Training in progress, epoch 2, checkpoint
Browse files
checkpoint-3056/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557116312
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b68e41325dbdb1437b0cba550afc81b90e36838c1043f61962d5eded12bdaac6
|
3 |
size 557116312
|
checkpoint-3056/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1113991930
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35a3bac36de4f7daf69d45a6a1559474ca3a6d2bbf09bff99f6344ec5339c5cc
|
3 |
size 1113991930
|
checkpoint-3056/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa9d1335bcf626664b9856d1d0008b505cd442c2fc0ed9f9e4da5747018686cf
|
3 |
size 1064
|
checkpoint-3056/trainer_state.json
CHANGED
@@ -42,41 +42,41 @@
|
|
42 |
},
|
43 |
{
|
44 |
"epoch": 1.3089005235602094,
|
45 |
-
"grad_norm": 3.
|
46 |
-
"learning_rate":
|
47 |
-
"loss": 0.
|
48 |
"step": 2000
|
49 |
},
|
50 |
{
|
51 |
"epoch": 1.6361256544502618,
|
52 |
-
"grad_norm":
|
53 |
-
"learning_rate":
|
54 |
-
"loss": 0.
|
55 |
"step": 2500
|
56 |
},
|
57 |
{
|
58 |
"epoch": 1.9633507853403143,
|
59 |
-
"grad_norm":
|
60 |
-
"learning_rate":
|
61 |
-
"loss": 0.
|
62 |
"step": 3000
|
63 |
},
|
64 |
{
|
65 |
"epoch": 2.0,
|
66 |
-
"eval_loss": 5.
|
67 |
-
"eval_rouge1": 25.
|
68 |
-
"eval_rouge2": 9.
|
69 |
-
"eval_rougeL": 21.
|
70 |
-
"eval_runtime":
|
71 |
-
"eval_samples_per_second": 5.
|
72 |
-
"eval_steps_per_second": 0.
|
73 |
"step": 3056
|
74 |
}
|
75 |
],
|
76 |
"logging_steps": 500,
|
77 |
-
"max_steps":
|
78 |
"num_input_tokens_seen": 0,
|
79 |
-
"num_train_epochs":
|
80 |
"save_steps": 500,
|
81 |
"stateful_callbacks": {
|
82 |
"TrainerControl": {
|
|
|
42 |
},
|
43 |
{
|
44 |
"epoch": 1.3089005235602094,
|
45 |
+
"grad_norm": 3.4732136726379395,
|
46 |
+
"learning_rate": 4.3455497382198955e-05,
|
47 |
+
"loss": 0.0456,
|
48 |
"step": 2000
|
49 |
},
|
50 |
{
|
51 |
"epoch": 1.6361256544502618,
|
52 |
+
"grad_norm": 2.2575156688690186,
|
53 |
+
"learning_rate": 4.181937172774869e-05,
|
54 |
+
"loss": 0.0619,
|
55 |
"step": 2500
|
56 |
},
|
57 |
{
|
58 |
"epoch": 1.9633507853403143,
|
59 |
+
"grad_norm": 6.030032157897949,
|
60 |
+
"learning_rate": 4.018324607329843e-05,
|
61 |
+
"loss": 0.0993,
|
62 |
"step": 3000
|
63 |
},
|
64 |
{
|
65 |
"epoch": 2.0,
|
66 |
+
"eval_loss": 5.542174339294434,
|
67 |
+
"eval_rouge1": 25.0744,
|
68 |
+
"eval_rouge2": 9.8534,
|
69 |
+
"eval_rougeL": 21.6992,
|
70 |
+
"eval_runtime": 411.9676,
|
71 |
+
"eval_samples_per_second": 5.328,
|
72 |
+
"eval_steps_per_second": 0.534,
|
73 |
"step": 3056
|
74 |
}
|
75 |
],
|
76 |
"logging_steps": 500,
|
77 |
+
"max_steps": 15280,
|
78 |
"num_input_tokens_seen": 0,
|
79 |
+
"num_train_epochs": 10,
|
80 |
"save_steps": 500,
|
81 |
"stateful_callbacks": {
|
82 |
"TrainerControl": {
|
checkpoint-3056/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6904
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a35dd57590090f24ebba9a087e2c3d94297cd357e1c5960144536e9514488b6a
|
3 |
size 6904
|