avsolatorio
commited on
Commit
•
439ad72
1
Parent(s):
b91e86d
Training in progress, step 2000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 567860028
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c8cc9a2f725c6934baa9d56c720425e0384071c22db96c2194527e1d922dbef
|
3 |
size 567860028
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1135783354
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68a0778a7ad31d64fe618dd6509a81ae2c6668b8e9aec7b97082b2e843f25005
|
3 |
size 1135783354
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69797e619b7f76fc3c65d1346887cd92f6a036b8a8ff866da9ca1a335d274133
|
3 |
size 14244
|
last-checkpoint/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:de10e3ea9e9f590bd00b7f01055683747e52076430fd0eff98a7f3083d4ae0fc
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "doc-topic-model_eval-01_train-02/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -33,6 +33,32 @@
|
|
33 |
"eval_samples_per_second": 677.827,
|
34 |
"eval_steps_per_second": 2.675,
|
35 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
}
|
37 |
],
|
38 |
"logging_steps": 500,
|
@@ -61,7 +87,7 @@
|
|
61 |
"attributes": {}
|
62 |
}
|
63 |
},
|
64 |
-
"total_flos":
|
65 |
"train_batch_size": 4,
|
66 |
"trial_name": null,
|
67 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.06878085434436798,
|
3 |
+
"best_model_checkpoint": "doc-topic-model_eval-01_train-02/checkpoint-2000",
|
4 |
+
"epoch": 0.9861932938856016,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 2000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
33 |
"eval_samples_per_second": 677.827,
|
34 |
"eval_steps_per_second": 2.675,
|
35 |
"step": 1000
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 0.7396449704142012,
|
39 |
+
"grad_norm": 0.385586678981781,
|
40 |
+
"learning_rate": 1.9852071005917162e-05,
|
41 |
+
"loss": 0.0863,
|
42 |
+
"step": 1500
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 0.9861932938856016,
|
46 |
+
"grad_norm": 0.3922920525074005,
|
47 |
+
"learning_rate": 1.980276134122288e-05,
|
48 |
+
"loss": 0.0769,
|
49 |
+
"step": 2000
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 0.9861932938856016,
|
53 |
+
"eval_accuracy": 0.9813966013294216,
|
54 |
+
"eval_f1": 0.0015213753232922562,
|
55 |
+
"eval_loss": 0.06878085434436798,
|
56 |
+
"eval_precision": 0.9090909090909091,
|
57 |
+
"eval_recall": 0.0007613247049866769,
|
58 |
+
"eval_runtime": 14.1244,
|
59 |
+
"eval_samples_per_second": 574.184,
|
60 |
+
"eval_steps_per_second": 2.266,
|
61 |
+
"step": 2000
|
62 |
}
|
63 |
],
|
64 |
"logging_steps": 500,
|
|
|
87 |
"attributes": {}
|
88 |
}
|
89 |
},
|
90 |
+
"total_flos": 45150252586560.0,
|
91 |
"train_batch_size": 4,
|
92 |
"trial_name": null,
|
93 |
"trial_params": null
|