Model save

README.md

@@ -2,28 +2,14 @@
 license: cc-by-nc-4.0
 base_model: sfairXC/FsfairX-LLaMA3-RM-v0.1
 tags:
-- easylm
-- alignment-handbook
 - trl
 - reward-trainer
+- easylm
+- alignment-handbook
 - generated_from_trainer
-datasets:
-- helpsteer-rm
-metrics:
-- accuracy
 model-index:
 - name: easylm-helpsteer-rm-FsfairX-LLaMA3-RM-v0.1
-  results:
-  - task:
-      name: Text Classification
-      type: text-classification
-    dataset:
-      name: helpsteer-rm
-      type: helpsteer-rm
-    metrics:
-    - name: Accuracy
-      type: accuracy
-      value: 0.6189111747851003
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,10 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # easylm-helpsteer-rm-FsfairX-LLaMA3-RM-v0.1
 
-This model is a fine-tuned version of [sfairXC/FsfairX-LLaMA3-RM-v0.1](https://huggingface.co/sfairXC/FsfairX-LLaMA3-RM-v0.1) on the helpsteer-rm dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.6558
-- Accuracy: 0.6189
+This model is a fine-tuned version of [sfairXC/FsfairX-LLaMA3-RM-v0.1](https://huggingface.co/sfairXC/FsfairX-LLaMA3-RM-v0.1) on an unknown dataset.
 
 ## Model description
 

all_results.json

@@ -7,9 +7,9 @@
     "eval_samples_per_second": 58.504,
     "eval_steps_per_second": 7.376,
     "total_flos": 0.0,
-    "train_loss": 0.6827200654027559,
-    "train_runtime": 753.5592,
+    "train_loss": 0.7041080118083268,
+    "train_runtime": 641.2149,
     "train_samples": 6666,
-    "train_samples_per_second": 8.846,
-    "train_steps_per_second": 1.107
+    "train_samples_per_second": 10.396,
+    "train_steps_per_second": 1.301
 }

config.json

@@ -31,6 +31,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.43.3",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 128257
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8acc17427f8f0dd8c1f1f528cf530b2d66f161b5911af5b8d36a2138fca1c667
+oid sha256:1f9b22e371184aacf60c8753ab4b3bf18b8091bd6600809c9d9a01574cf15ac6
 size 4976706864

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf18e01eb67a8e667dbe1c250eaddc16759f6e53f6c2ce59442fcf923204a156
+oid sha256:9fb9476172104f9cbf563c96804d75d9910295c5f44b62b4815cefd5928c837a
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fafe4d838dbd806b0a060badc69971b47e1b16f02ba269d0ca71421fd6f78dbe
+oid sha256:4be2c3efd182a08c5d23dddabf93c35c1ecb0316e338e60b7db71fabb06ce02e
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13cadc396a9ccebc408bad24f9762ca2e3d012d0bb83b69eaa3e43b7b0ca42cf
+oid sha256:816c0d28901233ff0b5b13c507ffdcb6f99a08574fb73c407351aa7ee9ea847a
 size 117473824

tokenizer_config.json

@@ -1,5 +1,4 @@
 {
-  "add_eos_token": true,
   "added_tokens_decoder": {
     "128000": {
       "content": "<|begin_of_text|>",

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 0.0,
-    "train_loss": 0.6827200654027559,
-    "train_runtime": 753.5592,
+    "train_loss": 0.7041080118083268,
+    "train_runtime": 641.2149,
     "train_samples": 6666,
-    "train_samples_per_second": 8.846,
-    "train_steps_per_second": 1.107
+    "train_samples_per_second": 10.396,
+    "train_steps_per_second": 1.301
 }

trainer_state.json

@@ -10,68 +10,68 @@
   "log_history": [
     {
       "epoch": 0.11990407673860912,
-      "grad_norm": 2.294161319732666,
+      "grad_norm": 33.553314208984375,
       "learning_rate": 1.929887378670186e-05,
-      "loss": 0.7381,
+      "loss": 0.7732,
       "step": 100
     },
     {
       "epoch": 0.23980815347721823,
-      "grad_norm": 2.2879245281219482,
+      "grad_norm": 5.416075706481934,
       "learning_rate": 1.729381074020218e-05,
-      "loss": 0.6867,
+      "loss": 0.7018,
       "step": 200
     },
     {
       "epoch": 0.3597122302158273,
-      "grad_norm": 4.782385349273682,
+      "grad_norm": 5.061486721038818,
       "learning_rate": 1.4265971312744252e-05,
-      "loss": 0.6877,
+      "loss": 0.7014,
       "step": 300
     },
     {
       "epoch": 0.47961630695443647,
-      "grad_norm": 4.921843528747559,
+      "grad_norm": 3.992720603942871,
       "learning_rate": 1.0639935022777741e-05,
-      "loss": 0.6793,
+      "loss": 0.6841,
       "step": 400
     },
     {
       "epoch": 0.5995203836930456,
-      "grad_norm": 3.5888805389404297,
+      "grad_norm": 4.914097785949707,
       "learning_rate": 6.924163688955825e-06,
-      "loss": 0.6807,
+      "loss": 0.7251,
       "step": 500
     },
     {
       "epoch": 0.7194244604316546,
-      "grad_norm": 4.4004926681518555,
+      "grad_norm": 4.0411577224731445,
       "learning_rate": 3.6397022482313804e-06,
-      "loss": 0.6611,
+      "loss": 0.6829,
       "step": 600
     },
     {
       "epoch": 0.8393285371702638,
-      "grad_norm": 7.610467910766602,
+      "grad_norm": 5.131595611572266,
       "learning_rate": 1.2471151031361795e-06,
-      "loss": 0.651,
+      "loss": 0.6744,
       "step": 700
     },
     {
       "epoch": 0.9592326139088729,
-      "grad_norm": 12.039061546325684,
+      "grad_norm": 12.620176315307617,
       "learning_rate": 8.190336667550869e-08,
-      "loss": 0.6708,
+      "loss": 0.6864,
       "step": 800
     },
     {
       "epoch": 1.0,
       "step": 834,
       "total_flos": 0.0,
-      "train_loss": 0.6827200654027559,
-      "train_runtime": 753.5592,
-      "train_samples_per_second": 8.846,
-      "train_steps_per_second": 1.107
+      "train_loss": 0.7041080118083268,
+      "train_runtime": 641.2149,
+      "train_samples_per_second": 10.396,
+      "train_steps_per_second": 1.301
     }
   ],
   "logging_steps": 100,