Training in progress, epoch 1

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "EleutherAI/pythia-160m",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

logs/events.out.tfevents.1717557630.jagupard32.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:201c1aa12fe21726ce564c9a61ae8027fd998c68ea64024f6ee78706626e1126
+size 4808

logs/events.out.tfevents.1717558039.jagupard32.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:643747da8986aef2e1558a5c71c8e567f33a921ebab2ffafc9f37998d559a6aa
+size 4800

logs/events.out.tfevents.1717558480.jagupard32.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e9bfef1269c6e938c33daa3bd8553fcadd9b53cfd3cb3bf54acbb17374ecea9
+size 4800

logs/events.out.tfevents.1717559070.jagupard32.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3ecd0f48c0324af3e289dc45bc804ce517b5d9c6e857fd890e08679e82a744a
+size 4800

logs/events.out.tfevents.1717559350.jagupard32.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c80a481051c9f34b76795b15f1f4336a0ea2f17a13910694402c7e94d73919a1
+size 4800

logs/events.out.tfevents.1717559427.jagupard32.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:793cc68c3fc2c37071448f3417838ac2c95f19706d0aa3f84bf61ef6c82e767c
+size 4800

logs/events.out.tfevents.1717559467.jagupard32.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:190bfa8d7be4fa057d690e90fb04b7ecd4595a782beb24ded8b4feebc6eeaad3
+size 4800

logs/events.out.tfevents.1717559511.jagupard32.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98e65ceb6c9d49bd311e95b4a38aec935fcbf4fa47a9e4710ea77e04c9f5e0cf
+size 4800

logs/events.out.tfevents.1717559599.jagupard32.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46aee3b73cdd63377671f0e0c781041f83777dc5e055e9a12c01c52c09173c37
+size 13642

logs/events.out.tfevents.1717561143.jagupard32.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af5238405a1ef733c61a569da4f32b6e7b172aeca28db327fd73dcc3cf1350a5
+size 5835

logs/events.out.tfevents.1717561390.jagupard32.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdaabc2c1d23f0d01c1fa4de38aba8ca96f9257c69c82ffd66e9efc535765bde
+size 5629

logs/events.out.tfevents.1717561496.jagupard32.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71e0db80a50786f3328663da7c7681282ad199f186bf0df1884f247cb3454293
+size 7524

logs/events.out.tfevents.1717561804.jagupard32.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c9ebe76dff6d6b9f328e1ce9627a269e7bf60fe17bdc8e2797aab1a977e4edb
+size 6680

logs/events.out.tfevents.1717562559.jagupard32.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdfcc0bee81f01070bc143007868a8e0aa4fd0f605dbc585adec3dabdda5cf7b
+size 6047

logs/events.out.tfevents.1717563001.jagupard32.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:299f5c3f6f7d4403fb1946737dc5f1f786ab0f6b467422b0a28f1ba8e13d0781
+size 6474

logs/events.out.tfevents.1717563490.jagupard32.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fbf6e855c690270a57b43b2abb86a8ee6a53933f716ee67841f61f641ec8f50
+size 11111

logs/events.out.tfevents.1717564216.jagupard32.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:332dc0498f772a8bc4a19a7beb87ca2dd54c6daba51accd4a944d990bf0679fe
+size 186130

logs/events.out.tfevents.1717595606.sphinx8.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8a1e4a981f95cd1d9b1621de6f9d6f48ed0b934c2c47382d755f0bc2d2d4edf
+size 6468

logs/events.out.tfevents.1717596031.sphinx8.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f38347e04f91e237920c2e757eb3291ace4a376bcef956ea81d5d6dd5515fddb
+size 15119

logs/events.out.tfevents.1717597260.sphinx8.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2854a0291228dbbce9c9d4fc13f13818e093427bfc64869538d1f32729b84ab2
+size 4801

logs/events.out.tfevents.1717597649.sphinx8.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7602f9bc108b7ea96f9219bec7f47ce675e6a0c04df59865e0590b49d826bb7
+size 6257

logs/events.out.tfevents.1717597840.sphinx8.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93011d367263149432cc3b4bf257e7897c5a8b023a910b85bdc565d34ae0b19e
+size 6257

logs/events.out.tfevents.1717598007.sphinx8.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:243f94799857458c09bfe2f52ba67d9e79e1e6bb12b8cc42b1a5514eb02244f0
+size 12165

logs/events.out.tfevents.1717598838.sphinx8.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcd773a2e64f6405822389c11404645fa0c1da2decd3a1026a5c5301982f1740
+size 6278

logs/events.out.tfevents.1717600105.sphinx8.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ec1d476020cb5b333507529c69571262395bd12d4c8a9426e10e84ee09cb76e
+size 4803

logs/events.out.tfevents.1717600206.sphinx8.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1471b3f410de39ec507eb8aa3724725926f88fca971b1a078ada35341b4dbb65
+size 14863

logs/events.out.tfevents.1717605625.sphinx8.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bb016554cbd4385c1b9975997c49137a6d8cf1163c9ac1c8ab30c73bfe0a8c9
+size 5019

logs/events.out.tfevents.1717606001.sphinx8.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7db78119c3c3d74582528503f5781e4247a43521491dc46f2243937867bf5919
+size 13680

logs/events.out.tfevents.1717610579.sphinx8.stanford.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f87d632239e7454105e5a36604b44cf8596c163e2fc4176e274efb985b323d41
+size 14879

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9a4d81c063af9e8d4fb180aae5607f9ca766b05cea909e2ae074bb073a0aee6
+size 649308728

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,214 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da3de593a178566106a687fdb5a46e82fe41dd54bbec49b16545fa18dbe35be4
+size 5112