Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: gabrielmbmb/Upcycled-Qwen1.5-MoE2.7B
+---
+
+# 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 0.10.0

adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "gabrielmbmb/Upcycled-Qwen1.5-MoE2.7B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "gate",
+    "q_proj",
+    "shared_expert_gate",
+    "v_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc74711cb80cd2f368730278bbc66f0dccae7ceec53b0d92abd237ef174689b4
+size 3272016504

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3e2166b49ce624fd811acb845fe3ff104a3739f4ab1201738da82b0c9e3f6fe
+size 6549209908

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53ee4688496b0162130b060f83f318885b4d612c5e7e4e82a0bb98689df63eb3
+size 1064

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1421 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6666666666666666,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 1.2757867574691772,
+      "learning_rate": 0.000499986292341378,
+      "loss": 5.9015,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.7096672654151917,
+      "learning_rate": 0.0004999451708687113,
+      "loss": 3.9877,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.6350783109664917,
+      "learning_rate": 0.0004998766400914329,
+      "loss": 3.7232,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.5088619589805603,
+      "learning_rate": 0.0004997807075247146,
+      "loss": 3.552,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.4739762842655182,
+      "learning_rate": 0.0004996573836886434,
+      "loss": 3.5127,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.628942608833313,
+      "learning_rate": 0.0004995066821070679,
+      "loss": 3.3798,
+      "step": 60
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.5002753138542175,
+      "learning_rate": 0.0004993286193061145,
+      "loss": 3.3999,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.4983285963535309,
+      "learning_rate": 0.0004991232148123761,
+      "loss": 3.3398,
+      "step": 80
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.4371359050273895,
+      "learning_rate": 0.00049889049115077,
+      "loss": 3.3405,
+      "step": 90
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.5125981569290161,
+      "learning_rate": 0.0004986304738420684,
+      "loss": 3.3053,
+      "step": 100
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.47835057973861694,
+      "learning_rate": 0.000498343191400099,
+      "loss": 3.2388,
+      "step": 110
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.4769553244113922,
+      "learning_rate": 0.0004980286753286195,
+      "loss": 3.2004,
+      "step": 120
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.44102832674980164,
+      "learning_rate": 0.0004976869601178609,
+      "loss": 3.2301,
+      "step": 130
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.44598281383514404,
+      "learning_rate": 0.0004973180832407472,
+      "loss": 3.2284,
+      "step": 140
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.5305857062339783,
+      "learning_rate": 0.0004969220851487844,
+      "loss": 3.1978,
+      "step": 150
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.5015985369682312,
+      "learning_rate": 0.0004964990092676262,
+      "loss": 3.198,
+      "step": 160
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.49595481157302856,
+      "learning_rate": 0.0004960489019923105,
+      "loss": 3.2582,
+      "step": 170
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.4686504602432251,
+      "learning_rate": 0.0004955718126821722,
+      "loss": 3.1974,
+      "step": 180
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.4878421425819397,
+      "learning_rate": 0.0004950677936554305,
+      "loss": 3.1467,
+      "step": 190
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.476806640625,
+      "learning_rate": 0.0004945369001834514,
+      "loss": 3.1321,
+      "step": 200
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.5151681900024414,
+      "learning_rate": 0.0004939791904846869,
+      "loss": 3.1478,
+      "step": 210
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.4726090133190155,
+      "learning_rate": 0.0004933947257182901,
+      "loss": 3.1757,
+      "step": 220
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.4868369698524475,
+      "learning_rate": 0.000492783569977409,
+      "loss": 3.1573,
+      "step": 230
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.4568879306316376,
+      "learning_rate": 0.0004921457902821578,
+      "loss": 3.2129,
+      "step": 240
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.45109352469444275,
+      "learning_rate": 0.0004914814565722671,
+      "loss": 3.1417,
+      "step": 250
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.5096346139907837,
+      "learning_rate": 0.0004907906416994146,
+      "loss": 3.1397,
+      "step": 260
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.44307172298431396,
+      "learning_rate": 0.0004900734214192358,
+      "loss": 3.1851,
+      "step": 270
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.469777375459671,
+      "learning_rate": 0.0004893298743830168,
+      "loss": 3.1117,
+      "step": 280
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.4518013596534729,
+      "learning_rate": 0.0004885600821290692,
+      "loss": 3.0941,
+      "step": 290
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.4657439589500427,
+      "learning_rate": 0.0004877641290737884,
+      "loss": 3.1936,
+      "step": 300
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.4461677372455597,
+      "learning_rate": 0.00048694210250239646,
+      "loss": 3.1158,
+      "step": 310
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.454722136259079,
+      "learning_rate": 0.0004860940925593703,
+      "loss": 3.0921,
+      "step": 320
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.4858105480670929,
+      "learning_rate": 0.0004852201922385564,
+      "loss": 3.1601,
+      "step": 330
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.4848730266094208,
+      "learning_rate": 0.0004843204973729729,
+      "loss": 3.1165,
+      "step": 340
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5170342922210693,
+      "learning_rate": 0.00048339510662430044,
+      "loss": 3.0897,
+      "step": 350
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.4945329427719116,
+      "learning_rate": 0.00048244412147206283,
+      "loss": 3.0792,
+      "step": 360
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.4752379357814789,
+      "learning_rate": 0.0004814676462024987,
+      "loss": 3.035,
+      "step": 370
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.4935299754142761,
+      "learning_rate": 0.00048046578789712516,
+      "loss": 3.1129,
+      "step": 380
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.47018569707870483,
+      "learning_rate": 0.00047943865642099525,
+      "loss": 3.1255,
+      "step": 390
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.45771998167037964,
+      "learning_rate": 0.0004783863644106502,
+      "loss": 3.0546,
+      "step": 400
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.4871847927570343,
+      "learning_rate": 0.00047730902726176715,
+      "loss": 3.1176,
+      "step": 410
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.5023790001869202,
+      "learning_rate": 0.0004762067631165049,
+      "loss": 3.1396,
+      "step": 420
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.5331537127494812,
+      "learning_rate": 0.0004750796928505484,
+      "loss": 3.0541,
+      "step": 430
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.46206673979759216,
+      "learning_rate": 0.0004739279400598532,
+      "loss": 3.1429,
+      "step": 440
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.5062265992164612,
+      "learning_rate": 0.00047275163104709196,
+      "loss": 3.0668,
+      "step": 450
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.7376482486724854,
+      "learning_rate": 0.00047155089480780364,
+      "loss": 3.1377,
+      "step": 460
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.5349658727645874,
+      "learning_rate": 0.00047032586301624804,
+      "loss": 3.0838,
+      "step": 470
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.49428579211235046,
+      "learning_rate": 0.0004690766700109659,
+      "loss": 3.1257,
+      "step": 480
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.4835917353630066,
+      "learning_rate": 0.0004678034527800474,
+      "loss": 3.0709,
+      "step": 490
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.5094427466392517,
+      "learning_rate": 0.00046650635094610973,
+      "loss": 3.0692,
+      "step": 500
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.5574087500572205,
+      "learning_rate": 0.0004651855067509859,
+      "loss": 3.0667,
+      "step": 510
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.5003999471664429,
+      "learning_rate": 0.0004638410650401267,
+      "loss": 3.0311,
+      "step": 520
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.5170697569847107,
+      "learning_rate": 0.000462473173246716,
+      "loss": 3.1082,
+      "step": 530
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.5004311800003052,
+      "learning_rate": 0.00046108198137550377,
+      "loss": 3.0825,
+      "step": 540
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.49480965733528137,
+      "learning_rate": 0.00045966764198635603,
+      "loss": 3.0888,
+      "step": 550
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.49261385202407837,
+      "learning_rate": 0.00045823031017752484,
+      "loss": 3.1568,
+      "step": 560
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.4577986001968384,
+      "learning_rate": 0.00045677014356864043,
+      "loss": 3.0953,
+      "step": 570
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.4814681112766266,
+      "learning_rate": 0.000455287302283426,
+      "loss": 3.0801,
+      "step": 580
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.563042402267456,
+      "learning_rate": 0.00045378194893213854,
+      "loss": 3.0719,
+      "step": 590
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.5507716536521912,
+      "learning_rate": 0.0004522542485937369,
+      "loss": 3.0724,
+      "step": 600
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.5448073148727417,
+      "learning_rate": 0.0004507043687977787,
+      "loss": 3.0294,
+      "step": 610
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.47773197293281555,
+      "learning_rate": 0.00044913247950604905,
+      "loss": 3.0682,
+      "step": 620
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.4662880301475525,
+      "learning_rate": 0.0004475387530939226,
+      "loss": 3.0106,
+      "step": 630
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.4735540747642517,
+      "learning_rate": 0.00044592336433145995,
+      "loss": 3.1345,
+      "step": 640
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.4746765196323395,
+      "learning_rate": 0.0004442864903642427,
+      "loss": 3.0772,
+      "step": 650
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.45668378472328186,
+      "learning_rate": 0.0004426283106939473,
+      "loss": 3.1174,
+      "step": 660
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.4704893231391907,
+      "learning_rate": 0.0004409490071586606,
+      "loss": 3.0816,
+      "step": 670
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.5290801525115967,
+      "learning_rate": 0.0004392487639129391,
+      "loss": 3.1089,
+      "step": 680
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.47564446926116943,
+      "learning_rate": 0.0004375277674076149,
+      "loss": 3.082,
+      "step": 690
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.4995107352733612,
+      "learning_rate": 0.00043578620636934855,
+      "loss": 3.1992,
+      "step": 700
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.48856520652770996,
+      "learning_rate": 0.00043402427177993366,
+      "loss": 3.0598,
+      "step": 710
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.4874037802219391,
+      "learning_rate": 0.00043224215685535287,
+      "loss": 3.0753,
+      "step": 720
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.45193690061569214,
+      "learning_rate": 0.00043044005702459054,
+      "loss": 2.9601,
+      "step": 730
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.46975770592689514,
+      "learning_rate": 0.00042861816990820087,
+      "loss": 3.0511,
+      "step": 740
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.5442278981208801,
+      "learning_rate": 0.00042677669529663686,
+      "loss": 3.0898,
+      "step": 750
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.5437372922897339,
+      "learning_rate": 0.00042491583512834137,
+      "loss": 3.0768,
+      "step": 760
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.4911404848098755,
+      "learning_rate": 0.0004230357934676017,
+      "loss": 3.1239,
+      "step": 770
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.4861234128475189,
+      "learning_rate": 0.0004211367764821722,
+      "loss": 3.0473,
+      "step": 780
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.49302661418914795,
+      "learning_rate": 0.0004192189924206652,
+      "loss": 3.0874,
+      "step": 790
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.4864264726638794,
+      "learning_rate": 0.0004172826515897146,
+      "loss": 3.0753,
+      "step": 800
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.48708102107048035,
+      "learning_rate": 0.00041532796633091297,
+      "loss": 3.1403,
+      "step": 810
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.5046274662017822,
+      "learning_rate": 0.0004133551509975264,
+      "loss": 3.0785,
+      "step": 820
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.5404755473136902,
+      "learning_rate": 0.00041136442193098765,
+      "loss": 3.0104,
+      "step": 830
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.5012314915657043,
+      "learning_rate": 0.00040935599743717243,
+      "loss": 3.0538,
+      "step": 840
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.5044212937355042,
+      "learning_rate": 0.0004073300977624594,
+      "loss": 3.0975,
+      "step": 850
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.5059216618537903,
+      "learning_rate": 0.0004052869450695776,
+      "loss": 3.1057,
+      "step": 860
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.4804486930370331,
+      "learning_rate": 0.00040322676341324415,
+      "loss": 3.0492,
+      "step": 870
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.5673746466636658,
+      "learning_rate": 0.00040114977871559375,
+      "loss": 2.9521,
+      "step": 880
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.4696684181690216,
+      "learning_rate": 0.00039905621874140396,
+      "loss": 3.0136,
+      "step": 890
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.5002209544181824,
+      "learning_rate": 0.0003969463130731183,
+      "loss": 3.0378,
+      "step": 900
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.48504123091697693,
+      "learning_rate": 0.0003948202930856697,
+      "loss": 3.0458,
+      "step": 910
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.48299267888069153,
+      "learning_rate": 0.000392678391921108,
+      "loss": 3.0699,
+      "step": 920
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.5440784096717834,
+      "learning_rate": 0.00039052084446303264,
+      "loss": 3.044,
+      "step": 930
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.498516321182251,
+      "learning_rate": 0.000388347887310836,
+      "loss": 3.0524,
+      "step": 940
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.49369409680366516,
+      "learning_rate": 0.00038615975875375683,
+      "loss": 3.0511,
+      "step": 950
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.5007414817810059,
+      "learning_rate": 0.00038395669874474915,
+      "loss": 3.0369,
+      "step": 960
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.4814367890357971,
+      "learning_rate": 0.00038173894887416946,
+      "loss": 3.0965,
+      "step": 970
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.5295039415359497,
+      "learning_rate": 0.00037950675234328256,
+      "loss": 3.0571,
+      "step": 980
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.5096908211708069,
+      "learning_rate": 0.00037726035393759286,
+      "loss": 2.9924,
+      "step": 990
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.49976101517677307,
+      "learning_rate": 0.000375,
+      "loss": 3.0523,
+      "step": 1000
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.486150860786438,
+      "learning_rate": 0.0003727259384037852,
+      "loss": 3.0453,
+      "step": 1010
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.4886365532875061,
+      "learning_rate": 0.0003704384185254288,
+      "loss": 3.0791,
+      "step": 1020
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.4869343638420105,
+      "learning_rate": 0.00036813769121726354,
+      "loss": 3.0962,
+      "step": 1030
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.47605258226394653,
+      "learning_rate": 0.00036582400877996547,
+      "loss": 3.087,
+      "step": 1040
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.49207133054733276,
+      "learning_rate": 0.00036349762493488667,
+      "loss": 3.0406,
+      "step": 1050
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.5010517835617065,
+      "learning_rate": 0.00036115879479623185,
+      "loss": 3.0638,
+      "step": 1060
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.48435714840888977,
+      "learning_rate": 0.0003588077748430819,
+      "loss": 3.0325,
+      "step": 1070
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5021737813949585,
+      "learning_rate": 0.0003564448228912682,
+      "loss": 3.0115,
+      "step": 1080
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.46703141927719116,
+      "learning_rate": 0.00035407019806510035,
+      "loss": 2.9539,
+      "step": 1090
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.521730363368988,
+      "learning_rate": 0.0003516841607689501,
+      "loss": 3.0114,
+      "step": 1100
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.4748888611793518,
+      "learning_rate": 0.00034928697265869515,
+      "loss": 3.0226,
+      "step": 1110
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.4812580645084381,
+      "learning_rate": 0.00034687889661302575,
+      "loss": 3.0065,
+      "step": 1120
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.5008811354637146,
+      "learning_rate": 0.00034446019670461683,
+      "loss": 3.027,
+      "step": 1130
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.49032077193260193,
+      "learning_rate": 0.00034203113817116957,
+      "loss": 2.9933,
+      "step": 1140
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.47988900542259216,
+      "learning_rate": 0.00033959198738632503,
+      "loss": 3.0474,
+      "step": 1150
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.49220654368400574,
+      "learning_rate": 0.0003371430118304538,
+      "loss": 3.0226,
+      "step": 1160
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.49873360991477966,
+      "learning_rate": 0.0003346844800613229,
+      "loss": 3.0082,
+      "step": 1170
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.5125187039375305,
+      "learning_rate": 0.0003322166616846458,
+      "loss": 3.0468,
+      "step": 1180
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.509082555770874,
+      "learning_rate": 0.0003297398273245175,
+      "loss": 3.1134,
+      "step": 1190
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.45824429392814636,
+      "learning_rate": 0.00032725424859373687,
+      "loss": 3.0516,
+      "step": 1200
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.49980753660202026,
+      "learning_rate": 0.0003247601980640217,
+      "loss": 2.9742,
+      "step": 1210
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.48861539363861084,
+      "learning_rate": 0.0003222579492361179,
+      "loss": 3.004,
+      "step": 1220
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.5454481840133667,
+      "learning_rate": 0.00031974777650980735,
+      "loss": 2.9608,
+      "step": 1230
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.4744034707546234,
+      "learning_rate": 0.0003172299551538164,
+      "loss": 3.0384,
+      "step": 1240
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.5317044854164124,
+      "learning_rate": 0.00031470476127563017,
+      "loss": 3.0209,
+      "step": 1250
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.49222180247306824,
+      "learning_rate": 0.0003121724717912138,
+      "loss": 3.0135,
+      "step": 1260
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.4853774309158325,
+      "learning_rate": 0.00030963336439464523,
+      "loss": 3.0235,
+      "step": 1270
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.4858599603176117,
+      "learning_rate": 0.00030708771752766396,
+      "loss": 3.0256,
+      "step": 1280
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.4980061948299408,
+      "learning_rate": 0.0003045358103491357,
+      "loss": 2.9718,
+      "step": 1290
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.49256446957588196,
+      "learning_rate": 0.0003019779227044398,
+      "loss": 3.0288,
+      "step": 1300
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.5088287591934204,
+      "learning_rate": 0.00029941433509478153,
+      "loss": 3.0268,
+      "step": 1310
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.5106491446495056,
+      "learning_rate": 0.0002968453286464312,
+      "loss": 3.0032,
+      "step": 1320
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4999896287918091,
+      "learning_rate": 0.0002942711850798959,
+      "loss": 2.9407,
+      "step": 1330
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.4718291163444519,
+      "learning_rate": 0.00029169218667902556,
+      "loss": 2.9313,
+      "step": 1340
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.485334187746048,
+      "learning_rate": 0.00028910861626005774,
+      "loss": 2.9993,
+      "step": 1350
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.47278451919555664,
+      "learning_rate": 0.00028652075714060294,
+      "loss": 3.0594,
+      "step": 1360
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.4961351454257965,
+      "learning_rate": 0.0002839288931085761,
+      "loss": 2.9736,
+      "step": 1370
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.48107197880744934,
+      "learning_rate": 0.00028133330839107606,
+      "loss": 2.9818,
+      "step": 1380
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.5018859505653381,
+      "learning_rate": 0.0002787342876232167,
+      "loss": 2.9993,
+      "step": 1390
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.5005733966827393,
+      "learning_rate": 0.0002761321158169134,
+      "loss": 2.971,
+      "step": 1400
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.45412546396255493,
+      "learning_rate": 0.0002735270783296286,
+      "loss": 2.9343,
+      "step": 1410
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.49526095390319824,
+      "learning_rate": 0.00027091946083307894,
+      "loss": 3.0247,
+      "step": 1420
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.5004629492759705,
+      "learning_rate": 0.00026830954928190793,
+      "loss": 2.9386,
+      "step": 1430
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.5008641481399536,
+      "learning_rate": 0.0002656976298823284,
+      "loss": 2.9768,
+      "step": 1440
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.4870932698249817,
+      "learning_rate": 0.000263083989060736,
+      "loss": 2.9825,
+      "step": 1450
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.47083091735839844,
+      "learning_rate": 0.0002604689134322999,
+      "loss": 2.9694,
+      "step": 1460
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.4780152440071106,
+      "learning_rate": 0.00025785268976953206,
+      "loss": 3.0139,
+      "step": 1470
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.47919341921806335,
+      "learning_rate": 0.00025523560497083924,
+      "loss": 2.9558,
+      "step": 1480
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.4744253158569336,
+      "learning_rate": 0.00025261794602906147,
+      "loss": 2.9823,
+      "step": 1490
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.47770825028419495,
+      "learning_rate": 0.00025,
+      "loss": 2.976,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.535241961479187,
+      "learning_rate": 0.00024738205397093865,
+      "loss": 2.9404,
+      "step": 1510
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.5206143260002136,
+      "learning_rate": 0.00024476439502916077,
+      "loss": 2.9697,
+      "step": 1520
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.4685532748699188,
+      "learning_rate": 0.00024214731023046793,
+      "loss": 3.031,
+      "step": 1530
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.45759207010269165,
+      "learning_rate": 0.00023953108656770016,
+      "loss": 2.9371,
+      "step": 1540
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.47409725189208984,
+      "learning_rate": 0.00023691601093926405,
+      "loss": 2.9492,
+      "step": 1550
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.4723811149597168,
+      "learning_rate": 0.00023430237011767165,
+      "loss": 3.0055,
+      "step": 1560
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.5121801495552063,
+      "learning_rate": 0.00023169045071809213,
+      "loss": 2.9654,
+      "step": 1570
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.47900766134262085,
+      "learning_rate": 0.00022908053916692117,
+      "loss": 2.9665,
+      "step": 1580
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.47504156827926636,
+      "learning_rate": 0.00022647292167037142,
+      "loss": 2.9543,
+      "step": 1590
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.48130717873573303,
+      "learning_rate": 0.00022386788418308668,
+      "loss": 2.9948,
+      "step": 1600
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.4968855381011963,
+      "learning_rate": 0.00022126571237678338,
+      "loss": 3.0497,
+      "step": 1610
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.45493414998054504,
+      "learning_rate": 0.00021866669160892392,
+      "loss": 3.0211,
+      "step": 1620
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.46341362595558167,
+      "learning_rate": 0.00021607110689142393,
+      "loss": 2.9249,
+      "step": 1630
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.4598373472690582,
+      "learning_rate": 0.00021347924285939712,
+      "loss": 2.9306,
+      "step": 1640
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.5339600443840027,
+      "learning_rate": 0.00021089138373994224,
+      "loss": 2.9457,
+      "step": 1650
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.4766974449157715,
+      "learning_rate": 0.00020830781332097445,
+      "loss": 2.9573,
+      "step": 1660
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.45860227942466736,
+      "learning_rate": 0.0002057288149201042,
+      "loss": 2.9067,
+      "step": 1670
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.4715401530265808,
+      "learning_rate": 0.0002031546713535688,
+      "loss": 2.9373,
+      "step": 1680
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.4715852439403534,
+      "learning_rate": 0.00020058566490521845,
+      "loss": 2.9486,
+      "step": 1690
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.4740593731403351,
+      "learning_rate": 0.0001980220772955602,
+      "loss": 2.9672,
+      "step": 1700
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.5071026086807251,
+      "learning_rate": 0.00019546418965086444,
+      "loss": 2.9791,
+      "step": 1710
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.46667274832725525,
+      "learning_rate": 0.00019291228247233605,
+      "loss": 2.9517,
+      "step": 1720
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.5175219178199768,
+      "learning_rate": 0.00019036663560535483,
+      "loss": 2.9765,
+      "step": 1730
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.4796634018421173,
+      "learning_rate": 0.00018782752820878634,
+      "loss": 2.9258,
+      "step": 1740
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.4871932566165924,
+      "learning_rate": 0.0001852952387243698,
+      "loss": 2.9403,
+      "step": 1750
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.4641266167163849,
+      "learning_rate": 0.00018277004484618358,
+      "loss": 2.9058,
+      "step": 1760
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.4585517346858978,
+      "learning_rate": 0.0001802522234901927,
+      "loss": 2.9802,
+      "step": 1770
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.4525165855884552,
+      "learning_rate": 0.00017774205076388205,
+      "loss": 3.0241,
+      "step": 1780
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.4651874303817749,
+      "learning_rate": 0.00017523980193597836,
+      "loss": 2.9783,
+      "step": 1790
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.4655090868473053,
+      "learning_rate": 0.00017274575140626317,
+      "loss": 2.9115,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.44796276092529297,
+      "learning_rate": 0.0001702601726754825,
+      "loss": 2.9357,
+      "step": 1810
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.5139617323875427,
+      "learning_rate": 0.00016778333831535418,
+      "loss": 2.9124,
+      "step": 1820
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.4756507873535156,
+      "learning_rate": 0.00016531551993867715,
+      "loss": 2.9252,
+      "step": 1830
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.47321391105651855,
+      "learning_rate": 0.00016285698816954626,
+      "loss": 2.9801,
+      "step": 1840
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.4512488842010498,
+      "learning_rate": 0.00016040801261367493,
+      "loss": 3.0134,
+      "step": 1850
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.5047795176506042,
+      "learning_rate": 0.00015796886182883053,
+      "loss": 2.9549,
+      "step": 1860
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.4670908451080322,
+      "learning_rate": 0.00015553980329538326,
+      "loss": 2.9534,
+      "step": 1870
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.4596426784992218,
+      "learning_rate": 0.00015312110338697426,
+      "loss": 2.9802,
+      "step": 1880
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.45904773473739624,
+      "learning_rate": 0.00015071302734130488,
+      "loss": 2.9435,
+      "step": 1890
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.48870381712913513,
+      "learning_rate": 0.00014831583923105,
+      "loss": 2.9378,
+      "step": 1900
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.4705340564250946,
+      "learning_rate": 0.00014592980193489974,
+      "loss": 2.9716,
+      "step": 1910
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.45324671268463135,
+      "learning_rate": 0.00014355517710873183,
+      "loss": 2.9729,
+      "step": 1920
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.4573574662208557,
+      "learning_rate": 0.00014119222515691815,
+      "loss": 2.9286,
+      "step": 1930
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.48345670104026794,
+      "learning_rate": 0.00013884120520376818,
+      "loss": 3.0016,
+      "step": 1940
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.4590473175048828,
+      "learning_rate": 0.00013650237506511331,
+      "loss": 2.8464,
+      "step": 1950
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.7705239057540894,
+      "learning_rate": 0.00013417599122003462,
+      "loss": 3.007,
+      "step": 1960
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.4770728647708893,
+      "learning_rate": 0.00013186230878273653,
+      "loss": 2.9381,
+      "step": 1970
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.44512978196144104,
+      "learning_rate": 0.00012956158147457115,
+      "loss": 2.9813,
+      "step": 1980
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.4624728262424469,
+      "learning_rate": 0.00012727406159621478,
+      "loss": 2.9069,
+      "step": 1990
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.47390344738960266,
+      "learning_rate": 0.00012500000000000006,
+      "loss": 2.9868,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 1000,
+  "total_flos": 2.85480780300288e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2220e9630781dc148b0f5bea27b08fb071f0652a6b90a0d5cc7e2519f0fa43fe
+size 5112