Training in progress, epoch 1
Browse files- adapter_config.json +1 -1
- adapter_model.safetensors +1 -1
- all_results.json +3 -3
- runs/Dec10_16-11-47_uclaml03.cs.ucla.edu/events.out.tfevents.1702253628.uclaml03.cs.ucla.edu.2936686.2 +3 -0
- runs/Dec10_16-14-13_uclaml03.cs.ucla.edu/events.out.tfevents.1702253720.uclaml03.cs.ucla.edu.2937386.0 +3 -0
- train_results.json +3 -3
- trainer_state.json +6 -6
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -16,9 +16,9 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"o_proj",
|
20 |
"v_proj",
|
21 |
"q_proj",
|
|
|
22 |
"k_proj"
|
23 |
],
|
24 |
"task_type": "CAUSAL_LM"
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"v_proj",
|
20 |
"q_proj",
|
21 |
+
"o_proj",
|
22 |
"k_proj"
|
23 |
],
|
24 |
"task_type": "CAUSAL_LM"
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 218138576
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c4851d0fda021876b9eb5ecbd6ec0d108d643bb4b81a517a68af72134d8b407
|
3 |
size 218138576
|
all_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"train_loss": 0.3465735912322998,
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 61966,
|
6 |
-
"train_samples_per_second": 0.
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"train_loss": 0.3465735912322998,
|
4 |
+
"train_runtime": 16.7146,
|
5 |
"train_samples": 61966,
|
6 |
+
"train_samples_per_second": 0.598,
|
7 |
+
"train_steps_per_second": 0.06
|
8 |
}
|
runs/Dec10_16-11-47_uclaml03.cs.ucla.edu/events.out.tfevents.1702253628.uclaml03.cs.ucla.edu.2936686.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:220c31979d0580f5ca59ef27307ec3ad72cbf69d58def2460a3f5c1d1635af9a
|
3 |
+
size 4391
|
runs/Dec10_16-14-13_uclaml03.cs.ucla.edu/events.out.tfevents.1702253720.uclaml03.cs.ucla.edu.2937386.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca529da1d1f17dff2ac746e5e5119fcf427fae950f22c4e1502b457c10e778d3
|
3 |
+
size 6088
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"train_loss": 0.3465735912322998,
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 61966,
|
6 |
-
"train_samples_per_second": 0.
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"train_loss": 0.3465735912322998,
|
4 |
+
"train_runtime": 16.7146,
|
5 |
"train_samples": 61966,
|
6 |
+
"train_samples_per_second": 0.598,
|
7 |
+
"train_steps_per_second": 0.06
|
8 |
}
|
trainer_state.json
CHANGED
@@ -33,9 +33,9 @@
|
|
33 |
"eval_rewards/chosen": 0.0,
|
34 |
"eval_rewards/margins": 0.0,
|
35 |
"eval_rewards/rejected": 0.0,
|
36 |
-
"eval_runtime": 5.
|
37 |
-
"eval_samples_per_second": 1.
|
38 |
-
"eval_steps_per_second": 0.
|
39 |
"step": 1
|
40 |
},
|
41 |
{
|
@@ -43,9 +43,9 @@
|
|
43 |
"step": 1,
|
44 |
"total_flos": 0.0,
|
45 |
"train_loss": 0.3465735912322998,
|
46 |
-
"train_runtime":
|
47 |
-
"train_samples_per_second": 0.
|
48 |
-
"train_steps_per_second": 0.
|
49 |
}
|
50 |
],
|
51 |
"logging_steps": 10,
|
|
|
33 |
"eval_rewards/chosen": 0.0,
|
34 |
"eval_rewards/margins": 0.0,
|
35 |
"eval_rewards/rejected": 0.0,
|
36 |
+
"eval_runtime": 5.0795,
|
37 |
+
"eval_samples_per_second": 1.969,
|
38 |
+
"eval_steps_per_second": 0.394,
|
39 |
"step": 1
|
40 |
},
|
41 |
{
|
|
|
43 |
"step": 1,
|
44 |
"total_flos": 0.0,
|
45 |
"train_loss": 0.3465735912322998,
|
46 |
+
"train_runtime": 16.7146,
|
47 |
+
"train_samples_per_second": 0.598,
|
48 |
+
"train_steps_per_second": 0.06
|
49 |
}
|
50 |
],
|
51 |
"logging_steps": 10,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b0aa5ec44479b8e7b8213598ab5cc2d816e5d7bc3932498e923623c2409faa9
|
3 |
size 4728
|