Training in progress, step 2000

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "models/smolm-autoreg-bpe-seed_222/config.json",
+  "_name_or_path": "models/smolm-autoreg-bpe-seed_222",
   "_remove_final_layer_norm": false,
   "activation_dropout": 0.0,
   "activation_function": "relu",
@@ -24,7 +24,7 @@
   "pad_token_id": 0,
   "prefix": "<s>",
   "torch_dtype": "float32",
-  "transformers_version": "4.32.1",
+  "transformers_version": "4.38.2",
   "use_cache": true,
   "vocab_size": 8192,
   "word_embed_proj_dim": 256

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e5663548083716c6ee201424827cd7058fd6633aa950f300165335b009ae1b0
+size 33810896

runs/Mar25_20-13-06_phyl-ling-p01.la.utexas.edu/events.out.tfevents.1711415605.phyl-ling-p01.la.utexas.edu.1051288.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4ae6602e49f78f2ff568f514c23245a2692bf904245a4e356242122d30d6ff6
+size 5615

tokenizer_config.json

@@ -1,17 +1,48 @@
 {
   "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8192": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
-  "max_length": 128,
+  "max_length": null,
   "model_max_length": 1000000000000000019884624838656,
   "pad_to_multiple_of": null,
   "pad_token": "<pad>",
   "pad_token_type_id": 0,
   "padding_side": "right",
-  "stride": 0,
   "tokenizer_class": "GPT2Tokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f39e91d80205cad423d540a55f78920ed0716d676fd086072be57cb61d24433e
-size 4155
+oid sha256:140458c0fef611a7c332adc9e30cf844a75bac7e50979ae49f1bfc6b0b1cdb83
+size 4984