Hugging Face's logo

jerseyjerry
/
task4-20250221-h100

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Community
jerseyjerry commited on
Commit
c5e090e
·
verified ·
1 Parent(s): f33d56c

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. README.md +59 -0
  2. adapter_config.json +31 -0
  3. adapter_model.safetensors +3 -0
  4. added_tokens.json +13 -0
  5. special_tokens_map.json +39 -0
  6. tokenizer.json +0 -0
  7. tokenizer.model +3 -0
  8. tokenizer_config.json +136 -0
  9. trainer_state.json +3687 -0
  10. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: other
4
+ base_model: microsoft/Phi-3-mini-4k-instruct
5
+ tags:
6
+ - llama-factory
7
+ - lora
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: lora
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # lora
18
+
19
+ This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on the flock_task4_tranning dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 1
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 2
43
+ - total_train_batch_size: 16
44
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_ratio: 0.1
47
+ - num_epochs: 2
48
+
49
+ ### Training results
50
+
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - PEFT 0.12.0
56
+ - Transformers 4.49.0
57
+ - Pytorch 2.6.0+cu124
58
+ - Datasets 3.2.0
59
+ - Tokenizers 0.21.0
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 128,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "o_proj",
24
+ "down_proj",
25
+ "gate_up_proj",
26
+ "qkv_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM",
29
+ "use_dora": false,
30
+ "use_rslora": false
31
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2482f0227446149ca1fd76ae0452189f22c561153785060d19856d5df9383b3f
3
+ size 402688040
added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32001,
3
+ "<|endoftext|>": 32000,
4
+ "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
11
+ "<|system|>": 32006,
12
+ "<|user|>": 32010
13
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|end|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|endoftext|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": {
26
+ "content": "<|endoftext|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "unk_token": {
33
+ "content": "<unk>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ }
39
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ }
118
+ },
119
+ "additional_special_tokens": [
120
+ "<|end|>"
121
+ ],
122
+ "bos_token": "<s>",
123
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
124
+ "clean_up_tokenization_spaces": false,
125
+ "eos_token": "<|endoftext|>",
126
+ "extra_special_tokens": {},
127
+ "legacy": false,
128
+ "model_max_length": 2048,
129
+ "pad_token": "<|endoftext|>",
130
+ "padding_side": "right",
131
+ "sp_model_kwargs": {},
132
+ "split_special_tokens": false,
133
+ "tokenizer_class": "LlamaTokenizer",
134
+ "unk_token": "<unk>",
135
+ "use_default_system_prompt": false
136
+ }
trainer_state.json ADDED
@@ -0,0 +1,3687 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.996996996996997,
5
+ "eval_steps": 50,
6
+ "global_step": 998,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.004004004004004004,
13
+ "grad_norm": 1.060176968574524,
14
+ "learning_rate": 1.0000000000000002e-06,
15
+ "loss": 1.2427,
16
+ "step": 2
17
+ },
18
+ {
19
+ "epoch": 0.008008008008008008,
20
+ "grad_norm": 1.2065035104751587,
21
+ "learning_rate": 2.0000000000000003e-06,
22
+ "loss": 1.2909,
23
+ "step": 4
24
+ },
25
+ {
26
+ "epoch": 0.012012012012012012,
27
+ "grad_norm": 1.3198168277740479,
28
+ "learning_rate": 3e-06,
29
+ "loss": 1.2386,
30
+ "step": 6
31
+ },
32
+ {
33
+ "epoch": 0.016016016016016016,
34
+ "grad_norm": 1.1702309846878052,
35
+ "learning_rate": 4.000000000000001e-06,
36
+ "loss": 1.2236,
37
+ "step": 8
38
+ },
39
+ {
40
+ "epoch": 0.02002002002002002,
41
+ "grad_norm": 1.0895090103149414,
42
+ "learning_rate": 5e-06,
43
+ "loss": 1.2185,
44
+ "step": 10
45
+ },
46
+ {
47
+ "epoch": 0.024024024024024024,
48
+ "grad_norm": 0.8205417394638062,
49
+ "learning_rate": 6e-06,
50
+ "loss": 1.2538,
51
+ "step": 12
52
+ },
53
+ {
54
+ "epoch": 0.028028028028028028,
55
+ "grad_norm": 0.9537830352783203,
56
+ "learning_rate": 7.000000000000001e-06,
57
+ "loss": 1.2461,
58
+ "step": 14
59
+ },
60
+ {
61
+ "epoch": 0.03203203203203203,
62
+ "grad_norm": 0.8598117828369141,
63
+ "learning_rate": 8.000000000000001e-06,
64
+ "loss": 1.2755,
65
+ "step": 16
66
+ },
67
+ {
68
+ "epoch": 0.036036036036036036,
69
+ "grad_norm": 0.5490444302558899,
70
+ "learning_rate": 9e-06,
71
+ "loss": 1.205,
72
+ "step": 18
73
+ },
74
+ {
75
+ "epoch": 0.04004004004004004,
76
+ "grad_norm": 0.3910800814628601,
77
+ "learning_rate": 1e-05,
78
+ "loss": 1.1335,
79
+ "step": 20
80
+ },
81
+ {
82
+ "epoch": 0.044044044044044044,
83
+ "grad_norm": 0.360065758228302,
84
+ "learning_rate": 1.1000000000000001e-05,
85
+ "loss": 1.1258,
86
+ "step": 22
87
+ },
88
+ {
89
+ "epoch": 0.04804804804804805,
90
+ "grad_norm": 0.36001095175743103,
91
+ "learning_rate": 1.2e-05,
92
+ "loss": 1.1287,
93
+ "step": 24
94
+ },
95
+ {
96
+ "epoch": 0.05205205205205205,
97
+ "grad_norm": 0.3197377026081085,
98
+ "learning_rate": 1.3000000000000001e-05,
99
+ "loss": 1.1417,
100
+ "step": 26
101
+ },
102
+ {
103
+ "epoch": 0.056056056056056056,
104
+ "grad_norm": 0.31732141971588135,
105
+ "learning_rate": 1.4000000000000001e-05,
106
+ "loss": 1.1494,
107
+ "step": 28
108
+ },
109
+ {
110
+ "epoch": 0.06006006006006006,
111
+ "grad_norm": 0.30313611030578613,
112
+ "learning_rate": 1.5e-05,
113
+ "loss": 1.07,
114
+ "step": 30
115
+ },
116
+ {
117
+ "epoch": 0.06406406406406406,
118
+ "grad_norm": 0.3234356641769409,
119
+ "learning_rate": 1.6000000000000003e-05,
120
+ "loss": 1.0969,
121
+ "step": 32
122
+ },
123
+ {
124
+ "epoch": 0.06806806806806807,
125
+ "grad_norm": 0.3222120404243469,
126
+ "learning_rate": 1.7000000000000003e-05,
127
+ "loss": 1.1026,
128
+ "step": 34
129
+ },
130
+ {
131
+ "epoch": 0.07207207207207207,
132
+ "grad_norm": 0.324735164642334,
133
+ "learning_rate": 1.8e-05,
134
+ "loss": 1.1261,
135
+ "step": 36
136
+ },
137
+ {
138
+ "epoch": 0.07607607607607608,
139
+ "grad_norm": 0.2944203317165375,
140
+ "learning_rate": 1.9e-05,
141
+ "loss": 1.1191,
142
+ "step": 38
143
+ },
144
+ {
145
+ "epoch": 0.08008008008008008,
146
+ "grad_norm": 0.290088027715683,
147
+ "learning_rate": 2e-05,
148
+ "loss": 1.0987,
149
+ "step": 40
150
+ },
151
+ {
152
+ "epoch": 0.08408408408408409,
153
+ "grad_norm": 0.32874158024787903,
154
+ "learning_rate": 2.1e-05,
155
+ "loss": 1.0157,
156
+ "step": 42
157
+ },
158
+ {
159
+ "epoch": 0.08808808808808809,
160
+ "grad_norm": 0.2925970256328583,
161
+ "learning_rate": 2.2000000000000003e-05,
162
+ "loss": 1.0582,
163
+ "step": 44
164
+ },
165
+ {
166
+ "epoch": 0.0920920920920921,
167
+ "grad_norm": 0.3364258408546448,
168
+ "learning_rate": 2.3000000000000003e-05,
169
+ "loss": 1.1005,
170
+ "step": 46
171
+ },
172
+ {
173
+ "epoch": 0.0960960960960961,
174
+ "grad_norm": 0.28330081701278687,
175
+ "learning_rate": 2.4e-05,
176
+ "loss": 1.0767,
177
+ "step": 48
178
+ },
179
+ {
180
+ "epoch": 0.1001001001001001,
181
+ "grad_norm": 0.3321577310562134,
182
+ "learning_rate": 2.5e-05,
183
+ "loss": 1.0742,
184
+ "step": 50
185
+ },
186
+ {
187
+ "epoch": 0.1001001001001001,
188
+ "eval_flock_task4_val_loss": 1.279232382774353,
189
+ "eval_flock_task4_val_runtime": 2.3219,
190
+ "eval_flock_task4_val_samples_per_second": 24.979,
191
+ "eval_flock_task4_val_steps_per_second": 24.979,
192
+ "step": 50
193
+ },
194
+ {
195
+ "epoch": 0.1041041041041041,
196
+ "grad_norm": 0.32319924235343933,
197
+ "learning_rate": 2.6000000000000002e-05,
198
+ "loss": 1.0973,
199
+ "step": 52
200
+ },
201
+ {
202
+ "epoch": 0.10810810810810811,
203
+ "grad_norm": 0.29113537073135376,
204
+ "learning_rate": 2.7000000000000002e-05,
205
+ "loss": 1.0901,
206
+ "step": 54
207
+ },
208
+ {
209
+ "epoch": 0.11211211211211211,
210
+ "grad_norm": 0.28851303458213806,
211
+ "learning_rate": 2.8000000000000003e-05,
212
+ "loss": 1.0673,
213
+ "step": 56
214
+ },
215
+ {
216
+ "epoch": 0.11611611611611612,
217
+ "grad_norm": 0.28908097743988037,
218
+ "learning_rate": 2.9e-05,
219
+ "loss": 1.0743,
220
+ "step": 58
221
+ },
222
+ {
223
+ "epoch": 0.12012012012012012,
224
+ "grad_norm": 0.35320213437080383,
225
+ "learning_rate": 3e-05,
226
+ "loss": 1.0607,
227
+ "step": 60
228
+ },
229
+ {
230
+ "epoch": 0.12412412412412413,
231
+ "grad_norm": 0.32404547929763794,
232
+ "learning_rate": 3.1e-05,
233
+ "loss": 1.1015,
234
+ "step": 62
235
+ },
236
+ {
237
+ "epoch": 0.12812812812812813,
238
+ "grad_norm": 0.2997118830680847,
239
+ "learning_rate": 3.2000000000000005e-05,
240
+ "loss": 1.0559,
241
+ "step": 64
242
+ },
243
+ {
244
+ "epoch": 0.13213213213213212,
245
+ "grad_norm": 0.3611145317554474,
246
+ "learning_rate": 3.3e-05,
247
+ "loss": 1.0911,
248
+ "step": 66
249
+ },
250
+ {
251
+ "epoch": 0.13613613613613615,
252
+ "grad_norm": 0.32707688212394714,
253
+ "learning_rate": 3.4000000000000007e-05,
254
+ "loss": 1.0275,
255
+ "step": 68
256
+ },
257
+ {
258
+ "epoch": 0.14014014014014015,
259
+ "grad_norm": 0.329102098941803,
260
+ "learning_rate": 3.5e-05,
261
+ "loss": 1.0566,
262
+ "step": 70
263
+ },
264
+ {
265
+ "epoch": 0.14414414414414414,
266
+ "grad_norm": 0.34922876954078674,
267
+ "learning_rate": 3.6e-05,
268
+ "loss": 1.0025,
269
+ "step": 72
270
+ },
271
+ {
272
+ "epoch": 0.14814814814814814,
273
+ "grad_norm": 0.359674334526062,
274
+ "learning_rate": 3.7e-05,
275
+ "loss": 1.0193,
276
+ "step": 74
277
+ },
278
+ {
279
+ "epoch": 0.15215215215215216,
280
+ "grad_norm": 0.34301552176475525,
281
+ "learning_rate": 3.8e-05,
282
+ "loss": 0.9956,
283
+ "step": 76
284
+ },
285
+ {
286
+ "epoch": 0.15615615615615616,
287
+ "grad_norm": 0.6669041514396667,
288
+ "learning_rate": 3.9000000000000006e-05,
289
+ "loss": 1.0541,
290
+ "step": 78
291
+ },
292
+ {
293
+ "epoch": 0.16016016016016016,
294
+ "grad_norm": 0.3566424548625946,
295
+ "learning_rate": 4e-05,
296
+ "loss": 0.9843,
297
+ "step": 80
298
+ },
299
+ {
300
+ "epoch": 0.16416416416416416,
301
+ "grad_norm": 0.35163360834121704,
302
+ "learning_rate": 4.1e-05,
303
+ "loss": 1.0346,
304
+ "step": 82
305
+ },
306
+ {
307
+ "epoch": 0.16816816816816818,
308
+ "grad_norm": 0.366845041513443,
309
+ "learning_rate": 4.2e-05,
310
+ "loss": 1.0351,
311
+ "step": 84
312
+ },
313
+ {
314
+ "epoch": 0.17217217217217218,
315
+ "grad_norm": 0.32546719908714294,
316
+ "learning_rate": 4.3e-05,
317
+ "loss": 0.9796,
318
+ "step": 86
319
+ },
320
+ {
321
+ "epoch": 0.17617617617617617,
322
+ "grad_norm": 0.3467786908149719,
323
+ "learning_rate": 4.4000000000000006e-05,
324
+ "loss": 1.0147,
325
+ "step": 88
326
+ },
327
+ {
328
+ "epoch": 0.18018018018018017,
329
+ "grad_norm": 0.32737115025520325,
330
+ "learning_rate": 4.5e-05,
331
+ "loss": 0.9844,
332
+ "step": 90
333
+ },
334
+ {
335
+ "epoch": 0.1841841841841842,
336
+ "grad_norm": 0.3682878911495209,
337
+ "learning_rate": 4.600000000000001e-05,
338
+ "loss": 1.0255,
339
+ "step": 92
340
+ },
341
+ {
342
+ "epoch": 0.1881881881881882,
343
+ "grad_norm": 0.31999263167381287,
344
+ "learning_rate": 4.7e-05,
345
+ "loss": 0.9682,
346
+ "step": 94
347
+ },
348
+ {
349
+ "epoch": 0.1921921921921922,
350
+ "grad_norm": 0.3726351857185364,
351
+ "learning_rate": 4.8e-05,
352
+ "loss": 1.0133,
353
+ "step": 96
354
+ },
355
+ {
356
+ "epoch": 0.1961961961961962,
357
+ "grad_norm": 0.3108680248260498,
358
+ "learning_rate": 4.9e-05,
359
+ "loss": 0.9993,
360
+ "step": 98
361
+ },
362
+ {
363
+ "epoch": 0.2002002002002002,
364
+ "grad_norm": 0.3874660134315491,
365
+ "learning_rate": 5e-05,
366
+ "loss": 1.0419,
367
+ "step": 100
368
+ },
369
+ {
370
+ "epoch": 0.2002002002002002,
371
+ "eval_flock_task4_val_loss": 1.2305223941802979,
372
+ "eval_flock_task4_val_runtime": 2.2833,
373
+ "eval_flock_task4_val_samples_per_second": 25.402,
374
+ "eval_flock_task4_val_steps_per_second": 25.402,
375
+ "step": 100
376
+ },
377
+ {
378
+ "epoch": 0.2042042042042042,
379
+ "grad_norm": 0.3987262547016144,
380
+ "learning_rate": 4.999938805089407e-05,
381
+ "loss": 1.0371,
382
+ "step": 102
383
+ },
384
+ {
385
+ "epoch": 0.2082082082082082,
386
+ "grad_norm": 0.37408047914505005,
387
+ "learning_rate": 4.999755223353482e-05,
388
+ "loss": 0.9826,
389
+ "step": 104
390
+ },
391
+ {
392
+ "epoch": 0.2122122122122122,
393
+ "grad_norm": 0.4258411228656769,
394
+ "learning_rate": 4.99944926377964e-05,
395
+ "loss": 0.9828,
396
+ "step": 106
397
+ },
398
+ {
399
+ "epoch": 0.21621621621621623,
400
+ "grad_norm": 0.3484812378883362,
401
+ "learning_rate": 4.9990209413464136e-05,
402
+ "loss": 0.9749,
403
+ "step": 108
404
+ },
405
+ {
406
+ "epoch": 0.22022022022022023,
407
+ "grad_norm": 0.32916268706321716,
408
+ "learning_rate": 4.9984702770227274e-05,
409
+ "loss": 1.0086,
410
+ "step": 110
411
+ },
412
+ {
413
+ "epoch": 0.22422422422422422,
414
+ "grad_norm": 0.38607460260391235,
415
+ "learning_rate": 4.997797297766864e-05,
416
+ "loss": 1.065,
417
+ "step": 112
418
+ },
419
+ {
420
+ "epoch": 0.22822822822822822,
421
+ "grad_norm": 0.3449179530143738,
422
+ "learning_rate": 4.997002036525148e-05,
423
+ "loss": 1.02,
424
+ "step": 114
425
+ },
426
+ {
427
+ "epoch": 0.23223223223223224,
428
+ "grad_norm": 0.3890361785888672,
429
+ "learning_rate": 4.9960845322303315e-05,
430
+ "loss": 1.015,
431
+ "step": 116
432
+ },
433
+ {
434
+ "epoch": 0.23623623623623624,
435
+ "grad_norm": 0.4259144961833954,
436
+ "learning_rate": 4.995044829799689e-05,
437
+ "loss": 0.9431,
438
+ "step": 118
439
+ },
440
+ {
441
+ "epoch": 0.24024024024024024,
442
+ "grad_norm": 0.3735407292842865,
443
+ "learning_rate": 4.993882980132819e-05,
444
+ "loss": 1.0119,
445
+ "step": 120
446
+ },
447
+ {
448
+ "epoch": 0.24424424424424424,
449
+ "grad_norm": 0.3555149734020233,
450
+ "learning_rate": 4.99259904010915e-05,
451
+ "loss": 0.9911,
452
+ "step": 122
453
+ },
454
+ {
455
+ "epoch": 0.24824824824824826,
456
+ "grad_norm": 0.3151463270187378,
457
+ "learning_rate": 4.9911930725851583e-05,
458
+ "loss": 0.9923,
459
+ "step": 124
460
+ },
461
+ {
462
+ "epoch": 0.25225225225225223,
463
+ "grad_norm": 0.4180292785167694,
464
+ "learning_rate": 4.989665146391289e-05,
465
+ "loss": 1.0518,
466
+ "step": 126
467
+ },
468
+ {
469
+ "epoch": 0.25625625625625625,
470
+ "grad_norm": 0.42882630228996277,
471
+ "learning_rate": 4.988015336328589e-05,
472
+ "loss": 0.9655,
473
+ "step": 128
474
+ },
475
+ {
476
+ "epoch": 0.2602602602602603,
477
+ "grad_norm": 0.3915731608867645,
478
+ "learning_rate": 4.986243723165039e-05,
479
+ "loss": 1.0272,
480
+ "step": 130
481
+ },
482
+ {
483
+ "epoch": 0.26426426426426425,
484
+ "grad_norm": 0.33155953884124756,
485
+ "learning_rate": 4.9843503936316095e-05,
486
+ "loss": 1.0169,
487
+ "step": 132
488
+ },
489
+ {
490
+ "epoch": 0.2682682682682683,
491
+ "grad_norm": 0.35307884216308594,
492
+ "learning_rate": 4.982335440418004e-05,
493
+ "loss": 0.9822,
494
+ "step": 134
495
+ },
496
+ {
497
+ "epoch": 0.2722722722722723,
498
+ "grad_norm": 0.35521459579467773,
499
+ "learning_rate": 4.980198962168128e-05,
500
+ "loss": 0.9748,
501
+ "step": 136
502
+ },
503
+ {
504
+ "epoch": 0.27627627627627627,
505
+ "grad_norm": 0.3592588007450104,
506
+ "learning_rate": 4.977941063475258e-05,
507
+ "loss": 0.9795,
508
+ "step": 138
509
+ },
510
+ {
511
+ "epoch": 0.2802802802802803,
512
+ "grad_norm": 0.36695194244384766,
513
+ "learning_rate": 4.97556185487692e-05,
514
+ "loss": 0.9808,
515
+ "step": 140
516
+ },
517
+ {
518
+ "epoch": 0.28428428428428426,
519
+ "grad_norm": 0.38413292169570923,
520
+ "learning_rate": 4.973061452849481e-05,
521
+ "loss": 0.9791,
522
+ "step": 142
523
+ },
524
+ {
525
+ "epoch": 0.2882882882882883,
526
+ "grad_norm": 0.36240625381469727,
527
+ "learning_rate": 4.970439979802445e-05,
528
+ "loss": 0.9871,
529
+ "step": 144
530
+ },
531
+ {
532
+ "epoch": 0.2922922922922923,
533
+ "grad_norm": 0.36706650257110596,
534
+ "learning_rate": 4.9676975640724565e-05,
535
+ "loss": 0.9562,
536
+ "step": 146
537
+ },
538
+ {
539
+ "epoch": 0.2962962962962963,
540
+ "grad_norm": 0.3560505509376526,
541
+ "learning_rate": 4.964834339917025e-05,
542
+ "loss": 1.0059,
543
+ "step": 148
544
+ },
545
+ {
546
+ "epoch": 0.3003003003003003,
547
+ "grad_norm": 0.3984704911708832,
548
+ "learning_rate": 4.961850447507948e-05,
549
+ "loss": 0.9505,
550
+ "step": 150
551
+ },
552
+ {
553
+ "epoch": 0.3003003003003003,
554
+ "eval_flock_task4_val_loss": 1.2094024419784546,
555
+ "eval_flock_task4_val_runtime": 2.2824,
556
+ "eval_flock_task4_val_samples_per_second": 25.412,
557
+ "eval_flock_task4_val_steps_per_second": 25.412,
558
+ "step": 150
559
+ },
560
+ {
561
+ "epoch": 0.30430430430430433,
562
+ "grad_norm": 0.35331350564956665,
563
+ "learning_rate": 4.958746032924448e-05,
564
+ "loss": 1.0262,
565
+ "step": 152
566
+ },
567
+ {
568
+ "epoch": 0.3083083083083083,
569
+ "grad_norm": 0.36896494030952454,
570
+ "learning_rate": 4.955521248146024e-05,
571
+ "loss": 0.9835,
572
+ "step": 154
573
+ },
574
+ {
575
+ "epoch": 0.3123123123123123,
576
+ "grad_norm": 0.3230743706226349,
577
+ "learning_rate": 4.952176251045008e-05,
578
+ "loss": 1.0156,
579
+ "step": 156
580
+ },
581
+ {
582
+ "epoch": 0.3163163163163163,
583
+ "grad_norm": 0.3876803517341614,
584
+ "learning_rate": 4.94871120537884e-05,
585
+ "loss": 0.963,
586
+ "step": 158
587
+ },
588
+ {
589
+ "epoch": 0.3203203203203203,
590
+ "grad_norm": 0.3794425129890442,
591
+ "learning_rate": 4.9451262807820466e-05,
592
+ "loss": 1.0087,
593
+ "step": 160
594
+ },
595
+ {
596
+ "epoch": 0.32432432432432434,
597
+ "grad_norm": 0.31706008315086365,
598
+ "learning_rate": 4.941421652757941e-05,
599
+ "loss": 0.9365,
600
+ "step": 162
601
+ },
602
+ {
603
+ "epoch": 0.3283283283283283,
604
+ "grad_norm": 0.35730335116386414,
605
+ "learning_rate": 4.937597502670027e-05,
606
+ "loss": 1.0208,
607
+ "step": 164
608
+ },
609
+ {
610
+ "epoch": 0.33233233233233234,
611
+ "grad_norm": 0.3496227562427521,
612
+ "learning_rate": 4.933654017733123e-05,
613
+ "loss": 1.0172,
614
+ "step": 166
615
+ },
616
+ {
617
+ "epoch": 0.33633633633633636,
618
+ "grad_norm": 0.3538665175437927,
619
+ "learning_rate": 4.929591391004196e-05,
620
+ "loss": 0.9329,
621
+ "step": 168
622
+ },
623
+ {
624
+ "epoch": 0.34034034034034033,
625
+ "grad_norm": 0.3327396512031555,
626
+ "learning_rate": 4.925409821372908e-05,
627
+ "loss": 0.9326,
628
+ "step": 170
629
+ },
630
+ {
631
+ "epoch": 0.34434434434434436,
632
+ "grad_norm": 0.3335298001766205,
633
+ "learning_rate": 4.921109513551885e-05,
634
+ "loss": 1.0233,
635
+ "step": 172
636
+ },
637
+ {
638
+ "epoch": 0.3483483483483483,
639
+ "grad_norm": 0.38584664463996887,
640
+ "learning_rate": 4.9166906780666874e-05,
641
+ "loss": 0.9675,
642
+ "step": 174
643
+ },
644
+ {
645
+ "epoch": 0.35235235235235235,
646
+ "grad_norm": 0.30182167887687683,
647
+ "learning_rate": 4.912153531245511e-05,
648
+ "loss": 0.8978,
649
+ "step": 176
650
+ },
651
+ {
652
+ "epoch": 0.3563563563563564,
653
+ "grad_norm": 0.3465532958507538,
654
+ "learning_rate": 4.907498295208589e-05,
655
+ "loss": 0.9589,
656
+ "step": 178
657
+ },
658
+ {
659
+ "epoch": 0.36036036036036034,
660
+ "grad_norm": 0.3306107223033905,
661
+ "learning_rate": 4.9027251978573244e-05,
662
+ "loss": 0.9715,
663
+ "step": 180
664
+ },
665
+ {
666
+ "epoch": 0.36436436436436437,
667
+ "grad_norm": 0.33348309993743896,
668
+ "learning_rate": 4.8978344728631306e-05,
669
+ "loss": 0.9542,
670
+ "step": 182
671
+ },
672
+ {
673
+ "epoch": 0.3683683683683684,
674
+ "grad_norm": 0.32247722148895264,
675
+ "learning_rate": 4.89282635965599e-05,
676
+ "loss": 0.937,
677
+ "step": 184
678
+ },
679
+ {
680
+ "epoch": 0.37237237237237236,
681
+ "grad_norm": 0.3330734074115753,
682
+ "learning_rate": 4.887701103412734e-05,
683
+ "loss": 0.9882,
684
+ "step": 186
685
+ },
686
+ {
687
+ "epoch": 0.3763763763763764,
688
+ "grad_norm": 0.3942042887210846,
689
+ "learning_rate": 4.8824589550450415e-05,
690
+ "loss": 1.005,
691
+ "step": 188
692
+ },
693
+ {
694
+ "epoch": 0.38038038038038036,
695
+ "grad_norm": 0.3293454349040985,
696
+ "learning_rate": 4.8771001711871534e-05,
697
+ "loss": 0.9591,
698
+ "step": 190
699
+ },
700
+ {
701
+ "epoch": 0.3843843843843844,
702
+ "grad_norm": 0.31077539920806885,
703
+ "learning_rate": 4.8716250141833075e-05,
704
+ "loss": 0.9016,
705
+ "step": 192
706
+ },
707
+ {
708
+ "epoch": 0.3883883883883884,
709
+ "grad_norm": 0.355177104473114,
710
+ "learning_rate": 4.8660337520749e-05,
711
+ "loss": 0.9712,
712
+ "step": 194
713
+ },
714
+ {
715
+ "epoch": 0.3923923923923924,
716
+ "grad_norm": 0.3732739984989166,
717
+ "learning_rate": 4.860326658587358e-05,
718
+ "loss": 0.9971,
719
+ "step": 196
720
+ },
721
+ {
722
+ "epoch": 0.3963963963963964,
723
+ "grad_norm": 0.32691335678100586,
724
+ "learning_rate": 4.8545040131167415e-05,
725
+ "loss": 0.9658,
726
+ "step": 198
727
+ },
728
+ {
729
+ "epoch": 0.4004004004004004,
730
+ "grad_norm": 0.31721362471580505,
731
+ "learning_rate": 4.848566100716066e-05,
732
+ "loss": 0.9486,
733
+ "step": 200
734
+ },
735
+ {
736
+ "epoch": 0.4004004004004004,
737
+ "eval_flock_task4_val_loss": 1.200321078300476,
738
+ "eval_flock_task4_val_runtime": 2.2838,
739
+ "eval_flock_task4_val_samples_per_second": 25.396,
740
+ "eval_flock_task4_val_steps_per_second": 25.396,
741
+ "step": 200
742
+ },
743
+ {
744
+ "epoch": 0.4044044044044044,
745
+ "grad_norm": 0.31772664189338684,
746
+ "learning_rate": 4.8425132120813474e-05,
747
+ "loss": 0.9132,
748
+ "step": 202
749
+ },
750
+ {
751
+ "epoch": 0.4084084084084084,
752
+ "grad_norm": 0.33230283856391907,
753
+ "learning_rate": 4.8363456435373686e-05,
754
+ "loss": 0.932,
755
+ "step": 204
756
+ },
757
+ {
758
+ "epoch": 0.4124124124124124,
759
+ "grad_norm": 0.34045132994651794,
760
+ "learning_rate": 4.830063697023173e-05,
761
+ "loss": 0.958,
762
+ "step": 206
763
+ },
764
+ {
765
+ "epoch": 0.4164164164164164,
766
+ "grad_norm": 0.3456396162509918,
767
+ "learning_rate": 4.8236676800772845e-05,
768
+ "loss": 0.9708,
769
+ "step": 208
770
+ },
771
+ {
772
+ "epoch": 0.42042042042042044,
773
+ "grad_norm": 0.31616365909576416,
774
+ "learning_rate": 4.817157905822652e-05,
775
+ "loss": 0.933,
776
+ "step": 210
777
+ },
778
+ {
779
+ "epoch": 0.4244244244244244,
780
+ "grad_norm": 0.3686939477920532,
781
+ "learning_rate": 4.8105346929513195e-05,
782
+ "loss": 0.937,
783
+ "step": 212
784
+ },
785
+ {
786
+ "epoch": 0.42842842842842843,
787
+ "grad_norm": 0.34076109528541565,
788
+ "learning_rate": 4.803798365708821e-05,
789
+ "loss": 0.929,
790
+ "step": 214
791
+ },
792
+ {
793
+ "epoch": 0.43243243243243246,
794
+ "grad_norm": 0.3262769877910614,
795
+ "learning_rate": 4.796949253878311e-05,
796
+ "loss": 1.0037,
797
+ "step": 216
798
+ },
799
+ {
800
+ "epoch": 0.4364364364364364,
801
+ "grad_norm": 0.32373276352882385,
802
+ "learning_rate": 4.789987692764419e-05,
803
+ "loss": 0.9531,
804
+ "step": 218
805
+ },
806
+ {
807
+ "epoch": 0.44044044044044045,
808
+ "grad_norm": 0.33934321999549866,
809
+ "learning_rate": 4.7829140231768335e-05,
810
+ "loss": 1.0434,
811
+ "step": 220
812
+ },
813
+ {
814
+ "epoch": 0.4444444444444444,
815
+ "grad_norm": 0.3485037386417389,
816
+ "learning_rate": 4.775728591413616e-05,
817
+ "loss": 0.9829,
818
+ "step": 222
819
+ },
820
+ {
821
+ "epoch": 0.44844844844844844,
822
+ "grad_norm": 0.32307952642440796,
823
+ "learning_rate": 4.768431749244251e-05,
824
+ "loss": 0.9767,
825
+ "step": 224
826
+ },
827
+ {
828
+ "epoch": 0.45245245245245247,
829
+ "grad_norm": 0.340285986661911,
830
+ "learning_rate": 4.76102385389242e-05,
831
+ "loss": 0.9601,
832
+ "step": 226
833
+ },
834
+ {
835
+ "epoch": 0.45645645645645644,
836
+ "grad_norm": 0.32007983326911926,
837
+ "learning_rate": 4.75350526801852e-05,
838
+ "loss": 0.9489,
839
+ "step": 228
840
+ },
841
+ {
842
+ "epoch": 0.46046046046046046,
843
+ "grad_norm": 0.3099637031555176,
844
+ "learning_rate": 4.7458763597019015e-05,
845
+ "loss": 0.9807,
846
+ "step": 230
847
+ },
848
+ {
849
+ "epoch": 0.4644644644644645,
850
+ "grad_norm": 0.3507792353630066,
851
+ "learning_rate": 4.7381375024228556e-05,
852
+ "loss": 0.9714,
853
+ "step": 232
854
+ },
855
+ {
856
+ "epoch": 0.46846846846846846,
857
+ "grad_norm": 0.34930968284606934,
858
+ "learning_rate": 4.7302890750443256e-05,
859
+ "loss": 0.9243,
860
+ "step": 234
861
+ },
862
+ {
863
+ "epoch": 0.4724724724724725,
864
+ "grad_norm": 0.34382864832878113,
865
+ "learning_rate": 4.7223314617933605e-05,
866
+ "loss": 0.9245,
867
+ "step": 236
868
+ },
869
+ {
870
+ "epoch": 0.47647647647647645,
871
+ "grad_norm": 0.3135361075401306,
872
+ "learning_rate": 4.714265052242306e-05,
873
+ "loss": 0.9382,
874
+ "step": 238
875
+ },
876
+ {
877
+ "epoch": 0.4804804804804805,
878
+ "grad_norm": 0.3600904047489166,
879
+ "learning_rate": 4.7060902412897304e-05,
880
+ "loss": 0.9611,
881
+ "step": 240
882
+ },
883
+ {
884
+ "epoch": 0.4844844844844845,
885
+ "grad_norm": 0.32109400629997253,
886
+ "learning_rate": 4.697807429141094e-05,
887
+ "loss": 0.9217,
888
+ "step": 242
889
+ },
890
+ {
891
+ "epoch": 0.48848848848848847,
892
+ "grad_norm": 0.3754291534423828,
893
+ "learning_rate": 4.689417021289157e-05,
894
+ "loss": 1.0129,
895
+ "step": 244
896
+ },
897
+ {
898
+ "epoch": 0.4924924924924925,
899
+ "grad_norm": 0.3417948782444,
900
+ "learning_rate": 4.6809194284941236e-05,
901
+ "loss": 0.9551,
902
+ "step": 246
903
+ },
904
+ {
905
+ "epoch": 0.4964964964964965,
906
+ "grad_norm": 0.3459557294845581,
907
+ "learning_rate": 4.672315066763542e-05,
908
+ "loss": 0.9363,
909
+ "step": 248
910
+ },
911
+ {
912
+ "epoch": 0.5005005005005005,
913
+ "grad_norm": 0.3685155212879181,
914
+ "learning_rate": 4.6636043573319275e-05,
915
+ "loss": 0.9385,
916
+ "step": 250
917
+ },
918
+ {
919
+ "epoch": 0.5005005005005005,
920
+ "eval_flock_task4_val_loss": 1.1836485862731934,
921
+ "eval_flock_task4_val_runtime": 2.2789,
922
+ "eval_flock_task4_val_samples_per_second": 25.451,
923
+ "eval_flock_task4_val_steps_per_second": 25.451,
924
+ "step": 250
925
+ },
926
+ {
927
+ "epoch": 0.5045045045045045,
928
+ "grad_norm": 0.3467947542667389,
929
+ "learning_rate": 4.65478772664015e-05,
930
+ "loss": 0.9636,
931
+ "step": 252
932
+ },
933
+ {
934
+ "epoch": 0.5085085085085085,
935
+ "grad_norm": 0.340094655752182,
936
+ "learning_rate": 4.6458656063145475e-05,
937
+ "loss": 0.9531,
938
+ "step": 254
939
+ },
940
+ {
941
+ "epoch": 0.5125125125125125,
942
+ "grad_norm": 0.29998838901519775,
943
+ "learning_rate": 4.6368384331458085e-05,
944
+ "loss": 0.9295,
945
+ "step": 256
946
+ },
947
+ {
948
+ "epoch": 0.5165165165165165,
949
+ "grad_norm": 0.3876248002052307,
950
+ "learning_rate": 4.627706649067575e-05,
951
+ "loss": 0.8926,
952
+ "step": 258
953
+ },
954
+ {
955
+ "epoch": 0.5205205205205206,
956
+ "grad_norm": 0.3211461007595062,
957
+ "learning_rate": 4.618470701134815e-05,
958
+ "loss": 0.8939,
959
+ "step": 260
960
+ },
961
+ {
962
+ "epoch": 0.5245245245245245,
963
+ "grad_norm": 0.31540125608444214,
964
+ "learning_rate": 4.609131041501935e-05,
965
+ "loss": 0.9418,
966
+ "step": 262
967
+ },
968
+ {
969
+ "epoch": 0.5285285285285285,
970
+ "grad_norm": 0.3534470200538635,
971
+ "learning_rate": 4.5996881274006446e-05,
972
+ "loss": 0.9571,
973
+ "step": 264
974
+ },
975
+ {
976
+ "epoch": 0.5325325325325325,
977
+ "grad_norm": 0.369412362575531,
978
+ "learning_rate": 4.5901424211175715e-05,
979
+ "loss": 0.9212,
980
+ "step": 266
981
+ },
982
+ {
983
+ "epoch": 0.5365365365365365,
984
+ "grad_norm": 0.3699535131454468,
985
+ "learning_rate": 4.580494389971628e-05,
986
+ "loss": 0.9377,
987
+ "step": 268
988
+ },
989
+ {
990
+ "epoch": 0.5405405405405406,
991
+ "grad_norm": 0.33457526564598083,
992
+ "learning_rate": 4.570744506291138e-05,
993
+ "loss": 0.9492,
994
+ "step": 270
995
+ },
996
+ {
997
+ "epoch": 0.5445445445445446,
998
+ "grad_norm": 0.37723392248153687,
999
+ "learning_rate": 4.56089324739071e-05,
1000
+ "loss": 0.9433,
1001
+ "step": 272
1002
+ },
1003
+ {
1004
+ "epoch": 0.5485485485485485,
1005
+ "grad_norm": 0.3375968039035797,
1006
+ "learning_rate": 4.5509410955478686e-05,
1007
+ "loss": 0.9699,
1008
+ "step": 274
1009
+ },
1010
+ {
1011
+ "epoch": 0.5525525525525525,
1012
+ "grad_norm": 0.36604395508766174,
1013
+ "learning_rate": 4.5408885379794494e-05,
1014
+ "loss": 0.8939,
1015
+ "step": 276
1016
+ },
1017
+ {
1018
+ "epoch": 0.5565565565565566,
1019
+ "grad_norm": 0.33874592185020447,
1020
+ "learning_rate": 4.5307360668177404e-05,
1021
+ "loss": 0.9053,
1022
+ "step": 278
1023
+ },
1024
+ {
1025
+ "epoch": 0.5605605605605606,
1026
+ "grad_norm": 0.3532886505126953,
1027
+ "learning_rate": 4.520484179086394e-05,
1028
+ "loss": 0.9273,
1029
+ "step": 280
1030
+ },
1031
+ {
1032
+ "epoch": 0.5645645645645646,
1033
+ "grad_norm": 0.3623044788837433,
1034
+ "learning_rate": 4.510133376676092e-05,
1035
+ "loss": 0.9356,
1036
+ "step": 282
1037
+ },
1038
+ {
1039
+ "epoch": 0.5685685685685685,
1040
+ "grad_norm": 0.31736573576927185,
1041
+ "learning_rate": 4.499684166319978e-05,
1042
+ "loss": 0.9171,
1043
+ "step": 284
1044
+ },
1045
+ {
1046
+ "epoch": 0.5725725725725725,
1047
+ "grad_norm": 0.335746705532074,
1048
+ "learning_rate": 4.489137059568847e-05,
1049
+ "loss": 0.9482,
1050
+ "step": 286
1051
+ },
1052
+ {
1053
+ "epoch": 0.5765765765765766,
1054
+ "grad_norm": 0.37591829895973206,
1055
+ "learning_rate": 4.478492572766102e-05,
1056
+ "loss": 0.9614,
1057
+ "step": 288
1058
+ },
1059
+ {
1060
+ "epoch": 0.5805805805805806,
1061
+ "grad_norm": 0.32530349493026733,
1062
+ "learning_rate": 4.4677512270224774e-05,
1063
+ "loss": 0.9871,
1064
+ "step": 290
1065
+ },
1066
+ {
1067
+ "epoch": 0.5845845845845846,
1068
+ "grad_norm": 0.36305058002471924,
1069
+ "learning_rate": 4.456913548190527e-05,
1070
+ "loss": 0.9783,
1071
+ "step": 292
1072
+ },
1073
+ {
1074
+ "epoch": 0.5885885885885885,
1075
+ "grad_norm": 0.34992191195487976,
1076
+ "learning_rate": 4.445980066838882e-05,
1077
+ "loss": 0.9204,
1078
+ "step": 294
1079
+ },
1080
+ {
1081
+ "epoch": 0.5925925925925926,
1082
+ "grad_norm": 0.357051819562912,
1083
+ "learning_rate": 4.4349513182262715e-05,
1084
+ "loss": 0.9342,
1085
+ "step": 296
1086
+ },
1087
+ {
1088
+ "epoch": 0.5965965965965966,
1089
+ "grad_norm": 0.6614818572998047,
1090
+ "learning_rate": 4.423827842275325e-05,
1091
+ "loss": 0.9105,
1092
+ "step": 298
1093
+ },
1094
+ {
1095
+ "epoch": 0.6006006006006006,
1096
+ "grad_norm": 0.3560963273048401,
1097
+ "learning_rate": 4.4126101835461346e-05,
1098
+ "loss": 0.9392,
1099
+ "step": 300
1100
+ },
1101
+ {
1102
+ "epoch": 0.6006006006006006,
1103
+ "eval_flock_task4_val_loss": 1.1696926355361938,
1104
+ "eval_flock_task4_val_runtime": 2.2897,
1105
+ "eval_flock_task4_val_samples_per_second": 25.331,
1106
+ "eval_flock_task4_val_steps_per_second": 25.331,
1107
+ "step": 300
1108
+ },
1109
+ {
1110
+ "epoch": 0.6046046046046046,
1111
+ "grad_norm": 0.35408785939216614,
1112
+ "learning_rate": 4.4012988912095995e-05,
1113
+ "loss": 0.9848,
1114
+ "step": 302
1115
+ },
1116
+ {
1117
+ "epoch": 0.6086086086086087,
1118
+ "grad_norm": 0.3559267520904541,
1119
+ "learning_rate": 4.3898945190205386e-05,
1120
+ "loss": 0.9635,
1121
+ "step": 304
1122
+ },
1123
+ {
1124
+ "epoch": 0.6126126126126126,
1125
+ "grad_norm": 0.3476458489894867,
1126
+ "learning_rate": 4.3783976252905804e-05,
1127
+ "loss": 0.9699,
1128
+ "step": 306
1129
+ },
1130
+ {
1131
+ "epoch": 0.6166166166166166,
1132
+ "grad_norm": 0.3224807381629944,
1133
+ "learning_rate": 4.3668087728608316e-05,
1134
+ "loss": 0.9391,
1135
+ "step": 308
1136
+ },
1137
+ {
1138
+ "epoch": 0.6206206206206206,
1139
+ "grad_norm": 0.3327246606349945,
1140
+ "learning_rate": 4.355128529074323e-05,
1141
+ "loss": 0.9049,
1142
+ "step": 310
1143
+ },
1144
+ {
1145
+ "epoch": 0.6246246246246246,
1146
+ "grad_norm": 0.3456214666366577,
1147
+ "learning_rate": 4.343357465748235e-05,
1148
+ "loss": 0.9336,
1149
+ "step": 312
1150
+ },
1151
+ {
1152
+ "epoch": 0.6286286286286287,
1153
+ "grad_norm": 0.36309632658958435,
1154
+ "learning_rate": 4.331496159145901e-05,
1155
+ "loss": 0.9568,
1156
+ "step": 314
1157
+ },
1158
+ {
1159
+ "epoch": 0.6326326326326326,
1160
+ "grad_norm": 0.31426164507865906,
1161
+ "learning_rate": 4.3195451899485994e-05,
1162
+ "loss": 0.9634,
1163
+ "step": 316
1164
+ },
1165
+ {
1166
+ "epoch": 0.6366366366366366,
1167
+ "grad_norm": 0.29084381461143494,
1168
+ "learning_rate": 4.307505143227122e-05,
1169
+ "loss": 0.9351,
1170
+ "step": 318
1171
+ },
1172
+ {
1173
+ "epoch": 0.6406406406406406,
1174
+ "grad_norm": 0.3159138560295105,
1175
+ "learning_rate": 4.295376608413137e-05,
1176
+ "loss": 0.9604,
1177
+ "step": 320
1178
+ },
1179
+ {
1180
+ "epoch": 0.6446446446446447,
1181
+ "grad_norm": 0.33817973732948303,
1182
+ "learning_rate": 4.2831601792703245e-05,
1183
+ "loss": 0.9504,
1184
+ "step": 322
1185
+ },
1186
+ {
1187
+ "epoch": 0.6486486486486487,
1188
+ "grad_norm": 0.3421194553375244,
1189
+ "learning_rate": 4.270856453865318e-05,
1190
+ "loss": 0.9784,
1191
+ "step": 324
1192
+ },
1193
+ {
1194
+ "epoch": 0.6526526526526526,
1195
+ "grad_norm": 0.3762097656726837,
1196
+ "learning_rate": 4.258466034538417e-05,
1197
+ "loss": 0.9177,
1198
+ "step": 326
1199
+ },
1200
+ {
1201
+ "epoch": 0.6566566566566566,
1202
+ "grad_norm": 0.3637877106666565,
1203
+ "learning_rate": 4.245989527874107e-05,
1204
+ "loss": 0.9737,
1205
+ "step": 328
1206
+ },
1207
+ {
1208
+ "epoch": 0.6606606606606606,
1209
+ "grad_norm": 0.399688184261322,
1210
+ "learning_rate": 4.233427544671351e-05,
1211
+ "loss": 0.9587,
1212
+ "step": 330
1213
+ },
1214
+ {
1215
+ "epoch": 0.6646646646646647,
1216
+ "grad_norm": 0.3639969527721405,
1217
+ "learning_rate": 4.2207806999137035e-05,
1218
+ "loss": 0.9308,
1219
+ "step": 332
1220
+ },
1221
+ {
1222
+ "epoch": 0.6686686686686687,
1223
+ "grad_norm": 0.390143483877182,
1224
+ "learning_rate": 4.208049612739192e-05,
1225
+ "loss": 0.9002,
1226
+ "step": 334
1227
+ },
1228
+ {
1229
+ "epoch": 0.6726726726726727,
1230
+ "grad_norm": 0.36150315403938293,
1231
+ "learning_rate": 4.1952349064100074e-05,
1232
+ "loss": 0.9214,
1233
+ "step": 336
1234
+ },
1235
+ {
1236
+ "epoch": 0.6766766766766766,
1237
+ "grad_norm": 0.36743301153182983,
1238
+ "learning_rate": 4.1823372082819975e-05,
1239
+ "loss": 0.9446,
1240
+ "step": 338
1241
+ },
1242
+ {
1243
+ "epoch": 0.6806806806806807,
1244
+ "grad_norm": 0.34222760796546936,
1245
+ "learning_rate": 4.1693571497739495e-05,
1246
+ "loss": 0.9083,
1247
+ "step": 340
1248
+ },
1249
+ {
1250
+ "epoch": 0.6846846846846847,
1251
+ "grad_norm": 0.31091299653053284,
1252
+ "learning_rate": 4.156295366336679e-05,
1253
+ "loss": 0.9626,
1254
+ "step": 342
1255
+ },
1256
+ {
1257
+ "epoch": 0.6886886886886887,
1258
+ "grad_norm": 0.3398517966270447,
1259
+ "learning_rate": 4.143152497421922e-05,
1260
+ "loss": 0.8785,
1261
+ "step": 344
1262
+ },
1263
+ {
1264
+ "epoch": 0.6926926926926927,
1265
+ "grad_norm": 0.3354012370109558,
1266
+ "learning_rate": 4.129929186451028e-05,
1267
+ "loss": 0.9608,
1268
+ "step": 346
1269
+ },
1270
+ {
1271
+ "epoch": 0.6966966966966966,
1272
+ "grad_norm": 0.3858669102191925,
1273
+ "learning_rate": 4.1166260807834644e-05,
1274
+ "loss": 0.9665,
1275
+ "step": 348
1276
+ },
1277
+ {
1278
+ "epoch": 0.7007007007007007,
1279
+ "grad_norm": 0.35795554518699646,
1280
+ "learning_rate": 4.103243831685121e-05,
1281
+ "loss": 0.9277,
1282
+ "step": 350
1283
+ },
1284
+ {
1285
+ "epoch": 0.7007007007007007,
1286
+ "eval_flock_task4_val_loss": 1.1536976099014282,
1287
+ "eval_flock_task4_val_runtime": 2.2912,
1288
+ "eval_flock_task4_val_samples_per_second": 25.314,
1289
+ "eval_flock_task4_val_steps_per_second": 25.314,
1290
+ "step": 350
1291
+ },
1292
+ {
1293
+ "epoch": 0.7047047047047047,
1294
+ "grad_norm": 0.3871535062789917,
1295
+ "learning_rate": 4.0897830942964255e-05,
1296
+ "loss": 0.9379,
1297
+ "step": 352
1298
+ },
1299
+ {
1300
+ "epoch": 0.7087087087087087,
1301
+ "grad_norm": 0.3559763431549072,
1302
+ "learning_rate": 4.076244527600276e-05,
1303
+ "loss": 0.9377,
1304
+ "step": 354
1305
+ },
1306
+ {
1307
+ "epoch": 0.7127127127127127,
1308
+ "grad_norm": 0.3114367425441742,
1309
+ "learning_rate": 4.0626287943897764e-05,
1310
+ "loss": 0.8784,
1311
+ "step": 356
1312
+ },
1313
+ {
1314
+ "epoch": 0.7167167167167167,
1315
+ "grad_norm": 0.3529565930366516,
1316
+ "learning_rate": 4.048936561235786e-05,
1317
+ "loss": 0.953,
1318
+ "step": 358
1319
+ },
1320
+ {
1321
+ "epoch": 0.7207207207207207,
1322
+ "grad_norm": 0.33330368995666504,
1323
+ "learning_rate": 4.035168498454292e-05,
1324
+ "loss": 0.9587,
1325
+ "step": 360
1326
+ },
1327
+ {
1328
+ "epoch": 0.7247247247247247,
1329
+ "grad_norm": 0.418038934469223,
1330
+ "learning_rate": 4.021325280073592e-05,
1331
+ "loss": 0.9108,
1332
+ "step": 362
1333
+ },
1334
+ {
1335
+ "epoch": 0.7287287287287287,
1336
+ "grad_norm": 0.373203307390213,
1337
+ "learning_rate": 4.007407583801295e-05,
1338
+ "loss": 0.9772,
1339
+ "step": 364
1340
+ },
1341
+ {
1342
+ "epoch": 0.7327327327327328,
1343
+ "grad_norm": 0.31042730808258057,
1344
+ "learning_rate": 3.9934160909911434e-05,
1345
+ "loss": 0.9174,
1346
+ "step": 366
1347
+ },
1348
+ {
1349
+ "epoch": 0.7367367367367368,
1350
+ "grad_norm": 0.3332262635231018,
1351
+ "learning_rate": 3.979351486609658e-05,
1352
+ "loss": 0.9127,
1353
+ "step": 368
1354
+ },
1355
+ {
1356
+ "epoch": 0.7407407407407407,
1357
+ "grad_norm": 0.32328566908836365,
1358
+ "learning_rate": 3.965214459202607e-05,
1359
+ "loss": 0.9197,
1360
+ "step": 370
1361
+ },
1362
+ {
1363
+ "epoch": 0.7447447447447447,
1364
+ "grad_norm": 0.3616783022880554,
1365
+ "learning_rate": 3.951005700861291e-05,
1366
+ "loss": 0.9017,
1367
+ "step": 372
1368
+ },
1369
+ {
1370
+ "epoch": 0.7487487487487487,
1371
+ "grad_norm": 0.4132612645626068,
1372
+ "learning_rate": 3.936725907188668e-05,
1373
+ "loss": 0.9353,
1374
+ "step": 374
1375
+ },
1376
+ {
1377
+ "epoch": 0.7527527527527528,
1378
+ "grad_norm": 0.34235623478889465,
1379
+ "learning_rate": 3.9223757772652956e-05,
1380
+ "loss": 0.9438,
1381
+ "step": 376
1382
+ },
1383
+ {
1384
+ "epoch": 0.7567567567567568,
1385
+ "grad_norm": 0.3544083833694458,
1386
+ "learning_rate": 3.9079560136151075e-05,
1387
+ "loss": 0.9663,
1388
+ "step": 378
1389
+ },
1390
+ {
1391
+ "epoch": 0.7607607607607607,
1392
+ "grad_norm": 0.37442663311958313,
1393
+ "learning_rate": 3.8934673221710215e-05,
1394
+ "loss": 0.9043,
1395
+ "step": 380
1396
+ },
1397
+ {
1398
+ "epoch": 0.7647647647647647,
1399
+ "grad_norm": 0.38071951270103455,
1400
+ "learning_rate": 3.878910412240381e-05,
1401
+ "loss": 0.9556,
1402
+ "step": 382
1403
+ },
1404
+ {
1405
+ "epoch": 0.7687687687687688,
1406
+ "grad_norm": 0.33478865027427673,
1407
+ "learning_rate": 3.864285996470226e-05,
1408
+ "loss": 0.8984,
1409
+ "step": 384
1410
+ },
1411
+ {
1412
+ "epoch": 0.7727727727727728,
1413
+ "grad_norm": 0.37500250339508057,
1414
+ "learning_rate": 3.8495947908124094e-05,
1415
+ "loss": 0.8947,
1416
+ "step": 386
1417
+ },
1418
+ {
1419
+ "epoch": 0.7767767767767768,
1420
+ "grad_norm": 0.3144890069961548,
1421
+ "learning_rate": 3.834837514488544e-05,
1422
+ "loss": 0.928,
1423
+ "step": 388
1424
+ },
1425
+ {
1426
+ "epoch": 0.7807807807807807,
1427
+ "grad_norm": 0.3349425494670868,
1428
+ "learning_rate": 3.8200148899547945e-05,
1429
+ "loss": 0.9221,
1430
+ "step": 390
1431
+ },
1432
+ {
1433
+ "epoch": 0.7847847847847848,
1434
+ "grad_norm": 0.4010365605354309,
1435
+ "learning_rate": 3.805127642866507e-05,
1436
+ "loss": 0.9071,
1437
+ "step": 392
1438
+ },
1439
+ {
1440
+ "epoch": 0.7887887887887888,
1441
+ "grad_norm": 0.4623183310031891,
1442
+ "learning_rate": 3.790176502042686e-05,
1443
+ "loss": 0.9169,
1444
+ "step": 394
1445
+ },
1446
+ {
1447
+ "epoch": 0.7927927927927928,
1448
+ "grad_norm": 0.35621941089630127,
1449
+ "learning_rate": 3.775162199430312e-05,
1450
+ "loss": 0.928,
1451
+ "step": 396
1452
+ },
1453
+ {
1454
+ "epoch": 0.7967967967967968,
1455
+ "grad_norm": 0.33506807684898376,
1456
+ "learning_rate": 3.76008547006851e-05,
1457
+ "loss": 0.8739,
1458
+ "step": 398
1459
+ },
1460
+ {
1461
+ "epoch": 0.8008008008008008,
1462
+ "grad_norm": 0.4462102949619293,
1463
+ "learning_rate": 3.744947052052562e-05,
1464
+ "loss": 0.8549,
1465
+ "step": 400
1466
+ },
1467
+ {
1468
+ "epoch": 0.8008008008008008,
1469
+ "eval_flock_task4_val_loss": 1.1560972929000854,
1470
+ "eval_flock_task4_val_runtime": 2.3054,
1471
+ "eval_flock_task4_val_samples_per_second": 25.159,
1472
+ "eval_flock_task4_val_steps_per_second": 25.159,
1473
+ "step": 400
1474
+ },
1475
+ {
1476
+ "epoch": 0.8048048048048048,
1477
+ "grad_norm": 0.39696791768074036,
1478
+ "learning_rate": 3.72974768649778e-05,
1479
+ "loss": 0.9826,
1480
+ "step": 402
1481
+ },
1482
+ {
1483
+ "epoch": 0.8088088088088088,
1484
+ "grad_norm": 0.33046942949295044,
1485
+ "learning_rate": 3.7144881175032174e-05,
1486
+ "loss": 0.9925,
1487
+ "step": 404
1488
+ },
1489
+ {
1490
+ "epoch": 0.8128128128128128,
1491
+ "grad_norm": 0.40008458495140076,
1492
+ "learning_rate": 3.69916909211524e-05,
1493
+ "loss": 0.8818,
1494
+ "step": 406
1495
+ },
1496
+ {
1497
+ "epoch": 0.8168168168168168,
1498
+ "grad_norm": 0.3182609975337982,
1499
+ "learning_rate": 3.683791360290961e-05,
1500
+ "loss": 0.9055,
1501
+ "step": 408
1502
+ },
1503
+ {
1504
+ "epoch": 0.8208208208208209,
1505
+ "grad_norm": 0.3375478684902191,
1506
+ "learning_rate": 3.6683556748615195e-05,
1507
+ "loss": 0.9267,
1508
+ "step": 410
1509
+ },
1510
+ {
1511
+ "epoch": 0.8248248248248248,
1512
+ "grad_norm": 0.35459277033805847,
1513
+ "learning_rate": 3.6528627914952266e-05,
1514
+ "loss": 0.954,
1515
+ "step": 412
1516
+ },
1517
+ {
1518
+ "epoch": 0.8288288288288288,
1519
+ "grad_norm": 0.31690555810928345,
1520
+ "learning_rate": 3.637313468660572e-05,
1521
+ "loss": 0.9145,
1522
+ "step": 414
1523
+ },
1524
+ {
1525
+ "epoch": 0.8328328328328328,
1526
+ "grad_norm": 0.35816216468811035,
1527
+ "learning_rate": 3.6217084675890935e-05,
1528
+ "loss": 0.879,
1529
+ "step": 416
1530
+ },
1531
+ {
1532
+ "epoch": 0.8368368368368369,
1533
+ "grad_norm": 0.36077073216438293,
1534
+ "learning_rate": 3.6060485522381065e-05,
1535
+ "loss": 0.9376,
1536
+ "step": 418
1537
+ },
1538
+ {
1539
+ "epoch": 0.8408408408408409,
1540
+ "grad_norm": 0.35410434007644653,
1541
+ "learning_rate": 3.590334489253306e-05,
1542
+ "loss": 0.9169,
1543
+ "step": 420
1544
+ },
1545
+ {
1546
+ "epoch": 0.8448448448448449,
1547
+ "grad_norm": 0.3886237144470215,
1548
+ "learning_rate": 3.5745670479312374e-05,
1549
+ "loss": 0.8846,
1550
+ "step": 422
1551
+ },
1552
+ {
1553
+ "epoch": 0.8488488488488488,
1554
+ "grad_norm": 0.33457881212234497,
1555
+ "learning_rate": 3.55874700018163e-05,
1556
+ "loss": 0.922,
1557
+ "step": 424
1558
+ },
1559
+ {
1560
+ "epoch": 0.8528528528528528,
1561
+ "grad_norm": 0.3439764082431793,
1562
+ "learning_rate": 3.5428751204896085e-05,
1563
+ "loss": 0.9225,
1564
+ "step": 426
1565
+ },
1566
+ {
1567
+ "epoch": 0.8568568568568569,
1568
+ "grad_norm": 0.3794129192829132,
1569
+ "learning_rate": 3.526952185877781e-05,
1570
+ "loss": 0.9177,
1571
+ "step": 428
1572
+ },
1573
+ {
1574
+ "epoch": 0.8608608608608609,
1575
+ "grad_norm": 0.36088061332702637,
1576
+ "learning_rate": 3.5109789758681946e-05,
1577
+ "loss": 0.9212,
1578
+ "step": 430
1579
+ },
1580
+ {
1581
+ "epoch": 0.8648648648648649,
1582
+ "grad_norm": 0.40673118829727173,
1583
+ "learning_rate": 3.494956272444177e-05,
1584
+ "loss": 0.9235,
1585
+ "step": 432
1586
+ },
1587
+ {
1588
+ "epoch": 0.8688688688688688,
1589
+ "grad_norm": 0.3603825271129608,
1590
+ "learning_rate": 3.4788848600120505e-05,
1591
+ "loss": 0.919,
1592
+ "step": 434
1593
+ },
1594
+ {
1595
+ "epoch": 0.8728728728728729,
1596
+ "grad_norm": 0.3395703136920929,
1597
+ "learning_rate": 3.4627655253627323e-05,
1598
+ "loss": 0.8724,
1599
+ "step": 436
1600
+ },
1601
+ {
1602
+ "epoch": 0.8768768768768769,
1603
+ "grad_norm": 0.3341948390007019,
1604
+ "learning_rate": 3.446599057633217e-05,
1605
+ "loss": 0.9189,
1606
+ "step": 438
1607
+ },
1608
+ {
1609
+ "epoch": 0.8808808808808809,
1610
+ "grad_norm": 0.342174768447876,
1611
+ "learning_rate": 3.430386248267943e-05,
1612
+ "loss": 0.9327,
1613
+ "step": 440
1614
+ },
1615
+ {
1616
+ "epoch": 0.8848848848848849,
1617
+ "grad_norm": 0.35033905506134033,
1618
+ "learning_rate": 3.4141278909800444e-05,
1619
+ "loss": 0.9197,
1620
+ "step": 442
1621
+ },
1622
+ {
1623
+ "epoch": 0.8888888888888888,
1624
+ "grad_norm": 0.3870660960674286,
1625
+ "learning_rate": 3.397824781712499e-05,
1626
+ "loss": 0.863,
1627
+ "step": 444
1628
+ },
1629
+ {
1630
+ "epoch": 0.8928928928928929,
1631
+ "grad_norm": 0.3849852383136749,
1632
+ "learning_rate": 3.381477718599157e-05,
1633
+ "loss": 0.8746,
1634
+ "step": 446
1635
+ },
1636
+ {
1637
+ "epoch": 0.8968968968968969,
1638
+ "grad_norm": 0.3900209963321686,
1639
+ "learning_rate": 3.365087501925673e-05,
1640
+ "loss": 0.9194,
1641
+ "step": 448
1642
+ },
1643
+ {
1644
+ "epoch": 0.9009009009009009,
1645
+ "grad_norm": 0.36199262738227844,
1646
+ "learning_rate": 3.3486549340903195e-05,
1647
+ "loss": 0.886,
1648
+ "step": 450
1649
+ },
1650
+ {
1651
+ "epoch": 0.9009009009009009,
1652
+ "eval_flock_task4_val_loss": 1.151094913482666,
1653
+ "eval_flock_task4_val_runtime": 2.4214,
1654
+ "eval_flock_task4_val_samples_per_second": 23.953,
1655
+ "eval_flock_task4_val_steps_per_second": 23.953,
1656
+ "step": 450
1657
+ },
1658
+ {
1659
+ "epoch": 0.9049049049049049,
1660
+ "grad_norm": 0.33788204193115234,
1661
+ "learning_rate": 3.332180819564714e-05,
1662
+ "loss": 0.9225,
1663
+ "step": 452
1664
+ },
1665
+ {
1666
+ "epoch": 0.908908908908909,
1667
+ "grad_norm": 0.3792935311794281,
1668
+ "learning_rate": 3.3156659648544276e-05,
1669
+ "loss": 0.9141,
1670
+ "step": 454
1671
+ },
1672
+ {
1673
+ "epoch": 0.9129129129129129,
1674
+ "grad_norm": 0.33289849758148193,
1675
+ "learning_rate": 3.299111178459507e-05,
1676
+ "loss": 0.9296,
1677
+ "step": 456
1678
+ },
1679
+ {
1680
+ "epoch": 0.9169169169169169,
1681
+ "grad_norm": 0.35779908299446106,
1682
+ "learning_rate": 3.282517270834891e-05,
1683
+ "loss": 0.8576,
1684
+ "step": 458
1685
+ },
1686
+ {
1687
+ "epoch": 0.9209209209209209,
1688
+ "grad_norm": 0.38421431183815,
1689
+ "learning_rate": 3.2658850543507334e-05,
1690
+ "loss": 0.9252,
1691
+ "step": 460
1692
+ },
1693
+ {
1694
+ "epoch": 0.924924924924925,
1695
+ "grad_norm": 0.4044077396392822,
1696
+ "learning_rate": 3.2492153432526355e-05,
1697
+ "loss": 0.8938,
1698
+ "step": 462
1699
+ },
1700
+ {
1701
+ "epoch": 0.928928928928929,
1702
+ "grad_norm": 0.4189876616001129,
1703
+ "learning_rate": 3.2325089536217815e-05,
1704
+ "loss": 0.938,
1705
+ "step": 464
1706
+ },
1707
+ {
1708
+ "epoch": 0.9329329329329329,
1709
+ "grad_norm": 0.33194634318351746,
1710
+ "learning_rate": 3.215766703334988e-05,
1711
+ "loss": 0.8809,
1712
+ "step": 466
1713
+ },
1714
+ {
1715
+ "epoch": 0.9369369369369369,
1716
+ "grad_norm": 0.3266729712486267,
1717
+ "learning_rate": 3.1989894120246614e-05,
1718
+ "loss": 0.9338,
1719
+ "step": 468
1720
+ },
1721
+ {
1722
+ "epoch": 0.9409409409409409,
1723
+ "grad_norm": 0.3905945122241974,
1724
+ "learning_rate": 3.1821779010386755e-05,
1725
+ "loss": 0.9709,
1726
+ "step": 470
1727
+ },
1728
+ {
1729
+ "epoch": 0.944944944944945,
1730
+ "grad_norm": 0.3806445598602295,
1731
+ "learning_rate": 3.1653329934001584e-05,
1732
+ "loss": 0.9232,
1733
+ "step": 472
1734
+ },
1735
+ {
1736
+ "epoch": 0.948948948948949,
1737
+ "grad_norm": 0.34493544697761536,
1738
+ "learning_rate": 3.148455513767206e-05,
1739
+ "loss": 0.9446,
1740
+ "step": 474
1741
+ },
1742
+ {
1743
+ "epoch": 0.9529529529529529,
1744
+ "grad_norm": 0.34965747594833374,
1745
+ "learning_rate": 3.1315462883925025e-05,
1746
+ "loss": 0.932,
1747
+ "step": 476
1748
+ },
1749
+ {
1750
+ "epoch": 0.9569569569569569,
1751
+ "grad_norm": 0.34367701411247253,
1752
+ "learning_rate": 3.114606145082876e-05,
1753
+ "loss": 0.9061,
1754
+ "step": 478
1755
+ },
1756
+ {
1757
+ "epoch": 0.960960960960961,
1758
+ "grad_norm": 0.36689406633377075,
1759
+ "learning_rate": 3.097635913158772e-05,
1760
+ "loss": 0.8817,
1761
+ "step": 480
1762
+ },
1763
+ {
1764
+ "epoch": 0.964964964964965,
1765
+ "grad_norm": 0.34466394782066345,
1766
+ "learning_rate": 3.080636423413649e-05,
1767
+ "loss": 0.9088,
1768
+ "step": 482
1769
+ },
1770
+ {
1771
+ "epoch": 0.968968968968969,
1772
+ "grad_norm": 0.3059948980808258,
1773
+ "learning_rate": 3.063608508073311e-05,
1774
+ "loss": 0.957,
1775
+ "step": 484
1776
+ },
1777
+ {
1778
+ "epoch": 0.972972972972973,
1779
+ "grad_norm": 0.3226034641265869,
1780
+ "learning_rate": 3.0465530007551645e-05,
1781
+ "loss": 0.8844,
1782
+ "step": 486
1783
+ },
1784
+ {
1785
+ "epoch": 0.9769769769769769,
1786
+ "grad_norm": 0.3674728274345398,
1787
+ "learning_rate": 3.0294707364274067e-05,
1788
+ "loss": 0.9126,
1789
+ "step": 488
1790
+ },
1791
+ {
1792
+ "epoch": 0.980980980980981,
1793
+ "grad_norm": 0.3241788148880005,
1794
+ "learning_rate": 3.0123625513681463e-05,
1795
+ "loss": 0.8676,
1796
+ "step": 490
1797
+ },
1798
+ {
1799
+ "epoch": 0.984984984984985,
1800
+ "grad_norm": 0.3742011487483978,
1801
+ "learning_rate": 2.9952292831244676e-05,
1802
+ "loss": 0.9293,
1803
+ "step": 492
1804
+ },
1805
+ {
1806
+ "epoch": 0.988988988988989,
1807
+ "grad_norm": 0.4942300617694855,
1808
+ "learning_rate": 2.9780717704714266e-05,
1809
+ "loss": 0.9426,
1810
+ "step": 494
1811
+ },
1812
+ {
1813
+ "epoch": 0.992992992992993,
1814
+ "grad_norm": 0.34072035551071167,
1815
+ "learning_rate": 2.960890853370985e-05,
1816
+ "loss": 0.9089,
1817
+ "step": 496
1818
+ },
1819
+ {
1820
+ "epoch": 0.996996996996997,
1821
+ "grad_norm": 0.47447457909584045,
1822
+ "learning_rate": 2.9436873729308912e-05,
1823
+ "loss": 0.8594,
1824
+ "step": 498
1825
+ },
1826
+ {
1827
+ "epoch": 1.0,
1828
+ "grad_norm": 0.5046526193618774,
1829
+ "learning_rate": 2.9264621713635028e-05,
1830
+ "loss": 0.6843,
1831
+ "step": 500
1832
+ },
1833
+ {
1834
+ "epoch": 1.0,
1835
+ "eval_flock_task4_val_loss": 1.1507720947265625,
1836
+ "eval_flock_task4_val_runtime": 2.3966,
1837
+ "eval_flock_task4_val_samples_per_second": 24.201,
1838
+ "eval_flock_task4_val_steps_per_second": 24.201,
1839
+ "step": 500
1840
+ },
1841
+ {
1842
+ "epoch": 1.004004004004004,
1843
+ "grad_norm": 0.36078399419784546,
1844
+ "learning_rate": 2.9092160919445567e-05,
1845
+ "loss": 0.8636,
1846
+ "step": 502
1847
+ },
1848
+ {
1849
+ "epoch": 1.008008008008008,
1850
+ "grad_norm": 0.3482002317905426,
1851
+ "learning_rate": 2.891949978971883e-05,
1852
+ "loss": 0.8479,
1853
+ "step": 504
1854
+ },
1855
+ {
1856
+ "epoch": 1.012012012012012,
1857
+ "grad_norm": 0.3719685673713684,
1858
+ "learning_rate": 2.874664677724072e-05,
1859
+ "loss": 0.8854,
1860
+ "step": 506
1861
+ },
1862
+ {
1863
+ "epoch": 1.016016016016016,
1864
+ "grad_norm": 0.3359503746032715,
1865
+ "learning_rate": 2.8573610344190975e-05,
1866
+ "loss": 0.8757,
1867
+ "step": 508
1868
+ },
1869
+ {
1870
+ "epoch": 1.02002002002002,
1871
+ "grad_norm": 0.5480461120605469,
1872
+ "learning_rate": 2.840039896172882e-05,
1873
+ "loss": 0.8581,
1874
+ "step": 510
1875
+ },
1876
+ {
1877
+ "epoch": 1.024024024024024,
1878
+ "grad_norm": 0.3680349588394165,
1879
+ "learning_rate": 2.822702110957831e-05,
1880
+ "loss": 0.9137,
1881
+ "step": 512
1882
+ },
1883
+ {
1884
+ "epoch": 1.028028028028028,
1885
+ "grad_norm": 0.3575070798397064,
1886
+ "learning_rate": 2.8053485275613178e-05,
1887
+ "loss": 0.8918,
1888
+ "step": 514
1889
+ },
1890
+ {
1891
+ "epoch": 1.032032032032032,
1892
+ "grad_norm": 0.4439910650253296,
1893
+ "learning_rate": 2.78797999554413e-05,
1894
+ "loss": 0.8673,
1895
+ "step": 516
1896
+ },
1897
+ {
1898
+ "epoch": 1.0360360360360361,
1899
+ "grad_norm": 0.40003103017807007,
1900
+ "learning_rate": 2.7705973651988776e-05,
1901
+ "loss": 0.8849,
1902
+ "step": 518
1903
+ },
1904
+ {
1905
+ "epoch": 1.04004004004004,
1906
+ "grad_norm": 0.38889795541763306,
1907
+ "learning_rate": 2.753201487508369e-05,
1908
+ "loss": 0.8631,
1909
+ "step": 520
1910
+ },
1911
+ {
1912
+ "epoch": 1.044044044044044,
1913
+ "grad_norm": 0.37320345640182495,
1914
+ "learning_rate": 2.7357932141039495e-05,
1915
+ "loss": 0.9151,
1916
+ "step": 522
1917
+ },
1918
+ {
1919
+ "epoch": 1.048048048048048,
1920
+ "grad_norm": 0.34984591603279114,
1921
+ "learning_rate": 2.718373397223804e-05,
1922
+ "loss": 0.8854,
1923
+ "step": 524
1924
+ },
1925
+ {
1926
+ "epoch": 1.052052052052052,
1927
+ "grad_norm": 0.3709803819656372,
1928
+ "learning_rate": 2.7009428896712442e-05,
1929
+ "loss": 0.889,
1930
+ "step": 526
1931
+ },
1932
+ {
1933
+ "epoch": 1.0560560560560561,
1934
+ "grad_norm": 0.4115319848060608,
1935
+ "learning_rate": 2.6835025447729495e-05,
1936
+ "loss": 0.9024,
1937
+ "step": 528
1938
+ },
1939
+ {
1940
+ "epoch": 1.06006006006006,
1941
+ "grad_norm": 0.3313678503036499,
1942
+ "learning_rate": 2.6660532163371992e-05,
1943
+ "loss": 0.8515,
1944
+ "step": 530
1945
+ },
1946
+ {
1947
+ "epoch": 1.064064064064064,
1948
+ "grad_norm": 0.3881412744522095,
1949
+ "learning_rate": 2.6485957586120663e-05,
1950
+ "loss": 0.8723,
1951
+ "step": 532
1952
+ },
1953
+ {
1954
+ "epoch": 1.068068068068068,
1955
+ "grad_norm": 0.4042016267776489,
1956
+ "learning_rate": 2.6311310262436036e-05,
1957
+ "loss": 0.8583,
1958
+ "step": 534
1959
+ },
1960
+ {
1961
+ "epoch": 1.072072072072072,
1962
+ "grad_norm": 0.37638312578201294,
1963
+ "learning_rate": 2.613659874233999e-05,
1964
+ "loss": 0.8764,
1965
+ "step": 536
1966
+ },
1967
+ {
1968
+ "epoch": 1.0760760760760761,
1969
+ "grad_norm": 0.3946394920349121,
1970
+ "learning_rate": 2.5961831578997215e-05,
1971
+ "loss": 0.89,
1972
+ "step": 538
1973
+ },
1974
+ {
1975
+ "epoch": 1.08008008008008,
1976
+ "grad_norm": 0.37551435828208923,
1977
+ "learning_rate": 2.5787017328296447e-05,
1978
+ "loss": 0.8913,
1979
+ "step": 540
1980
+ },
1981
+ {
1982
+ "epoch": 1.0840840840840842,
1983
+ "grad_norm": 0.4114207923412323,
1984
+ "learning_rate": 2.561216454843165e-05,
1985
+ "loss": 0.8973,
1986
+ "step": 542
1987
+ },
1988
+ {
1989
+ "epoch": 1.088088088088088,
1990
+ "grad_norm": 0.36333537101745605,
1991
+ "learning_rate": 2.5437281799483004e-05,
1992
+ "loss": 0.8764,
1993
+ "step": 544
1994
+ },
1995
+ {
1996
+ "epoch": 1.092092092092092,
1997
+ "grad_norm": 0.4394896328449249,
1998
+ "learning_rate": 2.526237764299786e-05,
1999
+ "loss": 0.93,
2000
+ "step": 546
2001
+ },
2002
+ {
2003
+ "epoch": 1.0960960960960962,
2004
+ "grad_norm": 0.37381502985954285,
2005
+ "learning_rate": 2.508746064157159e-05,
2006
+ "loss": 0.8433,
2007
+ "step": 548
2008
+ },
2009
+ {
2010
+ "epoch": 1.1001001001001,
2011
+ "grad_norm": 0.3822025656700134,
2012
+ "learning_rate": 2.4912539358428415e-05,
2013
+ "loss": 0.877,
2014
+ "step": 550
2015
+ },
2016
+ {
2017
+ "epoch": 1.1001001001001,
2018
+ "eval_flock_task4_val_loss": 1.1475247144699097,
2019
+ "eval_flock_task4_val_runtime": 2.41,
2020
+ "eval_flock_task4_val_samples_per_second": 24.067,
2021
+ "eval_flock_task4_val_steps_per_second": 24.067,
2022
+ "step": 550
2023
+ },
2024
+ {
2025
+ "epoch": 1.1041041041041042,
2026
+ "grad_norm": 0.49058809876441956,
2027
+ "learning_rate": 2.473762235700214e-05,
2028
+ "loss": 0.8725,
2029
+ "step": 552
2030
+ },
2031
+ {
2032
+ "epoch": 1.1081081081081081,
2033
+ "grad_norm": 0.3926384150981903,
2034
+ "learning_rate": 2.4562718200517002e-05,
2035
+ "loss": 0.8599,
2036
+ "step": 554
2037
+ },
2038
+ {
2039
+ "epoch": 1.112112112112112,
2040
+ "grad_norm": 0.39552003145217896,
2041
+ "learning_rate": 2.4387835451568355e-05,
2042
+ "loss": 0.8659,
2043
+ "step": 556
2044
+ },
2045
+ {
2046
+ "epoch": 1.1161161161161162,
2047
+ "grad_norm": 0.4861438274383545,
2048
+ "learning_rate": 2.421298267170356e-05,
2049
+ "loss": 0.8898,
2050
+ "step": 558
2051
+ },
2052
+ {
2053
+ "epoch": 1.12012012012012,
2054
+ "grad_norm": 0.418471097946167,
2055
+ "learning_rate": 2.4038168421002794e-05,
2056
+ "loss": 0.8401,
2057
+ "step": 560
2058
+ },
2059
+ {
2060
+ "epoch": 1.1241241241241242,
2061
+ "grad_norm": 0.3635142743587494,
2062
+ "learning_rate": 2.3863401257660018e-05,
2063
+ "loss": 0.8742,
2064
+ "step": 562
2065
+ },
2066
+ {
2067
+ "epoch": 1.1281281281281281,
2068
+ "grad_norm": 0.3907809257507324,
2069
+ "learning_rate": 2.3688689737563967e-05,
2070
+ "loss": 0.8774,
2071
+ "step": 564
2072
+ },
2073
+ {
2074
+ "epoch": 1.132132132132132,
2075
+ "grad_norm": 0.3826066553592682,
2076
+ "learning_rate": 2.3514042413879343e-05,
2077
+ "loss": 0.9037,
2078
+ "step": 566
2079
+ },
2080
+ {
2081
+ "epoch": 1.1361361361361362,
2082
+ "grad_norm": 0.36759504675865173,
2083
+ "learning_rate": 2.3339467836628017e-05,
2084
+ "loss": 0.8573,
2085
+ "step": 568
2086
+ },
2087
+ {
2088
+ "epoch": 1.14014014014014,
2089
+ "grad_norm": 0.3731608986854553,
2090
+ "learning_rate": 2.31649745522705e-05,
2091
+ "loss": 0.9056,
2092
+ "step": 570
2093
+ },
2094
+ {
2095
+ "epoch": 1.1441441441441442,
2096
+ "grad_norm": 0.42503395676612854,
2097
+ "learning_rate": 2.2990571103287567e-05,
2098
+ "loss": 0.8685,
2099
+ "step": 572
2100
+ },
2101
+ {
2102
+ "epoch": 1.1481481481481481,
2103
+ "grad_norm": 0.43720346689224243,
2104
+ "learning_rate": 2.2816266027761966e-05,
2105
+ "loss": 0.883,
2106
+ "step": 574
2107
+ },
2108
+ {
2109
+ "epoch": 1.1521521521521523,
2110
+ "grad_norm": 0.38943639397621155,
2111
+ "learning_rate": 2.2642067858960514e-05,
2112
+ "loss": 0.8981,
2113
+ "step": 576
2114
+ },
2115
+ {
2116
+ "epoch": 1.1561561561561562,
2117
+ "grad_norm": 0.43230053782463074,
2118
+ "learning_rate": 2.2467985124916314e-05,
2119
+ "loss": 0.8593,
2120
+ "step": 578
2121
+ },
2122
+ {
2123
+ "epoch": 1.16016016016016,
2124
+ "grad_norm": 0.4695190489292145,
2125
+ "learning_rate": 2.2294026348011223e-05,
2126
+ "loss": 0.8724,
2127
+ "step": 580
2128
+ },
2129
+ {
2130
+ "epoch": 1.1641641641641642,
2131
+ "grad_norm": 0.39060747623443604,
2132
+ "learning_rate": 2.2120200044558706e-05,
2133
+ "loss": 0.9046,
2134
+ "step": 582
2135
+ },
2136
+ {
2137
+ "epoch": 1.1681681681681682,
2138
+ "grad_norm": 0.3812834620475769,
2139
+ "learning_rate": 2.1946514724386828e-05,
2140
+ "loss": 0.8368,
2141
+ "step": 584
2142
+ },
2143
+ {
2144
+ "epoch": 1.1721721721721723,
2145
+ "grad_norm": 0.4360229969024658,
2146
+ "learning_rate": 2.1772978890421688e-05,
2147
+ "loss": 0.8587,
2148
+ "step": 586
2149
+ },
2150
+ {
2151
+ "epoch": 1.1761761761761762,
2152
+ "grad_norm": 0.4518442749977112,
2153
+ "learning_rate": 2.1599601038271186e-05,
2154
+ "loss": 0.8776,
2155
+ "step": 588
2156
+ },
2157
+ {
2158
+ "epoch": 1.1801801801801801,
2159
+ "grad_norm": 0.4748334586620331,
2160
+ "learning_rate": 2.142638965580903e-05,
2161
+ "loss": 0.8933,
2162
+ "step": 590
2163
+ },
2164
+ {
2165
+ "epoch": 1.1841841841841843,
2166
+ "grad_norm": 0.4352450966835022,
2167
+ "learning_rate": 2.125335322275928e-05,
2168
+ "loss": 0.8511,
2169
+ "step": 592
2170
+ },
2171
+ {
2172
+ "epoch": 1.1881881881881882,
2173
+ "grad_norm": 0.4232271611690521,
2174
+ "learning_rate": 2.108050021028118e-05,
2175
+ "loss": 0.8153,
2176
+ "step": 594
2177
+ },
2178
+ {
2179
+ "epoch": 1.1921921921921923,
2180
+ "grad_norm": 0.3999643325805664,
2181
+ "learning_rate": 2.0907839080554443e-05,
2182
+ "loss": 0.868,
2183
+ "step": 596
2184
+ },
2185
+ {
2186
+ "epoch": 1.1961961961961962,
2187
+ "grad_norm": 0.3707253336906433,
2188
+ "learning_rate": 2.073537828636497e-05,
2189
+ "loss": 0.882,
2190
+ "step": 598
2191
+ },
2192
+ {
2193
+ "epoch": 1.2002002002002001,
2194
+ "grad_norm": 0.44216448068618774,
2195
+ "learning_rate": 2.0563126270691097e-05,
2196
+ "loss": 0.8794,
2197
+ "step": 600
2198
+ },
2199
+ {
2200
+ "epoch": 1.2002002002002001,
2201
+ "eval_flock_task4_val_loss": 1.1478508710861206,
2202
+ "eval_flock_task4_val_runtime": 2.4198,
2203
+ "eval_flock_task4_val_samples_per_second": 23.969,
2204
+ "eval_flock_task4_val_steps_per_second": 23.969,
2205
+ "step": 600
2206
+ },
2207
+ {
2208
+ "epoch": 1.2042042042042043,
2209
+ "grad_norm": 0.4116131663322449,
2210
+ "learning_rate": 2.039109146629016e-05,
2211
+ "loss": 0.8466,
2212
+ "step": 602
2213
+ },
2214
+ {
2215
+ "epoch": 1.2082082082082082,
2216
+ "grad_norm": 0.36521586775779724,
2217
+ "learning_rate": 2.0219282295285737e-05,
2218
+ "loss": 0.8924,
2219
+ "step": 604
2220
+ },
2221
+ {
2222
+ "epoch": 1.2122122122122123,
2223
+ "grad_norm": 0.4010111391544342,
2224
+ "learning_rate": 2.004770716875533e-05,
2225
+ "loss": 0.8546,
2226
+ "step": 606
2227
+ },
2228
+ {
2229
+ "epoch": 1.2162162162162162,
2230
+ "grad_norm": 0.45376816391944885,
2231
+ "learning_rate": 1.9876374486318543e-05,
2232
+ "loss": 0.8457,
2233
+ "step": 608
2234
+ },
2235
+ {
2236
+ "epoch": 1.2202202202202201,
2237
+ "grad_norm": 0.4506365656852722,
2238
+ "learning_rate": 1.970529263572594e-05,
2239
+ "loss": 0.8564,
2240
+ "step": 610
2241
+ },
2242
+ {
2243
+ "epoch": 1.2242242242242243,
2244
+ "grad_norm": 0.4055129289627075,
2245
+ "learning_rate": 1.9534469992448358e-05,
2246
+ "loss": 0.8472,
2247
+ "step": 612
2248
+ },
2249
+ {
2250
+ "epoch": 1.2282282282282282,
2251
+ "grad_norm": 0.403263658285141,
2252
+ "learning_rate": 1.936391491926689e-05,
2253
+ "loss": 0.896,
2254
+ "step": 614
2255
+ },
2256
+ {
2257
+ "epoch": 1.2322322322322323,
2258
+ "grad_norm": 0.3937626779079437,
2259
+ "learning_rate": 1.9193635765863523e-05,
2260
+ "loss": 0.8931,
2261
+ "step": 616
2262
+ },
2263
+ {
2264
+ "epoch": 1.2362362362362362,
2265
+ "grad_norm": 0.42880845069885254,
2266
+ "learning_rate": 1.9023640868412297e-05,
2267
+ "loss": 0.8265,
2268
+ "step": 618
2269
+ },
2270
+ {
2271
+ "epoch": 1.2402402402402402,
2272
+ "grad_norm": 0.5050727128982544,
2273
+ "learning_rate": 1.885393854917124e-05,
2274
+ "loss": 0.8488,
2275
+ "step": 620
2276
+ },
2277
+ {
2278
+ "epoch": 1.2442442442442443,
2279
+ "grad_norm": 0.44161123037338257,
2280
+ "learning_rate": 1.868453711607498e-05,
2281
+ "loss": 0.845,
2282
+ "step": 622
2283
+ },
2284
+ {
2285
+ "epoch": 1.2482482482482482,
2286
+ "grad_norm": 0.42316916584968567,
2287
+ "learning_rate": 1.8515444862327946e-05,
2288
+ "loss": 0.9099,
2289
+ "step": 624
2290
+ },
2291
+ {
2292
+ "epoch": 1.2522522522522523,
2293
+ "grad_norm": 0.44850805401802063,
2294
+ "learning_rate": 1.834667006599841e-05,
2295
+ "loss": 0.8437,
2296
+ "step": 626
2297
+ },
2298
+ {
2299
+ "epoch": 1.2562562562562563,
2300
+ "grad_norm": 0.4694780707359314,
2301
+ "learning_rate": 1.8178220989613254e-05,
2302
+ "loss": 0.8875,
2303
+ "step": 628
2304
+ },
2305
+ {
2306
+ "epoch": 1.2602602602602602,
2307
+ "grad_norm": 0.4005432426929474,
2308
+ "learning_rate": 1.8010105879753396e-05,
2309
+ "loss": 0.8659,
2310
+ "step": 630
2311
+ },
2312
+ {
2313
+ "epoch": 1.2642642642642643,
2314
+ "grad_norm": 0.42025813460350037,
2315
+ "learning_rate": 1.784233296665012e-05,
2316
+ "loss": 0.8718,
2317
+ "step": 632
2318
+ },
2319
+ {
2320
+ "epoch": 1.2682682682682682,
2321
+ "grad_norm": 0.41626977920532227,
2322
+ "learning_rate": 1.7674910463782184e-05,
2323
+ "loss": 0.8716,
2324
+ "step": 634
2325
+ },
2326
+ {
2327
+ "epoch": 1.2722722722722724,
2328
+ "grad_norm": 0.458926260471344,
2329
+ "learning_rate": 1.7507846567473644e-05,
2330
+ "loss": 0.9085,
2331
+ "step": 636
2332
+ },
2333
+ {
2334
+ "epoch": 1.2762762762762763,
2335
+ "grad_norm": 0.45097580552101135,
2336
+ "learning_rate": 1.7341149456492672e-05,
2337
+ "loss": 0.9067,
2338
+ "step": 638
2339
+ },
2340
+ {
2341
+ "epoch": 1.2802802802802802,
2342
+ "grad_norm": 0.3684636652469635,
2343
+ "learning_rate": 1.71748272916511e-05,
2344
+ "loss": 0.8626,
2345
+ "step": 640
2346
+ },
2347
+ {
2348
+ "epoch": 1.2842842842842843,
2349
+ "grad_norm": 0.39824149012565613,
2350
+ "learning_rate": 1.7008888215404933e-05,
2351
+ "loss": 0.9234,
2352
+ "step": 642
2353
+ },
2354
+ {
2355
+ "epoch": 1.2882882882882882,
2356
+ "grad_norm": 0.37552574276924133,
2357
+ "learning_rate": 1.6843340351455726e-05,
2358
+ "loss": 0.826,
2359
+ "step": 644
2360
+ },
2361
+ {
2362
+ "epoch": 1.2922922922922924,
2363
+ "grad_norm": 0.44982481002807617,
2364
+ "learning_rate": 1.6678191804352872e-05,
2365
+ "loss": 0.8814,
2366
+ "step": 646
2367
+ },
2368
+ {
2369
+ "epoch": 1.2962962962962963,
2370
+ "grad_norm": 0.4010125994682312,
2371
+ "learning_rate": 1.6513450659096804e-05,
2372
+ "loss": 0.8905,
2373
+ "step": 648
2374
+ },
2375
+ {
2376
+ "epoch": 1.3003003003003002,
2377
+ "grad_norm": 0.43015238642692566,
2378
+ "learning_rate": 1.6349124980743276e-05,
2379
+ "loss": 0.8357,
2380
+ "step": 650
2381
+ },
2382
+ {
2383
+ "epoch": 1.3003003003003002,
2384
+ "eval_flock_task4_val_loss": 1.143893837928772,
2385
+ "eval_flock_task4_val_runtime": 2.291,
2386
+ "eval_flock_task4_val_samples_per_second": 25.317,
2387
+ "eval_flock_task4_val_steps_per_second": 25.317,
2388
+ "step": 650
2389
+ },
2390
+ {
2391
+ "epoch": 1.3043043043043043,
2392
+ "grad_norm": 0.44190534949302673,
2393
+ "learning_rate": 1.6185222814008433e-05,
2394
+ "loss": 0.8707,
2395
+ "step": 652
2396
+ },
2397
+ {
2398
+ "epoch": 1.3083083083083082,
2399
+ "grad_norm": 0.4301456809043884,
2400
+ "learning_rate": 1.602175218287501e-05,
2401
+ "loss": 0.8699,
2402
+ "step": 654
2403
+ },
2404
+ {
2405
+ "epoch": 1.3123123123123124,
2406
+ "grad_norm": 0.4133666455745697,
2407
+ "learning_rate": 1.5858721090199565e-05,
2408
+ "loss": 0.8277,
2409
+ "step": 656
2410
+ },
2411
+ {
2412
+ "epoch": 1.3163163163163163,
2413
+ "grad_norm": 0.459380179643631,
2414
+ "learning_rate": 1.569613751732058e-05,
2415
+ "loss": 0.8458,
2416
+ "step": 658
2417
+ },
2418
+ {
2419
+ "epoch": 1.3203203203203202,
2420
+ "grad_norm": 0.3874422311782837,
2421
+ "learning_rate": 1.5534009423667827e-05,
2422
+ "loss": 0.8508,
2423
+ "step": 660
2424
+ },
2425
+ {
2426
+ "epoch": 1.3243243243243243,
2427
+ "grad_norm": 0.5516605377197266,
2428
+ "learning_rate": 1.537234474637268e-05,
2429
+ "loss": 0.8989,
2430
+ "step": 662
2431
+ },
2432
+ {
2433
+ "epoch": 1.3283283283283283,
2434
+ "grad_norm": 0.38644006848335266,
2435
+ "learning_rate": 1.5211151399879506e-05,
2436
+ "loss": 0.8677,
2437
+ "step": 664
2438
+ },
2439
+ {
2440
+ "epoch": 1.3323323323323324,
2441
+ "grad_norm": 0.4062030017375946,
2442
+ "learning_rate": 1.5050437275558233e-05,
2443
+ "loss": 0.8896,
2444
+ "step": 666
2445
+ },
2446
+ {
2447
+ "epoch": 1.3363363363363363,
2448
+ "grad_norm": 0.43147289752960205,
2449
+ "learning_rate": 1.489021024131806e-05,
2450
+ "loss": 0.8782,
2451
+ "step": 668
2452
+ },
2453
+ {
2454
+ "epoch": 1.3403403403403402,
2455
+ "grad_norm": 0.35989537835121155,
2456
+ "learning_rate": 1.4730478141222192e-05,
2457
+ "loss": 0.9494,
2458
+ "step": 670
2459
+ },
2460
+ {
2461
+ "epoch": 1.3443443443443444,
2462
+ "grad_norm": 0.4030705988407135,
2463
+ "learning_rate": 1.457124879510392e-05,
2464
+ "loss": 0.8307,
2465
+ "step": 672
2466
+ },
2467
+ {
2468
+ "epoch": 1.3483483483483483,
2469
+ "grad_norm": 0.3988940715789795,
2470
+ "learning_rate": 1.441252999818371e-05,
2471
+ "loss": 0.8933,
2472
+ "step": 674
2473
+ },
2474
+ {
2475
+ "epoch": 1.3523523523523524,
2476
+ "grad_norm": 0.3888278603553772,
2477
+ "learning_rate": 1.4254329520687625e-05,
2478
+ "loss": 0.8324,
2479
+ "step": 676
2480
+ },
2481
+ {
2482
+ "epoch": 1.3563563563563563,
2483
+ "grad_norm": 0.3939126431941986,
2484
+ "learning_rate": 1.4096655107466945e-05,
2485
+ "loss": 0.89,
2486
+ "step": 678
2487
+ },
2488
+ {
2489
+ "epoch": 1.3603603603603602,
2490
+ "grad_norm": 0.4838270843029022,
2491
+ "learning_rate": 1.3939514477618942e-05,
2492
+ "loss": 0.8477,
2493
+ "step": 680
2494
+ },
2495
+ {
2496
+ "epoch": 1.3643643643643644,
2497
+ "grad_norm": 0.40554022789001465,
2498
+ "learning_rate": 1.3782915324109074e-05,
2499
+ "loss": 0.8645,
2500
+ "step": 682
2501
+ },
2502
+ {
2503
+ "epoch": 1.3683683683683685,
2504
+ "grad_norm": 0.40760108828544617,
2505
+ "learning_rate": 1.362686531339428e-05,
2506
+ "loss": 0.8567,
2507
+ "step": 684
2508
+ },
2509
+ {
2510
+ "epoch": 1.3723723723723724,
2511
+ "grad_norm": 0.3956020176410675,
2512
+ "learning_rate": 1.3471372085047742e-05,
2513
+ "loss": 0.8703,
2514
+ "step": 686
2515
+ },
2516
+ {
2517
+ "epoch": 1.3763763763763763,
2518
+ "grad_norm": 0.478240966796875,
2519
+ "learning_rate": 1.3316443251384807e-05,
2520
+ "loss": 0.8142,
2521
+ "step": 688
2522
+ },
2523
+ {
2524
+ "epoch": 1.3803803803803802,
2525
+ "grad_norm": 0.4959944188594818,
2526
+ "learning_rate": 1.316208639709039e-05,
2527
+ "loss": 0.8593,
2528
+ "step": 690
2529
+ },
2530
+ {
2531
+ "epoch": 1.3843843843843844,
2532
+ "grad_norm": 0.47035202383995056,
2533
+ "learning_rate": 1.3008309078847605e-05,
2534
+ "loss": 0.9078,
2535
+ "step": 692
2536
+ },
2537
+ {
2538
+ "epoch": 1.3883883883883885,
2539
+ "grad_norm": 0.44363516569137573,
2540
+ "learning_rate": 1.2855118824967833e-05,
2541
+ "loss": 0.8965,
2542
+ "step": 694
2543
+ },
2544
+ {
2545
+ "epoch": 1.3923923923923924,
2546
+ "grad_norm": 0.39717763662338257,
2547
+ "learning_rate": 1.2702523135022204e-05,
2548
+ "loss": 0.863,
2549
+ "step": 696
2550
+ },
2551
+ {
2552
+ "epoch": 1.3963963963963963,
2553
+ "grad_norm": 0.416452020406723,
2554
+ "learning_rate": 1.2550529479474383e-05,
2555
+ "loss": 0.8787,
2556
+ "step": 698
2557
+ },
2558
+ {
2559
+ "epoch": 1.4004004004004005,
2560
+ "grad_norm": 0.42090561985969543,
2561
+ "learning_rate": 1.2399145299314912e-05,
2562
+ "loss": 0.8709,
2563
+ "step": 700
2564
+ },
2565
+ {
2566
+ "epoch": 1.4004004004004005,
2567
+ "eval_flock_task4_val_loss": 1.1386691331863403,
2568
+ "eval_flock_task4_val_runtime": 2.2803,
2569
+ "eval_flock_task4_val_samples_per_second": 25.435,
2570
+ "eval_flock_task4_val_steps_per_second": 25.435,
2571
+ "step": 700
2572
+ },
2573
+ {
2574
+ "epoch": 1.4044044044044044,
2575
+ "grad_norm": 0.413644403219223,
2576
+ "learning_rate": 1.2248378005696889e-05,
2577
+ "loss": 0.8916,
2578
+ "step": 702
2579
+ },
2580
+ {
2581
+ "epoch": 1.4084084084084085,
2582
+ "grad_norm": 0.45839402079582214,
2583
+ "learning_rate": 1.209823497957314e-05,
2584
+ "loss": 0.8662,
2585
+ "step": 704
2586
+ },
2587
+ {
2588
+ "epoch": 1.4124124124124124,
2589
+ "grad_norm": 0.4414491653442383,
2590
+ "learning_rate": 1.1948723571334933e-05,
2591
+ "loss": 0.8382,
2592
+ "step": 706
2593
+ },
2594
+ {
2595
+ "epoch": 1.4164164164164164,
2596
+ "grad_norm": 0.43671172857284546,
2597
+ "learning_rate": 1.1799851100452066e-05,
2598
+ "loss": 0.8418,
2599
+ "step": 708
2600
+ },
2601
+ {
2602
+ "epoch": 1.4204204204204205,
2603
+ "grad_norm": 0.4703764021396637,
2604
+ "learning_rate": 1.1651624855114566e-05,
2605
+ "loss": 0.8407,
2606
+ "step": 710
2607
+ },
2608
+ {
2609
+ "epoch": 1.4244244244244244,
2610
+ "grad_norm": 0.4794108271598816,
2611
+ "learning_rate": 1.1504052091875916e-05,
2612
+ "loss": 0.8828,
2613
+ "step": 712
2614
+ },
2615
+ {
2616
+ "epoch": 1.4284284284284285,
2617
+ "grad_norm": 0.41678547859191895,
2618
+ "learning_rate": 1.1357140035297745e-05,
2619
+ "loss": 0.8714,
2620
+ "step": 714
2621
+ },
2622
+ {
2623
+ "epoch": 1.4324324324324325,
2624
+ "grad_norm": 0.4571875035762787,
2625
+ "learning_rate": 1.1210895877596194e-05,
2626
+ "loss": 0.8848,
2627
+ "step": 716
2628
+ },
2629
+ {
2630
+ "epoch": 1.4364364364364364,
2631
+ "grad_norm": 0.4822946786880493,
2632
+ "learning_rate": 1.1065326778289781e-05,
2633
+ "loss": 0.8514,
2634
+ "step": 718
2635
+ },
2636
+ {
2637
+ "epoch": 1.4404404404404405,
2638
+ "grad_norm": 0.392842561006546,
2639
+ "learning_rate": 1.092043986384893e-05,
2640
+ "loss": 0.842,
2641
+ "step": 720
2642
+ },
2643
+ {
2644
+ "epoch": 1.4444444444444444,
2645
+ "grad_norm": 0.43785953521728516,
2646
+ "learning_rate": 1.0776242227347045e-05,
2647
+ "loss": 0.8579,
2648
+ "step": 722
2649
+ },
2650
+ {
2651
+ "epoch": 1.4484484484484486,
2652
+ "grad_norm": 0.4331945776939392,
2653
+ "learning_rate": 1.0632740928113321e-05,
2654
+ "loss": 0.8866,
2655
+ "step": 724
2656
+ },
2657
+ {
2658
+ "epoch": 1.4524524524524525,
2659
+ "grad_norm": 0.3922359347343445,
2660
+ "learning_rate": 1.048994299138709e-05,
2661
+ "loss": 0.8631,
2662
+ "step": 726
2663
+ },
2664
+ {
2665
+ "epoch": 1.4564564564564564,
2666
+ "grad_norm": 0.46076324582099915,
2667
+ "learning_rate": 1.0347855407973934e-05,
2668
+ "loss": 0.8583,
2669
+ "step": 728
2670
+ },
2671
+ {
2672
+ "epoch": 1.4604604604604605,
2673
+ "grad_norm": 0.439680814743042,
2674
+ "learning_rate": 1.0206485133903424e-05,
2675
+ "loss": 0.8157,
2676
+ "step": 730
2677
+ },
2678
+ {
2679
+ "epoch": 1.4644644644644644,
2680
+ "grad_norm": 0.44809362292289734,
2681
+ "learning_rate": 1.0065839090088572e-05,
2682
+ "loss": 0.8127,
2683
+ "step": 732
2684
+ },
2685
+ {
2686
+ "epoch": 1.4684684684684686,
2687
+ "grad_norm": 0.46601828932762146,
2688
+ "learning_rate": 9.925924161987057e-06,
2689
+ "loss": 0.8641,
2690
+ "step": 734
2691
+ },
2692
+ {
2693
+ "epoch": 1.4724724724724725,
2694
+ "grad_norm": 0.4423384368419647,
2695
+ "learning_rate": 9.786747199264087e-06,
2696
+ "loss": 0.8645,
2697
+ "step": 736
2698
+ },
2699
+ {
2700
+ "epoch": 1.4764764764764764,
2701
+ "grad_norm": 0.4642850160598755,
2702
+ "learning_rate": 9.648315015457082e-06,
2703
+ "loss": 0.8303,
2704
+ "step": 738
2705
+ },
2706
+ {
2707
+ "epoch": 1.4804804804804805,
2708
+ "grad_norm": 0.4454893171787262,
2709
+ "learning_rate": 9.510634387642151e-06,
2710
+ "loss": 0.8334,
2711
+ "step": 740
2712
+ },
2713
+ {
2714
+ "epoch": 1.4844844844844844,
2715
+ "grad_norm": 0.5033170580863953,
2716
+ "learning_rate": 9.373712056102249e-06,
2717
+ "loss": 0.8668,
2718
+ "step": 742
2719
+ },
2720
+ {
2721
+ "epoch": 1.4884884884884886,
2722
+ "grad_norm": 0.45939940214157104,
2723
+ "learning_rate": 9.237554723997241e-06,
2724
+ "loss": 0.8321,
2725
+ "step": 744
2726
+ },
2727
+ {
2728
+ "epoch": 1.4924924924924925,
2729
+ "grad_norm": 0.42905375361442566,
2730
+ "learning_rate": 9.102169057035754e-06,
2731
+ "loss": 0.932,
2732
+ "step": 746
2733
+ },
2734
+ {
2735
+ "epoch": 1.4964964964964964,
2736
+ "grad_norm": 0.47114264965057373,
2737
+ "learning_rate": 8.967561683148798e-06,
2738
+ "loss": 0.8541,
2739
+ "step": 748
2740
+ },
2741
+ {
2742
+ "epoch": 1.5005005005005005,
2743
+ "grad_norm": 0.3895653188228607,
2744
+ "learning_rate": 8.833739192165352e-06,
2745
+ "loss": 0.8903,
2746
+ "step": 750
2747
+ },
2748
+ {
2749
+ "epoch": 1.5005005005005005,
2750
+ "eval_flock_task4_val_loss": 1.136841893196106,
2751
+ "eval_flock_task4_val_runtime": 2.2949,
2752
+ "eval_flock_task4_val_samples_per_second": 25.274,
2753
+ "eval_flock_task4_val_steps_per_second": 25.274,
2754
+ "step": 750
2755
+ },
2756
+ {
2757
+ "epoch": 1.5045045045045045,
2758
+ "grad_norm": 0.5534226894378662,
2759
+ "learning_rate": 8.700708135489721e-06,
2760
+ "loss": 0.8628,
2761
+ "step": 752
2762
+ },
2763
+ {
2764
+ "epoch": 1.5085085085085086,
2765
+ "grad_norm": 0.45723313093185425,
2766
+ "learning_rate": 8.56847502578078e-06,
2767
+ "loss": 0.8812,
2768
+ "step": 754
2769
+ },
2770
+ {
2771
+ "epoch": 1.5125125125125125,
2772
+ "grad_norm": 0.42593708634376526,
2773
+ "learning_rate": 8.43704633663321e-06,
2774
+ "loss": 0.8492,
2775
+ "step": 756
2776
+ },
2777
+ {
2778
+ "epoch": 1.5165165165165164,
2779
+ "grad_norm": 0.4144039452075958,
2780
+ "learning_rate": 8.306428502260511e-06,
2781
+ "loss": 0.8946,
2782
+ "step": 758
2783
+ },
2784
+ {
2785
+ "epoch": 1.5205205205205206,
2786
+ "grad_norm": 0.4269801080226898,
2787
+ "learning_rate": 8.176627917180024e-06,
2788
+ "loss": 0.8415,
2789
+ "step": 760
2790
+ },
2791
+ {
2792
+ "epoch": 1.5245245245245245,
2793
+ "grad_norm": 0.410341739654541,
2794
+ "learning_rate": 8.047650935899931e-06,
2795
+ "loss": 0.8318,
2796
+ "step": 762
2797
+ },
2798
+ {
2799
+ "epoch": 1.5285285285285286,
2800
+ "grad_norm": 0.4322713613510132,
2801
+ "learning_rate": 7.919503872608092e-06,
2802
+ "loss": 0.8473,
2803
+ "step": 764
2804
+ },
2805
+ {
2806
+ "epoch": 1.5325325325325325,
2807
+ "grad_norm": 0.5121660232543945,
2808
+ "learning_rate": 7.792193000862963e-06,
2809
+ "loss": 0.8559,
2810
+ "step": 766
2811
+ },
2812
+ {
2813
+ "epoch": 1.5365365365365364,
2814
+ "grad_norm": 0.4450767934322357,
2815
+ "learning_rate": 7.665724553286491e-06,
2816
+ "loss": 0.8338,
2817
+ "step": 768
2818
+ },
2819
+ {
2820
+ "epoch": 1.5405405405405406,
2821
+ "grad_norm": 0.4499673545360565,
2822
+ "learning_rate": 7.5401047212589444e-06,
2823
+ "loss": 0.9011,
2824
+ "step": 770
2825
+ },
2826
+ {
2827
+ "epoch": 1.5445445445445447,
2828
+ "grad_norm": 0.3775758445262909,
2829
+ "learning_rate": 7.415339654615824e-06,
2830
+ "loss": 0.8526,
2831
+ "step": 772
2832
+ },
2833
+ {
2834
+ "epoch": 1.5485485485485486,
2835
+ "grad_norm": 0.4253455102443695,
2836
+ "learning_rate": 7.291435461346827e-06,
2837
+ "loss": 0.8376,
2838
+ "step": 774
2839
+ },
2840
+ {
2841
+ "epoch": 1.5525525525525525,
2842
+ "grad_norm": 0.4507961869239807,
2843
+ "learning_rate": 7.1683982072967646e-06,
2844
+ "loss": 0.875,
2845
+ "step": 776
2846
+ },
2847
+ {
2848
+ "epoch": 1.5565565565565564,
2849
+ "grad_norm": 0.4244922697544098,
2850
+ "learning_rate": 7.0462339158686415e-06,
2851
+ "loss": 0.9,
2852
+ "step": 778
2853
+ },
2854
+ {
2855
+ "epoch": 1.5605605605605606,
2856
+ "grad_norm": 0.45657554268836975,
2857
+ "learning_rate": 6.924948567728786e-06,
2858
+ "loss": 0.8244,
2859
+ "step": 780
2860
+ },
2861
+ {
2862
+ "epoch": 1.5645645645645647,
2863
+ "grad_norm": 0.44866183400154114,
2864
+ "learning_rate": 6.804548100514013e-06,
2865
+ "loss": 0.849,
2866
+ "step": 782
2867
+ },
2868
+ {
2869
+ "epoch": 1.5685685685685686,
2870
+ "grad_norm": 0.4514263868331909,
2871
+ "learning_rate": 6.685038408540989e-06,
2872
+ "loss": 0.8307,
2873
+ "step": 784
2874
+ },
2875
+ {
2876
+ "epoch": 1.5725725725725725,
2877
+ "grad_norm": 0.4524141252040863,
2878
+ "learning_rate": 6.566425342517652e-06,
2879
+ "loss": 0.8082,
2880
+ "step": 786
2881
+ },
2882
+ {
2883
+ "epoch": 1.5765765765765765,
2884
+ "grad_norm": 0.5142974853515625,
2885
+ "learning_rate": 6.4487147092567675e-06,
2886
+ "loss": 0.8573,
2887
+ "step": 788
2888
+ },
2889
+ {
2890
+ "epoch": 1.5805805805805806,
2891
+ "grad_norm": 0.48223766684532166,
2892
+ "learning_rate": 6.331912271391688e-06,
2893
+ "loss": 0.8703,
2894
+ "step": 790
2895
+ },
2896
+ {
2897
+ "epoch": 1.5845845845845847,
2898
+ "grad_norm": 0.45007768273353577,
2899
+ "learning_rate": 6.216023747094207e-06,
2900
+ "loss": 0.8822,
2901
+ "step": 792
2902
+ },
2903
+ {
2904
+ "epoch": 1.5885885885885886,
2905
+ "grad_norm": 0.46107056736946106,
2906
+ "learning_rate": 6.101054809794615e-06,
2907
+ "loss": 0.8731,
2908
+ "step": 794
2909
+ },
2910
+ {
2911
+ "epoch": 1.5925925925925926,
2912
+ "grad_norm": 0.5555247664451599,
2913
+ "learning_rate": 5.987011087904007e-06,
2914
+ "loss": 0.7878,
2915
+ "step": 796
2916
+ },
2917
+ {
2918
+ "epoch": 1.5965965965965965,
2919
+ "grad_norm": 0.43157267570495605,
2920
+ "learning_rate": 5.873898164538657e-06,
2921
+ "loss": 0.8779,
2922
+ "step": 798
2923
+ },
2924
+ {
2925
+ "epoch": 1.6006006006006006,
2926
+ "grad_norm": 0.4325798451900482,
2927
+ "learning_rate": 5.7617215772467535e-06,
2928
+ "loss": 0.8346,
2929
+ "step": 800
2930
+ },
2931
+ {
2932
+ "epoch": 1.6006006006006006,
2933
+ "eval_flock_task4_val_loss": 1.1378659009933472,
2934
+ "eval_flock_task4_val_runtime": 2.3013,
2935
+ "eval_flock_task4_val_samples_per_second": 25.203,
2936
+ "eval_flock_task4_val_steps_per_second": 25.203,
2937
+ "step": 800
2938
+ },
2939
+ {
2940
+ "epoch": 1.6046046046046047,
2941
+ "grad_norm": 0.43533363938331604,
2942
+ "learning_rate": 5.650486817737291e-06,
2943
+ "loss": 0.8708,
2944
+ "step": 802
2945
+ },
2946
+ {
2947
+ "epoch": 1.6086086086086087,
2948
+ "grad_norm": 0.8679392337799072,
2949
+ "learning_rate": 5.54019933161119e-06,
2950
+ "loss": 0.8308,
2951
+ "step": 804
2952
+ },
2953
+ {
2954
+ "epoch": 1.6126126126126126,
2955
+ "grad_norm": 0.49564796686172485,
2956
+ "learning_rate": 5.430864518094731e-06,
2957
+ "loss": 0.8808,
2958
+ "step": 806
2959
+ },
2960
+ {
2961
+ "epoch": 1.6166166166166165,
2962
+ "grad_norm": 0.4227229356765747,
2963
+ "learning_rate": 5.322487729775233e-06,
2964
+ "loss": 0.9045,
2965
+ "step": 808
2966
+ },
2967
+ {
2968
+ "epoch": 1.6206206206206206,
2969
+ "grad_norm": 0.450801283121109,
2970
+ "learning_rate": 5.215074272338985e-06,
2971
+ "loss": 0.8726,
2972
+ "step": 810
2973
+ },
2974
+ {
2975
+ "epoch": 1.6246246246246248,
2976
+ "grad_norm": 0.4490666389465332,
2977
+ "learning_rate": 5.108629404311535e-06,
2978
+ "loss": 0.854,
2979
+ "step": 812
2980
+ },
2981
+ {
2982
+ "epoch": 1.6286286286286287,
2983
+ "grad_norm": 0.49601781368255615,
2984
+ "learning_rate": 5.003158336800218e-06,
2985
+ "loss": 0.9127,
2986
+ "step": 814
2987
+ },
2988
+ {
2989
+ "epoch": 1.6326326326326326,
2990
+ "grad_norm": 0.4565769135951996,
2991
+ "learning_rate": 4.898666233239083e-06,
2992
+ "loss": 0.8636,
2993
+ "step": 816
2994
+ },
2995
+ {
2996
+ "epoch": 1.6366366366366365,
2997
+ "grad_norm": 0.4938611090183258,
2998
+ "learning_rate": 4.795158209136066e-06,
2999
+ "loss": 0.8341,
3000
+ "step": 818
3001
+ },
3002
+ {
3003
+ "epoch": 1.6406406406406406,
3004
+ "grad_norm": 0.3954929709434509,
3005
+ "learning_rate": 4.692639331822604e-06,
3006
+ "loss": 0.8855,
3007
+ "step": 820
3008
+ },
3009
+ {
3010
+ "epoch": 1.6446446446446448,
3011
+ "grad_norm": 0.42091336846351624,
3012
+ "learning_rate": 4.5911146202055114e-06,
3013
+ "loss": 0.8929,
3014
+ "step": 822
3015
+ },
3016
+ {
3017
+ "epoch": 1.6486486486486487,
3018
+ "grad_norm": 0.49426716566085815,
3019
+ "learning_rate": 4.490589044521315e-06,
3020
+ "loss": 0.839,
3021
+ "step": 824
3022
+ },
3023
+ {
3024
+ "epoch": 1.6526526526526526,
3025
+ "grad_norm": 0.5828158259391785,
3026
+ "learning_rate": 4.39106752609291e-06,
3027
+ "loss": 0.8209,
3028
+ "step": 826
3029
+ },
3030
+ {
3031
+ "epoch": 1.6566566566566565,
3032
+ "grad_norm": 0.4805382788181305,
3033
+ "learning_rate": 4.292554937088622e-06,
3034
+ "loss": 0.8909,
3035
+ "step": 828
3036
+ },
3037
+ {
3038
+ "epoch": 1.6606606606606606,
3039
+ "grad_norm": 0.5196824669837952,
3040
+ "learning_rate": 4.195056100283726e-06,
3041
+ "loss": 0.8537,
3042
+ "step": 830
3043
+ },
3044
+ {
3045
+ "epoch": 1.6646646646646648,
3046
+ "grad_norm": 0.45226049423217773,
3047
+ "learning_rate": 4.098575788824297e-06,
3048
+ "loss": 0.8264,
3049
+ "step": 832
3050
+ },
3051
+ {
3052
+ "epoch": 1.6686686686686687,
3053
+ "grad_norm": 0.5464234352111816,
3054
+ "learning_rate": 4.003118725993554e-06,
3055
+ "loss": 0.832,
3056
+ "step": 834
3057
+ },
3058
+ {
3059
+ "epoch": 1.6726726726726726,
3060
+ "grad_norm": 0.5279391407966614,
3061
+ "learning_rate": 3.908689584980654e-06,
3062
+ "loss": 0.8355,
3063
+ "step": 836
3064
+ },
3065
+ {
3066
+ "epoch": 1.6766766766766765,
3067
+ "grad_norm": 0.5107043981552124,
3068
+ "learning_rate": 3.815292988651859e-06,
3069
+ "loss": 0.8848,
3070
+ "step": 838
3071
+ },
3072
+ {
3073
+ "epoch": 1.6806806806806807,
3074
+ "grad_norm": 0.49792614579200745,
3075
+ "learning_rate": 3.7229335093242585e-06,
3076
+ "loss": 0.8724,
3077
+ "step": 840
3078
+ },
3079
+ {
3080
+ "epoch": 1.6846846846846848,
3081
+ "grad_norm": 0.5087601542472839,
3082
+ "learning_rate": 3.6316156685419213e-06,
3083
+ "loss": 0.8495,
3084
+ "step": 842
3085
+ },
3086
+ {
3087
+ "epoch": 1.6886886886886887,
3088
+ "grad_norm": 0.4378841817378998,
3089
+ "learning_rate": 3.541343936854524e-06,
3090
+ "loss": 0.8915,
3091
+ "step": 844
3092
+ },
3093
+ {
3094
+ "epoch": 1.6926926926926926,
3095
+ "grad_norm": 0.47965216636657715,
3096
+ "learning_rate": 3.4521227335985145e-06,
3097
+ "loss": 0.7802,
3098
+ "step": 846
3099
+ },
3100
+ {
3101
+ "epoch": 1.6966966966966965,
3102
+ "grad_norm": 0.4828782379627228,
3103
+ "learning_rate": 3.363956426680728e-06,
3104
+ "loss": 0.8011,
3105
+ "step": 848
3106
+ },
3107
+ {
3108
+ "epoch": 1.7007007007007007,
3109
+ "grad_norm": 0.46208733320236206,
3110
+ "learning_rate": 3.276849332364587e-06,
3111
+ "loss": 0.8748,
3112
+ "step": 850
3113
+ },
3114
+ {
3115
+ "epoch": 1.7007007007007007,
3116
+ "eval_flock_task4_val_loss": 1.1365524530410767,
3117
+ "eval_flock_task4_val_runtime": 2.2775,
3118
+ "eval_flock_task4_val_samples_per_second": 25.466,
3119
+ "eval_flock_task4_val_steps_per_second": 25.466,
3120
+ "step": 850
3121
+ },
3122
+ {
3123
+ "epoch": 1.7047047047047048,
3124
+ "grad_norm": 0.38446688652038574,
3125
+ "learning_rate": 3.1908057150587643e-06,
3126
+ "loss": 0.8712,
3127
+ "step": 852
3128
+ },
3129
+ {
3130
+ "epoch": 1.7087087087087087,
3131
+ "grad_norm": 0.43955543637275696,
3132
+ "learning_rate": 3.105829787108444e-06,
3133
+ "loss": 0.8534,
3134
+ "step": 854
3135
+ },
3136
+ {
3137
+ "epoch": 1.7127127127127126,
3138
+ "grad_norm": 0.44339418411254883,
3139
+ "learning_rate": 3.0219257085890656e-06,
3140
+ "loss": 0.835,
3141
+ "step": 856
3142
+ },
3143
+ {
3144
+ "epoch": 1.7167167167167166,
3145
+ "grad_norm": 0.5061709880828857,
3146
+ "learning_rate": 2.939097587102704e-06,
3147
+ "loss": 0.8415,
3148
+ "step": 858
3149
+ },
3150
+ {
3151
+ "epoch": 1.7207207207207207,
3152
+ "grad_norm": 0.4325864315032959,
3153
+ "learning_rate": 2.8573494775769484e-06,
3154
+ "loss": 0.8284,
3155
+ "step": 860
3156
+ },
3157
+ {
3158
+ "epoch": 1.7247247247247248,
3159
+ "grad_norm": 0.46651405096054077,
3160
+ "learning_rate": 2.776685382066396e-06,
3161
+ "loss": 0.8204,
3162
+ "step": 862
3163
+ },
3164
+ {
3165
+ "epoch": 1.7287287287287287,
3166
+ "grad_norm": 0.46017175912857056,
3167
+ "learning_rate": 2.697109249556748e-06,
3168
+ "loss": 0.7886,
3169
+ "step": 864
3170
+ },
3171
+ {
3172
+ "epoch": 1.7327327327327327,
3173
+ "grad_norm": 0.45303404331207275,
3174
+ "learning_rate": 2.618624975771447e-06,
3175
+ "loss": 0.7975,
3176
+ "step": 866
3177
+ },
3178
+ {
3179
+ "epoch": 1.7367367367367368,
3180
+ "grad_norm": 0.4538724720478058,
3181
+ "learning_rate": 2.541236402980987e-06,
3182
+ "loss": 0.816,
3183
+ "step": 868
3184
+ },
3185
+ {
3186
+ "epoch": 1.7407407407407407,
3187
+ "grad_norm": 0.4861656725406647,
3188
+ "learning_rate": 2.464947319814806e-06,
3189
+ "loss": 0.762,
3190
+ "step": 870
3191
+ },
3192
+ {
3193
+ "epoch": 1.7447447447447448,
3194
+ "grad_norm": 0.5382648706436157,
3195
+ "learning_rate": 2.3897614610757983e-06,
3196
+ "loss": 0.8531,
3197
+ "step": 872
3198
+ },
3199
+ {
3200
+ "epoch": 1.7487487487487487,
3201
+ "grad_norm": 0.4602164328098297,
3202
+ "learning_rate": 2.3156825075574958e-06,
3203
+ "loss": 0.8246,
3204
+ "step": 874
3205
+ },
3206
+ {
3207
+ "epoch": 1.7527527527527527,
3208
+ "grad_norm": 0.517173707485199,
3209
+ "learning_rate": 2.242714085863842e-06,
3210
+ "loss": 0.8728,
3211
+ "step": 876
3212
+ },
3213
+ {
3214
+ "epoch": 1.7567567567567568,
3215
+ "grad_norm": 0.48782795667648315,
3216
+ "learning_rate": 2.1708597682316644e-06,
3217
+ "loss": 0.8758,
3218
+ "step": 878
3219
+ },
3220
+ {
3221
+ "epoch": 1.7607607607607607,
3222
+ "grad_norm": 0.40246081352233887,
3223
+ "learning_rate": 2.1001230723558083e-06,
3224
+ "loss": 0.8576,
3225
+ "step": 880
3226
+ },
3227
+ {
3228
+ "epoch": 1.7647647647647648,
3229
+ "grad_norm": 0.45257192850112915,
3230
+ "learning_rate": 2.0305074612168906e-06,
3231
+ "loss": 0.8405,
3232
+ "step": 882
3233
+ },
3234
+ {
3235
+ "epoch": 1.7687687687687688,
3236
+ "grad_norm": 0.49757951498031616,
3237
+ "learning_rate": 1.9620163429117905e-06,
3238
+ "loss": 0.7962,
3239
+ "step": 884
3240
+ },
3241
+ {
3242
+ "epoch": 1.7727727727727727,
3243
+ "grad_norm": 0.4517136514186859,
3244
+ "learning_rate": 1.894653070486807e-06,
3245
+ "loss": 0.8599,
3246
+ "step": 886
3247
+ },
3248
+ {
3249
+ "epoch": 1.7767767767767768,
3250
+ "grad_norm": 0.3954245448112488,
3251
+ "learning_rate": 1.828420941773476e-06,
3252
+ "loss": 0.8918,
3253
+ "step": 888
3254
+ },
3255
+ {
3256
+ "epoch": 1.7807807807807807,
3257
+ "grad_norm": 0.46916237473487854,
3258
+ "learning_rate": 1.763323199227157e-06,
3259
+ "loss": 0.8613,
3260
+ "step": 890
3261
+ },
3262
+ {
3263
+ "epoch": 1.7847847847847849,
3264
+ "grad_norm": 0.4551919102668762,
3265
+ "learning_rate": 1.6993630297682778e-06,
3266
+ "loss": 0.8169,
3267
+ "step": 892
3268
+ },
3269
+ {
3270
+ "epoch": 1.7887887887887888,
3271
+ "grad_norm": 0.5219541788101196,
3272
+ "learning_rate": 1.6365435646263222e-06,
3273
+ "loss": 0.8465,
3274
+ "step": 894
3275
+ },
3276
+ {
3277
+ "epoch": 1.7927927927927927,
3278
+ "grad_norm": 0.45977309346199036,
3279
+ "learning_rate": 1.5748678791865228e-06,
3280
+ "loss": 0.8893,
3281
+ "step": 896
3282
+ },
3283
+ {
3284
+ "epoch": 1.7967967967967968,
3285
+ "grad_norm": 0.5053537487983704,
3286
+ "learning_rate": 1.5143389928393398e-06,
3287
+ "loss": 0.8646,
3288
+ "step": 898
3289
+ },
3290
+ {
3291
+ "epoch": 1.800800800800801,
3292
+ "grad_norm": 0.5736296772956848,
3293
+ "learning_rate": 1.4549598688325893e-06,
3294
+ "loss": 0.8026,
3295
+ "step": 900
3296
+ },
3297
+ {
3298
+ "epoch": 1.800800800800801,
3299
+ "eval_flock_task4_val_loss": 1.1379015445709229,
3300
+ "eval_flock_task4_val_runtime": 2.2904,
3301
+ "eval_flock_task4_val_samples_per_second": 25.323,
3302
+ "eval_flock_task4_val_steps_per_second": 25.323,
3303
+ "step": 900
3304
+ },
3305
+ {
3306
+ "epoch": 1.8048048048048049,
3307
+ "grad_norm": 0.4098823070526123,
3308
+ "learning_rate": 1.3967334141264277e-06,
3309
+ "loss": 0.889,
3310
+ "step": 902
3311
+ },
3312
+ {
3313
+ "epoch": 1.8088088088088088,
3314
+ "grad_norm": 0.4983745217323303,
3315
+ "learning_rate": 1.3396624792510083e-06,
3316
+ "loss": 0.801,
3317
+ "step": 904
3318
+ },
3319
+ {
3320
+ "epoch": 1.8128128128128127,
3321
+ "grad_norm": 0.4158942997455597,
3322
+ "learning_rate": 1.2837498581669272e-06,
3323
+ "loss": 0.8228,
3324
+ "step": 906
3325
+ },
3326
+ {
3327
+ "epoch": 1.8168168168168168,
3328
+ "grad_norm": 0.46956199407577515,
3329
+ "learning_rate": 1.2289982881284718e-06,
3330
+ "loss": 0.8589,
3331
+ "step": 908
3332
+ },
3333
+ {
3334
+ "epoch": 1.820820820820821,
3335
+ "grad_norm": 0.38610410690307617,
3336
+ "learning_rate": 1.1754104495495883e-06,
3337
+ "loss": 0.8549,
3338
+ "step": 910
3339
+ },
3340
+ {
3341
+ "epoch": 1.8248248248248249,
3342
+ "grad_norm": 0.4316381812095642,
3343
+ "learning_rate": 1.1229889658726622e-06,
3344
+ "loss": 0.8648,
3345
+ "step": 912
3346
+ },
3347
+ {
3348
+ "epoch": 1.8288288288288288,
3349
+ "grad_norm": 0.4447328746318817,
3350
+ "learning_rate": 1.0717364034401074e-06,
3351
+ "loss": 0.8273,
3352
+ "step": 914
3353
+ },
3354
+ {
3355
+ "epoch": 1.8328328328328327,
3356
+ "grad_norm": 0.47008782625198364,
3357
+ "learning_rate": 1.0216552713686988e-06,
3358
+ "loss": 0.8811,
3359
+ "step": 916
3360
+ },
3361
+ {
3362
+ "epoch": 1.8368368368368369,
3363
+ "grad_norm": 0.41356533765792847,
3364
+ "learning_rate": 9.72748021426756e-07,
3365
+ "loss": 0.8253,
3366
+ "step": 918
3367
+ },
3368
+ {
3369
+ "epoch": 1.840840840840841,
3370
+ "grad_norm": 0.43283718824386597,
3371
+ "learning_rate": 9.250170479141146e-07,
3372
+ "loss": 0.8694,
3373
+ "step": 920
3374
+ },
3375
+ {
3376
+ "epoch": 1.844844844844845,
3377
+ "grad_norm": 0.46151700615882874,
3378
+ "learning_rate": 8.784646875448971e-07,
3379
+ "loss": 0.8889,
3380
+ "step": 922
3381
+ },
3382
+ {
3383
+ "epoch": 1.8488488488488488,
3384
+ "grad_norm": 0.4734440743923187,
3385
+ "learning_rate": 8.330932193331226e-07,
3386
+ "loss": 0.8338,
3387
+ "step": 924
3388
+ },
3389
+ {
3390
+ "epoch": 1.8528528528528527,
3391
+ "grad_norm": 0.44311681389808655,
3392
+ "learning_rate": 7.889048644811519e-07,
3393
+ "loss": 0.8679,
3394
+ "step": 926
3395
+ },
3396
+ {
3397
+ "epoch": 1.8568568568568569,
3398
+ "grad_norm": 0.5000930428504944,
3399
+ "learning_rate": 7.459017862709194e-07,
3400
+ "loss": 0.8324,
3401
+ "step": 928
3402
+ },
3403
+ {
3404
+ "epoch": 1.860860860860861,
3405
+ "grad_norm": 0.422635555267334,
3406
+ "learning_rate": 7.040860899580476e-07,
3407
+ "loss": 0.88,
3408
+ "step": 930
3409
+ },
3410
+ {
3411
+ "epoch": 1.864864864864865,
3412
+ "grad_norm": 0.4244588017463684,
3413
+ "learning_rate": 6.634598226687771e-07,
3414
+ "loss": 0.8555,
3415
+ "step": 932
3416
+ },
3417
+ {
3418
+ "epoch": 1.8688688688688688,
3419
+ "grad_norm": 1.2747561931610107,
3420
+ "learning_rate": 6.240249732997361e-07,
3421
+ "loss": 0.8798,
3422
+ "step": 934
3423
+ },
3424
+ {
3425
+ "epoch": 1.8728728728728727,
3426
+ "grad_norm": 0.4664041996002197,
3427
+ "learning_rate": 5.85783472420598e-07,
3428
+ "loss": 0.8003,
3429
+ "step": 936
3430
+ },
3431
+ {
3432
+ "epoch": 1.8768768768768769,
3433
+ "grad_norm": 0.5424234867095947,
3434
+ "learning_rate": 5.487371921795381e-07,
3435
+ "loss": 0.8488,
3436
+ "step": 938
3437
+ },
3438
+ {
3439
+ "epoch": 1.880880880880881,
3440
+ "grad_norm": 0.4183599352836609,
3441
+ "learning_rate": 5.12887946211607e-07,
3442
+ "loss": 0.8356,
3443
+ "step": 940
3444
+ },
3445
+ {
3446
+ "epoch": 1.884884884884885,
3447
+ "grad_norm": 0.5235341787338257,
3448
+ "learning_rate": 4.782374895499236e-07,
3449
+ "loss": 0.8021,
3450
+ "step": 942
3451
+ },
3452
+ {
3453
+ "epoch": 1.8888888888888888,
3454
+ "grad_norm": 0.4295443892478943,
3455
+ "learning_rate": 4.4478751853976597e-07,
3456
+ "loss": 0.8604,
3457
+ "step": 944
3458
+ },
3459
+ {
3460
+ "epoch": 1.8928928928928928,
3461
+ "grad_norm": 0.4572451114654541,
3462
+ "learning_rate": 4.1253967075552124e-07,
3463
+ "loss": 0.8838,
3464
+ "step": 946
3465
+ },
3466
+ {
3467
+ "epoch": 1.896896896896897,
3468
+ "grad_norm": 0.4556294083595276,
3469
+ "learning_rate": 3.814955249205221e-07,
3470
+ "loss": 0.8709,
3471
+ "step": 948
3472
+ },
3473
+ {
3474
+ "epoch": 1.900900900900901,
3475
+ "grad_norm": 0.4841032028198242,
3476
+ "learning_rate": 3.5165660082975005e-07,
3477
+ "loss": 0.8514,
3478
+ "step": 950
3479
+ },
3480
+ {
3481
+ "epoch": 1.900900900900901,
3482
+ "eval_flock_task4_val_loss": 1.1388740539550781,
3483
+ "eval_flock_task4_val_runtime": 2.3026,
3484
+ "eval_flock_task4_val_samples_per_second": 25.189,
3485
+ "eval_flock_task4_val_steps_per_second": 25.189,
3486
+ "step": 950
3487
+ },
3488
+ {
3489
+ "epoch": 1.904904904904905,
3490
+ "grad_norm": 0.4695403575897217,
3491
+ "learning_rate": 3.230243592754367e-07,
3492
+ "loss": 0.8065,
3493
+ "step": 952
3494
+ },
3495
+ {
3496
+ "epoch": 1.9089089089089089,
3497
+ "grad_norm": 0.5065103769302368,
3498
+ "learning_rate": 2.9560020197555714e-07,
3499
+ "loss": 0.8747,
3500
+ "step": 954
3501
+ },
3502
+ {
3503
+ "epoch": 1.9129129129129128,
3504
+ "grad_norm": 0.48485851287841797,
3505
+ "learning_rate": 2.6938547150518743e-07,
3506
+ "loss": 0.8536,
3507
+ "step": 956
3508
+ },
3509
+ {
3510
+ "epoch": 1.916916916916917,
3511
+ "grad_norm": 0.45243096351623535,
3512
+ "learning_rate": 2.443814512308018e-07,
3513
+ "loss": 0.8555,
3514
+ "step": 958
3515
+ },
3516
+ {
3517
+ "epoch": 1.920920920920921,
3518
+ "grad_norm": 0.4358191192150116,
3519
+ "learning_rate": 2.2058936524742835e-07,
3520
+ "loss": 0.8594,
3521
+ "step": 960
3522
+ },
3523
+ {
3524
+ "epoch": 1.924924924924925,
3525
+ "grad_norm": 0.4899273216724396,
3526
+ "learning_rate": 1.9801037831872482e-07,
3527
+ "loss": 0.8678,
3528
+ "step": 962
3529
+ },
3530
+ {
3531
+ "epoch": 1.9289289289289289,
3532
+ "grad_norm": 0.47123733162879944,
3533
+ "learning_rate": 1.766455958199631e-07,
3534
+ "loss": 0.9019,
3535
+ "step": 964
3536
+ },
3537
+ {
3538
+ "epoch": 1.9329329329329328,
3539
+ "grad_norm": 0.5304355025291443,
3540
+ "learning_rate": 1.564960636839058e-07,
3541
+ "loss": 0.8371,
3542
+ "step": 966
3543
+ },
3544
+ {
3545
+ "epoch": 1.936936936936937,
3546
+ "grad_norm": 0.4939720034599304,
3547
+ "learning_rate": 1.3756276834960557e-07,
3548
+ "loss": 0.8776,
3549
+ "step": 968
3550
+ },
3551
+ {
3552
+ "epoch": 1.940940940940941,
3553
+ "grad_norm": 0.4805956482887268,
3554
+ "learning_rate": 1.19846636714116e-07,
3555
+ "loss": 0.8481,
3556
+ "step": 970
3557
+ },
3558
+ {
3559
+ "epoch": 1.944944944944945,
3560
+ "grad_norm": 0.49638184905052185,
3561
+ "learning_rate": 1.0334853608710837e-07,
3562
+ "loss": 0.8513,
3563
+ "step": 972
3564
+ },
3565
+ {
3566
+ "epoch": 1.9489489489489489,
3567
+ "grad_norm": 0.4554474353790283,
3568
+ "learning_rate": 8.80692741484196e-08,
3569
+ "loss": 0.8635,
3570
+ "step": 974
3571
+ },
3572
+ {
3573
+ "epoch": 1.9529529529529528,
3574
+ "grad_norm": 0.4783639907836914,
3575
+ "learning_rate": 7.400959890850046e-08,
3576
+ "loss": 0.8719,
3577
+ "step": 976
3578
+ },
3579
+ {
3580
+ "epoch": 1.956956956956957,
3581
+ "grad_norm": 0.4808086156845093,
3582
+ "learning_rate": 6.117019867181162e-08,
3583
+ "loss": 0.878,
3584
+ "step": 978
3585
+ },
3586
+ {
3587
+ "epoch": 1.960960960960961,
3588
+ "grad_norm": 0.4793371260166168,
3589
+ "learning_rate": 4.955170200310888e-08,
3590
+ "loss": 0.85,
3591
+ "step": 980
3592
+ },
3593
+ {
3594
+ "epoch": 1.964964964964965,
3595
+ "grad_norm": 0.45383748412132263,
3596
+ "learning_rate": 3.9154677696687235e-08,
3597
+ "loss": 0.8224,
3598
+ "step": 982
3599
+ },
3600
+ {
3601
+ "epoch": 1.968968968968969,
3602
+ "grad_norm": 0.4468953609466553,
3603
+ "learning_rate": 2.997963474852261e-08,
3604
+ "loss": 0.8869,
3605
+ "step": 984
3606
+ },
3607
+ {
3608
+ "epoch": 1.972972972972973,
3609
+ "grad_norm": 0.46686744689941406,
3610
+ "learning_rate": 2.2027022331361224e-08,
3611
+ "loss": 0.8786,
3612
+ "step": 986
3613
+ },
3614
+ {
3615
+ "epoch": 1.976976976976977,
3616
+ "grad_norm": 0.3748922646045685,
3617
+ "learning_rate": 1.5297229772726074e-08,
3618
+ "loss": 0.9047,
3619
+ "step": 988
3620
+ },
3621
+ {
3622
+ "epoch": 1.980980980980981,
3623
+ "grad_norm": 0.4514774680137634,
3624
+ "learning_rate": 9.79058653586551e-09,
3625
+ "loss": 0.846,
3626
+ "step": 990
3627
+ },
3628
+ {
3629
+ "epoch": 1.984984984984985,
3630
+ "grad_norm": 0.4313613474369049,
3631
+ "learning_rate": 5.507362203607813e-09,
3632
+ "loss": 0.8178,
3633
+ "step": 992
3634
+ },
3635
+ {
3636
+ "epoch": 1.988988988988989,
3637
+ "grad_norm": 0.43718430399894714,
3638
+ "learning_rate": 2.4477664651800793e-09,
3639
+ "loss": 0.851,
3640
+ "step": 994
3641
+ },
3642
+ {
3643
+ "epoch": 1.992992992992993,
3644
+ "grad_norm": 0.4382748007774353,
3645
+ "learning_rate": 6.119491059303206e-10,
3646
+ "loss": 0.7938,
3647
+ "step": 996
3648
+ },
3649
+ {
3650
+ "epoch": 1.996996996996997,
3651
+ "grad_norm": 0.4784489572048187,
3652
+ "learning_rate": 0.0,
3653
+ "loss": 0.8333,
3654
+ "step": 998
3655
+ },
3656
+ {
3657
+ "epoch": 1.996996996996997,
3658
+ "step": 998,
3659
+ "total_flos": 2.4596562853380096e+17,
3660
+ "train_loss": 0.9170954039913858,
3661
+ "train_runtime": 1533.9501,
3662
+ "train_samples_per_second": 10.411,
3663
+ "train_steps_per_second": 0.651
3664
+ }
3665
+ ],
3666
+ "logging_steps": 2,
3667
+ "max_steps": 998,
3668
+ "num_input_tokens_seen": 0,
3669
+ "num_train_epochs": 2,
3670
+ "save_steps": 100,
3671
+ "stateful_callbacks": {
3672
+ "TrainerControl": {
3673
+ "args": {
3674
+ "should_epoch_stop": false,
3675
+ "should_evaluate": false,
3676
+ "should_log": false,
3677
+ "should_save": true,
3678
+ "should_training_stop": true
3679
+ },
3680
+ "attributes": {}
3681
+ }
3682
+ },
3683
+ "total_flos": 2.4596562853380096e+17,
3684
+ "train_batch_size": 8,
3685
+ "trial_name": null,
3686
+ "trial_params": null
3687
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02b043d66f32038d59956cfea3cf21737edbf7db71a52b7f2ba37f0722ed97f9
3
+ size 5624