avsolatorio
commited on
Commit
•
3bb0618
1
Parent(s):
1c8bd74
Training in progress, step 3000, 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 sha256:99d5c8a2e38dfc0e5d4e75372f346c6878310508558528f68c672cfb4ff543f9
|
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 sha256:0f5870303be3894bc74331f45deb4a92f7908a098d997e2e3efb25a72ef9e068
|
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:e64b28e054193eaeff0d625fef705a5122942e1a18af84585e7031e05f4d367e
|
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:bf1f1d71c2538f4e6c4311b28c8abb9dab5ee4ce70ffee85f9b380b76dcf0420
|
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":
|
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,
|
@@ -59,6 +59,32 @@
|
|
59 |
"eval_samples_per_second": 574.184,
|
60 |
"eval_steps_per_second": 2.266,
|
61 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
62 |
}
|
63 |
],
|
64 |
"logging_steps": 500,
|
@@ -87,7 +113,7 @@
|
|
87 |
"attributes": {}
|
88 |
}
|
89 |
},
|
90 |
-
"total_flos":
|
91 |
"train_batch_size": 4,
|
92 |
"trial_name": null,
|
93 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.05613817274570465,
|
3 |
+
"best_model_checkpoint": "doc-topic-model_eval-01_train-02/checkpoint-3000",
|
4 |
+
"epoch": 1.4792899408284024,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 3000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
59 |
"eval_samples_per_second": 574.184,
|
60 |
"eval_steps_per_second": 2.266,
|
61 |
"step": 2000
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 1.232741617357002,
|
65 |
+
"grad_norm": 0.40515828132629395,
|
66 |
+
"learning_rate": 1.9753451676528602e-05,
|
67 |
+
"loss": 0.0677,
|
68 |
+
"step": 2500
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 1.4792899408284024,
|
72 |
+
"grad_norm": 0.3946343958377838,
|
73 |
+
"learning_rate": 1.9704142011834322e-05,
|
74 |
+
"loss": 0.0607,
|
75 |
+
"step": 3000
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 1.4792899408284024,
|
79 |
+
"eval_accuracy": 0.982203041512536,
|
80 |
+
"eval_f1": 0.10543563439481371,
|
81 |
+
"eval_loss": 0.05613817274570465,
|
82 |
+
"eval_precision": 0.8203991130820399,
|
83 |
+
"eval_recall": 0.056338028169014086,
|
84 |
+
"eval_runtime": 14.2341,
|
85 |
+
"eval_samples_per_second": 569.76,
|
86 |
+
"eval_steps_per_second": 2.248,
|
87 |
+
"step": 3000
|
88 |
}
|
89 |
],
|
90 |
"logging_steps": 500,
|
|
|
113 |
"attributes": {}
|
114 |
}
|
115 |
},
|
116 |
+
"total_flos": 67737816965952.0,
|
117 |
"train_batch_size": 4,
|
118 |
"trial_name": null,
|
119 |
"trial_params": null
|