color_descriptions

README.md

@@ -39,6 +39,8 @@ The following hyperparameters were used during training:
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.03

adapter_config.json

@@ -16,7 +16,7 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:538fdbff1d625944a1d58b882700b018e3989acea3756f273c076d5dca8fc455
-size 28865136
+oid sha256:c774b1d1dbab6275f08d4c335a48e408a3a60d6f29feac6c148d9b8634d4c6e2
+size 57701064

runs/Jul17_02-57-24_ip-172-18-164-229.us-west-2.compute.internal/events.out.tfevents.1721185059.ip-172-18-164-229.us-west-2.compute.internal.13851.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:393bc8cf20d1a35c4aa4359d36431aa52dad9259b0f0137b67e01986a07b6243
+size 6723

runs/Jul17_02-57-55_ip-172-18-164-229.us-west-2.compute.internal/events.out.tfevents.1721185079.ip-172-18-164-229.us-west-2.compute.internal.13851.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4087ce3b2e928dbfb468aff886d6de1b93540c528dded30e93d65de939e98511
+size 8379

runs/Jul17_03-10-32_ip-172-18-164-229.us-west-2.compute.internal/events.out.tfevents.1721185837.ip-172-18-164-229.us-west-2.compute.internal.13851.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb08145a7af7d586f1e3e6a9866aaf0f48bd7573b9b98672dabcdcf6ba383de9
+size 452432

tokenizer.json

@@ -67,12 +67,6 @@
           "id": "A",
           "type_id": 0
         }
-      },
-      {
-        "SpecialToken": {
-          "id": "</s>",
-          "type_id": 0
-        }
       }
     ],
     "pair": [
@@ -88,12 +82,6 @@
           "type_id": 0
         }
       },
-      {
-        "SpecialToken": {
-          "id": "</s>",
-          "type_id": 0
-        }
-      },
       {
         "SpecialToken": {
           "id": "<s>",
@@ -105,24 +93,9 @@
           "id": "B",
           "type_id": 1
         }
-      },
-      {
-        "SpecialToken": {
-          "id": "</s>",
-          "type_id": 1
-        }
       }
     ],
     "special_tokens": {
-      "</s>": {
-        "id": "</s>",
-        "ids": [
-          2
-        ],
-        "tokens": [
-          "</s>"
-        ]
-      },
       "<s>": {
         "id": "<s>",
         "ids": [

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "add_bos_token": true,
-  "add_eos_token": true,
+  "add_eos_token": false,
   "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19f5daeac2a52babf39bbbd785344377fed2a39aa23a1208f0751347b5c9e72f
+oid sha256:8c51b4f76cd7106c343ff68fe7e955f3a205f65d0661177b6c663fc3211c67ae
 size 5368