tuanna08go
commited on
Training in progress, step 1, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
@@ -22,11 +22,11 @@
|
|
22 |
"target_modules": [
|
23 |
"k_proj",
|
24 |
"up_proj",
|
25 |
-
"gate_proj",
|
26 |
"down_proj",
|
27 |
-
"q_proj",
|
28 |
"v_proj",
|
29 |
-
"
|
|
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
22 |
"target_modules": [
|
23 |
"k_proj",
|
24 |
"up_proj",
|
|
|
25 |
"down_proj",
|
|
|
26 |
"v_proj",
|
27 |
+
"gate_proj",
|
28 |
+
"o_proj",
|
29 |
+
"q_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 27024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69645991c7cf506d5c30861569e6ed7d76b249f5689bfe534299d4c063f021da
|
3 |
size 27024
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 63974
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c925f8458671c13b3473bd084a612ed35e694984842649c8c2b9bb96f090a01
|
3 |
size 63974
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77d813df95ed5c5cb8c129d473a02cf923cf514e9f2baa1159356ec373c5aca4
|
3 |
size 14244
|
last-checkpoint/trainer_state.json
CHANGED
@@ -11,16 +11,16 @@
|
|
11 |
{
|
12 |
"epoch": 0.38095238095238093,
|
13 |
"eval_loss": 10.373360633850098,
|
14 |
-
"eval_runtime": 0.
|
15 |
-
"eval_samples_per_second":
|
16 |
-
"eval_steps_per_second":
|
17 |
"step": 1
|
18 |
}
|
19 |
],
|
20 |
"logging_steps": 10,
|
21 |
-
"max_steps":
|
22 |
"num_input_tokens_seen": 0,
|
23 |
-
"num_train_epochs":
|
24 |
"save_steps": 1,
|
25 |
"stateful_callbacks": {
|
26 |
"TrainerControl": {
|
@@ -29,7 +29,7 @@
|
|
29 |
"should_evaluate": false,
|
30 |
"should_log": false,
|
31 |
"should_save": true,
|
32 |
-
"should_training_stop":
|
33 |
},
|
34 |
"attributes": {}
|
35 |
}
|
|
|
11 |
{
|
12 |
"epoch": 0.38095238095238093,
|
13 |
"eval_loss": 10.373360633850098,
|
14 |
+
"eval_runtime": 0.0348,
|
15 |
+
"eval_samples_per_second": 517.209,
|
16 |
+
"eval_steps_per_second": 86.201,
|
17 |
"step": 1
|
18 |
}
|
19 |
],
|
20 |
"logging_steps": 10,
|
21 |
+
"max_steps": 3,
|
22 |
"num_input_tokens_seen": 0,
|
23 |
+
"num_train_epochs": 2,
|
24 |
"save_steps": 1,
|
25 |
"stateful_callbacks": {
|
26 |
"TrainerControl": {
|
|
|
29 |
"should_evaluate": false,
|
30 |
"should_log": false,
|
31 |
"should_save": true,
|
32 |
+
"should_training_stop": false
|
33 |
},
|
34 |
"attributes": {}
|
35 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6308be045fdc0e3ed396fe037bc4e24690208930c0d7ae981859e98692f767d6
|
3 |
size 6776
|