Training in progress, step 1000

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/opt-1.3b",
+  "_name_or_path": "facebook/opt-125m",
   "_remove_final_layer_norm": false,
   "activation_dropout": 0.0,
   "activation_function": "relu",
@@ -12,8 +12,8 @@
   "dropout": 0.1,
   "enable_bias": true,
   "eos_token_id": 2,
-  "ffn_dim": 8192,
-  "hidden_size": 2048,
+  "ffn_dim": 3072,
+  "hidden_size": 768,
   "id2label": {
     "0": "negative",
     "1": "positive"
@@ -27,8 +27,8 @@
   "layerdrop": 0.0,
   "max_position_embeddings": 2048,
   "model_type": "opt",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 24,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
   "prefix": "</s>",
   "problem_type": "single_label_classification",
@@ -36,5 +36,5 @@
   "transformers_version": "4.43.3",
   "use_cache": true,
   "vocab_size": 50272,
-  "word_embed_proj_dim": 2048
+  "word_embed_proj_dim": 768
 }

logs/events.out.tfevents.1722352743.163db1aa8eaf.2333.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b002f1a5c4557533bb190fa36ce35f1ec69449e2ff685f30d996ce9684aee71
+size 5130

logs/events.out.tfevents.1722352771.163db1aa8eaf.2333.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec0cd659c501310eb6145deba490bec9fe4686d18f79c36a58500be8cd4e2474
+size 5713

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1089ad5ca315c54f5915342212832d885e5227c028120fcee0d71fce2f2c5eaf
+size 500985832

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:077a20e9d853074663a32801a4612ac716bb32a6a8a9d14e943bf4bfc451ab96
+size 5240