Hugging Face's logo

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

PEFT
Safetensors
llama-factory
lora
trl
dpo
Generated from Trainer
Model card Files Community
chchen commited on
Commit
95b8f67
·
verified ·
1 Parent(s): 7170130

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_1000
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
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
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_4h_to_h",
26
+ "dense_h_to_4h"
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:b8c9c801ad0e0026117f5694d056da71527f0dad31739ebcac9a2abc96a1b8c4
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_1000
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
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
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": 1854, "loss": 1.8299, "accuracy": 0.518750011920929, "learning_rate": 4.999648198770648e-06, "epoch": 0.01616488179430188, "percentage": 0.54, "elapsed_time": "0:01:30", "remaining_time": "4:37:14"}
2
+ {"current_steps": 20, "total_steps": 1854, "loss": 2.0003, "accuracy": 0.48750001192092896, "learning_rate": 4.998578646361359e-06, "epoch": 0.03232976358860376, "percentage": 1.08, "elapsed_time": "0:03:02", "remaining_time": "4:39:09"}
3
+ {"current_steps": 30, "total_steps": 1854, "loss": 1.9128, "accuracy": 0.46875, "learning_rate": 4.996791614004449e-06, "epoch": 0.04849464538290564, "percentage": 1.62, "elapsed_time": "0:04:37", "remaining_time": "4:41:02"}
4
+ {"current_steps": 40, "total_steps": 1854, "loss": 2.0298, "accuracy": 0.45625001192092896, "learning_rate": 4.994287614855618e-06, "epoch": 0.06465952717720752, "percentage": 2.16, "elapsed_time": "0:06:01", "remaining_time": "4:33:35"}
5
+ {"current_steps": 50, "total_steps": 1854, "loss": 2.0958, "accuracy": 0.4124999940395355, "learning_rate": 4.991067367951343e-06, "epoch": 0.0808244089715094, "percentage": 2.7, "elapsed_time": "0:07:45", "remaining_time": "4:40:06"}
6
+ {"current_steps": 60, "total_steps": 1854, "loss": 1.9577, "accuracy": 0.5, "learning_rate": 4.987131798002389e-06, "epoch": 0.09698929076581128, "percentage": 3.24, "elapsed_time": "0:09:15", "remaining_time": "4:36:40"}
7
+ {"current_steps": 70, "total_steps": 1854, "loss": 2.1089, "accuracy": 0.42500001192092896, "learning_rate": 4.982482035128285e-06, "epoch": 0.11315417256011315, "percentage": 3.78, "elapsed_time": "0:10:48", "remaining_time": "4:35:18"}
8
+ {"current_steps": 80, "total_steps": 1854, "loss": 1.7468, "accuracy": 0.5375000238418579, "learning_rate": 4.9771194145328e-06, "epoch": 0.12931905435441504, "percentage": 4.31, "elapsed_time": "0:12:21", "remaining_time": "4:34:00"}
9
+ {"current_steps": 90, "total_steps": 1854, "loss": 1.9067, "accuracy": 0.4375, "learning_rate": 4.971045476120532e-06, "epoch": 0.1454839361487169, "percentage": 4.85, "elapsed_time": "0:13:55", "remaining_time": "4:32:49"}
10
+ {"current_steps": 100, "total_steps": 1854, "loss": 1.8297, "accuracy": 0.5062500238418579, "learning_rate": 4.964261964054713e-06, "epoch": 0.1616488179430188, "percentage": 5.39, "elapsed_time": "0:15:28", "remaining_time": "4:31:21"}
11
+ {"current_steps": 110, "total_steps": 1854, "loss": 1.7844, "accuracy": 0.512499988079071, "learning_rate": 4.956770826256372e-06, "epoch": 0.17781369973732067, "percentage": 5.93, "elapsed_time": "0:17:02", "remaining_time": "4:30:05"}
12
+ {"current_steps": 120, "total_steps": 1854, "loss": 1.7682, "accuracy": 0.5, "learning_rate": 4.94857421384497e-06, "epoch": 0.19397858153162256, "percentage": 6.47, "elapsed_time": "0:18:36", "remaining_time": "4:28:53"}
13
+ {"current_steps": 130, "total_steps": 1854, "loss": 1.7352, "accuracy": 0.48124998807907104, "learning_rate": 4.939674480520701e-06, "epoch": 0.21014346332592443, "percentage": 7.01, "elapsed_time": "0:20:12", "remaining_time": "4:27:58"}
14
+ {"current_steps": 140, "total_steps": 1854, "loss": 1.8234, "accuracy": 0.4625000059604645, "learning_rate": 4.930074181888613e-06, "epoch": 0.2263083451202263, "percentage": 7.55, "elapsed_time": "0:21:53", "remaining_time": "4:28:06"}
15
+ {"current_steps": 150, "total_steps": 1854, "loss": 1.7178, "accuracy": 0.4625000059604645, "learning_rate": 4.91977607472475e-06, "epoch": 0.2424732269145282, "percentage": 8.09, "elapsed_time": "0:23:21", "remaining_time": "4:25:17"}
16
+ {"current_steps": 160, "total_steps": 1854, "loss": 1.6837, "accuracy": 0.512499988079071, "learning_rate": 4.908783116184534e-06, "epoch": 0.2586381087088301, "percentage": 8.63, "elapsed_time": "0:24:54", "remaining_time": "4:23:47"}
17
+ {"current_steps": 170, "total_steps": 1854, "loss": 1.6438, "accuracy": 0.5062500238418579, "learning_rate": 4.897098462953598e-06, "epoch": 0.27480299050313195, "percentage": 9.17, "elapsed_time": "0:26:27", "remaining_time": "4:22:07"}
18
+ {"current_steps": 180, "total_steps": 1854, "loss": 1.5969, "accuracy": 0.574999988079071, "learning_rate": 4.884725470341331e-06, "epoch": 0.2909678722974338, "percentage": 9.71, "elapsed_time": "0:27:57", "remaining_time": "4:20:03"}
19
+ {"current_steps": 190, "total_steps": 1854, "loss": 1.6442, "accuracy": 0.45625001192092896, "learning_rate": 4.871667691317377e-06, "epoch": 0.3071327540917357, "percentage": 10.25, "elapsed_time": "0:29:33", "remaining_time": "4:18:50"}
20
+ {"current_steps": 200, "total_steps": 1854, "loss": 1.5575, "accuracy": 0.512499988079071, "learning_rate": 4.857928875491392e-06, "epoch": 0.3232976358860376, "percentage": 10.79, "elapsed_time": "0:31:02", "remaining_time": "4:16:42"}
21
+ {"current_steps": 210, "total_steps": 1854, "loss": 1.5606, "accuracy": 0.4937500059604645, "learning_rate": 4.843512968036314e-06, "epoch": 0.33946251768033947, "percentage": 11.33, "elapsed_time": "0:32:31", "remaining_time": "4:14:34"}
22
+ {"current_steps": 220, "total_steps": 1854, "loss": 1.6726, "accuracy": 0.518750011920929, "learning_rate": 4.828424108555486e-06, "epoch": 0.35562739947464134, "percentage": 11.87, "elapsed_time": "0:34:04", "remaining_time": "4:13:03"}
23
+ {"current_steps": 230, "total_steps": 1854, "loss": 1.599, "accuracy": 0.45625001192092896, "learning_rate": 4.812666629893957e-06, "epoch": 0.3717922812689432, "percentage": 12.41, "elapsed_time": "0:35:35", "remaining_time": "4:11:19"}
24
+ {"current_steps": 240, "total_steps": 1854, "loss": 1.6382, "accuracy": 0.4625000059604645, "learning_rate": 4.796245056894273e-06, "epoch": 0.3879571630632451, "percentage": 12.94, "elapsed_time": "0:37:14", "remaining_time": "4:10:29"}
25
+ {"current_steps": 250, "total_steps": 1854, "loss": 1.5308, "accuracy": 0.550000011920929, "learning_rate": 4.779164105097148e-06, "epoch": 0.404122044857547, "percentage": 13.48, "elapsed_time": "0:38:51", "remaining_time": "4:09:22"}
26
+ {"current_steps": 260, "total_steps": 1854, "loss": 1.5664, "accuracy": 0.518750011920929, "learning_rate": 4.761428679387373e-06, "epoch": 0.42028692665184886, "percentage": 14.02, "elapsed_time": "0:40:26", "remaining_time": "4:07:55"}
27
+ {"current_steps": 270, "total_steps": 1854, "loss": 1.5916, "accuracy": 0.5062500238418579, "learning_rate": 4.7430438725853515e-06, "epoch": 0.4364518084461507, "percentage": 14.56, "elapsed_time": "0:42:02", "remaining_time": "4:06:38"}
28
+ {"current_steps": 280, "total_steps": 1854, "loss": 1.5473, "accuracy": 0.45625001192092896, "learning_rate": 4.724014963984669e-06, "epoch": 0.4526166902404526, "percentage": 15.1, "elapsed_time": "0:43:40", "remaining_time": "4:05:30"}
29
+ {"current_steps": 290, "total_steps": 1854, "loss": 1.4462, "accuracy": 0.48124998807907104, "learning_rate": 4.704347417836116e-06, "epoch": 0.4687815720347545, "percentage": 15.64, "elapsed_time": "0:45:12", "remaining_time": "4:03:50"}
30
+ {"current_steps": 300, "total_steps": 1854, "loss": 1.456, "accuracy": 0.44999998807907104, "learning_rate": 4.684046881778603e-06, "epoch": 0.4849464538290564, "percentage": 16.18, "elapsed_time": "0:46:43", "remaining_time": "4:02:00"}
31
+ {"current_steps": 310, "total_steps": 1854, "loss": 1.5057, "accuracy": 0.5249999761581421, "learning_rate": 4.663119185217409e-06, "epoch": 0.5011113356233583, "percentage": 16.72, "elapsed_time": "0:48:19", "remaining_time": "4:00:40"}
32
+ {"current_steps": 320, "total_steps": 1854, "loss": 1.3866, "accuracy": 0.53125, "learning_rate": 4.641570337650232e-06, "epoch": 0.5172762174176602, "percentage": 17.26, "elapsed_time": "0:49:52", "remaining_time": "3:59:03"}
33
+ {"current_steps": 330, "total_steps": 1854, "loss": 1.5835, "accuracy": 0.4625000059604645, "learning_rate": 4.61940652694154e-06, "epoch": 0.533441099211962, "percentage": 17.8, "elapsed_time": "0:51:30", "remaining_time": "3:57:53"}
34
+ {"current_steps": 340, "total_steps": 1854, "loss": 1.6054, "accuracy": 0.512499988079071, "learning_rate": 4.596634117545689e-06, "epoch": 0.5496059810062639, "percentage": 18.34, "elapsed_time": "0:53:02", "remaining_time": "3:56:12"}
35
+ {"current_steps": 350, "total_steps": 1854, "loss": 1.546, "accuracy": 0.5249999761581421, "learning_rate": 4.573259648679335e-06, "epoch": 0.5657708628005658, "percentage": 18.88, "elapsed_time": "0:54:41", "remaining_time": "3:54:59"}
36
+ {"current_steps": 360, "total_steps": 1854, "loss": 1.5233, "accuracy": 0.5, "learning_rate": 4.549289832443663e-06, "epoch": 0.5819357445948676, "percentage": 19.42, "elapsed_time": "0:56:18", "remaining_time": "3:53:40"}
37
+ {"current_steps": 370, "total_steps": 1854, "loss": 1.4381, "accuracy": 0.44999998807907104, "learning_rate": 4.524731551896978e-06, "epoch": 0.5981006263891695, "percentage": 19.96, "elapsed_time": "0:57:52", "remaining_time": "3:52:08"}
38
+ {"current_steps": 380, "total_steps": 1854, "loss": 1.437, "accuracy": 0.53125, "learning_rate": 4.4995918590781925e-06, "epoch": 0.6142655081834714, "percentage": 20.5, "elapsed_time": "0:59:25", "remaining_time": "3:50:31"}
39
+ {"current_steps": 390, "total_steps": 1854, "loss": 1.4849, "accuracy": 0.550000011920929, "learning_rate": 4.473877972981797e-06, "epoch": 0.6304303899777733, "percentage": 21.04, "elapsed_time": "1:01:02", "remaining_time": "3:49:09"}
40
+ {"current_steps": 400, "total_steps": 1854, "loss": 1.3936, "accuracy": 0.48124998807907104, "learning_rate": 4.447597277484894e-06, "epoch": 0.6465952717720752, "percentage": 21.57, "elapsed_time": "1:02:32", "remaining_time": "3:47:19"}
41
+ {"current_steps": 410, "total_steps": 1854, "loss": 1.5684, "accuracy": 0.4625000059604645, "learning_rate": 4.42075731922687e-06, "epoch": 0.6627601535663771, "percentage": 22.11, "elapsed_time": "1:04:04", "remaining_time": "3:45:40"}
42
+ {"current_steps": 420, "total_steps": 1854, "loss": 1.4095, "accuracy": 0.48750001192092896, "learning_rate": 4.3933658054423465e-06, "epoch": 0.6789250353606789, "percentage": 22.65, "elapsed_time": "1:05:37", "remaining_time": "3:44:03"}
43
+ {"current_steps": 430, "total_steps": 1854, "loss": 1.6431, "accuracy": 0.512499988079071, "learning_rate": 4.365430601748003e-06, "epoch": 0.6950899171549808, "percentage": 23.19, "elapsed_time": "1:07:08", "remaining_time": "3:42:21"}
44
+ {"current_steps": 440, "total_steps": 1854, "loss": 1.4506, "accuracy": 0.4625000059604645, "learning_rate": 4.336959729883925e-06, "epoch": 0.7112547989492827, "percentage": 23.73, "elapsed_time": "1:08:41", "remaining_time": "3:40:43"}
45
+ {"current_steps": 450, "total_steps": 1854, "loss": 1.5134, "accuracy": 0.45625001192092896, "learning_rate": 4.307961365410118e-06, "epoch": 0.7274196807435845, "percentage": 24.27, "elapsed_time": "1:10:19", "remaining_time": "3:39:24"}
46
+ {"current_steps": 460, "total_steps": 1854, "loss": 1.4406, "accuracy": 0.550000011920929, "learning_rate": 4.278443835358854e-06, "epoch": 0.7435845625378864, "percentage": 24.81, "elapsed_time": "1:11:54", "remaining_time": "3:37:53"}
47
+ {"current_steps": 470, "total_steps": 1854, "loss": 1.4775, "accuracy": 0.4437499940395355, "learning_rate": 4.248415615843523e-06, "epoch": 0.7597494443321883, "percentage": 25.35, "elapsed_time": "1:13:21", "remaining_time": "3:36:00"}
48
+ {"current_steps": 480, "total_steps": 1854, "loss": 1.4137, "accuracy": 0.5562499761581421, "learning_rate": 4.217885329624666e-06, "epoch": 0.7759143261264903, "percentage": 25.89, "elapsed_time": "1:14:55", "remaining_time": "3:34:29"}
49
+ {"current_steps": 490, "total_steps": 1854, "loss": 1.4904, "accuracy": 0.5, "learning_rate": 4.186861743633911e-06, "epoch": 0.7920792079207921, "percentage": 26.43, "elapsed_time": "1:16:26", "remaining_time": "3:32:46"}
50
+ {"current_steps": 500, "total_steps": 1854, "loss": 1.5005, "accuracy": 0.46875, "learning_rate": 4.155353766456497e-06, "epoch": 0.808244089715094, "percentage": 26.97, "elapsed_time": "1:18:04", "remaining_time": "3:31:26"}
51
+ {"current_steps": 500, "total_steps": 1854, "eval_loss": 1.5202080011367798, "epoch": 0.808244089715094, "percentage": 26.97, "elapsed_time": "1:21:32", "remaining_time": "3:40:48"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6e80ca9d1798b5e28e8fd1a1d6eb5c9849005b9eabbf1ad700c4f813e210c4e
3
+ size 5240