Training in progress, step 50, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"gate_proj",
|
24 |
"v_proj",
|
25 |
"o_proj",
|
26 |
-
"down_proj",
|
27 |
-
"k_proj",
|
28 |
"up_proj",
|
29 |
-
"
|
|
|
|
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"v_proj",
|
24 |
"o_proj",
|
|
|
|
|
25 |
"up_proj",
|
26 |
+
"k_proj",
|
27 |
+
"q_proj",
|
28 |
+
"down_proj",
|
29 |
+
"gate_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
last-checkpoint/trainer_state.json
CHANGED
@@ -18,9 +18,9 @@
|
|
18 |
{
|
19 |
"epoch": 0.0003207955730210923,
|
20 |
"eval_loss": NaN,
|
21 |
-
"eval_runtime": 4.
|
22 |
-
"eval_samples_per_second": 12.
|
23 |
-
"eval_steps_per_second": 1.
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
@@ -194,9 +194,9 @@
|
|
194 |
{
|
195 |
"epoch": 0.008019889325527307,
|
196 |
"eval_loss": NaN,
|
197 |
-
"eval_runtime": 3.
|
198 |
-
"eval_samples_per_second": 13.
|
199 |
-
"eval_steps_per_second": 1.
|
200 |
"step": 25
|
201 |
},
|
202 |
{
|
@@ -377,8 +377,8 @@
|
|
377 |
{
|
378 |
"epoch": 0.016039778651054614,
|
379 |
"eval_loss": NaN,
|
380 |
-
"eval_runtime": 3.
|
381 |
-
"eval_samples_per_second": 13.
|
382 |
"eval_steps_per_second": 1.91,
|
383 |
"step": 50
|
384 |
}
|
|
|
18 |
{
|
19 |
"epoch": 0.0003207955730210923,
|
20 |
"eval_loss": NaN,
|
21 |
+
"eval_runtime": 4.1599,
|
22 |
+
"eval_samples_per_second": 12.019,
|
23 |
+
"eval_steps_per_second": 1.683,
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
|
|
194 |
{
|
195 |
"epoch": 0.008019889325527307,
|
196 |
"eval_loss": NaN,
|
197 |
+
"eval_runtime": 3.6585,
|
198 |
+
"eval_samples_per_second": 13.667,
|
199 |
+
"eval_steps_per_second": 1.913,
|
200 |
"step": 25
|
201 |
},
|
202 |
{
|
|
|
377 |
{
|
378 |
"epoch": 0.016039778651054614,
|
379 |
"eval_loss": NaN,
|
380 |
+
"eval_runtime": 3.665,
|
381 |
+
"eval_samples_per_second": 13.643,
|
382 |
"eval_steps_per_second": 1.91,
|
383 |
"step": 50
|
384 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6840
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d21707a2ebc8a7854b0b86eea4a7eff059aa9ac1ce3e4a51943992c444afbe2f
|
3 |
size 6840
|