Model save
Browse files- all_results.json +8 -0
- model.safetensors +1 -1
- runs/Mar21_23-39-14_X5C922065N/events.out.tfevents.1711060766.X5C922065N.86888.15 +3 -0
- train_results.json +8 -0
- trainer_state.json +37 -0
- training_args.bin +1 -1
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"total_flos": 9299872197181440.0,
|
4 |
+
"train_loss": 2.19787335395813,
|
5 |
+
"train_runtime": 9.6458,
|
6 |
+
"train_samples_per_second": 12.441,
|
7 |
+
"train_steps_per_second": 1.659
|
8 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343254736
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91a5a93286280abbc7080b1d52c268a5f4aa7d839be30fbfe11d56c82f4addbf
|
3 |
size 343254736
|
runs/Mar21_23-39-14_X5C922065N/events.out.tfevents.1711060766.X5C922065N.86888.15
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdb8f14f571fce39e5deb3ae03537cb13c053c9abc37157cf823400535d3225a
|
3 |
+
size 6018
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"total_flos": 9299872197181440.0,
|
4 |
+
"train_loss": 2.19787335395813,
|
5 |
+
"train_runtime": 9.6458,
|
6 |
+
"train_samples_per_second": 12.441,
|
7 |
+
"train_steps_per_second": 1.659
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 1000,
|
6 |
+
"global_step": 16,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 2.5,
|
13 |
+
"grad_norm": 2.5156421661376953,
|
14 |
+
"learning_rate": 1.8750000000000002e-05,
|
15 |
+
"loss": 2.3138,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 4.0,
|
20 |
+
"step": 16,
|
21 |
+
"total_flos": 9299872197181440.0,
|
22 |
+
"train_loss": 2.19787335395813,
|
23 |
+
"train_runtime": 9.6458,
|
24 |
+
"train_samples_per_second": 12.441,
|
25 |
+
"train_steps_per_second": 1.659
|
26 |
+
}
|
27 |
+
],
|
28 |
+
"logging_steps": 10,
|
29 |
+
"max_steps": 16,
|
30 |
+
"num_input_tokens_seen": 0,
|
31 |
+
"num_train_epochs": 4,
|
32 |
+
"save_steps": 1000,
|
33 |
+
"total_flos": 9299872197181440.0,
|
34 |
+
"train_batch_size": 8,
|
35 |
+
"trial_name": null,
|
36 |
+
"trial_params": null
|
37 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b53471da88ac891f6cf1d8d672d15ebb919a7297ac9d87622e592033071fef61
|
3 |
size 4920
|