Hugging Face's logo

chchen
/
Falcon-7B-Instruct-ORPO

PEFT
Safetensors
llama-factory
lora
trl
dpo
Generated from Trainer
Model card Files Community
chchen commited on
Commit
a04cf2b
·
verified ·
1 Parent(s): 68e69a8

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
12
+ dataset_dir: data
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
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
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
+ "query_key_value",
24
+ "dense",
25
+ "dense_h_to_4h",
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 sha256:96f29db797cf0416b61c8eaa483b098ffeab002b0817273e3e6040d753a2bd36
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
12
+ dataset_dir: data
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
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
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": 1686, "loss": 1.8528, "accuracy": 0.4437499940395355, "learning_rate": 4.9995745934141085e-06, "epoch": 0.017781729273171815, "percentage": 0.59, "elapsed_time": "0:01:36", "remaining_time": "4:30:50"}
2
+ {"current_steps": 20, "total_steps": 1686, "loss": 2.0025, "accuracy": 0.40625, "learning_rate": 4.9982812903243405e-06, "epoch": 0.03556345854634363, "percentage": 1.19, "elapsed_time": "0:03:13", "remaining_time": "4:28:09"}
3
+ {"current_steps": 30, "total_steps": 1686, "loss": 1.9359, "accuracy": 0.512499988079071, "learning_rate": 4.996120496405222e-06, "epoch": 0.05334518781951545, "percentage": 1.78, "elapsed_time": "0:04:49", "remaining_time": "4:26:04"}
4
+ {"current_steps": 40, "total_steps": 1686, "loss": 2.0128, "accuracy": 0.4437499940395355, "learning_rate": 4.99309296196014e-06, "epoch": 0.07112691709268726, "percentage": 2.37, "elapsed_time": "0:06:23", "remaining_time": "4:23:07"}
5
+ {"current_steps": 50, "total_steps": 1686, "loss": 1.9795, "accuracy": 0.46875, "learning_rate": 4.989199738255166e-06, "epoch": 0.08890864636585907, "percentage": 2.97, "elapsed_time": "0:08:00", "remaining_time": "4:22:01"}
6
+ {"current_steps": 60, "total_steps": 1686, "loss": 2.0526, "accuracy": 0.4437499940395355, "learning_rate": 4.984442177154031e-06, "epoch": 0.1066903756390309, "percentage": 3.56, "elapsed_time": "0:09:40", "remaining_time": "4:22:07"}
7
+ {"current_steps": 70, "total_steps": 1686, "loss": 2.0142, "accuracy": 0.44999998807907104, "learning_rate": 4.978821930648704e-06, "epoch": 0.12447210491220272, "percentage": 4.15, "elapsed_time": "0:11:19", "remaining_time": "4:21:30"}
8
+ {"current_steps": 80, "total_steps": 1686, "loss": 1.9505, "accuracy": 0.5062500238418579, "learning_rate": 4.97234095028576e-06, "epoch": 0.14225383418537452, "percentage": 4.74, "elapsed_time": "0:13:00", "remaining_time": "4:21:07"}
9
+ {"current_steps": 90, "total_steps": 1686, "loss": 1.8239, "accuracy": 0.44999998807907104, "learning_rate": 4.965001486488743e-06, "epoch": 0.16003556345854633, "percentage": 5.34, "elapsed_time": "0:14:38", "remaining_time": "4:19:31"}
10
+ {"current_steps": 100, "total_steps": 1686, "loss": 1.8891, "accuracy": 0.5, "learning_rate": 4.956806087776732e-06, "epoch": 0.17781729273171815, "percentage": 5.93, "elapsed_time": "0:16:13", "remaining_time": "4:17:24"}
11
+ {"current_steps": 110, "total_steps": 1686, "loss": 1.8394, "accuracy": 0.5249999761581421, "learning_rate": 4.947757599879411e-06, "epoch": 0.19559902200489, "percentage": 6.52, "elapsed_time": "0:17:45", "remaining_time": "4:14:20"}
12
+ {"current_steps": 120, "total_steps": 1686, "loss": 1.7267, "accuracy": 0.4937500059604645, "learning_rate": 4.937859164748931e-06, "epoch": 0.2133807512780618, "percentage": 7.12, "elapsed_time": "0:19:16", "remaining_time": "4:11:34"}
13
+ {"current_steps": 130, "total_steps": 1686, "loss": 1.7688, "accuracy": 0.4749999940395355, "learning_rate": 4.92711421946891e-06, "epoch": 0.23116248055123362, "percentage": 7.71, "elapsed_time": "0:20:59", "remaining_time": "4:11:18"}
14
+ {"current_steps": 140, "total_steps": 1686, "loss": 1.7433, "accuracy": 0.53125, "learning_rate": 4.915526495060961e-06, "epoch": 0.24894420982440543, "percentage": 8.3, "elapsed_time": "0:22:40", "remaining_time": "4:10:23"}
15
+ {"current_steps": 150, "total_steps": 1686, "loss": 1.7435, "accuracy": 0.44999998807907104, "learning_rate": 4.903100015189153e-06, "epoch": 0.26672593909757725, "percentage": 8.9, "elapsed_time": "0:24:18", "remaining_time": "4:08:58"}
16
+ {"current_steps": 160, "total_steps": 1686, "loss": 1.7489, "accuracy": 0.46875, "learning_rate": 4.889839094762848e-06, "epoch": 0.28450766837074903, "percentage": 9.49, "elapsed_time": "0:25:53", "remaining_time": "4:06:54"}
17
+ {"current_steps": 170, "total_steps": 1686, "loss": 1.7344, "accuracy": 0.44999998807907104, "learning_rate": 4.875748338438416e-06, "epoch": 0.3022893976439209, "percentage": 10.08, "elapsed_time": "0:27:28", "remaining_time": "4:04:56"}
18
+ {"current_steps": 180, "total_steps": 1686, "loss": 1.6907, "accuracy": 0.5, "learning_rate": 4.8608326390203386e-06, "epoch": 0.32007112691709266, "percentage": 10.68, "elapsed_time": "0:29:06", "remaining_time": "4:03:28"}
19
+ {"current_steps": 190, "total_steps": 1686, "loss": 1.6892, "accuracy": 0.4437499940395355, "learning_rate": 4.845097175762251e-06, "epoch": 0.3378528561902645, "percentage": 11.27, "elapsed_time": "0:30:43", "remaining_time": "4:01:51"}
20
+ {"current_steps": 200, "total_steps": 1686, "loss": 1.7433, "accuracy": 0.42500001192092896, "learning_rate": 4.8285474125685286e-06, "epoch": 0.3556345854634363, "percentage": 11.86, "elapsed_time": "0:32:18", "remaining_time": "4:00:01"}
21
+ {"current_steps": 210, "total_steps": 1686, "loss": 1.7425, "accuracy": 0.48124998807907104, "learning_rate": 4.811189096097025e-06, "epoch": 0.37341631473660813, "percentage": 12.46, "elapsed_time": "0:34:03", "remaining_time": "3:59:23"}
22
+ {"current_steps": 220, "total_steps": 1686, "loss": 1.6259, "accuracy": 0.46875, "learning_rate": 4.793028253763633e-06, "epoch": 0.39119804400978, "percentage": 13.05, "elapsed_time": "0:35:40", "remaining_time": "3:57:45"}
23
+ {"current_steps": 230, "total_steps": 1686, "loss": 1.6084, "accuracy": 0.550000011920929, "learning_rate": 4.774071191649352e-06, "epoch": 0.40897977328295176, "percentage": 13.64, "elapsed_time": "0:37:21", "remaining_time": "3:56:30"}
24
+ {"current_steps": 240, "total_steps": 1686, "loss": 1.7354, "accuracy": 0.4625000059604645, "learning_rate": 4.7543244923105975e-06, "epoch": 0.4267615025561236, "percentage": 14.23, "elapsed_time": "0:39:00", "remaining_time": "3:54:59"}
25
+ {"current_steps": 250, "total_steps": 1686, "loss": 1.7326, "accuracy": 0.44999998807907104, "learning_rate": 4.733795012493506e-06, "epoch": 0.4445432318292954, "percentage": 14.83, "elapsed_time": "0:40:40", "remaining_time": "3:53:39"}
26
+ {"current_steps": 260, "total_steps": 1686, "loss": 1.5619, "accuracy": 0.5062500238418579, "learning_rate": 4.712489880753035e-06, "epoch": 0.46232496110246724, "percentage": 15.42, "elapsed_time": "0:42:22", "remaining_time": "3:52:24"}
27
+ {"current_steps": 270, "total_steps": 1686, "loss": 1.6496, "accuracy": 0.5249999761581421, "learning_rate": 4.690416494977673e-06, "epoch": 0.480106690375639, "percentage": 16.01, "elapsed_time": "0:44:02", "remaining_time": "3:50:58"}
28
+ {"current_steps": 280, "total_steps": 1686, "loss": 1.6445, "accuracy": 0.5062500238418579, "learning_rate": 4.667582519820639e-06, "epoch": 0.49788841964881086, "percentage": 16.61, "elapsed_time": "0:45:47", "remaining_time": "3:49:57"}
29
+ {"current_steps": 290, "total_steps": 1686, "loss": 1.6894, "accuracy": 0.5062500238418579, "learning_rate": 4.643995884038443e-06, "epoch": 0.5156701489219827, "percentage": 17.2, "elapsed_time": "0:47:26", "remaining_time": "3:48:22"}
30
+ {"current_steps": 300, "total_steps": 1686, "loss": 1.6226, "accuracy": 0.4312500059604645, "learning_rate": 4.6196647777377475e-06, "epoch": 0.5334518781951545, "percentage": 17.79, "elapsed_time": "0:49:09", "remaining_time": "3:47:04"}
31
+ {"current_steps": 310, "total_steps": 1686, "loss": 1.6988, "accuracy": 0.4625000059604645, "learning_rate": 4.59459764953147e-06, "epoch": 0.5512336074683263, "percentage": 18.39, "elapsed_time": "0:50:54", "remaining_time": "3:45:59"}
32
+ {"current_steps": 320, "total_steps": 1686, "loss": 1.6966, "accuracy": 0.5, "learning_rate": 4.568803203605133e-06, "epoch": 0.5690153367414981, "percentage": 18.98, "elapsed_time": "0:52:34", "remaining_time": "3:44:25"}
33
+ {"current_steps": 330, "total_steps": 1686, "loss": 1.5853, "accuracy": 0.45625001192092896, "learning_rate": 4.542290396694462e-06, "epoch": 0.58679706601467, "percentage": 19.57, "elapsed_time": "0:54:17", "remaining_time": "3:43:03"}
34
+ {"current_steps": 340, "total_steps": 1686, "loss": 1.6155, "accuracy": 0.5, "learning_rate": 4.515068434975298e-06, "epoch": 0.6045787952878418, "percentage": 20.17, "elapsed_time": "0:55:55", "remaining_time": "3:41:23"}
35
+ {"current_steps": 350, "total_steps": 1686, "loss": 1.6804, "accuracy": 0.40625, "learning_rate": 4.487146770866887e-06, "epoch": 0.6223605245610135, "percentage": 20.76, "elapsed_time": "0:57:37", "remaining_time": "3:39:56"}
36
+ {"current_steps": 360, "total_steps": 1686, "loss": 1.6917, "accuracy": 0.4437499940395355, "learning_rate": 4.458535099749666e-06, "epoch": 0.6401422538341853, "percentage": 21.35, "elapsed_time": "0:59:13", "remaining_time": "3:38:07"}
37
+ {"current_steps": 370, "total_steps": 1686, "loss": 1.5568, "accuracy": 0.4937500059604645, "learning_rate": 4.429243356598694e-06, "epoch": 0.6579239831073572, "percentage": 21.95, "elapsed_time": "1:00:50", "remaining_time": "3:36:24"}
38
+ {"current_steps": 380, "total_steps": 1686, "loss": 1.5745, "accuracy": 0.4625000059604645, "learning_rate": 4.399281712533875e-06, "epoch": 0.675705712380529, "percentage": 22.54, "elapsed_time": "1:02:23", "remaining_time": "3:34:24"}
39
+ {"current_steps": 390, "total_steps": 1686, "loss": 1.6311, "accuracy": 0.46875, "learning_rate": 4.368660571288192e-06, "epoch": 0.6934874416537008, "percentage": 23.13, "elapsed_time": "1:04:06", "remaining_time": "3:33:01"}
40
+ {"current_steps": 400, "total_steps": 1686, "loss": 1.6304, "accuracy": 0.46875, "learning_rate": 4.337390565595163e-06, "epoch": 0.7112691709268726, "percentage": 23.72, "elapsed_time": "1:05:44", "remaining_time": "3:31:21"}
41
+ {"current_steps": 410, "total_steps": 1686, "loss": 1.6033, "accuracy": 0.543749988079071, "learning_rate": 4.305482553496786e-06, "epoch": 0.7290509002000445, "percentage": 24.32, "elapsed_time": "1:07:19", "remaining_time": "3:29:30"}
42
+ {"current_steps": 420, "total_steps": 1686, "loss": 1.7183, "accuracy": 0.4937500059604645, "learning_rate": 4.272947614573244e-06, "epoch": 0.7468326294732163, "percentage": 24.91, "elapsed_time": "1:08:54", "remaining_time": "3:27:43"}
43
+ {"current_steps": 430, "total_steps": 1686, "loss": 1.5868, "accuracy": 0.518750011920929, "learning_rate": 4.23979704609569e-06, "epoch": 0.7646143587463881, "percentage": 25.5, "elapsed_time": "1:10:33", "remaining_time": "3:26:07"}
44
+ {"current_steps": 440, "total_steps": 1686, "loss": 1.6799, "accuracy": 0.512499988079071, "learning_rate": 4.206042359103435e-06, "epoch": 0.78239608801956, "percentage": 26.1, "elapsed_time": "1:12:12", "remaining_time": "3:24:29"}
45
+ {"current_steps": 450, "total_steps": 1686, "loss": 1.6973, "accuracy": 0.42500001192092896, "learning_rate": 4.17169527440691e-06, "epoch": 0.8001778172927317, "percentage": 26.69, "elapsed_time": "1:13:47", "remaining_time": "3:22:40"}
46
+ {"current_steps": 460, "total_steps": 1686, "loss": 1.4918, "accuracy": 0.5562499761581421, "learning_rate": 4.136767718517797e-06, "epoch": 0.8179595465659035, "percentage": 27.28, "elapsed_time": "1:15:25", "remaining_time": "3:21:02"}
47
+ {"current_steps": 470, "total_steps": 1686, "loss": 1.6365, "accuracy": 0.40625, "learning_rate": 4.1012718195077196e-06, "epoch": 0.8357412758390753, "percentage": 27.88, "elapsed_time": "1:17:04", "remaining_time": "3:19:25"}
48
+ {"current_steps": 480, "total_steps": 1686, "loss": 1.6152, "accuracy": 0.48750001192092896, "learning_rate": 4.065219902796953e-06, "epoch": 0.8535230051122472, "percentage": 28.47, "elapsed_time": "1:18:40", "remaining_time": "3:17:39"}
49
+ {"current_steps": 490, "total_steps": 1686, "loss": 1.5343, "accuracy": 0.512499988079071, "learning_rate": 4.028624486874608e-06, "epoch": 0.871304734385419, "percentage": 29.06, "elapsed_time": "1:20:19", "remaining_time": "3:16:03"}
50
+ {"current_steps": 500, "total_steps": 1686, "loss": 1.6309, "accuracy": 0.4937500059604645, "learning_rate": 3.99149827895177e-06, "epoch": 0.8890864636585908, "percentage": 29.66, "elapsed_time": "1:22:01", "remaining_time": "3:14:33"}
51
+ {"current_steps": 500, "total_steps": 1686, "eval_loss": 1.5815595388412476, "epoch": 0.8890864636585908, "percentage": 29.66, "elapsed_time": "1:25:25", "remaining_time": "3:22:36"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72c9308fbf427887064123c6fa11013fa4bb15511da63a3eb153947467c1ebf8
3
+ size 5240