Training in progress, epoch 0

config.json

@@ -6,15 +6,15 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 128,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 256,
+  "intermediate_size": 2304,
   "max_position_embeddings": 2048,
   "model_type": "llama",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 3,
-  "num_key_value_heads": 8,
-  "pad_token_id": 2,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 12,
+  "pad_token_id": 3,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
@@ -23,5 +23,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.35.0",
   "use_cache": true,
-  "vocab_size": 5000
+  "vocab_size": 10000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a44e7d6e5b528530ea499c1816d26d896b51582f02e86fdf1ef2603247e5dece
-size 7092848
+oid sha256:933b85c55b2f90ec70e21aa648b81a66d44a9210da1748206a7fd66fd14cbe00
+size 429579272

runs/Nov10_08-41-42_ddf776d2631b/events.out.tfevents.1699605803.ddf776d2631b.2960.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60ee64d30c5ff92e1db4f2fb7e742c1e5baaf787318d1fa3b78048c3813f1a1b
+size 4359

runs/Nov10_08-52-09_ddf776d2631b/events.out.tfevents.1699606339.ddf776d2631b.5801.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ef14827bc46ef6b77a28c0b6f3fef85c7c38c88f6d4f51dfdcf1545005c1d3a
+size 4787

special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f283a54aa10902c1be4fea3071a0df9998e466bdab8c4d215c10c34de662920b
+oid sha256:c44fcd57369efc5b4f98de198677d74728c8f86c0e43ba5a8469346ace4f1b3f
 size 4600