Training in progress, step 125

config.json

@@ -12,7 +12,7 @@
   "hidden_size": 576,
   "initializer_range": 0.02,
   "intermediate_size": 1536,
-  "max_position_embeddings": 2048,
+  "max_position_embeddings": 1024,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 9,

logs/harness_benchmarks=tinyBenchmarks, learning_rate=0.0001, lr_scheduler_kwargs=__power___0.7___lr_end___2e-05_, lr_scheduler_type=polynomial, per_device_train_batch_size=8/events.out.tfevents.1727022301.1c1a426a2fee

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5036ac3b1a677b1b849c416aa627a939bbef278185e2f19ef5318c184cd5004
+size 511

logs/harness_benchmarks=tinyBenchmarks, learning_rate=0.0001, lr_scheduler_kwargs=__power___0.7___lr_end___2e-05_, lr_scheduler_type=polynomial, per_device_train_batch_size=8/events.out.tfevents.1727023146.1c1a426a2fee

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:918591d3973c64fa747334c1d24312275a181b3ac797d4473017c6a76a7e7990
+size 40

logs/harness_benchmarks=tinyBenchmarks, learning_rate=0.0001, lr_scheduler_kwargs=__power___0.7___lr_end___2e-05_, lr_scheduler_type=polynomial, per_device_train_batch_size=8/events.out.tfevents.1727023719.1c1a426a2fee

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97fd4b7bd8ab64166b2a3052902f10450508779fb1ab7cb2e0dd27ebc9209c76
+size 5401

logs/harness_benchmarks=tinyBenchmarks, learning_rate=0.0001, lr_scheduler_kwargs=__power___0.7___lr_end___2e-05_, lr_scheduler_type=polynomial, per_device_train_batch_size=8/events.out.tfevents.1727024062.1c1a426a2fee

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d8442b294316693d62dbe68f46f76668d8ef7083b6ec1927fda0939ae1d49f2
+size 5854

logs/harness_benchmarks=tinyBenchmarks, learning_rate=0.0001, lr_scheduler_kwargs=__power___0.7___lr_end___2e-05_, lr_scheduler_type=polynomial, per_device_train_batch_size=8/events.out.tfevents.1727025056.1c1a426a2fee

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94884cff1502b49daf186b7ceedca7f0fd870bd2457e038664b55853a0891a4f
+size 5598

logs/harness_benchmarks=tinyBenchmarks, learning_rate=0.0001, lr_scheduler_kwargs=__power___0.7___lr_end___2e-05_, lr_scheduler_type=polynomial, per_device_train_batch_size=8/events.out.tfevents.1727025458.1c1a426a2fee

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d470d5c8119cbf71600dc64cb5184c96eed24af537d8b4eba7b66ed31ffb8a9
+size 9163

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b767b51383f2ecc0f2b377273c67ccc7a6c933dcd8895a1ae890747d3d9b44ef
+oid sha256:6ece4acb8e87423306035fd87bde134984d419f8b2a41b121154934af62b9c2a
 size 325669528

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 511,
+    "max_length": 1023,
     "strategy": "LongestFirst",
     "stride": 0
   },

tokenizer_config.json

@@ -160,7 +160,7 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 1024,
   "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eeef6d1bbe2dfc3585646903a446ca690711f76fe21b79c270327c4b86d07768
+oid sha256:33770307270dda4ff4ae179bd8dcf984c23818fe946bac64c4f3bb769b90e44d
 size 5688