Hugging Face's logo

kastan
/
sf_peft_test

Model card Files Community
kastan commited on
Commit
0eccbca
•
1 Parent(s): 4622a94

First attempt at a BitsNBytes QLoRA Falcon model.

Browse files
Files changed (33) hide show
  1. checkpoint-100/README.md +32 -0
  2. checkpoint-100/adapter_config.json +22 -0
  3. checkpoint-100/adapter_model.bin +3 -0
  4. checkpoint-100/optimizer.pt +3 -0
  5. checkpoint-100/rng_state.pth +3 -0
  6. checkpoint-100/scheduler.pt +3 -0
  7. checkpoint-100/special_tokens_map.json +17 -0
  8. checkpoint-100/tokenizer.json +0 -0
  9. checkpoint-100/tokenizer_config.json +7 -0
  10. checkpoint-100/trainer_state.json +76 -0
  11. checkpoint-100/training_args.bin +3 -0
  12. checkpoint-150/README.md +32 -0
  13. checkpoint-150/adapter_config.json +22 -0
  14. checkpoint-150/adapter_model.bin +3 -0
  15. checkpoint-150/optimizer.pt +3 -0
  16. checkpoint-150/rng_state.pth +3 -0
  17. checkpoint-150/scheduler.pt +3 -0
  18. checkpoint-150/special_tokens_map.json +17 -0
  19. checkpoint-150/tokenizer.json +0 -0
  20. checkpoint-150/tokenizer_config.json +7 -0
  21. checkpoint-150/trainer_state.json +106 -0
  22. checkpoint-150/training_args.bin +3 -0
  23. checkpoint-50/README.md +32 -0
  24. checkpoint-50/adapter_config.json +22 -0
  25. checkpoint-50/adapter_model.bin +3 -0
  26. checkpoint-50/optimizer.pt +3 -0
  27. checkpoint-50/rng_state.pth +3 -0
  28. checkpoint-50/scheduler.pt +3 -0
  29. checkpoint-50/special_tokens_map.json +17 -0
  30. checkpoint-50/tokenizer.json +0 -0
  31. checkpoint-50/tokenizer_config.json +7 -0
  32. checkpoint-50/trainer_state.json +46 -0
  33. checkpoint-50/training_args.bin +3 -0
checkpoint-100/README.md ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float16
17
+
18
+ The following `bitsandbytes` quantization config was used during training:
19
+ - load_in_8bit: False
20
+ - load_in_4bit: True
21
+ - llm_int8_threshold: 6.0
22
+ - llm_int8_skip_modules: None
23
+ - llm_int8_enable_fp32_cpu_offload: False
24
+ - llm_int8_has_fp16_weight: False
25
+ - bnb_4bit_quant_type: nf4
26
+ - bnb_4bit_use_double_quant: False
27
+ - bnb_4bit_compute_dtype: float16
28
+ ### Framework versions
29
+
30
+ - PEFT 0.4.0.dev0
31
+
32
+ - PEFT 0.4.0.dev0
checkpoint-100/adapter_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "layers_pattern": null,
8
+ "layers_to_transform": null,
9
+ "lora_alpha": 16,
10
+ "lora_dropout": 0.1,
11
+ "modules_to_save": null,
12
+ "peft_type": "LORA",
13
+ "r": 64,
14
+ "revision": null,
15
+ "target_modules": [
16
+ "query_key_value",
17
+ "dense",
18
+ "dense_h_to_4h",
19
+ "dense_4h_to_h"
20
+ ],
21
+ "task_type": "CAUSAL_LM"
22
+ }
checkpoint-100/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6a68180625d7f5344f7ba7ab4ed4e819fc1acf6fc772bd9f64b1cd8586371f1
3
+ size 522284877
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cff3861facd3ab275760f6d069a4b60d4fbf40be3d0a4061f8c880627ff246d9
3
+ size 1044539653
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b55955509ba1d00714e9cce86f80ea357c7127e2be1ba37f034cfb1bb081bd85
3
+ size 14575
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:216f76b8039f833c337db298c81f13b12082d5fd4f9d866cecd34b2ca7550b37
3
+ size 627
checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ ">>TITLE<<",
4
+ ">>ABSTRACT<<",
5
+ ">>INTRODUCTION<<",
6
+ ">>SUMMARY<<",
7
+ ">>COMMENT<<",
8
+ ">>ANSWER<<",
9
+ ">>QUESTION<<",
10
+ ">>DOMAIN<<",
11
+ ">>PREFIX<<",
12
+ ">>SUFFIX<<",
13
+ ">>MIDDLE<<"
14
+ ],
15
+ "eos_token": "<|endoftext|>",
16
+ "pad_token": "<|endoftext|>"
17
+ }
checkpoint-100/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 2048,
6
+ "tokenizer_class": "PreTrainedTokenizerFast"
7
+ }
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.64,
5
+ "global_step": 100,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.06,
12
+ "learning_rate": 0.0002,
13
+ "loss": 2.8722,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.13,
18
+ "learning_rate": 0.0002,
19
+ "loss": 2.7951,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.19,
24
+ "learning_rate": 0.0002,
25
+ "loss": 2.7847,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.26,
30
+ "learning_rate": 0.0002,
31
+ "loss": 2.7507,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.32,
36
+ "learning_rate": 0.0002,
37
+ "loss": 2.7355,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.38,
42
+ "learning_rate": 0.0002,
43
+ "loss": 2.7085,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.45,
48
+ "learning_rate": 0.0002,
49
+ "loss": 2.6827,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.51,
54
+ "learning_rate": 0.0002,
55
+ "loss": 2.6429,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.58,
60
+ "learning_rate": 0.0002,
61
+ "loss": 2.6901,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.64,
66
+ "learning_rate": 0.0002,
67
+ "loss": 2.688,
68
+ "step": 100
69
+ }
70
+ ],
71
+ "max_steps": 156,
72
+ "num_train_epochs": 1,
73
+ "total_flos": 6.770832332292096e+16,
74
+ "trial_name": null,
75
+ "trial_params": null
76
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06aa948ab085088ada56ecf2747c82338501c15fcdff5b592094917bcb713d9d
3
+ size 3963
checkpoint-150/README.md ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float16
17
+
18
+ The following `bitsandbytes` quantization config was used during training:
19
+ - load_in_8bit: False
20
+ - load_in_4bit: True
21
+ - llm_int8_threshold: 6.0
22
+ - llm_int8_skip_modules: None
23
+ - llm_int8_enable_fp32_cpu_offload: False
24
+ - llm_int8_has_fp16_weight: False
25
+ - bnb_4bit_quant_type: nf4
26
+ - bnb_4bit_use_double_quant: False
27
+ - bnb_4bit_compute_dtype: float16
28
+ ### Framework versions
29
+
30
+ - PEFT 0.4.0.dev0
31
+
32
+ - PEFT 0.4.0.dev0
checkpoint-150/adapter_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "layers_pattern": null,
8
+ "layers_to_transform": null,
9
+ "lora_alpha": 16,
10
+ "lora_dropout": 0.1,
11
+ "modules_to_save": null,
12
+ "peft_type": "LORA",
13
+ "r": 64,
14
+ "revision": null,
15
+ "target_modules": [
16
+ "query_key_value",
17
+ "dense",
18
+ "dense_h_to_4h",
19
+ "dense_4h_to_h"
20
+ ],
21
+ "task_type": "CAUSAL_LM"
22
+ }
checkpoint-150/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76ee304e50331fa3057446aefbc1ca2d020137066725f7c3b4dc74cfd8b97782
3
+ size 522284877
checkpoint-150/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00ba98f1157ac1c94ca39537937548e4937574f90f4b8ebbf46d054b4e75aff5
3
+ size 1044539653
checkpoint-150/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5005f87b4048f2a98b8e173effa7b158007e428435416ebe049c79042f57bec3
3
+ size 14575
checkpoint-150/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01422943191c18f4ce94fe70c7ffd85d7e6e08513a418ac2779ae0b3b3ba38a4
3
+ size 627
checkpoint-150/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ ">>TITLE<<",
4
+ ">>ABSTRACT<<",
5
+ ">>INTRODUCTION<<",
6
+ ">>SUMMARY<<",
7
+ ">>COMMENT<<",
8
+ ">>ANSWER<<",
9
+ ">>QUESTION<<",
10
+ ">>DOMAIN<<",
11
+ ">>PREFIX<<",
12
+ ">>SUFFIX<<",
13
+ ">>MIDDLE<<"
14
+ ],
15
+ "eos_token": "<|endoftext|>",
16
+ "pad_token": "<|endoftext|>"
17
+ }
checkpoint-150/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-150/tokenizer_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 2048,
6
+ "tokenizer_class": "PreTrainedTokenizerFast"
7
+ }
checkpoint-150/trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.96,
5
+ "global_step": 150,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.06,
12
+ "learning_rate": 0.0002,
13
+ "loss": 2.8722,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.13,
18
+ "learning_rate": 0.0002,
19
+ "loss": 2.7951,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.19,
24
+ "learning_rate": 0.0002,
25
+ "loss": 2.7847,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.26,
30
+ "learning_rate": 0.0002,
31
+ "loss": 2.7507,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.32,
36
+ "learning_rate": 0.0002,
37
+ "loss": 2.7355,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.38,
42
+ "learning_rate": 0.0002,
43
+ "loss": 2.7085,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.45,
48
+ "learning_rate": 0.0002,
49
+ "loss": 2.6827,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.51,
54
+ "learning_rate": 0.0002,
55
+ "loss": 2.6429,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.58,
60
+ "learning_rate": 0.0002,
61
+ "loss": 2.6901,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.64,
66
+ "learning_rate": 0.0002,
67
+ "loss": 2.688,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.7,
72
+ "learning_rate": 0.0002,
73
+ "loss": 2.7024,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.77,
78
+ "learning_rate": 0.0002,
79
+ "loss": 2.6776,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.83,
84
+ "learning_rate": 0.0002,
85
+ "loss": 2.6491,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.9,
90
+ "learning_rate": 0.0002,
91
+ "loss": 2.6498,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.96,
96
+ "learning_rate": 0.0002,
97
+ "loss": 2.6607,
98
+ "step": 150
99
+ }
100
+ ],
101
+ "max_steps": 156,
102
+ "num_train_epochs": 1,
103
+ "total_flos": 1.0156248498438144e+17,
104
+ "trial_name": null,
105
+ "trial_params": null
106
+ }
checkpoint-150/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06aa948ab085088ada56ecf2747c82338501c15fcdff5b592094917bcb713d9d
3
+ size 3963
checkpoint-50/README.md ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float16
17
+
18
+ The following `bitsandbytes` quantization config was used during training:
19
+ - load_in_8bit: False
20
+ - load_in_4bit: True
21
+ - llm_int8_threshold: 6.0
22
+ - llm_int8_skip_modules: None
23
+ - llm_int8_enable_fp32_cpu_offload: False
24
+ - llm_int8_has_fp16_weight: False
25
+ - bnb_4bit_quant_type: nf4
26
+ - bnb_4bit_use_double_quant: False
27
+ - bnb_4bit_compute_dtype: float16
28
+ ### Framework versions
29
+
30
+ - PEFT 0.4.0.dev0
31
+
32
+ - PEFT 0.4.0.dev0
checkpoint-50/adapter_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "layers_pattern": null,
8
+ "layers_to_transform": null,
9
+ "lora_alpha": 16,
10
+ "lora_dropout": 0.1,
11
+ "modules_to_save": null,
12
+ "peft_type": "LORA",
13
+ "r": 64,
14
+ "revision": null,
15
+ "target_modules": [
16
+ "query_key_value",
17
+ "dense",
18
+ "dense_h_to_4h",
19
+ "dense_4h_to_h"
20
+ ],
21
+ "task_type": "CAUSAL_LM"
22
+ }
checkpoint-50/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:032f42d9d5c258856e19effca1ecaee7ec61f7188a473342290595c436c2adff
3
+ size 522284877
checkpoint-50/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39889cd8f1fad5b588fd13c98ed1b4c4284f8927f417f4bdb700da6e9ba3ee7a
3
+ size 1044539653
checkpoint-50/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44ad36cf584d2de00c5938d038a775667aba2a65d3fa5d28d0ef7b3ba129f0d7
3
+ size 14575
checkpoint-50/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d217edb059555be97837810de03dc22d79976c8832aac609d084f6016b5003c4
3
+ size 627
checkpoint-50/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ ">>TITLE<<",
4
+ ">>ABSTRACT<<",
5
+ ">>INTRODUCTION<<",
6
+ ">>SUMMARY<<",
7
+ ">>COMMENT<<",
8
+ ">>ANSWER<<",
9
+ ">>QUESTION<<",
10
+ ">>DOMAIN<<",
11
+ ">>PREFIX<<",
12
+ ">>SUFFIX<<",
13
+ ">>MIDDLE<<"
14
+ ],
15
+ "eos_token": "<|endoftext|>",
16
+ "pad_token": "<|endoftext|>"
17
+ }
checkpoint-50/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-50/tokenizer_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 2048,
6
+ "tokenizer_class": "PreTrainedTokenizerFast"
7
+ }
checkpoint-50/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.32,
5
+ "global_step": 50,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.06,
12
+ "learning_rate": 0.0002,
13
+ "loss": 2.8722,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.13,
18
+ "learning_rate": 0.0002,
19
+ "loss": 2.7951,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.19,
24
+ "learning_rate": 0.0002,
25
+ "loss": 2.7847,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.26,
30
+ "learning_rate": 0.0002,
31
+ "loss": 2.7507,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.32,
36
+ "learning_rate": 0.0002,
37
+ "loss": 2.7355,
38
+ "step": 50
39
+ }
40
+ ],
41
+ "max_steps": 156,
42
+ "num_train_epochs": 1,
43
+ "total_flos": 3.385416166146048e+16,
44
+ "trial_name": null,
45
+ "trial_params": null
46
+ }
checkpoint-50/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06aa948ab085088ada56ecf2747c82338501c15fcdff5b592094917bcb713d9d
3
+ size 3963