Training in progress, step 200, checkpoint

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v0.6
+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": "TinyLlama/TinyLlama-1.1B-Chat-v0.6",
+  "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": [
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "k_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 sha256:3fd39f0658097d2a407b159096b5ac74731b4a1fca718bf779353abd6b6c336e
+size 100966336

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a0c20730e90a29763f006c0c9dd520f3726ce32272a0274d558a786aefb3827
+size 51613348

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:822f40e83a7697d0a8d6ac463ce64ede327489c16a0694c1276bd50d3955fa6d
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:169b5a57dfd6231eaa41f664e1cb35dfeba56850d8efe784b9b872beb360577d
+size 1064

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": "</s>",
+    "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if 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": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,1458 @@
+{
+  "best_metric": 0.7152236104011536,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.14732965009208104,
+  "eval_steps": 200,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0007366482504604051,
+      "grad_norm": 0.28868868947029114,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.2866,
+      "step": 1
+    },
+    {
+      "epoch": 0.0007366482504604051,
+      "eval_loss": 1.2665157318115234,
+      "eval_runtime": 6.8378,
+      "eval_samples_per_second": 32.028,
+      "eval_steps_per_second": 2.047,
+      "step": 1
+    },
+    {
+      "epoch": 0.0014732965009208103,
+      "grad_norm": 0.2721092998981476,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.1921,
+      "step": 2
+    },
+    {
+      "epoch": 0.0022099447513812156,
+      "grad_norm": 0.2507239282131195,
+      "learning_rate": 2e-05,
+      "loss": 1.2248,
+      "step": 3
+    },
+    {
+      "epoch": 0.0029465930018416206,
+      "grad_norm": 0.31477007269859314,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 1.2239,
+      "step": 4
+    },
+    {
+      "epoch": 0.003683241252302026,
+      "grad_norm": 0.2397865504026413,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.1608,
+      "step": 5
+    },
+    {
+      "epoch": 0.004419889502762431,
+      "grad_norm": 0.3009697496891022,
+      "learning_rate": 4e-05,
+      "loss": 1.3438,
+      "step": 6
+    },
+    {
+      "epoch": 0.005156537753222836,
+      "grad_norm": 0.2904853820800781,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 1.2701,
+      "step": 7
+    },
+    {
+      "epoch": 0.005893186003683241,
+      "grad_norm": 0.33849483728408813,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 1.2262,
+      "step": 8
+    },
+    {
+      "epoch": 0.0066298342541436465,
+      "grad_norm": 0.3323328197002411,
+      "learning_rate": 6e-05,
+      "loss": 1.2717,
+      "step": 9
+    },
+    {
+      "epoch": 0.007366482504604052,
+      "grad_norm": 0.33532556891441345,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.2452,
+      "step": 10
+    },
+    {
+      "epoch": 0.008103130755064457,
+      "grad_norm": 0.2909528613090515,
+      "learning_rate": 7.333333333333333e-05,
+      "loss": 1.254,
+      "step": 11
+    },
+    {
+      "epoch": 0.008839779005524863,
+      "grad_norm": 0.3497731685638428,
+      "learning_rate": 8e-05,
+      "loss": 1.2461,
+      "step": 12
+    },
+    {
+      "epoch": 0.009576427255985266,
+      "grad_norm": 0.29530569911003113,
+      "learning_rate": 8.666666666666667e-05,
+      "loss": 1.1641,
+      "step": 13
+    },
+    {
+      "epoch": 0.010313075506445672,
+      "grad_norm": 0.2533603012561798,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 1.1072,
+      "step": 14
+    },
+    {
+      "epoch": 0.011049723756906077,
+      "grad_norm": 0.2972542643547058,
+      "learning_rate": 0.0001,
+      "loss": 1.149,
+      "step": 15
+    },
+    {
+      "epoch": 0.011786372007366482,
+      "grad_norm": 0.353914737701416,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 1.1723,
+      "step": 16
+    },
+    {
+      "epoch": 0.012523020257826888,
+      "grad_norm": 0.3351369798183441,
+      "learning_rate": 0.00011333333333333334,
+      "loss": 1.1044,
+      "step": 17
+    },
+    {
+      "epoch": 0.013259668508287293,
+      "grad_norm": 0.32723468542099,
+      "learning_rate": 0.00012,
+      "loss": 1.108,
+      "step": 18
+    },
+    {
+      "epoch": 0.013996316758747698,
+      "grad_norm": 0.28849488496780396,
+      "learning_rate": 0.00012666666666666666,
+      "loss": 1.0555,
+      "step": 19
+    },
+    {
+      "epoch": 0.014732965009208104,
+      "grad_norm": 0.3550494611263275,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 1.0161,
+      "step": 20
+    },
+    {
+      "epoch": 0.015469613259668509,
+      "grad_norm": 0.39074304699897766,
+      "learning_rate": 0.00014,
+      "loss": 1.0858,
+      "step": 21
+    },
+    {
+      "epoch": 0.016206261510128914,
+      "grad_norm": 0.37553301453590393,
+      "learning_rate": 0.00014666666666666666,
+      "loss": 1.0123,
+      "step": 22
+    },
+    {
+      "epoch": 0.01694290976058932,
+      "grad_norm": 0.3234458863735199,
+      "learning_rate": 0.00015333333333333334,
+      "loss": 1.0012,
+      "step": 23
+    },
+    {
+      "epoch": 0.017679558011049725,
+      "grad_norm": 0.35222887992858887,
+      "learning_rate": 0.00016,
+      "loss": 1.1103,
+      "step": 24
+    },
+    {
+      "epoch": 0.01841620626151013,
+      "grad_norm": 0.2721497416496277,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 0.9494,
+      "step": 25
+    },
+    {
+      "epoch": 0.019152854511970532,
+      "grad_norm": 0.2601194679737091,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 0.9577,
+      "step": 26
+    },
+    {
+      "epoch": 0.019889502762430938,
+      "grad_norm": 0.2771545648574829,
+      "learning_rate": 0.00018,
+      "loss": 1.0068,
+      "step": 27
+    },
+    {
+      "epoch": 0.020626151012891343,
+      "grad_norm": 0.3087043762207031,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 1.0227,
+      "step": 28
+    },
+    {
+      "epoch": 0.02136279926335175,
+      "grad_norm": 0.2947598993778229,
+      "learning_rate": 0.00019333333333333333,
+      "loss": 0.9619,
+      "step": 29
+    },
+    {
+      "epoch": 0.022099447513812154,
+      "grad_norm": 0.2529889643192291,
+      "learning_rate": 0.0002,
+      "loss": 0.9296,
+      "step": 30
+    },
+    {
+      "epoch": 0.02283609576427256,
+      "grad_norm": 0.27469512820243835,
+      "learning_rate": 0.0001999999697801693,
+      "loss": 0.9583,
+      "step": 31
+    },
+    {
+      "epoch": 0.023572744014732964,
+      "grad_norm": 0.2640707492828369,
+      "learning_rate": 0.00019999987912069548,
+      "loss": 0.9349,
+      "step": 32
+    },
+    {
+      "epoch": 0.02430939226519337,
+      "grad_norm": 0.2592534124851227,
+      "learning_rate": 0.0001999997280216333,
+      "loss": 0.8612,
+      "step": 33
+    },
+    {
+      "epoch": 0.025046040515653775,
+      "grad_norm": 0.27370938658714294,
+      "learning_rate": 0.0001999995164830741,
+      "loss": 0.918,
+      "step": 34
+    },
+    {
+      "epoch": 0.02578268876611418,
+      "grad_norm": 0.2904687523841858,
+      "learning_rate": 0.00019999924450514575,
+      "loss": 0.858,
+      "step": 35
+    },
+    {
+      "epoch": 0.026519337016574586,
+      "grad_norm": 0.27576470375061035,
+      "learning_rate": 0.00019999891208801263,
+      "loss": 0.8787,
+      "step": 36
+    },
+    {
+      "epoch": 0.02725598526703499,
+      "grad_norm": 0.3381502330303192,
+      "learning_rate": 0.00019999851923187563,
+      "loss": 0.924,
+      "step": 37
+    },
+    {
+      "epoch": 0.027992633517495397,
+      "grad_norm": 0.2836773097515106,
+      "learning_rate": 0.0001999980659369722,
+      "loss": 0.864,
+      "step": 38
+    },
+    {
+      "epoch": 0.028729281767955802,
+      "grad_norm": 0.25099191069602966,
+      "learning_rate": 0.00019999755220357628,
+      "loss": 0.8898,
+      "step": 39
+    },
+    {
+      "epoch": 0.029465930018416207,
+      "grad_norm": 0.27139487862586975,
+      "learning_rate": 0.00019999697803199843,
+      "loss": 0.865,
+      "step": 40
+    },
+    {
+      "epoch": 0.030202578268876613,
+      "grad_norm": 0.3184296786785126,
+      "learning_rate": 0.00019999634342258567,
+      "loss": 0.8712,
+      "step": 41
+    },
+    {
+      "epoch": 0.030939226519337018,
+      "grad_norm": 0.26392120122909546,
+      "learning_rate": 0.00019999564837572148,
+      "loss": 0.8369,
+      "step": 42
+    },
+    {
+      "epoch": 0.03167587476979742,
+      "grad_norm": 0.2767181694507599,
+      "learning_rate": 0.00019999489289182604,
+      "loss": 0.8852,
+      "step": 43
+    },
+    {
+      "epoch": 0.03241252302025783,
+      "grad_norm": 0.28793689608573914,
+      "learning_rate": 0.00019999407697135593,
+      "loss": 0.8736,
+      "step": 44
+    },
+    {
+      "epoch": 0.03314917127071823,
+      "grad_norm": 0.26001080870628357,
+      "learning_rate": 0.00019999320061480424,
+      "loss": 0.7787,
+      "step": 45
+    },
+    {
+      "epoch": 0.03388581952117864,
+      "grad_norm": 0.31403684616088867,
+      "learning_rate": 0.0001999922638227007,
+      "loss": 0.8567,
+      "step": 46
+    },
+    {
+      "epoch": 0.03462246777163904,
+      "grad_norm": 0.2915201783180237,
+      "learning_rate": 0.00019999126659561148,
+      "loss": 0.8611,
+      "step": 47
+    },
+    {
+      "epoch": 0.03535911602209945,
+      "grad_norm": 0.2969401776790619,
+      "learning_rate": 0.0001999902089341393,
+      "loss": 0.8481,
+      "step": 48
+    },
+    {
+      "epoch": 0.03609576427255985,
+      "grad_norm": 0.3141329288482666,
+      "learning_rate": 0.00019998909083892338,
+      "loss": 0.8658,
+      "step": 49
+    },
+    {
+      "epoch": 0.03683241252302026,
+      "grad_norm": 0.3031173646450043,
+      "learning_rate": 0.00019998791231063954,
+      "loss": 0.8331,
+      "step": 50
+    },
+    {
+      "epoch": 0.03756906077348066,
+      "grad_norm": 0.2515760064125061,
+      "learning_rate": 0.00019998667335000009,
+      "loss": 0.7917,
+      "step": 51
+    },
+    {
+      "epoch": 0.038305709023941065,
+      "grad_norm": 0.2739664614200592,
+      "learning_rate": 0.00019998537395775378,
+      "loss": 0.8586,
+      "step": 52
+    },
+    {
+      "epoch": 0.039042357274401474,
+      "grad_norm": 0.276120126247406,
+      "learning_rate": 0.00019998401413468602,
+      "loss": 0.787,
+      "step": 53
+    },
+    {
+      "epoch": 0.039779005524861875,
+      "grad_norm": 0.2712517976760864,
+      "learning_rate": 0.00019998259388161866,
+      "loss": 0.758,
+      "step": 54
+    },
+    {
+      "epoch": 0.040515653775322284,
+      "grad_norm": 0.28785476088523865,
+      "learning_rate": 0.00019998111319941009,
+      "loss": 0.779,
+      "step": 55
+    },
+    {
+      "epoch": 0.041252302025782686,
+      "grad_norm": 0.26709139347076416,
+      "learning_rate": 0.00019997957208895526,
+      "loss": 0.8495,
+      "step": 56
+    },
+    {
+      "epoch": 0.041988950276243095,
+      "grad_norm": 0.28016069531440735,
+      "learning_rate": 0.0001999779705511856,
+      "loss": 0.8042,
+      "step": 57
+    },
+    {
+      "epoch": 0.0427255985267035,
+      "grad_norm": 0.30033162236213684,
+      "learning_rate": 0.00019997630858706902,
+      "loss": 0.803,
+      "step": 58
+    },
+    {
+      "epoch": 0.043462246777163906,
+      "grad_norm": 0.2976544201374054,
+      "learning_rate": 0.00019997458619761007,
+      "loss": 0.8242,
+      "step": 59
+    },
+    {
+      "epoch": 0.04419889502762431,
+      "grad_norm": 0.30556997656822205,
+      "learning_rate": 0.00019997280338384974,
+      "loss": 0.797,
+      "step": 60
+    },
+    {
+      "epoch": 0.044935543278084716,
+      "grad_norm": 0.3246530294418335,
+      "learning_rate": 0.00019997096014686555,
+      "loss": 0.8576,
+      "step": 61
+    },
+    {
+      "epoch": 0.04567219152854512,
+      "grad_norm": 0.2900961637496948,
+      "learning_rate": 0.00019996905648777156,
+      "loss": 0.803,
+      "step": 62
+    },
+    {
+      "epoch": 0.04640883977900553,
+      "grad_norm": 0.28307750821113586,
+      "learning_rate": 0.00019996709240771834,
+      "loss": 0.7616,
+      "step": 63
+    },
+    {
+      "epoch": 0.04714548802946593,
+      "grad_norm": 0.31204795837402344,
+      "learning_rate": 0.0001999650679078929,
+      "loss": 0.7883,
+      "step": 64
+    },
+    {
+      "epoch": 0.04788213627992634,
+      "grad_norm": 0.2926878035068512,
+      "learning_rate": 0.00019996298298951897,
+      "loss": 0.7547,
+      "step": 65
+    },
+    {
+      "epoch": 0.04861878453038674,
+      "grad_norm": 0.26965269446372986,
+      "learning_rate": 0.00019996083765385655,
+      "loss": 0.807,
+      "step": 66
+    },
+    {
+      "epoch": 0.04935543278084715,
+      "grad_norm": 0.30936145782470703,
+      "learning_rate": 0.00019995863190220233,
+      "loss": 0.8217,
+      "step": 67
+    },
+    {
+      "epoch": 0.05009208103130755,
+      "grad_norm": 0.3084736466407776,
+      "learning_rate": 0.00019995636573588946,
+      "loss": 0.7949,
+      "step": 68
+    },
+    {
+      "epoch": 0.05082872928176796,
+      "grad_norm": 0.2856910228729248,
+      "learning_rate": 0.00019995403915628758,
+      "loss": 0.7871,
+      "step": 69
+    },
+    {
+      "epoch": 0.05156537753222836,
+      "grad_norm": 0.30720677971839905,
+      "learning_rate": 0.00019995165216480287,
+      "loss": 0.7813,
+      "step": 70
+    },
+    {
+      "epoch": 0.05230202578268876,
+      "grad_norm": 0.3214535713195801,
+      "learning_rate": 0.00019994920476287803,
+      "loss": 0.7059,
+      "step": 71
+    },
+    {
+      "epoch": 0.05303867403314917,
+      "grad_norm": 0.31556788086891174,
+      "learning_rate": 0.0001999466969519923,
+      "loss": 0.7798,
+      "step": 72
+    },
+    {
+      "epoch": 0.053775322283609574,
+      "grad_norm": 0.3107302188873291,
+      "learning_rate": 0.0001999441287336613,
+      "loss": 0.7093,
+      "step": 73
+    },
+    {
+      "epoch": 0.05451197053406998,
+      "grad_norm": 0.31890228390693665,
+      "learning_rate": 0.00019994150010943734,
+      "loss": 0.7975,
+      "step": 74
+    },
+    {
+      "epoch": 0.055248618784530384,
+      "grad_norm": 0.30909278988838196,
+      "learning_rate": 0.0001999388110809091,
+      "loss": 0.7854,
+      "step": 75
+    },
+    {
+      "epoch": 0.05598526703499079,
+      "grad_norm": 0.2844998836517334,
+      "learning_rate": 0.00019993606164970184,
+      "loss": 0.7994,
+      "step": 76
+    },
+    {
+      "epoch": 0.056721915285451195,
+      "grad_norm": 0.279021680355072,
+      "learning_rate": 0.0001999332518174773,
+      "loss": 0.7614,
+      "step": 77
+    },
+    {
+      "epoch": 0.057458563535911604,
+      "grad_norm": 0.29917311668395996,
+      "learning_rate": 0.00019993038158593374,
+      "loss": 0.6971,
+      "step": 78
+    },
+    {
+      "epoch": 0.058195211786372006,
+      "grad_norm": 0.28048795461654663,
+      "learning_rate": 0.0001999274509568059,
+      "loss": 0.7411,
+      "step": 79
+    },
+    {
+      "epoch": 0.058931860036832415,
+      "grad_norm": 0.2794869840145111,
+      "learning_rate": 0.0001999244599318651,
+      "loss": 0.7682,
+      "step": 80
+    },
+    {
+      "epoch": 0.05966850828729282,
+      "grad_norm": 0.2972111701965332,
+      "learning_rate": 0.00019992140851291903,
+      "loss": 0.6961,
+      "step": 81
+    },
+    {
+      "epoch": 0.060405156537753225,
+      "grad_norm": 0.29791033267974854,
+      "learning_rate": 0.00019991829670181196,
+      "loss": 0.7186,
+      "step": 82
+    },
+    {
+      "epoch": 0.06114180478821363,
+      "grad_norm": 0.37242040038108826,
+      "learning_rate": 0.00019991512450042475,
+      "loss": 0.825,
+      "step": 83
+    },
+    {
+      "epoch": 0.061878453038674036,
+      "grad_norm": 0.35006293654441833,
+      "learning_rate": 0.00019991189191067457,
+      "loss": 0.7969,
+      "step": 84
+    },
+    {
+      "epoch": 0.06261510128913444,
+      "grad_norm": 0.3174045979976654,
+      "learning_rate": 0.0001999085989345152,
+      "loss": 0.7855,
+      "step": 85
+    },
+    {
+      "epoch": 0.06335174953959484,
+      "grad_norm": 0.29581770300865173,
+      "learning_rate": 0.00019990524557393698,
+      "loss": 0.7082,
+      "step": 86
+    },
+    {
+      "epoch": 0.06408839779005525,
+      "grad_norm": 0.3099222779273987,
+      "learning_rate": 0.00019990183183096657,
+      "loss": 0.771,
+      "step": 87
+    },
+    {
+      "epoch": 0.06482504604051566,
+      "grad_norm": 0.28001388907432556,
+      "learning_rate": 0.00019989835770766728,
+      "loss": 0.6838,
+      "step": 88
+    },
+    {
+      "epoch": 0.06556169429097605,
+      "grad_norm": 0.2945444881916046,
+      "learning_rate": 0.00019989482320613888,
+      "loss": 0.7767,
+      "step": 89
+    },
+    {
+      "epoch": 0.06629834254143646,
+      "grad_norm": 0.26071885228157043,
+      "learning_rate": 0.00019989122832851755,
+      "loss": 0.7268,
+      "step": 90
+    },
+    {
+      "epoch": 0.06703499079189687,
+      "grad_norm": 0.2917459011077881,
+      "learning_rate": 0.00019988757307697606,
+      "loss": 0.7373,
+      "step": 91
+    },
+    {
+      "epoch": 0.06777163904235728,
+      "grad_norm": 0.2779064476490021,
+      "learning_rate": 0.0001998838574537236,
+      "loss": 0.6796,
+      "step": 92
+    },
+    {
+      "epoch": 0.06850828729281767,
+      "grad_norm": 0.3060937225818634,
+      "learning_rate": 0.00019988008146100593,
+      "loss": 0.7668,
+      "step": 93
+    },
+    {
+      "epoch": 0.06924493554327808,
+      "grad_norm": 0.36939218640327454,
+      "learning_rate": 0.0001998762451011052,
+      "loss": 0.8152,
+      "step": 94
+    },
+    {
+      "epoch": 0.06998158379373849,
+      "grad_norm": 0.2952641546726227,
+      "learning_rate": 0.00019987234837634012,
+      "loss": 0.8098,
+      "step": 95
+    },
+    {
+      "epoch": 0.0707182320441989,
+      "grad_norm": 0.29996800422668457,
+      "learning_rate": 0.00019986839128906584,
+      "loss": 0.7252,
+      "step": 96
+    },
+    {
+      "epoch": 0.0714548802946593,
+      "grad_norm": 0.31371477246284485,
+      "learning_rate": 0.00019986437384167402,
+      "loss": 0.7621,
+      "step": 97
+    },
+    {
+      "epoch": 0.0721915285451197,
+      "grad_norm": 0.3165487051010132,
+      "learning_rate": 0.0001998602960365928,
+      "loss": 0.8056,
+      "step": 98
+    },
+    {
+      "epoch": 0.07292817679558011,
+      "grad_norm": 0.2843554615974426,
+      "learning_rate": 0.0001998561578762868,
+      "loss": 0.7116,
+      "step": 99
+    },
+    {
+      "epoch": 0.07366482504604052,
+      "grad_norm": 0.2909322679042816,
+      "learning_rate": 0.00019985195936325707,
+      "loss": 0.757,
+      "step": 100
+    },
+    {
+      "epoch": 0.07440147329650092,
+      "grad_norm": 0.28609970211982727,
+      "learning_rate": 0.00019984770050004123,
+      "loss": 0.7086,
+      "step": 101
+    },
+    {
+      "epoch": 0.07513812154696133,
+      "grad_norm": 0.3476223945617676,
+      "learning_rate": 0.00019984338128921326,
+      "loss": 0.6919,
+      "step": 102
+    },
+    {
+      "epoch": 0.07587476979742173,
+      "grad_norm": 0.29145869612693787,
+      "learning_rate": 0.00019983900173338372,
+      "loss": 0.7425,
+      "step": 103
+    },
+    {
+      "epoch": 0.07661141804788213,
+      "grad_norm": 0.25402939319610596,
+      "learning_rate": 0.0001998345618351996,
+      "loss": 0.6566,
+      "step": 104
+    },
+    {
+      "epoch": 0.07734806629834254,
+      "grad_norm": 0.3344029188156128,
+      "learning_rate": 0.00019983006159734432,
+      "loss": 0.7738,
+      "step": 105
+    },
+    {
+      "epoch": 0.07808471454880295,
+      "grad_norm": 0.29914504289627075,
+      "learning_rate": 0.00019982550102253785,
+      "loss": 0.7981,
+      "step": 106
+    },
+    {
+      "epoch": 0.07882136279926336,
+      "grad_norm": 0.3142239451408386,
+      "learning_rate": 0.00019982088011353657,
+      "loss": 0.6684,
+      "step": 107
+    },
+    {
+      "epoch": 0.07955801104972375,
+      "grad_norm": 0.36736083030700684,
+      "learning_rate": 0.00019981619887313333,
+      "loss": 0.6815,
+      "step": 108
+    },
+    {
+      "epoch": 0.08029465930018416,
+      "grad_norm": 0.31467515230178833,
+      "learning_rate": 0.0001998114573041575,
+      "loss": 0.7808,
+      "step": 109
+    },
+    {
+      "epoch": 0.08103130755064457,
+      "grad_norm": 0.28194478154182434,
+      "learning_rate": 0.00019980665540947484,
+      "loss": 0.705,
+      "step": 110
+    },
+    {
+      "epoch": 0.08176795580110498,
+      "grad_norm": 0.33793193101882935,
+      "learning_rate": 0.00019980179319198756,
+      "loss": 0.6696,
+      "step": 111
+    },
+    {
+      "epoch": 0.08250460405156537,
+      "grad_norm": 0.3227858543395996,
+      "learning_rate": 0.00019979687065463443,
+      "loss": 0.7472,
+      "step": 112
+    },
+    {
+      "epoch": 0.08324125230202578,
+      "grad_norm": 0.30705466866493225,
+      "learning_rate": 0.0001997918878003906,
+      "loss": 0.7565,
+      "step": 113
+    },
+    {
+      "epoch": 0.08397790055248619,
+      "grad_norm": 0.30595332384109497,
+      "learning_rate": 0.00019978684463226764,
+      "loss": 0.7469,
+      "step": 114
+    },
+    {
+      "epoch": 0.0847145488029466,
+      "grad_norm": 0.3414095342159271,
+      "learning_rate": 0.0001997817411533137,
+      "loss": 0.7089,
+      "step": 115
+    },
+    {
+      "epoch": 0.085451197053407,
+      "grad_norm": 0.3420286476612091,
+      "learning_rate": 0.00019977657736661324,
+      "loss": 0.7702,
+      "step": 116
+    },
+    {
+      "epoch": 0.0861878453038674,
+      "grad_norm": 0.2991967499256134,
+      "learning_rate": 0.0001997713532752873,
+      "loss": 0.7767,
+      "step": 117
+    },
+    {
+      "epoch": 0.08692449355432781,
+      "grad_norm": 0.33018970489501953,
+      "learning_rate": 0.00019976606888249323,
+      "loss": 0.792,
+      "step": 118
+    },
+    {
+      "epoch": 0.08766114180478822,
+      "grad_norm": 0.27012234926223755,
+      "learning_rate": 0.00019976072419142495,
+      "loss": 0.6733,
+      "step": 119
+    },
+    {
+      "epoch": 0.08839779005524862,
+      "grad_norm": 0.2963539659976959,
+      "learning_rate": 0.00019975531920531276,
+      "loss": 0.719,
+      "step": 120
+    },
+    {
+      "epoch": 0.08913443830570902,
+      "grad_norm": 0.32407429814338684,
+      "learning_rate": 0.00019974985392742342,
+      "loss": 0.7758,
+      "step": 121
+    },
+    {
+      "epoch": 0.08987108655616943,
+      "grad_norm": 0.2743798792362213,
+      "learning_rate": 0.0001997443283610601,
+      "loss": 0.7117,
+      "step": 122
+    },
+    {
+      "epoch": 0.09060773480662983,
+      "grad_norm": 0.3306395411491394,
+      "learning_rate": 0.0001997387425095625,
+      "loss": 0.677,
+      "step": 123
+    },
+    {
+      "epoch": 0.09134438305709024,
+      "grad_norm": 0.268968403339386,
+      "learning_rate": 0.0001997330963763066,
+      "loss": 0.6439,
+      "step": 124
+    },
+    {
+      "epoch": 0.09208103130755065,
+      "grad_norm": 0.29267922043800354,
+      "learning_rate": 0.00019972738996470494,
+      "loss": 0.627,
+      "step": 125
+    },
+    {
+      "epoch": 0.09281767955801105,
+      "grad_norm": 0.33110713958740234,
+      "learning_rate": 0.0001997216232782065,
+      "loss": 0.7298,
+      "step": 126
+    },
+    {
+      "epoch": 0.09355432780847145,
+      "grad_norm": 0.2938537895679474,
+      "learning_rate": 0.0001997157963202966,
+      "loss": 0.7129,
+      "step": 127
+    },
+    {
+      "epoch": 0.09429097605893186,
+      "grad_norm": 0.2977161407470703,
+      "learning_rate": 0.00019970990909449704,
+      "loss": 0.7154,
+      "step": 128
+    },
+    {
+      "epoch": 0.09502762430939227,
+      "grad_norm": 0.24176570773124695,
+      "learning_rate": 0.000199703961604366,
+      "loss": 0.7216,
+      "step": 129
+    },
+    {
+      "epoch": 0.09576427255985268,
+      "grad_norm": 0.3133772611618042,
+      "learning_rate": 0.0001996979538534982,
+      "loss": 0.659,
+      "step": 130
+    },
+    {
+      "epoch": 0.09650092081031307,
+      "grad_norm": 0.3389708995819092,
+      "learning_rate": 0.00019969188584552467,
+      "loss": 0.794,
+      "step": 131
+    },
+    {
+      "epoch": 0.09723756906077348,
+      "grad_norm": 0.3355901539325714,
+      "learning_rate": 0.0001996857575841129,
+      "loss": 0.6453,
+      "step": 132
+    },
+    {
+      "epoch": 0.09797421731123389,
+      "grad_norm": 0.27540209889411926,
+      "learning_rate": 0.00019967956907296675,
+      "loss": 0.6572,
+      "step": 133
+    },
+    {
+      "epoch": 0.0987108655616943,
+      "grad_norm": 0.2828402519226074,
+      "learning_rate": 0.0001996733203158266,
+      "loss": 0.6854,
+      "step": 134
+    },
+    {
+      "epoch": 0.09944751381215469,
+      "grad_norm": 0.34255996346473694,
+      "learning_rate": 0.00019966701131646914,
+      "loss": 0.7159,
+      "step": 135
+    },
+    {
+      "epoch": 0.1001841620626151,
+      "grad_norm": 0.31941506266593933,
+      "learning_rate": 0.0001996606420787075,
+      "loss": 0.6888,
+      "step": 136
+    },
+    {
+      "epoch": 0.10092081031307551,
+      "grad_norm": 0.34405437111854553,
+      "learning_rate": 0.00019965421260639124,
+      "loss": 0.7615,
+      "step": 137
+    },
+    {
+      "epoch": 0.10165745856353592,
+      "grad_norm": 0.29358065128326416,
+      "learning_rate": 0.00019964772290340633,
+      "loss": 0.6478,
+      "step": 138
+    },
+    {
+      "epoch": 0.10239410681399631,
+      "grad_norm": 0.2881005108356476,
+      "learning_rate": 0.00019964117297367512,
+      "loss": 0.7167,
+      "step": 139
+    },
+    {
+      "epoch": 0.10313075506445672,
+      "grad_norm": 0.3143142759799957,
+      "learning_rate": 0.00019963456282115632,
+      "loss": 0.5813,
+      "step": 140
+    },
+    {
+      "epoch": 0.10386740331491713,
+      "grad_norm": 0.30442625284194946,
+      "learning_rate": 0.0001996278924498451,
+      "loss": 0.7286,
+      "step": 141
+    },
+    {
+      "epoch": 0.10460405156537753,
+      "grad_norm": 0.2968827784061432,
+      "learning_rate": 0.00019962116186377304,
+      "loss": 0.7118,
+      "step": 142
+    },
+    {
+      "epoch": 0.10534069981583793,
+      "grad_norm": 0.293175607919693,
+      "learning_rate": 0.00019961437106700807,
+      "loss": 0.7591,
+      "step": 143
+    },
+    {
+      "epoch": 0.10607734806629834,
+      "grad_norm": 0.283244788646698,
+      "learning_rate": 0.00019960752006365452,
+      "loss": 0.6542,
+      "step": 144
+    },
+    {
+      "epoch": 0.10681399631675875,
+      "grad_norm": 0.2727886438369751,
+      "learning_rate": 0.00019960060885785313,
+      "loss": 0.7061,
+      "step": 145
+    },
+    {
+      "epoch": 0.10755064456721915,
+      "grad_norm": 0.3356839120388031,
+      "learning_rate": 0.00019959363745378097,
+      "loss": 0.7102,
+      "step": 146
+    },
+    {
+      "epoch": 0.10828729281767956,
+      "grad_norm": 0.28260713815689087,
+      "learning_rate": 0.00019958660585565156,
+      "loss": 0.6925,
+      "step": 147
+    },
+    {
+      "epoch": 0.10902394106813997,
+      "grad_norm": 0.3257836103439331,
+      "learning_rate": 0.0001995795140677148,
+      "loss": 0.7314,
+      "step": 148
+    },
+    {
+      "epoch": 0.10976058931860037,
+      "grad_norm": 0.28633037209510803,
+      "learning_rate": 0.0001995723620942569,
+      "loss": 0.6382,
+      "step": 149
+    },
+    {
+      "epoch": 0.11049723756906077,
+      "grad_norm": 0.2877746522426605,
+      "learning_rate": 0.0001995651499396005,
+      "loss": 0.654,
+      "step": 150
+    },
+    {
+      "epoch": 0.11123388581952118,
+      "grad_norm": 0.347207248210907,
+      "learning_rate": 0.0001995578776081046,
+      "loss": 0.6402,
+      "step": 151
+    },
+    {
+      "epoch": 0.11197053406998159,
+      "grad_norm": 0.28628456592559814,
+      "learning_rate": 0.00019955054510416458,
+      "loss": 0.6642,
+      "step": 152
+    },
+    {
+      "epoch": 0.112707182320442,
+      "grad_norm": 0.3181871175765991,
+      "learning_rate": 0.00019954315243221217,
+      "loss": 0.6107,
+      "step": 153
+    },
+    {
+      "epoch": 0.11344383057090239,
+      "grad_norm": 0.339148610830307,
+      "learning_rate": 0.0001995356995967155,
+      "loss": 0.7438,
+      "step": 154
+    },
+    {
+      "epoch": 0.1141804788213628,
+      "grad_norm": 0.31777989864349365,
+      "learning_rate": 0.00019952818660217903,
+      "loss": 0.6979,
+      "step": 155
+    },
+    {
+      "epoch": 0.11491712707182321,
+      "grad_norm": 0.2775622010231018,
+      "learning_rate": 0.00019952061345314355,
+      "loss": 0.7056,
+      "step": 156
+    },
+    {
+      "epoch": 0.1156537753222836,
+      "grad_norm": 0.2825548052787781,
+      "learning_rate": 0.0001995129801541863,
+      "loss": 0.7069,
+      "step": 157
+    },
+    {
+      "epoch": 0.11639042357274401,
+      "grad_norm": 0.3609641492366791,
+      "learning_rate": 0.0001995052867099208,
+      "loss": 0.7159,
+      "step": 158
+    },
+    {
+      "epoch": 0.11712707182320442,
+      "grad_norm": 0.32540053129196167,
+      "learning_rate": 0.0001994975331249969,
+      "loss": 0.7354,
+      "step": 159
+    },
+    {
+      "epoch": 0.11786372007366483,
+      "grad_norm": 0.2758769392967224,
+      "learning_rate": 0.0001994897194041009,
+      "loss": 0.6599,
+      "step": 160
+    },
+    {
+      "epoch": 0.11860036832412522,
+      "grad_norm": 0.3288959264755249,
+      "learning_rate": 0.00019948184555195538,
+      "loss": 0.7291,
+      "step": 161
+    },
+    {
+      "epoch": 0.11933701657458563,
+      "grad_norm": 0.3150870203971863,
+      "learning_rate": 0.00019947391157331925,
+      "loss": 0.7996,
+      "step": 162
+    },
+    {
+      "epoch": 0.12007366482504604,
+      "grad_norm": 0.31521302461624146,
+      "learning_rate": 0.00019946591747298776,
+      "loss": 0.6422,
+      "step": 163
+    },
+    {
+      "epoch": 0.12081031307550645,
+      "grad_norm": 0.2747270464897156,
+      "learning_rate": 0.00019945786325579259,
+      "loss": 0.685,
+      "step": 164
+    },
+    {
+      "epoch": 0.12154696132596685,
+      "grad_norm": 0.3266451060771942,
+      "learning_rate": 0.00019944974892660157,
+      "loss": 0.6447,
+      "step": 165
+    },
+    {
+      "epoch": 0.12228360957642725,
+      "grad_norm": 0.2808232009410858,
+      "learning_rate": 0.00019944157449031908,
+      "loss": 0.7124,
+      "step": 166
+    },
+    {
+      "epoch": 0.12302025782688766,
+      "grad_norm": 0.3566378355026245,
+      "learning_rate": 0.00019943333995188568,
+      "loss": 0.6288,
+      "step": 167
+    },
+    {
+      "epoch": 0.12375690607734807,
+      "grad_norm": 0.2801951467990875,
+      "learning_rate": 0.00019942504531627827,
+      "loss": 0.7395,
+      "step": 168
+    },
+    {
+      "epoch": 0.12449355432780847,
+      "grad_norm": 0.32879137992858887,
+      "learning_rate": 0.00019941669058851015,
+      "loss": 0.7011,
+      "step": 169
+    },
+    {
+      "epoch": 0.1252302025782689,
+      "grad_norm": 0.3209787607192993,
+      "learning_rate": 0.00019940827577363086,
+      "loss": 0.6701,
+      "step": 170
+    },
+    {
+      "epoch": 0.12596685082872927,
+      "grad_norm": 0.36623483896255493,
+      "learning_rate": 0.00019939980087672627,
+      "loss": 0.7135,
+      "step": 171
+    },
+    {
+      "epoch": 0.12670349907918968,
+      "grad_norm": 0.37993544340133667,
+      "learning_rate": 0.00019939126590291862,
+      "loss": 0.7231,
+      "step": 172
+    },
+    {
+      "epoch": 0.1274401473296501,
+      "grad_norm": 0.30625516176223755,
+      "learning_rate": 0.00019938267085736636,
+      "loss": 0.5544,
+      "step": 173
+    },
+    {
+      "epoch": 0.1281767955801105,
+      "grad_norm": 0.2693084180355072,
+      "learning_rate": 0.00019937401574526438,
+      "loss": 0.7173,
+      "step": 174
+    },
+    {
+      "epoch": 0.1289134438305709,
+      "grad_norm": 0.31314727663993835,
+      "learning_rate": 0.00019936530057184374,
+      "loss": 0.7173,
+      "step": 175
+    },
+    {
+      "epoch": 0.12965009208103132,
+      "grad_norm": 0.33976224064826965,
+      "learning_rate": 0.00019935652534237193,
+      "loss": 0.721,
+      "step": 176
+    },
+    {
+      "epoch": 0.13038674033149172,
+      "grad_norm": 0.28331294655799866,
+      "learning_rate": 0.0001993476900621526,
+      "loss": 0.6468,
+      "step": 177
+    },
+    {
+      "epoch": 0.1311233885819521,
+      "grad_norm": 0.3256126046180725,
+      "learning_rate": 0.00019933879473652577,
+      "loss": 0.7391,
+      "step": 178
+    },
+    {
+      "epoch": 0.1318600368324125,
+      "grad_norm": 0.24356336891651154,
+      "learning_rate": 0.0001993298393708678,
+      "loss": 0.5802,
+      "step": 179
+    },
+    {
+      "epoch": 0.13259668508287292,
+      "grad_norm": 0.3167095184326172,
+      "learning_rate": 0.00019932082397059123,
+      "loss": 0.6943,
+      "step": 180
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.33187493681907654,
+      "learning_rate": 0.00019931174854114492,
+      "loss": 0.6605,
+      "step": 181
+    },
+    {
+      "epoch": 0.13406998158379374,
+      "grad_norm": 0.2955477237701416,
+      "learning_rate": 0.0001993026130880141,
+      "loss": 0.7117,
+      "step": 182
+    },
+    {
+      "epoch": 0.13480662983425415,
+      "grad_norm": 0.3144208788871765,
+      "learning_rate": 0.00019929341761672017,
+      "loss": 0.6282,
+      "step": 183
+    },
+    {
+      "epoch": 0.13554327808471456,
+      "grad_norm": 0.2676321566104889,
+      "learning_rate": 0.00019928416213282083,
+      "loss": 0.5672,
+      "step": 184
+    },
+    {
+      "epoch": 0.13627992633517497,
+      "grad_norm": 0.3019046187400818,
+      "learning_rate": 0.00019927484664191005,
+      "loss": 0.6008,
+      "step": 185
+    },
+    {
+      "epoch": 0.13701657458563535,
+      "grad_norm": 0.4058505892753601,
+      "learning_rate": 0.00019926547114961814,
+      "loss": 0.7004,
+      "step": 186
+    },
+    {
+      "epoch": 0.13775322283609576,
+      "grad_norm": 0.3833027184009552,
+      "learning_rate": 0.00019925603566161155,
+      "loss": 0.661,
+      "step": 187
+    },
+    {
+      "epoch": 0.13848987108655617,
+      "grad_norm": 0.3298625946044922,
+      "learning_rate": 0.0001992465401835931,
+      "loss": 0.5752,
+      "step": 188
+    },
+    {
+      "epoch": 0.13922651933701657,
+      "grad_norm": 0.3053440451622009,
+      "learning_rate": 0.00019923698472130183,
+      "loss": 0.7186,
+      "step": 189
+    },
+    {
+      "epoch": 0.13996316758747698,
+      "grad_norm": 0.30657535791397095,
+      "learning_rate": 0.000199227369280513,
+      "loss": 0.7074,
+      "step": 190
+    },
+    {
+      "epoch": 0.1406998158379374,
+      "grad_norm": 0.3137226998806,
+      "learning_rate": 0.00019921769386703817,
+      "loss": 0.7061,
+      "step": 191
+    },
+    {
+      "epoch": 0.1414364640883978,
+      "grad_norm": 0.26916223764419556,
+      "learning_rate": 0.00019920795848672512,
+      "loss": 0.6763,
+      "step": 192
+    },
+    {
+      "epoch": 0.14217311233885818,
+      "grad_norm": 0.30081868171691895,
+      "learning_rate": 0.00019919816314545785,
+      "loss": 0.6015,
+      "step": 193
+    },
+    {
+      "epoch": 0.1429097605893186,
+      "grad_norm": 0.32577744126319885,
+      "learning_rate": 0.00019918830784915667,
+      "loss": 0.6972,
+      "step": 194
+    },
+    {
+      "epoch": 0.143646408839779,
+      "grad_norm": 0.26235300302505493,
+      "learning_rate": 0.0001991783926037781,
+      "loss": 0.7166,
+      "step": 195
+    },
+    {
+      "epoch": 0.1443830570902394,
+      "grad_norm": 0.31801119446754456,
+      "learning_rate": 0.00019916841741531485,
+      "loss": 0.7071,
+      "step": 196
+    },
+    {
+      "epoch": 0.14511970534069982,
+      "grad_norm": 0.29373010993003845,
+      "learning_rate": 0.0001991583822897959,
+      "loss": 0.7695,
+      "step": 197
+    },
+    {
+      "epoch": 0.14585635359116023,
+      "grad_norm": 0.28376370668411255,
+      "learning_rate": 0.00019914828723328643,
+      "loss": 0.6963,
+      "step": 198
+    },
+    {
+      "epoch": 0.14659300184162063,
+      "grad_norm": 0.291465163230896,
+      "learning_rate": 0.0001991381322518879,
+      "loss": 0.6821,
+      "step": 199
+    },
+    {
+      "epoch": 0.14732965009208104,
+      "grad_norm": 0.33115917444229126,
+      "learning_rate": 0.00019912791735173787,
+      "loss": 0.7368,
+      "step": 200
+    },
+    {
+      "epoch": 0.14732965009208104,
+      "eval_loss": 0.7152236104011536,
+      "eval_runtime": 6.8871,
+      "eval_samples_per_second": 31.798,
+      "eval_steps_per_second": 2.033,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 4071,
+  "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": 2.039265734374195e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ab8dce95e57ea1529f24f6a3353e7d9934d819d7b76c2a7da57d009ac59fe61
+size 6776