Hugging Face's logo

cspn007
/
flyte-pythia-70m-deduped-v0

Safetensors
PyTorch
English
gpt_neox
causal-lm
pythia
fine-tuning
flyte repo dataset
Model card Files Community
cspn007 commited on
Commit
39ce0d1
•
1 Parent(s): 403001e

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. checkpoint-3/config.json +32 -0
  2. checkpoint-3/generation_config.json +6 -0
  3. checkpoint-3/model.safetensors +3 -0
  4. checkpoint-3/optimizer.pt +3 -0
  5. checkpoint-3/rng_state.pth +3 -0
  6. checkpoint-3/scheduler.pt +3 -0
  7. checkpoint-3/trainer_state.json +54 -0
  8. checkpoint-3/training_args.bin +3 -0
  9. config.json +32 -0
  10. generation_config.json +6 -0
  11. model.safetensors +3 -0
  12. training_args.bin +3 -0
checkpoint-3/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-70m-deduped-v0",
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
+ "partial_rotary_factor": 0.25,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000,
24
+ "rotary_emb_base": 10000,
25
+ "rotary_pct": 0.25,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.45.2",
29
+ "use_cache": true,
30
+ "use_parallel_residual": true,
31
+ "vocab_size": 50304
32
+ }
checkpoint-3/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.45.2"
6
+ }
checkpoint-3/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b1554b104dee315439e8833a6b03fc6c98f2e93781f20bf7d4ffd3198945b08
3
+ size 281715176
checkpoint-3/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f26f8d94e16e959d3f1bbf11334e8714975361156a02addee30f227522db3a5f
3
+ size 563474746
checkpoint-3/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bb8daa2218f661aab713b5c8d6a88cb76f435e9067862f52676baa950ad6801
3
+ size 13990
checkpoint-3/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac15d8a19cf2b200854676368efdc4b5f41ea1bbdf9751c12b3b9868abf6cb3a
3
+ size 1064
checkpoint-3/trainer_state.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 7.48839299086416e-05,
5
+ "eval_steps": 100,
6
+ "global_step": 3,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 2.4961309969547202e-05,
13
+ "grad_norm": 41.783329010009766,
14
+ "learning_rate": 0.0003,
15
+ "loss": 3.3915,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 4.9922619939094404e-05,
20
+ "grad_norm": 45.086753845214844,
21
+ "learning_rate": 0.00015,
22
+ "loss": 2.6814,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 7.48839299086416e-05,
27
+ "grad_norm": 71.21851348876953,
28
+ "learning_rate": 0.0,
29
+ "loss": 4.6356,
30
+ "step": 3
31
+ }
32
+ ],
33
+ "logging_steps": 1,
34
+ "max_steps": 3,
35
+ "num_input_tokens_seen": 0,
36
+ "num_train_epochs": 1,
37
+ "save_steps": 500,
38
+ "stateful_callbacks": {
39
+ "TrainerControl": {
40
+ "args": {
41
+ "should_epoch_stop": false,
42
+ "should_evaluate": false,
43
+ "should_log": false,
44
+ "should_save": true,
45
+ "should_training_stop": true
46
+ },
47
+ "attributes": {}
48
+ }
49
+ },
50
+ "total_flos": 131600695296.0,
51
+ "train_batch_size": 1,
52
+ "trial_name": null,
53
+ "trial_params": null
54
+ }
checkpoint-3/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83303a1b5feeac73c118102d0e04e5f20eb9f3fca3134ccdc07b951c4e498319
3
+ size 5176
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-70m-deduped-v0",
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
+ "partial_rotary_factor": 0.25,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000,
24
+ "rotary_emb_base": 10000,
25
+ "rotary_pct": 0.25,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.45.2",
29
+ "use_cache": true,
30
+ "use_parallel_residual": true,
31
+ "vocab_size": 50304
32
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.45.2"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b1554b104dee315439e8833a6b03fc6c98f2e93781f20bf7d4ffd3198945b08
3
+ size 281715176
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83303a1b5feeac73c118102d0e04e5f20eb9f3fca3134ccdc07b951c4e498319
3
+ size 5176