Markk commited on
Commit
5dec0d2
1 Parent(s): 18bfa12

Upload v1 model (Checkpoint 6000)

Browse files
Files changed (8) hide show
  1. config.json +75 -0
  2. optimizer.pt +3 -0
  3. pytorch_model.bin +3 -0
  4. rng_state.pth +3 -0
  5. scaler.pt +3 -0
  6. scheduler.pt +3 -0
  7. trainer_state.json +88 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/gpt-neo-1.3B",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local",
21
+ "global",
22
+ "local",
23
+ "global",
24
+ "local",
25
+ "global",
26
+ "local",
27
+ "global",
28
+ "local",
29
+ "global",
30
+ "local",
31
+ "global",
32
+ "local"
33
+ ],
34
+ "attention_types": [
35
+ [
36
+ [
37
+ "global",
38
+ "local"
39
+ ],
40
+ 12
41
+ ]
42
+ ],
43
+ "bos_token_id": 50256,
44
+ "embed_dropout": 0,
45
+ "eos_token_id": 50257,
46
+ "gradient_checkpointing": false,
47
+ "hidden_size": 2048,
48
+ "initializer_range": 0.02,
49
+ "intermediate_size": null,
50
+ "layer_norm_epsilon": 1e-05,
51
+ "max_position_embeddings": 2048,
52
+ "model_type": "gpt_neo",
53
+ "num_heads": 16,
54
+ "num_layers": 24,
55
+ "pad_token_id": 50258,
56
+ "resid_dropout": 0,
57
+ "summary_activation": null,
58
+ "summary_first_dropout": 0.1,
59
+ "summary_proj_to_labels": true,
60
+ "summary_type": "cls_index",
61
+ "summary_use_proj": true,
62
+ "task_specific_params": {
63
+ "text-generation": {
64
+ "do_sample": true,
65
+ "max_length": 50,
66
+ "temperature": 0.9
67
+ }
68
+ },
69
+ "tokenizer_class": "GPT2Tokenizer",
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.20.0",
72
+ "use_cache": true,
73
+ "vocab_size": 50259,
74
+ "window_size": 256
75
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bd3f6a9c08e12f0995b8987b6aa0be12f6f347b899e266e2a788f00e75afe7d
3
+ size 10524831541
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eca4b63e00c0cf643a0b4cbbeda9874195025489d5dd449f7db2b9e80ab0db0
3
+ size 5363104725
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b77d9a5a81ac8b69e0670f5933e23ce7468b78385324a6bbb8b86fd0ba74fb6b
3
+ size 15597
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b77c67ca3fb0d7234d39f939d0791074eda83a0f90bb8b136d320c3a473fa62
3
+ size 557
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35d421c455531e443ef68bd5042b7f963d2347c483d8dfcb6aeb3c14fd4ba202
3
+ size 627
trainer_state.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 8.875739644970414,
5
+ "global_step": 6000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.74,
12
+ "learning_rate": 4.96e-05,
13
+ "loss": 1.8134,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.48,
18
+ "learning_rate": 4.996328645447816e-05,
19
+ "loss": 1.3742,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 2.22,
24
+ "learning_rate": 4.992627683197632e-05,
25
+ "loss": 1.122,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 2.96,
30
+ "learning_rate": 4.988934122871947e-05,
31
+ "loss": 0.8645,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 3.7,
36
+ "learning_rate": 4.9852553663952626e-05,
37
+ "loss": 0.6174,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 4.44,
42
+ "learning_rate": 4.9815618060695786e-05,
43
+ "loss": 0.5355,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 5.18,
48
+ "learning_rate": 4.977868245743893e-05,
49
+ "loss": 0.4336,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 5.92,
54
+ "learning_rate": 4.974167283493709e-05,
55
+ "loss": 0.3695,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 6.66,
60
+ "learning_rate": 4.970466321243524e-05,
61
+ "loss": 0.3013,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 7.4,
66
+ "learning_rate": 4.966772760917839e-05,
67
+ "loss": 0.2954,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 8.14,
72
+ "learning_rate": 4.963071798667654e-05,
73
+ "loss": 0.2812,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 8.88,
78
+ "learning_rate": 4.959370836417469e-05,
79
+ "loss": 0.2718,
80
+ "step": 6000
81
+ }
82
+ ],
83
+ "max_steps": 676000,
84
+ "num_train_epochs": 1000,
85
+ "total_flos": 1.2118642683671347e+17,
86
+ "trial_name": null,
87
+ "trial_params": null
88
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9949c173097804108f0625268b24c63f3f1c70d9342dfee2164c0e5dc8f16ef3
3
+ size 3259