Training in progress, step 2000

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "models/smolm-autoreg-bpe-seed_111/config.json",
+  "_name_or_path": "models/smolm-autoreg-bpe-seed_111",
   "_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 sha256:93a8a299d58dd9cdf0e9dadfda5b5c5e8feddf981160ce055ed5a4314b866861
+size 33810896

runs/Mar25_19-52-30_phyl-ling-p01.la.utexas.edu/events.out.tfevents.1711414351.phyl-ling-p01.la.utexas.edu.1050359.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0efeab8972d124b1cd769c581bda83b6e328b966f07f9e22bd2d57a2f5a8d87
+size 5615

tokenizer.json

@@ -1,7 +1,14 @@
 {
   "version": "1.0",
   "truncation": null,
-  "padding": null,
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "<pad>"
+  },
   "added_tokens": [
     {
       "id": 0,

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 sha256:70f2c38b176e8ba2fc8f92d985de4ba0eeb130134571df536cbca03efd619cd3
-size 4155
+oid sha256:7ef9ec3ef00a9b0e23e5875b72fa574d46f08baf5b09e77dab41802806670864
+size 4984