Training in progress, step 1
Browse files- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +43 -0
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -26,12 +26,12 @@
|
|
26 |
"revision": null,
|
27 |
"target_modules": [
|
28 |
"k_proj",
|
29 |
-
"v_proj",
|
30 |
-
"gate_proj",
|
31 |
"q_proj",
|
32 |
-
"
|
33 |
"o_proj",
|
34 |
-
"
|
|
|
|
|
35 |
],
|
36 |
"task_type": "CAUSAL_LM",
|
37 |
"trainable_token_indices": null,
|
|
|
26 |
"revision": null,
|
27 |
"target_modules": [
|
28 |
"k_proj",
|
|
|
|
|
29 |
"q_proj",
|
30 |
+
"v_proj",
|
31 |
"o_proj",
|
32 |
+
"gate_proj",
|
33 |
+
"up_proj",
|
34 |
+
"down_proj"
|
35 |
],
|
36 |
"task_type": "CAUSAL_LM",
|
37 |
"trainable_token_indices": null,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1342238560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c26bc9dcfcc7a127254d00318f15481103c6fd91e843b2b3b2138d3d92fa40f1
|
3 |
size 1342238560
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.6187007086617606,
|
5 |
+
"train_runtime": 1438.7543,
|
6 |
+
"train_samples": 100,
|
7 |
+
"train_samples_per_second": 0.07,
|
8 |
+
"train_steps_per_second": 0.005
|
9 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.6187007086617606,
|
5 |
+
"train_runtime": 1438.7543,
|
6 |
+
"train_samples": 100,
|
7 |
+
"train_samples_per_second": 0.07,
|
8 |
+
"train_steps_per_second": 0.005
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": null,
|
3 |
+
"best_metric": null,
|
4 |
+
"best_model_checkpoint": null,
|
5 |
+
"epoch": 1.0,
|
6 |
+
"eval_steps": 100,
|
7 |
+
"global_step": 7,
|
8 |
+
"is_hyper_param_search": false,
|
9 |
+
"is_local_process_zero": true,
|
10 |
+
"is_world_process_zero": true,
|
11 |
+
"log_history": [
|
12 |
+
{
|
13 |
+
"epoch": 1.0,
|
14 |
+
"step": 7,
|
15 |
+
"total_flos": 0.0,
|
16 |
+
"train_loss": 0.6187007086617606,
|
17 |
+
"train_runtime": 1438.7543,
|
18 |
+
"train_samples_per_second": 0.07,
|
19 |
+
"train_steps_per_second": 0.005
|
20 |
+
}
|
21 |
+
],
|
22 |
+
"logging_steps": 10,
|
23 |
+
"max_steps": 7,
|
24 |
+
"num_input_tokens_seen": 0,
|
25 |
+
"num_train_epochs": 1,
|
26 |
+
"save_steps": 100,
|
27 |
+
"stateful_callbacks": {
|
28 |
+
"TrainerControl": {
|
29 |
+
"args": {
|
30 |
+
"should_epoch_stop": false,
|
31 |
+
"should_evaluate": false,
|
32 |
+
"should_log": false,
|
33 |
+
"should_save": true,
|
34 |
+
"should_training_stop": true
|
35 |
+
},
|
36 |
+
"attributes": {}
|
37 |
+
}
|
38 |
+
},
|
39 |
+
"total_flos": 0.0,
|
40 |
+
"train_batch_size": 4,
|
41 |
+
"trial_name": null,
|
42 |
+
"trial_params": null
|
43 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6737
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7203598c6c6f23cbdf67e730593cec68fe4d419ef781c6acddfae74008f25a78
|
3 |
size 6737
|