Training completed
Browse files- README.md +1 -1
- all_results.json +5 -5
- train_results.json +5 -5
- trainer_state.json +14 -7
README.md
CHANGED
@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
|
|
46 |
- total_train_batch_size: 160
|
47 |
- total_eval_batch_size: 64
|
48 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
49 |
-
- lr_scheduler_type:
|
50 |
- lr_scheduler_warmup_ratio: 0.03
|
51 |
- training_steps: 10
|
52 |
|
|
|
46 |
- total_train_batch_size: 160
|
47 |
- total_eval_batch_size: 64
|
48 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
49 |
+
- lr_scheduler_type: linear
|
50 |
- lr_scheduler_warmup_ratio: 0.03
|
51 |
- training_steps: 10
|
52 |
|
all_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 0.0182648401826484,
|
3 |
-
"total_flos":
|
4 |
-
"train_loss":
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 0.0182648401826484,
|
3 |
+
"total_flos": 1.394108846267433e+17,
|
4 |
+
"train_loss": 5.07354736328125,
|
5 |
+
"train_runtime": 154.4303,
|
6 |
+
"train_samples_per_second": 10.361,
|
7 |
+
"train_steps_per_second": 0.065
|
8 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 0.0182648401826484,
|
3 |
-
"total_flos":
|
4 |
-
"train_loss":
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 0.0182648401826484,
|
3 |
+
"total_flos": 1.394108846267433e+17,
|
4 |
+
"train_loss": 5.07354736328125,
|
5 |
+
"train_runtime": 154.4303,
|
6 |
+
"train_samples_per_second": 10.361,
|
7 |
+
"train_steps_per_second": 0.065
|
8 |
}
|
trainer_state.json
CHANGED
@@ -9,17 +9,24 @@
|
|
9 |
"is_local_process_zero": true,
|
10 |
"is_world_process_zero": true,
|
11 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
{
|
13 |
"epoch": 0.0182648401826484,
|
14 |
"step": 10,
|
15 |
-
"total_flos":
|
16 |
-
"train_loss":
|
17 |
-
"train_runtime":
|
18 |
-
"train_samples_per_second":
|
19 |
-
"train_steps_per_second": 0.
|
20 |
}
|
21 |
],
|
22 |
-
"logging_steps":
|
23 |
"max_steps": 10,
|
24 |
"num_input_tokens_seen": 0,
|
25 |
"num_train_epochs": 1,
|
@@ -36,7 +43,7 @@
|
|
36 |
"attributes": {}
|
37 |
}
|
38 |
},
|
39 |
-
"total_flos":
|
40 |
"train_batch_size": 2,
|
41 |
"trial_name": null,
|
42 |
"trial_params": null
|
|
|
9 |
"is_local_process_zero": true,
|
10 |
"is_world_process_zero": true,
|
11 |
"log_history": [
|
12 |
+
{
|
13 |
+
"epoch": 0.0182648401826484,
|
14 |
+
"grad_norm": 0.36667829751968384,
|
15 |
+
"learning_rate": 0.0001,
|
16 |
+
"loss": 5.0735,
|
17 |
+
"step": 10
|
18 |
+
},
|
19 |
{
|
20 |
"epoch": 0.0182648401826484,
|
21 |
"step": 10,
|
22 |
+
"total_flos": 1.394108846267433e+17,
|
23 |
+
"train_loss": 5.07354736328125,
|
24 |
+
"train_runtime": 154.4303,
|
25 |
+
"train_samples_per_second": 10.361,
|
26 |
+
"train_steps_per_second": 0.065
|
27 |
}
|
28 |
],
|
29 |
+
"logging_steps": 10,
|
30 |
"max_steps": 10,
|
31 |
"num_input_tokens_seen": 0,
|
32 |
"num_train_epochs": 1,
|
|
|
43 |
"attributes": {}
|
44 |
}
|
45 |
},
|
46 |
+
"total_flos": 1.394108846267433e+17,
|
47 |
"train_batch_size": 2,
|
48 |
"trial_name": null,
|
49 |
"trial_params": null
|