Training in progress, step 5000

config.json

@@ -18,7 +18,7 @@
   "max_position_embeddings": 256,
   "model_type": "opt",
   "num_attention_heads": 12,
-  "num_hidden_layers": 1,
+  "num_hidden_layers": 4,
   "pad_token_id": 1,
   "torch_dtype": "float32",
   "transformers_version": "4.39.3",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3d1d058efeff377d35c0a4e6fd543414a01bd702af605925bb8b74eb3f4ad9b
-size 157301184
+oid sha256:04580dfb10d55ede69faa8d4344f033ada1833861edd846ad16700ec577e710d
+size 161757984

runs/Apr12_12-34-39_593334df509e/events.out.tfevents.1712925280.593334df509e.2979.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a38d5ca978c293a645fd52c97e9b149312002bbea7fd9a1f82e4fc335b27653
+size 4524

runs/Apr12_12-35-06_593334df509e/events.out.tfevents.1712925306.593334df509e.2979.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5a197aa1c91cc8efded0a68cf1774bce30c04ed5f357861b8bb11d982d20358
+size 5006

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 64,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f0effdcadb80410c6623b77a6f39b0b18e94982a983184d5f2d92322bf8358c
+oid sha256:0c95ed6701116ee7b8a8b7a245b0e5735fc6fa102fbb496a7484a4146c747ed8
 size 4920