Hugging Face's logo

OscarXZQ
/
logical_deduction_three_objects

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
Community
OscarXZQ commited on
Commit
4b2c1a2
·
verified ·
1 Parent(s): cca3abc

OscarXZQ/bbh-lora-logical_deduction_three_objects-5e-05

Browse files
Files changed (3) hide show
  1. all_results.json +6 -6
  2. train_results.json +6 -6
  3. trainer_state.json +12 -12
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 10.0,
3
- "total_flos": 122214313082880.0,
4
- "train_loss": 0.36174999237060546,
5
- "train_runtime": 67.0978,
6
- "train_samples_per_second": 2.981,
7
- "train_steps_per_second": 2.981
8
  }
 
1
  {
2
+ "epoch": 5.0,
3
+ "total_flos": 61107156541440.0,
4
+ "train_loss": 0.5131120300292968,
5
+ "train_runtime": 37.8566,
6
+ "train_samples_per_second": 2.642,
7
+ "train_steps_per_second": 2.642
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 10.0,
3
- "total_flos": 122214313082880.0,
4
- "train_loss": 0.36174999237060546,
5
- "train_runtime": 67.0978,
6
- "train_samples_per_second": 2.981,
7
- "train_steps_per_second": 2.981
8
  }
 
1
  {
2
+ "epoch": 5.0,
3
+ "total_flos": 61107156541440.0,
4
+ "train_loss": 0.5131120300292968,
5
+ "train_runtime": 37.8566,
6
+ "train_samples_per_second": 2.642,
7
+ "train_steps_per_second": 2.642
8
  }
trainer_state.json CHANGED
@@ -1,27 +1,27 @@
1
  {
2
  "best_metric": null,
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": 122214313082880.0,
15
- "train_loss": 0.36174999237060546,
16
- "train_runtime": 67.0978,
17
- "train_samples_per_second": 2.981,
18
- "train_steps_per_second": 2.981
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,
26
  "stateful_callbacks": {
27
  "TrainerControl": {
@@ -35,7 +35,7 @@
35
  "attributes": {}
36
  }
37
  },
38
- "total_flos": 122214313082880.0,
39
  "train_batch_size": 1,
40
  "trial_name": null,
41
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
  "eval_steps": 500,
6
+ "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 5.0,
13
+ "step": 100,
14
+ "total_flos": 61107156541440.0,
15
+ "train_loss": 0.5131120300292968,
16
+ "train_runtime": 37.8566,
17
+ "train_samples_per_second": 2.642,
18
+ "train_steps_per_second": 2.642
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 100,
23
  "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 5,
25
  "save_steps": 500,
26
  "stateful_callbacks": {
27
  "TrainerControl": {
 
35
  "attributes": {}
36
  }
37
  },
38
+ "total_flos": 61107156541440.0,
39
  "train_batch_size": 1,
40
  "trial_name": null,
41
  "trial_params": null