Training in progress, step 200, checkpoint

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: openlm-research/open_llama_3b
+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": "openlm-research/open_llama_3b",
+  "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": [
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72f28cadd8c918a524132896352d2e8864faa8c0607da67b4118a48e26e08661
+size 203456160

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d16893120f3a2dd499e3d9e57b9667e48eba00408b6c77437a89b0ccd3f02230
+size 103716100

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b81d9955023da2f6aa938a016eed48b42010ceda70c7112468b9f2d00aa41cf5
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:371419fc299cc77a3496f86edf3fc71d13a6e0683fa703cd0e2a5207cd5461ba
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "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": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab1b681ec7fc02fed5edd3026687d7a692a918c4dd8e150ca2e3994a6229843b
+size 534194

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "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": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,1458 @@
+{
+  "best_metric": 0.48710426688194275,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.015965195872996867,
+  "eval_steps": 200,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 7.982597936498434e-05,
+      "grad_norm": 0.6978444457054138,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.8702,
+      "step": 1
+    },
+    {
+      "epoch": 7.982597936498434e-05,
+      "eval_loss": 0.9949384927749634,
+      "eval_runtime": 34.0877,
+      "eval_samples_per_second": 7.393,
+      "eval_steps_per_second": 7.393,
+      "step": 1
+    },
+    {
+      "epoch": 0.00015965195872996867,
+      "grad_norm": 0.6221582889556885,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.9368,
+      "step": 2
+    },
+    {
+      "epoch": 0.000239477938094953,
+      "grad_norm": 0.8889533877372742,
+      "learning_rate": 2e-05,
+      "loss": 0.9468,
+      "step": 3
+    },
+    {
+      "epoch": 0.00031930391745993734,
+      "grad_norm": 0.7401799559593201,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.7979,
+      "step": 4
+    },
+    {
+      "epoch": 0.0003991298968249217,
+      "grad_norm": 0.7739838361740112,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.8109,
+      "step": 5
+    },
+    {
+      "epoch": 0.000478955876189906,
+      "grad_norm": 0.6389685273170471,
+      "learning_rate": 4e-05,
+      "loss": 0.7721,
+      "step": 6
+    },
+    {
+      "epoch": 0.0005587818555548903,
+      "grad_norm": 0.6121872663497925,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 1.0764,
+      "step": 7
+    },
+    {
+      "epoch": 0.0006386078349198747,
+      "grad_norm": 0.5235614776611328,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 0.8227,
+      "step": 8
+    },
+    {
+      "epoch": 0.000718433814284859,
+      "grad_norm": 0.5427432656288147,
+      "learning_rate": 6e-05,
+      "loss": 0.6078,
+      "step": 9
+    },
+    {
+      "epoch": 0.0007982597936498434,
+      "grad_norm": 0.47566384077072144,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.6422,
+      "step": 10
+    },
+    {
+      "epoch": 0.0008780857730148276,
+      "grad_norm": 0.4659350514411926,
+      "learning_rate": 7.333333333333333e-05,
+      "loss": 0.596,
+      "step": 11
+    },
+    {
+      "epoch": 0.000957911752379812,
+      "grad_norm": 0.6114226579666138,
+      "learning_rate": 8e-05,
+      "loss": 0.6285,
+      "step": 12
+    },
+    {
+      "epoch": 0.0010377377317447964,
+      "grad_norm": 0.5205951929092407,
+      "learning_rate": 8.666666666666667e-05,
+      "loss": 0.7634,
+      "step": 13
+    },
+    {
+      "epoch": 0.0011175637111097807,
+      "grad_norm": 0.5503156781196594,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 0.6936,
+      "step": 14
+    },
+    {
+      "epoch": 0.001197389690474765,
+      "grad_norm": 0.6346184015274048,
+      "learning_rate": 0.0001,
+      "loss": 0.6529,
+      "step": 15
+    },
+    {
+      "epoch": 0.0012772156698397494,
+      "grad_norm": 0.7112955451011658,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 0.6017,
+      "step": 16
+    },
+    {
+      "epoch": 0.0013570416492047336,
+      "grad_norm": 0.7180954813957214,
+      "learning_rate": 0.00011333333333333334,
+      "loss": 0.7348,
+      "step": 17
+    },
+    {
+      "epoch": 0.001436867628569718,
+      "grad_norm": 0.9665006995201111,
+      "learning_rate": 0.00012,
+      "loss": 0.795,
+      "step": 18
+    },
+    {
+      "epoch": 0.0015166936079347023,
+      "grad_norm": 0.664631187915802,
+      "learning_rate": 0.00012666666666666666,
+      "loss": 0.5434,
+      "step": 19
+    },
+    {
+      "epoch": 0.0015965195872996868,
+      "grad_norm": 0.9294877648353577,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.6761,
+      "step": 20
+    },
+    {
+      "epoch": 0.001676345566664671,
+      "grad_norm": 0.921779990196228,
+      "learning_rate": 0.00014,
+      "loss": 0.7902,
+      "step": 21
+    },
+    {
+      "epoch": 0.0017561715460296552,
+      "grad_norm": 0.825416088104248,
+      "learning_rate": 0.00014666666666666666,
+      "loss": 0.4612,
+      "step": 22
+    },
+    {
+      "epoch": 0.0018359975253946397,
+      "grad_norm": 0.6585280895233154,
+      "learning_rate": 0.00015333333333333334,
+      "loss": 0.6872,
+      "step": 23
+    },
+    {
+      "epoch": 0.001915823504759624,
+      "grad_norm": 0.5992960929870605,
+      "learning_rate": 0.00016,
+      "loss": 0.5949,
+      "step": 24
+    },
+    {
+      "epoch": 0.0019956494841246084,
+      "grad_norm": 0.5506778359413147,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 0.6372,
+      "step": 25
+    },
+    {
+      "epoch": 0.002075475463489593,
+      "grad_norm": 0.4277991056442261,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 0.6599,
+      "step": 26
+    },
+    {
+      "epoch": 0.002155301442854577,
+      "grad_norm": 0.4358632564544678,
+      "learning_rate": 0.00018,
+      "loss": 0.4311,
+      "step": 27
+    },
+    {
+      "epoch": 0.0022351274222195613,
+      "grad_norm": 0.47243207693099976,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 0.4258,
+      "step": 28
+    },
+    {
+      "epoch": 0.002314953401584546,
+      "grad_norm": 0.49624741077423096,
+      "learning_rate": 0.00019333333333333333,
+      "loss": 0.5656,
+      "step": 29
+    },
+    {
+      "epoch": 0.00239477938094953,
+      "grad_norm": 0.5323299169540405,
+      "learning_rate": 0.0002,
+      "loss": 0.451,
+      "step": 30
+    },
+    {
+      "epoch": 0.0024746053603145143,
+      "grad_norm": 0.3971990942955017,
+      "learning_rate": 0.00019999999980322236,
+      "loss": 0.5564,
+      "step": 31
+    },
+    {
+      "epoch": 0.0025544313396794987,
+      "grad_norm": 0.8148688673973083,
+      "learning_rate": 0.00019999999921288937,
+      "loss": 0.4035,
+      "step": 32
+    },
+    {
+      "epoch": 0.002634257319044483,
+      "grad_norm": 0.570773184299469,
+      "learning_rate": 0.00019999999822900105,
+      "loss": 0.6842,
+      "step": 33
+    },
+    {
+      "epoch": 0.0027140832984094672,
+      "grad_norm": 0.5124844312667847,
+      "learning_rate": 0.00019999999685155743,
+      "loss": 0.5752,
+      "step": 34
+    },
+    {
+      "epoch": 0.0027939092777744517,
+      "grad_norm": 0.5524983406066895,
+      "learning_rate": 0.0001999999950805585,
+      "loss": 0.5707,
+      "step": 35
+    },
+    {
+      "epoch": 0.002873735257139436,
+      "grad_norm": 0.3884465992450714,
+      "learning_rate": 0.0001999999929160042,
+      "loss": 0.4453,
+      "step": 36
+    },
+    {
+      "epoch": 0.00295356123650442,
+      "grad_norm": 0.535567045211792,
+      "learning_rate": 0.00019999999035789467,
+      "loss": 0.4068,
+      "step": 37
+    },
+    {
+      "epoch": 0.0030333872158694046,
+      "grad_norm": 0.5301805734634399,
+      "learning_rate": 0.00019999998740622985,
+      "loss": 0.542,
+      "step": 38
+    },
+    {
+      "epoch": 0.003113213195234389,
+      "grad_norm": 0.5463919639587402,
+      "learning_rate": 0.00019999998406100976,
+      "loss": 0.4507,
+      "step": 39
+    },
+    {
+      "epoch": 0.0031930391745993735,
+      "grad_norm": 0.5074406862258911,
+      "learning_rate": 0.00019999998032223438,
+      "loss": 0.5171,
+      "step": 40
+    },
+    {
+      "epoch": 0.0032728651539643576,
+      "grad_norm": 0.6419821977615356,
+      "learning_rate": 0.00019999997618990375,
+      "loss": 0.6315,
+      "step": 41
+    },
+    {
+      "epoch": 0.003352691133329342,
+      "grad_norm": 0.7871913313865662,
+      "learning_rate": 0.0001999999716640179,
+      "loss": 0.6276,
+      "step": 42
+    },
+    {
+      "epoch": 0.0034325171126943265,
+      "grad_norm": 0.788992166519165,
+      "learning_rate": 0.00019999996674457683,
+      "loss": 0.6411,
+      "step": 43
+    },
+    {
+      "epoch": 0.0035123430920593105,
+      "grad_norm": 0.36080795526504517,
+      "learning_rate": 0.00019999996143158058,
+      "loss": 0.4389,
+      "step": 44
+    },
+    {
+      "epoch": 0.003592169071424295,
+      "grad_norm": 0.46374040842056274,
+      "learning_rate": 0.00019999995572502914,
+      "loss": 0.6004,
+      "step": 45
+    },
+    {
+      "epoch": 0.0036719950507892794,
+      "grad_norm": 0.4771120548248291,
+      "learning_rate": 0.00019999994962492255,
+      "loss": 0.4023,
+      "step": 46
+    },
+    {
+      "epoch": 0.003751821030154264,
+      "grad_norm": 0.39009377360343933,
+      "learning_rate": 0.00019999994313126083,
+      "loss": 0.5949,
+      "step": 47
+    },
+    {
+      "epoch": 0.003831647009519248,
+      "grad_norm": 0.44296398758888245,
+      "learning_rate": 0.00019999993624404404,
+      "loss": 0.5292,
+      "step": 48
+    },
+    {
+      "epoch": 0.003911472988884232,
+      "grad_norm": 0.41374722123146057,
+      "learning_rate": 0.00019999992896327213,
+      "loss": 0.5127,
+      "step": 49
+    },
+    {
+      "epoch": 0.003991298968249217,
+      "grad_norm": 0.6176245212554932,
+      "learning_rate": 0.0001999999212889452,
+      "loss": 0.5315,
+      "step": 50
+    },
+    {
+      "epoch": 0.004071124947614201,
+      "grad_norm": 0.5393801331520081,
+      "learning_rate": 0.00019999991322106327,
+      "loss": 0.6397,
+      "step": 51
+    },
+    {
+      "epoch": 0.004150950926979186,
+      "grad_norm": 0.41064855456352234,
+      "learning_rate": 0.00019999990475962632,
+      "loss": 0.4149,
+      "step": 52
+    },
+    {
+      "epoch": 0.004230776906344169,
+      "grad_norm": 0.41754090785980225,
+      "learning_rate": 0.00019999989590463444,
+      "loss": 0.5011,
+      "step": 53
+    },
+    {
+      "epoch": 0.004310602885709154,
+      "grad_norm": 0.4694159924983978,
+      "learning_rate": 0.00019999988665608763,
+      "loss": 0.4445,
+      "step": 54
+    },
+    {
+      "epoch": 0.004390428865074138,
+      "grad_norm": 0.44929438829421997,
+      "learning_rate": 0.00019999987701398595,
+      "loss": 0.549,
+      "step": 55
+    },
+    {
+      "epoch": 0.004470254844439123,
+      "grad_norm": 0.38041579723358154,
+      "learning_rate": 0.00019999986697832943,
+      "loss": 0.5887,
+      "step": 56
+    },
+    {
+      "epoch": 0.004550080823804107,
+      "grad_norm": 0.3928568959236145,
+      "learning_rate": 0.0001999998565491181,
+      "loss": 0.5408,
+      "step": 57
+    },
+    {
+      "epoch": 0.004629906803169092,
+      "grad_norm": 0.47993287444114685,
+      "learning_rate": 0.000199999845726352,
+      "loss": 0.4402,
+      "step": 58
+    },
+    {
+      "epoch": 0.004709732782534076,
+      "grad_norm": 0.5937661528587341,
+      "learning_rate": 0.00019999983451003122,
+      "loss": 0.7218,
+      "step": 59
+    },
+    {
+      "epoch": 0.00478955876189906,
+      "grad_norm": 0.48752108216285706,
+      "learning_rate": 0.00019999982290015573,
+      "loss": 0.4714,
+      "step": 60
+    },
+    {
+      "epoch": 0.004869384741264044,
+      "grad_norm": 0.4562622904777527,
+      "learning_rate": 0.00019999981089672563,
+      "loss": 0.4191,
+      "step": 61
+    },
+    {
+      "epoch": 0.0049492107206290286,
+      "grad_norm": 0.37795504927635193,
+      "learning_rate": 0.00019999979849974093,
+      "loss": 0.4863,
+      "step": 62
+    },
+    {
+      "epoch": 0.005029036699994013,
+      "grad_norm": 0.42114368081092834,
+      "learning_rate": 0.00019999978570920171,
+      "loss": 0.6121,
+      "step": 63
+    },
+    {
+      "epoch": 0.0051088626793589975,
+      "grad_norm": 0.562707781791687,
+      "learning_rate": 0.00019999977252510803,
+      "loss": 0.5966,
+      "step": 64
+    },
+    {
+      "epoch": 0.005188688658723982,
+      "grad_norm": 0.4490356147289276,
+      "learning_rate": 0.00019999975894745988,
+      "loss": 0.6387,
+      "step": 65
+    },
+    {
+      "epoch": 0.005268514638088966,
+      "grad_norm": 0.5229705572128296,
+      "learning_rate": 0.00019999974497625738,
+      "loss": 0.622,
+      "step": 66
+    },
+    {
+      "epoch": 0.00534834061745395,
+      "grad_norm": 0.3769994080066681,
+      "learning_rate": 0.00019999973061150055,
+      "loss": 0.3879,
+      "step": 67
+    },
+    {
+      "epoch": 0.0054281665968189344,
+      "grad_norm": 0.41189664602279663,
+      "learning_rate": 0.00019999971585318944,
+      "loss": 0.5614,
+      "step": 68
+    },
+    {
+      "epoch": 0.005507992576183919,
+      "grad_norm": 0.4498278796672821,
+      "learning_rate": 0.00019999970070132413,
+      "loss": 0.488,
+      "step": 69
+    },
+    {
+      "epoch": 0.005587818555548903,
+      "grad_norm": 0.5084874629974365,
+      "learning_rate": 0.0001999996851559047,
+      "loss": 0.3836,
+      "step": 70
+    },
+    {
+      "epoch": 0.005667644534913888,
+      "grad_norm": 0.4059184193611145,
+      "learning_rate": 0.00019999966921693113,
+      "loss": 0.495,
+      "step": 71
+    },
+    {
+      "epoch": 0.005747470514278872,
+      "grad_norm": 0.39916181564331055,
+      "learning_rate": 0.0001999996528844036,
+      "loss": 0.4647,
+      "step": 72
+    },
+    {
+      "epoch": 0.005827296493643857,
+      "grad_norm": 0.3999392092227936,
+      "learning_rate": 0.00019999963615832206,
+      "loss": 0.4268,
+      "step": 73
+    },
+    {
+      "epoch": 0.00590712247300884,
+      "grad_norm": 0.4153369069099426,
+      "learning_rate": 0.00019999961903868665,
+      "loss": 0.3885,
+      "step": 74
+    },
+    {
+      "epoch": 0.005986948452373825,
+      "grad_norm": 0.4322861135005951,
+      "learning_rate": 0.0001999996015254974,
+      "loss": 0.427,
+      "step": 75
+    },
+    {
+      "epoch": 0.006066774431738809,
+      "grad_norm": 0.34602755308151245,
+      "learning_rate": 0.0001999995836187544,
+      "loss": 0.4477,
+      "step": 76
+    },
+    {
+      "epoch": 0.006146600411103794,
+      "grad_norm": 0.3948773443698883,
+      "learning_rate": 0.0001999995653184577,
+      "loss": 0.2908,
+      "step": 77
+    },
+    {
+      "epoch": 0.006226426390468778,
+      "grad_norm": 0.42778024077415466,
+      "learning_rate": 0.00019999954662460742,
+      "loss": 0.4993,
+      "step": 78
+    },
+    {
+      "epoch": 0.006306252369833763,
+      "grad_norm": 0.5211858749389648,
+      "learning_rate": 0.00019999952753720356,
+      "loss": 0.4678,
+      "step": 79
+    },
+    {
+      "epoch": 0.006386078349198747,
+      "grad_norm": 0.3613867461681366,
+      "learning_rate": 0.00019999950805624626,
+      "loss": 0.4381,
+      "step": 80
+    },
+    {
+      "epoch": 0.006465904328563731,
+      "grad_norm": 0.4412776529788971,
+      "learning_rate": 0.00019999948818173556,
+      "loss": 0.5391,
+      "step": 81
+    },
+    {
+      "epoch": 0.006545730307928715,
+      "grad_norm": 0.418983519077301,
+      "learning_rate": 0.00019999946791367156,
+      "loss": 0.4712,
+      "step": 82
+    },
+    {
+      "epoch": 0.0066255562872937,
+      "grad_norm": 0.5155718326568604,
+      "learning_rate": 0.00019999944725205431,
+      "loss": 0.5338,
+      "step": 83
+    },
+    {
+      "epoch": 0.006705382266658684,
+      "grad_norm": 0.324404776096344,
+      "learning_rate": 0.00019999942619688393,
+      "loss": 0.3691,
+      "step": 84
+    },
+    {
+      "epoch": 0.0067852082460236685,
+      "grad_norm": 0.33547988533973694,
+      "learning_rate": 0.0001999994047481605,
+      "loss": 0.3652,
+      "step": 85
+    },
+    {
+      "epoch": 0.006865034225388653,
+      "grad_norm": 0.4007713496685028,
+      "learning_rate": 0.00019999938290588402,
+      "loss": 0.4699,
+      "step": 86
+    },
+    {
+      "epoch": 0.006944860204753637,
+      "grad_norm": 0.3604133427143097,
+      "learning_rate": 0.0001999993606700547,
+      "loss": 0.4361,
+      "step": 87
+    },
+    {
+      "epoch": 0.007024686184118621,
+      "grad_norm": 0.4794510304927826,
+      "learning_rate": 0.00019999933804067254,
+      "loss": 0.5803,
+      "step": 88
+    },
+    {
+      "epoch": 0.0071045121634836055,
+      "grad_norm": 0.3699691891670227,
+      "learning_rate": 0.00019999931501773767,
+      "loss": 0.4867,
+      "step": 89
+    },
+    {
+      "epoch": 0.00718433814284859,
+      "grad_norm": 0.38762685656547546,
+      "learning_rate": 0.00019999929160125017,
+      "loss": 0.4184,
+      "step": 90
+    },
+    {
+      "epoch": 0.007264164122213574,
+      "grad_norm": 0.5109147429466248,
+      "learning_rate": 0.00019999926779121015,
+      "loss": 0.466,
+      "step": 91
+    },
+    {
+      "epoch": 0.007343990101578559,
+      "grad_norm": 0.4178380072116852,
+      "learning_rate": 0.00019999924358761768,
+      "loss": 0.5317,
+      "step": 92
+    },
+    {
+      "epoch": 0.007423816080943543,
+      "grad_norm": 0.49985650181770325,
+      "learning_rate": 0.00019999921899047286,
+      "loss": 0.5815,
+      "step": 93
+    },
+    {
+      "epoch": 0.007503642060308528,
+      "grad_norm": 0.39766451716423035,
+      "learning_rate": 0.00019999919399977576,
+      "loss": 0.4655,
+      "step": 94
+    },
+    {
+      "epoch": 0.007583468039673511,
+      "grad_norm": 0.48783499002456665,
+      "learning_rate": 0.0001999991686155265,
+      "loss": 0.5225,
+      "step": 95
+    },
+    {
+      "epoch": 0.007663294019038496,
+      "grad_norm": 0.4448859989643097,
+      "learning_rate": 0.00019999914283772526,
+      "loss": 0.3419,
+      "step": 96
+    },
+    {
+      "epoch": 0.00774311999840348,
+      "grad_norm": 0.4495418667793274,
+      "learning_rate": 0.000199999116666372,
+      "loss": 0.5079,
+      "step": 97
+    },
+    {
+      "epoch": 0.007822945977768465,
+      "grad_norm": 0.4888549745082855,
+      "learning_rate": 0.00019999909010146692,
+      "loss": 0.4751,
+      "step": 98
+    },
+    {
+      "epoch": 0.007902771957133448,
+      "grad_norm": 0.4711008071899414,
+      "learning_rate": 0.0001999990631430101,
+      "loss": 0.5702,
+      "step": 99
+    },
+    {
+      "epoch": 0.007982597936498434,
+      "grad_norm": 0.4134286344051361,
+      "learning_rate": 0.00019999903579100164,
+      "loss": 0.4196,
+      "step": 100
+    },
+    {
+      "epoch": 0.008062423915863417,
+      "grad_norm": 0.43762391805648804,
+      "learning_rate": 0.0001999990080454416,
+      "loss": 0.4576,
+      "step": 101
+    },
+    {
+      "epoch": 0.008142249895228403,
+      "grad_norm": 0.3857693076133728,
+      "learning_rate": 0.0001999989799063302,
+      "loss": 0.5379,
+      "step": 102
+    },
+    {
+      "epoch": 0.008222075874593386,
+      "grad_norm": 0.3583117425441742,
+      "learning_rate": 0.00019999895137366743,
+      "loss": 0.4803,
+      "step": 103
+    },
+    {
+      "epoch": 0.008301901853958371,
+      "grad_norm": 0.35127314925193787,
+      "learning_rate": 0.00019999892244745352,
+      "loss": 0.3879,
+      "step": 104
+    },
+    {
+      "epoch": 0.008381727833323355,
+      "grad_norm": 0.41990524530410767,
+      "learning_rate": 0.0001999988931276885,
+      "loss": 0.499,
+      "step": 105
+    },
+    {
+      "epoch": 0.008461553812688339,
+      "grad_norm": 0.4216882288455963,
+      "learning_rate": 0.00019999886341437253,
+      "loss": 0.5233,
+      "step": 106
+    },
+    {
+      "epoch": 0.008541379792053324,
+      "grad_norm": 0.37515565752983093,
+      "learning_rate": 0.00019999883330750569,
+      "loss": 0.4384,
+      "step": 107
+    },
+    {
+      "epoch": 0.008621205771418308,
+      "grad_norm": 0.4432523548603058,
+      "learning_rate": 0.00019999880280708812,
+      "loss": 0.6059,
+      "step": 108
+    },
+    {
+      "epoch": 0.008701031750783293,
+      "grad_norm": 0.33889615535736084,
+      "learning_rate": 0.0001999987719131199,
+      "loss": 0.5097,
+      "step": 109
+    },
+    {
+      "epoch": 0.008780857730148276,
+      "grad_norm": 0.3930656909942627,
+      "learning_rate": 0.00019999874062560124,
+      "loss": 0.4573,
+      "step": 110
+    },
+    {
+      "epoch": 0.008860683709513262,
+      "grad_norm": 0.6760386824607849,
+      "learning_rate": 0.00019999870894453218,
+      "loss": 0.6336,
+      "step": 111
+    },
+    {
+      "epoch": 0.008940509688878245,
+      "grad_norm": 0.33040305972099304,
+      "learning_rate": 0.0001999986768699129,
+      "loss": 0.4666,
+      "step": 112
+    },
+    {
+      "epoch": 0.009020335668243229,
+      "grad_norm": 0.40810972452163696,
+      "learning_rate": 0.0001999986444017435,
+      "loss": 0.4627,
+      "step": 113
+    },
+    {
+      "epoch": 0.009100161647608214,
+      "grad_norm": 0.43593883514404297,
+      "learning_rate": 0.00019999861154002408,
+      "loss": 0.4535,
+      "step": 114
+    },
+    {
+      "epoch": 0.009179987626973198,
+      "grad_norm": 0.3248092234134674,
+      "learning_rate": 0.00019999857828475483,
+      "loss": 0.334,
+      "step": 115
+    },
+    {
+      "epoch": 0.009259813606338183,
+      "grad_norm": 0.4773208796977997,
+      "learning_rate": 0.00019999854463593583,
+      "loss": 0.5818,
+      "step": 116
+    },
+    {
+      "epoch": 0.009339639585703167,
+      "grad_norm": 0.3909766674041748,
+      "learning_rate": 0.00019999851059356724,
+      "loss": 0.551,
+      "step": 117
+    },
+    {
+      "epoch": 0.009419465565068152,
+      "grad_norm": 0.3928094506263733,
+      "learning_rate": 0.00019999847615764918,
+      "loss": 0.4713,
+      "step": 118
+    },
+    {
+      "epoch": 0.009499291544433136,
+      "grad_norm": 0.39069411158561707,
+      "learning_rate": 0.00019999844132818182,
+      "loss": 0.5715,
+      "step": 119
+    },
+    {
+      "epoch": 0.00957911752379812,
+      "grad_norm": 0.43581992387771606,
+      "learning_rate": 0.00019999840610516523,
+      "loss": 0.3993,
+      "step": 120
+    },
+    {
+      "epoch": 0.009658943503163105,
+      "grad_norm": 0.3481132984161377,
+      "learning_rate": 0.0001999983704885996,
+      "loss": 0.6186,
+      "step": 121
+    },
+    {
+      "epoch": 0.009738769482528088,
+      "grad_norm": 0.4838206470012665,
+      "learning_rate": 0.00019999833447848506,
+      "loss": 0.5156,
+      "step": 122
+    },
+    {
+      "epoch": 0.009818595461893074,
+      "grad_norm": 0.4503454566001892,
+      "learning_rate": 0.00019999829807482175,
+      "loss": 0.4654,
+      "step": 123
+    },
+    {
+      "epoch": 0.009898421441258057,
+      "grad_norm": 0.5744187831878662,
+      "learning_rate": 0.00019999826127760982,
+      "loss": 0.5526,
+      "step": 124
+    },
+    {
+      "epoch": 0.009978247420623042,
+      "grad_norm": 0.41850605607032776,
+      "learning_rate": 0.0001999982240868494,
+      "loss": 0.5531,
+      "step": 125
+    },
+    {
+      "epoch": 0.010058073399988026,
+      "grad_norm": 0.4065703749656677,
+      "learning_rate": 0.00019999818650254063,
+      "loss": 0.4563,
+      "step": 126
+    },
+    {
+      "epoch": 0.01013789937935301,
+      "grad_norm": 0.4612256586551666,
+      "learning_rate": 0.0001999981485246837,
+      "loss": 0.5501,
+      "step": 127
+    },
+    {
+      "epoch": 0.010217725358717995,
+      "grad_norm": 0.5699310898780823,
+      "learning_rate": 0.00019999811015327873,
+      "loss": 0.4936,
+      "step": 128
+    },
+    {
+      "epoch": 0.010297551338082979,
+      "grad_norm": 0.3447057604789734,
+      "learning_rate": 0.0001999980713883258,
+      "loss": 0.3729,
+      "step": 129
+    },
+    {
+      "epoch": 0.010377377317447964,
+      "grad_norm": 0.6038820743560791,
+      "learning_rate": 0.0001999980322298252,
+      "loss": 0.7055,
+      "step": 130
+    },
+    {
+      "epoch": 0.010457203296812947,
+      "grad_norm": 0.418125718832016,
+      "learning_rate": 0.00019999799267777704,
+      "loss": 0.4982,
+      "step": 131
+    },
+    {
+      "epoch": 0.010537029276177933,
+      "grad_norm": 0.4340413510799408,
+      "learning_rate": 0.0001999979527321814,
+      "loss": 0.456,
+      "step": 132
+    },
+    {
+      "epoch": 0.010616855255542916,
+      "grad_norm": 0.41115614771842957,
+      "learning_rate": 0.00019999791239303853,
+      "loss": 0.5136,
+      "step": 133
+    },
+    {
+      "epoch": 0.0106966812349079,
+      "grad_norm": 0.34936976432800293,
+      "learning_rate": 0.00019999787166034854,
+      "loss": 0.3294,
+      "step": 134
+    },
+    {
+      "epoch": 0.010776507214272885,
+      "grad_norm": 0.4253373146057129,
+      "learning_rate": 0.0001999978305341116,
+      "loss": 0.4935,
+      "step": 135
+    },
+    {
+      "epoch": 0.010856333193637869,
+      "grad_norm": 0.953768789768219,
+      "learning_rate": 0.00019999778901432788,
+      "loss": 0.4692,
+      "step": 136
+    },
+    {
+      "epoch": 0.010936159173002854,
+      "grad_norm": 0.4897603392601013,
+      "learning_rate": 0.0001999977471009975,
+      "loss": 0.5034,
+      "step": 137
+    },
+    {
+      "epoch": 0.011015985152367838,
+      "grad_norm": 0.710496187210083,
+      "learning_rate": 0.0001999977047941207,
+      "loss": 0.4708,
+      "step": 138
+    },
+    {
+      "epoch": 0.011095811131732823,
+      "grad_norm": 0.3537067174911499,
+      "learning_rate": 0.0001999976620936976,
+      "loss": 0.4012,
+      "step": 139
+    },
+    {
+      "epoch": 0.011175637111097807,
+      "grad_norm": 0.6554028987884521,
+      "learning_rate": 0.00019999761899972836,
+      "loss": 0.4493,
+      "step": 140
+    },
+    {
+      "epoch": 0.01125546309046279,
+      "grad_norm": 0.3419398069381714,
+      "learning_rate": 0.00019999757551221315,
+      "loss": 0.3197,
+      "step": 141
+    },
+    {
+      "epoch": 0.011335289069827776,
+      "grad_norm": 0.5509824156761169,
+      "learning_rate": 0.0001999975316311522,
+      "loss": 0.5036,
+      "step": 142
+    },
+    {
+      "epoch": 0.01141511504919276,
+      "grad_norm": 0.3651215136051178,
+      "learning_rate": 0.00019999748735654565,
+      "loss": 0.4805,
+      "step": 143
+    },
+    {
+      "epoch": 0.011494941028557745,
+      "grad_norm": 0.45155274868011475,
+      "learning_rate": 0.0001999974426883936,
+      "loss": 0.5689,
+      "step": 144
+    },
+    {
+      "epoch": 0.011574767007922728,
+      "grad_norm": 0.39543208479881287,
+      "learning_rate": 0.00019999739762669634,
+      "loss": 0.4676,
+      "step": 145
+    },
+    {
+      "epoch": 0.011654592987287713,
+      "grad_norm": 0.41634100675582886,
+      "learning_rate": 0.00019999735217145396,
+      "loss": 0.3764,
+      "step": 146
+    },
+    {
+      "epoch": 0.011734418966652697,
+      "grad_norm": 0.41329681873321533,
+      "learning_rate": 0.00019999730632266668,
+      "loss": 0.4684,
+      "step": 147
+    },
+    {
+      "epoch": 0.01181424494601768,
+      "grad_norm": 0.46196430921554565,
+      "learning_rate": 0.00019999726008033473,
+      "loss": 0.5029,
+      "step": 148
+    },
+    {
+      "epoch": 0.011894070925382666,
+      "grad_norm": 0.39667192101478577,
+      "learning_rate": 0.0001999972134444582,
+      "loss": 0.5727,
+      "step": 149
+    },
+    {
+      "epoch": 0.01197389690474765,
+      "grad_norm": 0.5304478406906128,
+      "learning_rate": 0.00019999716641503728,
+      "loss": 0.5028,
+      "step": 150
+    },
+    {
+      "epoch": 0.012053722884112635,
+      "grad_norm": 0.45046842098236084,
+      "learning_rate": 0.00019999711899207223,
+      "loss": 0.4463,
+      "step": 151
+    },
+    {
+      "epoch": 0.012133548863477618,
+      "grad_norm": 0.3761225938796997,
+      "learning_rate": 0.00019999707117556315,
+      "loss": 0.4575,
+      "step": 152
+    },
+    {
+      "epoch": 0.012213374842842604,
+      "grad_norm": 0.431652694940567,
+      "learning_rate": 0.00019999702296551032,
+      "loss": 0.5657,
+      "step": 153
+    },
+    {
+      "epoch": 0.012293200822207587,
+      "grad_norm": 0.41577762365341187,
+      "learning_rate": 0.00019999697436191385,
+      "loss": 0.5801,
+      "step": 154
+    },
+    {
+      "epoch": 0.012373026801572571,
+      "grad_norm": 0.5159163475036621,
+      "learning_rate": 0.00019999692536477396,
+      "loss": 0.5583,
+      "step": 155
+    },
+    {
+      "epoch": 0.012452852780937556,
+      "grad_norm": 0.5098326206207275,
+      "learning_rate": 0.00019999687597409084,
+      "loss": 0.5363,
+      "step": 156
+    },
+    {
+      "epoch": 0.01253267876030254,
+      "grad_norm": 0.37459591031074524,
+      "learning_rate": 0.00019999682618986473,
+      "loss": 0.5337,
+      "step": 157
+    },
+    {
+      "epoch": 0.012612504739667525,
+      "grad_norm": 0.4354023337364197,
+      "learning_rate": 0.00019999677601209576,
+      "loss": 0.4784,
+      "step": 158
+    },
+    {
+      "epoch": 0.012692330719032509,
+      "grad_norm": 0.3902154266834259,
+      "learning_rate": 0.00019999672544078413,
+      "loss": 0.3685,
+      "step": 159
+    },
+    {
+      "epoch": 0.012772156698397494,
+      "grad_norm": 0.5335967540740967,
+      "learning_rate": 0.0001999966744759301,
+      "loss": 0.6618,
+      "step": 160
+    },
+    {
+      "epoch": 0.012851982677762478,
+      "grad_norm": 0.46829479932785034,
+      "learning_rate": 0.0001999966231175338,
+      "loss": 0.4813,
+      "step": 161
+    },
+    {
+      "epoch": 0.012931808657127461,
+      "grad_norm": 0.4770427644252777,
+      "learning_rate": 0.0001999965713655955,
+      "loss": 0.3673,
+      "step": 162
+    },
+    {
+      "epoch": 0.013011634636492447,
+      "grad_norm": 0.43711262941360474,
+      "learning_rate": 0.00019999651922011534,
+      "loss": 0.5659,
+      "step": 163
+    },
+    {
+      "epoch": 0.01309146061585743,
+      "grad_norm": 0.35760849714279175,
+      "learning_rate": 0.00019999646668109356,
+      "loss": 0.3083,
+      "step": 164
+    },
+    {
+      "epoch": 0.013171286595222416,
+      "grad_norm": 0.5012556910514832,
+      "learning_rate": 0.00019999641374853036,
+      "loss": 0.5947,
+      "step": 165
+    },
+    {
+      "epoch": 0.0132511125745874,
+      "grad_norm": 1.034009337425232,
+      "learning_rate": 0.00019999636042242595,
+      "loss": 0.4826,
+      "step": 166
+    },
+    {
+      "epoch": 0.013330938553952384,
+      "grad_norm": 0.4241684675216675,
+      "learning_rate": 0.00019999630670278052,
+      "loss": 0.507,
+      "step": 167
+    },
+    {
+      "epoch": 0.013410764533317368,
+      "grad_norm": 0.6414814591407776,
+      "learning_rate": 0.00019999625258959434,
+      "loss": 0.6684,
+      "step": 168
+    },
+    {
+      "epoch": 0.013490590512682352,
+      "grad_norm": 0.56517493724823,
+      "learning_rate": 0.00019999619808286755,
+      "loss": 0.4408,
+      "step": 169
+    },
+    {
+      "epoch": 0.013570416492047337,
+      "grad_norm": 0.43821126222610474,
+      "learning_rate": 0.00019999614318260043,
+      "loss": 0.5258,
+      "step": 170
+    },
+    {
+      "epoch": 0.01365024247141232,
+      "grad_norm": 0.4854287803173065,
+      "learning_rate": 0.00019999608788879311,
+      "loss": 0.5077,
+      "step": 171
+    },
+    {
+      "epoch": 0.013730068450777306,
+      "grad_norm": 0.46524420380592346,
+      "learning_rate": 0.0001999960322014459,
+      "loss": 0.5869,
+      "step": 172
+    },
+    {
+      "epoch": 0.01380989443014229,
+      "grad_norm": 0.5089438557624817,
+      "learning_rate": 0.000199995976120559,
+      "loss": 0.5245,
+      "step": 173
+    },
+    {
+      "epoch": 0.013889720409507275,
+      "grad_norm": 0.623849630355835,
+      "learning_rate": 0.00019999591964613256,
+      "loss": 0.5839,
+      "step": 174
+    },
+    {
+      "epoch": 0.013969546388872258,
+      "grad_norm": 0.6017373204231262,
+      "learning_rate": 0.00019999586277816687,
+      "loss": 0.5344,
+      "step": 175
+    },
+    {
+      "epoch": 0.014049372368237242,
+      "grad_norm": 0.5433600544929504,
+      "learning_rate": 0.00019999580551666215,
+      "loss": 0.5068,
+      "step": 176
+    },
+    {
+      "epoch": 0.014129198347602227,
+      "grad_norm": 0.42345139384269714,
+      "learning_rate": 0.00019999574786161862,
+      "loss": 0.4692,
+      "step": 177
+    },
+    {
+      "epoch": 0.014209024326967211,
+      "grad_norm": 0.4489782154560089,
+      "learning_rate": 0.00019999568981303646,
+      "loss": 0.4773,
+      "step": 178
+    },
+    {
+      "epoch": 0.014288850306332196,
+      "grad_norm": 0.5150318145751953,
+      "learning_rate": 0.00019999563137091598,
+      "loss": 0.476,
+      "step": 179
+    },
+    {
+      "epoch": 0.01436867628569718,
+      "grad_norm": 0.43261510133743286,
+      "learning_rate": 0.00019999557253525733,
+      "loss": 0.624,
+      "step": 180
+    },
+    {
+      "epoch": 0.014448502265062165,
+      "grad_norm": 0.5488516092300415,
+      "learning_rate": 0.00019999551330606078,
+      "loss": 0.5521,
+      "step": 181
+    },
+    {
+      "epoch": 0.014528328244427149,
+      "grad_norm": 0.3631516098976135,
+      "learning_rate": 0.0001999954536833266,
+      "loss": 0.5664,
+      "step": 182
+    },
+    {
+      "epoch": 0.014608154223792132,
+      "grad_norm": 0.5660406947135925,
+      "learning_rate": 0.00019999539366705497,
+      "loss": 0.5762,
+      "step": 183
+    },
+    {
+      "epoch": 0.014687980203157118,
+      "grad_norm": 0.573652982711792,
+      "learning_rate": 0.00019999533325724614,
+      "loss": 0.4972,
+      "step": 184
+    },
+    {
+      "epoch": 0.014767806182522101,
+      "grad_norm": 0.4937921464443207,
+      "learning_rate": 0.00019999527245390035,
+      "loss": 0.5381,
+      "step": 185
+    },
+    {
+      "epoch": 0.014847632161887087,
+      "grad_norm": 0.4351513385772705,
+      "learning_rate": 0.00019999521125701783,
+      "loss": 0.5155,
+      "step": 186
+    },
+    {
+      "epoch": 0.01492745814125207,
+      "grad_norm": 0.34618648886680603,
+      "learning_rate": 0.00019999514966659882,
+      "loss": 0.3974,
+      "step": 187
+    },
+    {
+      "epoch": 0.015007284120617055,
+      "grad_norm": 0.3626372218132019,
+      "learning_rate": 0.0001999950876826436,
+      "loss": 0.3608,
+      "step": 188
+    },
+    {
+      "epoch": 0.015087110099982039,
+      "grad_norm": 0.5802507996559143,
+      "learning_rate": 0.00019999502530515238,
+      "loss": 0.4703,
+      "step": 189
+    },
+    {
+      "epoch": 0.015166936079347023,
+      "grad_norm": 0.4644535481929779,
+      "learning_rate": 0.00019999496253412543,
+      "loss": 0.4354,
+      "step": 190
+    },
+    {
+      "epoch": 0.015246762058712008,
+      "grad_norm": 0.37288615107536316,
+      "learning_rate": 0.00019999489936956298,
+      "loss": 0.4624,
+      "step": 191
+    },
+    {
+      "epoch": 0.015326588038076992,
+      "grad_norm": 0.4151481091976166,
+      "learning_rate": 0.00019999483581146523,
+      "loss": 0.405,
+      "step": 192
+    },
+    {
+      "epoch": 0.015406414017441977,
+      "grad_norm": 0.38800281286239624,
+      "learning_rate": 0.0001999947718598325,
+      "loss": 0.5023,
+      "step": 193
+    },
+    {
+      "epoch": 0.01548623999680696,
+      "grad_norm": 0.394400030374527,
+      "learning_rate": 0.00019999470751466504,
+      "loss": 0.6128,
+      "step": 194
+    },
+    {
+      "epoch": 0.015566065976171946,
+      "grad_norm": 0.48949894309043884,
+      "learning_rate": 0.00019999464277596307,
+      "loss": 0.4574,
+      "step": 195
+    },
+    {
+      "epoch": 0.01564589195553693,
+      "grad_norm": 0.4290977716445923,
+      "learning_rate": 0.00019999457764372687,
+      "loss": 0.5009,
+      "step": 196
+    },
+    {
+      "epoch": 0.015725717934901913,
+      "grad_norm": 0.5243070721626282,
+      "learning_rate": 0.00019999451211795668,
+      "loss": 0.3696,
+      "step": 197
+    },
+    {
+      "epoch": 0.015805543914266897,
+      "grad_norm": 0.5894675850868225,
+      "learning_rate": 0.00019999444619865276,
+      "loss": 0.5897,
+      "step": 198
+    },
+    {
+      "epoch": 0.015885369893631884,
+      "grad_norm": 0.3214614987373352,
+      "learning_rate": 0.00019999437988581535,
+      "loss": 0.3502,
+      "step": 199
+    },
+    {
+      "epoch": 0.015965195872996867,
+      "grad_norm": 0.42068052291870117,
+      "learning_rate": 0.00019999431317944475,
+      "loss": 0.6079,
+      "step": 200
+    },
+    {
+      "epoch": 0.015965195872996867,
+      "eval_loss": 0.48710426688194275,
+      "eval_runtime": 34.115,
+      "eval_samples_per_second": 7.387,
+      "eval_steps_per_second": 7.387,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 50108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 1.003600228122624e+16,
+  "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:b4b828da2213b3921a3d64e28255ff281633a5fab3de1cdbdcc0a56a84d9f94a
+size 6776