Model save

README.md

@@ -2,15 +2,10 @@
 license: apache-2.0
 base_model: martimfasantos/tinyllama-1.1b-mt-sft-full
 tags:
-- alignment-handbook
-- trl
-- dpo
-- generated_from_trainer
 - trl
 - dpo
+- alignment-handbook
 - generated_from_trainer
-datasets:
-- haoranxu/ALMA-R-Preference
 model-index:
 - name: tinyllama-1.1b-mt-simpo_beta2.0_gamma1.6_LR5e-8_BS16_adamw_3epochs
   results: []
@@ -21,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinyllama-1.1b-mt-simpo_beta2.0_gamma1.6_LR5e-8_BS16_adamw_3epochs
 
-This model is a fine-tuned version of [martimfasantos/tinyllama-1.1b-mt-sft-full](https://huggingface.co/martimfasantos/tinyllama-1.1b-mt-sft-full) on the haoranxu/ALMA-R-Preference dataset.
+This model is a fine-tuned version of [martimfasantos/tinyllama-1.1b-mt-sft-full](https://huggingface.co/martimfasantos/tinyllama-1.1b-mt-sft-full) on the None dataset.
 
 ## Model description
 

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 3.0,
     "total_flos": 0.0,
-    "train_loss": 1.6293500020856702,
-    "train_runtime": 6068.1309,
+    "train_loss": 0.024831957134572962,
+    "train_runtime": 70.0566,
     "train_samples": 22202,
-    "train_samples_per_second": 10.976,
-    "train_steps_per_second": 0.686
+    "train_samples_per_second": 950.746,
+    "train_steps_per_second": 59.438
 }

config.json

@@ -24,6 +24,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.41.2",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 32000
 }

runs/Jul11_18-00-56_poseidon/events.out.tfevents.1720720923.poseidon.2256828.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cb702cb5cfbd3da6b5f2756f6ca0102ce21ebe37402269667909ddd14bdb0b1
+size 9789

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 3.0,
     "total_flos": 0.0,
-    "train_loss": 1.6293500020856702,
-    "train_runtime": 6068.1309,
+    "train_loss": 0.024831957134572962,
+    "train_runtime": 70.0566,
     "train_samples": 22202,
-    "train_samples_per_second": 10.976,
-    "train_steps_per_second": 0.686
+    "train_samples_per_second": 950.746,
+    "train_steps_per_second": 59.438
 }

trainer_state.json

@@ -6267,10 +6267,10 @@
       "epoch": 3.0,
       "step": 4164,
       "total_flos": 0.0,
-      "train_loss": 1.6293500020856702,
-      "train_runtime": 6068.1309,
-      "train_samples_per_second": 10.976,
-      "train_steps_per_second": 0.686
+      "train_loss": 0.024831957134572962,
+      "train_runtime": 70.0566,
+      "train_samples_per_second": 950.746,
+      "train_steps_per_second": 59.438
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1f4372e16293484878746a4ee218fa4690e3e8672e3566ce03c0b2b93539bdb
+oid sha256:1dda14af00beb796bb74e1583a0c0a361de413b3d251c23058be6c925d62cd5b
 size 6712