Training in progress, epoch 0, checkpoint

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: HuggingFaceM4/tiny-random-LlamaForCausalLM
+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": "HuggingFaceM4/tiny-random-LlamaForCausalLM",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "up_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:ee687c6b4d3e5ead2dffe570df735ac824ae830a7629b47a0b2397c525b02930
+size 27024

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c7ac929589bd59efd8c74838ed47e6c16ae42a989cb7b51f09f61c0c64bb092
+size 63910

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d629fd5ba76e13469b4aa16dbfd3640d000777b913859f3961e56315077ff55
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b529c6dc606f7c4af8932b65821eaa427faee70c004932409321363fc742ca82
+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": "<unk>",
+    "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 +1,41 @@
+{
+  "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": true,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,1406 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9961685823754789,
+  "eval_steps": 500,
+  "global_step": 195,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005108556832694764,
+      "grad_norm": 0.06296706199645996,
+      "learning_rate": 0.00019998715457999314,
+      "loss": 10.3788,
+      "step": 1
+    },
+    {
+      "epoch": 0.010217113665389528,
+      "grad_norm": 0.06155822426080704,
+      "learning_rate": 0.0001999486216200688,
+      "loss": 10.3876,
+      "step": 2
+    },
+    {
+      "epoch": 0.01532567049808429,
+      "grad_norm": 0.04243969917297363,
+      "learning_rate": 0.0001998844110196681,
+      "loss": 10.383,
+      "step": 3
+    },
+    {
+      "epoch": 0.020434227330779056,
+      "grad_norm": 0.08324499428272247,
+      "learning_rate": 0.00019979453927503364,
+      "loss": 10.3854,
+      "step": 4
+    },
+    {
+      "epoch": 0.02554278416347382,
+      "grad_norm": 0.06429007649421692,
+      "learning_rate": 0.00019967902947497156,
+      "loss": 10.3783,
+      "step": 5
+    },
+    {
+      "epoch": 0.03065134099616858,
+      "grad_norm": 0.06722702831029892,
+      "learning_rate": 0.00019953791129491983,
+      "loss": 10.3771,
+      "step": 6
+    },
+    {
+      "epoch": 0.035759897828863345,
+      "grad_norm": 0.04376779869198799,
+      "learning_rate": 0.00019937122098932428,
+      "loss": 10.3768,
+      "step": 7
+    },
+    {
+      "epoch": 0.04086845466155811,
+      "grad_norm": 0.057710230350494385,
+      "learning_rate": 0.0001991790013823246,
+      "loss": 10.3731,
+      "step": 8
+    },
+    {
+      "epoch": 0.04597701149425287,
+      "grad_norm": 0.06998121738433838,
+      "learning_rate": 0.00019896130185675261,
+      "loss": 10.3783,
+      "step": 9
+    },
+    {
+      "epoch": 0.05108556832694764,
+      "grad_norm": 0.06011413037776947,
+      "learning_rate": 0.00019871817834144504,
+      "loss": 10.3773,
+      "step": 10
+    },
+    {
+      "epoch": 0.0561941251596424,
+      "grad_norm": 0.05903960019350052,
+      "learning_rate": 0.00019844969329687527,
+      "loss": 10.379,
+      "step": 11
+    },
+    {
+      "epoch": 0.06130268199233716,
+      "grad_norm": 0.06023373827338219,
+      "learning_rate": 0.00019815591569910654,
+      "loss": 10.3718,
+      "step": 12
+    },
+    {
+      "epoch": 0.06641123882503193,
+      "grad_norm": 0.07594680041074753,
+      "learning_rate": 0.00019783692102207155,
+      "loss": 10.3802,
+      "step": 13
+    },
+    {
+      "epoch": 0.07151979565772669,
+      "grad_norm": 0.07722143083810806,
+      "learning_rate": 0.00019749279121818235,
+      "loss": 10.3835,
+      "step": 14
+    },
+    {
+      "epoch": 0.07662835249042145,
+      "grad_norm": 0.06465964019298553,
+      "learning_rate": 0.0001971236146972764,
+      "loss": 10.3811,
+      "step": 15
+    },
+    {
+      "epoch": 0.08173690932311622,
+      "grad_norm": 0.08145278692245483,
+      "learning_rate": 0.00019672948630390294,
+      "loss": 10.3771,
+      "step": 16
+    },
+    {
+      "epoch": 0.08684546615581099,
+      "grad_norm": 0.06017107516527176,
+      "learning_rate": 0.00019631050729295707,
+      "loss": 10.3816,
+      "step": 17
+    },
+    {
+      "epoch": 0.09195402298850575,
+      "grad_norm": 0.07251092046499252,
+      "learning_rate": 0.00019586678530366606,
+      "loss": 10.3833,
+      "step": 18
+    },
+    {
+      "epoch": 0.0970625798212005,
+      "grad_norm": 0.04419001191854477,
+      "learning_rate": 0.00019539843433193639,
+      "loss": 10.3781,
+      "step": 19
+    },
+    {
+      "epoch": 0.10217113665389528,
+      "grad_norm": 0.0600612536072731,
+      "learning_rate": 0.00019490557470106686,
+      "loss": 10.3828,
+      "step": 20
+    },
+    {
+      "epoch": 0.10727969348659004,
+      "grad_norm": 0.07362791895866394,
+      "learning_rate": 0.00019438833303083678,
+      "loss": 10.3844,
+      "step": 21
+    },
+    {
+      "epoch": 0.1123882503192848,
+      "grad_norm": 0.06240883469581604,
+      "learning_rate": 0.00019384684220497605,
+      "loss": 10.3754,
+      "step": 22
+    },
+    {
+      "epoch": 0.11749680715197956,
+      "grad_norm": 0.06827075779438019,
+      "learning_rate": 0.0001932812413370265,
+      "loss": 10.3727,
+      "step": 23
+    },
+    {
+      "epoch": 0.12260536398467432,
+      "grad_norm": 0.06609390676021576,
+      "learning_rate": 0.0001926916757346022,
+      "loss": 10.3814,
+      "step": 24
+    },
+    {
+      "epoch": 0.1277139208173691,
+      "grad_norm": 0.06842462718486786,
+      "learning_rate": 0.00019207829686205882,
+      "loss": 10.3716,
+      "step": 25
+    },
+    {
+      "epoch": 0.13282247765006386,
+      "grad_norm": 0.06660367548465729,
+      "learning_rate": 0.00019144126230158127,
+      "loss": 10.3826,
+      "step": 26
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 0.08344798535108566,
+      "learning_rate": 0.00019078073571269922,
+      "loss": 10.3783,
+      "step": 27
+    },
+    {
+      "epoch": 0.14303959131545338,
+      "grad_norm": 0.08380083739757538,
+      "learning_rate": 0.0001900968867902419,
+      "loss": 10.3732,
+      "step": 28
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.0946107804775238,
+      "learning_rate": 0.00018938989122074197,
+      "loss": 10.37,
+      "step": 29
+    },
+    {
+      "epoch": 0.1532567049808429,
+      "grad_norm": 0.06197074055671692,
+      "learning_rate": 0.00018865993063730004,
+      "loss": 10.3761,
+      "step": 30
+    },
+    {
+      "epoch": 0.1583652618135377,
+      "grad_norm": 0.0819283053278923,
+      "learning_rate": 0.00018790719257292174,
+      "loss": 10.371,
+      "step": 31
+    },
+    {
+      "epoch": 0.16347381864623245,
+      "grad_norm": 0.09213186800479889,
+      "learning_rate": 0.00018713187041233896,
+      "loss": 10.3725,
+      "step": 32
+    },
+    {
+      "epoch": 0.1685823754789272,
+      "grad_norm": 0.08193743228912354,
+      "learning_rate": 0.00018633416334232753,
+      "loss": 10.3725,
+      "step": 33
+    },
+    {
+      "epoch": 0.17369093231162197,
+      "grad_norm": 0.07233049720525742,
+      "learning_rate": 0.00018551427630053463,
+      "loss": 10.374,
+      "step": 34
+    },
+    {
+      "epoch": 0.17879948914431673,
+      "grad_norm": 0.09028832614421844,
+      "learning_rate": 0.00018467241992282843,
+      "loss": 10.3732,
+      "step": 35
+    },
+    {
+      "epoch": 0.1839080459770115,
+      "grad_norm": 0.10519926995038986,
+      "learning_rate": 0.00018380881048918405,
+      "loss": 10.3769,
+      "step": 36
+    },
+    {
+      "epoch": 0.18901660280970625,
+      "grad_norm": 0.06255685538053513,
+      "learning_rate": 0.0001829236698681195,
+      "loss": 10.378,
+      "step": 37
+    },
+    {
+      "epoch": 0.194125159642401,
+      "grad_norm": 0.08233755081892014,
+      "learning_rate": 0.0001820172254596956,
+      "loss": 10.3704,
+      "step": 38
+    },
+    {
+      "epoch": 0.19923371647509577,
+      "grad_norm": 0.05263242870569229,
+      "learning_rate": 0.0001810897101370951,
+      "loss": 10.3834,
+      "step": 39
+    },
+    {
+      "epoch": 0.20434227330779056,
+      "grad_norm": 0.1387779265642166,
+      "learning_rate": 0.00018014136218679567,
+      "loss": 10.3707,
+      "step": 40
+    },
+    {
+      "epoch": 0.20945083014048532,
+      "grad_norm": 0.08574540168046951,
+      "learning_rate": 0.000179172425247352,
+      "loss": 10.377,
+      "step": 41
+    },
+    {
+      "epoch": 0.21455938697318008,
+      "grad_norm": 0.06211940944194794,
+      "learning_rate": 0.000178183148246803,
+      "loss": 10.3647,
+      "step": 42
+    },
+    {
+      "epoch": 0.21966794380587484,
+      "grad_norm": 0.09258867800235748,
+      "learning_rate": 0.00017717378533872017,
+      "loss": 10.3722,
+      "step": 43
+    },
+    {
+      "epoch": 0.2247765006385696,
+      "grad_norm": 0.08623415976762772,
+      "learning_rate": 0.00017614459583691346,
+      "loss": 10.3754,
+      "step": 44
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "grad_norm": 0.1082397997379303,
+      "learning_rate": 0.00017509584414881113,
+      "loss": 10.3736,
+      "step": 45
+    },
+    {
+      "epoch": 0.23499361430395913,
+      "grad_norm": 0.0896887555718422,
+      "learning_rate": 0.00017402779970753155,
+      "loss": 10.3732,
+      "step": 46
+    },
+    {
+      "epoch": 0.24010217113665389,
+      "grad_norm": 0.09336112439632416,
+      "learning_rate": 0.00017294073690266344,
+      "loss": 10.373,
+      "step": 47
+    },
+    {
+      "epoch": 0.24521072796934865,
+      "grad_norm": 0.08002498000860214,
+      "learning_rate": 0.00017183493500977278,
+      "loss": 10.3689,
+      "step": 48
+    },
+    {
+      "epoch": 0.2503192848020434,
+      "grad_norm": 0.07161203771829605,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 10.3702,
+      "step": 49
+    },
+    {
+      "epoch": 0.2554278416347382,
+      "grad_norm": 0.121755450963974,
+      "learning_rate": 0.00016956825506034867,
+      "loss": 10.3821,
+      "step": 50
+    },
+    {
+      "epoch": 0.26053639846743293,
+      "grad_norm": 0.08657146245241165,
+      "learning_rate": 0.00016840795933293463,
+      "loss": 10.3803,
+      "step": 51
+    },
+    {
+      "epoch": 0.2656449553001277,
+      "grad_norm": 0.07844258099794388,
+      "learning_rate": 0.0001672300890261317,
+      "loss": 10.3719,
+      "step": 52
+    },
+    {
+      "epoch": 0.2707535121328225,
+      "grad_norm": 0.08680905401706696,
+      "learning_rate": 0.00016603494674471593,
+      "loss": 10.3649,
+      "step": 53
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 0.10259506851434708,
+      "learning_rate": 0.00016482283953077887,
+      "loss": 10.3725,
+      "step": 54
+    },
+    {
+      "epoch": 0.280970625798212,
+      "grad_norm": 0.08116184920072556,
+      "learning_rate": 0.00016359407878484552,
+      "loss": 10.3681,
+      "step": 55
+    },
+    {
+      "epoch": 0.28607918263090676,
+      "grad_norm": 0.06668803840875626,
+      "learning_rate": 0.00016234898018587337,
+      "loss": 10.3731,
+      "step": 56
+    },
+    {
+      "epoch": 0.29118773946360155,
+      "grad_norm": 0.08566579967737198,
+      "learning_rate": 0.00016108786361015143,
+      "loss": 10.37,
+      "step": 57
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.11228417605161667,
+      "learning_rate": 0.00015981105304912162,
+      "loss": 10.3716,
+      "step": 58
+    },
+    {
+      "epoch": 0.30140485312899107,
+      "grad_norm": 0.07987914979457855,
+      "learning_rate": 0.00015851887652614237,
+      "loss": 10.3712,
+      "step": 59
+    },
+    {
+      "epoch": 0.3065134099616858,
+      "grad_norm": 0.1201016902923584,
+      "learning_rate": 0.00015721166601221698,
+      "loss": 10.3647,
+      "step": 60
+    },
+    {
+      "epoch": 0.3116219667943806,
+      "grad_norm": 0.08329416066408157,
+      "learning_rate": 0.00015588975734070717,
+      "loss": 10.3792,
+      "step": 61
+    },
+    {
+      "epoch": 0.3167305236270754,
+      "grad_norm": 0.10588457435369492,
+      "learning_rate": 0.00015455349012105486,
+      "loss": 10.3688,
+      "step": 62
+    },
+    {
+      "epoch": 0.3218390804597701,
+      "grad_norm": 0.12081307172775269,
+      "learning_rate": 0.00015320320765153367,
+      "loss": 10.3642,
+      "step": 63
+    },
+    {
+      "epoch": 0.3269476372924649,
+      "grad_norm": 0.08195498585700989,
+      "learning_rate": 0.00015183925683105254,
+      "loss": 10.3682,
+      "step": 64
+    },
+    {
+      "epoch": 0.33205619412515963,
+      "grad_norm": 0.06908663362264633,
+      "learning_rate": 0.0001504619880700346,
+      "loss": 10.367,
+      "step": 65
+    },
+    {
+      "epoch": 0.3371647509578544,
+      "grad_norm": 0.09832872450351715,
+      "learning_rate": 0.0001490717552003938,
+      "loss": 10.377,
+      "step": 66
+    },
+    {
+      "epoch": 0.34227330779054915,
+      "grad_norm": 0.0903470367193222,
+      "learning_rate": 0.00014766891538463254,
+      "loss": 10.3772,
+      "step": 67
+    },
+    {
+      "epoch": 0.34738186462324394,
+      "grad_norm": 0.09079986065626144,
+      "learning_rate": 0.00014625382902408356,
+      "loss": 10.366,
+      "step": 68
+    },
+    {
+      "epoch": 0.3524904214559387,
+      "grad_norm": 0.05147509649395943,
+      "learning_rate": 0.0001448268596663197,
+      "loss": 10.3652,
+      "step": 69
+    },
+    {
+      "epoch": 0.35759897828863346,
+      "grad_norm": 0.14060315489768982,
+      "learning_rate": 0.00014338837391175582,
+      "loss": 10.3629,
+      "step": 70
+    },
+    {
+      "epoch": 0.36270753512132825,
+      "grad_norm": 0.11259511113166809,
+      "learning_rate": 0.0001419387413194657,
+      "loss": 10.3691,
+      "step": 71
+    },
+    {
+      "epoch": 0.367816091954023,
+      "grad_norm": 0.09399597346782684,
+      "learning_rate": 0.00014047833431223938,
+      "loss": 10.3617,
+      "step": 72
+    },
+    {
+      "epoch": 0.37292464878671777,
+      "grad_norm": 0.11537044495344162,
+      "learning_rate": 0.00013900752808090468,
+      "loss": 10.366,
+      "step": 73
+    },
+    {
+      "epoch": 0.3780332056194125,
+      "grad_norm": 0.11738992482423782,
+      "learning_rate": 0.00013752670048793744,
+      "loss": 10.3471,
+      "step": 74
+    },
+    {
+      "epoch": 0.3831417624521073,
+      "grad_norm": 0.11229626834392548,
+      "learning_rate": 0.00013603623197038536,
+      "loss": 10.3645,
+      "step": 75
+    },
+    {
+      "epoch": 0.388250319284802,
+      "grad_norm": 0.14596045017242432,
+      "learning_rate": 0.00013453650544213076,
+      "loss": 10.3751,
+      "step": 76
+    },
+    {
+      "epoch": 0.3933588761174968,
+      "grad_norm": 0.06448373198509216,
+      "learning_rate": 0.00013302790619551674,
+      "loss": 10.3572,
+      "step": 77
+    },
+    {
+      "epoch": 0.39846743295019155,
+      "grad_norm": 0.11809150874614716,
+      "learning_rate": 0.0001315108218023621,
+      "loss": 10.3695,
+      "step": 78
+    },
+    {
+      "epoch": 0.40357598978288634,
+      "grad_norm": 0.08517828583717346,
+      "learning_rate": 0.00012998564201439116,
+      "loss": 10.3629,
+      "step": 79
+    },
+    {
+      "epoch": 0.4086845466155811,
+      "grad_norm": 0.12408934533596039,
+      "learning_rate": 0.00012845275866310324,
+      "loss": 10.3607,
+      "step": 80
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 0.12312637269496918,
+      "learning_rate": 0.00012691256555910768,
+      "loss": 10.3654,
+      "step": 81
+    },
+    {
+      "epoch": 0.41890166028097064,
+      "grad_norm": 0.12126640975475311,
+      "learning_rate": 0.00012536545839095074,
+      "loss": 10.3617,
+      "step": 82
+    },
+    {
+      "epoch": 0.4240102171136654,
+      "grad_norm": 0.15894931554794312,
+      "learning_rate": 0.00012381183462345982,
+      "loss": 10.3564,
+      "step": 83
+    },
+    {
+      "epoch": 0.42911877394636017,
+      "grad_norm": 0.07874782383441925,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 10.3653,
+      "step": 84
+    },
+    {
+      "epoch": 0.4342273307790549,
+      "grad_norm": 0.12640683352947235,
+      "learning_rate": 0.00012068663541808909,
+      "loss": 10.3631,
+      "step": 85
+    },
+    {
+      "epoch": 0.4393358876117497,
+      "grad_norm": 0.10024367272853851,
+      "learning_rate": 0.00011911586287013725,
+      "loss": 10.3672,
+      "step": 86
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.12512411177158356,
+      "learning_rate": 0.00011754017929643817,
+      "loss": 10.3611,
+      "step": 87
+    },
+    {
+      "epoch": 0.4495530012771392,
+      "grad_norm": 0.1329926997423172,
+      "learning_rate": 0.00011595998950333793,
+      "loss": 10.3591,
+      "step": 88
+    },
+    {
+      "epoch": 0.454661558109834,
+      "grad_norm": 0.11963527649641037,
+      "learning_rate": 0.00011437569945486819,
+      "loss": 10.365,
+      "step": 89
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "grad_norm": 0.11451319605112076,
+      "learning_rate": 0.00011278771616845061,
+      "loss": 10.3549,
+      "step": 90
+    },
+    {
+      "epoch": 0.4648786717752235,
+      "grad_norm": 0.09816919267177582,
+      "learning_rate": 0.00011119644761033078,
+      "loss": 10.3577,
+      "step": 91
+    },
+    {
+      "epoch": 0.46998722860791825,
+      "grad_norm": 0.15458016097545624,
+      "learning_rate": 0.00010960230259076818,
+      "loss": 10.3668,
+      "step": 92
+    },
+    {
+      "epoch": 0.47509578544061304,
+      "grad_norm": 0.1010480597615242,
+      "learning_rate": 0.00010800569065900933,
+      "loss": 10.3592,
+      "step": 93
+    },
+    {
+      "epoch": 0.48020434227330777,
+      "grad_norm": 0.11193486303091049,
+      "learning_rate": 0.0001064070219980713,
+      "loss": 10.3568,
+      "step": 94
+    },
+    {
+      "epoch": 0.48531289910600256,
+      "grad_norm": 0.10354366153478622,
+      "learning_rate": 0.00010480670731936208,
+      "loss": 10.3509,
+      "step": 95
+    },
+    {
+      "epoch": 0.4904214559386973,
+      "grad_norm": 0.15040072798728943,
+      "learning_rate": 0.00010320515775716555,
+      "loss": 10.3566,
+      "step": 96
+    },
+    {
+      "epoch": 0.4955300127713921,
+      "grad_norm": 0.10507191717624664,
+      "learning_rate": 0.0001016027847630174,
+      "loss": 10.3547,
+      "step": 97
+    },
+    {
+      "epoch": 0.5006385696040868,
+      "grad_norm": 0.11989340931177139,
+      "learning_rate": 0.0001,
+      "loss": 10.3656,
+      "step": 98
+    },
+    {
+      "epoch": 0.5057471264367817,
+      "grad_norm": 0.12597250938415527,
+      "learning_rate": 9.839721523698264e-05,
+      "loss": 10.3657,
+      "step": 99
+    },
+    {
+      "epoch": 0.5108556832694764,
+      "grad_norm": 0.16077381372451782,
+      "learning_rate": 9.679484224283449e-05,
+      "loss": 10.3527,
+      "step": 100
+    },
+    {
+      "epoch": 0.5159642401021711,
+      "grad_norm": 0.12048140168190002,
+      "learning_rate": 9.519329268063795e-05,
+      "loss": 10.3627,
+      "step": 101
+    },
+    {
+      "epoch": 0.5210727969348659,
+      "grad_norm": 0.10793527215719223,
+      "learning_rate": 9.359297800192872e-05,
+      "loss": 10.3508,
+      "step": 102
+    },
+    {
+      "epoch": 0.5261813537675607,
+      "grad_norm": 0.070986308157444,
+      "learning_rate": 9.199430934099068e-05,
+      "loss": 10.3545,
+      "step": 103
+    },
+    {
+      "epoch": 0.5312899106002554,
+      "grad_norm": 0.08290573209524155,
+      "learning_rate": 9.039769740923183e-05,
+      "loss": 10.3568,
+      "step": 104
+    },
+    {
+      "epoch": 0.5363984674329502,
+      "grad_norm": 0.09891117364168167,
+      "learning_rate": 8.880355238966923e-05,
+      "loss": 10.3572,
+      "step": 105
+    },
+    {
+      "epoch": 0.541507024265645,
+      "grad_norm": 0.10156704485416412,
+      "learning_rate": 8.721228383154939e-05,
+      "loss": 10.3588,
+      "step": 106
+    },
+    {
+      "epoch": 0.5466155810983397,
+      "grad_norm": 0.10102825611829758,
+      "learning_rate": 8.562430054513184e-05,
+      "loss": 10.3583,
+      "step": 107
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.10080267488956451,
+      "learning_rate": 8.404001049666211e-05,
+      "loss": 10.365,
+      "step": 108
+    },
+    {
+      "epoch": 0.5568326947637292,
+      "grad_norm": 0.08475471287965775,
+      "learning_rate": 8.245982070356185e-05,
+      "loss": 10.3606,
+      "step": 109
+    },
+    {
+      "epoch": 0.561941251596424,
+      "grad_norm": 0.13166114687919617,
+      "learning_rate": 8.08841371298628e-05,
+      "loss": 10.3538,
+      "step": 110
+    },
+    {
+      "epoch": 0.5670498084291188,
+      "grad_norm": 0.1031697690486908,
+      "learning_rate": 7.931336458191092e-05,
+      "loss": 10.3672,
+      "step": 111
+    },
+    {
+      "epoch": 0.5721583652618135,
+      "grad_norm": 0.08675719797611237,
+      "learning_rate": 7.774790660436858e-05,
+      "loss": 10.3575,
+      "step": 112
+    },
+    {
+      "epoch": 0.5772669220945083,
+      "grad_norm": 0.10204310715198517,
+      "learning_rate": 7.618816537654018e-05,
+      "loss": 10.3607,
+      "step": 113
+    },
+    {
+      "epoch": 0.5823754789272031,
+      "grad_norm": 0.12430866807699203,
+      "learning_rate": 7.463454160904928e-05,
+      "loss": 10.3586,
+      "step": 114
+    },
+    {
+      "epoch": 0.5874840357598978,
+      "grad_norm": 0.09749015420675278,
+      "learning_rate": 7.308743444089232e-05,
+      "loss": 10.3493,
+      "step": 115
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.11196263879537582,
+      "learning_rate": 7.154724133689677e-05,
+      "loss": 10.3479,
+      "step": 116
+    },
+    {
+      "epoch": 0.5977011494252874,
+      "grad_norm": 0.1198868602514267,
+      "learning_rate": 7.001435798560883e-05,
+      "loss": 10.349,
+      "step": 117
+    },
+    {
+      "epoch": 0.6028097062579821,
+      "grad_norm": 0.10104350000619888,
+      "learning_rate": 6.848917819763793e-05,
+      "loss": 10.353,
+      "step": 118
+    },
+    {
+      "epoch": 0.6079182630906769,
+      "grad_norm": 0.09838002175092697,
+      "learning_rate": 6.697209380448333e-05,
+      "loss": 10.3552,
+      "step": 119
+    },
+    {
+      "epoch": 0.6130268199233716,
+      "grad_norm": 0.12079446762800217,
+      "learning_rate": 6.546349455786926e-05,
+      "loss": 10.3541,
+      "step": 120
+    },
+    {
+      "epoch": 0.6181353767560664,
+      "grad_norm": 0.07775072753429413,
+      "learning_rate": 6.396376802961468e-05,
+      "loss": 10.3623,
+      "step": 121
+    },
+    {
+      "epoch": 0.6232439335887612,
+      "grad_norm": 0.10357434302568436,
+      "learning_rate": 6.24732995120626e-05,
+      "loss": 10.3578,
+      "step": 122
+    },
+    {
+      "epoch": 0.6283524904214559,
+      "grad_norm": 0.11605259031057358,
+      "learning_rate": 6.0992471919095315e-05,
+      "loss": 10.3513,
+      "step": 123
+    },
+    {
+      "epoch": 0.6334610472541508,
+      "grad_norm": 0.0947057381272316,
+      "learning_rate": 5.952166568776062e-05,
+      "loss": 10.3484,
+      "step": 124
+    },
+    {
+      "epoch": 0.6385696040868455,
+      "grad_norm": 0.09507757425308228,
+      "learning_rate": 5.806125868053433e-05,
+      "loss": 10.3521,
+      "step": 125
+    },
+    {
+      "epoch": 0.6436781609195402,
+      "grad_norm": 0.09619959443807602,
+      "learning_rate": 5.6611626088244194e-05,
+      "loss": 10.3583,
+      "step": 126
+    },
+    {
+      "epoch": 0.648786717752235,
+      "grad_norm": 0.0792725682258606,
+      "learning_rate": 5.5173140333680306e-05,
+      "loss": 10.354,
+      "step": 127
+    },
+    {
+      "epoch": 0.6538952745849298,
+      "grad_norm": 0.105789415538311,
+      "learning_rate": 5.37461709759165e-05,
+      "loss": 10.3583,
+      "step": 128
+    },
+    {
+      "epoch": 0.6590038314176245,
+      "grad_norm": 0.10440662503242493,
+      "learning_rate": 5.2331084615367485e-05,
+      "loss": 10.3523,
+      "step": 129
+    },
+    {
+      "epoch": 0.6641123882503193,
+      "grad_norm": 0.10326969623565674,
+      "learning_rate": 5.092824479960625e-05,
+      "loss": 10.3574,
+      "step": 130
+    },
+    {
+      "epoch": 0.669220945083014,
+      "grad_norm": 0.08976173400878906,
+      "learning_rate": 4.953801192996543e-05,
+      "loss": 10.3548,
+      "step": 131
+    },
+    {
+      "epoch": 0.6743295019157088,
+      "grad_norm": 0.09830819070339203,
+      "learning_rate": 4.8160743168947496e-05,
+      "loss": 10.3497,
+      "step": 132
+    },
+    {
+      "epoch": 0.6794380587484036,
+      "grad_norm": 0.12448275089263916,
+      "learning_rate": 4.6796792348466356e-05,
+      "loss": 10.3661,
+      "step": 133
+    },
+    {
+      "epoch": 0.6845466155810983,
+      "grad_norm": 0.1166510358452797,
+      "learning_rate": 4.544650987894514e-05,
+      "loss": 10.3572,
+      "step": 134
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.11028123646974564,
+      "learning_rate": 4.4110242659292836e-05,
+      "loss": 10.3607,
+      "step": 135
+    },
+    {
+      "epoch": 0.6947637292464879,
+      "grad_norm": 0.14801649749279022,
+      "learning_rate": 4.278833398778306e-05,
+      "loss": 10.3544,
+      "step": 136
+    },
+    {
+      "epoch": 0.6998722860791826,
+      "grad_norm": 0.10162738710641861,
+      "learning_rate": 4.148112347385762e-05,
+      "loss": 10.3514,
+      "step": 137
+    },
+    {
+      "epoch": 0.7049808429118773,
+      "grad_norm": 0.08851826190948486,
+      "learning_rate": 4.0188946950878404e-05,
+      "loss": 10.3545,
+      "step": 138
+    },
+    {
+      "epoch": 0.7100893997445722,
+      "grad_norm": 0.0674971416592598,
+      "learning_rate": 3.8912136389848576e-05,
+      "loss": 10.3527,
+      "step": 139
+    },
+    {
+      "epoch": 0.7151979565772669,
+      "grad_norm": 0.07837618142366409,
+      "learning_rate": 3.7651019814126654e-05,
+      "loss": 10.3495,
+      "step": 140
+    },
+    {
+      "epoch": 0.7203065134099617,
+      "grad_norm": 0.13337913155555725,
+      "learning_rate": 3.6405921215154494e-05,
+      "loss": 10.3601,
+      "step": 141
+    },
+    {
+      "epoch": 0.7254150702426565,
+      "grad_norm": 0.1068163514137268,
+      "learning_rate": 3.517716046922118e-05,
+      "loss": 10.3553,
+      "step": 142
+    },
+    {
+      "epoch": 0.7305236270753512,
+      "grad_norm": 0.09636684507131577,
+      "learning_rate": 3.3965053255284084e-05,
+      "loss": 10.3609,
+      "step": 143
+    },
+    {
+      "epoch": 0.735632183908046,
+      "grad_norm": 0.10259624570608139,
+      "learning_rate": 3.276991097386831e-05,
+      "loss": 10.3514,
+      "step": 144
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.08181837946176529,
+      "learning_rate": 3.159204066706539e-05,
+      "loss": 10.3508,
+      "step": 145
+    },
+    {
+      "epoch": 0.7458492975734355,
+      "grad_norm": 0.10370145738124847,
+      "learning_rate": 3.0431744939651364e-05,
+      "loss": 10.3518,
+      "step": 146
+    },
+    {
+      "epoch": 0.7509578544061303,
+      "grad_norm": 0.11586267501115799,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 10.3494,
+      "step": 147
+    },
+    {
+      "epoch": 0.756066411238825,
+      "grad_norm": 0.07326210290193558,
+      "learning_rate": 2.8165064990227252e-05,
+      "loss": 10.3618,
+      "step": 148
+    },
+    {
+      "epoch": 0.7611749680715197,
+      "grad_norm": 0.07508935779333115,
+      "learning_rate": 2.7059263097336597e-05,
+      "loss": 10.354,
+      "step": 149
+    },
+    {
+      "epoch": 0.7662835249042146,
+      "grad_norm": 0.09258796274662018,
+      "learning_rate": 2.5972200292468464e-05,
+      "loss": 10.3528,
+      "step": 150
+    },
+    {
+      "epoch": 0.7713920817369093,
+      "grad_norm": 0.09141936898231506,
+      "learning_rate": 2.4904155851188872e-05,
+      "loss": 10.3475,
+      "step": 151
+    },
+    {
+      "epoch": 0.776500638569604,
+      "grad_norm": 0.06457791477441788,
+      "learning_rate": 2.3855404163086558e-05,
+      "loss": 10.3594,
+      "step": 152
+    },
+    {
+      "epoch": 0.7816091954022989,
+      "grad_norm": 0.0867636650800705,
+      "learning_rate": 2.282621466127982e-05,
+      "loss": 10.357,
+      "step": 153
+    },
+    {
+      "epoch": 0.7867177522349936,
+      "grad_norm": 0.07386265695095062,
+      "learning_rate": 2.181685175319702e-05,
+      "loss": 10.3601,
+      "step": 154
+    },
+    {
+      "epoch": 0.7918263090676884,
+      "grad_norm": 0.09301372617483139,
+      "learning_rate": 2.0827574752648038e-05,
+      "loss": 10.3521,
+      "step": 155
+    },
+    {
+      "epoch": 0.7969348659003831,
+      "grad_norm": 0.09825734794139862,
+      "learning_rate": 1.985863781320435e-05,
+      "loss": 10.3518,
+      "step": 156
+    },
+    {
+      "epoch": 0.8020434227330779,
+      "grad_norm": 0.09146848320960999,
+      "learning_rate": 1.891028986290492e-05,
+      "loss": 10.3543,
+      "step": 157
+    },
+    {
+      "epoch": 0.8071519795657727,
+      "grad_norm": 0.10811572521924973,
+      "learning_rate": 1.7982774540304403e-05,
+      "loss": 10.3486,
+      "step": 158
+    },
+    {
+      "epoch": 0.8122605363984674,
+      "grad_norm": 0.10702500492334366,
+      "learning_rate": 1.7076330131880526e-05,
+      "loss": 10.3506,
+      "step": 159
+    },
+    {
+      "epoch": 0.8173690932311622,
+      "grad_norm": 0.09714721143245697,
+      "learning_rate": 1.619118951081594e-05,
+      "loss": 10.3542,
+      "step": 160
+    },
+    {
+      "epoch": 0.822477650063857,
+      "grad_norm": 0.09883596003055573,
+      "learning_rate": 1.5327580077171587e-05,
+      "loss": 10.355,
+      "step": 161
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.07649561762809753,
+      "learning_rate": 1.4485723699465392e-05,
+      "loss": 10.3488,
+      "step": 162
+    },
+    {
+      "epoch": 0.8326947637292464,
+      "grad_norm": 0.0714419037103653,
+      "learning_rate": 1.3665836657672493e-05,
+      "loss": 10.3463,
+      "step": 163
+    },
+    {
+      "epoch": 0.8378033205619413,
+      "grad_norm": 0.09287029504776001,
+      "learning_rate": 1.286812958766106e-05,
+      "loss": 10.3506,
+      "step": 164
+    },
+    {
+      "epoch": 0.842911877394636,
+      "grad_norm": 0.0882708728313446,
+      "learning_rate": 1.2092807427078279e-05,
+      "loss": 10.3538,
+      "step": 165
+    },
+    {
+      "epoch": 0.8480204342273308,
+      "grad_norm": 0.0939875915646553,
+      "learning_rate": 1.134006936269999e-05,
+      "loss": 10.3498,
+      "step": 166
+    },
+    {
+      "epoch": 0.8531289910600255,
+      "grad_norm": 0.10232677310705185,
+      "learning_rate": 1.0610108779258044e-05,
+      "loss": 10.3573,
+      "step": 167
+    },
+    {
+      "epoch": 0.8582375478927203,
+      "grad_norm": 0.09528540074825287,
+      "learning_rate": 9.903113209758096e-06,
+      "loss": 10.3558,
+      "step": 168
+    },
+    {
+      "epoch": 0.8633461047254151,
+      "grad_norm": 0.08980326354503632,
+      "learning_rate": 9.219264287300799e-06,
+      "loss": 10.3564,
+      "step": 169
+    },
+    {
+      "epoch": 0.8684546615581098,
+      "grad_norm": 0.0988466814160347,
+      "learning_rate": 8.558737698418761e-06,
+      "loss": 10.3518,
+      "step": 170
+    },
+    {
+      "epoch": 0.8735632183908046,
+      "grad_norm": 0.09410892426967621,
+      "learning_rate": 7.921703137941173e-06,
+      "loss": 10.3501,
+      "step": 171
+    },
+    {
+      "epoch": 0.8786717752234994,
+      "grad_norm": 0.0989941656589508,
+      "learning_rate": 7.308324265397836e-06,
+      "loss": 10.3563,
+      "step": 172
+    },
+    {
+      "epoch": 0.8837803320561941,
+      "grad_norm": 0.12267417460680008,
+      "learning_rate": 6.718758662973523e-06,
+      "loss": 10.3536,
+      "step": 173
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.09049776196479797,
+      "learning_rate": 6.153157795023956e-06,
+      "loss": 10.3524,
+      "step": 174
+    },
+    {
+      "epoch": 0.8939974457215837,
+      "grad_norm": 0.10820028930902481,
+      "learning_rate": 5.611666969163243e-06,
+      "loss": 10.3631,
+      "step": 175
+    },
+    {
+      "epoch": 0.8991060025542784,
+      "grad_norm": 0.08953528106212616,
+      "learning_rate": 5.094425298933136e-06,
+      "loss": 10.3467,
+      "step": 176
+    },
+    {
+      "epoch": 0.9042145593869731,
+      "grad_norm": 0.12113954871892929,
+      "learning_rate": 4.601565668063623e-06,
+      "loss": 10.3563,
+      "step": 177
+    },
+    {
+      "epoch": 0.909323116219668,
+      "grad_norm": 0.08720055967569351,
+      "learning_rate": 4.133214696333942e-06,
+      "loss": 10.356,
+      "step": 178
+    },
+    {
+      "epoch": 0.9144316730523627,
+      "grad_norm": 0.09181863814592361,
+      "learning_rate": 3.689492707042974e-06,
+      "loss": 10.3552,
+      "step": 179
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 0.09627222269773483,
+      "learning_rate": 3.270513696097055e-06,
+      "loss": 10.3541,
+      "step": 180
+    },
+    {
+      "epoch": 0.9246487867177522,
+      "grad_norm": 0.11901070922613144,
+      "learning_rate": 2.876385302723628e-06,
+      "loss": 10.3597,
+      "step": 181
+    },
+    {
+      "epoch": 0.929757343550447,
+      "grad_norm": 0.0824970006942749,
+      "learning_rate": 2.5072087818176382e-06,
+      "loss": 10.3537,
+      "step": 182
+    },
+    {
+      "epoch": 0.9348659003831418,
+      "grad_norm": 0.10875054448843002,
+      "learning_rate": 2.1630789779284675e-06,
+      "loss": 10.3465,
+      "step": 183
+    },
+    {
+      "epoch": 0.9399744572158365,
+      "grad_norm": 0.08391505479812622,
+      "learning_rate": 1.8440843008934561e-06,
+      "loss": 10.3537,
+      "step": 184
+    },
+    {
+      "epoch": 0.9450830140485313,
+      "grad_norm": 0.0997113361954689,
+      "learning_rate": 1.5503067031247598e-06,
+      "loss": 10.3528,
+      "step": 185
+    },
+    {
+      "epoch": 0.9501915708812261,
+      "grad_norm": 0.1007162481546402,
+      "learning_rate": 1.2818216585549825e-06,
+      "loss": 10.3498,
+      "step": 186
+    },
+    {
+      "epoch": 0.9553001277139208,
+      "grad_norm": 0.0825323835015297,
+      "learning_rate": 1.0386981432474074e-06,
+      "loss": 10.3464,
+      "step": 187
+    },
+    {
+      "epoch": 0.9604086845466155,
+      "grad_norm": 0.07373323291540146,
+      "learning_rate": 8.209986176753948e-07,
+      "loss": 10.3546,
+      "step": 188
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 0.10504812747240067,
+      "learning_rate": 6.287790106757396e-07,
+      "loss": 10.3522,
+      "step": 189
+    },
+    {
+      "epoch": 0.9706257982120051,
+      "grad_norm": 0.07949844747781754,
+      "learning_rate": 4.62088705080177e-07,
+      "loss": 10.3554,
+      "step": 190
+    },
+    {
+      "epoch": 0.9757343550446999,
+      "grad_norm": 0.09091745316982269,
+      "learning_rate": 3.2097052502843007e-07,
+      "loss": 10.3477,
+      "step": 191
+    },
+    {
+      "epoch": 0.9808429118773946,
+      "grad_norm": 0.11523844301700592,
+      "learning_rate": 2.054607249663665e-07,
+      "loss": 10.3526,
+      "step": 192
+    },
+    {
+      "epoch": 0.9859514687100894,
+      "grad_norm": 0.09753245860338211,
+      "learning_rate": 1.1558898033191546e-07,
+      "loss": 10.3566,
+      "step": 193
+    },
+    {
+      "epoch": 0.9910600255427842,
+      "grad_norm": 0.08241667598485947,
+      "learning_rate": 5.137837993121064e-08,
+      "loss": 10.3576,
+      "step": 194
+    },
+    {
+      "epoch": 0.9961685823754789,
+      "grad_norm": 0.08668815344572067,
+      "learning_rate": 1.2845420006879494e-08,
+      "loss": 10.3612,
+      "step": 195
+    },
+    {
+      "epoch": 0.9961685823754789,
+      "eval_loss": 10.354520797729492,
+      "eval_runtime": 0.2879,
+      "eval_samples_per_second": 145.877,
+      "eval_steps_per_second": 145.877,
+      "step": 195
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 196,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2531225272320.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88ed91cd51242af42cbb81b613e3dac906633d5dd9dab8eb5ab5d115d467f273
+size 6776