Upload folder using huggingface_hub

README.md

@@ -1,36 +1,27 @@
 ---
-license: other
-datasets:
-- Open-Orca/OpenOrca
-- ehartford/wizard_vicuna_70k_unfiltered
+base_model: ss5
 tags:
-- code
-- prompt
-- reverse prompt
-widget:
-- text: "Photosynthesis is the process by which plants, algae and some bacteria convert carbon dioxide and water into glucose and oxygen, using the energy of sunlight. This process is fundamental to life on Earth, as it provides the basis for almost all food chains and also contributes to the carbon cycle by helping to regulate the concentration of carbon dioxide in the atmosphere.\n[REVERSED-PROMPT] "
-  example_title: "reverse prompt"
-
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: ss6
+  results: []
 ---
 
-# core-prompt-reverser-opt-1.3b
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# ss6
 
-This model is a fine-tuned version of [facebook/opt-1.3b](https://huggingface.co/facebook/opt-1.3b) on an unknown dataset.
+This model is a fine-tuned version of [ss5](https://huggingface.co/ss5) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4784
-- Accuracy: 0.6753
+- Loss: 1.2950
+- Accuracy: 0.7084
 
 ## Model description
 
- [INSTRUCTION] {your question}  
- [RESPONSE] {model response}  
-
-or  
-
-[RESPONSE] {response}    
-[REVERSED-PROMPT] {model prompt reversed}  
-
- 
+More information needed
 
 ## Intended uses & limitations
 
@@ -38,9 +29,9 @@ More information needed
 
 ## Training and evaluation data
 
-Wizard, openOrca, custom data
-
+More information needed
 
+## Training procedure
 
 ### Training hyperparameters
 
@@ -54,7 +45,7 @@ The following hyperparameters were used during training:
 - num_epochs: 1.0
 
 ### Training results
- this model is still training, it ran only 5% of the total training data, it will finish in 4/set
+
 
 
 ### Framework versions
@@ -62,4 +53,4 @@ The following hyperparameters were used during training:
 - Transformers 4.33.0.dev0
 - Pytorch 2.1.0.dev20230605+cu121
 - Datasets 2.14.4
-- Tokenizers 0.13.3
+- Tokenizers 0.13.3

all_results.json

@@ -1,15 +1,15 @@
 {
     "epoch": 1.0,
-    "eval_accuracy": 0.6752705025786228,
-    "eval_loss": 1.4784468412399292,
-    "eval_runtime": 55.0697,
+    "eval_accuracy": 0.7083881079987865,
+    "eval_loss": 1.294954776763916,
+    "eval_runtime": 53.4048,
     "eval_samples": 232,
-    "eval_samples_per_second": 4.213,
-    "eval_steps_per_second": 0.527,
-    "perplexity": 4.3861280346659415,
-    "train_loss": 1.700456760354238,
-    "train_runtime": 3303.7788,
-    "train_samples": 11678,
-    "train_samples_per_second": 3.535,
-    "train_steps_per_second": 0.442
+    "eval_samples_per_second": 4.344,
+    "eval_steps_per_second": 0.543,
+    "perplexity": 3.6508308680217363,
+    "train_loss": 1.2382940134009472,
+    "train_runtime": 11022.1698,
+    "train_samples": 38349,
+    "train_samples_per_second": 3.479,
+    "train_steps_per_second": 0.435
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/opt-1.3b",
+  "_name_or_path": "ss5",
   "_remove_final_layer_norm": false,
   "activation_dropout": 0.0,
   "activation_function": "relu",

eval_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 1.0,
-    "eval_accuracy": 0.6752705025786228,
-    "eval_loss": 1.4784468412399292,
-    "eval_runtime": 55.0697,
+    "eval_accuracy": 0.7083881079987865,
+    "eval_loss": 1.294954776763916,
+    "eval_runtime": 53.4048,
     "eval_samples": 232,
-    "eval_samples_per_second": 4.213,
-    "eval_steps_per_second": 0.527,
-    "perplexity": 4.3861280346659415
+    "eval_samples_per_second": 4.344,
+    "eval_steps_per_second": 0.543,
+    "perplexity": 3.6508308680217363
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c82ac35a6d50d4f6668cf6fc2037aece6e394df4a65ef6ff81ad131822fe6e70
+oid sha256:f8c1c4b4f568da599148a79e669bbd5590428dfaf7064385627c5948af153ced
 size 2631648218

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "train_loss": 1.700456760354238,
-    "train_runtime": 3303.7788,
-    "train_samples": 11678,
-    "train_samples_per_second": 3.535,
-    "train_steps_per_second": 0.442
+    "train_loss": 1.2382940134009472,
+    "train_runtime": 11022.1698,
+    "train_samples": 38349,
+    "train_samples_per_second": 3.479,
+    "train_steps_per_second": 0.435
 }

trainer_state.json

@@ -3,38 +3,80 @@
   "best_model_checkpoint": null,
   "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 1460,
+  "global_step": 4794,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.34,
-      "learning_rate": 3.287671232876712e-05,
-      "loss": 1.776,
+      "epoch": 0.1,
+      "learning_rate": 4.478514810179391e-05,
+      "loss": 1.3792,
       "step": 500
     },
     {
-      "epoch": 0.68,
-      "learning_rate": 1.5753424657534248e-05,
-      "loss": 1.6672,
+      "epoch": 0.21,
+      "learning_rate": 3.9570296203587817e-05,
+      "loss": 1.3043,
       "step": 1000
     },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.435544430538173e-05,
+      "loss": 1.2641,
+      "step": 1500
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.9140592407175638e-05,
+      "loss": 1.2319,
+      "step": 2000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.3925740508969545e-05,
+      "loss": 1.2035,
+      "step": 2500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8710888610763455e-05,
+      "loss": 1.2072,
+      "step": 3000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.3496036712557364e-05,
+      "loss": 1.1955,
+      "step": 3500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 8.281184814351273e-06,
+      "loss": 1.1949,
+      "step": 4000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.0663329161451816e-06,
+      "loss": 1.194,
+      "step": 4500
+    },
     {
       "epoch": 1.0,
-      "step": 1460,
-      "total_flos": 8.671679350623437e+16,
-      "train_loss": 1.700456760354238,
-      "train_runtime": 3303.7788,
-      "train_samples_per_second": 3.535,
-      "train_steps_per_second": 0.442
+      "step": 4794,
+      "total_flos": 2.8476642525865574e+17,
+      "train_loss": 1.2382940134009472,
+      "train_runtime": 11022.1698,
+      "train_samples_per_second": 3.479,
+      "train_steps_per_second": 0.435
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1460,
+  "max_steps": 4794,
   "num_train_epochs": 1,
-  "save_steps": -1460,
-  "total_flos": 8.671679350623437e+16,
+  "save_steps": -4794,
+  "total_flos": 2.8476642525865574e+17,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68e5b42e7290d1422423b958c1cf982b94ae5db9e379c560d977a8e2c38edab8
+oid sha256:13435d31ff4c3a7b19d246d3aedb0e34f659b86388d243bd7658841e425d0944
 size 4472