Training in progress, step 100

config.json

@@ -12,6 +12,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 5632,
   "max_position_embeddings": 2048,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 22,
@@ -21,8 +22,8 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.39.3",
-  "use_cache": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": false,
   "vocab_size": 32000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d00fd21b1dbcc05ee02b0d5e7a41e719558957fa8ad20960c3126034891c356b
-size 2200119864
+oid sha256:958fd1aae9be1ad2fc22aa95bb8ba3d0bd2cc91be1633b3c1d3b346b9784d40e
+size 4400216536

runs/Jun05_01-08-42_poseidon/events.out.tfevents.1717550053.poseidon.2879567.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92584060b7ccdd7f5fbbb06fa41729d139ca8563f029c3d75e726c0f78910fb2
+size 13243

tokenizer.json

@@ -134,6 +134,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1536541e15b17a725697ea56e1ce1d9187e4dbe9bcfe0124f0f95f9fb7ac0d14
-size 6200
+oid sha256:d745fe69a0186cad10d9a8bcca31865063c8e9b214b03e09cc29d8b8c3839173
+size 5304