Model save

README.md

@@ -2,15 +2,12 @@
 license: mit
 base_model: gpt2
 tags:
-- alignment-handbook
-- trl
-- sft
-- generated_from_trainer
 - trl
 - sft
+- alignment-handbook
 - generated_from_trainer
 datasets:
-- appliedai-qx/sample-dataset-ah
+- generator
 model-index:
 - name: gpt2
   results: []
@@ -21,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gpt2
 
-This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the appliedai-qx/sample-dataset-ah dataset.
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset.
 
 ## Model description
 

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 7357983621120000.0,
-    "train_loss": 1.3856282998215068,
-    "train_runtime": 92.8881,
+    "train_loss": 0.11611378409645774,
+    "train_runtime": 16.2542,
     "train_samples": 10000,
-    "train_samples_per_second": 151.214,
-    "train_steps_per_second": 2.368
+    "train_samples_per_second": 864.147,
+    "train_steps_per_second": 13.535
 }

config.json

@@ -34,6 +34,6 @@
   },
   "torch_dtype": "bfloat16",
   "transformers_version": "4.41.2",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 50257
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02a7f1edfaf396ec82f65b48f1236d1895da1986033aa63a37a813f4bdd3f4e5
+oid sha256:bca3ffa173c3c144fb8fbee72f1c6755793b483e7d9fc736932542b22eb4b856
 size 248894656

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 7357983621120000.0,
-    "train_loss": 1.3856282998215068,
-    "train_runtime": 92.8881,
+    "train_loss": 0.11611378409645774,
+    "train_runtime": 16.2542,
     "train_samples": 10000,
-    "train_samples_per_second": 151.214,
-    "train_steps_per_second": 2.368
+    "train_samples_per_second": 864.147,
+    "train_steps_per_second": 13.535
 }

trainer_state.json

@@ -297,40 +297,40 @@
     },
     {
       "epoch": 0.9318181818181818,
-      "grad_norm": 0.65234375,
+      "grad_norm": 0.65625,
       "learning_rate": 2.818843167645835e-06,
       "loss": 1.2792,
       "step": 205
     },
     {
       "epoch": 0.9545454545454546,
-      "grad_norm": 0.5625,
+      "grad_norm": 0.5546875,
       "learning_rate": 1.2561111323605712e-06,
       "loss": 1.2774,
       "step": 210
     },
     {
       "epoch": 0.9772727272727273,
-      "grad_norm": 0.466796875,
+      "grad_norm": 0.47265625,
       "learning_rate": 3.145224048057727e-07,
-      "loss": 1.2792,
+      "loss": 1.2793,
       "step": 215
     },
     {
       "epoch": 1.0,
       "grad_norm": 0.51171875,
       "learning_rate": 0.0,
-      "loss": 1.2733,
+      "loss": 1.2731,
       "step": 220
     },
     {
       "epoch": 1.0,
       "step": 220,
       "total_flos": 7357983621120000.0,
-      "train_loss": 1.3856282998215068,
-      "train_runtime": 92.8881,
-      "train_samples_per_second": 151.214,
-      "train_steps_per_second": 2.368
+      "train_loss": 0.11611378409645774,
+      "train_runtime": 16.2542,
+      "train_samples_per_second": 864.147,
+      "train_steps_per_second": 13.535
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:449f32068558e0af9498f5259cc3c9120a26d378622c6ca421eec31b37715a3c
+oid sha256:bd0daf38ed0f1a900f3fba370b75fb8d3ed13aca8b90e5e840266baf26c6da76
 size 5496