Training in progress, step 200, checkpoint

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: NousResearch/Genstruct-7B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.2

last-checkpoint/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Genstruct-7B",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c6f89b03293c5cbbcb8083b5bb42244d10589ff5cbca5cad523f0f1e76671a2
+size 335604696

last-checkpoint/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:150c0f434dfd7f3d8f57bf13c70161ffcdd298d226bab72d7c08c0a2d4a801f4
+size 90187222

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00af82b6e07a0d505ff61602f1f74c4f93a2ca6f8089fe2e08b1c9d4b4c1e985
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54369f03531bd788b68e0a2f2978b7e878c2350e695e0f5a13bcb4c5ed1dee84
+size 2080

last-checkpoint/special_tokens_map.json

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

last-checkpoint/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1024,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,1458 @@
+{
+  "best_metric": 1.4815335273742676,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.015984335351355673,
+  "eval_steps": 200,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 7.992167675677835e-05,
+      "grad_norm": 37.22200012207031,
+      "learning_rate": 6.666666649834951e-06,
+      "loss": 8.4924,
+      "step": 1
+    },
+    {
+      "epoch": 7.992167675677835e-05,
+      "eval_loss": 1.8860477209091187,
+      "eval_runtime": 98.2926,
+      "eval_samples_per_second": 5.117,
+      "eval_steps_per_second": 2.564,
+      "step": 1
+    },
+    {
+      "epoch": 0.0001598433535135567,
+      "grad_norm": 32.39023208618164,
+      "learning_rate": 1.3333333299669903e-05,
+      "loss": 6.3871,
+      "step": 2
+    },
+    {
+      "epoch": 0.00023976503027033506,
+      "grad_norm": 19.843673706054688,
+      "learning_rate": 1.9999999494757503e-05,
+      "loss": 7.0815,
+      "step": 3
+    },
+    {
+      "epoch": 0.0003196867070271134,
+      "grad_norm": 36.497798919677734,
+      "learning_rate": 2.6666666599339806e-05,
+      "loss": 7.4722,
+      "step": 4
+    },
+    {
+      "epoch": 0.0003996083837838918,
+      "grad_norm": 28.07762908935547,
+      "learning_rate": 3.333333370392211e-05,
+      "loss": 7.1274,
+      "step": 5
+    },
+    {
+      "epoch": 0.0004795300605406701,
+      "grad_norm": 26.69931983947754,
+      "learning_rate": 3.9999998989515007e-05,
+      "loss": 7.3171,
+      "step": 6
+    },
+    {
+      "epoch": 0.0005594517372974486,
+      "grad_norm": 27.132741928100586,
+      "learning_rate": 4.6666664275107905e-05,
+      "loss": 6.9837,
+      "step": 7
+    },
+    {
+      "epoch": 0.0006393734140542268,
+      "grad_norm": 24.915857315063477,
+      "learning_rate": 5.333333319867961e-05,
+      "loss": 6.6875,
+      "step": 8
+    },
+    {
+      "epoch": 0.0007192950908110052,
+      "grad_norm": 29.66477394104004,
+      "learning_rate": 6.000000212225132e-05,
+      "loss": 6.3959,
+      "step": 9
+    },
+    {
+      "epoch": 0.0007992167675677836,
+      "grad_norm": 23.80030632019043,
+      "learning_rate": 6.666666740784422e-05,
+      "loss": 7.2813,
+      "step": 10
+    },
+    {
+      "epoch": 0.000879138444324562,
+      "grad_norm": 26.563720703125,
+      "learning_rate": 7.333333633141592e-05,
+      "loss": 6.9997,
+      "step": 11
+    },
+    {
+      "epoch": 0.0009590601210813402,
+      "grad_norm": 21.319900512695312,
+      "learning_rate": 7.999999797903001e-05,
+      "loss": 6.3217,
+      "step": 12
+    },
+    {
+      "epoch": 0.0010389817978381187,
+      "grad_norm": 19.37892723083496,
+      "learning_rate": 8.666666690260172e-05,
+      "loss": 5.9959,
+      "step": 13
+    },
+    {
+      "epoch": 0.001118903474594897,
+      "grad_norm": 19.95276641845703,
+      "learning_rate": 9.333332855021581e-05,
+      "loss": 6.4046,
+      "step": 14
+    },
+    {
+      "epoch": 0.0011988251513516753,
+      "grad_norm": 18.308610916137695,
+      "learning_rate": 9.999999747378752e-05,
+      "loss": 6.316,
+      "step": 15
+    },
+    {
+      "epoch": 0.0012787468281084536,
+      "grad_norm": 20.602689743041992,
+      "learning_rate": 0.00010666666639735922,
+      "loss": 7.1446,
+      "step": 16
+    },
+    {
+      "epoch": 0.001358668504865232,
+      "grad_norm": 22.548585891723633,
+      "learning_rate": 0.00011333332804497331,
+      "loss": 6.438,
+      "step": 17
+    },
+    {
+      "epoch": 0.0014385901816220104,
+      "grad_norm": 25.837305068969727,
+      "learning_rate": 0.00012000000424450263,
+      "loss": 6.1006,
+      "step": 18
+    },
+    {
+      "epoch": 0.0015185118583787888,
+      "grad_norm": 24.4260196685791,
+      "learning_rate": 0.00012666666589211673,
+      "loss": 5.1146,
+      "step": 19
+    },
+    {
+      "epoch": 0.0015984335351355672,
+      "grad_norm": 16.986284255981445,
+      "learning_rate": 0.00013333333481568843,
+      "loss": 5.8081,
+      "step": 20
+    },
+    {
+      "epoch": 0.0016783552118923455,
+      "grad_norm": 22.057117462158203,
+      "learning_rate": 0.0001399999891873449,
+      "loss": 5.0405,
+      "step": 21
+    },
+    {
+      "epoch": 0.001758276888649124,
+      "grad_norm": 18.927270889282227,
+      "learning_rate": 0.00014666667266283184,
+      "loss": 6.2159,
+      "step": 22
+    },
+    {
+      "epoch": 0.0018381985654059023,
+      "grad_norm": 17.182756423950195,
+      "learning_rate": 0.00015333332703448832,
+      "loss": 5.5238,
+      "step": 23
+    },
+    {
+      "epoch": 0.0019181202421626805,
+      "grad_norm": 23.40513801574707,
+      "learning_rate": 0.00015999999595806003,
+      "loss": 5.6867,
+      "step": 24
+    },
+    {
+      "epoch": 0.001998041918919459,
+      "grad_norm": 19.549362182617188,
+      "learning_rate": 0.00016666666488163173,
+      "loss": 5.2317,
+      "step": 25
+    },
+    {
+      "epoch": 0.0020779635956762374,
+      "grad_norm": 16.442903518676758,
+      "learning_rate": 0.00017333333380520344,
+      "loss": 5.5897,
+      "step": 26
+    },
+    {
+      "epoch": 0.002157885272433016,
+      "grad_norm": 19.469303131103516,
+      "learning_rate": 0.00017999998817685992,
+      "loss": 5.9926,
+      "step": 27
+    },
+    {
+      "epoch": 0.002237806949189794,
+      "grad_norm": 19.722259521484375,
+      "learning_rate": 0.00018666665710043162,
+      "loss": 5.7072,
+      "step": 28
+    },
+    {
+      "epoch": 0.002317728625946572,
+      "grad_norm": 24.905616760253906,
+      "learning_rate": 0.00019333332602400333,
+      "loss": 5.697,
+      "step": 29
+    },
+    {
+      "epoch": 0.0023976503027033505,
+      "grad_norm": 18.89331817626953,
+      "learning_rate": 0.00019999999494757503,
+      "loss": 5.961,
+      "step": 30
+    },
+    {
+      "epoch": 0.002477571979460129,
+      "grad_norm": 17.505300521850586,
+      "learning_rate": 0.00019999999494757503,
+      "loss": 6.1253,
+      "step": 31
+    },
+    {
+      "epoch": 0.0025574936562169073,
+      "grad_norm": 20.62216567993164,
+      "learning_rate": 0.00019999999494757503,
+      "loss": 6.2062,
+      "step": 32
+    },
+    {
+      "epoch": 0.0026374153329736857,
+      "grad_norm": 15.589210510253906,
+      "learning_rate": 0.00019999999494757503,
+      "loss": 5.8827,
+      "step": 33
+    },
+    {
+      "epoch": 0.002717337009730464,
+      "grad_norm": 13.581818580627441,
+      "learning_rate": 0.00019999999494757503,
+      "loss": 6.1903,
+      "step": 34
+    },
+    {
+      "epoch": 0.0027972586864872424,
+      "grad_norm": 15.075100898742676,
+      "learning_rate": 0.0001999999803956598,
+      "loss": 5.5081,
+      "step": 35
+    },
+    {
+      "epoch": 0.002877180363244021,
+      "grad_norm": 15.700014114379883,
+      "learning_rate": 0.0001999999803956598,
+      "loss": 7.7248,
+      "step": 36
+    },
+    {
+      "epoch": 0.002957102040000799,
+      "grad_norm": 19.782855987548828,
+      "learning_rate": 0.0001999999803956598,
+      "loss": 6.2952,
+      "step": 37
+    },
+    {
+      "epoch": 0.0030370237167575776,
+      "grad_norm": 11.753912925720215,
+      "learning_rate": 0.00019999996584374458,
+      "loss": 6.4965,
+      "step": 38
+    },
+    {
+      "epoch": 0.003116945393514356,
+      "grad_norm": 18.95167350769043,
+      "learning_rate": 0.00019999996584374458,
+      "loss": 5.7159,
+      "step": 39
+    },
+    {
+      "epoch": 0.0031968670702711343,
+      "grad_norm": 16.020509719848633,
+      "learning_rate": 0.00019999996584374458,
+      "loss": 5.3622,
+      "step": 40
+    },
+    {
+      "epoch": 0.0032767887470279127,
+      "grad_norm": 12.910431861877441,
+      "learning_rate": 0.00019999995129182935,
+      "loss": 5.8321,
+      "step": 41
+    },
+    {
+      "epoch": 0.003356710423784691,
+      "grad_norm": 16.463891983032227,
+      "learning_rate": 0.00019999995129182935,
+      "loss": 5.3326,
+      "step": 42
+    },
+    {
+      "epoch": 0.0034366321005414695,
+      "grad_norm": 14.053927421569824,
+      "learning_rate": 0.00019999993673991412,
+      "loss": 5.5936,
+      "step": 43
+    },
+    {
+      "epoch": 0.003516553777298248,
+      "grad_norm": 13.335920333862305,
+      "learning_rate": 0.0001999999221879989,
+      "loss": 7.4054,
+      "step": 44
+    },
+    {
+      "epoch": 0.0035964754540550262,
+      "grad_norm": 12.41428279876709,
+      "learning_rate": 0.00019999990763608366,
+      "loss": 5.7294,
+      "step": 45
+    },
+    {
+      "epoch": 0.0036763971308118046,
+      "grad_norm": 15.011008262634277,
+      "learning_rate": 0.00019999989308416843,
+      "loss": 6.3856,
+      "step": 46
+    },
+    {
+      "epoch": 0.003756318807568583,
+      "grad_norm": 13.659316062927246,
+      "learning_rate": 0.00019999989308416843,
+      "loss": 5.4182,
+      "step": 47
+    },
+    {
+      "epoch": 0.003836240484325361,
+      "grad_norm": 16.465682983398438,
+      "learning_rate": 0.0001999998785322532,
+      "loss": 6.0745,
+      "step": 48
+    },
+    {
+      "epoch": 0.00391616216108214,
+      "grad_norm": 13.805000305175781,
+      "learning_rate": 0.00019999986398033798,
+      "loss": 5.4226,
+      "step": 49
+    },
+    {
+      "epoch": 0.003996083837838918,
+      "grad_norm": 14.028168678283691,
+      "learning_rate": 0.00019999984942842275,
+      "loss": 5.8116,
+      "step": 50
+    },
+    {
+      "epoch": 0.0040760055145956965,
+      "grad_norm": 24.225095748901367,
+      "learning_rate": 0.00019999983487650752,
+      "loss": 6.5766,
+      "step": 51
+    },
+    {
+      "epoch": 0.004155927191352475,
+      "grad_norm": 11.127175331115723,
+      "learning_rate": 0.00019999983487650752,
+      "loss": 5.4361,
+      "step": 52
+    },
+    {
+      "epoch": 0.004235848868109253,
+      "grad_norm": 15.43554973602295,
+      "learning_rate": 0.00019999980577267706,
+      "loss": 5.6854,
+      "step": 53
+    },
+    {
+      "epoch": 0.004315770544866032,
+      "grad_norm": 14.479979515075684,
+      "learning_rate": 0.00019999979122076184,
+      "loss": 5.7449,
+      "step": 54
+    },
+    {
+      "epoch": 0.00439569222162281,
+      "grad_norm": 14.647807121276855,
+      "learning_rate": 0.0001999997766688466,
+      "loss": 5.0891,
+      "step": 55
+    },
+    {
+      "epoch": 0.004475613898379588,
+      "grad_norm": 15.126065254211426,
+      "learning_rate": 0.00019999976211693138,
+      "loss": 5.7412,
+      "step": 56
+    },
+    {
+      "epoch": 0.004555535575136366,
+      "grad_norm": 12.997159004211426,
+      "learning_rate": 0.00019999974756501615,
+      "loss": 6.1477,
+      "step": 57
+    },
+    {
+      "epoch": 0.004635457251893144,
+      "grad_norm": 12.93421459197998,
+      "learning_rate": 0.0001999997184611857,
+      "loss": 5.9496,
+      "step": 58
+    },
+    {
+      "epoch": 0.004715378928649923,
+      "grad_norm": 13.043478965759277,
+      "learning_rate": 0.00019999970390927047,
+      "loss": 5.6047,
+      "step": 59
+    },
+    {
+      "epoch": 0.004795300605406701,
+      "grad_norm": 14.799778938293457,
+      "learning_rate": 0.00019999968935735524,
+      "loss": 6.6172,
+      "step": 60
+    },
+    {
+      "epoch": 0.0048752222821634794,
+      "grad_norm": 14.475525856018066,
+      "learning_rate": 0.00019999966025352478,
+      "loss": 5.8054,
+      "step": 61
+    },
+    {
+      "epoch": 0.004955143958920258,
+      "grad_norm": 12.044877052307129,
+      "learning_rate": 0.00019999963114969432,
+      "loss": 5.5472,
+      "step": 62
+    },
+    {
+      "epoch": 0.005035065635677036,
+      "grad_norm": 18.49376678466797,
+      "learning_rate": 0.0001999996165977791,
+      "loss": 6.478,
+      "step": 63
+    },
+    {
+      "epoch": 0.005114987312433815,
+      "grad_norm": 15.709685325622559,
+      "learning_rate": 0.00019999958749394864,
+      "loss": 6.4301,
+      "step": 64
+    },
+    {
+      "epoch": 0.005194908989190593,
+      "grad_norm": 13.605525016784668,
+      "learning_rate": 0.0001999995729420334,
+      "loss": 5.1469,
+      "step": 65
+    },
+    {
+      "epoch": 0.005274830665947371,
+      "grad_norm": 16.368547439575195,
+      "learning_rate": 0.00019999954383820295,
+      "loss": 6.2394,
+      "step": 66
+    },
+    {
+      "epoch": 0.00535475234270415,
+      "grad_norm": 13.256637573242188,
+      "learning_rate": 0.0001999995147343725,
+      "loss": 5.9834,
+      "step": 67
+    },
+    {
+      "epoch": 0.005434674019460928,
+      "grad_norm": 11.835427284240723,
+      "learning_rate": 0.00019999950018245727,
+      "loss": 5.5385,
+      "step": 68
+    },
+    {
+      "epoch": 0.0055145956962177065,
+      "grad_norm": 16.929773330688477,
+      "learning_rate": 0.00019999945652671158,
+      "loss": 5.9053,
+      "step": 69
+    },
+    {
+      "epoch": 0.005594517372974485,
+      "grad_norm": 18.215625762939453,
+      "learning_rate": 0.00019999942742288113,
+      "loss": 5.7839,
+      "step": 70
+    },
+    {
+      "epoch": 0.005674439049731263,
+      "grad_norm": 18.41301918029785,
+      "learning_rate": 0.0001999994128709659,
+      "loss": 6.2079,
+      "step": 71
+    },
+    {
+      "epoch": 0.005754360726488042,
+      "grad_norm": 14.074054718017578,
+      "learning_rate": 0.0001999993692152202,
+      "loss": 5.6966,
+      "step": 72
+    },
+    {
+      "epoch": 0.00583428240324482,
+      "grad_norm": 10.257038116455078,
+      "learning_rate": 0.00019999935466330498,
+      "loss": 5.1932,
+      "step": 73
+    },
+    {
+      "epoch": 0.005914204080001598,
+      "grad_norm": 14.28661823272705,
+      "learning_rate": 0.0001999993110075593,
+      "loss": 5.4345,
+      "step": 74
+    },
+    {
+      "epoch": 0.005994125756758377,
+      "grad_norm": 16.10113525390625,
+      "learning_rate": 0.00019999928190372884,
+      "loss": 5.167,
+      "step": 75
+    },
+    {
+      "epoch": 0.006074047433515155,
+      "grad_norm": 14.477482795715332,
+      "learning_rate": 0.00019999925279989839,
+      "loss": 6.1596,
+      "step": 76
+    },
+    {
+      "epoch": 0.0061539691102719335,
+      "grad_norm": 13.428840637207031,
+      "learning_rate": 0.00019999922369606793,
+      "loss": 6.1208,
+      "step": 77
+    },
+    {
+      "epoch": 0.006233890787028712,
+      "grad_norm": 13.18740177154541,
+      "learning_rate": 0.00019999918004032224,
+      "loss": 5.4248,
+      "step": 78
+    },
+    {
+      "epoch": 0.00631381246378549,
+      "grad_norm": 13.634086608886719,
+      "learning_rate": 0.0001999991509364918,
+      "loss": 5.8622,
+      "step": 79
+    },
+    {
+      "epoch": 0.006393734140542269,
+      "grad_norm": 16.816160202026367,
+      "learning_rate": 0.0001999991072807461,
+      "loss": 6.4171,
+      "step": 80
+    },
+    {
+      "epoch": 0.006473655817299047,
+      "grad_norm": 12.509149551391602,
+      "learning_rate": 0.00019999907817691565,
+      "loss": 5.7765,
+      "step": 81
+    },
+    {
+      "epoch": 0.006553577494055825,
+      "grad_norm": 17.675949096679688,
+      "learning_rate": 0.00019999903452116996,
+      "loss": 6.0027,
+      "step": 82
+    },
+    {
+      "epoch": 0.006633499170812604,
+      "grad_norm": 12.419123649597168,
+      "learning_rate": 0.0001999990054173395,
+      "loss": 6.0692,
+      "step": 83
+    },
+    {
+      "epoch": 0.006713420847569382,
+      "grad_norm": 14.577573776245117,
+      "learning_rate": 0.00019999897631350905,
+      "loss": 5.8782,
+      "step": 84
+    },
+    {
+      "epoch": 0.006793342524326161,
+      "grad_norm": 13.743675231933594,
+      "learning_rate": 0.00019999893265776336,
+      "loss": 6.8122,
+      "step": 85
+    },
+    {
+      "epoch": 0.006873264201082939,
+      "grad_norm": 14.996304512023926,
+      "learning_rate": 0.0001999989035539329,
+      "loss": 6.0888,
+      "step": 86
+    },
+    {
+      "epoch": 0.006953185877839717,
+      "grad_norm": 12.670077323913574,
+      "learning_rate": 0.000199998845346272,
+      "loss": 5.7549,
+      "step": 87
+    },
+    {
+      "epoch": 0.007033107554596496,
+      "grad_norm": 12.052266120910645,
+      "learning_rate": 0.00019999881624244153,
+      "loss": 5.47,
+      "step": 88
+    },
+    {
+      "epoch": 0.007113029231353274,
+      "grad_norm": 15.410880088806152,
+      "learning_rate": 0.00019999877258669585,
+      "loss": 5.9132,
+      "step": 89
+    },
+    {
+      "epoch": 0.0071929509081100525,
+      "grad_norm": 11.291873931884766,
+      "learning_rate": 0.00019999872893095016,
+      "loss": 5.2329,
+      "step": 90
+    },
+    {
+      "epoch": 0.007272872584866831,
+      "grad_norm": 12.137274742126465,
+      "learning_rate": 0.00019999868527520448,
+      "loss": 5.7357,
+      "step": 91
+    },
+    {
+      "epoch": 0.007352794261623609,
+      "grad_norm": 11.003666877746582,
+      "learning_rate": 0.0001999986416194588,
+      "loss": 5.5711,
+      "step": 92
+    },
+    {
+      "epoch": 0.007432715938380388,
+      "grad_norm": 17.23655128479004,
+      "learning_rate": 0.0001999985979637131,
+      "loss": 6.0937,
+      "step": 93
+    },
+    {
+      "epoch": 0.007512637615137166,
+      "grad_norm": 10.531327247619629,
+      "learning_rate": 0.00019999855430796742,
+      "loss": 5.1367,
+      "step": 94
+    },
+    {
+      "epoch": 0.0075925592918939435,
+      "grad_norm": 12.727346420288086,
+      "learning_rate": 0.00019999851065222174,
+      "loss": 4.6675,
+      "step": 95
+    },
+    {
+      "epoch": 0.007672480968650722,
+      "grad_norm": 11.735225677490234,
+      "learning_rate": 0.00019999846699647605,
+      "loss": 5.4399,
+      "step": 96
+    },
+    {
+      "epoch": 0.0077524026454075,
+      "grad_norm": 14.266508102416992,
+      "learning_rate": 0.00019999842334073037,
+      "loss": 5.9256,
+      "step": 97
+    },
+    {
+      "epoch": 0.00783232432216428,
+      "grad_norm": 12.180765151977539,
+      "learning_rate": 0.00019999837968498468,
+      "loss": 5.3318,
+      "step": 98
+    },
+    {
+      "epoch": 0.007912245998921057,
+      "grad_norm": 9.44970417022705,
+      "learning_rate": 0.00019999832147732377,
+      "loss": 6.8112,
+      "step": 99
+    },
+    {
+      "epoch": 0.007992167675677836,
+      "grad_norm": 14.178834915161133,
+      "learning_rate": 0.00019999827782157809,
+      "loss": 6.0084,
+      "step": 100
+    },
+    {
+      "epoch": 0.008072089352434614,
+      "grad_norm": 13.65369701385498,
+      "learning_rate": 0.0001999982341658324,
+      "loss": 5.6329,
+      "step": 101
+    },
+    {
+      "epoch": 0.008152011029191393,
+      "grad_norm": 13.261893272399902,
+      "learning_rate": 0.0001999981759581715,
+      "loss": 5.8068,
+      "step": 102
+    },
+    {
+      "epoch": 0.00823193270594817,
+      "grad_norm": 12.14011001586914,
+      "learning_rate": 0.00019999811775051057,
+      "loss": 5.6214,
+      "step": 103
+    },
+    {
+      "epoch": 0.00831185438270495,
+      "grad_norm": 16.864675521850586,
+      "learning_rate": 0.0001999980740947649,
+      "loss": 5.7395,
+      "step": 104
+    },
+    {
+      "epoch": 0.008391776059461727,
+      "grad_norm": 12.982168197631836,
+      "learning_rate": 0.00019999801588710397,
+      "loss": 5.7591,
+      "step": 105
+    },
+    {
+      "epoch": 0.008471697736218507,
+      "grad_norm": 12.251543998718262,
+      "learning_rate": 0.0001999979722313583,
+      "loss": 6.0408,
+      "step": 106
+    },
+    {
+      "epoch": 0.008551619412975284,
+      "grad_norm": 14.649770736694336,
+      "learning_rate": 0.00019999791402369738,
+      "loss": 5.1775,
+      "step": 107
+    },
+    {
+      "epoch": 0.008631541089732063,
+      "grad_norm": 13.069527626037598,
+      "learning_rate": 0.00019999785581603646,
+      "loss": 5.9182,
+      "step": 108
+    },
+    {
+      "epoch": 0.00871146276648884,
+      "grad_norm": 12.86717414855957,
+      "learning_rate": 0.00019999779760837555,
+      "loss": 6.3589,
+      "step": 109
+    },
+    {
+      "epoch": 0.00879138444324562,
+      "grad_norm": 15.912751197814941,
+      "learning_rate": 0.00019999775395262986,
+      "loss": 5.4512,
+      "step": 110
+    },
+    {
+      "epoch": 0.008871306120002398,
+      "grad_norm": 11.879186630249023,
+      "learning_rate": 0.00019999769574496895,
+      "loss": 4.5065,
+      "step": 111
+    },
+    {
+      "epoch": 0.008951227796759177,
+      "grad_norm": 10.903776168823242,
+      "learning_rate": 0.00019999763753730804,
+      "loss": 5.432,
+      "step": 112
+    },
+    {
+      "epoch": 0.009031149473515954,
+      "grad_norm": 15.748176574707031,
+      "learning_rate": 0.00019999757932964712,
+      "loss": 5.8155,
+      "step": 113
+    },
+    {
+      "epoch": 0.009111071150272732,
+      "grad_norm": 15.767736434936523,
+      "learning_rate": 0.0001999975211219862,
+      "loss": 5.8575,
+      "step": 114
+    },
+    {
+      "epoch": 0.009190992827029511,
+      "grad_norm": 25.656700134277344,
+      "learning_rate": 0.0001999974629143253,
+      "loss": 6.0736,
+      "step": 115
+    },
+    {
+      "epoch": 0.009270914503786289,
+      "grad_norm": 15.422691345214844,
+      "learning_rate": 0.00019999739015474916,
+      "loss": 6.5791,
+      "step": 116
+    },
+    {
+      "epoch": 0.009350836180543068,
+      "grad_norm": 11.980931282043457,
+      "learning_rate": 0.00019999733194708824,
+      "loss": 5.2912,
+      "step": 117
+    },
+    {
+      "epoch": 0.009430757857299845,
+      "grad_norm": 10.28679084777832,
+      "learning_rate": 0.00019999727373942733,
+      "loss": 6.3176,
+      "step": 118
+    },
+    {
+      "epoch": 0.009510679534056625,
+      "grad_norm": 10.766956329345703,
+      "learning_rate": 0.00019999721553176641,
+      "loss": 6.1716,
+      "step": 119
+    },
+    {
+      "epoch": 0.009590601210813402,
+      "grad_norm": 13.33298397064209,
+      "learning_rate": 0.0001999971573241055,
+      "loss": 5.8501,
+      "step": 120
+    },
+    {
+      "epoch": 0.009670522887570181,
+      "grad_norm": 14.927980422973633,
+      "learning_rate": 0.00019999708456452936,
+      "loss": 5.6786,
+      "step": 121
+    },
+    {
+      "epoch": 0.009750444564326959,
+      "grad_norm": 14.196168899536133,
+      "learning_rate": 0.00019999702635686845,
+      "loss": 5.0638,
+      "step": 122
+    },
+    {
+      "epoch": 0.009830366241083738,
+      "grad_norm": 15.0933837890625,
+      "learning_rate": 0.0001999969535972923,
+      "loss": 6.3901,
+      "step": 123
+    },
+    {
+      "epoch": 0.009910287917840516,
+      "grad_norm": 15.541980743408203,
+      "learning_rate": 0.0001999968953896314,
+      "loss": 5.8216,
+      "step": 124
+    },
+    {
+      "epoch": 0.009990209594597295,
+      "grad_norm": 13.888919830322266,
+      "learning_rate": 0.00019999682263005525,
+      "loss": 6.0595,
+      "step": 125
+    },
+    {
+      "epoch": 0.010070131271354072,
+      "grad_norm": 14.613118171691895,
+      "learning_rate": 0.00019999676442239434,
+      "loss": 5.9248,
+      "step": 126
+    },
+    {
+      "epoch": 0.010150052948110852,
+      "grad_norm": 11.033568382263184,
+      "learning_rate": 0.0001999966916628182,
+      "loss": 5.2841,
+      "step": 127
+    },
+    {
+      "epoch": 0.01022997462486763,
+      "grad_norm": 14.347121238708496,
+      "learning_rate": 0.00019999661890324205,
+      "loss": 7.3311,
+      "step": 128
+    },
+    {
+      "epoch": 0.010309896301624408,
+      "grad_norm": 16.174713134765625,
+      "learning_rate": 0.00019999656069558114,
+      "loss": 6.0626,
+      "step": 129
+    },
+    {
+      "epoch": 0.010389817978381186,
+      "grad_norm": 13.292625427246094,
+      "learning_rate": 0.000199996487936005,
+      "loss": 5.5513,
+      "step": 130
+    },
+    {
+      "epoch": 0.010469739655137965,
+      "grad_norm": 12.685737609863281,
+      "learning_rate": 0.00019999641517642885,
+      "loss": 6.0869,
+      "step": 131
+    },
+    {
+      "epoch": 0.010549661331894743,
+      "grad_norm": 15.05136775970459,
+      "learning_rate": 0.0001999963424168527,
+      "loss": 6.4054,
+      "step": 132
+    },
+    {
+      "epoch": 0.010629583008651522,
+      "grad_norm": 14.444158554077148,
+      "learning_rate": 0.00019999626965727657,
+      "loss": 6.1854,
+      "step": 133
+    },
+    {
+      "epoch": 0.0107095046854083,
+      "grad_norm": 11.998517036437988,
+      "learning_rate": 0.00019999619689770043,
+      "loss": 5.8521,
+      "step": 134
+    },
+    {
+      "epoch": 0.010789426362165079,
+      "grad_norm": 13.579330444335938,
+      "learning_rate": 0.00019999613869003952,
+      "loss": 5.3571,
+      "step": 135
+    },
+    {
+      "epoch": 0.010869348038921856,
+      "grad_norm": 12.388849258422852,
+      "learning_rate": 0.00019999605137854815,
+      "loss": 5.463,
+      "step": 136
+    },
+    {
+      "epoch": 0.010949269715678635,
+      "grad_norm": 19.74486541748047,
+      "learning_rate": 0.000199995978618972,
+      "loss": 5.247,
+      "step": 137
+    },
+    {
+      "epoch": 0.011029191392435413,
+      "grad_norm": 14.033202171325684,
+      "learning_rate": 0.00019999590585939586,
+      "loss": 5.8407,
+      "step": 138
+    },
+    {
+      "epoch": 0.011109113069192192,
+      "grad_norm": 18.360633850097656,
+      "learning_rate": 0.0001999958185479045,
+      "loss": 6.1892,
+      "step": 139
+    },
+    {
+      "epoch": 0.01118903474594897,
+      "grad_norm": 17.674312591552734,
+      "learning_rate": 0.00019999574578832835,
+      "loss": 6.0194,
+      "step": 140
+    },
+    {
+      "epoch": 0.011268956422705749,
+      "grad_norm": 15.879343032836914,
+      "learning_rate": 0.0001999956730287522,
+      "loss": 6.4648,
+      "step": 141
+    },
+    {
+      "epoch": 0.011348878099462527,
+      "grad_norm": 17.84900665283203,
+      "learning_rate": 0.00019999560026917607,
+      "loss": 5.1712,
+      "step": 142
+    },
+    {
+      "epoch": 0.011428799776219306,
+      "grad_norm": 15.98507022857666,
+      "learning_rate": 0.0001999955129576847,
+      "loss": 6.4617,
+      "step": 143
+    },
+    {
+      "epoch": 0.011508721452976083,
+      "grad_norm": 13.717947006225586,
+      "learning_rate": 0.00019999544019810855,
+      "loss": 5.5989,
+      "step": 144
+    },
+    {
+      "epoch": 0.011588643129732863,
+      "grad_norm": 12.210638046264648,
+      "learning_rate": 0.00019999535288661718,
+      "loss": 5.3995,
+      "step": 145
+    },
+    {
+      "epoch": 0.01166856480648964,
+      "grad_norm": 16.785219192504883,
+      "learning_rate": 0.00019999528012704104,
+      "loss": 6.6433,
+      "step": 146
+    },
+    {
+      "epoch": 0.01174848648324642,
+      "grad_norm": 11.631070137023926,
+      "learning_rate": 0.00019999519281554967,
+      "loss": 6.1817,
+      "step": 147
+    },
+    {
+      "epoch": 0.011828408160003197,
+      "grad_norm": 16.383235931396484,
+      "learning_rate": 0.0001999951055040583,
+      "loss": 7.2722,
+      "step": 148
+    },
+    {
+      "epoch": 0.011908329836759976,
+      "grad_norm": 14.994651794433594,
+      "learning_rate": 0.00019999501819256693,
+      "loss": 6.1687,
+      "step": 149
+    },
+    {
+      "epoch": 0.011988251513516754,
+      "grad_norm": 11.364398956298828,
+      "learning_rate": 0.0001999949454329908,
+      "loss": 5.7946,
+      "step": 150
+    },
+    {
+      "epoch": 0.012068173190273533,
+      "grad_norm": 13.537617683410645,
+      "learning_rate": 0.00019999485812149942,
+      "loss": 7.089,
+      "step": 151
+    },
+    {
+      "epoch": 0.01214809486703031,
+      "grad_norm": 12.958017349243164,
+      "learning_rate": 0.00019999477081000805,
+      "loss": 5.9082,
+      "step": 152
+    },
+    {
+      "epoch": 0.012228016543787088,
+      "grad_norm": 12.98481273651123,
+      "learning_rate": 0.00019999468349851668,
+      "loss": 5.6679,
+      "step": 153
+    },
+    {
+      "epoch": 0.012307938220543867,
+      "grad_norm": 12.365118980407715,
+      "learning_rate": 0.00019999461073894054,
+      "loss": 6.0434,
+      "step": 154
+    },
+    {
+      "epoch": 0.012387859897300645,
+      "grad_norm": 12.932500839233398,
+      "learning_rate": 0.00019999450887553394,
+      "loss": 6.1713,
+      "step": 155
+    },
+    {
+      "epoch": 0.012467781574057424,
+      "grad_norm": 19.78156089782715,
+      "learning_rate": 0.00019999442156404257,
+      "loss": 6.2086,
+      "step": 156
+    },
+    {
+      "epoch": 0.012547703250814201,
+      "grad_norm": 11.061141014099121,
+      "learning_rate": 0.0001999943342525512,
+      "loss": 6.0355,
+      "step": 157
+    },
+    {
+      "epoch": 0.01262762492757098,
+      "grad_norm": 13.9314546585083,
+      "learning_rate": 0.00019999424694105983,
+      "loss": 5.9093,
+      "step": 158
+    },
+    {
+      "epoch": 0.012707546604327758,
+      "grad_norm": 14.172832489013672,
+      "learning_rate": 0.00019999415962956846,
+      "loss": 6.8526,
+      "step": 159
+    },
+    {
+      "epoch": 0.012787468281084537,
+      "grad_norm": 18.87773323059082,
+      "learning_rate": 0.0001999940723180771,
+      "loss": 6.3218,
+      "step": 160
+    },
+    {
+      "epoch": 0.012867389957841315,
+      "grad_norm": 16.51616668701172,
+      "learning_rate": 0.0001999939704546705,
+      "loss": 6.2822,
+      "step": 161
+    },
+    {
+      "epoch": 0.012947311634598094,
+      "grad_norm": 12.870879173278809,
+      "learning_rate": 0.00019999388314317912,
+      "loss": 6.0757,
+      "step": 162
+    },
+    {
+      "epoch": 0.013027233311354872,
+      "grad_norm": 14.032119750976562,
+      "learning_rate": 0.00019999378127977252,
+      "loss": 6.1563,
+      "step": 163
+    },
+    {
+      "epoch": 0.01310715498811165,
+      "grad_norm": 11.09622573852539,
+      "learning_rate": 0.00019999369396828115,
+      "loss": 6.4961,
+      "step": 164
+    },
+    {
+      "epoch": 0.013187076664868428,
+      "grad_norm": 17.513566970825195,
+      "learning_rate": 0.00019999360665678978,
+      "loss": 5.6312,
+      "step": 165
+    },
+    {
+      "epoch": 0.013266998341625208,
+      "grad_norm": 15.271513938903809,
+      "learning_rate": 0.00019999350479338318,
+      "loss": 5.5845,
+      "step": 166
+    },
+    {
+      "epoch": 0.013346920018381985,
+      "grad_norm": 16.279600143432617,
+      "learning_rate": 0.0001999934174818918,
+      "loss": 7.2343,
+      "step": 167
+    },
+    {
+      "epoch": 0.013426841695138764,
+      "grad_norm": 11.651063919067383,
+      "learning_rate": 0.0001999933156184852,
+      "loss": 5.5595,
+      "step": 168
+    },
+    {
+      "epoch": 0.013506763371895542,
+      "grad_norm": 13.22779655456543,
+      "learning_rate": 0.00019999321375507861,
+      "loss": 5.3407,
+      "step": 169
+    },
+    {
+      "epoch": 0.013586685048652321,
+      "grad_norm": 14.671384811401367,
+      "learning_rate": 0.00019999311189167202,
+      "loss": 5.88,
+      "step": 170
+    },
+    {
+      "epoch": 0.013666606725409099,
+      "grad_norm": 14.504816055297852,
+      "learning_rate": 0.00019999302458018064,
+      "loss": 7.0499,
+      "step": 171
+    },
+    {
+      "epoch": 0.013746528402165878,
+      "grad_norm": 12.481976509094238,
+      "learning_rate": 0.00019999292271677405,
+      "loss": 5.5081,
+      "step": 172
+    },
+    {
+      "epoch": 0.013826450078922655,
+      "grad_norm": 12.96068286895752,
+      "learning_rate": 0.00019999282085336745,
+      "loss": 6.2696,
+      "step": 173
+    },
+    {
+      "epoch": 0.013906371755679435,
+      "grad_norm": 13.803003311157227,
+      "learning_rate": 0.00019999271898996085,
+      "loss": 6.0317,
+      "step": 174
+    },
+    {
+      "epoch": 0.013986293432436212,
+      "grad_norm": 11.114527702331543,
+      "learning_rate": 0.00019999261712655425,
+      "loss": 5.5847,
+      "step": 175
+    },
+    {
+      "epoch": 0.014066215109192991,
+      "grad_norm": 15.764811515808105,
+      "learning_rate": 0.00019999251526314765,
+      "loss": 5.6269,
+      "step": 176
+    },
+    {
+      "epoch": 0.014146136785949769,
+      "grad_norm": 15.654651641845703,
+      "learning_rate": 0.00019999241339974105,
+      "loss": 5.5381,
+      "step": 177
+    },
+    {
+      "epoch": 0.014226058462706548,
+      "grad_norm": 13.531250953674316,
+      "learning_rate": 0.00019999231153633446,
+      "loss": 5.8497,
+      "step": 178
+    },
+    {
+      "epoch": 0.014305980139463326,
+      "grad_norm": 14.135481834411621,
+      "learning_rate": 0.00019999220967292786,
+      "loss": 6.4536,
+      "step": 179
+    },
+    {
+      "epoch": 0.014385901816220105,
+      "grad_norm": 14.79910945892334,
+      "learning_rate": 0.00019999210780952126,
+      "loss": 5.445,
+      "step": 180
+    },
+    {
+      "epoch": 0.014465823492976882,
+      "grad_norm": 17.633644104003906,
+      "learning_rate": 0.00019999199139419943,
+      "loss": 6.4133,
+      "step": 181
+    },
+    {
+      "epoch": 0.014545745169733662,
+      "grad_norm": 17.391921997070312,
+      "learning_rate": 0.00019999188953079283,
+      "loss": 7.1431,
+      "step": 182
+    },
+    {
+      "epoch": 0.01462566684649044,
+      "grad_norm": 12.602208137512207,
+      "learning_rate": 0.00019999178766738623,
+      "loss": 5.4025,
+      "step": 183
+    },
+    {
+      "epoch": 0.014705588523247218,
+      "grad_norm": 14.608774185180664,
+      "learning_rate": 0.0001999916712520644,
+      "loss": 6.0169,
+      "step": 184
+    },
+    {
+      "epoch": 0.014785510200003996,
+      "grad_norm": 10.606766700744629,
+      "learning_rate": 0.0001999915693886578,
+      "loss": 5.8955,
+      "step": 185
+    },
+    {
+      "epoch": 0.014865431876760775,
+      "grad_norm": 12.560757637023926,
+      "learning_rate": 0.00019999145297333598,
+      "loss": 5.2885,
+      "step": 186
+    },
+    {
+      "epoch": 0.014945353553517553,
+      "grad_norm": 11.710776329040527,
+      "learning_rate": 0.00019999135110992938,
+      "loss": 5.5265,
+      "step": 187
+    },
+    {
+      "epoch": 0.015025275230274332,
+      "grad_norm": 15.717044830322266,
+      "learning_rate": 0.00019999123469460756,
+      "loss": 5.9089,
+      "step": 188
+    },
+    {
+      "epoch": 0.01510519690703111,
+      "grad_norm": 12.741106986999512,
+      "learning_rate": 0.00019999113283120096,
+      "loss": 5.3491,
+      "step": 189
+    },
+    {
+      "epoch": 0.015185118583787887,
+      "grad_norm": 14.55860710144043,
+      "learning_rate": 0.00019999101641587913,
+      "loss": 5.7533,
+      "step": 190
+    },
+    {
+      "epoch": 0.015265040260544666,
+      "grad_norm": 11.902217864990234,
+      "learning_rate": 0.0001999909000005573,
+      "loss": 5.9205,
+      "step": 191
+    },
+    {
+      "epoch": 0.015344961937301444,
+      "grad_norm": 10.153369903564453,
+      "learning_rate": 0.0001999907981371507,
+      "loss": 5.5668,
+      "step": 192
+    },
+    {
+      "epoch": 0.015424883614058223,
+      "grad_norm": 18.138729095458984,
+      "learning_rate": 0.00019999066716991365,
+      "loss": 6.0714,
+      "step": 193
+    },
+    {
+      "epoch": 0.015504805290815,
+      "grad_norm": 16.432695388793945,
+      "learning_rate": 0.00019999056530650705,
+      "loss": 6.283,
+      "step": 194
+    },
+    {
+      "epoch": 0.01558472696757178,
+      "grad_norm": 16.78881072998047,
+      "learning_rate": 0.00019999044889118522,
+      "loss": 5.4842,
+      "step": 195
+    },
+    {
+      "epoch": 0.01566464864432856,
+      "grad_norm": 15.031536102294922,
+      "learning_rate": 0.0001999903324758634,
+      "loss": 5.5433,
+      "step": 196
+    },
+    {
+      "epoch": 0.015744570321085335,
+      "grad_norm": 14.146148681640625,
+      "learning_rate": 0.00019999020150862634,
+      "loss": 6.1189,
+      "step": 197
+    },
+    {
+      "epoch": 0.015824491997842114,
+      "grad_norm": 13.80488109588623,
+      "learning_rate": 0.00019999008509330451,
+      "loss": 5.4253,
+      "step": 198
+    },
+    {
+      "epoch": 0.015904413674598893,
+      "grad_norm": 20.306961059570312,
+      "learning_rate": 0.00019998998322989792,
+      "loss": 6.6715,
+      "step": 199
+    },
+    {
+      "epoch": 0.015984335351355673,
+      "grad_norm": 13.931363105773926,
+      "learning_rate": 0.0001999898668145761,
+      "loss": 5.5369,
+      "step": 200
+    },
+    {
+      "epoch": 0.015984335351355673,
+      "eval_loss": 1.4815335273742676,
+      "eval_runtime": 98.2759,
+      "eval_samples_per_second": 5.118,
+      "eval_steps_per_second": 2.564,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 37536,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.766122597423514e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d084c02b5cdbdbb320414cfcc9d853380e808010c84a0102f338da720bf1f3e8
+size 6776