AndrewOficial commited on
Commit
9b24859
1 Parent(s): 728116d

Training in progress, step 1701

Browse files
config.json CHANGED
@@ -1,33 +1,33 @@
1
- {
2
- "_name_or_path": "AndrewOficial/metrology",
3
- "architectures": [
4
- "T5ForConditionalGeneration"
5
- ],
6
- "classifier_dropout": 0.0,
7
- "d_ff": 2816,
8
- "d_kv": 64,
9
- "d_model": 1024,
10
- "decoder_start_token_id": 0,
11
- "dense_act_fn": "gelu_new",
12
- "dropout_rate": 0.1,
13
- "eos_token_id": 1,
14
- "feed_forward_proj": "gated-gelu",
15
- "initializer_factor": 1.0,
16
- "is_encoder_decoder": true,
17
- "is_gated_act": true,
18
- "layer_norm_epsilon": 1e-06,
19
- "model_type": "t5",
20
- "n_positions": 512,
21
- "num_decoder_layers": 24,
22
- "num_heads": 16,
23
- "num_layers": 24,
24
- "output_past": true,
25
- "pad_token_id": 0,
26
- "relative_attention_max_distance": 128,
27
- "relative_attention_num_buckets": 32,
28
- "tie_word_embeddings": false,
29
- "torch_dtype": "float32",
30
- "transformers_version": "4.44.2",
31
- "use_cache": true,
32
- "vocab_size": 3574
33
- }
 
1
+ {
2
+ "_name_or_path": "AndrewOficial/metrology",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2816,
8
+ "d_kv": 64,
9
+ "d_model": 1024,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 24,
22
+ "num_heads": 16,
23
+ "num_layers": 24,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.44.2",
31
+ "use_cache": true,
32
+ "vocab_size": 3574
33
+ }
events.out.tfevents.1725974487.cf6f4403f6f5.3578.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc2faa17858a82745f81b1f779f7ef504b4b3f45c496fcb89c3c07e27e2b9bae
3
+ size 4184
events.out.tfevents.1725974649.cf6f4403f6f5.4729.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00682aea1123a0d29dae6adbb945f24852085f69182d24874a08b901f0b76f95
3
+ size 4184
events.out.tfevents.1725974768.cf6f4403f6f5.5337.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:661b26a8c15273eeb262807df82827bc6ddfb6f9cd1aea802b689db2874d66d4
3
+ size 4184
events.out.tfevents.1725974897.cf6f4403f6f5.5811.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35da6832cb0e0f42b2f60127fb30729e7d4f61dc262bf7eff75e354a989ecb59
3
+ size 8616
events.out.tfevents.1725975273.cf6f4403f6f5.7585.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef467680aea6e9fa53742725dbb2fce75ee72f417950f07cc2d26bc9d710211e
3
+ size 23317
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7bc58a00098526affc740a7cde86288829b633d320ac7c8dd63b43c34792152
3
  size 2898754440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:153a04cccf7f50dcaebfd148eb124671086339f4e1402e695b67459be87e39e6
3
  size 2898754440
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0dbf6b220b21965abb6dc9ae2b2193d99eab3be61c31ab293619930342edc381
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f861cc4c1bef8c9edfd5d8d682a73ff9e09f1931f9d0966ae1d7100dcb0dabb
3
  size 5176