Training in progress, step 2500, checkpoint
Browse files
checkpoint-2500/config.json
CHANGED
@@ -16,7 +16,7 @@
|
|
16 |
"intermediate_size": 3072,
|
17 |
"layer_norm_eps": 1e-12,
|
18 |
"max_blocks": 200,
|
19 |
-
"max_position_embeddings":
|
20 |
"max_relative_position_embeddings": 8,
|
21 |
"model_type": "longelm",
|
22 |
"node_size": 1,
|
|
|
16 |
"intermediate_size": 3072,
|
17 |
"layer_norm_eps": 1e-12,
|
18 |
"max_blocks": 200,
|
19 |
+
"max_position_embeddings": 1805,
|
20 |
"max_relative_position_embeddings": 8,
|
21 |
"model_type": "longelm",
|
22 |
"node_size": 1,
|
checkpoint-2500/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c7ca46d7779ff3d1da496e7d5fe14362ea418f448336127babc31395fcd8e9b
|
3 |
+
size 1010431994
|
checkpoint-2500/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e6e5bd25802b059a9ec66a75fd07e39039b0c74b36c5121b4d9a3396b886932
|
3 |
+
size 505200682
|
checkpoint-2500/trainer_state.json
CHANGED
@@ -9,43 +9,43 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"ep_loss": 4.
|
13 |
"epoch": 0.04,
|
14 |
"learning_rate": 2.5e-05,
|
15 |
-
"loss": 11.
|
16 |
-
"mlm_loss": 6.
|
17 |
"step": 500
|
18 |
},
|
19 |
{
|
20 |
-
"ep_loss": 0.
|
21 |
"epoch": 0.08,
|
22 |
"learning_rate": 5e-05,
|
23 |
-
"loss":
|
24 |
-
"mlm_loss": 2.
|
25 |
"step": 1000
|
26 |
},
|
27 |
{
|
28 |
-
"ep_loss": 0.
|
29 |
"epoch": 0.12,
|
30 |
"learning_rate": 7.5e-05,
|
31 |
-
"loss": 2.
|
32 |
-
"mlm_loss": 1.
|
33 |
"step": 1500
|
34 |
},
|
35 |
{
|
36 |
-
"ep_loss": 0.
|
37 |
"epoch": 0.15,
|
38 |
"learning_rate": 0.0001,
|
39 |
-
"loss": 1.
|
40 |
-
"mlm_loss": 1.
|
41 |
"step": 2000
|
42 |
},
|
43 |
{
|
44 |
-
"ep_loss": 0.
|
45 |
"epoch": 0.19,
|
46 |
"learning_rate": 0.00012495,
|
47 |
-
"loss": 1.
|
48 |
-
"mlm_loss": 1.
|
49 |
"step": 2500
|
50 |
}
|
51 |
],
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"ep_loss": 4.4238,
|
13 |
"epoch": 0.04,
|
14 |
"learning_rate": 2.5e-05,
|
15 |
+
"loss": 11.1467,
|
16 |
+
"mlm_loss": 6.7229,
|
17 |
"step": 500
|
18 |
},
|
19 |
{
|
20 |
+
"ep_loss": 0.4305,
|
21 |
"epoch": 0.08,
|
22 |
"learning_rate": 5e-05,
|
23 |
+
"loss": 2.9841,
|
24 |
+
"mlm_loss": 2.5537,
|
25 |
"step": 1000
|
26 |
},
|
27 |
{
|
28 |
+
"ep_loss": 0.3724,
|
29 |
"epoch": 0.12,
|
30 |
"learning_rate": 7.5e-05,
|
31 |
+
"loss": 2.2371,
|
32 |
+
"mlm_loss": 1.8647,
|
33 |
"step": 1500
|
34 |
},
|
35 |
{
|
36 |
+
"ep_loss": 0.364,
|
37 |
"epoch": 0.15,
|
38 |
"learning_rate": 0.0001,
|
39 |
+
"loss": 1.8477,
|
40 |
+
"mlm_loss": 1.4837,
|
41 |
"step": 2000
|
42 |
},
|
43 |
{
|
44 |
+
"ep_loss": 0.3678,
|
45 |
"epoch": 0.19,
|
46 |
"learning_rate": 0.00012495,
|
47 |
+
"loss": 1.5215,
|
48 |
+
"mlm_loss": 1.1538,
|
49 |
"step": 2500
|
50 |
}
|
51 |
],
|
checkpoint-2500/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b26e03be70ebe5d40a81a81be94421c0578a9d8742b065bc029501df48632957
|
3 |
size 4664
|