Hugging Face's logo

chchen
/
Falcon-7B-Instruct-ORPO-SALT-HALF

PEFT
Safetensors
llama-factory
lora
trl
dpo
Generated from Trainer
Model card Files
xet
Community
chchen commited on
Commit
dde2dcd
·
verified ·
1 Parent(s): 7c19795

Training in progress, step 500

Browse files
Files changed (9) hide show
  1. .ipynb_checkpoints/lora_orpo-checkpoint.yaml +43 -0
  2. adapter_config.json +31 -0
  3. adapter_model.safetensors +3 -0
  4. lora_orpo.yaml +43 -0
  5. special_tokens_map.json +23 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +126 -0
  8. trainer_log.jsonl +51 -0
  9. training_args.bin +3 -0
.ipynb_checkpoints/lora_orpo-checkpoint.yaml ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ### model
2
+ model_name_or_path: tiiuae/falcon-7b-instruct
3
+
4
+ ### method
5
+ stage: orpo
6
+ do_train: true
7
+ finetuning_type: lora
8
+ lora_target: all
9
+
10
+ ### dataset
11
+ dataset: dpo_mix_en,bct_non_cot_dpo_500
12
+ dataset_dir: data_private
13
+ template: falcon
14
+ cutoff_len: 1024
15
+ # max_samples: 1000
16
+ overwrite_cache: true
17
+ preprocessing_num_workers: 16
18
+
19
+ ### output
20
+ output_dir: saves/Falcon-7B-Instruct/lora/orpo-salt-half
21
+ logging_steps: 10
22
+ save_steps: 500
23
+ plot_loss: true
24
+ overwrite_output_dir: true
25
+ save_total_limit: 3
26
+ load_best_model_at_end: true
27
+ push_to_hub: true
28
+ hub_model_id: chchen/Falcon-7B-Instruct-ORPO-SALT-HALF
29
+
30
+ ### train
31
+ per_device_train_batch_size: 2
32
+ gradient_accumulation_steps: 8
33
+ learning_rate: 0.000005
34
+ num_train_epochs: 3.0
35
+ lr_scheduler_type: cosine
36
+ warmup_steps: 0.1
37
+ bf16: true
38
+
39
+ ### eval
40
+ val_size: 0.1
41
+ per_device_eval_batch_size: 2
42
+ evaluation_strategy: steps
43
+ eval_steps: 500
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "tiiuae/falcon-7b-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": 16,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "dense",
24
+ "dense_h_to_4h",
25
+ "query_key_value",
26
+ "dense_4h_to_h"
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:a538ef300caa75293e5388886b3f0146f5fa2c6f420b663cf3b1931c5cc05f5f
3
+ size 65309632
lora_orpo.yaml ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ### model
2
+ model_name_or_path: tiiuae/falcon-7b-instruct
3
+
4
+ ### method
5
+ stage: orpo
6
+ do_train: true
7
+ finetuning_type: lora
8
+ lora_target: all
9
+
10
+ ### dataset
11
+ dataset: dpo_mix_en,bct_non_cot_dpo_500
12
+ dataset_dir: data_private
13
+ template: falcon
14
+ cutoff_len: 1024
15
+ # max_samples: 1000
16
+ overwrite_cache: true
17
+ preprocessing_num_workers: 16
18
+
19
+ ### output
20
+ output_dir: saves/Falcon-7B-Instruct/lora/orpo-salt-half
21
+ logging_steps: 10
22
+ save_steps: 500
23
+ plot_loss: true
24
+ overwrite_output_dir: true
25
+ save_total_limit: 3
26
+ load_best_model_at_end: true
27
+ push_to_hub: true
28
+ hub_model_id: chchen/Falcon-7B-Instruct-ORPO-SALT-HALF
29
+
30
+ ### train
31
+ per_device_train_batch_size: 2
32
+ gradient_accumulation_steps: 8
33
+ learning_rate: 0.000005
34
+ num_train_epochs: 3.0
35
+ lr_scheduler_type: cosine
36
+ warmup_steps: 0.1
37
+ bf16: true
38
+
39
+ ### eval
40
+ val_size: 0.1
41
+ per_device_eval_batch_size: 2
42
+ evaluation_strategy: steps
43
+ eval_steps: 500
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
16
+ "content": "<|endoftext|>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "pad_token": "<|endoftext|>"
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": ">>TITLE<<",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": ">>ABSTRACT<<",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": ">>INTRODUCTION<<",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": ">>SUMMARY<<",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": ">>COMMENT<<",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": ">>ANSWER<<",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": ">>QUESTION<<",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": ">>DOMAIN<<",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": ">>PREFIX<<",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": ">>SUFFIX<<",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": ">>MIDDLE<<",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<|endoftext|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ }
100
+ },
101
+ "additional_special_tokens": [
102
+ ">>TITLE<<",
103
+ ">>ABSTRACT<<",
104
+ ">>INTRODUCTION<<",
105
+ ">>SUMMARY<<",
106
+ ">>COMMENT<<",
107
+ ">>ANSWER<<",
108
+ ">>QUESTION<<",
109
+ ">>DOMAIN<<",
110
+ ">>PREFIX<<",
111
+ ">>SUFFIX<<",
112
+ ">>MIDDLE<<"
113
+ ],
114
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\nFalcon:' }}{% elif message['role'] == 'assistant' %}{{ content + '\n' }}{% endif %}{% endfor %}",
115
+ "clean_up_tokenization_spaces": true,
116
+ "eos_token": "<|endoftext|>",
117
+ "model_input_names": [
118
+ "input_ids",
119
+ "attention_mask"
120
+ ],
121
+ "model_max_length": 2048,
122
+ "pad_token": "<|endoftext|>",
123
+ "padding_side": "right",
124
+ "split_special_tokens": false,
125
+ "tokenizer_class": "PreTrainedTokenizerFast"
126
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 1770, "loss": 2.0361, "accuracy": 0.5, "learning_rate": 4.999614014035063e-06, "epoch": 0.01693480101608806, "percentage": 0.56, "elapsed_time": "0:01:39", "remaining_time": "4:51:19"}
2
+ {"current_steps": 20, "total_steps": 1770, "loss": 2.0019, "accuracy": 0.5249999761581421, "learning_rate": 4.998440543386042e-06, "epoch": 0.03386960203217612, "percentage": 1.13, "elapsed_time": "0:03:13", "remaining_time": "4:42:34"}
3
+ {"current_steps": 30, "total_steps": 1770, "loss": 1.9146, "accuracy": 0.5062500238418579, "learning_rate": 4.996479918381253e-06, "epoch": 0.05080440304826418, "percentage": 1.69, "elapsed_time": "0:04:52", "remaining_time": "4:42:18"}
4
+ {"current_steps": 40, "total_steps": 1770, "loss": 1.889, "accuracy": 0.4625000059604645, "learning_rate": 4.993732756731818e-06, "epoch": 0.06773920406435224, "percentage": 2.26, "elapsed_time": "0:06:28", "remaining_time": "4:40:07"}
5
+ {"current_steps": 50, "total_steps": 1770, "loss": 2.0255, "accuracy": 0.48124998807907104, "learning_rate": 4.9901999239537345e-06, "epoch": 0.0846740050804403, "percentage": 2.82, "elapsed_time": "0:07:55", "remaining_time": "4:32:49"}
6
+ {"current_steps": 60, "total_steps": 1770, "loss": 1.8465, "accuracy": 0.4749999940395355, "learning_rate": 4.985882533095186e-06, "epoch": 0.10160880609652836, "percentage": 3.39, "elapsed_time": "0:09:26", "remaining_time": "4:29:15"}
7
+ {"current_steps": 70, "total_steps": 1770, "loss": 1.8722, "accuracy": 0.48750001192092896, "learning_rate": 4.9807819443858705e-06, "epoch": 0.11854360711261643, "percentage": 3.95, "elapsed_time": "0:10:56", "remaining_time": "4:25:52"}
8
+ {"current_steps": 80, "total_steps": 1770, "loss": 1.8688, "accuracy": 0.48124998807907104, "learning_rate": 4.9748997648084404e-06, "epoch": 0.1354784081287045, "percentage": 4.52, "elapsed_time": "0:12:30", "remaining_time": "4:24:17"}
9
+ {"current_steps": 90, "total_steps": 1770, "loss": 1.8161, "accuracy": 0.4437499940395355, "learning_rate": 4.96823784759222e-06, "epoch": 0.15241320914479256, "percentage": 5.08, "elapsed_time": "0:14:05", "remaining_time": "4:22:54"}
10
+ {"current_steps": 100, "total_steps": 1770, "loss": 1.8785, "accuracy": 0.4437499940395355, "learning_rate": 4.960798291629323e-06, "epoch": 0.1693480101608806, "percentage": 5.65, "elapsed_time": "0:15:41", "remaining_time": "4:22:03"}
11
+ {"current_steps": 110, "total_steps": 1770, "loss": 1.885, "accuracy": 0.46875, "learning_rate": 4.952583440813383e-06, "epoch": 0.18628281117696868, "percentage": 6.21, "elapsed_time": "0:17:12", "remaining_time": "4:19:44"}
12
+ {"current_steps": 120, "total_steps": 1770, "loss": 1.8966, "accuracy": 0.4625000059604645, "learning_rate": 4.943595883301086e-06, "epoch": 0.20321761219305673, "percentage": 6.78, "elapsed_time": "0:18:50", "remaining_time": "4:19:04"}
13
+ {"current_steps": 130, "total_steps": 1770, "loss": 1.7441, "accuracy": 0.48750001192092896, "learning_rate": 4.933838450696757e-06, "epoch": 0.2201524132091448, "percentage": 7.34, "elapsed_time": "0:20:29", "remaining_time": "4:18:29"}
14
+ {"current_steps": 140, "total_steps": 1770, "loss": 1.8341, "accuracy": 0.39375001192092896, "learning_rate": 4.923314217160234e-06, "epoch": 0.23708721422523285, "percentage": 7.91, "elapsed_time": "0:22:01", "remaining_time": "4:16:27"}
15
+ {"current_steps": 150, "total_steps": 1770, "loss": 1.6472, "accuracy": 0.45625001192092896, "learning_rate": 4.9120264984383285e-06, "epoch": 0.2540220152413209, "percentage": 8.47, "elapsed_time": "0:23:39", "remaining_time": "4:15:32"}
16
+ {"current_steps": 160, "total_steps": 1770, "loss": 1.7925, "accuracy": 0.48124998807907104, "learning_rate": 4.899978850820176e-06, "epoch": 0.270956816257409, "percentage": 9.04, "elapsed_time": "0:25:21", "remaining_time": "4:15:14"}
17
+ {"current_steps": 170, "total_steps": 1770, "loss": 1.5883, "accuracy": 0.5062500238418579, "learning_rate": 4.887175070016795e-06, "epoch": 0.28789161727349705, "percentage": 9.6, "elapsed_time": "0:26:54", "remaining_time": "4:13:17"}
18
+ {"current_steps": 180, "total_steps": 1770, "loss": 1.6635, "accuracy": 0.581250011920929, "learning_rate": 4.873619189965217e-06, "epoch": 0.3048264182895851, "percentage": 10.17, "elapsed_time": "0:28:32", "remaining_time": "4:12:10"}
19
+ {"current_steps": 190, "total_steps": 1770, "loss": 1.6487, "accuracy": 0.48124998807907104, "learning_rate": 4.859315481557563e-06, "epoch": 0.32176121930567314, "percentage": 10.73, "elapsed_time": "0:30:07", "remaining_time": "4:10:31"}
20
+ {"current_steps": 200, "total_steps": 1770, "loss": 1.7261, "accuracy": 0.42500001192092896, "learning_rate": 4.84426845129546e-06, "epoch": 0.3386960203217612, "percentage": 11.3, "elapsed_time": "0:31:43", "remaining_time": "4:09:05"}
21
+ {"current_steps": 210, "total_steps": 1770, "loss": 1.6618, "accuracy": 0.45625001192092896, "learning_rate": 4.828482839870233e-06, "epoch": 0.3556308213378493, "percentage": 11.86, "elapsed_time": "0:33:14", "remaining_time": "4:06:54"}
22
+ {"current_steps": 220, "total_steps": 1770, "loss": 1.6187, "accuracy": 0.44999998807907104, "learning_rate": 4.811963620669314e-06, "epoch": 0.37256562235393736, "percentage": 12.43, "elapsed_time": "0:34:49", "remaining_time": "4:05:21"}
23
+ {"current_steps": 230, "total_steps": 1770, "loss": 1.6132, "accuracy": 0.5062500238418579, "learning_rate": 4.794715998209328e-06, "epoch": 0.3895004233700254, "percentage": 12.99, "elapsed_time": "0:36:24", "remaining_time": "4:03:46"}
24
+ {"current_steps": 240, "total_steps": 1770, "loss": 1.6455, "accuracy": 0.53125, "learning_rate": 4.7767454064963724e-06, "epoch": 0.40643522438611346, "percentage": 13.56, "elapsed_time": "0:37:57", "remaining_time": "4:02:01"}
25
+ {"current_steps": 250, "total_steps": 1770, "loss": 1.5708, "accuracy": 0.512499988079071, "learning_rate": 4.758057507313987e-06, "epoch": 0.42337002540220153, "percentage": 14.12, "elapsed_time": "0:39:29", "remaining_time": "4:00:06"}
26
+ {"current_steps": 260, "total_steps": 1770, "loss": 1.6715, "accuracy": 0.46875, "learning_rate": 4.73865818843936e-06, "epoch": 0.4403048264182896, "percentage": 14.69, "elapsed_time": "0:41:06", "remaining_time": "3:58:46"}
27
+ {"current_steps": 270, "total_steps": 1770, "loss": 1.5596, "accuracy": 0.44999998807907104, "learning_rate": 4.718553561788339e-06, "epoch": 0.4572396274343776, "percentage": 15.25, "elapsed_time": "0:42:40", "remaining_time": "3:57:06"}
28
+ {"current_steps": 280, "total_steps": 1770, "loss": 1.6957, "accuracy": 0.46875, "learning_rate": 4.697749961489822e-06, "epoch": 0.4741744284504657, "percentage": 15.82, "elapsed_time": "0:44:15", "remaining_time": "3:55:32"}
29
+ {"current_steps": 290, "total_steps": 1770, "loss": 1.5387, "accuracy": 0.5375000238418579, "learning_rate": 4.67625394189013e-06, "epoch": 0.4911092294665538, "percentage": 16.38, "elapsed_time": "0:45:49", "remaining_time": "3:53:51"}
30
+ {"current_steps": 300, "total_steps": 1770, "loss": 1.4878, "accuracy": 0.5562499761581421, "learning_rate": 4.654072275488016e-06, "epoch": 0.5080440304826418, "percentage": 16.95, "elapsed_time": "0:47:23", "remaining_time": "3:52:15"}
31
+ {"current_steps": 310, "total_steps": 1770, "loss": 1.4748, "accuracy": 0.59375, "learning_rate": 4.631211950800925e-06, "epoch": 0.5249788314987299, "percentage": 17.51, "elapsed_time": "0:48:58", "remaining_time": "3:50:37"}
32
+ {"current_steps": 320, "total_steps": 1770, "loss": 1.5925, "accuracy": 0.4937500059604645, "learning_rate": 4.6076801701632095e-06, "epoch": 0.541913632514818, "percentage": 18.08, "elapsed_time": "0:50:27", "remaining_time": "3:48:39"}
33
+ {"current_steps": 330, "total_steps": 1770, "loss": 1.648, "accuracy": 0.5375000238418579, "learning_rate": 4.583484347456972e-06, "epoch": 0.558848433530906, "percentage": 18.64, "elapsed_time": "0:51:56", "remaining_time": "3:46:38"}
34
+ {"current_steps": 340, "total_steps": 1770, "loss": 1.6172, "accuracy": 0.5562499761581421, "learning_rate": 4.55863210577626e-06, "epoch": 0.5757832345469941, "percentage": 19.21, "elapsed_time": "0:53:32", "remaining_time": "3:45:11"}
35
+ {"current_steps": 350, "total_steps": 1770, "loss": 1.5652, "accuracy": 0.45625001192092896, "learning_rate": 4.5331312750253465e-06, "epoch": 0.5927180355630821, "percentage": 19.77, "elapsed_time": "0:55:09", "remaining_time": "3:43:45"}
36
+ {"current_steps": 360, "total_steps": 1770, "loss": 1.5735, "accuracy": 0.4375, "learning_rate": 4.506989889451858e-06, "epoch": 0.6096528365791702, "percentage": 20.34, "elapsed_time": "0:56:49", "remaining_time": "3:42:34"}
37
+ {"current_steps": 370, "total_steps": 1770, "loss": 1.5673, "accuracy": 0.53125, "learning_rate": 4.480216185115512e-06, "epoch": 0.6265876375952583, "percentage": 20.9, "elapsed_time": "0:58:27", "remaining_time": "3:41:12"}
38
+ {"current_steps": 380, "total_steps": 1770, "loss": 1.5915, "accuracy": 0.5, "learning_rate": 4.4528185972932856e-06, "epoch": 0.6435224386113463, "percentage": 21.47, "elapsed_time": "1:00:03", "remaining_time": "3:39:42"}
39
+ {"current_steps": 390, "total_steps": 1770, "loss": 1.6513, "accuracy": 0.4312500059604645, "learning_rate": 4.424805757821803e-06, "epoch": 0.6604572396274344, "percentage": 22.03, "elapsed_time": "1:01:40", "remaining_time": "3:38:14"}
40
+ {"current_steps": 400, "total_steps": 1770, "loss": 1.5797, "accuracy": 0.518750011920929, "learning_rate": 4.396186492377812e-06, "epoch": 0.6773920406435224, "percentage": 22.6, "elapsed_time": "1:03:18", "remaining_time": "3:36:50"}
41
+ {"current_steps": 410, "total_steps": 1770, "loss": 1.5766, "accuracy": 0.4312500059604645, "learning_rate": 4.366969817697578e-06, "epoch": 0.6943268416596104, "percentage": 23.16, "elapsed_time": "1:04:51", "remaining_time": "3:35:07"}
42
+ {"current_steps": 420, "total_steps": 1770, "loss": 1.6108, "accuracy": 0.4437499940395355, "learning_rate": 4.337164938736086e-06, "epoch": 0.7112616426756986, "percentage": 23.73, "elapsed_time": "1:06:28", "remaining_time": "3:33:41"}
43
+ {"current_steps": 430, "total_steps": 1770, "loss": 1.4336, "accuracy": 0.5062500238418579, "learning_rate": 4.306781245766945e-06, "epoch": 0.7281964436917866, "percentage": 24.29, "elapsed_time": "1:07:58", "remaining_time": "3:31:50"}
44
+ {"current_steps": 440, "total_steps": 1770, "loss": 1.709, "accuracy": 0.4749999940395355, "learning_rate": 4.275828311423903e-06, "epoch": 0.7451312447078747, "percentage": 24.86, "elapsed_time": "1:09:28", "remaining_time": "3:30:01"}
45
+ {"current_steps": 450, "total_steps": 1770, "loss": 1.5595, "accuracy": 0.550000011920929, "learning_rate": 4.244315887684912e-06, "epoch": 0.7620660457239627, "percentage": 25.42, "elapsed_time": "1:11:05", "remaining_time": "3:28:31"}
46
+ {"current_steps": 460, "total_steps": 1770, "loss": 1.5023, "accuracy": 0.46875, "learning_rate": 4.212253902799685e-06, "epoch": 0.7790008467400508, "percentage": 25.99, "elapsed_time": "1:12:42", "remaining_time": "3:27:02"}
47
+ {"current_steps": 470, "total_steps": 1770, "loss": 1.5259, "accuracy": 0.45625001192092896, "learning_rate": 4.179652458161718e-06, "epoch": 0.7959356477561389, "percentage": 26.55, "elapsed_time": "1:14:14", "remaining_time": "3:25:19"}
48
+ {"current_steps": 480, "total_steps": 1770, "loss": 1.5509, "accuracy": 0.4749999940395355, "learning_rate": 4.146521825125765e-06, "epoch": 0.8128704487722269, "percentage": 27.12, "elapsed_time": "1:15:52", "remaining_time": "3:23:54"}
49
+ {"current_steps": 490, "total_steps": 1770, "loss": 1.5245, "accuracy": 0.4937500059604645, "learning_rate": 4.11287244177176e-06, "epoch": 0.8298052497883149, "percentage": 27.68, "elapsed_time": "1:17:31", "remaining_time": "3:22:31"}
50
+ {"current_steps": 500, "total_steps": 1770, "loss": 1.5988, "accuracy": 0.512499988079071, "learning_rate": 4.078714909616215e-06, "epoch": 0.8467400508044031, "percentage": 28.25, "elapsed_time": "1:19:04", "remaining_time": "3:20:50"}
51
+ {"current_steps": 500, "total_steps": 1770, "eval_loss": 1.5655477046966553, "epoch": 0.8467400508044031, "percentage": 28.25, "elapsed_time": "1:22:32", "remaining_time": "3:29:38"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95ac72cdbc047f11dfd6beeb28dab12b7009fc3d25302b531f0d6871f94ed904
3
+ size 5240