Hugging Face's logo

chchen
/
Mistral-7B-Instruct-v0.2-ORPO-SALT-HALF

PEFT
Safetensors
llama-factory
lora
trl
dpo
Generated from Trainer
Model card Files
xet
 Community
chchen commited on
Commit
997e38e
·
verified ·
1 Parent(s): 0d09c95

Training in progress, step 500

Browse files
Files changed (10) hide show
  1. .ipynb_checkpoints/lora_orpo-checkpoint.yaml +43 -0
  2. adapter_config.json +34 -0
  3. adapter_model.safetensors +3 -0
  4. lora_orpo.yaml +43 -0
  5. special_tokens_map.json +24 -0
  6. tokenizer.json +0 -0
  7. tokenizer.model +3 -0
  8. tokenizer_config.json +45 -0
  9. trainer_log.jsonl +51 -0
  10. training_args.bin +3 -0
.ipynb_checkpoints/lora_orpo-checkpoint.yaml ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ### model
2
+ model_name_or_path: mistralai/Mistral-7B-Instruct-v0.2
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: mistral
14
+ cutoff_len: 1024
15
+ # max_samples: 1000
16
+ overwrite_cache: true
17
+ preprocessing_num_workers: 16
18
+
19
+ ### output
20
+ output_dir: saves/Mistral-7B-Instruct-v0.2/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/Mistral-7B-Instruct-v0.2-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 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
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
+ "up_proj",
24
+ "k_proj",
25
+ "o_proj",
26
+ "v_proj",
27
+ "down_proj",
28
+ "q_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8d35176dade1ba8fee75161b01d21d12887e8a6f3465a53909ebda28fbaafd0
3
+ size 83945296
lora_orpo.yaml ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ### model
2
+ model_name_or_path: mistralai/Mistral-7B-Instruct-v0.2
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: mistral
14
+ cutoff_len: 1024
15
+ # max_samples: 1000
16
+ overwrite_cache: true
17
+ preprocessing_num_workers: 16
18
+
19
+ ### output
20
+ output_dir: saves/Mistral-7B-Instruct-v0.2/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/Mistral-7B-Instruct-v0.2-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 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '<s>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ ' [INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": false,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "</s>",
38
+ "padding_side": "right",
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "split_special_tokens": false,
42
+ "tokenizer_class": "LlamaTokenizer",
43
+ "unk_token": "<unk>",
44
+ "use_default_system_prompt": false
45
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 1770, "loss": 1.8227, "accuracy": 0.5, "learning_rate": 4.999614014035063e-06, "epoch": 0.01693480101608806, "percentage": 0.56, "elapsed_time": "0:01:38", "remaining_time": "4:49:36"}
2
+ {"current_steps": 20, "total_steps": 1770, "loss": 1.9564, "accuracy": 0.675000011920929, "learning_rate": 4.998440543386042e-06, "epoch": 0.03386960203217612, "percentage": 1.13, "elapsed_time": "0:03:13", "remaining_time": "4:42:32"}
3
+ {"current_steps": 30, "total_steps": 1770, "loss": 1.5696, "accuracy": 0.5625, "learning_rate": 4.996479918381253e-06, "epoch": 0.05080440304826418, "percentage": 1.69, "elapsed_time": "0:04:52", "remaining_time": "4:42:52"}
4
+ {"current_steps": 40, "total_steps": 1770, "loss": 1.3545, "accuracy": 0.574999988079071, "learning_rate": 4.993732756731818e-06, "epoch": 0.06773920406435224, "percentage": 2.26, "elapsed_time": "0:06:29", "remaining_time": "4:40:59"}
5
+ {"current_steps": 50, "total_steps": 1770, "loss": 1.5083, "accuracy": 0.606249988079071, "learning_rate": 4.9901999239537345e-06, "epoch": 0.0846740050804403, "percentage": 2.82, "elapsed_time": "0:07:58", "remaining_time": "4:34:24"}
6
+ {"current_steps": 60, "total_steps": 1770, "loss": 1.4627, "accuracy": 0.5687500238418579, "learning_rate": 4.985882533095186e-06, "epoch": 0.10160880609652836, "percentage": 3.39, "elapsed_time": "0:09:30", "remaining_time": "4:31:10"}
7
+ {"current_steps": 70, "total_steps": 1770, "loss": 1.286, "accuracy": 0.637499988079071, "learning_rate": 4.9807819443858705e-06, "epoch": 0.11854360711261643, "percentage": 3.95, "elapsed_time": "0:11:02", "remaining_time": "4:28:15"}
8
+ {"current_steps": 80, "total_steps": 1770, "loss": 1.273, "accuracy": 0.543749988079071, "learning_rate": 4.9748997648084404e-06, "epoch": 0.1354784081287045, "percentage": 4.52, "elapsed_time": "0:12:37", "remaining_time": "4:26:34"}
9
+ {"current_steps": 90, "total_steps": 1770, "loss": 1.2066, "accuracy": 0.6499999761581421, "learning_rate": 4.96823784759222e-06, "epoch": 0.15241320914479256, "percentage": 5.08, "elapsed_time": "0:14:11", "remaining_time": "4:25:01"}
10
+ {"current_steps": 100, "total_steps": 1770, "loss": 1.1448, "accuracy": 0.5062500238418579, "learning_rate": 4.960798291629323e-06, "epoch": 0.1693480101608806, "percentage": 5.65, "elapsed_time": "0:15:48", "remaining_time": "4:24:03"}
11
+ {"current_steps": 110, "total_steps": 1770, "loss": 1.2352, "accuracy": 0.606249988079071, "learning_rate": 4.952583440813383e-06, "epoch": 0.18628281117696868, "percentage": 6.21, "elapsed_time": "0:17:21", "remaining_time": "4:22:03"}
12
+ {"current_steps": 120, "total_steps": 1770, "loss": 1.0615, "accuracy": 0.5249999761581421, "learning_rate": 4.943595883301086e-06, "epoch": 0.20321761219305673, "percentage": 6.78, "elapsed_time": "0:18:58", "remaining_time": "4:20:51"}
13
+ {"current_steps": 130, "total_steps": 1770, "loss": 1.1352, "accuracy": 0.512499988079071, "learning_rate": 4.933838450696757e-06, "epoch": 0.2201524132091448, "percentage": 7.34, "elapsed_time": "0:20:37", "remaining_time": "4:20:05"}
14
+ {"current_steps": 140, "total_steps": 1770, "loss": 1.119, "accuracy": 0.5, "learning_rate": 4.923314217160234e-06, "epoch": 0.23708721422523285, "percentage": 7.91, "elapsed_time": "0:22:09", "remaining_time": "4:18:04"}
15
+ {"current_steps": 150, "total_steps": 1770, "loss": 0.9557, "accuracy": 0.5687500238418579, "learning_rate": 4.9120264984383285e-06, "epoch": 0.2540220152413209, "percentage": 8.47, "elapsed_time": "0:23:49", "remaining_time": "4:17:16"}
16
+ {"current_steps": 160, "total_steps": 1770, "loss": 1.0702, "accuracy": 0.612500011920929, "learning_rate": 4.899978850820176e-06, "epoch": 0.270956816257409, "percentage": 9.04, "elapsed_time": "0:25:32", "remaining_time": "4:17:03"}
17
+ {"current_steps": 170, "total_steps": 1770, "loss": 0.9314, "accuracy": 0.6187499761581421, "learning_rate": 4.887175070016795e-06, "epoch": 0.28789161727349705, "percentage": 9.6, "elapsed_time": "0:27:07", "remaining_time": "4:15:17"}
18
+ {"current_steps": 180, "total_steps": 1770, "loss": 0.9713, "accuracy": 0.6187499761581421, "learning_rate": 4.873619189965217e-06, "epoch": 0.3048264182895851, "percentage": 10.17, "elapsed_time": "0:28:45", "remaining_time": "4:13:58"}
19
+ {"current_steps": 190, "total_steps": 1770, "loss": 0.9551, "accuracy": 0.574999988079071, "learning_rate": 4.859315481557563e-06, "epoch": 0.32176121930567314, "percentage": 10.73, "elapsed_time": "0:30:20", "remaining_time": "4:12:20"}
20
+ {"current_steps": 200, "total_steps": 1770, "loss": 0.9737, "accuracy": 0.5562499761581421, "learning_rate": 4.84426845129546e-06, "epoch": 0.3386960203217612, "percentage": 11.3, "elapsed_time": "0:31:57", "remaining_time": "4:10:54"}
21
+ {"current_steps": 210, "total_steps": 1770, "loss": 0.9726, "accuracy": 0.574999988079071, "learning_rate": 4.828482839870233e-06, "epoch": 0.3556308213378493, "percentage": 11.86, "elapsed_time": "0:33:31", "remaining_time": "4:09:00"}
22
+ {"current_steps": 220, "total_steps": 1770, "loss": 1.009, "accuracy": 0.53125, "learning_rate": 4.811963620669314e-06, "epoch": 0.37256562235393736, "percentage": 12.43, "elapsed_time": "0:35:07", "remaining_time": "4:07:27"}
23
+ {"current_steps": 230, "total_steps": 1770, "loss": 1.0027, "accuracy": 0.574999988079071, "learning_rate": 4.794715998209328e-06, "epoch": 0.3895004233700254, "percentage": 12.99, "elapsed_time": "0:36:44", "remaining_time": "4:05:59"}
24
+ {"current_steps": 240, "total_steps": 1770, "loss": 0.9798, "accuracy": 0.6312500238418579, "learning_rate": 4.7767454064963724e-06, "epoch": 0.40643522438611346, "percentage": 13.56, "elapsed_time": "0:38:19", "remaining_time": "4:04:22"}
25
+ {"current_steps": 250, "total_steps": 1770, "loss": 0.941, "accuracy": 0.5687500238418579, "learning_rate": 4.758057507313987e-06, "epoch": 0.42337002540220153, "percentage": 14.12, "elapsed_time": "0:39:53", "remaining_time": "4:02:30"}
26
+ {"current_steps": 260, "total_steps": 1770, "loss": 0.9696, "accuracy": 0.550000011920929, "learning_rate": 4.73865818843936e-06, "epoch": 0.4403048264182896, "percentage": 14.69, "elapsed_time": "0:41:30", "remaining_time": "4:01:03"}
27
+ {"current_steps": 270, "total_steps": 1770, "loss": 0.94, "accuracy": 0.6000000238418579, "learning_rate": 4.718553561788339e-06, "epoch": 0.4572396274343776, "percentage": 15.25, "elapsed_time": "0:43:06", "remaining_time": "3:59:30"}
28
+ {"current_steps": 280, "total_steps": 1770, "loss": 1.0204, "accuracy": 0.4937500059604645, "learning_rate": 4.697749961489822e-06, "epoch": 0.4741744284504657, "percentage": 15.82, "elapsed_time": "0:44:42", "remaining_time": "3:57:55"}
29
+ {"current_steps": 290, "total_steps": 1770, "loss": 0.8893, "accuracy": 0.612500011920929, "learning_rate": 4.67625394189013e-06, "epoch": 0.4911092294665538, "percentage": 16.38, "elapsed_time": "0:46:17", "remaining_time": "3:56:12"}
30
+ {"current_steps": 300, "total_steps": 1770, "loss": 0.8613, "accuracy": 0.606249988079071, "learning_rate": 4.654072275488016e-06, "epoch": 0.5080440304826418, "percentage": 16.95, "elapsed_time": "0:47:53", "remaining_time": "3:54:39"}
31
+ {"current_steps": 310, "total_steps": 1770, "loss": 0.9303, "accuracy": 0.625, "learning_rate": 4.631211950800925e-06, "epoch": 0.5249788314987299, "percentage": 17.51, "elapsed_time": "0:49:28", "remaining_time": "3:52:59"}
32
+ {"current_steps": 320, "total_steps": 1770, "loss": 0.8904, "accuracy": 0.5687500238418579, "learning_rate": 4.6076801701632095e-06, "epoch": 0.541913632514818, "percentage": 18.08, "elapsed_time": "0:51:00", "remaining_time": "3:51:05"}
33
+ {"current_steps": 330, "total_steps": 1770, "loss": 0.9722, "accuracy": 0.5562499761581421, "learning_rate": 4.583484347456972e-06, "epoch": 0.558848433530906, "percentage": 18.64, "elapsed_time": "0:52:31", "remaining_time": "3:49:12"}
34
+ {"current_steps": 340, "total_steps": 1770, "loss": 1.001, "accuracy": 0.59375, "learning_rate": 4.55863210577626e-06, "epoch": 0.5757832345469941, "percentage": 19.21, "elapsed_time": "0:54:07", "remaining_time": "3:47:40"}
35
+ {"current_steps": 350, "total_steps": 1770, "loss": 0.8865, "accuracy": 0.5249999761581421, "learning_rate": 4.5331312750253465e-06, "epoch": 0.5927180355630821, "percentage": 19.77, "elapsed_time": "0:55:45", "remaining_time": "3:46:12"}
36
+ {"current_steps": 360, "total_steps": 1770, "loss": 0.9432, "accuracy": 0.543749988079071, "learning_rate": 4.506989889451858e-06, "epoch": 0.6096528365791702, "percentage": 20.34, "elapsed_time": "0:57:25", "remaining_time": "3:44:54"}
37
+ {"current_steps": 370, "total_steps": 1770, "loss": 0.9083, "accuracy": 0.581250011920929, "learning_rate": 4.480216185115512e-06, "epoch": 0.6265876375952583, "percentage": 20.9, "elapsed_time": "0:59:02", "remaining_time": "3:43:24"}
38
+ {"current_steps": 380, "total_steps": 1770, "loss": 0.9359, "accuracy": 0.5687500238418579, "learning_rate": 4.4528185972932856e-06, "epoch": 0.6435224386113463, "percentage": 21.47, "elapsed_time": "1:00:39", "remaining_time": "3:41:52"}
39
+ {"current_steps": 390, "total_steps": 1770, "loss": 0.9617, "accuracy": 0.5375000238418579, "learning_rate": 4.424805757821803e-06, "epoch": 0.6604572396274344, "percentage": 22.03, "elapsed_time": "1:02:16", "remaining_time": "3:40:22"}
40
+ {"current_steps": 400, "total_steps": 1770, "loss": 0.9349, "accuracy": 0.606249988079071, "learning_rate": 4.396186492377812e-06, "epoch": 0.6773920406435224, "percentage": 22.6, "elapsed_time": "1:03:55", "remaining_time": "3:38:55"}
41
+ {"current_steps": 410, "total_steps": 1770, "loss": 0.9025, "accuracy": 0.5874999761581421, "learning_rate": 4.366969817697578e-06, "epoch": 0.6943268416596104, "percentage": 23.16, "elapsed_time": "1:05:28", "remaining_time": "3:37:12"}
42
+ {"current_steps": 420, "total_steps": 1770, "loss": 0.9431, "accuracy": 0.4937500059604645, "learning_rate": 4.337164938736086e-06, "epoch": 0.7112616426756986, "percentage": 23.73, "elapsed_time": "1:07:06", "remaining_time": "3:35:41"}
43
+ {"current_steps": 430, "total_steps": 1770, "loss": 0.8529, "accuracy": 0.581250011920929, "learning_rate": 4.306781245766945e-06, "epoch": 0.7281964436917866, "percentage": 24.29, "elapsed_time": "1:08:37", "remaining_time": "3:33:50"}
44
+ {"current_steps": 440, "total_steps": 1770, "loss": 1.0052, "accuracy": 0.5375000238418579, "learning_rate": 4.275828311423903e-06, "epoch": 0.7451312447078747, "percentage": 24.86, "elapsed_time": "1:10:08", "remaining_time": "3:32:02"}
45
+ {"current_steps": 450, "total_steps": 1770, "loss": 0.8586, "accuracy": 0.643750011920929, "learning_rate": 4.244315887684912e-06, "epoch": 0.7620660457239627, "percentage": 25.42, "elapsed_time": "1:11:47", "remaining_time": "3:30:35"}
46
+ {"current_steps": 460, "total_steps": 1770, "loss": 0.9458, "accuracy": 0.5874999761581421, "learning_rate": 4.212253902799685e-06, "epoch": 0.7790008467400508, "percentage": 25.99, "elapsed_time": "1:13:24", "remaining_time": "3:29:04"}
47
+ {"current_steps": 470, "total_steps": 1770, "loss": 0.9571, "accuracy": 0.518750011920929, "learning_rate": 4.179652458161718e-06, "epoch": 0.7959356477561389, "percentage": 26.55, "elapsed_time": "1:14:58", "remaining_time": "3:27:23"}
48
+ {"current_steps": 480, "total_steps": 1770, "loss": 0.9492, "accuracy": 0.543749988079071, "learning_rate": 4.146521825125765e-06, "epoch": 0.8128704487722269, "percentage": 27.12, "elapsed_time": "1:16:37", "remaining_time": "3:25:55"}
49
+ {"current_steps": 490, "total_steps": 1770, "loss": 0.9463, "accuracy": 0.59375, "learning_rate": 4.11287244177176e-06, "epoch": 0.8298052497883149, "percentage": 27.68, "elapsed_time": "1:18:16", "remaining_time": "3:24:29"}
50
+ {"current_steps": 500, "total_steps": 1770, "loss": 0.9115, "accuracy": 0.6000000238418579, "learning_rate": 4.078714909616215e-06, "epoch": 0.8467400508044031, "percentage": 28.25, "elapsed_time": "1:19:53", "remaining_time": "3:22:55"}
51
+ {"current_steps": 500, "total_steps": 1770, "eval_loss": 0.9161481857299805, "epoch": 0.8467400508044031, "percentage": 28.25, "elapsed_time": "1:23:08", "remaining_time": "3:31:09"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39462ffc5c50d0e5b3e6f853ccc24e27b36ae466ad9572dede0535641beec346
3
+ size 5240