Training in progress, step 200, checkpoint

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/Phi-3-mini-4k-instruct
+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 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "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_up_proj",
+    "down_proj",
+    "qkv_proj",
+    "o_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:dafa4b35903272d9a5875a528613d55b70de489a4cba4b0c5d90b8e7372447d6
+size 201361312

last-checkpoint/added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cf933217f2a1496df6e505c373994ec60d2e9cb4e4182654a65e173712ea973
+size 102537556

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fe7d0a617f855b2bc9dfdd7c58ade6a034334dc9ab8264f32d86ab4c71b68ff
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2a83f712de79bb514499d2ca3730c9bd34c456c994df59c25a6345a223b9b1e
+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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "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 +1,131 @@
+{
+  "add_bos_token": false,
+  "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": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "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": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,1458 @@
+{
+  "best_metric": 1.6985455751419067,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.009545286418250587,
+  "eval_steps": 200,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 4.772643209125294e-05,
+      "grad_norm": 8.156052589416504,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 12.5501,
+      "step": 1
+    },
+    {
+      "epoch": 4.772643209125294e-05,
+      "eval_loss": 3.1170473098754883,
+      "eval_runtime": 95.9454,
+      "eval_samples_per_second": 8.786,
+      "eval_steps_per_second": 4.398,
+      "step": 1
+    },
+    {
+      "epoch": 9.545286418250588e-05,
+      "grad_norm": 9.274253845214844,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 12.0242,
+      "step": 2
+    },
+    {
+      "epoch": 0.00014317929627375881,
+      "grad_norm": 7.303795337677002,
+      "learning_rate": 2e-05,
+      "loss": 12.9485,
+      "step": 3
+    },
+    {
+      "epoch": 0.00019090572836501175,
+      "grad_norm": 8.46444320678711,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 13.4995,
+      "step": 4
+    },
+    {
+      "epoch": 0.0002386321604562647,
+      "grad_norm": 15.278627395629883,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 12.9846,
+      "step": 5
+    },
+    {
+      "epoch": 0.00028635859254751763,
+      "grad_norm": 13.401786804199219,
+      "learning_rate": 4e-05,
+      "loss": 13.6205,
+      "step": 6
+    },
+    {
+      "epoch": 0.00033408502463877054,
+      "grad_norm": 11.049997329711914,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 10.501,
+      "step": 7
+    },
+    {
+      "epoch": 0.0003818114567300235,
+      "grad_norm": 7.455288887023926,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 9.7858,
+      "step": 8
+    },
+    {
+      "epoch": 0.0004295378888212764,
+      "grad_norm": 8.7234468460083,
+      "learning_rate": 6e-05,
+      "loss": 14.5011,
+      "step": 9
+    },
+    {
+      "epoch": 0.0004772643209125294,
+      "grad_norm": 12.033916473388672,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 14.7143,
+      "step": 10
+    },
+    {
+      "epoch": 0.0005249907530037823,
+      "grad_norm": 8.46088981628418,
+      "learning_rate": 7.333333333333333e-05,
+      "loss": 10.654,
+      "step": 11
+    },
+    {
+      "epoch": 0.0005727171850950353,
+      "grad_norm": 6.730998516082764,
+      "learning_rate": 8e-05,
+      "loss": 9.5019,
+      "step": 12
+    },
+    {
+      "epoch": 0.0006204436171862882,
+      "grad_norm": 9.581258773803711,
+      "learning_rate": 8.666666666666667e-05,
+      "loss": 13.3483,
+      "step": 13
+    },
+    {
+      "epoch": 0.0006681700492775411,
+      "grad_norm": 9.198789596557617,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 11.0057,
+      "step": 14
+    },
+    {
+      "epoch": 0.000715896481368794,
+      "grad_norm": 9.850581169128418,
+      "learning_rate": 0.0001,
+      "loss": 9.8186,
+      "step": 15
+    },
+    {
+      "epoch": 0.000763622913460047,
+      "grad_norm": 6.305893898010254,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 8.5701,
+      "step": 16
+    },
+    {
+      "epoch": 0.0008113493455513,
+      "grad_norm": 13.963780403137207,
+      "learning_rate": 0.00011333333333333334,
+      "loss": 12.3859,
+      "step": 17
+    },
+    {
+      "epoch": 0.0008590757776425528,
+      "grad_norm": 9.068361282348633,
+      "learning_rate": 0.00012,
+      "loss": 9.8092,
+      "step": 18
+    },
+    {
+      "epoch": 0.0009068022097338058,
+      "grad_norm": 7.555756092071533,
+      "learning_rate": 0.00012666666666666666,
+      "loss": 8.3725,
+      "step": 19
+    },
+    {
+      "epoch": 0.0009545286418250588,
+      "grad_norm": 8.059484481811523,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 9.078,
+      "step": 20
+    },
+    {
+      "epoch": 0.0010022550739163117,
+      "grad_norm": 8.002023696899414,
+      "learning_rate": 0.00014,
+      "loss": 8.0143,
+      "step": 21
+    },
+    {
+      "epoch": 0.0010499815060075646,
+      "grad_norm": 7.968870162963867,
+      "learning_rate": 0.00014666666666666666,
+      "loss": 9.9062,
+      "step": 22
+    },
+    {
+      "epoch": 0.0010977079380988177,
+      "grad_norm": 7.092574119567871,
+      "learning_rate": 0.00015333333333333334,
+      "loss": 8.0895,
+      "step": 23
+    },
+    {
+      "epoch": 0.0011454343701900705,
+      "grad_norm": 6.445763111114502,
+      "learning_rate": 0.00016,
+      "loss": 8.1857,
+      "step": 24
+    },
+    {
+      "epoch": 0.0011931608022813234,
+      "grad_norm": 6.455519676208496,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 7.3903,
+      "step": 25
+    },
+    {
+      "epoch": 0.0012408872343725764,
+      "grad_norm": 5.985039234161377,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 7.787,
+      "step": 26
+    },
+    {
+      "epoch": 0.0012886136664638293,
+      "grad_norm": 5.788380146026611,
+      "learning_rate": 0.00018,
+      "loss": 7.7579,
+      "step": 27
+    },
+    {
+      "epoch": 0.0013363400985550822,
+      "grad_norm": 7.366934299468994,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 8.845,
+      "step": 28
+    },
+    {
+      "epoch": 0.0013840665306463352,
+      "grad_norm": 6.39143180847168,
+      "learning_rate": 0.00019333333333333333,
+      "loss": 7.9672,
+      "step": 29
+    },
+    {
+      "epoch": 0.001431792962737588,
+      "grad_norm": 5.3974289894104,
+      "learning_rate": 0.0002,
+      "loss": 6.9981,
+      "step": 30
+    },
+    {
+      "epoch": 0.0014795193948288412,
+      "grad_norm": 9.380810737609863,
+      "learning_rate": 0.00019999999987497673,
+      "loss": 7.2882,
+      "step": 31
+    },
+    {
+      "epoch": 0.001527245826920094,
+      "grad_norm": 6.234286785125732,
+      "learning_rate": 0.00019999999949990685,
+      "loss": 7.2575,
+      "step": 32
+    },
+    {
+      "epoch": 0.0015749722590113469,
+      "grad_norm": 7.635664463043213,
+      "learning_rate": 0.00019999999887479038,
+      "loss": 9.1833,
+      "step": 33
+    },
+    {
+      "epoch": 0.0016226986911026,
+      "grad_norm": 5.845251083374023,
+      "learning_rate": 0.00019999999799962735,
+      "loss": 6.3639,
+      "step": 34
+    },
+    {
+      "epoch": 0.0016704251231938528,
+      "grad_norm": 6.020627021789551,
+      "learning_rate": 0.00019999999687441772,
+      "loss": 8.5162,
+      "step": 35
+    },
+    {
+      "epoch": 0.0017181515552851057,
+      "grad_norm": 7.508661270141602,
+      "learning_rate": 0.00019999999549916153,
+      "loss": 7.2014,
+      "step": 36
+    },
+    {
+      "epoch": 0.0017658779873763587,
+      "grad_norm": 63.37688446044922,
+      "learning_rate": 0.00019999999387385878,
+      "loss": 8.6904,
+      "step": 37
+    },
+    {
+      "epoch": 0.0018136044194676116,
+      "grad_norm": 6.846808433532715,
+      "learning_rate": 0.00019999999199850943,
+      "loss": 9.6905,
+      "step": 38
+    },
+    {
+      "epoch": 0.0018613308515588647,
+      "grad_norm": 7.53931999206543,
+      "learning_rate": 0.0001999999898731135,
+      "loss": 7.0634,
+      "step": 39
+    },
+    {
+      "epoch": 0.0019090572836501175,
+      "grad_norm": 7.517793655395508,
+      "learning_rate": 0.00019999998749767108,
+      "loss": 8.7579,
+      "step": 40
+    },
+    {
+      "epoch": 0.0019567837157413704,
+      "grad_norm": 6.793584823608398,
+      "learning_rate": 0.00019999998487218207,
+      "loss": 6.5392,
+      "step": 41
+    },
+    {
+      "epoch": 0.0020045101478326235,
+      "grad_norm": 5.361453056335449,
+      "learning_rate": 0.0001999999819966465,
+      "loss": 7.2578,
+      "step": 42
+    },
+    {
+      "epoch": 0.0020522365799238765,
+      "grad_norm": 5.260591506958008,
+      "learning_rate": 0.00019999997887106444,
+      "loss": 6.9882,
+      "step": 43
+    },
+    {
+      "epoch": 0.002099963012015129,
+      "grad_norm": 5.026567459106445,
+      "learning_rate": 0.0001999999754954358,
+      "loss": 6.6926,
+      "step": 44
+    },
+    {
+      "epoch": 0.0021476894441063822,
+      "grad_norm": 4.541498184204102,
+      "learning_rate": 0.00019999997186976066,
+      "loss": 5.9309,
+      "step": 45
+    },
+    {
+      "epoch": 0.0021954158761976353,
+      "grad_norm": 4.459763050079346,
+      "learning_rate": 0.000199999967994039,
+      "loss": 5.5164,
+      "step": 46
+    },
+    {
+      "epoch": 0.002243142308288888,
+      "grad_norm": 5.727092266082764,
+      "learning_rate": 0.00019999996386827084,
+      "loss": 6.5041,
+      "step": 47
+    },
+    {
+      "epoch": 0.002290868740380141,
+      "grad_norm": 5.828995227813721,
+      "learning_rate": 0.00019999995949245616,
+      "loss": 8.1646,
+      "step": 48
+    },
+    {
+      "epoch": 0.002338595172471394,
+      "grad_norm": 5.327517509460449,
+      "learning_rate": 0.00019999995486659505,
+      "loss": 5.8227,
+      "step": 49
+    },
+    {
+      "epoch": 0.0023863216045626467,
+      "grad_norm": 6.896716117858887,
+      "learning_rate": 0.0001999999499906874,
+      "loss": 7.6883,
+      "step": 50
+    },
+    {
+      "epoch": 0.0024340480366539,
+      "grad_norm": 7.029616832733154,
+      "learning_rate": 0.00019999994486473335,
+      "loss": 8.2224,
+      "step": 51
+    },
+    {
+      "epoch": 0.002481774468745153,
+      "grad_norm": 8.25517749786377,
+      "learning_rate": 0.00019999993948873284,
+      "loss": 8.5333,
+      "step": 52
+    },
+    {
+      "epoch": 0.0025295009008364055,
+      "grad_norm": 7.740312576293945,
+      "learning_rate": 0.0001999999338626859,
+      "loss": 9.7768,
+      "step": 53
+    },
+    {
+      "epoch": 0.0025772273329276586,
+      "grad_norm": 8.219902992248535,
+      "learning_rate": 0.00019999992798659254,
+      "loss": 9.2211,
+      "step": 54
+    },
+    {
+      "epoch": 0.0026249537650189117,
+      "grad_norm": 5.783295154571533,
+      "learning_rate": 0.00019999992186045277,
+      "loss": 5.6035,
+      "step": 55
+    },
+    {
+      "epoch": 0.0026726801971101643,
+      "grad_norm": 6.954888820648193,
+      "learning_rate": 0.0001999999154842666,
+      "loss": 7.6935,
+      "step": 56
+    },
+    {
+      "epoch": 0.0027204066292014174,
+      "grad_norm": 4.878210544586182,
+      "learning_rate": 0.00019999990885803407,
+      "loss": 4.9927,
+      "step": 57
+    },
+    {
+      "epoch": 0.0027681330612926705,
+      "grad_norm": 8.59322738647461,
+      "learning_rate": 0.00019999990198175518,
+      "loss": 8.2478,
+      "step": 58
+    },
+    {
+      "epoch": 0.0028158594933839235,
+      "grad_norm": 7.328903675079346,
+      "learning_rate": 0.00019999989485542996,
+      "loss": 7.7432,
+      "step": 59
+    },
+    {
+      "epoch": 0.002863585925475176,
+      "grad_norm": 7.1839599609375,
+      "learning_rate": 0.00019999988747905842,
+      "loss": 8.6058,
+      "step": 60
+    },
+    {
+      "epoch": 0.0029113123575664293,
+      "grad_norm": 6.993515491485596,
+      "learning_rate": 0.00019999987985264058,
+      "loss": 8.6523,
+      "step": 61
+    },
+    {
+      "epoch": 0.0029590387896576823,
+      "grad_norm": 7.754829406738281,
+      "learning_rate": 0.00019999987197617643,
+      "loss": 7.7147,
+      "step": 62
+    },
+    {
+      "epoch": 0.003006765221748935,
+      "grad_norm": 6.434046268463135,
+      "learning_rate": 0.00019999986384966603,
+      "loss": 6.4865,
+      "step": 63
+    },
+    {
+      "epoch": 0.003054491653840188,
+      "grad_norm": 4.396024703979492,
+      "learning_rate": 0.0001999998554731094,
+      "loss": 5.6103,
+      "step": 64
+    },
+    {
+      "epoch": 0.003102218085931441,
+      "grad_norm": 5.07852840423584,
+      "learning_rate": 0.00019999984684650654,
+      "loss": 7.4121,
+      "step": 65
+    },
+    {
+      "epoch": 0.0031499445180226938,
+      "grad_norm": 6.753673076629639,
+      "learning_rate": 0.00019999983796985748,
+      "loss": 7.207,
+      "step": 66
+    },
+    {
+      "epoch": 0.003197670950113947,
+      "grad_norm": 5.469264030456543,
+      "learning_rate": 0.00019999982884316223,
+      "loss": 5.161,
+      "step": 67
+    },
+    {
+      "epoch": 0.0032453973822052,
+      "grad_norm": 6.778441905975342,
+      "learning_rate": 0.00019999981946642085,
+      "loss": 6.7959,
+      "step": 68
+    },
+    {
+      "epoch": 0.0032931238142964525,
+      "grad_norm": 5.161728382110596,
+      "learning_rate": 0.0001999998098396333,
+      "loss": 6.7924,
+      "step": 69
+    },
+    {
+      "epoch": 0.0033408502463877056,
+      "grad_norm": 6.251170635223389,
+      "learning_rate": 0.0001999997999627997,
+      "loss": 7.2183,
+      "step": 70
+    },
+    {
+      "epoch": 0.0033885766784789587,
+      "grad_norm": 6.930290222167969,
+      "learning_rate": 0.00019999978983591997,
+      "loss": 7.5263,
+      "step": 71
+    },
+    {
+      "epoch": 0.0034363031105702113,
+      "grad_norm": 7.092405796051025,
+      "learning_rate": 0.0001999997794589942,
+      "loss": 9.01,
+      "step": 72
+    },
+    {
+      "epoch": 0.0034840295426614644,
+      "grad_norm": 6.196310997009277,
+      "learning_rate": 0.00019999976883202237,
+      "loss": 7.5049,
+      "step": 73
+    },
+    {
+      "epoch": 0.0035317559747527175,
+      "grad_norm": 5.769287586212158,
+      "learning_rate": 0.00019999975795500455,
+      "loss": 7.797,
+      "step": 74
+    },
+    {
+      "epoch": 0.0035794824068439706,
+      "grad_norm": 5.971030235290527,
+      "learning_rate": 0.00019999974682794076,
+      "loss": 6.4961,
+      "step": 75
+    },
+    {
+      "epoch": 0.003627208838935223,
+      "grad_norm": 4.6939697265625,
+      "learning_rate": 0.000199999735450831,
+      "loss": 6.9824,
+      "step": 76
+    },
+    {
+      "epoch": 0.0036749352710264763,
+      "grad_norm": 7.828939437866211,
+      "learning_rate": 0.00019999972382367536,
+      "loss": 10.0984,
+      "step": 77
+    },
+    {
+      "epoch": 0.0037226617031177293,
+      "grad_norm": 5.222005367279053,
+      "learning_rate": 0.00019999971194647377,
+      "loss": 7.0103,
+      "step": 78
+    },
+    {
+      "epoch": 0.003770388135208982,
+      "grad_norm": 5.610576152801514,
+      "learning_rate": 0.00019999969981922638,
+      "loss": 7.0152,
+      "step": 79
+    },
+    {
+      "epoch": 0.003818114567300235,
+      "grad_norm": 7.603675842285156,
+      "learning_rate": 0.00019999968744193312,
+      "loss": 6.8389,
+      "step": 80
+    },
+    {
+      "epoch": 0.003865840999391488,
+      "grad_norm": 5.232549667358398,
+      "learning_rate": 0.00019999967481459406,
+      "loss": 6.354,
+      "step": 81
+    },
+    {
+      "epoch": 0.003913567431482741,
+      "grad_norm": 6.516291618347168,
+      "learning_rate": 0.00019999966193720922,
+      "loss": 7.2243,
+      "step": 82
+    },
+    {
+      "epoch": 0.003961293863573994,
+      "grad_norm": 5.813276290893555,
+      "learning_rate": 0.00019999964880977866,
+      "loss": 6.343,
+      "step": 83
+    },
+    {
+      "epoch": 0.004009020295665247,
+      "grad_norm": 4.524149417877197,
+      "learning_rate": 0.0001999996354323024,
+      "loss": 7.7151,
+      "step": 84
+    },
+    {
+      "epoch": 0.0040567467277565,
+      "grad_norm": 4.268386363983154,
+      "learning_rate": 0.00019999962180478043,
+      "loss": 6.0883,
+      "step": 85
+    },
+    {
+      "epoch": 0.004104473159847753,
+      "grad_norm": 16.34364891052246,
+      "learning_rate": 0.00019999960792721285,
+      "loss": 10.0296,
+      "step": 86
+    },
+    {
+      "epoch": 0.004152199591939005,
+      "grad_norm": 4.498778820037842,
+      "learning_rate": 0.00019999959379959968,
+      "loss": 7.1151,
+      "step": 87
+    },
+    {
+      "epoch": 0.004199926024030258,
+      "grad_norm": 5.004024028778076,
+      "learning_rate": 0.00019999957942194092,
+      "loss": 6.8547,
+      "step": 88
+    },
+    {
+      "epoch": 0.004247652456121511,
+      "grad_norm": 5.410999298095703,
+      "learning_rate": 0.00019999956479423663,
+      "loss": 7.0691,
+      "step": 89
+    },
+    {
+      "epoch": 0.0042953788882127645,
+      "grad_norm": 5.083662033081055,
+      "learning_rate": 0.00019999954991648683,
+      "loss": 7.1524,
+      "step": 90
+    },
+    {
+      "epoch": 0.004343105320304018,
+      "grad_norm": 4.258586406707764,
+      "learning_rate": 0.0001999995347886916,
+      "loss": 6.7408,
+      "step": 91
+    },
+    {
+      "epoch": 0.004390831752395271,
+      "grad_norm": 3.56187105178833,
+      "learning_rate": 0.00019999951941085097,
+      "loss": 4.324,
+      "step": 92
+    },
+    {
+      "epoch": 0.004438558184486523,
+      "grad_norm": 5.012781143188477,
+      "learning_rate": 0.0001999995037829649,
+      "loss": 6.2041,
+      "step": 93
+    },
+    {
+      "epoch": 0.004486284616577776,
+      "grad_norm": 6.942680835723877,
+      "learning_rate": 0.0001999994879050335,
+      "loss": 5.8268,
+      "step": 94
+    },
+    {
+      "epoch": 0.004534011048669029,
+      "grad_norm": 5.844181060791016,
+      "learning_rate": 0.0001999994717770568,
+      "loss": 6.4547,
+      "step": 95
+    },
+    {
+      "epoch": 0.004581737480760282,
+      "grad_norm": 5.277218341827393,
+      "learning_rate": 0.00019999945539903486,
+      "loss": 6.5379,
+      "step": 96
+    },
+    {
+      "epoch": 0.004629463912851535,
+      "grad_norm": 6.048219680786133,
+      "learning_rate": 0.0001999994387709677,
+      "loss": 6.9474,
+      "step": 97
+    },
+    {
+      "epoch": 0.004677190344942788,
+      "grad_norm": 10.516984939575195,
+      "learning_rate": 0.0001999994218928553,
+      "loss": 6.5548,
+      "step": 98
+    },
+    {
+      "epoch": 0.004724916777034041,
+      "grad_norm": 4.922785758972168,
+      "learning_rate": 0.00019999940476469785,
+      "loss": 6.4903,
+      "step": 99
+    },
+    {
+      "epoch": 0.0047726432091252935,
+      "grad_norm": 5.574140548706055,
+      "learning_rate": 0.00019999938738649524,
+      "loss": 6.753,
+      "step": 100
+    },
+    {
+      "epoch": 0.004820369641216547,
+      "grad_norm": 5.692989349365234,
+      "learning_rate": 0.00019999936975824761,
+      "loss": 7.8935,
+      "step": 101
+    },
+    {
+      "epoch": 0.0048680960733078,
+      "grad_norm": 3.9527132511138916,
+      "learning_rate": 0.00019999935187995496,
+      "loss": 5.6235,
+      "step": 102
+    },
+    {
+      "epoch": 0.004915822505399053,
+      "grad_norm": 4.653379440307617,
+      "learning_rate": 0.00019999933375161737,
+      "loss": 6.1317,
+      "step": 103
+    },
+    {
+      "epoch": 0.004963548937490306,
+      "grad_norm": 5.225219249725342,
+      "learning_rate": 0.00019999931537323482,
+      "loss": 7.7239,
+      "step": 104
+    },
+    {
+      "epoch": 0.005011275369581559,
+      "grad_norm": 5.7530517578125,
+      "learning_rate": 0.00019999929674480743,
+      "loss": 9.6706,
+      "step": 105
+    },
+    {
+      "epoch": 0.005059001801672811,
+      "grad_norm": 4.033590316772461,
+      "learning_rate": 0.0001999992778663352,
+      "loss": 5.506,
+      "step": 106
+    },
+    {
+      "epoch": 0.005106728233764064,
+      "grad_norm": 6.715490341186523,
+      "learning_rate": 0.0001999992587378182,
+      "loss": 7.9386,
+      "step": 107
+    },
+    {
+      "epoch": 0.005154454665855317,
+      "grad_norm": 4.433899402618408,
+      "learning_rate": 0.00019999923935925648,
+      "loss": 7.3948,
+      "step": 108
+    },
+    {
+      "epoch": 0.00520218109794657,
+      "grad_norm": 4.419589519500732,
+      "learning_rate": 0.00019999921973065004,
+      "loss": 5.1343,
+      "step": 109
+    },
+    {
+      "epoch": 0.005249907530037823,
+      "grad_norm": 3.680023193359375,
+      "learning_rate": 0.00019999919985199898,
+      "loss": 5.7496,
+      "step": 110
+    },
+    {
+      "epoch": 0.0052976339621290764,
+      "grad_norm": 4.177944660186768,
+      "learning_rate": 0.00019999917972330334,
+      "loss": 5.9936,
+      "step": 111
+    },
+    {
+      "epoch": 0.005345360394220329,
+      "grad_norm": 4.320446014404297,
+      "learning_rate": 0.0001999991593445632,
+      "loss": 7.4622,
+      "step": 112
+    },
+    {
+      "epoch": 0.005393086826311582,
+      "grad_norm": 3.077852725982666,
+      "learning_rate": 0.00019999913871577855,
+      "loss": 3.8202,
+      "step": 113
+    },
+    {
+      "epoch": 0.005440813258402835,
+      "grad_norm": 4.988670825958252,
+      "learning_rate": 0.0001999991178369495,
+      "loss": 6.3419,
+      "step": 114
+    },
+    {
+      "epoch": 0.005488539690494088,
+      "grad_norm": 6.100823879241943,
+      "learning_rate": 0.00019999909670807603,
+      "loss": 7.4201,
+      "step": 115
+    },
+    {
+      "epoch": 0.005536266122585341,
+      "grad_norm": 5.46522331237793,
+      "learning_rate": 0.00019999907532915824,
+      "loss": 7.8764,
+      "step": 116
+    },
+    {
+      "epoch": 0.005583992554676594,
+      "grad_norm": 5.026033878326416,
+      "learning_rate": 0.0001999990537001962,
+      "loss": 8.8585,
+      "step": 117
+    },
+    {
+      "epoch": 0.005631718986767847,
+      "grad_norm": 5.422964096069336,
+      "learning_rate": 0.0001999990318211899,
+      "loss": 7.0363,
+      "step": 118
+    },
+    {
+      "epoch": 0.005679445418859099,
+      "grad_norm": 5.562786102294922,
+      "learning_rate": 0.0001999990096921395,
+      "loss": 8.6947,
+      "step": 119
+    },
+    {
+      "epoch": 0.005727171850950352,
+      "grad_norm": 4.488889217376709,
+      "learning_rate": 0.00019999898731304496,
+      "loss": 6.6352,
+      "step": 120
+    },
+    {
+      "epoch": 0.0057748982830416054,
+      "grad_norm": 6.206261157989502,
+      "learning_rate": 0.00019999896468390636,
+      "loss": 8.9197,
+      "step": 121
+    },
+    {
+      "epoch": 0.0058226247151328585,
+      "grad_norm": 3.885154962539673,
+      "learning_rate": 0.00019999894180472376,
+      "loss": 6.5824,
+      "step": 122
+    },
+    {
+      "epoch": 0.005870351147224112,
+      "grad_norm": 4.657262325286865,
+      "learning_rate": 0.00019999891867549725,
+      "loss": 7.4743,
+      "step": 123
+    },
+    {
+      "epoch": 0.005918077579315365,
+      "grad_norm": 4.30035924911499,
+      "learning_rate": 0.00019999889529622684,
+      "loss": 7.2783,
+      "step": 124
+    },
+    {
+      "epoch": 0.005965804011406617,
+      "grad_norm": 9.447369575500488,
+      "learning_rate": 0.00019999887166691262,
+      "loss": 7.4739,
+      "step": 125
+    },
+    {
+      "epoch": 0.00601353044349787,
+      "grad_norm": 4.820959568023682,
+      "learning_rate": 0.00019999884778755465,
+      "loss": 6.1332,
+      "step": 126
+    },
+    {
+      "epoch": 0.006061256875589123,
+      "grad_norm": 6.934280872344971,
+      "learning_rate": 0.00019999882365815294,
+      "loss": 6.8292,
+      "step": 127
+    },
+    {
+      "epoch": 0.006108983307680376,
+      "grad_norm": 4.936176776885986,
+      "learning_rate": 0.00019999879927870762,
+      "loss": 8.7501,
+      "step": 128
+    },
+    {
+      "epoch": 0.006156709739771629,
+      "grad_norm": 5.515492916107178,
+      "learning_rate": 0.0001999987746492187,
+      "loss": 7.3772,
+      "step": 129
+    },
+    {
+      "epoch": 0.006204436171862882,
+      "grad_norm": 5.130324363708496,
+      "learning_rate": 0.00019999874976968626,
+      "loss": 9.1506,
+      "step": 130
+    },
+    {
+      "epoch": 0.006252162603954135,
+      "grad_norm": 4.996119976043701,
+      "learning_rate": 0.00019999872464011037,
+      "loss": 6.213,
+      "step": 131
+    },
+    {
+      "epoch": 0.0062998890360453875,
+      "grad_norm": 4.5611114501953125,
+      "learning_rate": 0.0001999986992604911,
+      "loss": 7.0564,
+      "step": 132
+    },
+    {
+      "epoch": 0.006347615468136641,
+      "grad_norm": 12.032221794128418,
+      "learning_rate": 0.0001999986736308285,
+      "loss": 4.7228,
+      "step": 133
+    },
+    {
+      "epoch": 0.006395341900227894,
+      "grad_norm": 4.067997455596924,
+      "learning_rate": 0.0001999986477511226,
+      "loss": 6.1123,
+      "step": 134
+    },
+    {
+      "epoch": 0.006443068332319147,
+      "grad_norm": 5.277679920196533,
+      "learning_rate": 0.0001999986216213735,
+      "loss": 8.8908,
+      "step": 135
+    },
+    {
+      "epoch": 0.0064907947644104,
+      "grad_norm": 6.415206432342529,
+      "learning_rate": 0.0001999985952415813,
+      "loss": 7.0391,
+      "step": 136
+    },
+    {
+      "epoch": 0.006538521196501653,
+      "grad_norm": 6.522372245788574,
+      "learning_rate": 0.000199998568611746,
+      "loss": 8.9838,
+      "step": 137
+    },
+    {
+      "epoch": 0.006586247628592905,
+      "grad_norm": 5.012221336364746,
+      "learning_rate": 0.0001999985417318677,
+      "loss": 7.661,
+      "step": 138
+    },
+    {
+      "epoch": 0.006633974060684158,
+      "grad_norm": 5.40250825881958,
+      "learning_rate": 0.00019999851460194646,
+      "loss": 7.2033,
+      "step": 139
+    },
+    {
+      "epoch": 0.006681700492775411,
+      "grad_norm": 5.069441795349121,
+      "learning_rate": 0.00019999848722198236,
+      "loss": 6.6148,
+      "step": 140
+    },
+    {
+      "epoch": 0.006729426924866664,
+      "grad_norm": 5.3148064613342285,
+      "learning_rate": 0.00019999845959197546,
+      "loss": 7.3913,
+      "step": 141
+    },
+    {
+      "epoch": 0.006777153356957917,
+      "grad_norm": 4.556090354919434,
+      "learning_rate": 0.00019999843171192582,
+      "loss": 4.5144,
+      "step": 142
+    },
+    {
+      "epoch": 0.0068248797890491705,
+      "grad_norm": 4.365043640136719,
+      "learning_rate": 0.0001999984035818335,
+      "loss": 6.4603,
+      "step": 143
+    },
+    {
+      "epoch": 0.006872606221140423,
+      "grad_norm": 7.352154731750488,
+      "learning_rate": 0.0001999983752016986,
+      "loss": 6.9395,
+      "step": 144
+    },
+    {
+      "epoch": 0.006920332653231676,
+      "grad_norm": 5.900674819946289,
+      "learning_rate": 0.00019999834657152122,
+      "loss": 5.3865,
+      "step": 145
+    },
+    {
+      "epoch": 0.006968059085322929,
+      "grad_norm": 4.4542670249938965,
+      "learning_rate": 0.00019999831769130133,
+      "loss": 5.7073,
+      "step": 146
+    },
+    {
+      "epoch": 0.007015785517414182,
+      "grad_norm": 4.517548561096191,
+      "learning_rate": 0.0001999982885610391,
+      "loss": 5.8635,
+      "step": 147
+    },
+    {
+      "epoch": 0.007063511949505435,
+      "grad_norm": 4.733120441436768,
+      "learning_rate": 0.00019999825918073455,
+      "loss": 7.162,
+      "step": 148
+    },
+    {
+      "epoch": 0.007111238381596688,
+      "grad_norm": 5.98193359375,
+      "learning_rate": 0.00019999822955038776,
+      "loss": 8.3258,
+      "step": 149
+    },
+    {
+      "epoch": 0.007158964813687941,
+      "grad_norm": 5.3873610496521,
+      "learning_rate": 0.00019999819966999883,
+      "loss": 7.9001,
+      "step": 150
+    },
+    {
+      "epoch": 0.007206691245779193,
+      "grad_norm": 8.724983215332031,
+      "learning_rate": 0.00019999816953956783,
+      "loss": 8.8156,
+      "step": 151
+    },
+    {
+      "epoch": 0.007254417677870446,
+      "grad_norm": 5.680585861206055,
+      "learning_rate": 0.0001999981391590948,
+      "loss": 6.7082,
+      "step": 152
+    },
+    {
+      "epoch": 0.0073021441099616995,
+      "grad_norm": 6.000738620758057,
+      "learning_rate": 0.00019999810852857985,
+      "loss": 7.2123,
+      "step": 153
+    },
+    {
+      "epoch": 0.0073498705420529525,
+      "grad_norm": 5.984689712524414,
+      "learning_rate": 0.00019999807764802303,
+      "loss": 6.9426,
+      "step": 154
+    },
+    {
+      "epoch": 0.007397596974144206,
+      "grad_norm": 6.926332473754883,
+      "learning_rate": 0.00019999804651742447,
+      "loss": 7.4237,
+      "step": 155
+    },
+    {
+      "epoch": 0.007445323406235459,
+      "grad_norm": 4.661206245422363,
+      "learning_rate": 0.00019999801513678417,
+      "loss": 7.7377,
+      "step": 156
+    },
+    {
+      "epoch": 0.007493049838326711,
+      "grad_norm": 4.511832237243652,
+      "learning_rate": 0.00019999798350610229,
+      "loss": 5.908,
+      "step": 157
+    },
+    {
+      "epoch": 0.007540776270417964,
+      "grad_norm": 4.867547512054443,
+      "learning_rate": 0.00019999795162537886,
+      "loss": 6.5205,
+      "step": 158
+    },
+    {
+      "epoch": 0.007588502702509217,
+      "grad_norm": 6.225820541381836,
+      "learning_rate": 0.00019999791949461393,
+      "loss": 7.0262,
+      "step": 159
+    },
+    {
+      "epoch": 0.00763622913460047,
+      "grad_norm": 5.769981384277344,
+      "learning_rate": 0.00019999788711380764,
+      "loss": 6.9616,
+      "step": 160
+    },
+    {
+      "epoch": 0.007683955566691723,
+      "grad_norm": 5.535105228424072,
+      "learning_rate": 0.00019999785448296005,
+      "loss": 7.2659,
+      "step": 161
+    },
+    {
+      "epoch": 0.007731681998782976,
+      "grad_norm": 4.4427642822265625,
+      "learning_rate": 0.00019999782160207125,
+      "loss": 5.8697,
+      "step": 162
+    },
+    {
+      "epoch": 0.007779408430874229,
+      "grad_norm": 7.328268527984619,
+      "learning_rate": 0.0001999977884711413,
+      "loss": 6.6268,
+      "step": 163
+    },
+    {
+      "epoch": 0.007827134862965482,
+      "grad_norm": 6.006573677062988,
+      "learning_rate": 0.00019999775509017028,
+      "loss": 9.1153,
+      "step": 164
+    },
+    {
+      "epoch": 0.007874861295056735,
+      "grad_norm": 4.760677814483643,
+      "learning_rate": 0.00019999772145915833,
+      "loss": 6.9565,
+      "step": 165
+    },
+    {
+      "epoch": 0.007922587727147988,
+      "grad_norm": 4.592026233673096,
+      "learning_rate": 0.00019999768757810547,
+      "loss": 5.6614,
+      "step": 166
+    },
+    {
+      "epoch": 0.00797031415923924,
+      "grad_norm": 4.596296310424805,
+      "learning_rate": 0.00019999765344701182,
+      "loss": 6.0717,
+      "step": 167
+    },
+    {
+      "epoch": 0.008018040591330494,
+      "grad_norm": 5.7095417976379395,
+      "learning_rate": 0.00019999761906587743,
+      "loss": 8.2684,
+      "step": 168
+    },
+    {
+      "epoch": 0.008065767023421747,
+      "grad_norm": 5.1179986000061035,
+      "learning_rate": 0.00019999758443470245,
+      "loss": 6.6392,
+      "step": 169
+    },
+    {
+      "epoch": 0.008113493455513,
+      "grad_norm": 5.473196983337402,
+      "learning_rate": 0.00019999754955348688,
+      "loss": 5.9417,
+      "step": 170
+    },
+    {
+      "epoch": 0.008161219887604253,
+      "grad_norm": 4.3178324699401855,
+      "learning_rate": 0.0001999975144222309,
+      "loss": 6.3279,
+      "step": 171
+    },
+    {
+      "epoch": 0.008208946319695506,
+      "grad_norm": 6.818999767303467,
+      "learning_rate": 0.00019999747904093451,
+      "loss": 7.9789,
+      "step": 172
+    },
+    {
+      "epoch": 0.008256672751786757,
+      "grad_norm": 4.3126983642578125,
+      "learning_rate": 0.00019999744340959787,
+      "loss": 6.9174,
+      "step": 173
+    },
+    {
+      "epoch": 0.00830439918387801,
+      "grad_norm": 5.491178512573242,
+      "learning_rate": 0.00019999740752822104,
+      "loss": 7.5142,
+      "step": 174
+    },
+    {
+      "epoch": 0.008352125615969264,
+      "grad_norm": 6.331181526184082,
+      "learning_rate": 0.0001999973713968041,
+      "loss": 7.3434,
+      "step": 175
+    },
+    {
+      "epoch": 0.008399852048060517,
+      "grad_norm": 5.401471138000488,
+      "learning_rate": 0.00019999733501534713,
+      "loss": 6.7435,
+      "step": 176
+    },
+    {
+      "epoch": 0.00844757848015177,
+      "grad_norm": 4.26669979095459,
+      "learning_rate": 0.00019999729838385025,
+      "loss": 5.7267,
+      "step": 177
+    },
+    {
+      "epoch": 0.008495304912243023,
+      "grad_norm": 3.7150814533233643,
+      "learning_rate": 0.00019999726150231355,
+      "loss": 5.5032,
+      "step": 178
+    },
+    {
+      "epoch": 0.008543031344334276,
+      "grad_norm": 5.715814113616943,
+      "learning_rate": 0.00019999722437073712,
+      "loss": 7.3256,
+      "step": 179
+    },
+    {
+      "epoch": 0.008590757776425529,
+      "grad_norm": 4.25509786605835,
+      "learning_rate": 0.000199997186989121,
+      "loss": 5.542,
+      "step": 180
+    },
+    {
+      "epoch": 0.008638484208516782,
+      "grad_norm": 4.596546173095703,
+      "learning_rate": 0.0001999971493574654,
+      "loss": 6.845,
+      "step": 181
+    },
+    {
+      "epoch": 0.008686210640608035,
+      "grad_norm": 5.3774309158325195,
+      "learning_rate": 0.00019999711147577028,
+      "loss": 7.6096,
+      "step": 182
+    },
+    {
+      "epoch": 0.008733937072699288,
+      "grad_norm": 5.344915390014648,
+      "learning_rate": 0.00019999707334403586,
+      "loss": 7.2455,
+      "step": 183
+    },
+    {
+      "epoch": 0.008781663504790541,
+      "grad_norm": 5.402298450469971,
+      "learning_rate": 0.00019999703496226213,
+      "loss": 7.7967,
+      "step": 184
+    },
+    {
+      "epoch": 0.008829389936881794,
+      "grad_norm": 3.6488380432128906,
+      "learning_rate": 0.00019999699633044927,
+      "loss": 4.383,
+      "step": 185
+    },
+    {
+      "epoch": 0.008877116368973046,
+      "grad_norm": 6.237378120422363,
+      "learning_rate": 0.0001999969574485973,
+      "loss": 8.9452,
+      "step": 186
+    },
+    {
+      "epoch": 0.008924842801064299,
+      "grad_norm": 6.196676731109619,
+      "learning_rate": 0.00019999691831670634,
+      "loss": 5.9055,
+      "step": 187
+    },
+    {
+      "epoch": 0.008972569233155552,
+      "grad_norm": 5.825589656829834,
+      "learning_rate": 0.00019999687893477655,
+      "loss": 7.6183,
+      "step": 188
+    },
+    {
+      "epoch": 0.009020295665246805,
+      "grad_norm": 4.964183807373047,
+      "learning_rate": 0.00019999683930280795,
+      "loss": 6.7619,
+      "step": 189
+    },
+    {
+      "epoch": 0.009068022097338058,
+      "grad_norm": 5.618199825286865,
+      "learning_rate": 0.0001999967994208007,
+      "loss": 8.0128,
+      "step": 190
+    },
+    {
+      "epoch": 0.009115748529429311,
+      "grad_norm": 4.945575714111328,
+      "learning_rate": 0.00019999675928875484,
+      "loss": 5.723,
+      "step": 191
+    },
+    {
+      "epoch": 0.009163474961520564,
+      "grad_norm": 3.8588993549346924,
+      "learning_rate": 0.0001999967189066705,
+      "loss": 6.2638,
+      "step": 192
+    },
+    {
+      "epoch": 0.009211201393611817,
+      "grad_norm": 5.020188331604004,
+      "learning_rate": 0.0001999966782745478,
+      "loss": 7.6009,
+      "step": 193
+    },
+    {
+      "epoch": 0.00925892782570307,
+      "grad_norm": 4.792932033538818,
+      "learning_rate": 0.0001999966373923868,
+      "loss": 6.7725,
+      "step": 194
+    },
+    {
+      "epoch": 0.009306654257794323,
+      "grad_norm": 4.707699775695801,
+      "learning_rate": 0.00019999659626018763,
+      "loss": 6.275,
+      "step": 195
+    },
+    {
+      "epoch": 0.009354380689885576,
+      "grad_norm": 4.85133171081543,
+      "learning_rate": 0.0001999965548779504,
+      "loss": 8.7349,
+      "step": 196
+    },
+    {
+      "epoch": 0.00940210712197683,
+      "grad_norm": 5.022207260131836,
+      "learning_rate": 0.00019999651324567518,
+      "loss": 7.265,
+      "step": 197
+    },
+    {
+      "epoch": 0.009449833554068083,
+      "grad_norm": 6.977590560913086,
+      "learning_rate": 0.0001999964713633621,
+      "loss": 6.1847,
+      "step": 198
+    },
+    {
+      "epoch": 0.009497559986159334,
+      "grad_norm": 4.008247375488281,
+      "learning_rate": 0.00019999642923101128,
+      "loss": 5.4763,
+      "step": 199
+    },
+    {
+      "epoch": 0.009545286418250587,
+      "grad_norm": 5.237358093261719,
+      "learning_rate": 0.0001999963868486228,
+      "loss": 8.1989,
+      "step": 200
+    },
+    {
+      "epoch": 0.009545286418250587,
+      "eval_loss": 1.6985455751419067,
+      "eval_runtime": 96.4787,
+      "eval_samples_per_second": 8.738,
+      "eval_steps_per_second": 4.374,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 62856,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.85446101417984e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcb0000bf368288d0acbc98ac984fb491ab14afd71b05fcadf3fe67fe64e1653
+size 6776