Training in progress, epoch 3, checkpoint
Browse files
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d901799237c1b0fc406667280e8b40ceab6ca131806bb9e1c8b4b50ff1d2a491
|
3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d48782f3748f5325ae4a6a95bda94865d59ccf3bbef02a1ec6555ceeff70fa42
|
3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71b95f8b75b55684da4f6ea49e34202c4c204d83b8d1764ce81ef74007f4d50a
|
3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15a4fbbf671c57b999de663c974b296eb08bcae9d842c84922d6ec497b9fef72
|
3 |
size 15024
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint": "./models/rootflo/fauna-v3.6/checkpoint-
|
4 |
"epoch": 3.9845559845559846,
|
5 |
"eval_steps": 100,
|
6 |
"global_step": 516,
|
@@ -69,6 +69,15 @@
|
|
69 |
"learning_rate": 8.229706450227802e-09,
|
70 |
"loss": 0.2285,
|
71 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
72 |
}
|
73 |
],
|
74 |
"logging_steps": 100,
|
@@ -83,7 +92,7 @@
|
|
83 |
"early_stopping_threshold": 1
|
84 |
},
|
85 |
"attributes": {
|
86 |
-
"early_stopping_patience_counter":
|
87 |
}
|
88 |
},
|
89 |
"TrainerControl": {
|
|
|
1 |
{
|
2 |
+
"best_metric": 19.603507093484392,
|
3 |
+
"best_model_checkpoint": "./models/rootflo/fauna-v3.6/checkpoint-516",
|
4 |
"epoch": 3.9845559845559846,
|
5 |
"eval_steps": 100,
|
6 |
"global_step": 516,
|
|
|
69 |
"learning_rate": 8.229706450227802e-09,
|
70 |
"loss": 0.2285,
|
71 |
"step": 500
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 3.9845559845559846,
|
75 |
+
"eval_bleu": 19.603507093484392,
|
76 |
+
"eval_loss": 0.11292669177055359,
|
77 |
+
"eval_runtime": 2938.0533,
|
78 |
+
"eval_samples_per_second": 1.649,
|
79 |
+
"eval_steps_per_second": 0.004,
|
80 |
+
"step": 516
|
81 |
}
|
82 |
],
|
83 |
"logging_steps": 100,
|
|
|
92 |
"early_stopping_threshold": 1
|
93 |
},
|
94 |
"attributes": {
|
95 |
+
"early_stopping_patience_counter": 0
|
96 |
}
|
97 |
},
|
98 |
"TrainerControl": {
|