phi-2-pl-v_0_1

README.md

@@ -33,11 +33,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 2
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 8
-- total_train_batch_size: 16
+- total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-07
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:276bb6f686d172bbbf9b000c931999898ece611d35cbc4b269639c40cc2d9a69
+oid sha256:e9ffe1f32b8689c03b97d5762743a466ba23b35262fae0001cc16245322294db
 size 4999313176

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74550b77907e679d7fb4097c6da838a7465e65d6f5b3e18212a34b17aa45a112
+oid sha256:c738f2e447de0c934098cc04bb2b593490581ae424c132a2c63c160a0721cc77
 size 4982541984

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca3adbf4919bae32feb46a646c9c6a3b70486efb5c3511f9e4b2e53345562560
+oid sha256:1ef2cd58d7c591ec7a6675e30ed08e84ba8bdbc36fc114250af5463a7b32cf3f
 size 1118391932

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f28ce3ddcbc8b13a6c615831bf588ff102af28b764dbc834001a1bacfa3af6e7
+oid sha256:31d27b69c949be36db63f2b23566090956aa9bd1e651e5ae633fdd6c91a1d19a
 size 4664