Hugging Face's logo

w-ahmad
/
STRESS-TEST2

Safetensors
Model card Files
xet
 Community
w-ahmad commited on
Commit
8c0fb15
·
verified ·
1 Parent(s): 6de20d1

Auto upload zain 2026-08-14T21:19:40.486080 (part 3)

Browse files
Files changed (37) hide show
  1. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-100/config.json +36 -0
  2. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-100/model.safetensors +3 -0
  3. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-100/optimizer.pt +3 -0
  4. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-100/rng_state.pth +3 -0
  5. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-100/scheduler.pt +3 -0
  6. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-100/tokenizer.json +0 -0
  7. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-100/tokenizer_config.json +13 -0
  8. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-100/trainer_state.json +69 -0
  9. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-100/training_args.bin +3 -0
  10. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-200/config.json +36 -0
  11. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-200/model.safetensors +3 -0
  12. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-200/optimizer.pt +3 -0
  13. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-200/rng_state.pth +3 -0
  14. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-200/scheduler.pt +3 -0
  15. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-200/tokenizer.json +0 -0
  16. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-200/tokenizer_config.json +13 -0
  17. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-200/trainer_state.json +104 -0
  18. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-200/training_args.bin +3 -0
  19. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-300/config.json +36 -0
  20. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-300/model.safetensors +3 -0
  21. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-300/optimizer.pt +3 -0
  22. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-300/rng_state.pth +3 -0
  23. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-300/scheduler.pt +3 -0
  24. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-300/tokenizer.json +0 -0
  25. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-300/tokenizer_config.json +13 -0
  26. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-300/trainer_state.json +139 -0
  27. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-300/training_args.bin +3 -0
  28. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-400/config.json +36 -0
  29. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-400/model.safetensors +3 -0
  30. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-400/optimizer.pt +3 -0
  31. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-400/rng_state.pth +3 -0
  32. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-400/scheduler.pt +3 -0
  33. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-400/tokenizer.json +0 -0
  34. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-400/tokenizer_config.json +13 -0
  35. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-400/trainer_state.json +174 -0
  36. zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-400/training_args.bin +3 -0
  37. zain/Activation/out/glu-waleedglu_low-9L_run/training_log.jsonl +22 -0
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-100/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "waleedglu_low",
3
+ "architectures": [
4
+ "TinyLlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "dtype": "bfloat16",
10
+ "eos_token_id": 2,
11
+ "head_dim": 32,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 128,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 256,
16
+ "max_position_embeddings": 512,
17
+ "mlp_bias": false,
18
+ "mlp_type": "glu",
19
+ "model_type": "tiny_llama",
20
+ "num_attention_heads": 4,
21
+ "num_hidden_layers": 9,
22
+ "num_key_value_heads": 4,
23
+ "pad_token_id": 0,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-06,
26
+ "rope_parameters": {
27
+ "rope_theta": 10000.0,
28
+ "rope_type": "default"
29
+ },
30
+ "tie_word_embeddings": true,
31
+ "tokenizer_name": "w-ahmad/tiny-stories-tokenizer",
32
+ "transformers_version": "5.16.0.dev0",
33
+ "use_cache": false,
34
+ "vocab_size": 4096,
35
+ "waleed_beta": 10.0
36
+ }
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8161666e1b82d196d87f5d36d7202d1a3cecddb08149d3d44c675fabf6b319bf
3
+ size 4011496
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba00e3c385c16d0bdda2d5bf6560b055a73e232722f1f8ea8faa024cce8967df
3
+ size 8074746
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
3
+ size 14244
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:906745ab5f61e73e8c1ba850ef3b839e2766eba889b49c843836266988895165
3
+ size 1064
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-100/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "local_files_only": false,
9
+ "model_max_length": 1024,
10
+ "pad_token": "<|endoftext|>",
11
+ "tokenizer_class": "GPT2Tokenizer",
12
+ "unk_token": "<|endoftext|>"
13
+ }
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.05390835579514825,
6
+ "eval_steps": 60000,
7
+ "global_step": 100,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.01078167115902965,
14
+ "grad_norm": 0.97265625,
15
+ "learning_rate": 0.001,
16
+ "loss": 7.142742156982422,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 0.0215633423180593,
21
+ "grad_norm": 0.8125,
22
+ "learning_rate": 0.001,
23
+ "loss": 5.904148101806641,
24
+ "step": 40
25
+ },
26
+ {
27
+ "epoch": 0.03234501347708895,
28
+ "grad_norm": 0.75,
29
+ "learning_rate": 0.001,
30
+ "loss": 5.3337047576904295,
31
+ "step": 60
32
+ },
33
+ {
34
+ "epoch": 0.0431266846361186,
35
+ "grad_norm": 0.412109375,
36
+ "learning_rate": 0.001,
37
+ "loss": 4.781595230102539,
38
+ "step": 80
39
+ },
40
+ {
41
+ "epoch": 0.05390835579514825,
42
+ "grad_norm": 0.60546875,
43
+ "learning_rate": 0.001,
44
+ "loss": 4.378475570678711,
45
+ "step": 100
46
+ }
47
+ ],
48
+ "logging_steps": 20,
49
+ "max_steps": 1000,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 1,
52
+ "save_steps": 100,
53
+ "stateful_callbacks": {
54
+ "TrainerControl": {
55
+ "args": {
56
+ "should_epoch_stop": false,
57
+ "should_evaluate": false,
58
+ "should_log": false,
59
+ "should_save": true,
60
+ "should_training_stop": false
61
+ },
62
+ "attributes": {}
63
+ }
64
+ },
65
+ "total_flos": 232310754508800.0,
66
+ "train_batch_size": 512,
67
+ "trial_name": null,
68
+ "trial_params": null
69
+ }
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f407d56ebb06d0a5638185b1d3995ddaf419213345d6af2b2318046d202d294a
3
+ size 4920
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-200/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "waleedglu_low",
3
+ "architectures": [
4
+ "TinyLlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "dtype": "bfloat16",
10
+ "eos_token_id": 2,
11
+ "head_dim": 32,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 128,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 256,
16
+ "max_position_embeddings": 512,
17
+ "mlp_bias": false,
18
+ "mlp_type": "glu",
19
+ "model_type": "tiny_llama",
20
+ "num_attention_heads": 4,
21
+ "num_hidden_layers": 9,
22
+ "num_key_value_heads": 4,
23
+ "pad_token_id": 0,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-06,
26
+ "rope_parameters": {
27
+ "rope_theta": 10000.0,
28
+ "rope_type": "default"
29
+ },
30
+ "tie_word_embeddings": true,
31
+ "tokenizer_name": "w-ahmad/tiny-stories-tokenizer",
32
+ "transformers_version": "5.16.0.dev0",
33
+ "use_cache": false,
34
+ "vocab_size": 4096,
35
+ "waleed_beta": 10.0
36
+ }
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fa065b0189a98d0fd2d94c40aafeb680187a42d0f371e4cebe8d419651ad06f
3
+ size 4011496
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ab697aec9423a7ffabf46efd33697a9ee8373ef2ae705f7c26e9d5a82660dd8
3
+ size 8074746
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
3
+ size 14244
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d3b5a970fc92af42664e84ba686059eaaacfaa668691c0cf6d2afddda677461
3
+ size 1064
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "local_files_only": false,
9
+ "model_max_length": 1024,
10
+ "pad_token": "<|endoftext|>",
11
+ "tokenizer_class": "GPT2Tokenizer",
12
+ "unk_token": "<|endoftext|>"
13
+ }
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.1078167115902965,
6
+ "eval_steps": 60000,
7
+ "global_step": 200,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.01078167115902965,
14
+ "grad_norm": 0.97265625,
15
+ "learning_rate": 0.001,
16
+ "loss": 7.142742156982422,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 0.0215633423180593,
21
+ "grad_norm": 0.8125,
22
+ "learning_rate": 0.001,
23
+ "loss": 5.904148101806641,
24
+ "step": 40
25
+ },
26
+ {
27
+ "epoch": 0.03234501347708895,
28
+ "grad_norm": 0.75,
29
+ "learning_rate": 0.001,
30
+ "loss": 5.3337047576904295,
31
+ "step": 60
32
+ },
33
+ {
34
+ "epoch": 0.0431266846361186,
35
+ "grad_norm": 0.412109375,
36
+ "learning_rate": 0.001,
37
+ "loss": 4.781595230102539,
38
+ "step": 80
39
+ },
40
+ {
41
+ "epoch": 0.05390835579514825,
42
+ "grad_norm": 0.60546875,
43
+ "learning_rate": 0.001,
44
+ "loss": 4.378475570678711,
45
+ "step": 100
46
+ },
47
+ {
48
+ "epoch": 0.0646900269541779,
49
+ "grad_norm": 1.125,
50
+ "learning_rate": 0.001,
51
+ "loss": 4.1198162078857425,
52
+ "step": 120
53
+ },
54
+ {
55
+ "epoch": 0.07547169811320754,
56
+ "grad_norm": 0.8046875,
57
+ "learning_rate": 0.001,
58
+ "loss": 3.9039352416992186,
59
+ "step": 140
60
+ },
61
+ {
62
+ "epoch": 0.0862533692722372,
63
+ "grad_norm": 1.2578125,
64
+ "learning_rate": 0.001,
65
+ "loss": 3.714673614501953,
66
+ "step": 160
67
+ },
68
+ {
69
+ "epoch": 0.09703504043126684,
70
+ "grad_norm": 0.62890625,
71
+ "learning_rate": 0.001,
72
+ "loss": 3.5654438018798826,
73
+ "step": 180
74
+ },
75
+ {
76
+ "epoch": 0.1078167115902965,
77
+ "grad_norm": 0.578125,
78
+ "learning_rate": 0.001,
79
+ "loss": 3.436704635620117,
80
+ "step": 200
81
+ }
82
+ ],
83
+ "logging_steps": 20,
84
+ "max_steps": 1000,
85
+ "num_input_tokens_seen": 0,
86
+ "num_train_epochs": 1,
87
+ "save_steps": 100,
88
+ "stateful_callbacks": {
89
+ "TrainerControl": {
90
+ "args": {
91
+ "should_epoch_stop": false,
92
+ "should_evaluate": false,
93
+ "should_log": false,
94
+ "should_save": true,
95
+ "should_training_stop": false
96
+ },
97
+ "attributes": {}
98
+ }
99
+ },
100
+ "total_flos": 464621509017600.0,
101
+ "train_batch_size": 512,
102
+ "trial_name": null,
103
+ "trial_params": null
104
+ }
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f407d56ebb06d0a5638185b1d3995ddaf419213345d6af2b2318046d202d294a
3
+ size 4920
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-300/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "waleedglu_low",
3
+ "architectures": [
4
+ "TinyLlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "dtype": "bfloat16",
10
+ "eos_token_id": 2,
11
+ "head_dim": 32,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 128,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 256,
16
+ "max_position_embeddings": 512,
17
+ "mlp_bias": false,
18
+ "mlp_type": "glu",
19
+ "model_type": "tiny_llama",
20
+ "num_attention_heads": 4,
21
+ "num_hidden_layers": 9,
22
+ "num_key_value_heads": 4,
23
+ "pad_token_id": 0,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-06,
26
+ "rope_parameters": {
27
+ "rope_theta": 10000.0,
28
+ "rope_type": "default"
29
+ },
30
+ "tie_word_embeddings": true,
31
+ "tokenizer_name": "w-ahmad/tiny-stories-tokenizer",
32
+ "transformers_version": "5.16.0.dev0",
33
+ "use_cache": false,
34
+ "vocab_size": 4096,
35
+ "waleed_beta": 10.0
36
+ }
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-300/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc60bd9b14470491c7083143bb08e950c072a544fa9883c68e73daab5c972b80
3
+ size 4011496
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-300/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dade17d59363b2703b3b4f9a3c30c393d63e3327d1edf83b8d22637c0c5036a3
3
+ size 8074746
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-300/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
3
+ size 14244
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76cd21f32221b90fb8288fd2428595ec8b5039fe2425086d67cacb5c8d814c9e
3
+ size 1064
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-300/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-300/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "local_files_only": false,
9
+ "model_max_length": 1024,
10
+ "pad_token": "<|endoftext|>",
11
+ "tokenizer_class": "GPT2Tokenizer",
12
+ "unk_token": "<|endoftext|>"
13
+ }
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-300/trainer_state.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.16172506738544473,
6
+ "eval_steps": 60000,
7
+ "global_step": 300,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.01078167115902965,
14
+ "grad_norm": 0.97265625,
15
+ "learning_rate": 0.001,
16
+ "loss": 7.142742156982422,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 0.0215633423180593,
21
+ "grad_norm": 0.8125,
22
+ "learning_rate": 0.001,
23
+ "loss": 5.904148101806641,
24
+ "step": 40
25
+ },
26
+ {
27
+ "epoch": 0.03234501347708895,
28
+ "grad_norm": 0.75,
29
+ "learning_rate": 0.001,
30
+ "loss": 5.3337047576904295,
31
+ "step": 60
32
+ },
33
+ {
34
+ "epoch": 0.0431266846361186,
35
+ "grad_norm": 0.412109375,
36
+ "learning_rate": 0.001,
37
+ "loss": 4.781595230102539,
38
+ "step": 80
39
+ },
40
+ {
41
+ "epoch": 0.05390835579514825,
42
+ "grad_norm": 0.60546875,
43
+ "learning_rate": 0.001,
44
+ "loss": 4.378475570678711,
45
+ "step": 100
46
+ },
47
+ {
48
+ "epoch": 0.0646900269541779,
49
+ "grad_norm": 1.125,
50
+ "learning_rate": 0.001,
51
+ "loss": 4.1198162078857425,
52
+ "step": 120
53
+ },
54
+ {
55
+ "epoch": 0.07547169811320754,
56
+ "grad_norm": 0.8046875,
57
+ "learning_rate": 0.001,
58
+ "loss": 3.9039352416992186,
59
+ "step": 140
60
+ },
61
+ {
62
+ "epoch": 0.0862533692722372,
63
+ "grad_norm": 1.2578125,
64
+ "learning_rate": 0.001,
65
+ "loss": 3.714673614501953,
66
+ "step": 160
67
+ },
68
+ {
69
+ "epoch": 0.09703504043126684,
70
+ "grad_norm": 0.62890625,
71
+ "learning_rate": 0.001,
72
+ "loss": 3.5654438018798826,
73
+ "step": 180
74
+ },
75
+ {
76
+ "epoch": 0.1078167115902965,
77
+ "grad_norm": 0.578125,
78
+ "learning_rate": 0.001,
79
+ "loss": 3.436704635620117,
80
+ "step": 200
81
+ },
82
+ {
83
+ "epoch": 0.11859838274932614,
84
+ "grad_norm": 0.83203125,
85
+ "learning_rate": 0.001,
86
+ "loss": 3.3229846954345703,
87
+ "step": 220
88
+ },
89
+ {
90
+ "epoch": 0.1293800539083558,
91
+ "grad_norm": 0.62109375,
92
+ "learning_rate": 0.001,
93
+ "loss": 3.2290836334228517,
94
+ "step": 240
95
+ },
96
+ {
97
+ "epoch": 0.14016172506738545,
98
+ "grad_norm": 0.5859375,
99
+ "learning_rate": 0.001,
100
+ "loss": 3.1386213302612305,
101
+ "step": 260
102
+ },
103
+ {
104
+ "epoch": 0.1509433962264151,
105
+ "grad_norm": 0.94921875,
106
+ "learning_rate": 0.001,
107
+ "loss": 3.056053352355957,
108
+ "step": 280
109
+ },
110
+ {
111
+ "epoch": 0.16172506738544473,
112
+ "grad_norm": 0.453125,
113
+ "learning_rate": 0.001,
114
+ "loss": 2.9869314193725587,
115
+ "step": 300
116
+ }
117
+ ],
118
+ "logging_steps": 20,
119
+ "max_steps": 1000,
120
+ "num_input_tokens_seen": 0,
121
+ "num_train_epochs": 1,
122
+ "save_steps": 100,
123
+ "stateful_callbacks": {
124
+ "TrainerControl": {
125
+ "args": {
126
+ "should_epoch_stop": false,
127
+ "should_evaluate": false,
128
+ "should_log": false,
129
+ "should_save": true,
130
+ "should_training_stop": false
131
+ },
132
+ "attributes": {}
133
+ }
134
+ },
135
+ "total_flos": 696932263526400.0,
136
+ "train_batch_size": 512,
137
+ "trial_name": null,
138
+ "trial_params": null
139
+ }
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f407d56ebb06d0a5638185b1d3995ddaf419213345d6af2b2318046d202d294a
3
+ size 4920
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-400/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "waleedglu_low",
3
+ "architectures": [
4
+ "TinyLlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "dtype": "bfloat16",
10
+ "eos_token_id": 2,
11
+ "head_dim": 32,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 128,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 256,
16
+ "max_position_embeddings": 512,
17
+ "mlp_bias": false,
18
+ "mlp_type": "glu",
19
+ "model_type": "tiny_llama",
20
+ "num_attention_heads": 4,
21
+ "num_hidden_layers": 9,
22
+ "num_key_value_heads": 4,
23
+ "pad_token_id": 0,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-06,
26
+ "rope_parameters": {
27
+ "rope_theta": 10000.0,
28
+ "rope_type": "default"
29
+ },
30
+ "tie_word_embeddings": true,
31
+ "tokenizer_name": "w-ahmad/tiny-stories-tokenizer",
32
+ "transformers_version": "5.16.0.dev0",
33
+ "use_cache": false,
34
+ "vocab_size": 4096,
35
+ "waleed_beta": 10.0
36
+ }
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-400/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6535cc46e29036bce556bdb0f56a7cf980617c7effa4c19d6232b412084ce09d
3
+ size 4011496
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:944bf6062da33b7ab4270e228f736e5423844b3572f9d941b887366bbbac1251
3
+ size 8074746
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-400/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
3
+ size 14244
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51769a11c87b2b665cbe64c58b934afdb1fa1998bffb4addcc2f852b172d6681
3
+ size 1064
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-400/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-400/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "local_files_only": false,
9
+ "model_max_length": 1024,
10
+ "pad_token": "<|endoftext|>",
11
+ "tokenizer_class": "GPT2Tokenizer",
12
+ "unk_token": "<|endoftext|>"
13
+ }
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-400/trainer_state.json ADDED
@@ -0,0 +1,174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.215633423180593,
6
+ "eval_steps": 60000,
7
+ "global_step": 400,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.01078167115902965,
14
+ "grad_norm": 0.97265625,
15
+ "learning_rate": 0.001,
16
+ "loss": 7.142742156982422,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 0.0215633423180593,
21
+ "grad_norm": 0.8125,
22
+ "learning_rate": 0.001,
23
+ "loss": 5.904148101806641,
24
+ "step": 40
25
+ },
26
+ {
27
+ "epoch": 0.03234501347708895,
28
+ "grad_norm": 0.75,
29
+ "learning_rate": 0.001,
30
+ "loss": 5.3337047576904295,
31
+ "step": 60
32
+ },
33
+ {
34
+ "epoch": 0.0431266846361186,
35
+ "grad_norm": 0.412109375,
36
+ "learning_rate": 0.001,
37
+ "loss": 4.781595230102539,
38
+ "step": 80
39
+ },
40
+ {
41
+ "epoch": 0.05390835579514825,
42
+ "grad_norm": 0.60546875,
43
+ "learning_rate": 0.001,
44
+ "loss": 4.378475570678711,
45
+ "step": 100
46
+ },
47
+ {
48
+ "epoch": 0.0646900269541779,
49
+ "grad_norm": 1.125,
50
+ "learning_rate": 0.001,
51
+ "loss": 4.1198162078857425,
52
+ "step": 120
53
+ },
54
+ {
55
+ "epoch": 0.07547169811320754,
56
+ "grad_norm": 0.8046875,
57
+ "learning_rate": 0.001,
58
+ "loss": 3.9039352416992186,
59
+ "step": 140
60
+ },
61
+ {
62
+ "epoch": 0.0862533692722372,
63
+ "grad_norm": 1.2578125,
64
+ "learning_rate": 0.001,
65
+ "loss": 3.714673614501953,
66
+ "step": 160
67
+ },
68
+ {
69
+ "epoch": 0.09703504043126684,
70
+ "grad_norm": 0.62890625,
71
+ "learning_rate": 0.001,
72
+ "loss": 3.5654438018798826,
73
+ "step": 180
74
+ },
75
+ {
76
+ "epoch": 0.1078167115902965,
77
+ "grad_norm": 0.578125,
78
+ "learning_rate": 0.001,
79
+ "loss": 3.436704635620117,
80
+ "step": 200
81
+ },
82
+ {
83
+ "epoch": 0.11859838274932614,
84
+ "grad_norm": 0.83203125,
85
+ "learning_rate": 0.001,
86
+ "loss": 3.3229846954345703,
87
+ "step": 220
88
+ },
89
+ {
90
+ "epoch": 0.1293800539083558,
91
+ "grad_norm": 0.62109375,
92
+ "learning_rate": 0.001,
93
+ "loss": 3.2290836334228517,
94
+ "step": 240
95
+ },
96
+ {
97
+ "epoch": 0.14016172506738545,
98
+ "grad_norm": 0.5859375,
99
+ "learning_rate": 0.001,
100
+ "loss": 3.1386213302612305,
101
+ "step": 260
102
+ },
103
+ {
104
+ "epoch": 0.1509433962264151,
105
+ "grad_norm": 0.94921875,
106
+ "learning_rate": 0.001,
107
+ "loss": 3.056053352355957,
108
+ "step": 280
109
+ },
110
+ {
111
+ "epoch": 0.16172506738544473,
112
+ "grad_norm": 0.453125,
113
+ "learning_rate": 0.001,
114
+ "loss": 2.9869314193725587,
115
+ "step": 300
116
+ },
117
+ {
118
+ "epoch": 0.1725067385444744,
119
+ "grad_norm": 0.59375,
120
+ "learning_rate": 0.001,
121
+ "loss": 2.9244447708129884,
122
+ "step": 320
123
+ },
124
+ {
125
+ "epoch": 0.18328840970350405,
126
+ "grad_norm": 0.68359375,
127
+ "learning_rate": 0.001,
128
+ "loss": 2.8627126693725584,
129
+ "step": 340
130
+ },
131
+ {
132
+ "epoch": 0.1940700808625337,
133
+ "grad_norm": 0.58203125,
134
+ "learning_rate": 0.001,
135
+ "loss": 2.8148895263671876,
136
+ "step": 360
137
+ },
138
+ {
139
+ "epoch": 0.20485175202156333,
140
+ "grad_norm": 0.671875,
141
+ "learning_rate": 0.001,
142
+ "loss": 2.769453239440918,
143
+ "step": 380
144
+ },
145
+ {
146
+ "epoch": 0.215633423180593,
147
+ "grad_norm": 0.578125,
148
+ "learning_rate": 0.001,
149
+ "loss": 2.7255327224731447,
150
+ "step": 400
151
+ }
152
+ ],
153
+ "logging_steps": 20,
154
+ "max_steps": 1000,
155
+ "num_input_tokens_seen": 0,
156
+ "num_train_epochs": 1,
157
+ "save_steps": 100,
158
+ "stateful_callbacks": {
159
+ "TrainerControl": {
160
+ "args": {
161
+ "should_epoch_stop": false,
162
+ "should_evaluate": false,
163
+ "should_log": false,
164
+ "should_save": true,
165
+ "should_training_stop": false
166
+ },
167
+ "attributes": {}
168
+ }
169
+ },
170
+ "total_flos": 929243018035200.0,
171
+ "train_batch_size": 512,
172
+ "trial_name": null,
173
+ "trial_params": null
174
+ }
zain/Activation/out/glu-waleedglu_low-9L_run/checkpoint-400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f407d56ebb06d0a5638185b1d3995ddaf419213345d6af2b2318046d202d294a
3
+ size 4920
zain/Activation/out/glu-waleedglu_low-9L_run/training_log.jsonl CHANGED
@@ -1,2 +1,24 @@
1
  {"step": 20, "epoch": 0.01078167115902965, "timestamp": 1786742062.4714627, "loss": 7.142742156982422, "grad_norm": 0.97265625, "learning_rate": 0.001, "train/total_time_seconds": 5.759636055678129, "train/time_per_step_avg": 0.28798180278390645, "train/epoch_time_elapsed": 13.796517938375473, "train/estimated_remaining_minutes": 4.703702778803805}
2
  {"step": 40, "epoch": 0.0215633423180593, "timestamp": 1786742075.9721467, "loss": 5.904148101806641, "grad_norm": 0.8125, "learning_rate": 0.001, "train/total_time_seconds": 11.669862788170576, "train/time_per_step_avg": 0.2917465697042644, "train/epoch_time_elapsed": 27.297202467918396, "train/estimated_remaining_minutes": 4.66794511526823}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {"step": 20, "epoch": 0.01078167115902965, "timestamp": 1786742062.4714627, "loss": 7.142742156982422, "grad_norm": 0.97265625, "learning_rate": 0.001, "train/total_time_seconds": 5.759636055678129, "train/time_per_step_avg": 0.28798180278390645, "train/epoch_time_elapsed": 13.796517938375473, "train/estimated_remaining_minutes": 4.703702778803805}
2
  {"step": 40, "epoch": 0.0215633423180593, "timestamp": 1786742075.9721467, "loss": 5.904148101806641, "grad_norm": 0.8125, "learning_rate": 0.001, "train/total_time_seconds": 11.669862788170576, "train/time_per_step_avg": 0.2917465697042644, "train/epoch_time_elapsed": 27.297202467918396, "train/estimated_remaining_minutes": 4.66794511526823}
3
+ {"step": 60, "epoch": 0.03234501347708895, "timestamp": 1786742088.241962, "loss": 5.3337047576904295, "grad_norm": 0.75, "learning_rate": 0.001, "train/total_time_seconds": 16.46451184898615, "train/time_per_step_avg": 0.2744085308164358, "train/epoch_time_elapsed": 39.567017927765846, "train/estimated_remaining_minutes": 4.299066982790828}
4
+ {"step": 80, "epoch": 0.0431266846361186, "timestamp": 1786742099.8676906, "loss": 4.781595230102539, "grad_norm": 0.412109375, "learning_rate": 0.001, "train/total_time_seconds": 20.629995711147785, "train/time_per_step_avg": 0.2578749463893473, "train/epoch_time_elapsed": 51.192746471613646, "train/estimated_remaining_minutes": 3.9540825113033256}
5
+ {"step": 100, "epoch": 0.05390835579514825, "timestamp": 1786742111.5637069, "loss": 4.378475570678711, "grad_norm": 0.60546875, "learning_rate": 0.001, "train/total_time_seconds": 24.68515096232295, "train/time_per_step_avg": 0.2468515096232295, "train/epoch_time_elapsed": 62.88876183703542, "train/estimated_remaining_minutes": 3.7027726443484426}
6
+ {"step": 120, "epoch": 0.0646900269541779, "timestamp": 1786742125.8701537, "loss": 4.1198162078857425, "grad_norm": 1.125, "learning_rate": 0.001, "train/total_time_seconds": 31.45543760806322, "train/time_per_step_avg": 0.2569580155238509, "train/epoch_time_elapsed": 77.19520807266235, "train/estimated_remaining_minutes": 3.844553485429949}
7
+ {"step": 140, "epoch": 0.07547169811320754, "timestamp": 1786742139.8269417, "loss": 3.9039352416992186, "grad_norm": 0.8046875, "learning_rate": 0.001, "train/total_time_seconds": 37.796065241098404, "train/time_per_step_avg": 0.26126202452927827, "train/epoch_time_elapsed": 91.15199727192521, "train/estimated_remaining_minutes": 3.8695971556362654}
8
+ {"step": 160, "epoch": 0.0862533692722372, "timestamp": 1786742153.7062178, "loss": 3.714673614501953, "grad_norm": 1.2578125, "learning_rate": 0.001, "train/total_time_seconds": 44.084308575838804, "train/time_per_step_avg": 0.2761979672685266, "train/epoch_time_elapsed": 105.03127274289727, "train/estimated_remaining_minutes": 3.8573770003858954}
9
+ {"step": 180, "epoch": 0.09703504043126684, "timestamp": 1786742167.568087, "loss": 3.5654438018798826, "grad_norm": 0.62890625, "learning_rate": 0.001, "train/total_time_seconds": 50.41633830592036, "train/time_per_step_avg": 0.29786342594772575, "train/epoch_time_elapsed": 118.89314214885235, "train/estimated_remaining_minutes": 3.827907167671732}
10
+ {"step": 200, "epoch": 0.1078167115902965, "timestamp": 1786742182.0534978, "loss": 3.436704635620117, "grad_norm": 0.578125, "learning_rate": 0.001, "train/total_time_seconds": 57.40205043926835, "train/time_per_step_avg": 0.327168994769454, "train/epoch_time_elapsed": 133.3785528615117, "train/estimated_remaining_minutes": 3.82680336261789}
11
+ {"step": 220, "epoch": 0.11859838274932614, "timestamp": 1786742196.659039, "loss": 3.3229846954345703, "grad_norm": 0.83203125, "learning_rate": 0.001, "train/total_time_seconds": 64.54477836191654, "train/time_per_step_avg": 0.3308934075385332, "train/epoch_time_elapsed": 147.9840943366289, "train/estimated_remaining_minutes": 3.8140096304768867}
12
+ {"step": 240, "epoch": 0.1293800539083558, "timestamp": 1786742210.540067, "loss": 3.2290836334228517, "grad_norm": 0.62109375, "learning_rate": 0.001, "train/total_time_seconds": 70.93688360229135, "train/time_per_step_avg": 0.3314081836119294, "train/epoch_time_elapsed": 161.86512281745672, "train/estimated_remaining_minutes": 3.743891079009821}
13
+ {"step": 260, "epoch": 0.14016172506738545, "timestamp": 1786742224.5380383, "loss": 3.1386213302612305, "grad_norm": 0.5859375, "learning_rate": 0.001, "train/total_time_seconds": 77.43044716492295, "train/time_per_step_avg": 0.3334613858908415, "train/epoch_time_elapsed": 175.863093521446, "train/estimated_remaining_minutes": 3.6729827501309606}
14
+ {"step": 280, "epoch": 0.1509433962264151, "timestamp": 1786742238.5658176, "loss": 3.056053352355957, "grad_norm": 0.94921875, "learning_rate": 0.001, "train/total_time_seconds": 83.82333216443658, "train/time_per_step_avg": 0.33406993858516215, "train/epoch_time_elapsed": 189.89087346941233, "train/estimated_remaining_minutes": 3.5924285213329963}
15
+ {"step": 300, "epoch": 0.16172506738544473, "timestamp": 1786742252.4049437, "loss": 2.9869314193725587, "grad_norm": 0.453125, "learning_rate": 0.001, "train/total_time_seconds": 90.27841727435589, "train/time_per_step_avg": 0.3287636683508754, "train/epoch_time_elapsed": 203.72999892383814, "train/estimated_remaining_minutes": 3.5108273384471733}
16
+ {"step": 320, "epoch": 0.1725067385444744, "timestamp": 1786742266.610275, "loss": 2.9244447708129884, "grad_norm": 0.59375, "learning_rate": 0.001, "train/total_time_seconds": 96.86544046550989, "train/time_per_step_avg": 0.3232066210359335, "train/epoch_time_elapsed": 217.93533045053482, "train/estimated_remaining_minutes": 3.430651016486808}
17
+ {"step": 340, "epoch": 0.18328840970350405, "timestamp": 1786742280.4086695, "loss": 2.8627126693725584, "grad_norm": 0.68359375, "learning_rate": 0.001, "train/total_time_seconds": 103.12597471475601, "train/time_per_step_avg": 0.3218909111246467, "train/epoch_time_elapsed": 231.73372469097376, "train/estimated_remaining_minutes": 3.3364285937126947}
18
+ {"step": 360, "epoch": 0.1940700808625337, "timestamp": 1786742294.5913475, "loss": 2.8148895263671876, "grad_norm": 0.58203125, "learning_rate": 0.001, "train/total_time_seconds": 109.76122856512666, "train/time_per_step_avg": 0.32330781400203706, "train/epoch_time_elapsed": 245.91640236228704, "train/estimated_remaining_minutes": 3.2521845500778275}
19
+ {"step": 380, "epoch": 0.20485175202156333, "timestamp": 1786742309.0352, "loss": 2.769453239440918, "grad_norm": 0.671875, "learning_rate": 0.001, "train/total_time_seconds": 116.67853581905365, "train/time_per_step_avg": 0.3285520365461707, "train/epoch_time_elapsed": 260.3602552227676, "train/estimated_remaining_minutes": 3.1728373775356697}
20
+ {"step": 400, "epoch": 0.215633423180593, "timestamp": 1786742323.4303114, "loss": 2.7255327224731447, "grad_norm": 0.578125, "learning_rate": 0.001, "train/total_time_seconds": 123.64962760731578, "train/time_per_step_avg": 0.3337121033295989, "train/epoch_time_elapsed": 274.7553662918508, "train/estimated_remaining_minutes": 3.0912406901828944}
21
+ {"step": 420, "epoch": 0.22641509433962265, "timestamp": 1786742337.4866757, "loss": 2.6909984588623046, "grad_norm": 0.7578125, "learning_rate": 0.001, "train/total_time_seconds": 130.08213763311505, "train/time_per_step_avg": 0.33216697167605164, "train/epoch_time_elapsed": 288.8117315992713, "train/estimated_remaining_minutes": 2.9939539613970925}
22
+ {"step": 440, "epoch": 0.2371967654986523, "timestamp": 1786742351.3360703, "loss": 2.667934036254883, "grad_norm": 0.61328125, "learning_rate": 0.001, "train/total_time_seconds": 136.42845050618052, "train/time_per_step_avg": 0.33302475791424513, "train/epoch_time_elapsed": 302.66112614423037, "train/estimated_remaining_minutes": 2.893936828918981}
23
+ {"step": 460, "epoch": 0.24797843665768193, "timestamp": 1786742365.3302343, "loss": 2.6315393447875977, "grad_norm": 0.74609375, "learning_rate": 0.001, "train/total_time_seconds": 142.82130414247513, "train/time_per_step_avg": 0.3306007557734847, "train/epoch_time_elapsed": 316.6552901901305, "train/estimated_remaining_minutes": 2.7943298636571217}
24
+ {"step": 480, "epoch": 0.2587601078167116, "timestamp": 1786742379.153006, "loss": 2.600478744506836, "grad_norm": 0.67578125, "learning_rate": 0.001, "train/total_time_seconds": 149.15363596752286, "train/time_per_step_avg": 0.3247510014846921, "train/epoch_time_elapsed": 330.47806179895997, "train/estimated_remaining_minutes": 2.693051760524718}