Hugging Face's logo

OscarXZQ
/
logical_deduction_three_objects

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
Community
OscarXZQ commited on
Commit
ee4e39a
·
verified ·
1 Parent(s): 099ef20

OscarXZQ/bbh-lora-logical_deduction_three_objects

Browse files
Files changed (3) hide show
  1. all_results.json +5 -5
  2. train_results.json +5 -5
  3. trainer_state.json +9 -9
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 10.0,
3
- "total_flos": 122531399884800.0,
4
- "train_loss": 0.3025847053527832,
5
- "train_runtime": 63.1156,
6
- "train_samples_per_second": 3.169,
7
- "train_steps_per_second": 3.169
8
  }
 
1
  {
2
  "epoch": 10.0,
3
+ "total_flos": 152292261150720.0,
4
+ "train_loss": 0.3122243957519531,
5
+ "train_runtime": 76.5728,
6
+ "train_samples_per_second": 3.265,
7
+ "train_steps_per_second": 3.265
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 10.0,
3
- "total_flos": 122531399884800.0,
4
- "train_loss": 0.3025847053527832,
5
- "train_runtime": 63.1156,
6
- "train_samples_per_second": 3.169,
7
- "train_steps_per_second": 3.169
8
  }
 
1
  {
2
  "epoch": 10.0,
3
+ "total_flos": 152292261150720.0,
4
+ "train_loss": 0.3122243957519531,
5
+ "train_runtime": 76.5728,
6
+ "train_samples_per_second": 3.265,
7
+ "train_steps_per_second": 3.265
8
  }
trainer_state.json CHANGED
@@ -3,23 +3,23 @@
3
  "best_model_checkpoint": null,
4
  "epoch": 10.0,
5
  "eval_steps": 500,
6
- "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 10.0,
13
- "step": 200,
14
- "total_flos": 122531399884800.0,
15
- "train_loss": 0.3025847053527832,
16
- "train_runtime": 63.1156,
17
- "train_samples_per_second": 3.169,
18
- "train_steps_per_second": 3.169
19
  }
20
  ],
21
  "logging_steps": 500,
22
- "max_steps": 200,
23
  "num_input_tokens_seen": 0,
24
  "num_train_epochs": 10,
25
  "save_steps": 500,
@@ -35,7 +35,7 @@
35
  "attributes": {}
36
  }
37
  },
38
- "total_flos": 122531399884800.0,
39
  "train_batch_size": 1,
40
  "trial_name": null,
41
  "trial_params": null
 
3
  "best_model_checkpoint": null,
4
  "epoch": 10.0,
5
  "eval_steps": 500,
6
+ "global_step": 250,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 10.0,
13
+ "step": 250,
14
+ "total_flos": 152292261150720.0,
15
+ "train_loss": 0.3122243957519531,
16
+ "train_runtime": 76.5728,
17
+ "train_samples_per_second": 3.265,
18
+ "train_steps_per_second": 3.265
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 250,
23
  "num_input_tokens_seen": 0,
24
  "num_train_epochs": 10,
25
  "save_steps": 500,
 
35
  "attributes": {}
36
  }
37
  },
38
+ "total_flos": 152292261150720.0,
39
  "train_batch_size": 1,
40
  "trial_name": null,
41
  "trial_params": null