step": 150
+    },
+    {
+      "epoch": 0.026427962489343565,
+      "grad_norm": 0.20348776876926422,
+      "learning_rate": 2.457446808510638e-05,
+      "loss": 0.0636233150959015,
+      "step": 155
+    },
+    {
+      "epoch": 0.027280477408354646,
+      "grad_norm": 0.21693550050258636,
+      "learning_rate": 2.537234042553191e-05,
+      "loss": 0.0691483736038208,
+      "step": 160
+    },
+    {
+      "epoch": 0.028132992327365727,
+      "grad_norm": 0.2008240669965744,
+      "learning_rate": 2.6170212765957446e-05,
+      "loss": 0.05855585932731629,
+      "step": 165
+    },
+    {
+      "epoch": 0.028985507246376812,
+      "grad_norm": 0.22839540243148804,
+      "learning_rate": 2.6968085106382977e-05,
+      "loss": 0.06012563109397888,
+      "step": 170
+    },
+    {
+      "epoch": 0.029838022165387893,
+      "grad_norm": 0.20269300043582916,
+      "learning_rate": 2.7765957446808508e-05,
+      "loss": 0.054646140336990355,
+      "step": 175
+    },
+    {
+      "epoch": 0.030690537084398978,
+      "grad_norm": 0.25422361493110657,
+      "learning_rate": 2.856382978723404e-05,
+      "loss": 0.06128175258636474,
+      "step": 180
+    },
+    {
+      "epoch": 0.03154305200341006,
+      "grad_norm": 0.1701997071504593,
+      "learning_rate": 2.9361702127659574e-05,
+      "loss": 0.05077495574951172,
+      "step": 185
+    },
+    {
+      "epoch": 0.03239556692242114,
+      "grad_norm": 0.2417565882205963,
+      "learning_rate": 3.0159574468085105e-05,
+      "loss": 0.04601706862449646,
+      "step": 190
+    },
+    {
+      "epoch": 0.03324808184143223,
+      "grad_norm": 0.2608591318130493,
+      "learning_rate": 3.0957446808510636e-05,
+      "loss": 0.05892879366874695,
+      "step": 195
+    },
+    {
+      "epoch": 0.03410059676044331,
+      "grad_norm": 0.2680520713329315,
+      "learning_rate": 3.175531914893617e-05,
+      "loss": 0.047013303637504576,
+      "step": 200
+    },
+    {
+      "epoch": 0.03495311167945439,
+      "grad_norm": 0.22654250264167786,
+      "learning_rate": 3.25531914893617e-05,
+      "loss": 0.05578266978263855,
+      "step": 205
+    },
+    {
+      "epoch": 0.03580562659846547,
+      "grad_norm": 0.23171734809875488,
+      "learning_rate": 3.3351063829787226e-05,
+      "loss": 0.04092026948928833,
+      "step": 210
+    },
+    {
+      "epoch": 0.03665814151747655,
+      "grad_norm": 0.3024536669254303,
+      "learning_rate": 3.414893617021276e-05,
+      "loss": 0.048113960027694705,
+      "step": 215
+    },
+    {
+      "epoch": 0.03751065643648764,
+      "grad_norm": 0.21944984793663025,
+      "learning_rate": 3.4946808510638296e-05,
+      "loss": 0.06023481488227844,
+      "step": 220
+    },
+    {
+      "epoch": 0.03836317135549872,
+      "grad_norm": 0.21161283552646637,
+      "learning_rate": 3.574468085106383e-05,
+      "loss": 0.04402200579643249,
+      "step": 225
+    },
+    {
+      "epoch": 0.0392156862745098,
+      "grad_norm": 0.22785748541355133,
+      "learning_rate": 3.654255319148936e-05,
+      "loss": 0.04179250001907349,
+      "step": 230
+    },
+    {
+      "epoch": 0.040068201193520885,
+      "grad_norm": 0.25685593485832214,
+      "learning_rate": 3.734042553191489e-05,
+      "loss": 0.04237877726554871,
+      "step": 235
+    },
+    {
+      "epoch": 0.04092071611253197,
+      "grad_norm": 0.2640145421028137,
+      "learning_rate": 3.813829787234042e-05,
+      "loss": 0.050156861543655396,
+      "step": 240
+    },
+    {
+      "epoch": 0.041773231031543054,
+      "grad_norm": 0.2713942229747772,
+      "learning_rate": 3.8936170212765955e-05,
+      "loss": 0.0409070074558258,
+      "step": 245
+    },
+    {
+      "epoch": 0.042625745950554135,
+      "grad_norm": 0.23422108590602875,
+      "learning_rate": 3.973404255319149e-05,
+      "loss": 0.0364731103181839,
+      "step": 250
+    },
+    {
+      "epoch": 0.043478260869565216,
+      "grad_norm": 0.19113923609256744,
+      "learning_rate": 4.053191489361702e-05,
+      "loss": 0.037750616669654846,
+      "step": 255
+    },
+    {
+      "epoch": 0.0443307757885763,
+      "grad_norm": 0.24328471720218658,
+      "learning_rate": 4.1329787234042545e-05,
+      "loss": 0.0389731228351593,
+      "step": 260
+    },
+    {
+      "epoch": 0.045183290707587385,
+      "grad_norm": 0.15357369184494019,
+      "learning_rate": 4.2127659574468086e-05,
+      "loss": 0.0336186945438385,
+      "step": 265
+    },
+    {
+      "epoch": 0.04603580562659847,
+      "grad_norm": 0.24376599490642548,
+      "learning_rate": 4.2925531914893614e-05,
+      "loss": 0.03668908774852753,
+      "step": 270
+    },
+    {
+      "epoch": 0.04688832054560955,
+      "grad_norm": 0.29594436287879944,
+      "learning_rate": 4.372340425531914e-05,
+      "loss": 0.04451665282249451,
+      "step": 275
+    },
+    {
+      "epoch": 0.04774083546462063,
+      "grad_norm": 0.19453556835651398,
+      "learning_rate": 4.452127659574468e-05,
+      "loss": 0.03592076897621155,
+      "step": 280
+    },
+    {
+      "epoch": 0.04859335038363171,
+      "grad_norm": 0.2916566729545593,
+      "learning_rate": 4.5319148936170204e-05,
+      "loss": 0.039958652853965757,
+      "step": 285
+    },
+    {
+      "epoch": 0.0494458653026428,
+      "grad_norm": 0.21568676829338074,
+      "learning_rate": 4.6117021276595746e-05,
+      "loss": 0.03157965838909149,
+      "step": 290
+    },
+    {
+      "epoch": 0.05029838022165388,
+      "grad_norm": 0.26071974635124207,
+      "learning_rate": 4.6914893617021274e-05,
+      "loss": 0.04068298935890198,
+      "step": 295
+    },
+    {
+      "epoch": 0.05115089514066496,
+      "grad_norm": 0.3324560225009918,
+      "learning_rate": 4.77127659574468e-05,
+      "loss": 0.03286807537078858,
+      "step": 300
+    },
+    {
+      "epoch": 0.05200341005967604,
+      "grad_norm": 0.28684696555137634,
+      "learning_rate": 4.851063829787234e-05,
+      "loss": 0.040812617540359496,
+      "step": 305
+    },
+    {
+      "epoch": 0.05285592497868713,
+      "grad_norm": 0.23505407571792603,
+      "learning_rate": 4.930851063829787e-05,
+      "loss": 0.031041297316551208,
+      "step": 310
+    },
+    {
+      "epoch": 0.05370843989769821,
+      "grad_norm": 0.16107261180877686,
+      "learning_rate": 5.01063829787234e-05,
+      "loss": 0.02798473834991455,
+      "step": 315
+    },
+    {
+      "epoch": 0.05456095481670929,
+      "grad_norm": 0.26245057582855225,
+      "learning_rate": 5.090425531914893e-05,
+      "loss": 0.029034197330474854,
+      "step": 320
+    },
+    {
+      "epoch": 0.05541346973572037,
+      "grad_norm": 0.28591933846473694,
+      "learning_rate": 5.170212765957446e-05,
+      "loss": 0.03308171033859253,
+      "step": 325
+    },
+    {
+      "epoch": 0.056265984654731455,
+      "grad_norm": 0.24634616076946259,
+      "learning_rate": 5.2499999999999995e-05,
+      "loss": 0.02535790503025055,
+      "step": 330
+    },
+    {
+      "epoch": 0.05711849957374254,
+      "grad_norm": 0.28306257724761963,
+      "learning_rate": 5.329787234042553e-05,
+      "loss": 0.031932130455970764,
+      "step": 335
+    },
+    {
+      "epoch": 0.057971014492753624,
+      "grad_norm": 0.22408922016620636,
+      "learning_rate": 5.409574468085106e-05,
+      "loss": 0.0343563050031662,
+      "step": 340
+    },
+    {
+      "epoch": 0.058823529411764705,
+      "grad_norm": 0.3133672773838043,
+      "learning_rate": 5.4893617021276586e-05,
+      "loss": 0.03774818181991577,
+      "step": 345
+    },
+    {
+      "epoch": 0.059676044330775786,
+      "grad_norm": 0.33814433217048645,
+      "learning_rate": 5.569148936170213e-05,
+      "loss": 0.03156721591949463,
+      "step": 350
+    },
+    {
+      "epoch": 0.060528559249786874,
+      "grad_norm": 0.17259150743484497,
+      "learning_rate": 5.6489361702127655e-05,
+      "loss": 0.028145447373390198,
+      "step": 355
+    },
+    {
+      "epoch": 0.061381074168797956,
+      "grad_norm": 0.25732940435409546,
+      "learning_rate": 5.728723404255319e-05,
+      "loss": 0.037197616696357724,
+      "step": 360
+    },
+    {
+      "epoch": 0.06223358908780904,
+      "grad_norm": 0.22246433794498444,
+      "learning_rate": 5.808510638297872e-05,
+      "loss": 0.02986128032207489,
+      "step": 365
+    },
+    {
+      "epoch": 0.06308610400682012,
+      "grad_norm": 0.3112792372703552,
+      "learning_rate": 5.8882978723404245e-05,
+      "loss": 0.03034401834011078,
+      "step": 370
+    },
+    {
+      "epoch": 0.0639386189258312,
+      "grad_norm": 0.2766200006008148,
+      "learning_rate": 5.9680851063829786e-05,
+      "loss": 0.03152766227722168,
+      "step": 375
+    },
+    {
+      "epoch": 0.06479113384484228,
+      "grad_norm": 0.2531411945819855,
+      "learning_rate": 6.0478723404255314e-05,
+      "loss": 0.031791338324546815,
+      "step": 380
+    },
+    {
+      "epoch": 0.06564364876385337,
+      "grad_norm": 0.29931405186653137,
+      "learning_rate": 6.127659574468084e-05,
+      "loss": 0.028663474321365356,
+      "step": 385
+    },
+    {
+      "epoch": 0.06649616368286446,
+      "grad_norm": 0.2471776157617569,
+      "learning_rate": 6.207446808510638e-05,
+      "loss": 0.03083355724811554,
+      "step": 390
+    },
+    {
+      "epoch": 0.06734867860187553,
+      "grad_norm": 0.23945043981075287,
+      "learning_rate": 6.287234042553191e-05,
+      "loss": 0.030578643083572388,
+      "step": 395
+    },
+    {
+      "epoch": 0.06820119352088662,
+      "grad_norm": 0.30501049757003784,
+      "learning_rate": 6.367021276595743e-05,
+      "loss": 0.029327672719955445,
+      "step": 400
+    },
+    {
+      "epoch": 0.06905370843989769,
+      "grad_norm": 0.2621583044528961,
+      "learning_rate": 6.446808510638298e-05,
+      "loss": 0.030047428607940675,
+      "step": 405
+    },
+    {
+      "epoch": 0.06990622335890878,
+      "grad_norm": 0.29637840390205383,
+      "learning_rate": 6.52659574468085e-05,
+      "loss": 0.032990914583206174,
+      "step": 410
+    },
+    {
+      "epoch": 0.07075873827791987,
+      "grad_norm": 0.2790025472640991,
+      "learning_rate": 6.606382978723404e-05,
+      "loss": 0.02616017162799835,
+      "step": 415
+    },
+    {
+      "epoch": 0.07161125319693094,
+      "grad_norm": 0.2781897783279419,
+      "learning_rate": 6.686170212765957e-05,
+      "loss": 0.025333160161972047,
+      "step": 420
+    },
+    {
+      "epoch": 0.07246376811594203,
+      "grad_norm": 0.26609721779823303,
+      "learning_rate": 6.765957446808509e-05,
+      "loss": 0.024090659618377686,
+      "step": 425
+    },
+    {
+      "epoch": 0.0733162830349531,
+      "grad_norm": 0.22948430478572845,
+      "learning_rate": 6.845744680851064e-05,
+      "loss": 0.030253008008003235,
+      "step": 430
+    },
+    {
+      "epoch": 0.0741687979539642,
+      "grad_norm": 0.21689315140247345,
+      "learning_rate": 6.925531914893616e-05,
+      "loss": 0.02709486484527588,
+      "step": 435
+    },
+    {
+      "epoch": 0.07502131287297528,
+      "grad_norm": 0.27341127395629883,
+      "learning_rate": 7.00531914893617e-05,
+      "loss": 0.02555806338787079,
+      "step": 440
+    },
+    {
+      "epoch": 0.07587382779198636,
+      "grad_norm": 0.3059982359409332,
+      "learning_rate": 7.085106382978723e-05,
+      "loss": 0.02590309679508209,
+      "step": 445
+    },
+    {
+      "epoch": 0.07672634271099744,
+      "grad_norm": 0.29078978300094604,
+      "learning_rate": 7.164893617021276e-05,
+      "loss": 0.03434495031833649,
+      "step": 450
+    },
+    {
+      "epoch": 0.07757885763000852,
+      "grad_norm": 0.1730230152606964,
+      "learning_rate": 7.244680851063829e-05,
+      "loss": 0.027434590458869933,
+      "step": 455
+    },
+    {
+      "epoch": 0.0784313725490196,
+      "grad_norm": 0.23046822845935822,
+      "learning_rate": 7.324468085106382e-05,
+      "loss": 0.024511393904685975,
+      "step": 460
+    },
+    {
+      "epoch": 0.0792838874680307,
+      "grad_norm": 0.21193982660770416,
+      "learning_rate": 7.404255319148935e-05,
+      "loss": 0.028409674763679504,
+      "step": 465
+    },
+    {
+      "epoch": 0.08013640238704177,
+      "grad_norm": 0.14851854741573334,
+      "learning_rate": 7.484042553191489e-05,
+      "loss": 0.022292758524417877,
+      "step": 470
+    },
+    {
+      "epoch": 0.08098891730605286,
+      "grad_norm": 0.2605791985988617,
+      "learning_rate": 7.499999439800074e-05,
+      "loss": 0.021705128252506256,
+      "step": 475
+    },
+    {
+      "epoch": 0.08184143222506395,
+      "grad_norm": 0.3485381603240967,
+      "learning_rate": 7.499997163988164e-05,
+      "loss": 0.027302873134613038,
+      "step": 480
+    },
+    {
+      "epoch": 0.08269394714407502,
+      "grad_norm": 0.2511079013347626,
+      "learning_rate": 7.499993137552834e-05,
+      "loss": 0.022480341792106628,
+      "step": 485
+    },
+    {
+      "epoch": 0.08354646206308611,
+      "grad_norm": 0.23074299097061157,
+      "learning_rate": 7.499987360495964e-05,
+      "loss": 0.032788214087486264,
+      "step": 490
+    },
+    {
+      "epoch": 0.08439897698209718,
+      "grad_norm": 0.2591882348060608,
+      "learning_rate": 7.499979832820255e-05,
+      "loss": 0.030076757073402405,
+      "step": 495
+    },
+    {
+      "epoch": 0.08525149190110827,
+      "grad_norm": 0.17042620480060577,
+      "learning_rate": 7.499970554529216e-05,
+      "loss": 0.023710650205612183,
+      "step": 500
+    },
+    {
+      "epoch": 0.08610400682011936,
+      "grad_norm": 0.2072867602109909,
+      "learning_rate": 7.49995952562718e-05,
+      "loss": 0.02641989290714264,
+      "step": 505
+    },
+    {
+      "epoch": 0.08695652173913043,
+      "grad_norm": 0.22865015268325806,
+      "learning_rate": 7.499946746119296e-05,
+      "loss": 0.026545605063438414,
+      "step": 510
+    },
+    {
+      "epoch": 0.08780903665814152,
+      "grad_norm": 0.18163245916366577,
+      "learning_rate": 7.499932216011531e-05,
+      "loss": 0.022438524663448332,
+      "step": 515
+    },
+    {
+      "epoch": 0.0886615515771526,
+      "grad_norm": 0.21268488466739655,
+      "learning_rate": 7.499915935310667e-05,
+      "loss": 0.02982390522956848,
+      "step": 520
+    },
+    {
+      "epoch": 0.08951406649616368,
+      "grad_norm": 0.28650423884391785,
+      "learning_rate": 7.499897904024303e-05,
+      "loss": 0.02888711094856262,
+      "step": 525
+    },
+    {
+      "epoch": 0.09036658141517477,
+      "grad_norm": 0.17938083410263062,
+      "learning_rate": 7.499878122160858e-05,
+      "loss": 0.025293585658073426,
+      "step": 530
+    },
+    {
+      "epoch": 0.09121909633418585,
+      "grad_norm": 0.21884122490882874,
+      "learning_rate": 7.499856589729569e-05,
+      "loss": 0.029227742552757265,
+      "step": 535
+    },
+    {
+      "epoch": 0.09207161125319693,
+      "grad_norm": 0.24997380375862122,
+      "learning_rate": 7.499833306740485e-05,
+      "loss": 0.026770782470703126,
+      "step": 540
+    },
+    {
+      "epoch": 0.09292412617220801,
+      "grad_norm": 0.1759740710258484,
+      "learning_rate": 7.499808273204476e-05,
+      "loss": 0.020788520574569702,
+      "step": 545
+    },
+    {
+      "epoch": 0.0937766410912191,
+      "grad_norm": 0.21122577786445618,
+      "learning_rate": 7.499781489133228e-05,
+      "loss": 0.02833372950553894,
+      "step": 550
+    },
+    {
+      "epoch": 0.09462915601023018,
+      "grad_norm": 0.17823946475982666,
+      "learning_rate": 7.499752954539245e-05,
+      "loss": 0.02394527941942215,
+      "step": 555
+    },
+    {
+      "epoch": 0.09548167092924126,
+      "grad_norm": 0.22122310101985931,
+      "learning_rate": 7.49972266943585e-05,
+      "loss": 0.022127175331115724,
+      "step": 560
+    },
+    {
+      "epoch": 0.09633418584825235,
+      "grad_norm": 0.25811049342155457,
+      "learning_rate": 7.499690633837178e-05,
+      "loss": 0.024325409531593324,
+      "step": 565
+    },
+    {
+      "epoch": 0.09718670076726342,
+      "grad_norm": 0.22042953968048096,
+      "learning_rate": 7.499656847758187e-05,
+      "loss": 0.02605798840522766,
+      "step": 570
+    },
+    {
+      "epoch": 0.09803921568627451,
+      "grad_norm": 0.2860932946205139,
+      "learning_rate": 7.499621311214646e-05,
+      "loss": 0.026523932814598083,
+      "step": 575
+    },
+    {
+      "epoch": 0.0988917306052856,
+      "grad_norm": 0.1485099345445633,
+      "learning_rate": 7.499584024223149e-05,
+      "loss": 0.02095140814781189,
+      "step": 580
+    },
+    {
+      "epoch": 0.09974424552429667,
+      "grad_norm": 0.19851070642471313,
+      "learning_rate": 7.499544986801099e-05,
+      "loss": 0.02706519663333893,
+      "step": 585
+    },
+    {
+      "epoch": 0.10059676044330776,
+      "grad_norm": 0.25508561730384827,
+      "learning_rate": 7.499504198966722e-05,
+      "loss": 0.024473744630813598,
+      "step": 590
+    },
+    {
+      "epoch": 0.10144927536231885,
+      "grad_norm": 0.17818157374858856,
+      "learning_rate": 7.499461660739059e-05,
+      "loss": 0.026624396443367004,
+      "step": 595
+    },
+    {
+      "epoch": 0.10230179028132992,
+      "grad_norm": 0.16915369033813477,
+      "learning_rate": 7.499417372137968e-05,
+      "loss": 0.02158043682575226,
+      "step": 600
+    },
+    {
+      "epoch": 0.10315430520034101,
+      "grad_norm": 0.19104211032390594,
+      "learning_rate": 7.499371333184125e-05,
+      "loss": 0.02661653459072113,
+      "step": 605
+    },
+    {
+      "epoch": 0.10400682011935208,
+      "grad_norm": 0.19765061140060425,
+      "learning_rate": 7.49932354389902e-05,
+      "loss": 0.02049233466386795,
+      "step": 610
+    },
+    {
+      "epoch": 0.10485933503836317,
+      "grad_norm": 0.20652534067630768,
+      "learning_rate": 7.499274004304964e-05,
+      "loss": 0.026903703808784485,
+      "step": 615
+    },
+    {
+      "epoch": 0.10571184995737426,
+      "grad_norm": 0.19068656861782074,
+      "learning_rate": 7.499222714425087e-05,
+      "loss": 0.02817963659763336,
+      "step": 620
+    },
+    {
+      "epoch": 0.10656436487638533,
+      "grad_norm": 0.2244884967803955,
+      "learning_rate": 7.499169674283328e-05,
+      "loss": 0.022825565934181214,
+      "step": 625
+    },
+    {
+      "epoch": 0.10741687979539642,
+      "grad_norm": 0.15769504010677338,
+      "learning_rate": 7.499114883904451e-05,
+      "loss": 0.023618267476558687,
+      "step": 630
+    },
+    {
+      "epoch": 0.1082693947144075,
+      "grad_norm": 0.2758719325065613,
+      "learning_rate": 7.499058343314031e-05,
+      "loss": 0.027484145760536195,
+      "step": 635
+    },
+    {
+      "epoch": 0.10912190963341858,
+      "grad_norm": 0.14344681799411774,
+      "learning_rate": 7.499000052538467e-05,
+      "loss": 0.02188411056995392,
+      "step": 640
+    },
+    {
+      "epoch": 0.10997442455242967,
+      "grad_norm": 0.21053647994995117,
+      "learning_rate": 7.498940011604968e-05,
+      "loss": 0.024330951273441315,
+      "step": 645
+    },
+    {
+      "epoch": 0.11082693947144075,
+      "grad_norm": 0.21875615417957306,
+      "learning_rate": 7.498878220541564e-05,
+      "loss": 0.024424785375595094,
+      "step": 650
+    },
+    {
+      "epoch": 0.11167945439045183,
+      "grad_norm": 0.123925119638443,
+      "learning_rate": 7.498814679377101e-05,
+      "loss": 0.02317858040332794,
+      "step": 655
+    },
+    {
+      "epoch": 0.11253196930946291,
+      "grad_norm": 0.14151433110237122,
+      "learning_rate": 7.498749388141243e-05,
+      "loss": 0.022727210819721223,
+      "step": 660
+    },
+    {
+      "epoch": 0.113384484228474,
+      "grad_norm": 0.18616050481796265,
+      "learning_rate": 7.498682346864469e-05,
+      "loss": 0.01945887804031372,
+      "step": 665
+    },
+    {
+      "epoch": 0.11423699914748509,
+      "grad_norm": 0.1922500878572464,
+      "learning_rate": 7.498613555578076e-05,
+      "loss": 0.022058220207691194,
+      "step": 670
+    },
+    {
+      "epoch": 0.11508951406649616,
+      "grad_norm": 0.18918555974960327,
+      "learning_rate": 7.49854301431418e-05,
+      "loss": 0.0243424192070961,
+      "step": 675
+    },
+    {
+      "epoch": 0.11594202898550725,
+      "grad_norm": 0.16539838910102844,
+      "learning_rate": 7.49847072310571e-05,
+      "loss": 0.020285174250602722,
+      "step": 680
+    },
+    {
+      "epoch": 0.11679454390451834,
+      "grad_norm": 0.18860585987567902,
+      "learning_rate": 7.498396681986413e-05,
+      "loss": 0.023155918717384337,
+      "step": 685
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 0.14543582499027252,
+      "learning_rate": 7.498320890990857e-05,
+      "loss": 0.027234339714050294,
+      "step": 690
+    },
+    {
+      "epoch": 0.1184995737425405,
+      "grad_norm": 0.19847829639911652,
+      "learning_rate": 7.498243350154423e-05,
+      "loss": 0.023280018568038942,
+      "step": 695
+    },
+    {
+      "epoch": 0.11935208866155157,
+      "grad_norm": 0.17652468383312225,
+      "learning_rate": 7.498164059513307e-05,
+      "loss": 0.01944337636232376,
+      "step": 700
+    },
+    {
+      "epoch": 0.12020460358056266,
+      "grad_norm": 0.17437686026096344,
+      "learning_rate": 7.498083019104527e-05,
+      "loss": 0.024408455193042754,
+      "step": 705
+    },
+    {
+      "epoch": 0.12105711849957375,
+      "grad_norm": 0.23269855976104736,
+      "learning_rate": 7.498000228965913e-05,
+      "loss": 0.023170632123947144,
+      "step": 710
+    },
+    {
+      "epoch": 0.12190963341858482,
+      "grad_norm": 0.23201921582221985,
+      "learning_rate": 7.497915689136119e-05,
+      "loss": 0.020825451612472533,
+      "step": 715
+    },
+    {
+      "epoch": 0.12276214833759591,
+      "grad_norm": 0.21852006018161774,
+      "learning_rate": 7.497829399654607e-05,
+      "loss": 0.02518810033798218,
+      "step": 720
+    },
+    {
+      "epoch": 0.12361466325660699,
+      "grad_norm": 0.13872551918029785,
+      "learning_rate": 7.49774136056166e-05,
+      "loss": 0.019051629304885864,
+      "step": 725
+    },
+    {
+      "epoch": 0.12446717817561807,
+      "grad_norm": 0.19865746796131134,
+      "learning_rate": 7.497651571898379e-05,
+      "loss": 0.029187721014022828,
+      "step": 730
+    },
+    {
+      "epoch": 0.12531969309462915,
+      "grad_norm": 0.1114022508263588,
+      "learning_rate": 7.49756003370668e-05,
+      "loss": 0.019581268727779388,
+      "step": 735
+    },
+    {
+      "epoch": 0.12617220801364024,
+      "grad_norm": 0.15444278717041016,
+      "learning_rate": 7.497466746029293e-05,
+      "loss": 0.022893126308918,
+      "step": 740
+    },
+    {
+      "epoch": 0.12702472293265132,
+      "grad_norm": 0.17494694888591766,
+      "learning_rate": 7.497371708909771e-05,
+      "loss": 0.0201113760471344,
+      "step": 745
+    },
+    {
+      "epoch": 0.1278772378516624,
+      "grad_norm": 0.22953887283802032,
+      "learning_rate": 7.497274922392483e-05,
+      "loss": 0.019417384266853334,
+      "step": 750
+    },
+    {
+      "epoch": 0.1287297527706735,
+      "grad_norm": 0.3160583972930908,
+      "learning_rate": 7.497176386522606e-05,
+      "loss": 0.02309718430042267,
+      "step": 755
+    },
+    {
+      "epoch": 0.12958226768968456,
+      "grad_norm": 0.17354142665863037,
+      "learning_rate": 7.497076101346144e-05,
+      "loss": 0.023600351810455323,
+      "step": 760
+    },
+    {
+      "epoch": 0.13043478260869565,
+      "grad_norm": 0.16583387553691864,
+      "learning_rate": 7.496974066909913e-05,
+      "loss": 0.019191825389862062,
+      "step": 765
+    },
+    {
+      "epoch": 0.13128729752770674,
+      "grad_norm": 0.15626493096351624,
+      "learning_rate": 7.496870283261546e-05,
+      "loss": 0.02239798903465271,
+      "step": 770
+    },
+    {
+      "epoch": 0.13213981244671782,
+      "grad_norm": 0.14147315919399261,
+      "learning_rate": 7.49676475044949e-05,
+      "loss": 0.023734869062900545,
+      "step": 775
+    },
+    {
+      "epoch": 0.1329923273657289,
+      "grad_norm": 0.15843693912029266,
+      "learning_rate": 7.496657468523014e-05,
+      "loss": 0.025466001033782958,
+      "step": 780
+    },
+    {
+      "epoch": 0.13384484228473997,
+      "grad_norm": 0.22425507009029388,
+      "learning_rate": 7.496548437532202e-05,
+      "loss": 0.023076604306697845,
+      "step": 785
+    },
+    {
+      "epoch": 0.13469735720375106,
+      "grad_norm": 0.18824175000190735,
+      "learning_rate": 7.496437657527949e-05,
+      "loss": 0.021127034723758698,
+      "step": 790
+    },
+    {
+      "epoch": 0.13554987212276215,
+      "grad_norm": 0.16782736778259277,
+      "learning_rate": 7.496325128561975e-05,
+      "loss": 0.022259844839572905,
+      "step": 795
+    },
+    {
+      "epoch": 0.13640238704177324,
+      "grad_norm": 0.1475634127855301,
+      "learning_rate": 7.496210850686809e-05,
+      "loss": 0.022344502806663512,
+      "step": 800
+    },
+    {
+      "epoch": 0.13725490196078433,
+      "grad_norm": 0.20939050614833832,
+      "learning_rate": 7.496094823955801e-05,
+      "loss": 0.022960008680820466,
+      "step": 805
+    },
+    {
+      "epoch": 0.13810741687979539,
+      "grad_norm": 0.16113007068634033,
+      "learning_rate": 7.495977048423117e-05,
+      "loss": 0.02274739146232605,
+      "step": 810
+    },
+    {
+      "epoch": 0.13895993179880647,
+      "grad_norm": 0.15893374383449554,
+      "learning_rate": 7.495857524143738e-05,
+      "loss": 0.02106706500053406,
+      "step": 815
+    },
+    {
+      "epoch": 0.13981244671781756,
+      "grad_norm": 0.15888579189777374,
+      "learning_rate": 7.495736251173463e-05,
+      "loss": 0.023226001858711244,
+      "step": 820
+    },
+    {
+      "epoch": 0.14066496163682865,
+      "grad_norm": 0.11525560915470123,
+      "learning_rate": 7.495613229568903e-05,
+      "loss": 0.022408871352672576,
+      "step": 825
+    },
+    {
+      "epoch": 0.14151747655583974,
+      "grad_norm": 0.14761297404766083,
+      "learning_rate": 7.49548845938749e-05,
+      "loss": 0.019345660507678986,
+      "step": 830
+    },
+    {
+      "epoch": 0.1423699914748508,
+      "grad_norm": 0.13265904784202576,
+      "learning_rate": 7.495361940687475e-05,
+      "loss": 0.019794172048568724,
+      "step": 835
+    },
+    {
+      "epoch": 0.1432225063938619,
+      "grad_norm": 0.11557731032371521,
+      "learning_rate": 7.495233673527914e-05,
+      "loss": 0.024709561467170717,
+      "step": 840
+    },
+    {
+      "epoch": 0.14407502131287298,
+      "grad_norm": 0.17875051498413086,
+      "learning_rate": 7.495103657968692e-05,
+      "loss": 0.025614869594573975,
+      "step": 845
+    },
+    {
+      "epoch": 0.14492753623188406,
+      "grad_norm": 0.1512315273284912,
+      "learning_rate": 7.494971894070501e-05,
+      "loss": 0.025504299998283388,
+      "step": 850
+    },
+    {
+      "epoch": 0.14578005115089515,
+      "grad_norm": 0.14291605353355408,
+      "learning_rate": 7.494838381894856e-05,
+      "loss": 0.021080103516578675,
+      "step": 855
+    },
+    {
+      "epoch": 0.1466325660699062,
+      "grad_norm": 0.15058816969394684,
+      "learning_rate": 7.494703121504082e-05,
+      "loss": 0.02321579456329346,
+      "step": 860
+    },
+    {
+      "epoch": 0.1474850809889173,
+      "grad_norm": 0.1318487823009491,
+      "learning_rate": 7.494566112961325e-05,
+      "loss": 0.02411908209323883,
+      "step": 865
+    },
+    {
+      "epoch": 0.1483375959079284,
+      "grad_norm": 0.12876658141613007,
+      "learning_rate": 7.494427356330544e-05,
+      "loss": 0.019800490140914916,
+      "step": 870
+    },
+    {
+      "epoch": 0.14919011082693948,
+      "grad_norm": 0.12533710896968842,
+      "learning_rate": 7.494286851676515e-05,
+      "loss": 0.017035895586013795,
+      "step": 875
+    },
+    {
+      "epoch": 0.15004262574595056,
+      "grad_norm": 0.2429656982421875,
+      "learning_rate": 7.494144599064833e-05,
+      "loss": 0.0231891930103302,
+      "step": 880
+    },
+    {
+      "epoch": 0.15089514066496162,
+      "grad_norm": 0.16483844816684723,
+      "learning_rate": 7.494000598561902e-05,
+      "loss": 0.020446807146072388,
+      "step": 885
+    },
+    {
+      "epoch": 0.1517476555839727,
+      "grad_norm": 0.18868009746074677,
+      "learning_rate": 7.49385485023495e-05,
+      "loss": 0.01781340092420578,
+      "step": 890
+    },
+    {
+      "epoch": 0.1526001705029838,
+      "grad_norm": 0.1524050384759903,
+      "learning_rate": 7.493707354152015e-05,
+      "loss": 0.02079763263463974,
+      "step": 895
+    },
+    {
+      "epoch": 0.1534526854219949,
+      "grad_norm": 0.14906258881092072,
+      "learning_rate": 7.493558110381954e-05,
+      "loss": 0.020413240790367125,
+      "step": 900
+    },
+    {
+      "epoch": 0.15430520034100598,
+      "grad_norm": 0.17433762550354004,
+      "learning_rate": 7.493407118994437e-05,
+      "loss": 0.023528662323951722,
+      "step": 905
+    },
+    {
+      "epoch": 0.15515771526001704,
+      "grad_norm": 0.15428426861763,
+      "learning_rate": 7.493254380059954e-05,
+      "loss": 0.0167276993393898,
+      "step": 910
+    },
+    {
+      "epoch": 0.15601023017902813,
+      "grad_norm": 0.14796046912670135,
+      "learning_rate": 7.49309989364981e-05,
+      "loss": 0.021766343712806703,
+      "step": 915
+    },
+    {
+      "epoch": 0.1568627450980392,
+      "grad_norm": 0.19506044685840607,
+      "learning_rate": 7.492943659836121e-05,
+      "loss": 0.019172856211662294,
+      "step": 920
+    },
+    {
+      "epoch": 0.1577152600170503,
+      "grad_norm": 0.10270880907773972,
+      "learning_rate": 7.492785678691822e-05,
+      "loss": 0.017702698707580566,
+      "step": 925
+    },
+    {
+      "epoch": 0.1585677749360614,
+      "grad_norm": 0.19830335676670074,
+      "learning_rate": 7.492625950290668e-05,
+      "loss": 0.02414294332265854,
+      "step": 930
+    },
+    {
+      "epoch": 0.15942028985507245,
+      "grad_norm": 0.13340385258197784,
+      "learning_rate": 7.492464474707222e-05,
+      "loss": 0.020504102110862732,
+      "step": 935
+    },
+    {
+      "epoch": 0.16027280477408354,
+      "grad_norm": 0.15535341203212738,
+      "learning_rate": 7.492301252016867e-05,
+      "loss": 0.024209281802177428,
+      "step": 940
+    },
+    {
+      "epoch": 0.16112531969309463,
+      "grad_norm": 0.1643867790699005,
+      "learning_rate": 7.492136282295801e-05,
+      "loss": 0.023817232251167296,
+      "step": 945
+    },
+    {
+      "epoch": 0.16197783461210571,
+      "grad_norm": 0.17358379065990448,
+      "learning_rate": 7.491969565621036e-05,
+      "loss": 0.022003316879272462,
+      "step": 950
+    },
+    {
+      "epoch": 0.1628303495311168,
+      "grad_norm": 0.18677742779254913,
+      "learning_rate": 7.491801102070403e-05,
+      "loss": 0.018950483202934264,
+      "step": 955
+    },
+    {
+      "epoch": 0.1636828644501279,
+      "grad_norm": 0.13851206004619598,
+      "learning_rate": 7.491630891722547e-05,
+      "loss": 0.017542189359664916,
+      "step": 960
+    },
+    {
+      "epoch": 0.16453537936913895,
+      "grad_norm": 0.19967755675315857,
+      "learning_rate": 7.491458934656925e-05,
+      "loss": 0.022756266593933105,
+      "step": 965
+    },
+    {
+      "epoch": 0.16538789428815004,
+      "grad_norm": 0.12368317693471909,
+      "learning_rate": 7.491285230953814e-05,
+      "loss": 0.02156476378440857,
+      "step": 970
+    },
+    {
+      "epoch": 0.16624040920716113,
+      "grad_norm": 0.15940691530704498,
+      "learning_rate": 7.491109780694303e-05,
+      "loss": 0.020778095722198485,
+      "step": 975
+    },
+    {
+      "epoch": 0.16709292412617222,
+      "grad_norm": 0.13057319819927216,
+      "learning_rate": 7.490932583960302e-05,
+      "loss": 0.017678585648536683,
+      "step": 980
+    },
+    {
+      "epoch": 0.1679454390451833,
+      "grad_norm": 0.23632560670375824,
+      "learning_rate": 7.490753640834527e-05,
+      "loss": 0.0188615620136261,
+      "step": 985
+    },
+    {
+      "epoch": 0.16879795396419436,
+      "grad_norm": 0.17829905450344086,
+      "learning_rate": 7.490572951400518e-05,
+      "loss": 0.017176347970962524,
+      "step": 990
+    },
+    {
+      "epoch": 0.16965046888320545,
+      "grad_norm": 0.2470170259475708,
+      "learning_rate": 7.490390515742626e-05,
+      "loss": 0.020955404639244078,
+      "step": 995
+    },
+    {
+      "epoch": 0.17050298380221654,
+      "grad_norm": 0.17038558423519135,
+      "learning_rate": 7.490206333946019e-05,
+      "loss": 0.0216932088136673,
+      "step": 1000
+    },
+    {
+      "epoch": 0.17135549872122763,
+      "grad_norm": 0.18727493286132812,
+      "learning_rate": 7.490020406096678e-05,
+      "loss": 0.02001047134399414,
+      "step": 1005
+    },
+    {
+      "epoch": 0.17220801364023872,
+      "grad_norm": 0.13901565968990326,
+      "learning_rate": 7.489832732281401e-05,
+      "loss": 0.02116202861070633,
+      "step": 1010
+    },
+    {
+      "epoch": 0.17306052855924978,
+      "grad_norm": 0.15908955037593842,
+      "learning_rate": 7.489643312587799e-05,
+      "loss": 0.021178147196769713,
+      "step": 1015
+    },
+    {
+      "epoch": 0.17391304347826086,
+      "grad_norm": 0.10865574330091476,
+      "learning_rate": 7.489452147104301e-05,
+      "loss": 0.018146297335624693,
+      "step": 1020
+    },
+    {
+      "epoch": 0.17476555839727195,
+      "grad_norm": 0.15789146721363068,
+      "learning_rate": 7.489259235920149e-05,
+      "loss": 0.01937219351530075,
+      "step": 1025
+    },
+    {
+      "epoch": 0.17561807331628304,
+      "grad_norm": 0.15732690691947937,
+      "learning_rate": 7.489064579125399e-05,
+      "loss": 0.017243795096874237,
+      "step": 1030
+    },
+    {
+      "epoch": 0.17647058823529413,
+      "grad_norm": 0.16714419424533844,
+      "learning_rate": 7.488868176810926e-05,
+      "loss": 0.02017078697681427,
+      "step": 1035
+    },
+    {
+      "epoch": 0.1773231031543052,
+      "grad_norm": 0.17852213978767395,
+      "learning_rate": 7.488670029068415e-05,
+      "loss": 0.021479792892932892,
+      "step": 1040
+    },
+    {
+      "epoch": 0.17817561807331628,
+      "grad_norm": 0.13795003294944763,
+      "learning_rate": 7.488470135990369e-05,
+      "loss": 0.020610035955905916,
+      "step": 1045
+    },
+    {
+      "epoch": 0.17902813299232737,
+      "grad_norm": 0.1261966973543167,
+      "learning_rate": 7.488268497670103e-05,
+      "loss": 0.020418691635131835,
+      "step": 1050
+    },
+    {
+      "epoch": 0.17988064791133845,
+      "grad_norm": 0.14397430419921875,
+      "learning_rate": 7.488065114201752e-05,
+      "loss": 0.021986766159534453,
+      "step": 1055
+    },
+    {
+      "epoch": 0.18073316283034954,
+      "grad_norm": 0.16623377799987793,
+      "learning_rate": 7.487859985680257e-05,
+      "loss": 0.015715084969997406,
+      "step": 1060
+    },
+    {
+      "epoch": 0.1815856777493606,
+      "grad_norm": 0.16128598153591156,
+      "learning_rate": 7.487653112201385e-05,
+      "loss": 0.020126304030418395,
+      "step": 1065
+    },
+    {
+      "epoch": 0.1824381926683717,
+      "grad_norm": 0.16765518486499786,
+      "learning_rate": 7.487444493861705e-05,
+      "loss": 0.026783743500709535,
+      "step": 1070
+    },
+    {
+      "epoch": 0.18329070758738278,
+      "grad_norm": 0.1425476372241974,
+      "learning_rate": 7.487234130758613e-05,
+      "loss": 0.014856821298599244,
+      "step": 1075
+    },
+    {
+      "epoch": 0.18414322250639387,
+      "grad_norm": 0.12260995805263519,
+      "learning_rate": 7.487022022990309e-05,
+      "loss": 0.020856201648712158,
+      "step": 1080
+    },
+    {
+      "epoch": 0.18499573742540495,
+      "grad_norm": 0.19255946576595306,
+      "learning_rate": 7.486808170655813e-05,
+      "loss": 0.018779371678829194,
+      "step": 1085
+    },
+    {
+      "epoch": 0.18584825234441602,
+      "grad_norm": 0.10923872888088226,
+      "learning_rate": 7.48659257385496e-05,
+      "loss": 0.019713962078094484,
+      "step": 1090
+    },
+    {
+      "epoch": 0.1867007672634271,
+      "grad_norm": 0.1676846742630005,
+      "learning_rate": 7.486375232688397e-05,
+      "loss": 0.01982394903898239,
+      "step": 1095
+    },
+    {
+      "epoch": 0.1875532821824382,
+      "grad_norm": 0.1513833999633789,
+      "learning_rate": 7.486156147257584e-05,
+      "loss": 0.020366309583187102,
+      "step": 1100
+    },
+    {
+      "epoch": 0.18840579710144928,
+      "grad_norm": 0.19411510229110718,
+      "learning_rate": 7.485935317664801e-05,
+      "loss": 0.02244427800178528,
+      "step": 1105
+    },
+    {
+      "epoch": 0.18925831202046037,
+      "grad_norm": 0.15320256352424622,
+      "learning_rate": 7.485712744013137e-05,
+      "loss": 0.018899278342723848,
+      "step": 1110
+    },
+    {
+      "epoch": 0.19011082693947143,
+      "grad_norm": 0.1213340014219284,
+      "learning_rate": 7.485488426406495e-05,
+      "loss": 0.022865024209022523,
+      "step": 1115
+    },
+    {
+      "epoch": 0.19096334185848252,
+      "grad_norm": 0.156148761510849,
+      "learning_rate": 7.485262364949597e-05,
+      "loss": 0.01619085520505905,
+      "step": 1120
+    },
+    {
+      "epoch": 0.1918158567774936,
+      "grad_norm": 0.17139101028442383,
+      "learning_rate": 7.485034559747974e-05,
+      "loss": 0.024563166499137878,
+      "step": 1125
+    },
+    {
+      "epoch": 0.1926683716965047,
+      "grad_norm": 0.1486269235610962,
+      "learning_rate": 7.484805010907975e-05,
+      "loss": 0.017760181427001955,
+      "step": 1130
+    },
+    {
+      "epoch": 0.19352088661551578,
+      "grad_norm": 0.10183791071176529,
+      "learning_rate": 7.484573718536758e-05,
+      "loss": 0.018906766176223756,
+      "step": 1135
+    },
+    {
+      "epoch": 0.19437340153452684,
+      "grad_norm": 0.09899614751338959,
+      "learning_rate": 7.4843406827423e-05,
+      "loss": 0.017186886072158812,
+      "step": 1140
+    },
+    {
+      "epoch": 0.19522591645353793,
+      "grad_norm": 0.18609358370304108,
+      "learning_rate": 7.484105903633388e-05,
+      "loss": 0.023327428102493285,
+      "step": 1145
+    },
+    {
+      "epoch": 0.19607843137254902,
+      "grad_norm": 0.1430123895406723,
+      "learning_rate": 7.483869381319627e-05,
+      "loss": 0.01837810128927231,
+      "step": 1150
+    },
+    {
+      "epoch": 0.1969309462915601,
+      "grad_norm": 0.12148093432188034,
+      "learning_rate": 7.483631115911434e-05,
+      "loss": 0.020873771607875825,
+      "step": 1155
+    },
+    {
+      "epoch": 0.1977834612105712,
+      "grad_norm": 0.1707390397787094,
+      "learning_rate": 7.483391107520037e-05,
+      "loss": 0.020981839299201964,
+      "step": 1160
+    },
+    {
+      "epoch": 0.19863597612958228,
+      "grad_norm": 0.15569454431533813,
+      "learning_rate": 7.483149356257479e-05,
+      "loss": 0.020050540566444397,
+      "step": 1165
+    },
+    {
+      "epoch": 0.19948849104859334,
+      "grad_norm": 0.14249219000339508,
+      "learning_rate": 7.482905862236622e-05,
+      "loss": 0.023225483298301697,
+      "step": 1170
+    },
+    {
+      "epoch": 0.20034100596760443,
+      "grad_norm": 0.1274043619632721,
+      "learning_rate": 7.482660625571134e-05,
+      "loss": 0.019820016622543336,
+      "step": 1175
+    },
+    {
+      "epoch": 0.20119352088661552,
+      "grad_norm": 0.1457318663597107,
+      "learning_rate": 7.482413646375498e-05,
+      "loss": 0.02005559056997299,
+      "step": 1180
+    },
+    {
+      "epoch": 0.2020460358056266,
+      "grad_norm": 0.07950291782617569,
+      "learning_rate": 7.482164924765016e-05,
+      "loss": 0.017948240041732788,
+      "step": 1185
+    },
+    {
+      "epoch": 0.2028985507246377,
+      "grad_norm": 0.1678423136472702,
+      "learning_rate": 7.481914460855796e-05,
+      "loss": 0.019546866416931152,
+      "step": 1190
+    },
+    {
+      "epoch": 0.20375106564364875,
+      "grad_norm": 0.11161832511425018,
+      "learning_rate": 7.481662254764765e-05,
+      "loss": 0.016936585307121277,
+      "step": 1195
+    },
+    {
+      "epoch": 0.20460358056265984,
+      "grad_norm": 0.13490277528762817,
+      "learning_rate": 7.481408306609662e-05,
+      "loss": 0.0162262961268425,
+      "step": 1200
+    },
+    {
+      "epoch": 0.20545609548167093,
+      "grad_norm": 0.12022645026445389,
+      "learning_rate": 7.481152616509037e-05,
+      "loss": 0.016806957125663758,
+      "step": 1205
+    },
+    {
+      "epoch": 0.20630861040068202,
+      "grad_norm": 0.12359227240085602,
+      "learning_rate": 7.480895184582253e-05,
+      "loss": 0.018499378859996796,
+      "step": 1210
+    },
+    {
+      "epoch": 0.2071611253196931,
+      "grad_norm": 0.19136857986450195,
+      "learning_rate": 7.48063601094949e-05,
+      "loss": 0.020433078706264495,
+      "step": 1215
+    },
+    {
+      "epoch": 0.20801364023870417,
+      "grad_norm": 0.12723380327224731,
+      "learning_rate": 7.48037509573174e-05,
+      "loss": 0.02018003910779953,
+      "step": 1220
+    },
+    {
+      "epoch": 0.20886615515771526,
+      "grad_norm": 0.15497322380542755,
+      "learning_rate": 7.480112439050804e-05,
+      "loss": 0.02107332944869995,
+      "step": 1225
+    },
+    {
+      "epoch": 0.20971867007672634,
+      "grad_norm": 0.11446765065193176,
+      "learning_rate": 7.4798480410293e-05,
+      "loss": 0.019103091955184937,
+      "step": 1230
+    },
+    {
+      "epoch": 0.21057118499573743,
+      "grad_norm": 0.1497345268726349,
+      "learning_rate": 7.47958190179066e-05,
+      "loss": 0.017369136214256287,
+      "step": 1235
+    },
+    {
+      "epoch": 0.21142369991474852,
+      "grad_norm": 0.15736299753189087,
+      "learning_rate": 7.479314021459123e-05,
+      "loss": 0.021430164575576782,
+      "step": 1240
+    },
+    {
+      "epoch": 0.21227621483375958,
+      "grad_norm": 0.08084041625261307,
+      "learning_rate": 7.479044400159746e-05,
+      "loss": 0.020121607184410095,
+      "step": 1245
+    },
+    {
+      "epoch": 0.21312872975277067,
+      "grad_norm": 0.17284823954105377,
+      "learning_rate": 7.478773038018397e-05,
+      "loss": 0.01935868263244629,
+      "step": 1250
+    },
+    {
+      "epoch": 0.21398124467178176,
+      "grad_norm": 0.13502685725688934,
+      "learning_rate": 7.478499935161758e-05,
+      "loss": 0.01848755180835724,
+      "step": 1255
+    },
+    {
+      "epoch": 0.21483375959079284,
+      "grad_norm": 0.08890935033559799,
+      "learning_rate": 7.478225091717323e-05,
+      "loss": 0.015054155886173249,
+      "step": 1260
+    },
+    {
+      "epoch": 0.21568627450980393,
+      "grad_norm": 0.07348521798849106,
+      "learning_rate": 7.477948507813396e-05,
+      "loss": 0.02302621454000473,
+      "step": 1265
+    },
+    {
+      "epoch": 0.216538789428815,
+      "grad_norm": 0.12460815906524658,
+      "learning_rate": 7.477670183579094e-05,
+      "loss": 0.015830089151859284,
+      "step": 1270
+    },
+    {
+      "epoch": 0.21739130434782608,
+      "grad_norm": 0.09965575486421585,
+      "learning_rate": 7.477390119144353e-05,
+      "loss": 0.022217030823230743,
+      "step": 1275
+    },
+    {
+      "epoch": 0.21824381926683717,
+      "grad_norm": 0.1208283007144928,
+      "learning_rate": 7.477108314639913e-05,
+      "loss": 0.020600679516792297,
+      "step": 1280
+    },
+    {
+      "epoch": 0.21909633418584826,
+      "grad_norm": 0.1510528177022934,
+      "learning_rate": 7.47682477019733e-05,
+      "loss": 0.02392968088388443,
+      "step": 1285
+    },
+    {
+      "epoch": 0.21994884910485935,
+      "grad_norm": 0.1437598615884781,
+      "learning_rate": 7.476539485948973e-05,
+      "loss": 0.017244428396224976,
+      "step": 1290
+    },
+    {
+      "epoch": 0.2208013640238704,
+      "grad_norm": 0.20599612593650818,
+      "learning_rate": 7.476252462028021e-05,
+      "loss": 0.02182443141937256,
+      "step": 1295
+    },
+    {
+      "epoch": 0.2216538789428815,
+      "grad_norm": 0.12018046528100967,
+      "learning_rate": 7.475963698568468e-05,
+      "loss": 0.017898209393024445,
+      "step": 1300
+    },
+    {
+      "epoch": 0.22250639386189258,
+      "grad_norm": 0.14739947021007538,
+      "learning_rate": 7.475673195705116e-05,
+      "loss": 0.01632039248943329,
+      "step": 1305
+    },
+    {
+      "epoch": 0.22335890878090367,
+      "grad_norm": 0.1594342738389969,
+      "learning_rate": 7.475380953573583e-05,
+      "loss": 0.019042639434337615,
+      "step": 1310
+    },
+    {
+      "epoch": 0.22421142369991476,
+      "grad_norm": 0.15422497689723969,
+      "learning_rate": 7.475086972310297e-05,
+      "loss": 0.01909550428390503,
+      "step": 1315
+    },
+    {
+      "epoch": 0.22506393861892582,
+      "grad_norm": 0.10997913032770157,
+      "learning_rate": 7.474791252052498e-05,
+      "loss": 0.01707080900669098,
+      "step": 1320
+    },
+    {
+      "epoch": 0.2259164535379369,
+      "grad_norm": 0.14125043153762817,
+      "learning_rate": 7.47449379293824e-05,
+      "loss": 0.025346797704696656,
+      "step": 1325
+    },
+    {
+      "epoch": 0.226768968456948,
+      "grad_norm": 0.15269587934017181,
+      "learning_rate": 7.474194595106384e-05,
+      "loss": 0.017649538815021515,
+      "step": 1330
+    },
+    {
+      "epoch": 0.22762148337595908,
+      "grad_norm": 0.11451391130685806,
+      "learning_rate": 7.473893658696605e-05,
+      "loss": 0.016222651302814483,
+      "step": 1335
+    },
+    {
+      "epoch": 0.22847399829497017,
+      "grad_norm": 0.15066254138946533,
+      "learning_rate": 7.473590983849396e-05,
+      "loss": 0.019333544373512267,
+      "step": 1340
+    },
+    {
+      "epoch": 0.22932651321398123,
+      "grad_norm": 0.16034111380577087,
+      "learning_rate": 7.473286570706047e-05,
+      "loss": 0.020681440830230713,
+      "step": 1345
+    },
+    {
+      "epoch": 0.23017902813299232,
+      "grad_norm": 0.13590551912784576,
+      "learning_rate": 7.472980419408675e-05,
+      "loss": 0.01912907660007477,
+      "step": 1350
+    },
+    {
+      "epoch": 0.2310315430520034,
+      "grad_norm": 0.1059318482875824,
+      "learning_rate": 7.472672530100199e-05,
+      "loss": 0.013612470030784607,
+      "step": 1355
+    },
+    {
+      "epoch": 0.2318840579710145,
+      "grad_norm": 0.14834082126617432,
+      "learning_rate": 7.472362902924352e-05,
+      "loss": 0.01864627152681351,
+      "step": 1360
+    },
+    {
+      "epoch": 0.23273657289002558,
+      "grad_norm": 0.11334261298179626,
+      "learning_rate": 7.472051538025678e-05,
+      "loss": 0.018771368265151977,
+      "step": 1365
+    },
+    {
+      "epoch": 0.23358908780903667,
+      "grad_norm": 0.13945090770721436,
+      "learning_rate": 7.471738435549533e-05,
+      "loss": 0.01627613455057144,
+      "step": 1370
+    },
+    {
+      "epoch": 0.23444160272804773,
+      "grad_norm": 0.17654946446418762,
+      "learning_rate": 7.471423595642084e-05,
+      "loss": 0.02347823977470398,
+      "step": 1375
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 0.12936590611934662,
+      "learning_rate": 7.471107018450309e-05,
+      "loss": 0.02045731246471405,
+      "step": 1380
+    },
+    {
+      "epoch": 0.2361466325660699,
+      "grad_norm": 0.11726986616849899,
+      "learning_rate": 7.470788704121995e-05,
+      "loss": 0.020318010449409486,
+      "step": 1385
+    },
+    {
+      "epoch": 0.236999147485081,
+      "grad_norm": 0.08884494006633759,
+      "learning_rate": 7.470468652805743e-05,
+      "loss": 0.016616788506507874,
+      "step": 1390
+    },
+    {
+      "epoch": 0.23785166240409208,
+      "grad_norm": 0.1384650319814682,
+      "learning_rate": 7.470146864650965e-05,
+      "loss": 0.017017421126365662,
+      "step": 1395
+    },
+    {
+      "epoch": 0.23870417732310314,
+      "grad_norm": 0.17975082993507385,
+      "learning_rate": 7.46982333980788e-05,
+      "loss": 0.021484333276748657,
+      "step": 1400
+    },
+    {
+      "epoch": 0.23955669224211423,
+      "grad_norm": 0.12423302978277206,
+      "learning_rate": 7.469498078427519e-05,
+      "loss": 0.017081032693386077,
+      "step": 1405
+    },
+    {
+      "epoch": 0.24040920716112532,
+      "grad_norm": 0.1501087099313736,
+      "learning_rate": 7.46917108066173e-05,
+      "loss": 0.015354931354522705,
+      "step": 1410
+    },
+    {
+      "epoch": 0.2412617220801364,
+      "grad_norm": 0.09775341302156448,
+      "learning_rate": 7.468842346663162e-05,
+      "loss": 0.015043070912361145,
+      "step": 1415
+    },
+    {
+      "epoch": 0.2421142369991475,
+      "grad_norm": 0.22517770528793335,
+      "learning_rate": 7.468511876585279e-05,
+      "loss": 0.01923089921474457,
+      "step": 1420
+    },
+    {
+      "epoch": 0.24296675191815856,
+      "grad_norm": 0.16673070192337036,
+      "learning_rate": 7.468179670582359e-05,
+      "loss": 0.022077682614326476,
+      "step": 1425
+    },
+    {
+      "epoch": 0.24381926683716965,
+      "grad_norm": 0.15411542356014252,
+      "learning_rate": 7.467845728809483e-05,
+      "loss": 0.01438840925693512,
+      "step": 1430
+    },
+    {
+      "epoch": 0.24467178175618073,
+      "grad_norm": 0.14152199029922485,
+      "learning_rate": 7.46751005142255e-05,
+      "loss": 0.023038744926452637,
+      "step": 1435
+    },
+    {
+      "epoch": 0.24552429667519182,
+      "grad_norm": 0.22134003043174744,
+      "learning_rate": 7.46717263857826e-05,
+      "loss": 0.02072407156229019,
+      "step": 1440
+    },
+    {
+      "epoch": 0.2463768115942029,
+      "grad_norm": 0.16586056351661682,
+      "learning_rate": 7.466833490434132e-05,
+      "loss": 0.022452065348625184,
+      "step": 1445
+    },
+    {
+      "epoch": 0.24722932651321397,
+      "grad_norm": 0.2230711281299591,
+      "learning_rate": 7.466492607148492e-05,
+      "loss": 0.022158581018447875,
+      "step": 1450
+    },
+    {
+      "epoch": 0.24808184143222506,
+      "grad_norm": 0.1271371692419052,
+      "learning_rate": 7.466149988880474e-05,
+      "loss": 0.016606763005256653,
+      "step": 1455
+    },
+    {
+      "epoch": 0.24893435635123615,
+      "grad_norm": 0.16286347806453705,
+      "learning_rate": 7.465805635790024e-05,
+      "loss": 0.021220946311950685,
+      "step": 1460
+    },
+    {
+      "epoch": 0.24978687127024723,
+      "grad_norm": 0.1534752994775772,
+      "learning_rate": 7.4654595480379e-05,
+      "loss": 0.019277589023113252,
+      "step": 1465
+    },
+    {
+      "epoch": 0.24995737425404946,
+      "eval_loss": 0.048333022743463516,
+      "eval_runtime": 3.8326,
+      "eval_samples_per_second": 65.751,
+      "eval_steps_per_second": 1.044,
+      "step": 1466
+    },
+    {
+      "eval_cer_subset": 0.023708870569999294,
+      "eval_cer_subset_edit_distance": 1346,
+      "eval_cer_subset_groups": 250,
+      "eval_cer_subset_items": 250,
+      "eval_cer_subset_ref_chars": 56772,
+      "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": 6.463872307682918e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

meta-llama__llama-3.2-1b/sft/checkpoints/checkpoint-1466/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7511870667487ff1f832bd96611ce3c2683811bf8946eb2af6c034f3792899b8
+size 5841

meta-llama__llama-3.2-1b/sft/run_manifest.json

@@ -0,0 +1,25 @@
+{
+  "schema_version": 1,
+  "run_id": "297b34c8-0ca0-4b1d-8d20-7702c51d147c",
+  "run_type": "sft",
+  "profile_name": "llama3_2_1b_base",
+  "model_name": "meta-llama/Llama-3.2-1B",
+  "status": "running",
+  "best_metric_name": "eval_loss",
+  "best_metric_value": 0.048333022743463516,
+  "best_step": 1466,
+  "best_checkpoint_step": 1466,
+  "latest_checkpoint_step": 1466,
+  "checkpoints": [
+    {
+      "step": 1466,
+      "epoch": 0.24995737425404946,
+      "repo_path": "meta-llama__llama-3.2-1b/sft/checkpoints/checkpoint-1466",
+      "timestamp": "2026-04-08T02:56:19.031847+00:00"
+    }
+  ],
+  "epoch_artifacts": [],
+  "resume_history": [],
+  "created_at": "2026-04-08T02:28:34.984361+00:00",
+  "updated_at": "2026-04-08T02:56:19.031861+00:00"
+}