Hugging Face's logo

SeragAmin
/
sib-models

Safetensors
Model card Files
xet
Community
SeragAmin commited on
Commit
e7ddc6d
·
verified ·
1 Parent(s): 26f64c6

Upload folder using huggingface_hub

Browse files
Files changed (28) hide show
  1. sib200_random_distil/best/config.json +72 -0
  2. sib200_random_distil/best/generation_config.json +13 -0
  3. sib200_random_distil/best/model.safetensors +3 -0
  4. sib200_random_distil/best/training_args.bin +3 -0
  5. sib200_random_distil/checkpoint-1317/config.json +72 -0
  6. sib200_random_distil/checkpoint-1317/generation_config.json +13 -0
  7. sib200_random_distil/checkpoint-1317/model.safetensors +3 -0
  8. sib200_random_distil/checkpoint-1317/optimizer.pt +3 -0
  9. sib200_random_distil/checkpoint-1317/rng_state.pth +3 -0
  10. sib200_random_distil/checkpoint-1317/scheduler.pt +3 -0
  11. sib200_random_distil/checkpoint-1317/trainer_state.json +48 -0
  12. sib200_random_distil/checkpoint-1317/training_args.bin +3 -0
  13. sib200_random_distil/checkpoint-439/config.json +72 -0
  14. sib200_random_distil/checkpoint-439/generation_config.json +13 -0
  15. sib200_random_distil/checkpoint-439/model.safetensors +3 -0
  16. sib200_random_distil/checkpoint-439/optimizer.pt +3 -0
  17. sib200_random_distil/checkpoint-439/rng_state.pth +3 -0
  18. sib200_random_distil/checkpoint-439/scheduler.pt +3 -0
  19. sib200_random_distil/checkpoint-439/trainer_state.json +33 -0
  20. sib200_random_distil/checkpoint-439/training_args.bin +3 -0
  21. sib200_random_distil/checkpoint-878/config.json +72 -0
  22. sib200_random_distil/checkpoint-878/generation_config.json +13 -0
  23. sib200_random_distil/checkpoint-878/model.safetensors +3 -0
  24. sib200_random_distil/checkpoint-878/optimizer.pt +3 -0
  25. sib200_random_distil/checkpoint-878/rng_state.pth +3 -0
  26. sib200_random_distil/checkpoint-878/scheduler.pt +3 -0
  27. sib200_random_distil/checkpoint-878/trainer_state.json +41 -0
  28. sib200_random_distil/checkpoint-878/training_args.bin +3 -0
sib200_random_distil/best/config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_sliding_window_pattern": 6,
3
+ "architectures": [
4
+ "Gemma3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": null,
9
+ "bos_token_id": 2,
10
+ "cache_implementation": "hybrid",
11
+ "dtype": "bfloat16",
12
+ "eos_token_id": 1,
13
+ "final_logit_softcapping": null,
14
+ "head_dim": 256,
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 1152,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 6912,
19
+ "layer_types": [
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "sliding_attention",
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "sliding_attention"
46
+ ],
47
+ "max_position_embeddings": 32768,
48
+ "model_type": "gemma3_text",
49
+ "num_attention_heads": 4,
50
+ "num_hidden_layers": 26,
51
+ "num_key_value_heads": 1,
52
+ "pad_token_id": 0,
53
+ "query_pre_attn_scalar": 256,
54
+ "rms_norm_eps": 1e-06,
55
+ "rope_parameters": {
56
+ "full_attention": {
57
+ "rope_theta": 1000000,
58
+ "rope_type": "default"
59
+ },
60
+ "sliding_attention": {
61
+ "rope_theta": 10000,
62
+ "rope_type": "default"
63
+ }
64
+ },
65
+ "sliding_window": 512,
66
+ "sliding_window_pattern": 6,
67
+ "tie_word_embeddings": true,
68
+ "transformers_version": "5.0.0",
69
+ "use_bidirectional_attention": false,
70
+ "use_cache": false,
71
+ "vocab_size": 262144
72
+ }
sib200_random_distil/best/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
+ "pad_token_id": 0,
10
+ "top_k": 64,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.0.0"
13
+ }
sib200_random_distil/best/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed7d28dae9dbf7e7d05b49c09586d41c7fecdc57d9b2befcb66ad28f32972c06
3
+ size 1999811208
sib200_random_distil/best/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5937e813a601057d9c30bb4ad64ea0a5b1fb0d54a92e6c7a66b80c4e96bc7e1f
3
+ size 4728
sib200_random_distil/checkpoint-1317/config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_sliding_window_pattern": 6,
3
+ "architectures": [
4
+ "Gemma3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": null,
9
+ "bos_token_id": 2,
10
+ "cache_implementation": "hybrid",
11
+ "dtype": "bfloat16",
12
+ "eos_token_id": 1,
13
+ "final_logit_softcapping": null,
14
+ "head_dim": 256,
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 1152,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 6912,
19
+ "layer_types": [
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "sliding_attention",
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "sliding_attention"
46
+ ],
47
+ "max_position_embeddings": 32768,
48
+ "model_type": "gemma3_text",
49
+ "num_attention_heads": 4,
50
+ "num_hidden_layers": 26,
51
+ "num_key_value_heads": 1,
52
+ "pad_token_id": 0,
53
+ "query_pre_attn_scalar": 256,
54
+ "rms_norm_eps": 1e-06,
55
+ "rope_parameters": {
56
+ "full_attention": {
57
+ "rope_theta": 1000000,
58
+ "rope_type": "default"
59
+ },
60
+ "sliding_attention": {
61
+ "rope_theta": 10000,
62
+ "rope_type": "default"
63
+ }
64
+ },
65
+ "sliding_window": 512,
66
+ "sliding_window_pattern": 6,
67
+ "tie_word_embeddings": true,
68
+ "transformers_version": "5.0.0",
69
+ "use_bidirectional_attention": false,
70
+ "use_cache": false,
71
+ "vocab_size": 262144
72
+ }
sib200_random_distil/checkpoint-1317/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
+ "pad_token_id": 0,
10
+ "top_k": 64,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.0.0"
13
+ }
sib200_random_distil/checkpoint-1317/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed7d28dae9dbf7e7d05b49c09586d41c7fecdc57d9b2befcb66ad28f32972c06
3
+ size 1999811208
sib200_random_distil/checkpoint-1317/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb5bb575ffc6654ca30ff743dd99290175a01786ce8735429883685738e883bb
3
+ size 3999829006
sib200_random_distil/checkpoint-1317/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
3
+ size 14244
sib200_random_distil/checkpoint-1317/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a5fdd8a4950f27ad62ea5af67ee1da50fcd591564034d789fe37e485ea8c9ea
3
+ size 1064
sib200_random_distil/checkpoint-1317/trainer_state.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1317,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.1389521640091116,
14
+ "grad_norm": 98.5,
15
+ "learning_rate": 1.2422171602126046e-05,
16
+ "loss": 0.2761865234375,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 2.277904328018223,
21
+ "grad_norm": 0.000125885009765625,
22
+ "learning_rate": 4.829157175398634e-06,
23
+ "loss": 0.00846030044555664,
24
+ "step": 1000
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 1317,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 3,
31
+ "save_steps": 500,
32
+ "stateful_callbacks": {
33
+ "TrainerControl": {
34
+ "args": {
35
+ "should_epoch_stop": false,
36
+ "should_evaluate": false,
37
+ "should_log": false,
38
+ "should_save": true,
39
+ "should_training_stop": true
40
+ },
41
+ "attributes": {}
42
+ }
43
+ },
44
+ "total_flos": 1.127174724550656e+16,
45
+ "train_batch_size": 8,
46
+ "trial_name": null,
47
+ "trial_params": null
48
+ }
sib200_random_distil/checkpoint-1317/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5937e813a601057d9c30bb4ad64ea0a5b1fb0d54a92e6c7a66b80c4e96bc7e1f
3
+ size 4728
sib200_random_distil/checkpoint-439/config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_sliding_window_pattern": 6,
3
+ "architectures": [
4
+ "Gemma3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": null,
9
+ "bos_token_id": 2,
10
+ "cache_implementation": "hybrid",
11
+ "dtype": "bfloat16",
12
+ "eos_token_id": 1,
13
+ "final_logit_softcapping": null,
14
+ "head_dim": 256,
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 1152,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 6912,
19
+ "layer_types": [
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "sliding_attention",
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "sliding_attention"
46
+ ],
47
+ "max_position_embeddings": 32768,
48
+ "model_type": "gemma3_text",
49
+ "num_attention_heads": 4,
50
+ "num_hidden_layers": 26,
51
+ "num_key_value_heads": 1,
52
+ "pad_token_id": 0,
53
+ "query_pre_attn_scalar": 256,
54
+ "rms_norm_eps": 1e-06,
55
+ "rope_parameters": {
56
+ "full_attention": {
57
+ "rope_theta": 1000000,
58
+ "rope_type": "default"
59
+ },
60
+ "sliding_attention": {
61
+ "rope_theta": 10000,
62
+ "rope_type": "default"
63
+ }
64
+ },
65
+ "sliding_window": 512,
66
+ "sliding_window_pattern": 6,
67
+ "tie_word_embeddings": true,
68
+ "transformers_version": "5.0.0",
69
+ "use_bidirectional_attention": false,
70
+ "use_cache": false,
71
+ "vocab_size": 262144
72
+ }
sib200_random_distil/checkpoint-439/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
+ "pad_token_id": 0,
10
+ "top_k": 64,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.0.0"
13
+ }
sib200_random_distil/checkpoint-439/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4dc50948a135e42e2dc9e00d48881ca48338038a37ecc39ff98fd76c78ea314
3
+ size 1999811208
sib200_random_distil/checkpoint-439/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1563bf9f9f7f2af778855fe379476f0b20f247aa39b6c3e7271c28592ce33be2
3
+ size 3999829006
sib200_random_distil/checkpoint-439/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
3
+ size 14244
sib200_random_distil/checkpoint-439/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b726c05ca678a451ae01f645aa4525cbb065d65810ec87b74dc2ce67d6dd83ef
3
+ size 1064
sib200_random_distil/checkpoint-439/trainer_state.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 439,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [],
12
+ "logging_steps": 500,
13
+ "max_steps": 1317,
14
+ "num_input_tokens_seen": 0,
15
+ "num_train_epochs": 3,
16
+ "save_steps": 500,
17
+ "stateful_callbacks": {
18
+ "TrainerControl": {
19
+ "args": {
20
+ "should_epoch_stop": false,
21
+ "should_evaluate": false,
22
+ "should_log": false,
23
+ "should_save": true,
24
+ "should_training_stop": false
25
+ },
26
+ "attributes": {}
27
+ }
28
+ },
29
+ "total_flos": 3757249081835520.0,
30
+ "train_batch_size": 8,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
sib200_random_distil/checkpoint-439/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5937e813a601057d9c30bb4ad64ea0a5b1fb0d54a92e6c7a66b80c4e96bc7e1f
3
+ size 4728
sib200_random_distil/checkpoint-878/config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_sliding_window_pattern": 6,
3
+ "architectures": [
4
+ "Gemma3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": null,
9
+ "bos_token_id": 2,
10
+ "cache_implementation": "hybrid",
11
+ "dtype": "bfloat16",
12
+ "eos_token_id": 1,
13
+ "final_logit_softcapping": null,
14
+ "head_dim": 256,
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 1152,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 6912,
19
+ "layer_types": [
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "sliding_attention",
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "sliding_attention"
46
+ ],
47
+ "max_position_embeddings": 32768,
48
+ "model_type": "gemma3_text",
49
+ "num_attention_heads": 4,
50
+ "num_hidden_layers": 26,
51
+ "num_key_value_heads": 1,
52
+ "pad_token_id": 0,
53
+ "query_pre_attn_scalar": 256,
54
+ "rms_norm_eps": 1e-06,
55
+ "rope_parameters": {
56
+ "full_attention": {
57
+ "rope_theta": 1000000,
58
+ "rope_type": "default"
59
+ },
60
+ "sliding_attention": {
61
+ "rope_theta": 10000,
62
+ "rope_type": "default"
63
+ }
64
+ },
65
+ "sliding_window": 512,
66
+ "sliding_window_pattern": 6,
67
+ "tie_word_embeddings": true,
68
+ "transformers_version": "5.0.0",
69
+ "use_bidirectional_attention": false,
70
+ "use_cache": false,
71
+ "vocab_size": 262144
72
+ }
sib200_random_distil/checkpoint-878/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
+ "pad_token_id": 0,
10
+ "top_k": 64,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.0.0"
13
+ }
sib200_random_distil/checkpoint-878/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:765080680a745b81266ab3af07ac2bb405c69d2f0aeacdf8fbf0804c79c51a3e
3
+ size 1999811208
sib200_random_distil/checkpoint-878/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88cf849b2c02afdfefc821934bebe4f2f58b96aa4d14112da0033f45530448e8
3
+ size 3999829006
sib200_random_distil/checkpoint-878/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
3
+ size 14244
sib200_random_distil/checkpoint-878/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f779096b2003bdfbcea99f7ac07fdd5a686ecd63c6d4b5906dd719d9be4c676a
3
+ size 1064
sib200_random_distil/checkpoint-878/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 878,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.1389521640091116,
14
+ "grad_norm": 98.5,
15
+ "learning_rate": 1.2422171602126046e-05,
16
+ "loss": 0.2761865234375,
17
+ "step": 500
18
+ }
19
+ ],
20
+ "logging_steps": 500,
21
+ "max_steps": 1317,
22
+ "num_input_tokens_seen": 0,
23
+ "num_train_epochs": 3,
24
+ "save_steps": 500,
25
+ "stateful_callbacks": {
26
+ "TrainerControl": {
27
+ "args": {
28
+ "should_epoch_stop": false,
29
+ "should_evaluate": false,
30
+ "should_log": false,
31
+ "should_save": true,
32
+ "should_training_stop": false
33
+ },
34
+ "attributes": {}
35
+ }
36
+ },
37
+ "total_flos": 7514498163671040.0,
38
+ "train_batch_size": 8,
39
+ "trial_name": null,
40
+ "trial_params": null
41
+ }
sib200_random_distil/checkpoint-878/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5937e813a601057d9c30bb4ad64ea0a5b1fb0d54a92e6c7a66b80c4e96bc7e1f
3
+ size 4728