Upload 15 files

LICENSE.txt

@@ -0,0 +1,190 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   Copyright Nicholas Kluge Corrêa
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -16,11 +16,9 @@ tags:
 ---
 # RewardModel
 
-The `RewardModel` is a modified BERT model that can be used to score the quality of completion for a given prompt. It is based on a [BERT model](https://huggingface.co/bert-base-cased), modified to act as a regression model.
+The `RewardModel` is a [BERT](https://huggingface.co/bert-base-cased)model that can be used to score the quality of a completion for a given prompt.
 
-The `RewardModel` allows the specification of an `alpha` parameter, which is a multiplier to the reward score. This multiplier is set to 1 during training (since our reward values are bounded between -1 and 1) but can be changed at inference to allow for rewards with higher bounds.
-
-The model was trained with a dataset composed of `prompt`, `completions`, and annotated `rewards`.
+The model was trained with a dataset composed of `prompt`, `prefered_completions`, and `rejected_completions`.
 
 > Note: These prompt + completions are samples of intruction datasets created via the [Self-Instruct](https://github.com/yizhongw/self-instruct) framework.
 
@@ -30,23 +28,30 @@ The model was trained with a dataset composed of `prompt`, `completions`, and an
 - **Dataset:** [Reward-Aira Dataset](https://huggingface.co/datasets/nicholasKluge/reward-aira-dataset)
 - **Language:** English
 - **Number of Epochs:** 5
-- **Batch size:** 64
-- **Optimizer:** `torch.optim.Adam`
-- **Learning Rate:** 1e-4
-- **Loss Function:** `torch.nn.MSELoss()`
+- **Batch size:** 42
+- **Optimizer:** `torch.optim.AdamW`
+- **Learning Rate:** 5e-5
 - **GPU:** 1 NVIDIA A100-SXM4-40GB
-- **RMSE in testing:** 0.1190
-- **Emissions:** 0.21 KgCO2
-- **Total Energy Consumption:** 0.60 kWh
-
-
-| Epoch/Loss|Training|Validation|
-|---|---|---|
-| 1 |0.06136|0.031815|
-| 2 |0.030398|0.02459|
-| 3 |0.02389|0.026569|
-| 4 |0.024755|0.02109|
-| 5 |0.019445|0.01416|
+- **Emissions:** 0.17 KgCO2
+- **Total Energy Consumption:** 0.48 kWh
+
+| Step|Training Loss|Validation Loss|Accuracy|
+|---|---|---|---|
+| 200 |0.080300|0.037106|0.987499|
+| 400 |0.039300|0.036421|0.988433|
+| 600 |0.037200|0.041799|0.986447|
+| 800 |0.011400|0.039411|0.989602|
+| 1000 |0.013800|0.039781|0.989718|
+| 1200 |0.012700|0.034337|0.990887|
+| 1400 |0.005200|0.037403|0.991120|
+| 1600 |0.001800|0.047661|0.990653|
+| 1800 |0.000900|0.051354|0.991237|
+| 2000 |0.001000|0.046224|0.990419|
+| 2200 |0.000200|0.046582|0.991120|
+| 2400 |0.000600|0.046632|0.990536|
+| 2600 |0.000100|0.051437|0.990770|
+| 2800 |0.000500|0.049085|0.990887|
+| 3000 |0.000400|0.049938|0.991004|
 
 > Note: This repository has the notebook used to train this model.
 
@@ -55,64 +60,60 @@ The model was trained with a dataset composed of `prompt`, `completions`, and an
 Here's an example of how to use the `RewardModel` to score the quality of a response to a given prompt:
 
 ```python
-from transformers import AutoTokenizer,AutoConfig, AutoModel
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import torch
 
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
-config = AutoConfig.from_pretrained('nicholasKluge/RewardModel', trust_remote_code=True, revision='main') 
-tokenizer = AutoTokenizer.from_pretrained('nicholasKluge/RewardModel', trust_remote_code=True, config=config, revision='main')
-rewardModel = AutoModel.from_pretrained('nicholasKluge/RewardModel', trust_remote_code=True, config=config, revision='main') 
+tokenizer = AutoTokenizer.from_pretrained("nicholasKluge/RewardModel")
+rewardModel = AutoModelForSequenceClassification.from_pretrained("nicholasKluge/RewardModel")
 
 rewardModel.eval()
 rewardModel.to(device)
 
 # Define the question and response
-question = "What is the capital of France?"
-response1 = "Paris, France's capital, is a major European city and a global center for art, fashion, gastronomy and culture."
-response2 = "Google it pal."
+prompt = "Why is AI Ethics important?"
+response_good = "The field of AI Ethics delves deeply into the intricate ethical considerations that arise with respect to AI systems. This includes the role of humanity in creating and deploying these systems, as well as the conduct of machines themselves. Broadly speaking, AI Ethics can be divided into two major categories : concerns surrounding the morality of human actions in relation to creating and using AI, and concerns regarding the moral implications of machine behavior."
+response_bad = "Who cares about AI Ethics? It's just a bunch of whining about humans making and using AI and bitching about what the machines do."
 
 # Tokenize the question and response
-tokens = tokenizer(question, response1,
+tokens_good = tokenizer(prompt, response_good,
+                truncation=True,
+                max_length=512,
                 return_token_type_ids=False,
-                return_tensors="pt", 
+                return_tensors="pt",
                 return_attention_mask=True)
 
-tokens.to(device)
-
-# Score the response
-score = rewardModel(**tokens, alpha=10).item()
-
-print(f"Question: {question} \n")
-print(f"Response 1: {response1} Score: {score:.3f}")
-
-tokens = tokenizer(question, response2,
+tokens_bad = tokenizer(prompt, response_bad,
+                truncation=True,
+                max_length=512,
                 return_token_type_ids=False,
-                return_tensors="pt", 
+                return_tensors="pt",
                 return_attention_mask=True)
 
-tokens.to(device)
-
-score = rewardModel(**tokens, alpha=10).item()
+score_good = rewardModel(**tokens_good)[0].item()
+score_bad = rewardModel(**tokens_bad)[0].item()
 
-print(f"Response 2: {response2} Score: {score:.3f}")
+print(f"Question: {prompt} \n")
+print(f"Response 1: {response_good} Score: {score_good:.3f}")
+print(f"Response 2: {response_bad} Score: {score_bad:.3f}")
 ```
 
 This will output the following:
 
 ```markdown
->>> Question: What is the capital of France? 
+>>> Question: Why is AI Ethics important?
 
->>>Response: Paris, France's capital, is a major European city and a global center for art, fashion, gastronomy and culture. Score: 3.183
->>>Response: Google it pal. Score: -5.781
+>>>Response 1: The field of AI Ethics delves deeply into the intricate ethical considerations that arise with respect to AI systems. This includes the role of humanity in creating and deploying these systems, as well as the conduct of machines themselves. Broadly speaking, AI Ethics can be divided into two major categories : concerns surrounding the morality of human actions in relation to creating and using AI, and concerns regarding the moral implications of machine behavior. Score: 4.777
+>>>Response 2: Who cares about AI Ethics? It's just a bunch of whining about humans making and using AI and bitching about what the machines do. Score: -11.582
 ```
 
 ## Performance
 
 | Acc  | [WebGPT](https://huggingface.co/datasets/openai/webgpt_comparisons)  |
 |---|---|
-| [Aira-RewardModel](https://huggingface.co/nicholasKluge/RewardModel)  | 53.54%  |
+| [Aira-RewardModel](https://huggingface.co/nicholasKluge/RewardModel)  | 96.54%  |
 
 ## License
 
-The `RewardModel` is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.
+The `RewardModel` is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.

RewardModel_emissions.csv

@@ -0,0 +1,2 @@
+timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
+2023-06-13T15:03:57,RewardModel_emissions,34e3fabc-108d-42d0-8a10-d218a32c89f6,4812.4118773937225,0.17002787857474966,3.5331115230068865e-05,42.5,273.41,31.30528450012207,0.056805772867467685,0.3882571562884012,0.04180739816835735,0.4868703273242265,United States,USA,nevada,,,Linux-5.15.107+-x86_64-with-glibc2.31,3.10.12,2.2.3,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,-115.1164,36.1685,83.48075866699219,machine,N,1.0

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c52bed61e330ec59d12c04564eb6df59e95ccd9bad6cc5adf5e754358c57566
+size 866606277

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41545686d6ccaf2f3efe0173dacc4c4634b0ade6710f046361ab31987f195591
+size 433316981

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:008304bdd46c688bbf5feaf85cbcc083837da7f9be6bf363f309170ac62a6d4e
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24c083a5f4303f0b59a009934c6dcb05a44520e05c10e837a7e2149a6d4a68d1
+size 627

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,241 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.901960784313726,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.673202614379085e-05,
+      "loss": 0.0803,
+      "step": 200
+    },
+    {
+      "epoch": 0.33,
+      "eval_accuracy": 0.9874985395490128,
+      "eval_loss": 0.03710582107305527,
+      "eval_runtime": 80.6999,
+      "eval_samples_per_second": 106.06,
+      "eval_steps_per_second": 2.528,
+      "step": 200
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 4.3464052287581704e-05,
+      "loss": 0.0393,
+      "step": 400
+    },
+    {
+      "epoch": 0.65,
+      "eval_accuracy": 0.9884332281808622,
+      "eval_loss": 0.03642109036445618,
+      "eval_runtime": 80.6008,
+      "eval_samples_per_second": 106.19,
+      "eval_steps_per_second": 2.531,
+      "step": 400
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 4.0196078431372555e-05,
+      "loss": 0.0372,
+      "step": 600
+    },
+    {
+      "epoch": 0.98,
+      "eval_accuracy": 0.986447014838182,
+      "eval_loss": 0.04179869592189789,
+      "eval_runtime": 80.6457,
+      "eval_samples_per_second": 106.131,
+      "eval_steps_per_second": 2.53,
+      "step": 600
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 3.6928104575163405e-05,
+      "loss": 0.0114,
+      "step": 800
+    },
+    {
+      "epoch": 1.31,
+      "eval_accuracy": 0.9896015889706742,
+      "eval_loss": 0.0394107885658741,
+      "eval_runtime": 80.6065,
+      "eval_samples_per_second": 106.182,
+      "eval_steps_per_second": 2.531,
+      "step": 800
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 3.366013071895425e-05,
+      "loss": 0.0138,
+      "step": 1000
+    },
+    {
+      "epoch": 1.63,
+      "eval_accuracy": 0.9897184250496553,
+      "eval_loss": 0.0397811159491539,
+      "eval_runtime": 80.5677,
+      "eval_samples_per_second": 106.234,
+      "eval_steps_per_second": 2.532,
+      "step": 1000
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 3.0392156862745097e-05,
+      "loss": 0.0127,
+      "step": 1200
+    },
+    {
+      "epoch": 1.96,
+      "eval_accuracy": 0.9908867858394672,
+      "eval_loss": 0.034337081015110016,
+      "eval_runtime": 80.5302,
+      "eval_samples_per_second": 106.283,
+      "eval_steps_per_second": 2.533,
+      "step": 1200
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.7124183006535947e-05,
+      "loss": 0.0052,
+      "step": 1400
+    },
+    {
+      "epoch": 2.29,
+      "eval_accuracy": 0.9911204579974296,
+      "eval_loss": 0.037403274327516556,
+      "eval_runtime": 80.6258,
+      "eval_samples_per_second": 106.157,
+      "eval_steps_per_second": 2.53,
+      "step": 1400
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 2.38562091503268e-05,
+      "loss": 0.0018,
+      "step": 1600
+    },
+    {
+      "epoch": 2.61,
+      "eval_accuracy": 0.9906531136815049,
+      "eval_loss": 0.04766124114394188,
+      "eval_runtime": 80.6271,
+      "eval_samples_per_second": 106.155,
+      "eval_steps_per_second": 2.53,
+      "step": 1600
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 2.058823529411765e-05,
+      "loss": 0.0009,
+      "step": 1800
+    },
+    {
+      "epoch": 2.94,
+      "eval_accuracy": 0.9912372940764108,
+      "eval_loss": 0.0513538159430027,
+      "eval_runtime": 80.6405,
+      "eval_samples_per_second": 106.138,
+      "eval_steps_per_second": 2.53,
+      "step": 1800
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 1.7320261437908496e-05,
+      "loss": 0.001,
+      "step": 2000
+    },
+    {
+      "epoch": 3.27,
+      "eval_accuracy": 0.9904194415235424,
+      "eval_loss": 0.046223659068346024,
+      "eval_runtime": 80.5163,
+      "eval_samples_per_second": 106.301,
+      "eval_steps_per_second": 2.534,
+      "step": 2000
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 1.4052287581699347e-05,
+      "loss": 0.0002,
+      "step": 2200
+    },
+    {
+      "epoch": 3.59,
+      "eval_accuracy": 0.9911204579974296,
+      "eval_loss": 0.04658184573054314,
+      "eval_runtime": 80.6281,
+      "eval_samples_per_second": 106.154,
+      "eval_steps_per_second": 2.53,
+      "step": 2200
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 1.0784313725490197e-05,
+      "loss": 0.0006,
+      "step": 2400
+    },
+    {
+      "epoch": 3.92,
+      "eval_accuracy": 0.9905362776025236,
+      "eval_loss": 0.046631619334220886,
+      "eval_runtime": 80.5126,
+      "eval_samples_per_second": 106.306,
+      "eval_steps_per_second": 2.534,
+      "step": 2400
+    },
+    {
+      "epoch": 4.25,
+      "learning_rate": 7.5163398692810456e-06,
+      "loss": 0.0001,
+      "step": 2600
+    },
+    {
+      "epoch": 4.25,
+      "eval_accuracy": 0.990769949760486,
+      "eval_loss": 0.05143677070736885,
+      "eval_runtime": 80.6039,
+      "eval_samples_per_second": 106.186,
+      "eval_steps_per_second": 2.531,
+      "step": 2600
+    },
+    {
+      "epoch": 4.58,
+      "learning_rate": 4.2483660130718954e-06,
+      "loss": 0.0005,
+      "step": 2800
+    },
+    {
+      "epoch": 4.58,
+      "eval_accuracy": 0.9908867858394672,
+      "eval_loss": 0.04908544197678566,
+      "eval_runtime": 80.4782,
+      "eval_samples_per_second": 106.352,
+      "eval_steps_per_second": 2.535,
+      "step": 2800
+    },
+    {
+      "epoch": 4.9,
+      "learning_rate": 9.80392156862745e-07,
+      "loss": 0.0004,
+      "step": 3000
+    },
+    {
+      "epoch": 4.9,
+      "eval_accuracy": 0.9910036219184484,
+      "eval_loss": 0.049937766045331955,
+      "eval_runtime": 80.6026,
+      "eval_samples_per_second": 106.188,
+      "eval_steps_per_second": 2.531,
+      "step": 3000
+    }
+  ],
+  "max_steps": 3060,
+  "num_train_epochs": 5,
+  "total_flos": 0.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6715260d8f8dc2d9b6f203feba5b1e85999035d08e8d456813784a2d7ce39f95
+size 4027