Model save

README.md

@@ -3,15 +3,10 @@ library_name: transformers
 license: llama3.2
 base_model: meta-llama/Llama-3.2-1B
 tags:
-- alignment-handbook
-- trl
-- sft
-- generated_from_trainer
 - trl
 - sft
+- alignment-handbook
 - generated_from_trainer
-datasets:
-- data/small_transduction_heavy
 model-index:
 - name: llama_32_1b_testing
   results: []
@@ -22,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama_32_1b_testing
 
-This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on the data/small_transduction_heavy dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
 
 ## Model description
 

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 570977206272.0,
-    "train_loss": 0.5035594925284386,
-    "train_runtime": 19.8483,
+    "train_loss": 0.5035885199904442,
+    "train_runtime": 17.9848,
     "train_samples": 1024,
-    "train_samples_per_second": 51.591,
-    "train_steps_per_second": 0.202
+    "train_samples_per_second": 56.937,
+    "train_steps_per_second": 0.222
 }

config.json

@@ -31,6 +31,6 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.0.dev0",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 128256
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f008024762f4d07e17b56f0b8ecb48e3a8b306de261f571de05422cca7bdcb00
+oid sha256:ad43bd7c79d44bfad86dc2612e5bb3e12ed10fa0489bb3921507c26bd0926958
 size 2471645608

runs/Jan10_02-47-49_a100-40gx8-dev/events.out.tfevents.1736477280.a100-40gx8-dev.25091.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f315437cfb9d3bbb344aa704f00ebaa8066ffc1cf9c888795383491efc7f240
+size 7137

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 8192,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 570977206272.0,
-    "train_loss": 0.5035594925284386,
-    "train_runtime": 19.8483,
+    "train_loss": 0.5035885199904442,
+    "train_runtime": 17.9848,
     "train_samples": 1024,
-    "train_samples_per_second": 51.591,
-    "train_steps_per_second": 0.202
+    "train_samples_per_second": 56.937,
+    "train_steps_per_second": 0.222
 }

trainer_state.json

@@ -10,40 +10,40 @@
   "log_history": [
     {
       "epoch": 0.25,
-      "grad_norm": 21.95132839761702,
+      "grad_norm": 21.951654746952823,
       "learning_rate": 1e-05,
       "loss": 0.6512,
       "step": 1
     },
     {
       "epoch": 0.5,
-      "grad_norm": 19.159738592443173,
+      "grad_norm": 19.16167803635957,
       "learning_rate": 7.500000000000001e-06,
       "loss": 0.5545,
       "step": 2
     },
     {
       "epoch": 0.75,
-      "grad_norm": 10.60737320174702,
+      "grad_norm": 10.64027050880986,
       "learning_rate": 2.5000000000000015e-06,
-      "loss": 0.4432,
+      "loss": 0.4433,
       "step": 3
     },
     {
       "epoch": 1.0,
-      "grad_norm": 10.173966822336837,
+      "grad_norm": 10.18099018466467,
       "learning_rate": 0.0,
-      "loss": 0.3654,
+      "loss": 0.3655,
       "step": 4
     },
     {
       "epoch": 1.0,
       "step": 4,
       "total_flos": 570977206272.0,
-      "train_loss": 0.5035594925284386,
-      "train_runtime": 19.8483,
-      "train_samples_per_second": 51.591,
-      "train_steps_per_second": 0.202
+      "train_loss": 0.5035885199904442,
+      "train_runtime": 17.9848,
+      "train_samples_per_second": 56.937,
+      "train_steps_per_second": 0.222
     }
   ],
   "logging_steps": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66b018c5cc7f0d124f0f6db86d379b2f8deb008819f32a7736c2ac46b244d31e
+oid sha256:6a35f3d6fa879193785016c7c518bef52884520ea80b30a5c823df6360ec4859
 size 7160