Hugging Face's logo

Globaly
/
Globaly-1-Ladrillos-es-v0.1

Text Generation
TensorBoard
Safetensors
Trained with AutoTrain
Model card Files Metrics Community
Globaly commited on
Commit
1fdc4c2
•
1 Parent(s): dbfd96e

Upload 33 files

Browse files
Files changed (33) hide show
  1. README.md +9 -0
  2. adapter_config.json +21 -0
  3. adapter_model.safetensors +3 -0
  4. added_tokens.json +3 -0
  5. checkpoint-3500/README.md +34 -0
  6. checkpoint-3500/adapter_config.json +21 -0
  7. checkpoint-3500/adapter_model.bin +3 -0
  8. checkpoint-3500/adapter_model.safetensors +3 -0
  9. checkpoint-3500/added_tokens.json +3 -0
  10. checkpoint-3500/optimizer.pt +3 -0
  11. checkpoint-3500/pytorch_model.bin +3 -0
  12. checkpoint-3500/rng_state_0.pth +3 -0
  13. checkpoint-3500/rng_state_1.pth +3 -0
  14. checkpoint-3500/rng_state_2.pth +3 -0
  15. checkpoint-3500/rng_state_3.pth +3 -0
  16. checkpoint-3500/rng_state_4.pth +3 -0
  17. checkpoint-3500/rng_state_5.pth +3 -0
  18. checkpoint-3500/rng_state_6.pth +3 -0
  19. checkpoint-3500/rng_state_7.pth +3 -0
  20. checkpoint-3500/scheduler.pt +3 -0
  21. checkpoint-3500/special_tokens_map.json +30 -0
  22. checkpoint-3500/tokenizer.json +0 -0
  23. checkpoint-3500/tokenizer.model +3 -0
  24. checkpoint-3500/tokenizer_config.json +49 -0
  25. checkpoint-3500/trainer_state.json +1069 -0
  26. checkpoint-3500/training_args.bin +3 -0
  27. runs/Dec09_15-58-56_globaly/events.out.tfevents.1702159147.globaly.90463.0 +3 -0
  28. special_tokens_map.json +30 -0
  29. tokenizer.json +0 -0
  30. tokenizer.model +3 -0
  31. tokenizer_config.json +49 -0
  32. training_args.bin +3 -0
  33. training_params.json +1 -0
README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - autotrain
4
+ - text-generation
5
+ widget:
6
+ - text: "I love AutoTrain because "
7
+ ---
8
+
9
+ # Model Trained Using AutoTrain
adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "marianbasti/Llama-2-13b-fp16-alpaca-spanish",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 32,
11
+ "lora_dropout": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 16,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51065c696c7b84688f4fcb9339b75366f0d43c43983a93a0eb8cc0793d2fddd2
3
+ size 52450328
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<PAD>": 32000
3
+ }
checkpoint-3500/README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float16
18
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: False
22
+ - load_in_4bit: True
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: nf4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float16
30
+ ### Framework versions
31
+
32
+ - PEFT 0.5.0
33
+
34
+ - PEFT 0.5.0
checkpoint-3500/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "marianbasti/Llama-2-13b-fp16-alpaca-spanish",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 32,
11
+ "lora_dropout": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 16,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-3500/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2e0cab6e809e01b5f6614a01311d6956c17046385b79f51877556d86838b0db
3
+ size 52486922
checkpoint-3500/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51065c696c7b84688f4fcb9339b75366f0d43c43983a93a0eb8cc0793d2fddd2
3
+ size 52450328
checkpoint-3500/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<PAD>": 32000
3
+ }
checkpoint-3500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f08eab127c1c605d079954f3dd2077616476d3770a89ef09edbdbf004b2d3a16
3
+ size 104992698
checkpoint-3500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
3
+ size 888
checkpoint-3500/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5a681e456e8a692fb37d9caf2471a4753c0acca3a13cb3bb9a78d2fec8d9a2f
3
+ size 15984
checkpoint-3500/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713bb18554a1e3c5a72833dfa19d0cf3225ae83aae08d9049d68228cda74383e
3
+ size 15984
checkpoint-3500/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4ca494ba118e14ec8e654393614df828412dc097871766af0a81032a64c2495
3
+ size 15984
checkpoint-3500/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3c2090bc8b9b1fe895ee9061b74f9c9e536eb5d6521091690f9516484bcbc8b
3
+ size 15984
checkpoint-3500/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e11b047e7c6986ed844dc44e6db43f005d863e8fd69b192ed100b64c0e6119e0
3
+ size 15984
checkpoint-3500/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:114992f466b025b197187c7cfb9d43ebd40be10d6a618bae7f5beb587c622ace
3
+ size 15984
checkpoint-3500/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a91359054d826e5cad9fa38e6b8a8896d5828b0b3d1e7c3da102b689f76457e
3
+ size 15984
checkpoint-3500/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6aa26f22bce34b072b635062e87a6dd6933261670119052ef2c4b422c8c5b60
3
+ size 15984
checkpoint-3500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32162909fb4ad1aaa8310854cc0e657acd87e31128a5b09c62d070c09f4e3b3a
3
+ size 1064
checkpoint-3500/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<PAD>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-3500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3500/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-3500/tokenizer_config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<PAD>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "bos_token": "<s>",
39
+ "clean_up_tokenization_spaces": false,
40
+ "eos_token": "</s>",
41
+ "legacy": true,
42
+ "model_max_length": 1024,
43
+ "pad_token": "<PAD>",
44
+ "sp_model_kwargs": {},
45
+ "spaces_between_special_tokens": false,
46
+ "tokenizer_class": "LlamaTokenizer",
47
+ "unk_token": "<unk>",
48
+ "use_default_system_prompt": false
49
+ }
checkpoint-3500/trainer_state.json ADDED
@@ -0,0 +1,1069 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.997715591090805,
5
+ "eval_steps": 500,
6
+ "global_step": 3500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "learning_rate": 1.1428571428571429e-05,
14
+ "loss": 1.2017,
15
+ "step": 20
16
+ },
17
+ {
18
+ "epoch": 0.05,
19
+ "learning_rate": 2.2857142857142858e-05,
20
+ "loss": 1.0787,
21
+ "step": 40
22
+ },
23
+ {
24
+ "epoch": 0.07,
25
+ "learning_rate": 3.428571428571429e-05,
26
+ "loss": 0.8575,
27
+ "step": 60
28
+ },
29
+ {
30
+ "epoch": 0.09,
31
+ "learning_rate": 4.5714285714285716e-05,
32
+ "loss": 0.6726,
33
+ "step": 80
34
+ },
35
+ {
36
+ "epoch": 0.11,
37
+ "learning_rate": 5.714285714285714e-05,
38
+ "loss": 0.5158,
39
+ "step": 100
40
+ },
41
+ {
42
+ "epoch": 0.14,
43
+ "learning_rate": 6.857142857142858e-05,
44
+ "loss": 0.4596,
45
+ "step": 120
46
+ },
47
+ {
48
+ "epoch": 0.16,
49
+ "learning_rate": 8e-05,
50
+ "loss": 0.3966,
51
+ "step": 140
52
+ },
53
+ {
54
+ "epoch": 0.18,
55
+ "learning_rate": 9.142857142857143e-05,
56
+ "loss": 0.3319,
57
+ "step": 160
58
+ },
59
+ {
60
+ "epoch": 0.21,
61
+ "learning_rate": 0.00010285714285714286,
62
+ "loss": 0.2927,
63
+ "step": 180
64
+ },
65
+ {
66
+ "epoch": 0.23,
67
+ "learning_rate": 0.00011428571428571428,
68
+ "loss": 0.2578,
69
+ "step": 200
70
+ },
71
+ {
72
+ "epoch": 0.25,
73
+ "learning_rate": 0.00012571428571428572,
74
+ "loss": 0.2507,
75
+ "step": 220
76
+ },
77
+ {
78
+ "epoch": 0.27,
79
+ "learning_rate": 0.00013714285714285716,
80
+ "loss": 0.2223,
81
+ "step": 240
82
+ },
83
+ {
84
+ "epoch": 0.3,
85
+ "learning_rate": 0.00014857142857142857,
86
+ "loss": 0.2021,
87
+ "step": 260
88
+ },
89
+ {
90
+ "epoch": 0.32,
91
+ "learning_rate": 0.00016,
92
+ "loss": 0.1848,
93
+ "step": 280
94
+ },
95
+ {
96
+ "epoch": 0.34,
97
+ "learning_rate": 0.00017142857142857143,
98
+ "loss": 0.1727,
99
+ "step": 300
100
+ },
101
+ {
102
+ "epoch": 0.37,
103
+ "learning_rate": 0.00018285714285714286,
104
+ "loss": 0.1633,
105
+ "step": 320
106
+ },
107
+ {
108
+ "epoch": 0.39,
109
+ "learning_rate": 0.0001942857142857143,
110
+ "loss": 0.1532,
111
+ "step": 340
112
+ },
113
+ {
114
+ "epoch": 0.41,
115
+ "learning_rate": 0.00019936507936507938,
116
+ "loss": 0.1502,
117
+ "step": 360
118
+ },
119
+ {
120
+ "epoch": 0.43,
121
+ "learning_rate": 0.0001980952380952381,
122
+ "loss": 0.142,
123
+ "step": 380
124
+ },
125
+ {
126
+ "epoch": 0.46,
127
+ "learning_rate": 0.00019682539682539682,
128
+ "loss": 0.1393,
129
+ "step": 400
130
+ },
131
+ {
132
+ "epoch": 0.48,
133
+ "learning_rate": 0.00019555555555555556,
134
+ "loss": 0.1345,
135
+ "step": 420
136
+ },
137
+ {
138
+ "epoch": 0.5,
139
+ "learning_rate": 0.0001942857142857143,
140
+ "loss": 0.1305,
141
+ "step": 440
142
+ },
143
+ {
144
+ "epoch": 0.53,
145
+ "learning_rate": 0.00019301587301587302,
146
+ "loss": 0.1282,
147
+ "step": 460
148
+ },
149
+ {
150
+ "epoch": 0.55,
151
+ "learning_rate": 0.00019174603174603176,
152
+ "loss": 0.124,
153
+ "step": 480
154
+ },
155
+ {
156
+ "epoch": 0.57,
157
+ "learning_rate": 0.00019047619047619048,
158
+ "loss": 0.1238,
159
+ "step": 500
160
+ },
161
+ {
162
+ "epoch": 0.59,
163
+ "learning_rate": 0.0001892063492063492,
164
+ "loss": 0.1221,
165
+ "step": 520
166
+ },
167
+ {
168
+ "epoch": 0.62,
169
+ "learning_rate": 0.00018793650793650794,
170
+ "loss": 0.1185,
171
+ "step": 540
172
+ },
173
+ {
174
+ "epoch": 0.64,
175
+ "learning_rate": 0.0001866666666666667,
176
+ "loss": 0.1182,
177
+ "step": 560
178
+ },
179
+ {
180
+ "epoch": 0.66,
181
+ "learning_rate": 0.0001853968253968254,
182
+ "loss": 0.1183,
183
+ "step": 580
184
+ },
185
+ {
186
+ "epoch": 0.69,
187
+ "learning_rate": 0.00018412698412698412,
188
+ "loss": 0.1151,
189
+ "step": 600
190
+ },
191
+ {
192
+ "epoch": 0.71,
193
+ "learning_rate": 0.00018285714285714286,
194
+ "loss": 0.119,
195
+ "step": 620
196
+ },
197
+ {
198
+ "epoch": 0.73,
199
+ "learning_rate": 0.00018158730158730158,
200
+ "loss": 0.1161,
201
+ "step": 640
202
+ },
203
+ {
204
+ "epoch": 0.75,
205
+ "learning_rate": 0.00018031746031746033,
206
+ "loss": 0.1139,
207
+ "step": 660
208
+ },
209
+ {
210
+ "epoch": 0.78,
211
+ "learning_rate": 0.00017904761904761907,
212
+ "loss": 0.113,
213
+ "step": 680
214
+ },
215
+ {
216
+ "epoch": 0.8,
217
+ "learning_rate": 0.00017777777777777779,
218
+ "loss": 0.1098,
219
+ "step": 700
220
+ },
221
+ {
222
+ "epoch": 0.82,
223
+ "learning_rate": 0.0001765079365079365,
224
+ "loss": 0.1136,
225
+ "step": 720
226
+ },
227
+ {
228
+ "epoch": 0.85,
229
+ "learning_rate": 0.00017523809523809525,
230
+ "loss": 0.1094,
231
+ "step": 740
232
+ },
233
+ {
234
+ "epoch": 0.87,
235
+ "learning_rate": 0.000173968253968254,
236
+ "loss": 0.1121,
237
+ "step": 760
238
+ },
239
+ {
240
+ "epoch": 0.89,
241
+ "learning_rate": 0.0001726984126984127,
242
+ "loss": 0.1116,
243
+ "step": 780
244
+ },
245
+ {
246
+ "epoch": 0.91,
247
+ "learning_rate": 0.00017142857142857143,
248
+ "loss": 0.1091,
249
+ "step": 800
250
+ },
251
+ {
252
+ "epoch": 0.94,
253
+ "learning_rate": 0.00017015873015873017,
254
+ "loss": 0.1084,
255
+ "step": 820
256
+ },
257
+ {
258
+ "epoch": 0.96,
259
+ "learning_rate": 0.00016888888888888889,
260
+ "loss": 0.1112,
261
+ "step": 840
262
+ },
263
+ {
264
+ "epoch": 0.98,
265
+ "learning_rate": 0.00016761904761904763,
266
+ "loss": 0.1096,
267
+ "step": 860
268
+ },
269
+ {
270
+ "epoch": 1.01,
271
+ "learning_rate": 0.00016634920634920637,
272
+ "loss": 0.1078,
273
+ "step": 880
274
+ },
275
+ {
276
+ "epoch": 1.03,
277
+ "learning_rate": 0.0001650793650793651,
278
+ "loss": 0.1075,
279
+ "step": 900
280
+ },
281
+ {
282
+ "epoch": 1.05,
283
+ "learning_rate": 0.0001638095238095238,
284
+ "loss": 0.1045,
285
+ "step": 920
286
+ },
287
+ {
288
+ "epoch": 1.07,
289
+ "learning_rate": 0.00016253968253968255,
290
+ "loss": 0.1091,
291
+ "step": 940
292
+ },
293
+ {
294
+ "epoch": 1.1,
295
+ "learning_rate": 0.00016126984126984127,
296
+ "loss": 0.1064,
297
+ "step": 960
298
+ },
299
+ {
300
+ "epoch": 1.12,
301
+ "learning_rate": 0.00016,
302
+ "loss": 0.1031,
303
+ "step": 980
304
+ },
305
+ {
306
+ "epoch": 1.14,
307
+ "learning_rate": 0.00015873015873015873,
308
+ "loss": 0.1048,
309
+ "step": 1000
310
+ },
311
+ {
312
+ "epoch": 1.17,
313
+ "learning_rate": 0.00015746031746031747,
314
+ "loss": 0.1044,
315
+ "step": 1020
316
+ },
317
+ {
318
+ "epoch": 1.19,
319
+ "learning_rate": 0.0001561904761904762,
320
+ "loss": 0.1065,
321
+ "step": 1040
322
+ },
323
+ {
324
+ "epoch": 1.21,
325
+ "learning_rate": 0.00015492063492063494,
326
+ "loss": 0.1025,
327
+ "step": 1060
328
+ },
329
+ {
330
+ "epoch": 1.23,
331
+ "learning_rate": 0.00015365079365079368,
332
+ "loss": 0.1016,
333
+ "step": 1080
334
+ },
335
+ {
336
+ "epoch": 1.26,
337
+ "learning_rate": 0.00015238095238095237,
338
+ "loss": 0.1053,
339
+ "step": 1100
340
+ },
341
+ {
342
+ "epoch": 1.28,
343
+ "learning_rate": 0.0001511111111111111,
344
+ "loss": 0.1049,
345
+ "step": 1120
346
+ },
347
+ {
348
+ "epoch": 1.3,
349
+ "learning_rate": 0.00014984126984126986,
350
+ "loss": 0.1025,
351
+ "step": 1140
352
+ },
353
+ {
354
+ "epoch": 1.32,
355
+ "learning_rate": 0.00014857142857142857,
356
+ "loss": 0.1032,
357
+ "step": 1160
358
+ },
359
+ {
360
+ "epoch": 1.35,
361
+ "learning_rate": 0.00014730158730158732,
362
+ "loss": 0.1037,
363
+ "step": 1180
364
+ },
365
+ {
366
+ "epoch": 1.37,
367
+ "learning_rate": 0.00014603174603174603,
368
+ "loss": 0.1028,
369
+ "step": 1200
370
+ },
371
+ {
372
+ "epoch": 1.39,
373
+ "learning_rate": 0.00014476190476190475,
374
+ "loss": 0.1026,
375
+ "step": 1220
376
+ },
377
+ {
378
+ "epoch": 1.42,
379
+ "learning_rate": 0.0001434920634920635,
380
+ "loss": 0.1031,
381
+ "step": 1240
382
+ },
383
+ {
384
+ "epoch": 1.44,
385
+ "learning_rate": 0.00014222222222222224,
386
+ "loss": 0.0998,
387
+ "step": 1260
388
+ },
389
+ {
390
+ "epoch": 1.46,
391
+ "learning_rate": 0.00014095238095238096,
392
+ "loss": 0.1023,
393
+ "step": 1280
394
+ },
395
+ {
396
+ "epoch": 1.48,
397
+ "learning_rate": 0.00013968253968253967,
398
+ "loss": 0.1005,
399
+ "step": 1300
400
+ },
401
+ {
402
+ "epoch": 1.51,
403
+ "learning_rate": 0.00013841269841269842,
404
+ "loss": 0.1006,
405
+ "step": 1320
406
+ },
407
+ {
408
+ "epoch": 1.53,
409
+ "learning_rate": 0.00013714285714285716,
410
+ "loss": 0.1007,
411
+ "step": 1340
412
+ },
413
+ {
414
+ "epoch": 1.55,
415
+ "learning_rate": 0.00013587301587301588,
416
+ "loss": 0.0991,
417
+ "step": 1360
418
+ },
419
+ {
420
+ "epoch": 1.58,
421
+ "learning_rate": 0.00013460317460317462,
422
+ "loss": 0.1,
423
+ "step": 1380
424
+ },
425
+ {
426
+ "epoch": 1.6,
427
+ "learning_rate": 0.00013333333333333334,
428
+ "loss": 0.0991,
429
+ "step": 1400
430
+ },
431
+ {
432
+ "epoch": 1.62,
433
+ "learning_rate": 0.00013206349206349206,
434
+ "loss": 0.0994,
435
+ "step": 1420
436
+ },
437
+ {
438
+ "epoch": 1.64,
439
+ "learning_rate": 0.0001307936507936508,
440
+ "loss": 0.1,
441
+ "step": 1440
442
+ },
443
+ {
444
+ "epoch": 1.67,
445
+ "learning_rate": 0.00012952380952380954,
446
+ "loss": 0.0976,
447
+ "step": 1460
448
+ },
449
+ {
450
+ "epoch": 1.69,
451
+ "learning_rate": 0.00012825396825396826,
452
+ "loss": 0.099,
453
+ "step": 1480
454
+ },
455
+ {
456
+ "epoch": 1.71,
457
+ "learning_rate": 0.00012698412698412698,
458
+ "loss": 0.102,
459
+ "step": 1500
460
+ },
461
+ {
462
+ "epoch": 1.74,
463
+ "learning_rate": 0.00012571428571428572,
464
+ "loss": 0.099,
465
+ "step": 1520
466
+ },
467
+ {
468
+ "epoch": 1.76,
469
+ "learning_rate": 0.00012444444444444444,
470
+ "loss": 0.0984,
471
+ "step": 1540
472
+ },
473
+ {
474
+ "epoch": 1.78,
475
+ "learning_rate": 0.00012317460317460318,
476
+ "loss": 0.0985,
477
+ "step": 1560
478
+ },
479
+ {
480
+ "epoch": 1.8,
481
+ "learning_rate": 0.00012190476190476193,
482
+ "loss": 0.0958,
483
+ "step": 1580
484
+ },
485
+ {
486
+ "epoch": 1.83,
487
+ "learning_rate": 0.00012063492063492063,
488
+ "loss": 0.0997,
489
+ "step": 1600
490
+ },
491
+ {
492
+ "epoch": 1.85,
493
+ "learning_rate": 0.00011936507936507938,
494
+ "loss": 0.0975,
495
+ "step": 1620
496
+ },
497
+ {
498
+ "epoch": 1.87,
499
+ "learning_rate": 0.0001180952380952381,
500
+ "loss": 0.0991,
501
+ "step": 1640
502
+ },
503
+ {
504
+ "epoch": 1.9,
505
+ "learning_rate": 0.00011682539682539684,
506
+ "loss": 0.0981,
507
+ "step": 1660
508
+ },
509
+ {
510
+ "epoch": 1.92,
511
+ "learning_rate": 0.00011555555555555555,
512
+ "loss": 0.0977,
513
+ "step": 1680
514
+ },
515
+ {
516
+ "epoch": 1.94,
517
+ "learning_rate": 0.00011428571428571428,
518
+ "loss": 0.0972,
519
+ "step": 1700
520
+ },
521
+ {
522
+ "epoch": 1.96,
523
+ "learning_rate": 0.00011301587301587301,
524
+ "loss": 0.0998,
525
+ "step": 1720
526
+ },
527
+ {
528
+ "epoch": 1.99,
529
+ "learning_rate": 0.00011174603174603176,
530
+ "loss": 0.0964,
531
+ "step": 1740
532
+ },
533
+ {
534
+ "epoch": 2.01,
535
+ "learning_rate": 0.00011047619047619049,
536
+ "loss": 0.0972,
537
+ "step": 1760
538
+ },
539
+ {
540
+ "epoch": 2.03,
541
+ "learning_rate": 0.0001092063492063492,
542
+ "loss": 0.0959,
543
+ "step": 1780
544
+ },
545
+ {
546
+ "epoch": 2.06,
547
+ "learning_rate": 0.00010793650793650794,
548
+ "loss": 0.0962,
549
+ "step": 1800
550
+ },
551
+ {
552
+ "epoch": 2.08,
553
+ "learning_rate": 0.00010666666666666667,
554
+ "loss": 0.0979,
555
+ "step": 1820
556
+ },
557
+ {
558
+ "epoch": 2.1,
559
+ "learning_rate": 0.00010539682539682541,
560
+ "loss": 0.0956,
561
+ "step": 1840
562
+ },
563
+ {
564
+ "epoch": 2.12,
565
+ "learning_rate": 0.00010412698412698414,
566
+ "loss": 0.0943,
567
+ "step": 1860
568
+ },
569
+ {
570
+ "epoch": 2.15,
571
+ "learning_rate": 0.00010285714285714286,
572
+ "loss": 0.0959,
573
+ "step": 1880
574
+ },
575
+ {
576
+ "epoch": 2.17,
577
+ "learning_rate": 0.00010158730158730159,
578
+ "loss": 0.096,
579
+ "step": 1900
580
+ },
581
+ {
582
+ "epoch": 2.19,
583
+ "learning_rate": 0.00010031746031746032,
584
+ "loss": 0.0961,
585
+ "step": 1920
586
+ },
587
+ {
588
+ "epoch": 2.22,
589
+ "learning_rate": 9.904761904761905e-05,
590
+ "loss": 0.094,
591
+ "step": 1940
592
+ },
593
+ {
594
+ "epoch": 2.24,
595
+ "learning_rate": 9.777777777777778e-05,
596
+ "loss": 0.0945,
597
+ "step": 1960
598
+ },
599
+ {
600
+ "epoch": 2.26,
601
+ "learning_rate": 9.650793650793651e-05,
602
+ "loss": 0.0968,
603
+ "step": 1980
604
+ },
605
+ {
606
+ "epoch": 2.28,
607
+ "learning_rate": 9.523809523809524e-05,
608
+ "loss": 0.0956,
609
+ "step": 2000
610
+ },
611
+ {
612
+ "epoch": 2.31,
613
+ "learning_rate": 9.396825396825397e-05,
614
+ "loss": 0.0951,
615
+ "step": 2020
616
+ },
617
+ {
618
+ "epoch": 2.33,
619
+ "learning_rate": 9.26984126984127e-05,
620
+ "loss": 0.0947,
621
+ "step": 2040
622
+ },
623
+ {
624
+ "epoch": 2.35,
625
+ "learning_rate": 9.142857142857143e-05,
626
+ "loss": 0.0958,
627
+ "step": 2060
628
+ },
629
+ {
630
+ "epoch": 2.38,
631
+ "learning_rate": 9.015873015873016e-05,
632
+ "loss": 0.0948,
633
+ "step": 2080
634
+ },
635
+ {
636
+ "epoch": 2.4,
637
+ "learning_rate": 8.888888888888889e-05,
638
+ "loss": 0.095,
639
+ "step": 2100
640
+ },
641
+ {
642
+ "epoch": 2.42,
643
+ "learning_rate": 8.761904761904762e-05,
644
+ "loss": 0.0959,
645
+ "step": 2120
646
+ },
647
+ {
648
+ "epoch": 2.44,
649
+ "learning_rate": 8.634920634920635e-05,
650
+ "loss": 0.0931,
651
+ "step": 2140
652
+ },
653
+ {
654
+ "epoch": 2.47,
655
+ "learning_rate": 8.507936507936508e-05,
656
+ "loss": 0.0948,
657
+ "step": 2160
658
+ },
659
+ {
660
+ "epoch": 2.49,
661
+ "learning_rate": 8.380952380952382e-05,
662
+ "loss": 0.0926,
663
+ "step": 2180
664
+ },
665
+ {
666
+ "epoch": 2.51,
667
+ "learning_rate": 8.253968253968255e-05,
668
+ "loss": 0.0945,
669
+ "step": 2200
670
+ },
671
+ {
672
+ "epoch": 2.54,
673
+ "learning_rate": 8.126984126984128e-05,
674
+ "loss": 0.0934,
675
+ "step": 2220
676
+ },
677
+ {
678
+ "epoch": 2.56,
679
+ "learning_rate": 8e-05,
680
+ "loss": 0.0937,
681
+ "step": 2240
682
+ },
683
+ {
684
+ "epoch": 2.58,
685
+ "learning_rate": 7.873015873015874e-05,
686
+ "loss": 0.0929,
687
+ "step": 2260
688
+ },
689
+ {
690
+ "epoch": 2.6,
691
+ "learning_rate": 7.746031746031747e-05,
692
+ "loss": 0.093,
693
+ "step": 2280
694
+ },
695
+ {
696
+ "epoch": 2.63,
697
+ "learning_rate": 7.619047619047618e-05,
698
+ "loss": 0.0926,
699
+ "step": 2300
700
+ },
701
+ {
702
+ "epoch": 2.65,
703
+ "learning_rate": 7.492063492063493e-05,
704
+ "loss": 0.0929,
705
+ "step": 2320
706
+ },
707
+ {
708
+ "epoch": 2.67,
709
+ "learning_rate": 7.365079365079366e-05,
710
+ "loss": 0.0922,
711
+ "step": 2340
712
+ },
713
+ {
714
+ "epoch": 2.7,
715
+ "learning_rate": 7.238095238095238e-05,
716
+ "loss": 0.0925,
717
+ "step": 2360
718
+ },
719
+ {
720
+ "epoch": 2.72,
721
+ "learning_rate": 7.111111111111112e-05,
722
+ "loss": 0.0966,
723
+ "step": 2380
724
+ },
725
+ {
726
+ "epoch": 2.74,
727
+ "learning_rate": 6.984126984126984e-05,
728
+ "loss": 0.0931,
729
+ "step": 2400
730
+ },
731
+ {
732
+ "epoch": 2.76,
733
+ "learning_rate": 6.857142857142858e-05,
734
+ "loss": 0.0921,
735
+ "step": 2420
736
+ },
737
+ {
738
+ "epoch": 2.79,
739
+ "learning_rate": 6.730158730158731e-05,
740
+ "loss": 0.0923,
741
+ "step": 2440
742
+ },
743
+ {
744
+ "epoch": 2.81,
745
+ "learning_rate": 6.603174603174603e-05,
746
+ "loss": 0.0912,
747
+ "step": 2460
748
+ },
749
+ {
750
+ "epoch": 2.83,
751
+ "learning_rate": 6.476190476190477e-05,
752
+ "loss": 0.092,
753
+ "step": 2480
754
+ },
755
+ {
756
+ "epoch": 2.86,
757
+ "learning_rate": 6.349206349206349e-05,
758
+ "loss": 0.0924,
759
+ "step": 2500
760
+ },
761
+ {
762
+ "epoch": 2.88,
763
+ "learning_rate": 6.222222222222222e-05,
764
+ "loss": 0.0934,
765
+ "step": 2520
766
+ },
767
+ {
768
+ "epoch": 2.9,
769
+ "learning_rate": 6.0952380952380964e-05,
770
+ "loss": 0.0924,
771
+ "step": 2540
772
+ },
773
+ {
774
+ "epoch": 2.92,
775
+ "learning_rate": 5.968253968253969e-05,
776
+ "loss": 0.0917,
777
+ "step": 2560
778
+ },
779
+ {
780
+ "epoch": 2.95,
781
+ "learning_rate": 5.841269841269842e-05,
782
+ "loss": 0.0934,
783
+ "step": 2580
784
+ },
785
+ {
786
+ "epoch": 2.97,
787
+ "learning_rate": 5.714285714285714e-05,
788
+ "loss": 0.0936,
789
+ "step": 2600
790
+ },
791
+ {
792
+ "epoch": 2.99,
793
+ "learning_rate": 5.587301587301588e-05,
794
+ "loss": 0.0896,
795
+ "step": 2620
796
+ },
797
+ {
798
+ "epoch": 3.02,
799
+ "learning_rate": 5.46031746031746e-05,
800
+ "loss": 0.0931,
801
+ "step": 2640
802
+ },
803
+ {
804
+ "epoch": 3.04,
805
+ "learning_rate": 5.333333333333333e-05,
806
+ "loss": 0.0894,
807
+ "step": 2660
808
+ },
809
+ {
810
+ "epoch": 3.06,
811
+ "learning_rate": 5.206349206349207e-05,
812
+ "loss": 0.0933,
813
+ "step": 2680
814
+ },
815
+ {
816
+ "epoch": 3.08,
817
+ "learning_rate": 5.0793650793650794e-05,
818
+ "loss": 0.0921,
819
+ "step": 2700
820
+ },
821
+ {
822
+ "epoch": 3.11,
823
+ "learning_rate": 4.9523809523809525e-05,
824
+ "loss": 0.0897,
825
+ "step": 2720
826
+ },
827
+ {
828
+ "epoch": 3.13,
829
+ "learning_rate": 4.8253968253968255e-05,
830
+ "loss": 0.09,
831
+ "step": 2740
832
+ },
833
+ {
834
+ "epoch": 3.15,
835
+ "learning_rate": 4.6984126984126986e-05,
836
+ "loss": 0.0895,
837
+ "step": 2760
838
+ },
839
+ {
840
+ "epoch": 3.18,
841
+ "learning_rate": 4.5714285714285716e-05,
842
+ "loss": 0.0927,
843
+ "step": 2780
844
+ },
845
+ {
846
+ "epoch": 3.2,
847
+ "learning_rate": 4.4444444444444447e-05,
848
+ "loss": 0.0901,
849
+ "step": 2800
850
+ },
851
+ {
852
+ "epoch": 3.22,
853
+ "learning_rate": 4.317460317460318e-05,
854
+ "loss": 0.091,
855
+ "step": 2820
856
+ },
857
+ {
858
+ "epoch": 3.24,
859
+ "learning_rate": 4.190476190476191e-05,
860
+ "loss": 0.0887,
861
+ "step": 2840
862
+ },
863
+ {
864
+ "epoch": 3.27,
865
+ "learning_rate": 4.063492063492064e-05,
866
+ "loss": 0.093,
867
+ "step": 2860
868
+ },
869
+ {
870
+ "epoch": 3.29,
871
+ "learning_rate": 3.936507936507937e-05,
872
+ "loss": 0.091,
873
+ "step": 2880
874
+ },
875
+ {
876
+ "epoch": 3.31,
877
+ "learning_rate": 3.809523809523809e-05,
878
+ "loss": 0.0899,
879
+ "step": 2900
880
+ },
881
+ {
882
+ "epoch": 3.34,
883
+ "learning_rate": 3.682539682539683e-05,
884
+ "loss": 0.0911,
885
+ "step": 2920
886
+ },
887
+ {
888
+ "epoch": 3.36,
889
+ "learning_rate": 3.555555555555556e-05,
890
+ "loss": 0.091,
891
+ "step": 2940
892
+ },
893
+ {
894
+ "epoch": 3.38,
895
+ "learning_rate": 3.428571428571429e-05,
896
+ "loss": 0.0907,
897
+ "step": 2960
898
+ },
899
+ {
900
+ "epoch": 3.4,
901
+ "learning_rate": 3.3015873015873014e-05,
902
+ "loss": 0.0911,
903
+ "step": 2980
904
+ },
905
+ {
906
+ "epoch": 3.43,
907
+ "learning_rate": 3.1746031746031745e-05,
908
+ "loss": 0.0904,
909
+ "step": 3000
910
+ },
911
+ {
912
+ "epoch": 3.45,
913
+ "learning_rate": 3.0476190476190482e-05,
914
+ "loss": 0.0901,
915
+ "step": 3020
916
+ },
917
+ {
918
+ "epoch": 3.47,
919
+ "learning_rate": 2.920634920634921e-05,
920
+ "loss": 0.0895,
921
+ "step": 3040
922
+ },
923
+ {
924
+ "epoch": 3.5,
925
+ "learning_rate": 2.793650793650794e-05,
926
+ "loss": 0.0888,
927
+ "step": 3060
928
+ },
929
+ {
930
+ "epoch": 3.52,
931
+ "learning_rate": 2.6666666666666667e-05,
932
+ "loss": 0.0904,
933
+ "step": 3080
934
+ },
935
+ {
936
+ "epoch": 3.54,
937
+ "learning_rate": 2.5396825396825397e-05,
938
+ "loss": 0.0884,
939
+ "step": 3100
940
+ },
941
+ {
942
+ "epoch": 3.56,
943
+ "learning_rate": 2.4126984126984128e-05,
944
+ "loss": 0.0893,
945
+ "step": 3120
946
+ },
947
+ {
948
+ "epoch": 3.59,
949
+ "learning_rate": 2.2857142857142858e-05,
950
+ "loss": 0.0892,
951
+ "step": 3140
952
+ },
953
+ {
954
+ "epoch": 3.61,
955
+ "learning_rate": 2.158730158730159e-05,
956
+ "loss": 0.0886,
957
+ "step": 3160
958
+ },
959
+ {
960
+ "epoch": 3.63,
961
+ "learning_rate": 2.031746031746032e-05,
962
+ "loss": 0.0897,
963
+ "step": 3180
964
+ },
965
+ {
966
+ "epoch": 3.66,
967
+ "learning_rate": 1.9047619047619046e-05,
968
+ "loss": 0.0886,
969
+ "step": 3200
970
+ },
971
+ {
972
+ "epoch": 3.68,
973
+ "learning_rate": 1.777777777777778e-05,
974
+ "loss": 0.0884,
975
+ "step": 3220
976
+ },
977
+ {
978
+ "epoch": 3.7,
979
+ "learning_rate": 1.6507936507936507e-05,
980
+ "loss": 0.091,
981
+ "step": 3240
982
+ },
983
+ {
984
+ "epoch": 3.72,
985
+ "learning_rate": 1.5238095238095241e-05,
986
+ "loss": 0.091,
987
+ "step": 3260
988
+ },
989
+ {
990
+ "epoch": 3.75,
991
+ "learning_rate": 1.396825396825397e-05,
992
+ "loss": 0.0895,
993
+ "step": 3280
994
+ },
995
+ {
996
+ "epoch": 3.77,
997
+ "learning_rate": 1.2698412698412699e-05,
998
+ "loss": 0.0889,
999
+ "step": 3300
1000
+ },
1001
+ {
1002
+ "epoch": 3.79,
1003
+ "learning_rate": 1.1428571428571429e-05,
1004
+ "loss": 0.0868,
1005
+ "step": 3320
1006
+ },
1007
+ {
1008
+ "epoch": 3.81,
1009
+ "learning_rate": 1.015873015873016e-05,
1010
+ "loss": 0.0888,
1011
+ "step": 3340
1012
+ },
1013
+ {
1014
+ "epoch": 3.84,
1015
+ "learning_rate": 8.88888888888889e-06,
1016
+ "loss": 0.0887,
1017
+ "step": 3360
1018
+ },
1019
+ {
1020
+ "epoch": 3.86,
1021
+ "learning_rate": 7.6190476190476205e-06,
1022
+ "loss": 0.0896,
1023
+ "step": 3380
1024
+ },
1025
+ {
1026
+ "epoch": 3.88,
1027
+ "learning_rate": 6.349206349206349e-06,
1028
+ "loss": 0.0891,
1029
+ "step": 3400
1030
+ },
1031
+ {
1032
+ "epoch": 3.91,
1033
+ "learning_rate": 5.07936507936508e-06,
1034
+ "loss": 0.0892,
1035
+ "step": 3420
1036
+ },
1037
+ {
1038
+ "epoch": 3.93,
1039
+ "learning_rate": 3.8095238095238102e-06,
1040
+ "loss": 0.088,
1041
+ "step": 3440
1042
+ },
1043
+ {
1044
+ "epoch": 3.95,
1045
+ "learning_rate": 2.53968253968254e-06,
1046
+ "loss": 0.091,
1047
+ "step": 3460
1048
+ },
1049
+ {
1050
+ "epoch": 3.97,
1051
+ "learning_rate": 1.26984126984127e-06,
1052
+ "loss": 0.0898,
1053
+ "step": 3480
1054
+ },
1055
+ {
1056
+ "epoch": 4.0,
1057
+ "learning_rate": 0.0,
1058
+ "loss": 0.0869,
1059
+ "step": 3500
1060
+ }
1061
+ ],
1062
+ "logging_steps": 20,
1063
+ "max_steps": 3500,
1064
+ "num_train_epochs": 4,
1065
+ "save_steps": 500,
1066
+ "total_flos": 1.7705720940790284e+19,
1067
+ "trial_name": null,
1068
+ "trial_params": null
1069
+ }
checkpoint-3500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27738e8e23347f04140396ba9758402049d446b442105e3356d4295df15f60e8
3
+ size 4536
runs/Dec09_15-58-56_globaly/events.out.tfevents.1702159147.globaly.90463.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d3fef626893b47612f354c54e44eaab7d9adf98f7dcf25010c739a91a803ebe
3
+ size 32438
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<PAD>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
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 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<PAD>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "bos_token": "<s>",
39
+ "clean_up_tokenization_spaces": false,
40
+ "eos_token": "</s>",
41
+ "legacy": true,
42
+ "model_max_length": 1024,
43
+ "pad_token": "<PAD>",
44
+ "sp_model_kwargs": {},
45
+ "spaces_between_special_tokens": false,
46
+ "tokenizer_class": "LlamaTokenizer",
47
+ "unk_token": "<unk>",
48
+ "use_default_system_prompt": false
49
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27738e8e23347f04140396ba9758402049d446b442105e3356d4295df15f60e8
3
+ size 4536
training_params.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model": "marianbasti/Llama-2-13b-fp16-alpaca-spanish", "data_path": "Globaly/bricks-165k", "project_name": "gl_autotrain", "train_split": "train", "valid_split": null, "text_column": "text", "rejected_text_column": "rejected", "lr": 0.0002, "epochs": 4, "batch_size": 2, "warmup_ratio": 0.1, "gradient_accumulation": 4, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.01, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": 1024, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "logging_steps": 20, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": true, "push_to_hub": true, "use_int8": false, "model_max_length": 1024, "repo_id": "Globaly/Globaly-1-es-bricks-164k", "use_int4": true, "trainer": "default", "target_modules": null, "merge_adapter": false, "username": null, "use_flash_attention_2": false, "log": "tensorboard", "disable_gradient_checkpointing": false}