Hugging Face's logo

Alignment-Lab-AI
/
AttourneyAtLam

PEFT
Model card Files
xet
Community
1
Alignment-Lab-AI commited on
Commit
7382415
·
1 Parent(s): b99b68d

Upload 10 files

Browse files
Files changed (10) hide show
  1. README.md +20 -0
  2. adapter_config.json +20 -0
  3. adapter_model.bin +3 -0
  4. all_results.json +7 -0
  5. finetuning_args.json +13 -0
  6. train_results.json +7 -0
  7. trainer_log.jsonl +114 -0
  8. trainer_state.json +367 -0
  9. training_args.bin +3 -0
  10. training_loss.png +0 -0
README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: True
16
+ - bnb_4bit_compute_dtype: float16
17
+ ### Framework versions
18
+
19
+
20
+ - PEFT 0.4.0.dev0
adapter_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "Open-Orca/OpenOrca-Preview1-13B",
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": 32.0,
10
+ "lora_dropout": 0.1,
11
+ "modules_to_save": null,
12
+ "peft_type": "LORA",
13
+ "r": 8,
14
+ "revision": null,
15
+ "target_modules": [
16
+ "q_proj",
17
+ "v_proj"
18
+ ],
19
+ "task_type": "CAUSAL_LM"
20
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee873dcba4592cbe930fa73f24f9136dd7b5ff5bae6824d84653234441634063
3
+ size 26269517
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 1.4581370320699618,
4
+ "train_runtime": 1932.4895,
5
+ "train_samples_per_second": 4.782,
6
+ "train_steps_per_second": 0.299
7
+ }
finetuning_args.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "finetuning_type": "lora",
3
+ "lora_alpha": 32.0,
4
+ "lora_dropout": 0.1,
5
+ "lora_rank": 8,
6
+ "lora_target": [
7
+ "q_proj",
8
+ "v_proj"
9
+ ],
10
+ "name_module_trainable": "mlp",
11
+ "num_hidden_layers": 32,
12
+ "num_layer_trainable": 3
13
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 1.4581370320699618,
4
+ "train_runtime": 1932.4895,
5
+ "train_samples_per_second": 4.782,
6
+ "train_steps_per_second": 0.299
7
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 578, "loss": 2.529, "reward": null, "learning_rate": 4.996308123523995e-05, "epoch": 0.02, "percentage": 1.73, "elapsed_time": "0:00:33", "remaining_time": "0:31:54"}
2
+ {"current_steps": 10, "total_steps": 578, "loss": 2.529, "reward": null, "learning_rate": 4.996308123523995e-05, "epoch": 0.02, "percentage": 1.73, "elapsed_time": "0:00:33", "remaining_time": "0:31:54"}
3
+ {"current_steps": 20, "total_steps": 578, "loss": 2.3135, "reward": null, "learning_rate": 4.98524339805751e-05, "epoch": 0.03, "percentage": 3.46, "elapsed_time": "0:01:05", "remaining_time": "0:30:25"}
4
+ {"current_steps": 20, "total_steps": 578, "loss": 2.3135, "reward": null, "learning_rate": 4.98524339805751e-05, "epoch": 0.03, "percentage": 3.46, "elapsed_time": "0:01:05", "remaining_time": "0:30:25"}
5
+ {"current_steps": 30, "total_steps": 578, "loss": 2.0123, "reward": null, "learning_rate": 4.966838503280275e-05, "epoch": 0.05, "percentage": 5.19, "elapsed_time": "0:01:34", "remaining_time": "0:28:52"}
6
+ {"current_steps": 30, "total_steps": 578, "loss": 2.0123, "reward": null, "learning_rate": 4.966838503280275e-05, "epoch": 0.05, "percentage": 5.19, "elapsed_time": "0:01:34", "remaining_time": "0:28:52"}
7
+ {"current_steps": 40, "total_steps": 578, "loss": 1.8671, "reward": null, "learning_rate": 4.941147798070748e-05, "epoch": 0.07, "percentage": 6.92, "elapsed_time": "0:02:07", "remaining_time": "0:28:29"}
8
+ {"current_steps": 40, "total_steps": 578, "loss": 1.8671, "reward": null, "learning_rate": 4.941147798070748e-05, "epoch": 0.07, "percentage": 6.92, "elapsed_time": "0:02:07", "remaining_time": "0:28:30"}
9
+ {"current_steps": 50, "total_steps": 578, "loss": 1.8716, "reward": null, "learning_rate": 4.9082471599571015e-05, "epoch": 0.09, "percentage": 8.65, "elapsed_time": "0:02:42", "remaining_time": "0:28:38"}
10
+ {"current_steps": 50, "total_steps": 578, "loss": 1.8716, "reward": null, "learning_rate": 4.9082471599571015e-05, "epoch": 0.09, "percentage": 8.65, "elapsed_time": "0:02:42", "remaining_time": "0:28:38"}
11
+ {"current_steps": 60, "total_steps": 578, "loss": 1.8011, "reward": null, "learning_rate": 4.8682337610128526e-05, "epoch": 0.1, "percentage": 10.38, "elapsed_time": "0:03:14", "remaining_time": "0:28:01"}
12
+ {"current_steps": 60, "total_steps": 578, "loss": 1.8011, "reward": null, "learning_rate": 4.8682337610128526e-05, "epoch": 0.1, "percentage": 10.38, "elapsed_time": "0:03:14", "remaining_time": "0:28:01"}
13
+ {"current_steps": 70, "total_steps": 578, "loss": 1.6831, "reward": null, "learning_rate": 4.821225780859032e-05, "epoch": 0.12, "percentage": 12.11, "elapsed_time": "0:03:48", "remaining_time": "0:27:38"}
14
+ {"current_steps": 70, "total_steps": 578, "loss": 1.6831, "reward": null, "learning_rate": 4.821225780859032e-05, "epoch": 0.12, "percentage": 12.11, "elapsed_time": "0:03:48", "remaining_time": "0:27:38"}
15
+ {"current_steps": 80, "total_steps": 578, "loss": 1.6496, "reward": null, "learning_rate": 4.7673620576205294e-05, "epoch": 0.14, "percentage": 13.84, "elapsed_time": "0:04:21", "remaining_time": "0:27:10"}
16
+ {"current_steps": 80, "total_steps": 578, "loss": 1.6496, "reward": null, "learning_rate": 4.7673620576205294e-05, "epoch": 0.14, "percentage": 13.84, "elapsed_time": "0:04:21", "remaining_time": "0:27:10"}
17
+ {"current_steps": 90, "total_steps": 578, "loss": 1.5882, "reward": null, "learning_rate": 4.7131541204339604e-05, "epoch": 0.16, "percentage": 15.57, "elapsed_time": "0:04:55", "remaining_time": "0:26:42"}
18
+ {"current_steps": 90, "total_steps": 578, "loss": 1.5882, "reward": null, "learning_rate": 4.7131541204339604e-05, "epoch": 0.16, "percentage": 15.57, "elapsed_time": "0:04:55", "remaining_time": "0:26:42"}
19
+ {"current_steps": 100, "total_steps": 578, "loss": 1.5674, "reward": null, "learning_rate": 4.646719126488686e-05, "epoch": 0.17, "percentage": 17.3, "elapsed_time": "0:05:25", "remaining_time": "0:25:57"}
20
+ {"current_steps": 100, "total_steps": 578, "loss": 1.5674, "reward": null, "learning_rate": 4.646719126488686e-05, "epoch": 0.17, "percentage": 17.3, "elapsed_time": "0:05:25", "remaining_time": "0:25:57"}
21
+ {"current_steps": 110, "total_steps": 578, "loss": 1.5274, "reward": null, "learning_rate": 4.573943795068471e-05, "epoch": 0.19, "percentage": 19.03, "elapsed_time": "0:06:02", "remaining_time": "0:25:42"}
22
+ {"current_steps": 110, "total_steps": 578, "loss": 1.5274, "reward": null, "learning_rate": 4.573943795068471e-05, "epoch": 0.19, "percentage": 19.03, "elapsed_time": "0:06:02", "remaining_time": "0:25:42"}
23
+ {"current_steps": 120, "total_steps": 578, "loss": 1.503, "reward": null, "learning_rate": 4.4950430682006e-05, "epoch": 0.21, "percentage": 20.76, "elapsed_time": "0:06:37", "remaining_time": "0:25:15"}
24
+ {"current_steps": 120, "total_steps": 578, "loss": 1.503, "reward": null, "learning_rate": 4.4950430682006e-05, "epoch": 0.21, "percentage": 20.76, "elapsed_time": "0:06:37", "remaining_time": "0:25:15"}
25
+ {"current_steps": 130, "total_steps": 578, "loss": 1.5161, "reward": null, "learning_rate": 4.410249979275041e-05, "epoch": 0.22, "percentage": 22.49, "elapsed_time": "0:07:10", "remaining_time": "0:24:43"}
26
+ {"current_steps": 130, "total_steps": 578, "loss": 1.5161, "reward": null, "learning_rate": 4.410249979275041e-05, "epoch": 0.22, "percentage": 22.49, "elapsed_time": "0:07:10", "remaining_time": "0:24:43"}
27
+ {"current_steps": 140, "total_steps": 578, "loss": 1.4715, "reward": null, "learning_rate": 4.319814964780064e-05, "epoch": 0.24, "percentage": 24.22, "elapsed_time": "0:07:44", "remaining_time": "0:24:12"}
28
+ {"current_steps": 140, "total_steps": 578, "loss": 1.4715, "reward": null, "learning_rate": 4.319814964780064e-05, "epoch": 0.24, "percentage": 24.22, "elapsed_time": "0:07:44", "remaining_time": "0:24:12"}
29
+ {"current_steps": 150, "total_steps": 578, "loss": 1.4587, "reward": null, "learning_rate": 4.2240051246377613e-05, "epoch": 0.26, "percentage": 25.95, "elapsed_time": "0:08:17", "remaining_time": "0:23:39"}
30
+ {"current_steps": 150, "total_steps": 578, "loss": 1.4587, "reward": null, "learning_rate": 4.2240051246377613e-05, "epoch": 0.26, "percentage": 25.95, "elapsed_time": "0:08:17", "remaining_time": "0:23:39"}
31
+ {"current_steps": 160, "total_steps": 578, "loss": 1.3959, "reward": null, "learning_rate": 4.123103433324129e-05, "epoch": 0.28, "percentage": 27.68, "elapsed_time": "0:08:52", "remaining_time": "0:23:10"}
32
+ {"current_steps": 160, "total_steps": 578, "loss": 1.3959, "reward": null, "learning_rate": 4.123103433324129e-05, "epoch": 0.28, "percentage": 27.68, "elapsed_time": "0:08:52", "remaining_time": "0:23:10"}
33
+ {"current_steps": 170, "total_steps": 578, "loss": 1.3988, "reward": null, "learning_rate": 4.017407904103607e-05, "epoch": 0.29, "percentage": 29.41, "elapsed_time": "0:09:22", "remaining_time": "0:22:30"}
34
+ {"current_steps": 170, "total_steps": 578, "loss": 1.3988, "reward": null, "learning_rate": 4.017407904103607e-05, "epoch": 0.29, "percentage": 29.41, "elapsed_time": "0:09:22", "remaining_time": "0:22:30"}
35
+ {"current_steps": 180, "total_steps": 578, "loss": 1.3834, "reward": null, "learning_rate": 3.907230708846552e-05, "epoch": 0.31, "percentage": 31.14, "elapsed_time": "0:09:53", "remaining_time": "0:21:53"}
36
+ {"current_steps": 180, "total_steps": 578, "loss": 1.3834, "reward": null, "learning_rate": 3.907230708846552e-05, "epoch": 0.31, "percentage": 31.14, "elapsed_time": "0:09:53", "remaining_time": "0:21:53"}
37
+ {"current_steps": 190, "total_steps": 578, "loss": 1.4369, "reward": null, "learning_rate": 3.7928972560292554e-05, "epoch": 0.33, "percentage": 32.87, "elapsed_time": "0:10:27", "remaining_time": "0:21:21"}
38
+ {"current_steps": 190, "total_steps": 578, "loss": 1.4369, "reward": null, "learning_rate": 3.7928972560292554e-05, "epoch": 0.33, "percentage": 32.87, "elapsed_time": "0:10:27", "remaining_time": "0:21:21"}
39
+ {"current_steps": 200, "total_steps": 578, "loss": 1.4171, "reward": null, "learning_rate": 3.674745229639617e-05, "epoch": 0.35, "percentage": 34.6, "elapsed_time": "0:11:02", "remaining_time": "0:20:52"}
40
+ {"current_steps": 200, "total_steps": 578, "loss": 1.4171, "reward": null, "learning_rate": 3.674745229639617e-05, "epoch": 0.35, "percentage": 34.6, "elapsed_time": "0:11:02", "remaining_time": "0:20:52"}
41
+ {"current_steps": 210, "total_steps": 578, "loss": 1.4079, "reward": null, "learning_rate": 3.553123591827093e-05, "epoch": 0.36, "percentage": 36.33, "elapsed_time": "0:11:34", "remaining_time": "0:20:17"}
42
+ {"current_steps": 210, "total_steps": 578, "loss": 1.4079, "reward": null, "learning_rate": 3.553123591827093e-05, "epoch": 0.36, "percentage": 36.33, "elapsed_time": "0:11:35", "remaining_time": "0:20:17"}
43
+ {"current_steps": 220, "total_steps": 578, "loss": 1.2868, "reward": null, "learning_rate": 3.428391552242576e-05, "epoch": 0.38, "percentage": 38.06, "elapsed_time": "0:12:10", "remaining_time": "0:19:48"}
44
+ {"current_steps": 220, "total_steps": 578, "loss": 1.2868, "reward": null, "learning_rate": 3.428391552242576e-05, "epoch": 0.38, "percentage": 38.06, "elapsed_time": "0:12:10", "remaining_time": "0:19:48"}
45
+ {"current_steps": 230, "total_steps": 578, "loss": 1.3193, "reward": null, "learning_rate": 3.300917507112261e-05, "epoch": 0.4, "percentage": 39.79, "elapsed_time": "0:12:43", "remaining_time": "0:19:15"}
46
+ {"current_steps": 230, "total_steps": 578, "loss": 1.3193, "reward": null, "learning_rate": 3.300917507112261e-05, "epoch": 0.4, "percentage": 39.79, "elapsed_time": "0:12:43", "remaining_time": "0:19:15"}
47
+ {"current_steps": 240, "total_steps": 578, "loss": 1.3231, "reward": null, "learning_rate": 3.171077951178964e-05, "epoch": 0.42, "percentage": 41.52, "elapsed_time": "0:13:14", "remaining_time": "0:18:39"}
48
+ {"current_steps": 240, "total_steps": 578, "loss": 1.3231, "reward": null, "learning_rate": 3.171077951178964e-05, "epoch": 0.42, "percentage": 41.52, "elapsed_time": "0:13:14", "remaining_time": "0:18:39"}
49
+ {"current_steps": 250, "total_steps": 578, "loss": 1.3896, "reward": null, "learning_rate": 3.039256365724447e-05, "epoch": 0.43, "percentage": 43.25, "elapsed_time": "0:13:45", "remaining_time": "0:18:03"}
50
+ {"current_steps": 250, "total_steps": 578, "loss": 1.3896, "reward": null, "learning_rate": 3.039256365724447e-05, "epoch": 0.43, "percentage": 43.25, "elapsed_time": "0:13:45", "remaining_time": "0:18:03"}
51
+ {"current_steps": 260, "total_steps": 578, "loss": 1.3857, "reward": null, "learning_rate": 2.905842085957007e-05, "epoch": 0.45, "percentage": 44.98, "elapsed_time": "0:14:17", "remaining_time": "0:17:28"}
52
+ {"current_steps": 260, "total_steps": 578, "loss": 1.3857, "reward": null, "learning_rate": 2.905842085957007e-05, "epoch": 0.45, "percentage": 44.98, "elapsed_time": "0:14:17", "remaining_time": "0:17:28"}
53
+ {"current_steps": 270, "total_steps": 578, "loss": 1.3863, "reward": null, "learning_rate": 2.7712291511094725e-05, "epoch": 0.47, "percentage": 46.71, "elapsed_time": "0:14:48", "remaining_time": "0:16:53"}
54
+ {"current_steps": 270, "total_steps": 578, "loss": 1.3863, "reward": null, "learning_rate": 2.7712291511094725e-05, "epoch": 0.47, "percentage": 46.71, "elapsed_time": "0:14:48", "remaining_time": "0:16:53"}
55
+ {"current_steps": 280, "total_steps": 578, "loss": 1.4821, "reward": null, "learning_rate": 2.6358151406438674e-05, "epoch": 0.48, "percentage": 48.44, "elapsed_time": "0:15:20", "remaining_time": "0:16:20"}
56
+ {"current_steps": 280, "total_steps": 578, "loss": 1.4821, "reward": null, "learning_rate": 2.6358151406438674e-05, "epoch": 0.48, "percentage": 48.44, "elapsed_time": "0:15:20", "remaining_time": "0:16:20"}
57
+ {"current_steps": 290, "total_steps": 578, "loss": 1.3522, "reward": null, "learning_rate": 2.5e-05, "epoch": 0.5, "percentage": 50.17, "elapsed_time": "0:15:54", "remaining_time": "0:15:47"}
58
+ {"current_steps": 290, "total_steps": 578, "loss": 1.3522, "reward": null, "learning_rate": 2.5e-05, "epoch": 0.5, "percentage": 50.17, "elapsed_time": "0:15:54", "remaining_time": "0:15:47"}
59
+ {"current_steps": 300, "total_steps": 578, "loss": 1.312, "reward": null, "learning_rate": 2.3641848593561322e-05, "epoch": 0.52, "percentage": 51.9, "elapsed_time": "0:16:28", "remaining_time": "0:15:16"}
60
+ {"current_steps": 300, "total_steps": 578, "loss": 1.312, "reward": null, "learning_rate": 2.3641848593561322e-05, "epoch": 0.52, "percentage": 51.9, "elapsed_time": "0:16:28", "remaining_time": "0:15:16"}
61
+ {"current_steps": 310, "total_steps": 578, "loss": 1.3254, "reward": null, "learning_rate": 2.228770848890528e-05, "epoch": 0.54, "percentage": 53.63, "elapsed_time": "0:17:05", "remaining_time": "0:14:46"}
62
+ {"current_steps": 310, "total_steps": 578, "loss": 1.3254, "reward": null, "learning_rate": 2.228770848890528e-05, "epoch": 0.54, "percentage": 53.63, "elapsed_time": "0:17:05", "remaining_time": "0:14:46"}
63
+ {"current_steps": 320, "total_steps": 578, "loss": 1.3726, "reward": null, "learning_rate": 2.0941579140429933e-05, "epoch": 0.55, "percentage": 55.36, "elapsed_time": "0:17:37", "remaining_time": "0:14:12"}
64
+ {"current_steps": 320, "total_steps": 578, "loss": 1.3726, "reward": null, "learning_rate": 2.0941579140429933e-05, "epoch": 0.55, "percentage": 55.36, "elapsed_time": "0:17:37", "remaining_time": "0:14:12"}
65
+ {"current_steps": 330, "total_steps": 578, "loss": 1.2926, "reward": null, "learning_rate": 1.960743634275554e-05, "epoch": 0.57, "percentage": 57.09, "elapsed_time": "0:18:10", "remaining_time": "0:13:39"}
66
+ {"current_steps": 330, "total_steps": 578, "loss": 1.2926, "reward": null, "learning_rate": 1.960743634275554e-05, "epoch": 0.57, "percentage": 57.09, "elapsed_time": "0:18:10", "remaining_time": "0:13:39"}
67
+ {"current_steps": 340, "total_steps": 578, "loss": 1.3776, "reward": null, "learning_rate": 1.828922048821037e-05, "epoch": 0.59, "percentage": 58.82, "elapsed_time": "0:18:42", "remaining_time": "0:13:05"}
68
+ {"current_steps": 340, "total_steps": 578, "loss": 1.3776, "reward": null, "learning_rate": 1.828922048821037e-05, "epoch": 0.59, "percentage": 58.82, "elapsed_time": "0:18:42", "remaining_time": "0:13:05"}
69
+ {"current_steps": 350, "total_steps": 578, "loss": 1.4351, "reward": null, "learning_rate": 1.6990824928877393e-05, "epoch": 0.61, "percentage": 60.55, "elapsed_time": "0:19:15", "remaining_time": "0:12:32"}
70
+ {"current_steps": 350, "total_steps": 578, "loss": 1.4351, "reward": null, "learning_rate": 1.6990824928877393e-05, "epoch": 0.61, "percentage": 60.55, "elapsed_time": "0:19:15", "remaining_time": "0:12:32"}
71
+ {"current_steps": 360, "total_steps": 578, "loss": 1.3105, "reward": null, "learning_rate": 1.5716084477574245e-05, "epoch": 0.62, "percentage": 62.28, "elapsed_time": "0:19:46", "remaining_time": "0:11:58"}
72
+ {"current_steps": 360, "total_steps": 578, "loss": 1.3105, "reward": null, "learning_rate": 1.5716084477574245e-05, "epoch": 0.62, "percentage": 62.28, "elapsed_time": "0:19:46", "remaining_time": "0:11:58"}
73
+ {"current_steps": 370, "total_steps": 578, "loss": 1.3345, "reward": null, "learning_rate": 1.4468764081729063e-05, "epoch": 0.64, "percentage": 64.01, "elapsed_time": "0:20:18", "remaining_time": "0:11:25"}
74
+ {"current_steps": 370, "total_steps": 578, "loss": 1.3345, "reward": null, "learning_rate": 1.4468764081729063e-05, "epoch": 0.64, "percentage": 64.01, "elapsed_time": "0:20:18", "remaining_time": "0:11:25"}
75
+ {"current_steps": 380, "total_steps": 578, "loss": 1.3971, "reward": null, "learning_rate": 1.3252547703603829e-05, "epoch": 0.66, "percentage": 65.74, "elapsed_time": "0:20:52", "remaining_time": "0:10:52"}
76
+ {"current_steps": 380, "total_steps": 578, "loss": 1.3971, "reward": null, "learning_rate": 1.3252547703603829e-05, "epoch": 0.66, "percentage": 65.74, "elapsed_time": "0:20:52", "remaining_time": "0:10:52"}
77
+ {"current_steps": 390, "total_steps": 578, "loss": 1.2962, "reward": null, "learning_rate": 1.207102743970745e-05, "epoch": 0.67, "percentage": 67.47, "elapsed_time": "0:21:27", "remaining_time": "0:10:20"}
78
+ {"current_steps": 390, "total_steps": 578, "loss": 1.2962, "reward": null, "learning_rate": 1.207102743970745e-05, "epoch": 0.67, "percentage": 67.47, "elapsed_time": "0:21:27", "remaining_time": "0:10:20"}
79
+ {"current_steps": 400, "total_steps": 578, "loss": 1.3572, "reward": null, "learning_rate": 1.0927692911534476e-05, "epoch": 0.69, "percentage": 69.2, "elapsed_time": "0:22:04", "remaining_time": "0:09:49"}
80
+ {"current_steps": 400, "total_steps": 578, "loss": 1.3572, "reward": null, "learning_rate": 1.0927692911534476e-05, "epoch": 0.69, "percentage": 69.2, "elapsed_time": "0:22:04", "remaining_time": "0:09:49"}
81
+ {"current_steps": 410, "total_steps": 578, "loss": 1.318, "reward": null, "learning_rate": 9.825920958963936e-06, "epoch": 0.71, "percentage": 70.93, "elapsed_time": "0:22:38", "remaining_time": "0:09:16"}
82
+ {"current_steps": 410, "total_steps": 578, "loss": 1.318, "reward": null, "learning_rate": 9.825920958963936e-06, "epoch": 0.71, "percentage": 70.93, "elapsed_time": "0:22:38", "remaining_time": "0:09:16"}
83
+ {"current_steps": 420, "total_steps": 578, "loss": 1.3644, "reward": null, "learning_rate": 8.768965666758704e-06, "epoch": 0.73, "percentage": 72.66, "elapsed_time": "0:23:12", "remaining_time": "0:08:44"}
84
+ {"current_steps": 420, "total_steps": 578, "loss": 1.3644, "reward": null, "learning_rate": 8.768965666758704e-06, "epoch": 0.73, "percentage": 72.66, "elapsed_time": "0:23:12", "remaining_time": "0:08:44"}
85
+ {"current_steps": 430, "total_steps": 578, "loss": 1.4429, "reward": null, "learning_rate": 7.759948753622389e-06, "epoch": 0.74, "percentage": 74.39, "elapsed_time": "0:23:48", "remaining_time": "0:08:11"}
86
+ {"current_steps": 430, "total_steps": 578, "loss": 1.4429, "reward": null, "learning_rate": 7.759948753622389e-06, "epoch": 0.74, "percentage": 74.39, "elapsed_time": "0:23:48", "remaining_time": "0:08:11"}
87
+ {"current_steps": 440, "total_steps": 578, "loss": 1.3241, "reward": null, "learning_rate": 6.801850352199371e-06, "epoch": 0.76, "percentage": 76.12, "elapsed_time": "0:24:23", "remaining_time": "0:07:39"}
88
+ {"current_steps": 440, "total_steps": 578, "loss": 1.3241, "reward": null, "learning_rate": 6.801850352199371e-06, "epoch": 0.76, "percentage": 76.12, "elapsed_time": "0:24:23", "remaining_time": "0:07:39"}
89
+ {"current_steps": 450, "total_steps": 578, "loss": 1.3219, "reward": null, "learning_rate": 5.897500207249593e-06, "epoch": 0.78, "percentage": 77.85, "elapsed_time": "0:24:56", "remaining_time": "0:07:05"}
90
+ {"current_steps": 450, "total_steps": 578, "loss": 1.3219, "reward": null, "learning_rate": 5.897500207249593e-06, "epoch": 0.78, "percentage": 77.85, "elapsed_time": "0:24:56", "remaining_time": "0:07:05"}
91
+ {"current_steps": 460, "total_steps": 578, "loss": 1.2544, "reward": null, "learning_rate": 5.049569317994013e-06, "epoch": 0.8, "percentage": 79.58, "elapsed_time": "0:25:32", "remaining_time": "0:06:33"}
92
+ {"current_steps": 460, "total_steps": 578, "loss": 1.2544, "reward": null, "learning_rate": 5.049569317994013e-06, "epoch": 0.8, "percentage": 79.58, "elapsed_time": "0:25:32", "remaining_time": "0:06:33"}
93
+ {"current_steps": 470, "total_steps": 578, "loss": 1.4059, "reward": null, "learning_rate": 4.260562049315301e-06, "epoch": 0.81, "percentage": 81.31, "elapsed_time": "0:26:05", "remaining_time": "0:05:59"}
94
+ {"current_steps": 470, "total_steps": 578, "loss": 1.4059, "reward": null, "learning_rate": 4.260562049315301e-06, "epoch": 0.81, "percentage": 81.31, "elapsed_time": "0:26:05", "remaining_time": "0:05:59"}
95
+ {"current_steps": 480, "total_steps": 578, "loss": 1.3633, "reward": null, "learning_rate": 3.5328087351131495e-06, "epoch": 0.83, "percentage": 83.04, "elapsed_time": "0:26:38", "remaining_time": "0:05:26"}
96
+ {"current_steps": 480, "total_steps": 578, "loss": 1.3633, "reward": null, "learning_rate": 3.5328087351131495e-06, "epoch": 0.83, "percentage": 83.04, "elapsed_time": "0:26:38", "remaining_time": "0:05:26"}
97
+ {"current_steps": 490, "total_steps": 578, "loss": 1.2363, "reward": null, "learning_rate": 2.8684587956604e-06, "epoch": 0.85, "percentage": 84.78, "elapsed_time": "0:27:10", "remaining_time": "0:04:52"}
98
+ {"current_steps": 490, "total_steps": 578, "loss": 1.2363, "reward": null, "learning_rate": 2.8684587956604e-06, "epoch": 0.85, "percentage": 84.78, "elapsed_time": "0:27:10", "remaining_time": "0:04:52"}
99
+ {"current_steps": 500, "total_steps": 578, "loss": 1.3308, "reward": null, "learning_rate": 2.2694743892876873e-06, "epoch": 0.87, "percentage": 86.51, "elapsed_time": "0:27:46", "remaining_time": "0:04:19"}
100
+ {"current_steps": 500, "total_steps": 578, "loss": 1.3308, "reward": null, "learning_rate": 2.2694743892876873e-06, "epoch": 0.87, "percentage": 86.51, "elapsed_time": "0:27:46", "remaining_time": "0:04:19"}
101
+ {"current_steps": 510, "total_steps": 578, "loss": 1.3525, "reward": null, "learning_rate": 1.7376246171465188e-06, "epoch": 0.88, "percentage": 88.24, "elapsed_time": "0:28:19", "remaining_time": "0:03:46"}
102
+ {"current_steps": 510, "total_steps": 578, "loss": 1.3525, "reward": null, "learning_rate": 1.7376246171465188e-06, "epoch": 0.88, "percentage": 88.24, "elapsed_time": "0:28:19", "remaining_time": "0:03:46"}
103
+ {"current_steps": 520, "total_steps": 578, "loss": 1.3765, "reward": null, "learning_rate": 1.2744802981669217e-06, "epoch": 0.9, "percentage": 89.97, "elapsed_time": "0:28:54", "remaining_time": "0:03:13"}
104
+ {"current_steps": 520, "total_steps": 578, "loss": 1.3765, "reward": null, "learning_rate": 1.2744802981669217e-06, "epoch": 0.9, "percentage": 89.97, "elapsed_time": "0:28:54", "remaining_time": "0:03:13"}
105
+ {"current_steps": 530, "total_steps": 578, "loss": 1.3155, "reward": null, "learning_rate": 8.814093296418885e-07, "epoch": 0.92, "percentage": 91.7, "elapsed_time": "0:29:27", "remaining_time": "0:02:40"}
106
+ {"current_steps": 530, "total_steps": 578, "loss": 1.3155, "reward": null, "learning_rate": 8.814093296418885e-07, "epoch": 0.92, "percentage": 91.7, "elapsed_time": "0:29:27", "remaining_time": "0:02:40"}
107
+ {"current_steps": 540, "total_steps": 578, "loss": 1.3324, "reward": null, "learning_rate": 5.595726471410961e-07, "epoch": 0.93, "percentage": 93.43, "elapsed_time": "0:30:01", "remaining_time": "0:02:06"}
108
+ {"current_steps": 540, "total_steps": 578, "loss": 1.3324, "reward": null, "learning_rate": 5.595726471410961e-07, "epoch": 0.93, "percentage": 93.43, "elapsed_time": "0:30:01", "remaining_time": "0:02:06"}
109
+ {"current_steps": 550, "total_steps": 578, "loss": 1.3114, "reward": null, "learning_rate": 3.099207956863359e-07, "epoch": 0.95, "percentage": 95.16, "elapsed_time": "0:30:33", "remaining_time": "0:01:33"}
110
+ {"current_steps": 550, "total_steps": 578, "loss": 1.3114, "reward": null, "learning_rate": 3.099207956863359e-07, "epoch": 0.95, "percentage": 95.16, "elapsed_time": "0:30:33", "remaining_time": "0:01:33"}
111
+ {"current_steps": 560, "total_steps": 578, "loss": 1.2908, "reward": null, "learning_rate": 1.3319112231567344e-07, "epoch": 0.97, "percentage": 96.89, "elapsed_time": "0:31:07", "remaining_time": "0:01:00"}
112
+ {"current_steps": 560, "total_steps": 578, "loss": 1.2908, "reward": null, "learning_rate": 1.3319112231567344e-07, "epoch": 0.97, "percentage": 96.89, "elapsed_time": "0:31:07", "remaining_time": "0:01:00"}
113
+ {"current_steps": 570, "total_steps": 578, "loss": 1.3837, "reward": null, "learning_rate": 2.990559832808659e-08, "epoch": 0.99, "percentage": 98.62, "elapsed_time": "0:31:44", "remaining_time": "0:00:26"}
114
+ {"current_steps": 570, "total_steps": 578, "loss": 1.3837, "reward": null, "learning_rate": 2.990559832808659e-08, "epoch": 0.99, "percentage": 98.62, "elapsed_time": "0:31:44", "remaining_time": "0:00:26"}
trainer_state.json ADDED
@@ -0,0 +1,367 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 578,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 4.996308123523995e-05,
13
+ "loss": 2.529,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.03,
18
+ "learning_rate": 4.98524339805751e-05,
19
+ "loss": 2.3135,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.05,
24
+ "learning_rate": 4.966838503280275e-05,
25
+ "loss": 2.0123,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.07,
30
+ "learning_rate": 4.941147798070748e-05,
31
+ "loss": 1.8671,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.09,
36
+ "learning_rate": 4.9082471599571015e-05,
37
+ "loss": 1.8716,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.1,
42
+ "learning_rate": 4.8682337610128526e-05,
43
+ "loss": 1.8011,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.12,
48
+ "learning_rate": 4.821225780859032e-05,
49
+ "loss": 1.6831,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.14,
54
+ "learning_rate": 4.7673620576205294e-05,
55
+ "loss": 1.6496,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.16,
60
+ "learning_rate": 4.7131541204339604e-05,
61
+ "loss": 1.5882,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.17,
66
+ "learning_rate": 4.646719126488686e-05,
67
+ "loss": 1.5674,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.19,
72
+ "learning_rate": 4.573943795068471e-05,
73
+ "loss": 1.5274,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.21,
78
+ "learning_rate": 4.4950430682006e-05,
79
+ "loss": 1.503,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.22,
84
+ "learning_rate": 4.410249979275041e-05,
85
+ "loss": 1.5161,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.24,
90
+ "learning_rate": 4.319814964780064e-05,
91
+ "loss": 1.4715,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.26,
96
+ "learning_rate": 4.2240051246377613e-05,
97
+ "loss": 1.4587,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.28,
102
+ "learning_rate": 4.123103433324129e-05,
103
+ "loss": 1.3959,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.29,
108
+ "learning_rate": 4.017407904103607e-05,
109
+ "loss": 1.3988,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 0.31,
114
+ "learning_rate": 3.907230708846552e-05,
115
+ "loss": 1.3834,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 0.33,
120
+ "learning_rate": 3.7928972560292554e-05,
121
+ "loss": 1.4369,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 0.35,
126
+ "learning_rate": 3.674745229639617e-05,
127
+ "loss": 1.4171,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 0.36,
132
+ "learning_rate": 3.553123591827093e-05,
133
+ "loss": 1.4079,
134
+ "step": 210
135
+ },
136
+ {
137
+ "epoch": 0.38,
138
+ "learning_rate": 3.428391552242576e-05,
139
+ "loss": 1.2868,
140
+ "step": 220
141
+ },
142
+ {
143
+ "epoch": 0.4,
144
+ "learning_rate": 3.300917507112261e-05,
145
+ "loss": 1.3193,
146
+ "step": 230
147
+ },
148
+ {
149
+ "epoch": 0.42,
150
+ "learning_rate": 3.171077951178964e-05,
151
+ "loss": 1.3231,
152
+ "step": 240
153
+ },
154
+ {
155
+ "epoch": 0.43,
156
+ "learning_rate": 3.039256365724447e-05,
157
+ "loss": 1.3896,
158
+ "step": 250
159
+ },
160
+ {
161
+ "epoch": 0.45,
162
+ "learning_rate": 2.905842085957007e-05,
163
+ "loss": 1.3857,
164
+ "step": 260
165
+ },
166
+ {
167
+ "epoch": 0.47,
168
+ "learning_rate": 2.7712291511094725e-05,
169
+ "loss": 1.3863,
170
+ "step": 270
171
+ },
172
+ {
173
+ "epoch": 0.48,
174
+ "learning_rate": 2.6358151406438674e-05,
175
+ "loss": 1.4821,
176
+ "step": 280
177
+ },
178
+ {
179
+ "epoch": 0.5,
180
+ "learning_rate": 2.5e-05,
181
+ "loss": 1.3522,
182
+ "step": 290
183
+ },
184
+ {
185
+ "epoch": 0.52,
186
+ "learning_rate": 2.3641848593561322e-05,
187
+ "loss": 1.312,
188
+ "step": 300
189
+ },
190
+ {
191
+ "epoch": 0.54,
192
+ "learning_rate": 2.228770848890528e-05,
193
+ "loss": 1.3254,
194
+ "step": 310
195
+ },
196
+ {
197
+ "epoch": 0.55,
198
+ "learning_rate": 2.0941579140429933e-05,
199
+ "loss": 1.3726,
200
+ "step": 320
201
+ },
202
+ {
203
+ "epoch": 0.57,
204
+ "learning_rate": 1.960743634275554e-05,
205
+ "loss": 1.2926,
206
+ "step": 330
207
+ },
208
+ {
209
+ "epoch": 0.59,
210
+ "learning_rate": 1.828922048821037e-05,
211
+ "loss": 1.3776,
212
+ "step": 340
213
+ },
214
+ {
215
+ "epoch": 0.61,
216
+ "learning_rate": 1.6990824928877393e-05,
217
+ "loss": 1.4351,
218
+ "step": 350
219
+ },
220
+ {
221
+ "epoch": 0.62,
222
+ "learning_rate": 1.5716084477574245e-05,
223
+ "loss": 1.3105,
224
+ "step": 360
225
+ },
226
+ {
227
+ "epoch": 0.64,
228
+ "learning_rate": 1.4468764081729063e-05,
229
+ "loss": 1.3345,
230
+ "step": 370
231
+ },
232
+ {
233
+ "epoch": 0.66,
234
+ "learning_rate": 1.3252547703603829e-05,
235
+ "loss": 1.3971,
236
+ "step": 380
237
+ },
238
+ {
239
+ "epoch": 0.67,
240
+ "learning_rate": 1.207102743970745e-05,
241
+ "loss": 1.2962,
242
+ "step": 390
243
+ },
244
+ {
245
+ "epoch": 0.69,
246
+ "learning_rate": 1.0927692911534476e-05,
247
+ "loss": 1.3572,
248
+ "step": 400
249
+ },
250
+ {
251
+ "epoch": 0.71,
252
+ "learning_rate": 9.825920958963936e-06,
253
+ "loss": 1.318,
254
+ "step": 410
255
+ },
256
+ {
257
+ "epoch": 0.73,
258
+ "learning_rate": 8.768965666758704e-06,
259
+ "loss": 1.3644,
260
+ "step": 420
261
+ },
262
+ {
263
+ "epoch": 0.74,
264
+ "learning_rate": 7.759948753622389e-06,
265
+ "loss": 1.4429,
266
+ "step": 430
267
+ },
268
+ {
269
+ "epoch": 0.76,
270
+ "learning_rate": 6.801850352199371e-06,
271
+ "loss": 1.3241,
272
+ "step": 440
273
+ },
274
+ {
275
+ "epoch": 0.78,
276
+ "learning_rate": 5.897500207249593e-06,
277
+ "loss": 1.3219,
278
+ "step": 450
279
+ },
280
+ {
281
+ "epoch": 0.8,
282
+ "learning_rate": 5.049569317994013e-06,
283
+ "loss": 1.2544,
284
+ "step": 460
285
+ },
286
+ {
287
+ "epoch": 0.81,
288
+ "learning_rate": 4.260562049315301e-06,
289
+ "loss": 1.4059,
290
+ "step": 470
291
+ },
292
+ {
293
+ "epoch": 0.83,
294
+ "learning_rate": 3.5328087351131495e-06,
295
+ "loss": 1.3633,
296
+ "step": 480
297
+ },
298
+ {
299
+ "epoch": 0.85,
300
+ "learning_rate": 2.8684587956604e-06,
301
+ "loss": 1.2363,
302
+ "step": 490
303
+ },
304
+ {
305
+ "epoch": 0.87,
306
+ "learning_rate": 2.2694743892876873e-06,
307
+ "loss": 1.3308,
308
+ "step": 500
309
+ },
310
+ {
311
+ "epoch": 0.88,
312
+ "learning_rate": 1.7376246171465188e-06,
313
+ "loss": 1.3525,
314
+ "step": 510
315
+ },
316
+ {
317
+ "epoch": 0.9,
318
+ "learning_rate": 1.2744802981669217e-06,
319
+ "loss": 1.3765,
320
+ "step": 520
321
+ },
322
+ {
323
+ "epoch": 0.92,
324
+ "learning_rate": 8.814093296418885e-07,
325
+ "loss": 1.3155,
326
+ "step": 530
327
+ },
328
+ {
329
+ "epoch": 0.93,
330
+ "learning_rate": 5.595726471410961e-07,
331
+ "loss": 1.3324,
332
+ "step": 540
333
+ },
334
+ {
335
+ "epoch": 0.95,
336
+ "learning_rate": 3.099207956863359e-07,
337
+ "loss": 1.3114,
338
+ "step": 550
339
+ },
340
+ {
341
+ "epoch": 0.97,
342
+ "learning_rate": 1.3319112231567344e-07,
343
+ "loss": 1.2908,
344
+ "step": 560
345
+ },
346
+ {
347
+ "epoch": 0.99,
348
+ "learning_rate": 2.990559832808659e-08,
349
+ "loss": 1.3837,
350
+ "step": 570
351
+ },
352
+ {
353
+ "epoch": 1.0,
354
+ "step": 578,
355
+ "total_flos": 8.80125790828626e+16,
356
+ "train_loss": 1.4581370320699618,
357
+ "train_runtime": 1932.4895,
358
+ "train_samples_per_second": 4.782,
359
+ "train_steps_per_second": 0.299
360
+ }
361
+ ],
362
+ "max_steps": 578,
363
+ "num_train_epochs": 1,
364
+ "total_flos": 8.80125790828626e+16,
365
+ "trial_name": null,
366
+ "trial_params": null
367
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74c87246be12325ce4c0cc9f9877e1132195d07606b2297b205efdaa6346e79f
3
+ size 3352
training_loss.png ADDED