Hugging Face's logo

bit2vec
/
bitsseal

Safetensors
Model card Files
xet
 Community
xujjia commited on
Commit
79359fa
·
verified ·
1 Parent(s): a9a122c

s43_std: all checkpoints

Browse files
Files changed (35) hide show
  1. qwen2.5-7b_c4_1B/s43_std/checkpoint-12204/bf16.log +2 -0
  2. qwen2.5-7b_c4_1B/s43_std/checkpoint-12204/config.json +62 -0
  3. qwen2.5-7b_c4_1B/s43_std/checkpoint-12204/generation_config.json +9 -0
  4. qwen2.5-7b_c4_1B/s43_std/checkpoint-12204/model.safetensors +3 -0
  5. qwen2.5-7b_c4_1B/s43_std/checkpoint-12204/trainer_state.json +0 -0
  6. qwen2.5-7b_c4_1B/s43_std/checkpoint-15255/bf16.log +2 -0
  7. qwen2.5-7b_c4_1B/s43_std/checkpoint-15255/config.json +62 -0
  8. qwen2.5-7b_c4_1B/s43_std/checkpoint-15255/generation_config.json +9 -0
  9. qwen2.5-7b_c4_1B/s43_std/checkpoint-15255/model.safetensors +3 -0
  10. qwen2.5-7b_c4_1B/s43_std/checkpoint-15255/trainer_state.json +0 -0
  11. qwen2.5-7b_c4_1B/s43_std/checkpoint-3051/bf16.log +2 -0
  12. qwen2.5-7b_c4_1B/s43_std/checkpoint-3051/config.json +62 -0
  13. qwen2.5-7b_c4_1B/s43_std/checkpoint-3051/generation_config.json +9 -0
  14. qwen2.5-7b_c4_1B/s43_std/checkpoint-3051/model.safetensors +3 -0
  15. qwen2.5-7b_c4_1B/s43_std/checkpoint-3051/trainer_state.json +2169 -0
  16. qwen2.5-7b_c4_1B/s43_std/checkpoint-30510/bf16.log +2 -0
  17. qwen2.5-7b_c4_1B/s43_std/checkpoint-30510/config.json +62 -0
  18. qwen2.5-7b_c4_1B/s43_std/checkpoint-30510/generation_config.json +9 -0
  19. qwen2.5-7b_c4_1B/s43_std/checkpoint-30510/model.safetensors +3 -0
  20. qwen2.5-7b_c4_1B/s43_std/checkpoint-30510/trainer_state.json +0 -0
  21. qwen2.5-7b_c4_1B/s43_std/checkpoint-30517/bf16.log +2 -0
  22. qwen2.5-7b_c4_1B/s43_std/checkpoint-30517/config.json +62 -0
  23. qwen2.5-7b_c4_1B/s43_std/checkpoint-30517/generation_config.json +9 -0
  24. qwen2.5-7b_c4_1B/s43_std/checkpoint-30517/model.safetensors +3 -0
  25. qwen2.5-7b_c4_1B/s43_std/checkpoint-30517/trainer_state.json +0 -0
  26. qwen2.5-7b_c4_1B/s43_std/checkpoint-6102/bf16.log +2 -0
  27. qwen2.5-7b_c4_1B/s43_std/checkpoint-6102/config.json +62 -0
  28. qwen2.5-7b_c4_1B/s43_std/checkpoint-6102/generation_config.json +9 -0
  29. qwen2.5-7b_c4_1B/s43_std/checkpoint-6102/model.safetensors +3 -0
  30. qwen2.5-7b_c4_1B/s43_std/checkpoint-6102/trainer_state.json +0 -0
  31. qwen2.5-7b_c4_1B/s43_std/checkpoint-9153/bf16.log +2 -0
  32. qwen2.5-7b_c4_1B/s43_std/checkpoint-9153/config.json +62 -0
  33. qwen2.5-7b_c4_1B/s43_std/checkpoint-9153/generation_config.json +9 -0
  34. qwen2.5-7b_c4_1B/s43_std/checkpoint-9153/model.safetensors +3 -0
  35. qwen2.5-7b_c4_1B/s43_std/checkpoint-9153/trainer_state.json +0 -0
qwen2.5-7b_c4_1B/s43_std/checkpoint-12204/bf16.log ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ bf16 /root/traj/s3_1B/s43_std/checkpoint-12204/model.safetensors 7615616512
2
+ DONE
qwen2.5-7b_c4_1B/s43_std/checkpoint-12204/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "float32",
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention"
42
+ ],
43
+ "max_position_embeddings": 131072,
44
+ "max_window_layers": 28,
45
+ "model_type": "qwen2",
46
+ "num_attention_heads": 28,
47
+ "num_hidden_layers": 28,
48
+ "num_key_value_heads": 4,
49
+ "pad_token_id": null,
50
+ "rms_norm_eps": 1e-06,
51
+ "rope_parameters": {
52
+ "rope_theta": 1000000.0,
53
+ "rope_type": "default"
54
+ },
55
+ "sliding_window": null,
56
+ "tie_word_embeddings": false,
57
+ "transformers_version": "5.22.1",
58
+ "use_cache": false,
59
+ "use_mrope": false,
60
+ "use_sliding_window": false,
61
+ "vocab_size": 152064
62
+ }
qwen2.5-7b_c4_1B/s43_std/checkpoint-12204/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151643,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.22.1",
8
+ "use_cache": true
9
+ }
qwen2.5-7b_c4_1B/s43_std/checkpoint-12204/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb9592bf6d1c309dcd3e2a05a8136f8892d90ec7f6686ef516d6642db685fa8d
3
+ size 15231272152
qwen2.5-7b_c4_1B/s43_std/checkpoint-12204/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5-7b_c4_1B/s43_std/checkpoint-15255/bf16.log ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ bf16 /root/traj/s3_1B/s43_std/checkpoint-15255/model.safetensors 7615616512
2
+ DONE
qwen2.5-7b_c4_1B/s43_std/checkpoint-15255/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "float32",
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention"
42
+ ],
43
+ "max_position_embeddings": 131072,
44
+ "max_window_layers": 28,
45
+ "model_type": "qwen2",
46
+ "num_attention_heads": 28,
47
+ "num_hidden_layers": 28,
48
+ "num_key_value_heads": 4,
49
+ "pad_token_id": null,
50
+ "rms_norm_eps": 1e-06,
51
+ "rope_parameters": {
52
+ "rope_theta": 1000000.0,
53
+ "rope_type": "default"
54
+ },
55
+ "sliding_window": null,
56
+ "tie_word_embeddings": false,
57
+ "transformers_version": "5.22.1",
58
+ "use_cache": false,
59
+ "use_mrope": false,
60
+ "use_sliding_window": false,
61
+ "vocab_size": 152064
62
+ }
qwen2.5-7b_c4_1B/s43_std/checkpoint-15255/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151643,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.22.1",
8
+ "use_cache": true
9
+ }
qwen2.5-7b_c4_1B/s43_std/checkpoint-15255/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef01e48af9a587e3fb9c35c27683dbc811c7a7e51f178991fb0ac31b3f60bd23
3
+ size 15231272152
qwen2.5-7b_c4_1B/s43_std/checkpoint-15255/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5-7b_c4_1B/s43_std/checkpoint-3051/bf16.log ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ bf16 /root/traj/s3_1B/s43_std/checkpoint-3051/model.safetensors 7615616512
2
+ DONE
qwen2.5-7b_c4_1B/s43_std/checkpoint-3051/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "float32",
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention"
42
+ ],
43
+ "max_position_embeddings": 131072,
44
+ "max_window_layers": 28,
45
+ "model_type": "qwen2",
46
+ "num_attention_heads": 28,
47
+ "num_hidden_layers": 28,
48
+ "num_key_value_heads": 4,
49
+ "pad_token_id": null,
50
+ "rms_norm_eps": 1e-06,
51
+ "rope_parameters": {
52
+ "rope_theta": 1000000.0,
53
+ "rope_type": "default"
54
+ },
55
+ "sliding_window": null,
56
+ "tie_word_embeddings": false,
57
+ "transformers_version": "5.22.1",
58
+ "use_cache": false,
59
+ "use_mrope": false,
60
+ "use_sliding_window": false,
61
+ "vocab_size": 152064
62
+ }
qwen2.5-7b_c4_1B/s43_std/checkpoint-3051/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151643,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.22.1",
8
+ "use_cache": true
9
+ }
qwen2.5-7b_c4_1B/s43_std/checkpoint-3051/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04f26fb542553dbb705a79aae03f97c342eba2058a7d047bb54ebc0891cc2a4f
3
+ size 15231272152
qwen2.5-7b_c4_1B/s43_std/checkpoint-3051/trainer_state.json ADDED
@@ -0,0 +1,2169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.09997706196546187,
6
+ "eval_steps": 500,
7
+ "global_step": 3051,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.00032768620768751843,
14
+ "grad_norm": 6.687935829162598,
15
+ "learning_rate": 4.4189852700491e-06,
16
+ "loss": 12.6359375,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.0006553724153750369,
21
+ "grad_norm": 7.099649906158447,
22
+ "learning_rate": 9.328968903436987e-06,
23
+ "loss": 12.390625,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.0009830586230625553,
28
+ "grad_norm": 6.1579694747924805,
29
+ "learning_rate": 1.4238952536824876e-05,
30
+ "loss": 11.003125,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.0013107448307500737,
35
+ "grad_norm": 3.0869617462158203,
36
+ "learning_rate": 1.9148936170212762e-05,
37
+ "loss": 9.515625,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.0016384310384375922,
42
+ "grad_norm": 2.296570062637329,
43
+ "learning_rate": 2.405891980360065e-05,
44
+ "loss": 8.578125,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.0019661172461251106,
49
+ "grad_norm": 1.5988047122955322,
50
+ "learning_rate": 2.896890343698854e-05,
51
+ "loss": 7.93046875,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.002293803453812629,
56
+ "grad_norm": 1.468277096748352,
57
+ "learning_rate": 3.3878887070376427e-05,
58
+ "loss": 7.63515625,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.0026214896615001475,
63
+ "grad_norm": 2.1447181701660156,
64
+ "learning_rate": 3.878887070376432e-05,
65
+ "loss": 7.4328125,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.002949175869187666,
70
+ "grad_norm": 2.2946114540100098,
71
+ "learning_rate": 4.3698854337152205e-05,
72
+ "loss": 7.409375,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.0032768620768751843,
77
+ "grad_norm": 3.852699041366577,
78
+ "learning_rate": 4.860883797054009e-05,
79
+ "loss": 7.40390625,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.0036045482845627028,
84
+ "grad_norm": 1.5922746658325195,
85
+ "learning_rate": 5.3518821603927984e-05,
86
+ "loss": 7.14609375,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.003932234492250221,
91
+ "grad_norm": 2.1730661392211914,
92
+ "learning_rate": 5.842880523731587e-05,
93
+ "loss": 7.0421875,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.004259920699937739,
98
+ "grad_norm": 1.7380120754241943,
99
+ "learning_rate": 6.333878887070376e-05,
100
+ "loss": 7.00859375,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.004587606907625258,
105
+ "grad_norm": 1.800024390220642,
106
+ "learning_rate": 6.824877250409165e-05,
107
+ "loss": 6.99609375,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.004915293115312776,
112
+ "grad_norm": 2.439539909362793,
113
+ "learning_rate": 7.315875613747954e-05,
114
+ "loss": 6.88671875,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.005242979323000295,
119
+ "grad_norm": 2.319902181625366,
120
+ "learning_rate": 7.806873977086742e-05,
121
+ "loss": 6.80625,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.005570665530687813,
126
+ "grad_norm": 1.4037840366363525,
127
+ "learning_rate": 8.297872340425531e-05,
128
+ "loss": 6.76953125,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.005898351738375332,
133
+ "grad_norm": 1.7466950416564941,
134
+ "learning_rate": 8.78887070376432e-05,
135
+ "loss": 6.8,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.00622603794606285,
140
+ "grad_norm": 1.4992178678512573,
141
+ "learning_rate": 9.279869067103108e-05,
142
+ "loss": 6.665625,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.006553724153750369,
147
+ "grad_norm": 1.3870316743850708,
148
+ "learning_rate": 9.770867430441898e-05,
149
+ "loss": 6.58828125,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.006881410361437887,
154
+ "grad_norm": 1.765749216079712,
155
+ "learning_rate": 0.00010261865793780687,
156
+ "loss": 6.615625,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.0072090965691254056,
161
+ "grad_norm": 1.435910701751709,
162
+ "learning_rate": 0.00010752864157119475,
163
+ "loss": 6.51796875,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.0075367827768129236,
168
+ "grad_norm": 1.5797899961471558,
169
+ "learning_rate": 0.00011243862520458264,
170
+ "loss": 6.478125,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.007864468984500442,
175
+ "grad_norm": 1.752839207649231,
176
+ "learning_rate": 0.00011734860883797053,
177
+ "loss": 6.43203125,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.008192155192187961,
182
+ "grad_norm": 1.431261420249939,
183
+ "learning_rate": 0.0001222585924713584,
184
+ "loss": 6.5203125,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.008519841399875478,
189
+ "grad_norm": 1.4530874490737915,
190
+ "learning_rate": 0.0001271685761047463,
191
+ "loss": 6.4,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.008847527607562997,
196
+ "grad_norm": 1.2793446779251099,
197
+ "learning_rate": 0.0001320785597381342,
198
+ "loss": 6.3921875,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.009175213815250516,
203
+ "grad_norm": 1.4799035787582397,
204
+ "learning_rate": 0.0001369885433715221,
205
+ "loss": 6.34609375,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.009502900022938035,
210
+ "grad_norm": 1.5895757675170898,
211
+ "learning_rate": 0.00014189852700490998,
212
+ "loss": 6.29921875,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.009830586230625552,
217
+ "grad_norm": 1.2123584747314453,
218
+ "learning_rate": 0.00014680851063829785,
219
+ "loss": 6.30390625,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.010158272438313071,
224
+ "grad_norm": 1.4102599620819092,
225
+ "learning_rate": 0.00015171849427168577,
226
+ "loss": 6.34609375,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.01048595864600059,
231
+ "grad_norm": 2.396242618560791,
232
+ "learning_rate": 0.00015662847790507363,
233
+ "loss": 6.3109375,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.010813644853688109,
238
+ "grad_norm": 1.1571189165115356,
239
+ "learning_rate": 0.00016153846153846153,
240
+ "loss": 6.303125,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.011141331061375626,
245
+ "grad_norm": 1.2486337423324585,
246
+ "learning_rate": 0.00016644844517184942,
247
+ "loss": 6.265625,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.011469017269063145,
252
+ "grad_norm": 1.3293136358261108,
253
+ "learning_rate": 0.0001713584288052373,
254
+ "loss": 6.228125,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.011796703476750664,
259
+ "grad_norm": 1.1541768312454224,
260
+ "learning_rate": 0.0001762684124386252,
261
+ "loss": 6.128125,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.012124389684438183,
266
+ "grad_norm": 1.2318528890609741,
267
+ "learning_rate": 0.0001811783960720131,
268
+ "loss": 6.18984375,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.0124520758921257,
273
+ "grad_norm": 1.5763192176818848,
274
+ "learning_rate": 0.000186088379705401,
275
+ "loss": 6.1015625,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.012779762099813219,
280
+ "grad_norm": 1.0083833932876587,
281
+ "learning_rate": 0.00019099836333878883,
282
+ "loss": 6.0734375,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.013107448307500737,
287
+ "grad_norm": 1.2412079572677612,
288
+ "learning_rate": 0.00019590834697217672,
289
+ "loss": 6.1203125,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.013435134515188256,
294
+ "grad_norm": 1.109154462814331,
295
+ "learning_rate": 0.0002008183306055646,
296
+ "loss": 6.003125,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.013762820722875773,
301
+ "grad_norm": 1.3962513208389282,
302
+ "learning_rate": 0.0002057283142389525,
303
+ "loss": 6.0046875,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.014090506930563292,
308
+ "grad_norm": 1.1538583040237427,
309
+ "learning_rate": 0.0002106382978723404,
310
+ "loss": 6.03046875,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.014418193138250811,
315
+ "grad_norm": 1.1562613248825073,
316
+ "learning_rate": 0.0002155482815057283,
317
+ "loss": 6.05625,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.01474587934593833,
322
+ "grad_norm": 1.144105315208435,
323
+ "learning_rate": 0.00022045826513911618,
324
+ "loss": 5.99140625,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.015073565553625847,
329
+ "grad_norm": 1.1402214765548706,
330
+ "learning_rate": 0.00022536824877250405,
331
+ "loss": 5.94609375,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.015401251761313366,
336
+ "grad_norm": 0.9526482224464417,
337
+ "learning_rate": 0.00023027823240589194,
338
+ "loss": 5.92421875,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.015728937969000885,
343
+ "grad_norm": 0.9701732993125916,
344
+ "learning_rate": 0.00023518821603927983,
345
+ "loss": 5.97578125,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.016056624176688402,
350
+ "grad_norm": 0.9096916317939758,
351
+ "learning_rate": 0.00024009819967266773,
352
+ "loss": 5.92734375,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.016384310384375923,
357
+ "grad_norm": 1.4619733095169067,
358
+ "learning_rate": 0.0002450081833060556,
359
+ "loss": 5.93828125,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.01671199659206344,
364
+ "grad_norm": 1.182580590248108,
365
+ "learning_rate": 0.0002499181669394435,
366
+ "loss": 5.815625,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.017039682799750957,
371
+ "grad_norm": 1.208715558052063,
372
+ "learning_rate": 0.0002548281505728314,
373
+ "loss": 5.81875,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.017367369007438477,
378
+ "grad_norm": 0.8653039336204529,
379
+ "learning_rate": 0.0002597381342062193,
380
+ "loss": 5.859375,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.017695055215125995,
385
+ "grad_norm": 1.1806159019470215,
386
+ "learning_rate": 0.0002646481178396072,
387
+ "loss": 5.8484375,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.018022741422813515,
392
+ "grad_norm": 1.244727373123169,
393
+ "learning_rate": 0.0002695581014729951,
394
+ "loss": 5.84609375,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.018350427630501032,
399
+ "grad_norm": 0.9296864867210388,
400
+ "learning_rate": 0.000274468085106383,
401
+ "loss": 5.7859375,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.01867811383818855,
406
+ "grad_norm": 0.900589644908905,
407
+ "learning_rate": 0.00027937806873977087,
408
+ "loss": 5.81796875,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.01900580004587607,
413
+ "grad_norm": 0.9115001559257507,
414
+ "learning_rate": 0.00028428805237315876,
415
+ "loss": 5.67421875,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.019333486253563587,
420
+ "grad_norm": 1.119329571723938,
421
+ "learning_rate": 0.00028919803600654665,
422
+ "loss": 5.7671875,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.019661172461251104,
427
+ "grad_norm": 1.1810953617095947,
428
+ "learning_rate": 0.00029410801963993455,
429
+ "loss": 5.7859375,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.019988858668938625,
434
+ "grad_norm": 0.8665738105773926,
435
+ "learning_rate": 0.0002990180032733224,
436
+ "loss": 5.76640625,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.020316544876626142,
441
+ "grad_norm": 1.0014612674713135,
442
+ "learning_rate": 0.00029999994703069194,
443
+ "loss": 5.678125,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.020644231084313663,
448
+ "grad_norm": 0.9615908265113831,
449
+ "learning_rate": 0.0002999997318429423,
450
+ "loss": 5.73046875,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.02097191729200118,
455
+ "grad_norm": 0.9453482627868652,
456
+ "learning_rate": 0.00029999935112640666,
457
+ "loss": 5.690625,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.021299603499688697,
462
+ "grad_norm": 1.2007803916931152,
463
+ "learning_rate": 0.000299998804881505,
464
+ "loss": 5.703125,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.021627289707376218,
469
+ "grad_norm": 1.0227398872375488,
470
+ "learning_rate": 0.00029999809310884013,
471
+ "loss": 5.6203125,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.021954975915063735,
476
+ "grad_norm": 0.7052202820777893,
477
+ "learning_rate": 0.0002999972158091976,
478
+ "loss": 5.63203125,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.022282662122751252,
483
+ "grad_norm": 0.7329296469688416,
484
+ "learning_rate": 0.0002999961729835454,
485
+ "loss": 5.6296875,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.022610348330438772,
490
+ "grad_norm": 1.13410222530365,
491
+ "learning_rate": 0.0002999949646330345,
492
+ "loss": 5.6140625,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.02293803453812629,
497
+ "grad_norm": 1.0296196937561035,
498
+ "learning_rate": 0.0002999935907589982,
499
+ "loss": 5.571875,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.02326572074581381,
504
+ "grad_norm": 0.7488977909088135,
505
+ "learning_rate": 0.00029999205136295275,
506
+ "loss": 5.4640625,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.023593406953501327,
511
+ "grad_norm": 1.1496649980545044,
512
+ "learning_rate": 0.00029999034644659676,
513
+ "loss": 5.64375,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.023921093161188844,
518
+ "grad_norm": 0.7740235924720764,
519
+ "learning_rate": 0.0002999884760118118,
520
+ "loss": 5.571875,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.024248779368876365,
525
+ "grad_norm": 0.9806471467018127,
526
+ "learning_rate": 0.0002999864400606617,
527
+ "loss": 5.52734375,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.024576465576563882,
532
+ "grad_norm": 0.7786164283752441,
533
+ "learning_rate": 0.0002999842385953935,
534
+ "loss": 5.4859375,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.0249041517842514,
539
+ "grad_norm": 0.9503687024116516,
540
+ "learning_rate": 0.0002999818716184364,
541
+ "loss": 5.465625,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.02523183799193892,
546
+ "grad_norm": 1.0149359703063965,
547
+ "learning_rate": 0.0002999793391324024,
548
+ "loss": 5.52890625,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.025559524199626437,
553
+ "grad_norm": 0.7834537029266357,
554
+ "learning_rate": 0.00029997664114008626,
555
+ "loss": 5.46796875,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.025887210407313958,
560
+ "grad_norm": 0.9464772939682007,
561
+ "learning_rate": 0.00029997377764446524,
562
+ "loss": 5.47265625,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.026214896615001475,
567
+ "grad_norm": 0.6793913841247559,
568
+ "learning_rate": 0.00029997074864869923,
569
+ "loss": 5.48828125,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.026542582822688992,
574
+ "grad_norm": 0.7155113816261292,
575
+ "learning_rate": 0.0002999675541561309,
576
+ "loss": 5.50859375,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.026870269030376513,
581
+ "grad_norm": 0.6579717397689819,
582
+ "learning_rate": 0.00029996419417028554,
583
+ "loss": 5.41796875,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.02719795523806403,
588
+ "grad_norm": 0.8174270987510681,
589
+ "learning_rate": 0.00029996066869487074,
590
+ "loss": 5.471875,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.027525641445751547,
595
+ "grad_norm": 0.826265811920166,
596
+ "learning_rate": 0.0002999569777337772,
597
+ "loss": 5.43046875,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.027853327653439067,
602
+ "grad_norm": 0.7678508758544922,
603
+ "learning_rate": 0.00029995312129107776,
604
+ "loss": 5.45703125,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.028181013861126585,
609
+ "grad_norm": 0.7229366898536682,
610
+ "learning_rate": 0.00029994909937102837,
611
+ "loss": 5.3296875,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.028508700068814105,
616
+ "grad_norm": 0.714480459690094,
617
+ "learning_rate": 0.00029994491197806713,
618
+ "loss": 5.42734375,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.028836386276501622,
623
+ "grad_norm": 0.9651358723640442,
624
+ "learning_rate": 0.000299940559116815,
625
+ "loss": 5.4375,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.02916407248418914,
630
+ "grad_norm": 0.7454858422279358,
631
+ "learning_rate": 0.00029993604079207555,
632
+ "loss": 5.4171875,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.02949175869187666,
637
+ "grad_norm": 0.6072654128074646,
638
+ "learning_rate": 0.0002999313570088348,
639
+ "loss": 5.3796875,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.029819444899564177,
644
+ "grad_norm": 0.690458357334137,
645
+ "learning_rate": 0.0002999265077722614,
646
+ "loss": 5.36015625,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.030147131107251694,
651
+ "grad_norm": 0.6867303252220154,
652
+ "learning_rate": 0.0002999214930877067,
653
+ "loss": 5.45859375,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.030474817314939215,
658
+ "grad_norm": 0.7038459181785583,
659
+ "learning_rate": 0.0002999163129607045,
660
+ "loss": 5.35859375,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.030802503522626732,
665
+ "grad_norm": 0.6149375438690186,
666
+ "learning_rate": 0.0002999109673969712,
667
+ "loss": 5.27265625,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.031130189730314253,
672
+ "grad_norm": 0.681347668170929,
673
+ "learning_rate": 0.00029990545640240583,
674
+ "loss": 5.39453125,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.03145787593800177,
679
+ "grad_norm": 0.7548319101333618,
680
+ "learning_rate": 0.00029989977998308984,
681
+ "loss": 5.41171875,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.03178556214568929,
686
+ "grad_norm": 0.7723563313484192,
687
+ "learning_rate": 0.0002998939381452874,
688
+ "loss": 5.31328125,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.032113248353376804,
693
+ "grad_norm": 0.9256216883659363,
694
+ "learning_rate": 0.000299887930895445,
695
+ "loss": 5.3171875,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.032440934561064325,
700
+ "grad_norm": 0.7921758890151978,
701
+ "learning_rate": 0.000299881758240192,
702
+ "loss": 5.3,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.032768620768751845,
707
+ "grad_norm": 0.8458987474441528,
708
+ "learning_rate": 0.00029987542018633994,
709
+ "loss": 5.2859375,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.03309630697643936,
714
+ "grad_norm": 0.7938087582588196,
715
+ "learning_rate": 0.0002998689167408831,
716
+ "loss": 5.31953125,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.03342399318412688,
721
+ "grad_norm": 0.7000190019607544,
722
+ "learning_rate": 0.0002998622479109982,
723
+ "loss": 5.41171875,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.0337516793918144,
728
+ "grad_norm": 0.7116875648498535,
729
+ "learning_rate": 0.0002998554137040444,
730
+ "loss": 5.25,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.034079365599501914,
735
+ "grad_norm": 0.9430018663406372,
736
+ "learning_rate": 0.00029984841412756353,
737
+ "loss": 5.30859375,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.034407051807189434,
742
+ "grad_norm": 1.159864068031311,
743
+ "learning_rate": 0.00029984124918927985,
744
+ "loss": 4.853125,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.034734738014876955,
749
+ "grad_norm": 2.156740188598633,
750
+ "learning_rate": 0.00029983391889709996,
751
+ "loss": 5.425,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.035062424222564476,
756
+ "grad_norm": 1.243762731552124,
757
+ "learning_rate": 0.00029982642325911303,
758
+ "loss": 5.2921875,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.03539011043025199,
763
+ "grad_norm": 0.6277818083763123,
764
+ "learning_rate": 0.00029981876228359083,
765
+ "loss": 5.33359375,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.03571779663793951,
770
+ "grad_norm": 0.9032336473464966,
771
+ "learning_rate": 0.0002998109359789873,
772
+ "loss": 5.2890625,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.03604548284562703,
777
+ "grad_norm": 0.8140321969985962,
778
+ "learning_rate": 0.0002998029443539391,
779
+ "loss": 5.23515625,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.036373169053314544,
784
+ "grad_norm": 0.6642375588417053,
785
+ "learning_rate": 0.00029979478741726516,
786
+ "loss": 5.21484375,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.036700855261002065,
791
+ "grad_norm": 0.6437631249427795,
792
+ "learning_rate": 0.00029978646517796686,
793
+ "loss": 5.2671875,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.037028541468689585,
798
+ "grad_norm": 0.6919775605201721,
799
+ "learning_rate": 0.000299777977645228,
800
+ "loss": 5.234375,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.0373562276763771,
805
+ "grad_norm": 0.5739749670028687,
806
+ "learning_rate": 0.0002997693248284149,
807
+ "loss": 5.19921875,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.03768391388406462,
812
+ "grad_norm": 0.6206057071685791,
813
+ "learning_rate": 0.0002997605067370761,
814
+ "loss": 5.15703125,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.03801160009175214,
819
+ "grad_norm": 0.7688435316085815,
820
+ "learning_rate": 0.0002997515233809426,
821
+ "loss": 5.15390625,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.038339286299439654,
826
+ "grad_norm": 0.666733980178833,
827
+ "learning_rate": 0.0002997423747699278,
828
+ "loss": 5.18203125,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.038666972507127174,
833
+ "grad_norm": 0.5137982964515686,
834
+ "learning_rate": 0.00029973306091412747,
835
+ "loss": 5.16953125,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.038994658714814695,
840
+ "grad_norm": 0.74537193775177,
841
+ "learning_rate": 0.0002997235818238197,
842
+ "loss": 5.196875,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.03932234492250221,
847
+ "grad_norm": 0.665001392364502,
848
+ "learning_rate": 0.0002997139375094648,
849
+ "loss": 5.1890625,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.03965003113018973,
854
+ "grad_norm": 0.625221848487854,
855
+ "learning_rate": 0.0002997041279817057,
856
+ "loss": 5.1265625,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.03997771733787725,
861
+ "grad_norm": 1.1352128982543945,
862
+ "learning_rate": 0.0002996941532513674,
863
+ "loss": 5.1234375,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.04030540354556477,
868
+ "grad_norm": 0.6672996878623962,
869
+ "learning_rate": 0.0002996840133294573,
870
+ "loss": 5.12421875,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.040633089753252284,
875
+ "grad_norm": 0.773441731929779,
876
+ "learning_rate": 0.0002996737082271651,
877
+ "loss": 5.18046875,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.040960775960939805,
882
+ "grad_norm": 0.7460806965827942,
883
+ "learning_rate": 0.00029966323795586273,
884
+ "loss": 5.074609375,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.041288462168627325,
889
+ "grad_norm": 0.7149096727371216,
890
+ "learning_rate": 0.00029965260252710446,
891
+ "loss": 5.165234375,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.04161614837631484,
896
+ "grad_norm": 0.555608332157135,
897
+ "learning_rate": 0.00029964180195262666,
898
+ "loss": 5.18984375,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.04194383458400236,
903
+ "grad_norm": 1.1048178672790527,
904
+ "learning_rate": 0.0002996308362443482,
905
+ "loss": 5.12421875,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.04227152079168988,
910
+ "grad_norm": 0.742000937461853,
911
+ "learning_rate": 0.00029961970541437,
912
+ "loss": 5.21875,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.042599206999377394,
917
+ "grad_norm": 0.6364598274230957,
918
+ "learning_rate": 0.0002996084094749751,
919
+ "loss": 5.1953125,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 0.042926893207064915,
924
+ "grad_norm": 0.6934845447540283,
925
+ "learning_rate": 0.00029959694843862913,
926
+ "loss": 5.28828125,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 0.043254579414752435,
931
+ "grad_norm": 0.6088553071022034,
932
+ "learning_rate": 0.00029958532231797943,
933
+ "loss": 5.0875,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 0.04358226562243995,
938
+ "grad_norm": 0.6441696882247925,
939
+ "learning_rate": 0.0002995735311258559,
940
+ "loss": 5.17890625,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 0.04390995183012747,
945
+ "grad_norm": 0.8299684524536133,
946
+ "learning_rate": 0.00029956157487527027,
947
+ "loss": 5.1515625,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 0.04423763803781499,
952
+ "grad_norm": 0.6226475834846497,
953
+ "learning_rate": 0.0002995494535794168,
954
+ "loss": 5.09921875,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 0.044565324245502504,
959
+ "grad_norm": 0.5452665090560913,
960
+ "learning_rate": 0.00029953716725167144,
961
+ "loss": 5.1046875,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 0.044893010453190024,
966
+ "grad_norm": 0.6435659527778625,
967
+ "learning_rate": 0.00029952471590559263,
968
+ "loss": 5.0609375,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 0.045220696660877545,
973
+ "grad_norm": 0.6248849034309387,
974
+ "learning_rate": 0.00029951209955492083,
975
+ "loss": 5.00546875,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 0.045548382868565065,
980
+ "grad_norm": 0.6792166233062744,
981
+ "learning_rate": 0.00029949931821357837,
982
+ "loss": 5.07890625,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 0.04587606907625258,
987
+ "grad_norm": 0.6581612825393677,
988
+ "learning_rate": 0.00029948637189566987,
989
+ "loss": 5.1359375,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 0.0462037552839401,
994
+ "grad_norm": 0.5826892256736755,
995
+ "learning_rate": 0.00029947326061548196,
996
+ "loss": 5.096875,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 0.04653144149162762,
1001
+ "grad_norm": 0.7383049726486206,
1002
+ "learning_rate": 0.0002994599843874833,
1003
+ "loss": 5.15625,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 0.046859127699315134,
1008
+ "grad_norm": 0.7601944804191589,
1009
+ "learning_rate": 0.0002994465432263245,
1010
+ "loss": 5.17109375,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 0.047186813907002655,
1015
+ "grad_norm": 0.6689663529396057,
1016
+ "learning_rate": 0.0002994329371468384,
1017
+ "loss": 5.04609375,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 0.047514500114690175,
1022
+ "grad_norm": 0.5483173727989197,
1023
+ "learning_rate": 0.0002994191661640395,
1024
+ "loss": 5.04296875,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 0.04784218632237769,
1029
+ "grad_norm": 0.6037015914916992,
1030
+ "learning_rate": 0.00029940523029312456,
1031
+ "loss": 4.9984375,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 0.04816987253006521,
1036
+ "grad_norm": 0.6324152946472168,
1037
+ "learning_rate": 0.00029939112954947215,
1038
+ "loss": 5.08671875,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 0.04849755873775273,
1043
+ "grad_norm": 0.7272245287895203,
1044
+ "learning_rate": 0.00029937686394864284,
1045
+ "loss": 5.03515625,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 0.048825244945440244,
1050
+ "grad_norm": 0.6952782273292542,
1051
+ "learning_rate": 0.00029936243350637913,
1052
+ "loss": 5.06484375,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 0.049152931153127764,
1057
+ "grad_norm": 0.7304527759552002,
1058
+ "learning_rate": 0.00029934783823860536,
1059
+ "loss": 5.0484375,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 0.049480617360815285,
1064
+ "grad_norm": 0.6440735459327698,
1065
+ "learning_rate": 0.00029933307816142784,
1066
+ "loss": 5.0375,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 0.0498083035685028,
1071
+ "grad_norm": 0.7903344035148621,
1072
+ "learning_rate": 0.00029931815329113475,
1073
+ "loss": 5.0296875,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 0.05013598977619032,
1078
+ "grad_norm": 0.6211580634117126,
1079
+ "learning_rate": 0.000299303063644196,
1080
+ "loss": 5.07890625,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 0.05046367598387784,
1085
+ "grad_norm": 0.6022477149963379,
1086
+ "learning_rate": 0.0002992878092372635,
1087
+ "loss": 5.05078125,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 0.05079136219156536,
1092
+ "grad_norm": 0.7670354247093201,
1093
+ "learning_rate": 0.00029927239008717085,
1094
+ "loss": 5.0265625,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 0.051119048399252874,
1099
+ "grad_norm": 0.586107075214386,
1100
+ "learning_rate": 0.0002992568062109335,
1101
+ "loss": 5.02578125,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 0.051446734606940395,
1106
+ "grad_norm": 0.602085530757904,
1107
+ "learning_rate": 0.0002992410576257488,
1108
+ "loss": 5.0546875,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 0.051774420814627915,
1113
+ "grad_norm": 0.5870761275291443,
1114
+ "learning_rate": 0.00029922514434899556,
1115
+ "loss": 5.009375,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 0.05210210702231543,
1120
+ "grad_norm": 0.5971726775169373,
1121
+ "learning_rate": 0.0002992090663982346,
1122
+ "loss": 5.05234375,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 0.05242979323000295,
1127
+ "grad_norm": 0.7121400237083435,
1128
+ "learning_rate": 0.00029919282379120847,
1129
+ "loss": 5.0640625,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 0.05275747943769047,
1134
+ "grad_norm": 0.596053421497345,
1135
+ "learning_rate": 0.0002991764165458412,
1136
+ "loss": 5.01484375,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 0.053085165645377984,
1141
+ "grad_norm": 0.6770414113998413,
1142
+ "learning_rate": 0.0002991598446802387,
1143
+ "loss": 5.08203125,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 0.053412851853065504,
1148
+ "grad_norm": 0.6685618162155151,
1149
+ "learning_rate": 0.0002991431082126884,
1150
+ "loss": 4.920703125,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 0.053740538060753025,
1155
+ "grad_norm": 0.5692399740219116,
1156
+ "learning_rate": 0.00029912620716165955,
1157
+ "loss": 4.98515625,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 0.05406822426844054,
1162
+ "grad_norm": 0.7707079648971558,
1163
+ "learning_rate": 0.0002991091415458028,
1164
+ "loss": 4.965625,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 0.05439591047612806,
1169
+ "grad_norm": 0.7270776033401489,
1170
+ "learning_rate": 0.00029909191138395065,
1171
+ "loss": 5.01796875,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 0.05472359668381558,
1176
+ "grad_norm": 0.6686804890632629,
1177
+ "learning_rate": 0.00029907451669511695,
1178
+ "loss": 4.959375,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 0.055051282891503094,
1183
+ "grad_norm": 0.747658908367157,
1184
+ "learning_rate": 0.0002990569574984973,
1185
+ "loss": 4.953125,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 0.055378969099190614,
1190
+ "grad_norm": 0.6157137751579285,
1191
+ "learning_rate": 0.00029903923381346866,
1192
+ "loss": 5.00546875,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 0.055706655306878135,
1197
+ "grad_norm": 0.6419448256492615,
1198
+ "learning_rate": 0.00029902134565958966,
1199
+ "loss": 4.97421875,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 0.056034341514565655,
1204
+ "grad_norm": 0.5898386240005493,
1205
+ "learning_rate": 0.0002990032930566003,
1206
+ "loss": 4.98828125,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 0.05636202772225317,
1211
+ "grad_norm": 0.6013345122337341,
1212
+ "learning_rate": 0.0002989850760244222,
1213
+ "loss": 4.98515625,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 0.05668971392994069,
1218
+ "grad_norm": 0.5871553421020508,
1219
+ "learning_rate": 0.0002989666945831583,
1220
+ "loss": 4.990625,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 0.05701740013762821,
1225
+ "grad_norm": 0.6453852653503418,
1226
+ "learning_rate": 0.00029894814875309307,
1227
+ "loss": 4.9796875,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 0.057345086345315724,
1232
+ "grad_norm": 0.8662845492362976,
1233
+ "learning_rate": 0.00029892943855469226,
1234
+ "loss": 5.12734375,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 0.057672772553003245,
1239
+ "grad_norm": 0.731332540512085,
1240
+ "learning_rate": 0.00029891056400860316,
1241
+ "loss": 4.9296875,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 0.058000458760690765,
1246
+ "grad_norm": 0.7299115657806396,
1247
+ "learning_rate": 0.00029889152513565433,
1248
+ "loss": 4.97109375,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 0.05832814496837828,
1253
+ "grad_norm": 0.6478477716445923,
1254
+ "learning_rate": 0.00029887232195685565,
1255
+ "loss": 4.8265625,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 0.0586558311760658,
1260
+ "grad_norm": 0.7282979488372803,
1261
+ "learning_rate": 0.0002988529544933984,
1262
+ "loss": 4.97109375,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 0.05898351738375332,
1267
+ "grad_norm": 0.6562245488166809,
1268
+ "learning_rate": 0.000298833422766655,
1269
+ "loss": 4.978125,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 0.059311203591440834,
1274
+ "grad_norm": 0.7543336153030396,
1275
+ "learning_rate": 0.00029881372679817935,
1276
+ "loss": 5.0359375,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 0.059638889799128354,
1281
+ "grad_norm": 0.719120442867279,
1282
+ "learning_rate": 0.0002987938666097064,
1283
+ "loss": 5.06640625,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 0.059966576006815875,
1288
+ "grad_norm": 0.6869373917579651,
1289
+ "learning_rate": 0.00029877384222315256,
1290
+ "loss": 5.01328125,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 0.06029426221450339,
1295
+ "grad_norm": 0.6405544877052307,
1296
+ "learning_rate": 0.0002987536536606151,
1297
+ "loss": 4.9390625,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 0.06062194842219091,
1302
+ "grad_norm": 0.7226877808570862,
1303
+ "learning_rate": 0.00029873330094437275,
1304
+ "loss": 4.9796875,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 0.06094963462987843,
1309
+ "grad_norm": 0.6627829074859619,
1310
+ "learning_rate": 0.00029871278409688526,
1311
+ "loss": 4.8859375,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 0.06127732083756594,
1316
+ "grad_norm": 0.6940677165985107,
1317
+ "learning_rate": 0.0002986921031407936,
1318
+ "loss": 4.9734375,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 0.061605007045253464,
1323
+ "grad_norm": 0.6842754483222961,
1324
+ "learning_rate": 0.00029867125809891965,
1325
+ "loss": 4.9984375,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 0.061932693252940985,
1330
+ "grad_norm": 0.6037126183509827,
1331
+ "learning_rate": 0.0002986502489942665,
1332
+ "loss": 5.08828125,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 0.062260379460628505,
1337
+ "grad_norm": 0.5988043546676636,
1338
+ "learning_rate": 0.0002986290758500184,
1339
+ "loss": 4.96484375,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 0.06258806566831603,
1344
+ "grad_norm": 0.6226351261138916,
1345
+ "learning_rate": 0.00029860773868954036,
1346
+ "loss": 4.9578125,
1347
+ "step": 1910
1348
+ },
1349
+ {
1350
+ "epoch": 0.06291575187600354,
1351
+ "grad_norm": 0.7705016732215881,
1352
+ "learning_rate": 0.0002985862375363785,
1353
+ "loss": 5.03671875,
1354
+ "step": 1920
1355
+ },
1356
+ {
1357
+ "epoch": 0.06324343808369105,
1358
+ "grad_norm": 0.7060153484344482,
1359
+ "learning_rate": 0.00029856457241426006,
1360
+ "loss": 4.91640625,
1361
+ "step": 1930
1362
+ },
1363
+ {
1364
+ "epoch": 0.06357112429137858,
1365
+ "grad_norm": 0.8074666261672974,
1366
+ "learning_rate": 0.000298542743347093,
1367
+ "loss": 4.95625,
1368
+ "step": 1940
1369
+ },
1370
+ {
1371
+ "epoch": 0.0638988104990661,
1372
+ "grad_norm": 0.7484197020530701,
1373
+ "learning_rate": 0.00029852075035896624,
1374
+ "loss": 4.99140625,
1375
+ "step": 1950
1376
+ },
1377
+ {
1378
+ "epoch": 0.06422649670675361,
1379
+ "grad_norm": 0.6902222633361816,
1380
+ "learning_rate": 0.0002984985934741498,
1381
+ "loss": 4.99921875,
1382
+ "step": 1960
1383
+ },
1384
+ {
1385
+ "epoch": 0.06455418291444114,
1386
+ "grad_norm": 0.6182175278663635,
1387
+ "learning_rate": 0.00029847627271709423,
1388
+ "loss": 4.92890625,
1389
+ "step": 1970
1390
+ },
1391
+ {
1392
+ "epoch": 0.06488186912212865,
1393
+ "grad_norm": 0.6556650400161743,
1394
+ "learning_rate": 0.0002984537881124312,
1395
+ "loss": 4.85703125,
1396
+ "step": 1980
1397
+ },
1398
+ {
1399
+ "epoch": 0.06520955532981616,
1400
+ "grad_norm": 0.708215594291687,
1401
+ "learning_rate": 0.00029843113968497305,
1402
+ "loss": 4.9671875,
1403
+ "step": 1990
1404
+ },
1405
+ {
1406
+ "epoch": 0.06553724153750369,
1407
+ "grad_norm": 0.6763514876365662,
1408
+ "learning_rate": 0.00029840832745971294,
1409
+ "loss": 4.873828125,
1410
+ "step": 2000
1411
+ },
1412
+ {
1413
+ "epoch": 0.0658649277451912,
1414
+ "grad_norm": 1.0005897283554077,
1415
+ "learning_rate": 0.0002983853514618248,
1416
+ "loss": 4.9078125,
1417
+ "step": 2010
1418
+ },
1419
+ {
1420
+ "epoch": 0.06619261395287872,
1421
+ "grad_norm": 0.8568900227546692,
1422
+ "learning_rate": 0.0002983622117166632,
1423
+ "loss": 4.9984375,
1424
+ "step": 2020
1425
+ },
1426
+ {
1427
+ "epoch": 0.06652030016056625,
1428
+ "grad_norm": 1.0986026525497437,
1429
+ "learning_rate": 0.0002983389082497635,
1430
+ "loss": 4.98671875,
1431
+ "step": 2030
1432
+ },
1433
+ {
1434
+ "epoch": 0.06684798636825376,
1435
+ "grad_norm": 0.7695608139038086,
1436
+ "learning_rate": 0.00029831544108684186,
1437
+ "loss": 4.865625,
1438
+ "step": 2040
1439
+ },
1440
+ {
1441
+ "epoch": 0.06717567257594127,
1442
+ "grad_norm": 0.6754547357559204,
1443
+ "learning_rate": 0.0002982918102537948,
1444
+ "loss": 4.996875,
1445
+ "step": 2050
1446
+ },
1447
+ {
1448
+ "epoch": 0.0675033587836288,
1449
+ "grad_norm": 0.7993380427360535,
1450
+ "learning_rate": 0.0002982680157766995,
1451
+ "loss": 4.92109375,
1452
+ "step": 2060
1453
+ },
1454
+ {
1455
+ "epoch": 0.06783104499131631,
1456
+ "grad_norm": 0.8771316409111023,
1457
+ "learning_rate": 0.000298244057681814,
1458
+ "loss": 4.86640625,
1459
+ "step": 2070
1460
+ },
1461
+ {
1462
+ "epoch": 0.06815873119900383,
1463
+ "grad_norm": 0.6798153519630432,
1464
+ "learning_rate": 0.0002982199359955766,
1465
+ "loss": 4.95078125,
1466
+ "step": 2080
1467
+ },
1468
+ {
1469
+ "epoch": 0.06848641740669136,
1470
+ "grad_norm": 0.6671808362007141,
1471
+ "learning_rate": 0.0002981956507446062,
1472
+ "loss": 4.90390625,
1473
+ "step": 2090
1474
+ },
1475
+ {
1476
+ "epoch": 0.06881410361437887,
1477
+ "grad_norm": 0.7146123647689819,
1478
+ "learning_rate": 0.0002981712019557024,
1479
+ "loss": 4.90625,
1480
+ "step": 2100
1481
+ },
1482
+ {
1483
+ "epoch": 0.06914178982206638,
1484
+ "grad_norm": 0.7707953453063965,
1485
+ "learning_rate": 0.0002981465896558449,
1486
+ "loss": 4.85703125,
1487
+ "step": 2110
1488
+ },
1489
+ {
1490
+ "epoch": 0.06946947602975391,
1491
+ "grad_norm": 0.8035035133361816,
1492
+ "learning_rate": 0.00029812181387219424,
1493
+ "loss": 4.853125,
1494
+ "step": 2120
1495
+ },
1496
+ {
1497
+ "epoch": 0.06979716223744142,
1498
+ "grad_norm": 0.7028154730796814,
1499
+ "learning_rate": 0.00029809687463209096,
1500
+ "loss": 4.8515625,
1501
+ "step": 2130
1502
+ },
1503
+ {
1504
+ "epoch": 0.07012484844512895,
1505
+ "grad_norm": 0.7226858735084534,
1506
+ "learning_rate": 0.0002980717719630564,
1507
+ "loss": 4.9453125,
1508
+ "step": 2140
1509
+ },
1510
+ {
1511
+ "epoch": 0.07045253465281646,
1512
+ "grad_norm": 0.7521721720695496,
1513
+ "learning_rate": 0.0002980465058927919,
1514
+ "loss": 4.88671875,
1515
+ "step": 2150
1516
+ },
1517
+ {
1518
+ "epoch": 0.07078022086050398,
1519
+ "grad_norm": 0.6852249503135681,
1520
+ "learning_rate": 0.00029802107644917933,
1521
+ "loss": 4.8875,
1522
+ "step": 2160
1523
+ },
1524
+ {
1525
+ "epoch": 0.0711079070681915,
1526
+ "grad_norm": 0.6818333864212036,
1527
+ "learning_rate": 0.00029799548366028067,
1528
+ "loss": 4.96875,
1529
+ "step": 2170
1530
+ },
1531
+ {
1532
+ "epoch": 0.07143559327587902,
1533
+ "grad_norm": 2.0193891525268555,
1534
+ "learning_rate": 0.00029796972755433837,
1535
+ "loss": 4.88828125,
1536
+ "step": 2180
1537
+ },
1538
+ {
1539
+ "epoch": 0.07176327948356653,
1540
+ "grad_norm": 0.7372580766677856,
1541
+ "learning_rate": 0.000297943808159775,
1542
+ "loss": 5.0515625,
1543
+ "step": 2190
1544
+ },
1545
+ {
1546
+ "epoch": 0.07209096569125406,
1547
+ "grad_norm": 1.0684303045272827,
1548
+ "learning_rate": 0.0002979177255051932,
1549
+ "loss": 4.9421875,
1550
+ "step": 2200
1551
+ },
1552
+ {
1553
+ "epoch": 0.07241865189894157,
1554
+ "grad_norm": 0.8580313920974731,
1555
+ "learning_rate": 0.00029789147961937595,
1556
+ "loss": 4.90625,
1557
+ "step": 2210
1558
+ },
1559
+ {
1560
+ "epoch": 0.07274633810662909,
1561
+ "grad_norm": 0.8764984607696533,
1562
+ "learning_rate": 0.0002978650705312864,
1563
+ "loss": 4.86484375,
1564
+ "step": 2220
1565
+ },
1566
+ {
1567
+ "epoch": 0.07307402431431662,
1568
+ "grad_norm": 0.8726807832717896,
1569
+ "learning_rate": 0.00029783849827006754,
1570
+ "loss": 4.821875,
1571
+ "step": 2230
1572
+ },
1573
+ {
1574
+ "epoch": 0.07340171052200413,
1575
+ "grad_norm": 0.7488795518875122,
1576
+ "learning_rate": 0.00029781176286504266,
1577
+ "loss": 4.8453125,
1578
+ "step": 2240
1579
+ },
1580
+ {
1581
+ "epoch": 0.07372939672969164,
1582
+ "grad_norm": 0.7865507006645203,
1583
+ "learning_rate": 0.000297784864345715,
1584
+ "loss": 4.8515625,
1585
+ "step": 2250
1586
+ },
1587
+ {
1588
+ "epoch": 0.07405708293737917,
1589
+ "grad_norm": 1.8572865724563599,
1590
+ "learning_rate": 0.0002977578027417678,
1591
+ "loss": 4.88203125,
1592
+ "step": 2260
1593
+ },
1594
+ {
1595
+ "epoch": 0.07438476914506668,
1596
+ "grad_norm": 0.8269322514533997,
1597
+ "learning_rate": 0.0002977305780830643,
1598
+ "loss": 4.784375,
1599
+ "step": 2270
1600
+ },
1601
+ {
1602
+ "epoch": 0.0747124553527542,
1603
+ "grad_norm": 0.8239268660545349,
1604
+ "learning_rate": 0.0002977031903996476,
1605
+ "loss": 4.88203125,
1606
+ "step": 2280
1607
+ },
1608
+ {
1609
+ "epoch": 0.07504014156044173,
1610
+ "grad_norm": 0.7805508375167847,
1611
+ "learning_rate": 0.00029767563972174087,
1612
+ "loss": 4.719921875,
1613
+ "step": 2290
1614
+ },
1615
+ {
1616
+ "epoch": 0.07536782776812924,
1617
+ "grad_norm": 0.7358950972557068,
1618
+ "learning_rate": 0.00029764792607974686,
1619
+ "loss": 4.9,
1620
+ "step": 2300
1621
+ },
1622
+ {
1623
+ "epoch": 0.07569551397581675,
1624
+ "grad_norm": 1.00836980342865,
1625
+ "learning_rate": 0.0002976200495042484,
1626
+ "loss": 4.83125,
1627
+ "step": 2310
1628
+ },
1629
+ {
1630
+ "epoch": 0.07602320018350428,
1631
+ "grad_norm": 0.8957743644714355,
1632
+ "learning_rate": 0.00029759201002600813,
1633
+ "loss": 4.86875,
1634
+ "step": 2320
1635
+ },
1636
+ {
1637
+ "epoch": 0.0763508863911918,
1638
+ "grad_norm": 0.8436468839645386,
1639
+ "learning_rate": 0.0002975638076759683,
1640
+ "loss": 4.8734375,
1641
+ "step": 2330
1642
+ },
1643
+ {
1644
+ "epoch": 0.07667857259887931,
1645
+ "grad_norm": 0.7431784272193909,
1646
+ "learning_rate": 0.000297535442485251,
1647
+ "loss": 4.85234375,
1648
+ "step": 2340
1649
+ },
1650
+ {
1651
+ "epoch": 0.07700625880656684,
1652
+ "grad_norm": 0.8118292689323425,
1653
+ "learning_rate": 0.00029750691448515796,
1654
+ "loss": 4.8375,
1655
+ "step": 2350
1656
+ },
1657
+ {
1658
+ "epoch": 0.07733394501425435,
1659
+ "grad_norm": 0.7904531955718994,
1660
+ "learning_rate": 0.0002974782237071706,
1661
+ "loss": 4.88515625,
1662
+ "step": 2360
1663
+ },
1664
+ {
1665
+ "epoch": 0.07766163122194186,
1666
+ "grad_norm": 0.8368480205535889,
1667
+ "learning_rate": 0.00029744937018295,
1668
+ "loss": 4.77890625,
1669
+ "step": 2370
1670
+ },
1671
+ {
1672
+ "epoch": 0.07798931742962939,
1673
+ "grad_norm": 0.7238487601280212,
1674
+ "learning_rate": 0.00029742035394433685,
1675
+ "loss": 4.86484375,
1676
+ "step": 2380
1677
+ },
1678
+ {
1679
+ "epoch": 0.0783170036373169,
1680
+ "grad_norm": 0.7777819633483887,
1681
+ "learning_rate": 0.00029739117502335127,
1682
+ "loss": 4.81796875,
1683
+ "step": 2390
1684
+ },
1685
+ {
1686
+ "epoch": 0.07864468984500442,
1687
+ "grad_norm": 1.076075792312622,
1688
+ "learning_rate": 0.00029736183345219306,
1689
+ "loss": 4.92421875,
1690
+ "step": 2400
1691
+ },
1692
+ {
1693
+ "epoch": 0.07897237605269194,
1694
+ "grad_norm": 0.7192528247833252,
1695
+ "learning_rate": 0.00029733232926324143,
1696
+ "loss": 4.903125,
1697
+ "step": 2410
1698
+ },
1699
+ {
1700
+ "epoch": 0.07930006226037946,
1701
+ "grad_norm": 0.8702367544174194,
1702
+ "learning_rate": 0.000297302662489055,
1703
+ "loss": 4.8453125,
1704
+ "step": 2420
1705
+ },
1706
+ {
1707
+ "epoch": 0.07962774846806697,
1708
+ "grad_norm": 0.6946535706520081,
1709
+ "learning_rate": 0.0002972728331623719,
1710
+ "loss": 4.91953125,
1711
+ "step": 2430
1712
+ },
1713
+ {
1714
+ "epoch": 0.0799554346757545,
1715
+ "grad_norm": 1.0389535427093506,
1716
+ "learning_rate": 0.0002972428413161097,
1717
+ "loss": 4.77890625,
1718
+ "step": 2440
1719
+ },
1720
+ {
1721
+ "epoch": 0.08028312088344201,
1722
+ "grad_norm": 0.8404636383056641,
1723
+ "learning_rate": 0.00029721268698336504,
1724
+ "loss": 4.8625,
1725
+ "step": 2450
1726
+ },
1727
+ {
1728
+ "epoch": 0.08061080709112954,
1729
+ "grad_norm": 0.8492134213447571,
1730
+ "learning_rate": 0.0002971823701974142,
1731
+ "loss": 4.76484375,
1732
+ "step": 2460
1733
+ },
1734
+ {
1735
+ "epoch": 0.08093849329881705,
1736
+ "grad_norm": 1.1323004961013794,
1737
+ "learning_rate": 0.0002971518909917124,
1738
+ "loss": 4.809375,
1739
+ "step": 2470
1740
+ },
1741
+ {
1742
+ "epoch": 0.08126617950650457,
1743
+ "grad_norm": 0.8315953016281128,
1744
+ "learning_rate": 0.00029712124939989447,
1745
+ "loss": 4.855078125,
1746
+ "step": 2480
1747
+ },
1748
+ {
1749
+ "epoch": 0.0815938657141921,
1750
+ "grad_norm": 0.8824076056480408,
1751
+ "learning_rate": 0.00029709044545577417,
1752
+ "loss": 4.83359375,
1753
+ "step": 2490
1754
+ },
1755
+ {
1756
+ "epoch": 0.08192155192187961,
1757
+ "grad_norm": 0.9721917510032654,
1758
+ "learning_rate": 0.0002970594791933444,
1759
+ "loss": 4.778125,
1760
+ "step": 2500
1761
+ },
1762
+ {
1763
+ "epoch": 0.08224923812956712,
1764
+ "grad_norm": 0.7818214893341064,
1765
+ "learning_rate": 0.0002970283506467774,
1766
+ "loss": 4.846875,
1767
+ "step": 2510
1768
+ },
1769
+ {
1770
+ "epoch": 0.08257692433725465,
1771
+ "grad_norm": 0.8877561092376709,
1772
+ "learning_rate": 0.0002969970598504244,
1773
+ "loss": 4.85234375,
1774
+ "step": 2520
1775
+ },
1776
+ {
1777
+ "epoch": 0.08290461054494216,
1778
+ "grad_norm": 0.8331444263458252,
1779
+ "learning_rate": 0.00029696560683881547,
1780
+ "loss": 4.9421875,
1781
+ "step": 2530
1782
+ },
1783
+ {
1784
+ "epoch": 0.08323229675262968,
1785
+ "grad_norm": 0.7759410738945007,
1786
+ "learning_rate": 0.00029693399164665995,
1787
+ "loss": 4.77265625,
1788
+ "step": 2540
1789
+ },
1790
+ {
1791
+ "epoch": 0.0835599829603172,
1792
+ "grad_norm": 0.9405922293663025,
1793
+ "learning_rate": 0.00029690221430884615,
1794
+ "loss": 4.8171875,
1795
+ "step": 2550
1796
+ },
1797
+ {
1798
+ "epoch": 0.08388766916800472,
1799
+ "grad_norm": 0.8609956502914429,
1800
+ "learning_rate": 0.00029687027486044107,
1801
+ "loss": 4.81484375,
1802
+ "step": 2560
1803
+ },
1804
+ {
1805
+ "epoch": 0.08421535537569223,
1806
+ "grad_norm": 0.9754828214645386,
1807
+ "learning_rate": 0.0002968381733366908,
1808
+ "loss": 4.78125,
1809
+ "step": 2570
1810
+ },
1811
+ {
1812
+ "epoch": 0.08454304158337976,
1813
+ "grad_norm": 1.0310945510864258,
1814
+ "learning_rate": 0.0002968059097730204,
1815
+ "loss": 4.796875,
1816
+ "step": 2580
1817
+ },
1818
+ {
1819
+ "epoch": 0.08487072779106727,
1820
+ "grad_norm": 1.1128381490707397,
1821
+ "learning_rate": 0.0002967734842050335,
1822
+ "loss": 4.928125,
1823
+ "step": 2590
1824
+ },
1825
+ {
1826
+ "epoch": 0.08519841399875479,
1827
+ "grad_norm": 0.9402220845222473,
1828
+ "learning_rate": 0.0002967408966685125,
1829
+ "loss": 5.01875,
1830
+ "step": 2600
1831
+ },
1832
+ {
1833
+ "epoch": 0.08552610020644232,
1834
+ "grad_norm": 0.9044272899627686,
1835
+ "learning_rate": 0.0002967081471994187,
1836
+ "loss": 4.80859375,
1837
+ "step": 2610
1838
+ },
1839
+ {
1840
+ "epoch": 0.08585378641412983,
1841
+ "grad_norm": 0.9822449088096619,
1842
+ "learning_rate": 0.00029667523583389206,
1843
+ "loss": 4.76875,
1844
+ "step": 2620
1845
+ },
1846
+ {
1847
+ "epoch": 0.08618147262181734,
1848
+ "grad_norm": 0.9555259943008423,
1849
+ "learning_rate": 0.00029664216260825115,
1850
+ "loss": 4.8484375,
1851
+ "step": 2630
1852
+ },
1853
+ {
1854
+ "epoch": 0.08650915882950487,
1855
+ "grad_norm": 0.9148328304290771,
1856
+ "learning_rate": 0.00029660892755899317,
1857
+ "loss": 4.77890625,
1858
+ "step": 2640
1859
+ },
1860
+ {
1861
+ "epoch": 0.08683684503719238,
1862
+ "grad_norm": 1.045342206954956,
1863
+ "learning_rate": 0.0002965755307227938,
1864
+ "loss": 4.81796875,
1865
+ "step": 2650
1866
+ },
1867
+ {
1868
+ "epoch": 0.0871645312448799,
1869
+ "grad_norm": 1.055479645729065,
1870
+ "learning_rate": 0.00029654197213650757,
1871
+ "loss": 4.809375,
1872
+ "step": 2660
1873
+ },
1874
+ {
1875
+ "epoch": 0.08749221745256743,
1876
+ "grad_norm": 0.7820264101028442,
1877
+ "learning_rate": 0.0002965082518371672,
1878
+ "loss": 4.8265625,
1879
+ "step": 2670
1880
+ },
1881
+ {
1882
+ "epoch": 0.08781990366025494,
1883
+ "grad_norm": 1.0174428224563599,
1884
+ "learning_rate": 0.0002964743698619839,
1885
+ "loss": 4.85390625,
1886
+ "step": 2680
1887
+ },
1888
+ {
1889
+ "epoch": 0.08814758986794245,
1890
+ "grad_norm": 1.0016568899154663,
1891
+ "learning_rate": 0.0002964403262483474,
1892
+ "loss": 4.81328125,
1893
+ "step": 2690
1894
+ },
1895
+ {
1896
+ "epoch": 0.08847527607562998,
1897
+ "grad_norm": 1.1866505146026611,
1898
+ "learning_rate": 0.0002964061210338257,
1899
+ "loss": 4.84609375,
1900
+ "step": 2700
1901
+ },
1902
+ {
1903
+ "epoch": 0.0888029622833175,
1904
+ "grad_norm": 0.9405037760734558,
1905
+ "learning_rate": 0.00029637175425616526,
1906
+ "loss": 4.8203125,
1907
+ "step": 2710
1908
+ },
1909
+ {
1910
+ "epoch": 0.08913064849100501,
1911
+ "grad_norm": 0.9117628931999207,
1912
+ "learning_rate": 0.0002963372259532907,
1913
+ "loss": 4.79375,
1914
+ "step": 2720
1915
+ },
1916
+ {
1917
+ "epoch": 0.08945833469869253,
1918
+ "grad_norm": 1.3953324556350708,
1919
+ "learning_rate": 0.000296302536163305,
1920
+ "loss": 4.7890625,
1921
+ "step": 2730
1922
+ },
1923
+ {
1924
+ "epoch": 0.08978602090638005,
1925
+ "grad_norm": 0.9645633697509766,
1926
+ "learning_rate": 0.00029626768492448926,
1927
+ "loss": 4.73359375,
1928
+ "step": 2740
1929
+ },
1930
+ {
1931
+ "epoch": 0.09011370711406756,
1932
+ "grad_norm": 1.0412721633911133,
1933
+ "learning_rate": 0.00029623267227530276,
1934
+ "loss": 4.7328125,
1935
+ "step": 2750
1936
+ },
1937
+ {
1938
+ "epoch": 0.09044139332175509,
1939
+ "grad_norm": 1.2440223693847656,
1940
+ "learning_rate": 0.0002961974982543829,
1941
+ "loss": 4.82421875,
1942
+ "step": 2760
1943
+ },
1944
+ {
1945
+ "epoch": 0.0907690795294426,
1946
+ "grad_norm": 0.8880364298820496,
1947
+ "learning_rate": 0.0002961621629005452,
1948
+ "loss": 4.739453125,
1949
+ "step": 2770
1950
+ },
1951
+ {
1952
+ "epoch": 0.09109676573713013,
1953
+ "grad_norm": 1.0993216037750244,
1954
+ "learning_rate": 0.00029612666625278316,
1955
+ "loss": 4.7875,
1956
+ "step": 2780
1957
+ },
1958
+ {
1959
+ "epoch": 0.09142445194481764,
1960
+ "grad_norm": 1.0973334312438965,
1961
+ "learning_rate": 0.00029609100835026835,
1962
+ "loss": 4.84453125,
1963
+ "step": 2790
1964
+ },
1965
+ {
1966
+ "epoch": 0.09175213815250516,
1967
+ "grad_norm": 1.1454707384109497,
1968
+ "learning_rate": 0.0002960551892323501,
1969
+ "loss": 4.74453125,
1970
+ "step": 2800
1971
+ },
1972
+ {
1973
+ "epoch": 0.09207982436019269,
1974
+ "grad_norm": 0.8968997001647949,
1975
+ "learning_rate": 0.0002960192089385559,
1976
+ "loss": 4.8453125,
1977
+ "step": 2810
1978
+ },
1979
+ {
1980
+ "epoch": 0.0924075105678802,
1981
+ "grad_norm": 1.5437283515930176,
1982
+ "learning_rate": 0.00029598306750859105,
1983
+ "loss": 4.77109375,
1984
+ "step": 2820
1985
+ },
1986
+ {
1987
+ "epoch": 0.09273519677556771,
1988
+ "grad_norm": 0.9663252234458923,
1989
+ "learning_rate": 0.0002959467649823384,
1990
+ "loss": 4.803125,
1991
+ "step": 2830
1992
+ },
1993
+ {
1994
+ "epoch": 0.09306288298325524,
1995
+ "grad_norm": 0.9821021556854248,
1996
+ "learning_rate": 0.0002959103013998589,
1997
+ "loss": 4.7421875,
1998
+ "step": 2840
1999
+ },
2000
+ {
2001
+ "epoch": 0.09339056919094275,
2002
+ "grad_norm": 0.9745010137557983,
2003
+ "learning_rate": 0.0002958736768013911,
2004
+ "loss": 4.80234375,
2005
+ "step": 2850
2006
+ },
2007
+ {
2008
+ "epoch": 0.09371825539863027,
2009
+ "grad_norm": 0.9119879007339478,
2010
+ "learning_rate": 0.00029583689122735125,
2011
+ "loss": 4.79140625,
2012
+ "step": 2860
2013
+ },
2014
+ {
2015
+ "epoch": 0.0940459416063178,
2016
+ "grad_norm": 0.8870778679847717,
2017
+ "learning_rate": 0.0002957999447183332,
2018
+ "loss": 4.775,
2019
+ "step": 2870
2020
+ },
2021
+ {
2022
+ "epoch": 0.09437362781400531,
2023
+ "grad_norm": 1.048074722290039,
2024
+ "learning_rate": 0.00029576283731510845,
2025
+ "loss": 4.77265625,
2026
+ "step": 2880
2027
+ },
2028
+ {
2029
+ "epoch": 0.09470131402169282,
2030
+ "grad_norm": 0.966056227684021,
2031
+ "learning_rate": 0.00029572556905862606,
2032
+ "loss": 4.94765625,
2033
+ "step": 2890
2034
+ },
2035
+ {
2036
+ "epoch": 0.09502900022938035,
2037
+ "grad_norm": 1.296233057975769,
2038
+ "learning_rate": 0.0002956881399900124,
2039
+ "loss": 4.81328125,
2040
+ "step": 2900
2041
+ },
2042
+ {
2043
+ "epoch": 0.09535668643706786,
2044
+ "grad_norm": 1.2167632579803467,
2045
+ "learning_rate": 0.0002956505501505717,
2046
+ "loss": 4.71015625,
2047
+ "step": 2910
2048
+ },
2049
+ {
2050
+ "epoch": 0.09568437264475538,
2051
+ "grad_norm": 0.9469176530838013,
2052
+ "learning_rate": 0.0002956127995817853,
2053
+ "loss": 4.79453125,
2054
+ "step": 2920
2055
+ },
2056
+ {
2057
+ "epoch": 0.0960120588524429,
2058
+ "grad_norm": 1.1666737794876099,
2059
+ "learning_rate": 0.0002955748883253118,
2060
+ "loss": 4.728125,
2061
+ "step": 2930
2062
+ },
2063
+ {
2064
+ "epoch": 0.09633974506013042,
2065
+ "grad_norm": 0.8718119859695435,
2066
+ "learning_rate": 0.00029553681642298754,
2067
+ "loss": 4.68515625,
2068
+ "step": 2940
2069
+ },
2070
+ {
2071
+ "epoch": 0.09666743126781793,
2072
+ "grad_norm": 0.9728034734725952,
2073
+ "learning_rate": 0.00029549858391682575,
2074
+ "loss": 4.7328125,
2075
+ "step": 2950
2076
+ },
2077
+ {
2078
+ "epoch": 0.09699511747550546,
2079
+ "grad_norm": 0.9123638272285461,
2080
+ "learning_rate": 0.00029546019084901714,
2081
+ "loss": 4.725,
2082
+ "step": 2960
2083
+ },
2084
+ {
2085
+ "epoch": 0.09732280368319297,
2086
+ "grad_norm": 1.2971138954162598,
2087
+ "learning_rate": 0.00029542163726192945,
2088
+ "loss": 4.733984375,
2089
+ "step": 2970
2090
+ },
2091
+ {
2092
+ "epoch": 0.09765048989088049,
2093
+ "grad_norm": 0.889515221118927,
2094
+ "learning_rate": 0.0002953829231981076,
2095
+ "loss": 4.7703125,
2096
+ "step": 2980
2097
+ },
2098
+ {
2099
+ "epoch": 0.09797817609856802,
2100
+ "grad_norm": 1.6193628311157227,
2101
+ "learning_rate": 0.00029534404870027364,
2102
+ "loss": 4.78359375,
2103
+ "step": 2990
2104
+ },
2105
+ {
2106
+ "epoch": 0.09830586230625553,
2107
+ "grad_norm": 0.9275179505348206,
2108
+ "learning_rate": 0.0002953050138113267,
2109
+ "loss": 4.73828125,
2110
+ "step": 3000
2111
+ },
2112
+ {
2113
+ "epoch": 0.09863354851394304,
2114
+ "grad_norm": 1.0541638135910034,
2115
+ "learning_rate": 0.0002952658185743427,
2116
+ "loss": 4.67421875,
2117
+ "step": 3010
2118
+ },
2119
+ {
2120
+ "epoch": 0.09896123472163057,
2121
+ "grad_norm": 0.8868362307548523,
2122
+ "learning_rate": 0.00029522646303257473,
2123
+ "loss": 4.70703125,
2124
+ "step": 3020
2125
+ },
2126
+ {
2127
+ "epoch": 0.09928892092931808,
2128
+ "grad_norm": 1.4845198392868042,
2129
+ "learning_rate": 0.0002951869472294527,
2130
+ "loss": 4.74765625,
2131
+ "step": 3030
2132
+ },
2133
+ {
2134
+ "epoch": 0.0996166071370056,
2135
+ "grad_norm": 0.9316787719726562,
2136
+ "learning_rate": 0.0002951472712085834,
2137
+ "loss": 4.68984375,
2138
+ "step": 3040
2139
+ },
2140
+ {
2141
+ "epoch": 0.09994429334469312,
2142
+ "grad_norm": 0.9629783630371094,
2143
+ "learning_rate": 0.00029510743501375036,
2144
+ "loss": 4.69453125,
2145
+ "step": 3050
2146
+ }
2147
+ ],
2148
+ "logging_steps": 10,
2149
+ "max_steps": 30517,
2150
+ "num_input_tokens_seen": 0,
2151
+ "num_train_epochs": 9223372036854775807,
2152
+ "save_steps": 3051,
2153
+ "stateful_callbacks": {
2154
+ "TrainerControl": {
2155
+ "args": {
2156
+ "should_epoch_stop": false,
2157
+ "should_evaluate": false,
2158
+ "should_log": false,
2159
+ "should_save": true,
2160
+ "should_training_stop": false
2161
+ },
2162
+ "attributes": {}
2163
+ }
2164
+ },
2165
+ "total_flos": 4.241317913539117e+18,
2166
+ "train_batch_size": 16,
2167
+ "trial_name": null,
2168
+ "trial_params": null
2169
+ }
qwen2.5-7b_c4_1B/s43_std/checkpoint-30510/bf16.log ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ bf16 /root/traj/s3_1B/s43_std/checkpoint-30510/model.safetensors 7615616512
2
+ DONE
qwen2.5-7b_c4_1B/s43_std/checkpoint-30510/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "float32",
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention"
42
+ ],
43
+ "max_position_embeddings": 131072,
44
+ "max_window_layers": 28,
45
+ "model_type": "qwen2",
46
+ "num_attention_heads": 28,
47
+ "num_hidden_layers": 28,
48
+ "num_key_value_heads": 4,
49
+ "pad_token_id": null,
50
+ "rms_norm_eps": 1e-06,
51
+ "rope_parameters": {
52
+ "rope_theta": 1000000.0,
53
+ "rope_type": "default"
54
+ },
55
+ "sliding_window": null,
56
+ "tie_word_embeddings": false,
57
+ "transformers_version": "5.22.1",
58
+ "use_cache": false,
59
+ "use_mrope": false,
60
+ "use_sliding_window": false,
61
+ "vocab_size": 152064
62
+ }
qwen2.5-7b_c4_1B/s43_std/checkpoint-30510/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151643,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.22.1",
8
+ "use_cache": true
9
+ }
qwen2.5-7b_c4_1B/s43_std/checkpoint-30510/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c84a3e1ca9de5eaa4f0462f36d918a853aeedface2964944fc3788e266b872d4
3
+ size 15231272152
qwen2.5-7b_c4_1B/s43_std/checkpoint-30510/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5-7b_c4_1B/s43_std/checkpoint-30517/bf16.log ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ bf16 /root/traj/s3_1B/s43_std/checkpoint-30517/model.safetensors 7615616512
2
+ DONE
qwen2.5-7b_c4_1B/s43_std/checkpoint-30517/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "float32",
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention"
42
+ ],
43
+ "max_position_embeddings": 131072,
44
+ "max_window_layers": 28,
45
+ "model_type": "qwen2",
46
+ "num_attention_heads": 28,
47
+ "num_hidden_layers": 28,
48
+ "num_key_value_heads": 4,
49
+ "pad_token_id": null,
50
+ "rms_norm_eps": 1e-06,
51
+ "rope_parameters": {
52
+ "rope_theta": 1000000.0,
53
+ "rope_type": "default"
54
+ },
55
+ "sliding_window": null,
56
+ "tie_word_embeddings": false,
57
+ "transformers_version": "5.22.1",
58
+ "use_cache": false,
59
+ "use_mrope": false,
60
+ "use_sliding_window": false,
61
+ "vocab_size": 152064
62
+ }
qwen2.5-7b_c4_1B/s43_std/checkpoint-30517/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151643,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.22.1",
8
+ "use_cache": true
9
+ }
qwen2.5-7b_c4_1B/s43_std/checkpoint-30517/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1adfb9fd8c0f16af41ce139b090558ef999c1dd80cbe0ca03fc92d16f7154ec
3
+ size 15231272152
qwen2.5-7b_c4_1B/s43_std/checkpoint-30517/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5-7b_c4_1B/s43_std/checkpoint-6102/bf16.log ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ bf16 /root/traj/s3_1B/s43_std/checkpoint-6102/model.safetensors 7615616512
2
+ DONE
qwen2.5-7b_c4_1B/s43_std/checkpoint-6102/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "float32",
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention"
42
+ ],
43
+ "max_position_embeddings": 131072,
44
+ "max_window_layers": 28,
45
+ "model_type": "qwen2",
46
+ "num_attention_heads": 28,
47
+ "num_hidden_layers": 28,
48
+ "num_key_value_heads": 4,
49
+ "pad_token_id": null,
50
+ "rms_norm_eps": 1e-06,
51
+ "rope_parameters": {
52
+ "rope_theta": 1000000.0,
53
+ "rope_type": "default"
54
+ },
55
+ "sliding_window": null,
56
+ "tie_word_embeddings": false,
57
+ "transformers_version": "5.22.1",
58
+ "use_cache": false,
59
+ "use_mrope": false,
60
+ "use_sliding_window": false,
61
+ "vocab_size": 152064
62
+ }
qwen2.5-7b_c4_1B/s43_std/checkpoint-6102/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151643,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.22.1",
8
+ "use_cache": true
9
+ }
qwen2.5-7b_c4_1B/s43_std/checkpoint-6102/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6170bc0ac852450ece2ce7a7ff444aea5307ded923f11f6cc19ac035be95ebcb
3
+ size 15231272152
qwen2.5-7b_c4_1B/s43_std/checkpoint-6102/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5-7b_c4_1B/s43_std/checkpoint-9153/bf16.log ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ bf16 /root/traj/s3_1B/s43_std/checkpoint-9153/model.safetensors 7615616512
2
+ DONE
qwen2.5-7b_c4_1B/s43_std/checkpoint-9153/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "float32",
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention"
42
+ ],
43
+ "max_position_embeddings": 131072,
44
+ "max_window_layers": 28,
45
+ "model_type": "qwen2",
46
+ "num_attention_heads": 28,
47
+ "num_hidden_layers": 28,
48
+ "num_key_value_heads": 4,
49
+ "pad_token_id": null,
50
+ "rms_norm_eps": 1e-06,
51
+ "rope_parameters": {
52
+ "rope_theta": 1000000.0,
53
+ "rope_type": "default"
54
+ },
55
+ "sliding_window": null,
56
+ "tie_word_embeddings": false,
57
+ "transformers_version": "5.22.1",
58
+ "use_cache": false,
59
+ "use_mrope": false,
60
+ "use_sliding_window": false,
61
+ "vocab_size": 152064
62
+ }
qwen2.5-7b_c4_1B/s43_std/checkpoint-9153/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151643,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.22.1",
8
+ "use_cache": true
9
+ }
qwen2.5-7b_c4_1B/s43_std/checkpoint-9153/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d9fbd8ef840725ffd4f524c68962ff60537092db30e0596b20f01705abb915
3
+ size 15231272152
qwen2.5-7b_c4_1B/s43_std/checkpoint-9153/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff