thashim commited on
Commit
b5c8e56
·
verified ·
1 Parent(s): 5086e91

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-70m",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 0,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 512,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 2048,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "gpt_neox",
19
+ "num_attention_heads": 8,
20
+ "num_hidden_layers": 6,
21
+ "rope_scaling": null,
22
+ "rotary_emb_base": 10000,
23
+ "rotary_pct": 0.25,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.41.2",
27
+ "use_cache": true,
28
+ "use_parallel_residual": true,
29
+ "vocab_size": 50304
30
+ }
logs/events.out.tfevents.1717557366.jagupard19.stanford.edu ADDED
File without changes
logs/events.out.tfevents.1717557630.jagupard32.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:201c1aa12fe21726ce564c9a61ae8027fd998c68ea64024f6ee78706626e1126
3
+ size 4808
logs/events.out.tfevents.1717558039.jagupard32.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:643747da8986aef2e1558a5c71c8e567f33a921ebab2ffafc9f37998d559a6aa
3
+ size 4800
logs/events.out.tfevents.1717558480.jagupard32.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e9bfef1269c6e938c33daa3bd8553fcadd9b53cfd3cb3bf54acbb17374ecea9
3
+ size 4800
logs/events.out.tfevents.1717558972.jagupard32.stanford.edu ADDED
File without changes
logs/events.out.tfevents.1717559070.jagupard32.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3ecd0f48c0324af3e289dc45bc804ce517b5d9c6e857fd890e08679e82a744a
3
+ size 4800
logs/events.out.tfevents.1717559350.jagupard32.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c80a481051c9f34b76795b15f1f4336a0ea2f17a13910694402c7e94d73919a1
3
+ size 4800
logs/events.out.tfevents.1717559427.jagupard32.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:793cc68c3fc2c37071448f3417838ac2c95f19706d0aa3f84bf61ef6c82e767c
3
+ size 4800
logs/events.out.tfevents.1717559467.jagupard32.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:190bfa8d7be4fa057d690e90fb04b7ecd4595a782beb24ded8b4feebc6eeaad3
3
+ size 4800
logs/events.out.tfevents.1717559511.jagupard32.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98e65ceb6c9d49bd311e95b4a38aec935fcbf4fa47a9e4710ea77e04c9f5e0cf
3
+ size 4800
logs/events.out.tfevents.1717559599.jagupard32.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46aee3b73cdd63377671f0e0c781041f83777dc5e055e9a12c01c52c09173c37
3
+ size 13642
logs/events.out.tfevents.1717561143.jagupard32.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af5238405a1ef733c61a569da4f32b6e7b172aeca28db327fd73dcc3cf1350a5
3
+ size 5835
logs/events.out.tfevents.1717561390.jagupard32.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdaabc2c1d23f0d01c1fa4de38aba8ca96f9257c69c82ffd66e9efc535765bde
3
+ size 5629
logs/events.out.tfevents.1717561496.jagupard32.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e0db80a50786f3328663da7c7681282ad199f186bf0df1884f247cb3454293
3
+ size 7524
logs/events.out.tfevents.1717561804.jagupard32.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c9ebe76dff6d6b9f328e1ce9627a269e7bf60fe17bdc8e2797aab1a977e4edb
3
+ size 6680
logs/events.out.tfevents.1717562559.jagupard32.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdfcc0bee81f01070bc143007868a8e0aa4fd0f605dbc585adec3dabdda5cf7b
3
+ size 6047
logs/events.out.tfevents.1717563001.jagupard32.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:299f5c3f6f7d4403fb1946737dc5f1f786ab0f6b467422b0a28f1ba8e13d0781
3
+ size 6474
logs/events.out.tfevents.1717563490.jagupard32.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fbf6e855c690270a57b43b2abb86a8ee6a53933f716ee67841f61f641ec8f50
3
+ size 11111
logs/events.out.tfevents.1717564216.jagupard32.stanford.edu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:332dc0498f772a8bc4a19a7beb87ca2dd54c6daba51accd4a944d990bf0679fe
3
+ size 186130
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32480ebb74aef7716fb6d8013eadee68137de8ff6329297cd526c9c7b6468788
3
+ size 281715176
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13e0bfd76591446f76582435702778ca13cd179b988dd8a946784a4880cc3ac6
3
+ size 5112