Commit
•
e616016
1
Parent(s):
6e8a7ed
Training in progress, step 4000, 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 267835644
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d1559d5c4ceadde2aa023f48dd93b8416f2f8aa0643389bcba68c12b992efa8
|
3 |
size 267835644
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 535733434
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f0c475760564744c662dab6ac098185417c8813fd6a2b68031142b7baf6f03e
|
3 |
size 535733434
|
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 sha256:961a595705c86d1e3825267783cc61e0ff8cf7fff9fd42c90081270529f9b97c
|
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 sha256:12921cac8baef4519674a5132945a5195f3291a8d5b5367c7d05afa86f16027a
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "training_dir/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,
|
@@ -64,6 +64,25 @@
|
|
64 |
"eval_samples_per_second": 88.174,
|
65 |
"eval_steps_per_second": 11.022,
|
66 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
}
|
68 |
],
|
69 |
"logging_steps": 1000,
|
@@ -83,7 +102,7 @@
|
|
83 |
"attributes": {}
|
84 |
}
|
85 |
},
|
86 |
-
"total_flos":
|
87 |
"train_batch_size": 8,
|
88 |
"trial_name": null,
|
89 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6877643727244785,
|
3 |
+
"best_model_checkpoint": "training_dir/checkpoint-4000",
|
4 |
+
"epoch": 0.4238635159478648,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 4000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
64 |
"eval_samples_per_second": 88.174,
|
65 |
"eval_steps_per_second": 11.022,
|
66 |
"step": 3000
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.4238635159478648,
|
70 |
+
"grad_norm": 9.338201522827148,
|
71 |
+
"learning_rate": 9.627143922445936e-06,
|
72 |
+
"loss": 0.5233,
|
73 |
+
"step": 4000
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.4238635159478648,
|
77 |
+
"eval_accuracy": 0.7023601398601399,
|
78 |
+
"eval_f1": 0.6877643727244785,
|
79 |
+
"eval_loss": 0.9143859148025513,
|
80 |
+
"eval_precision": 0.7132978004907108,
|
81 |
+
"eval_recall": 0.7023601398601399,
|
82 |
+
"eval_runtime": 26.1039,
|
83 |
+
"eval_samples_per_second": 87.65,
|
84 |
+
"eval_steps_per_second": 10.956,
|
85 |
+
"step": 4000
|
86 |
}
|
87 |
],
|
88 |
"logging_steps": 1000,
|
|
|
102 |
"attributes": {}
|
103 |
}
|
104 |
},
|
105 |
+
"total_flos": 3879664659350064.0,
|
106 |
"train_batch_size": 8,
|
107 |
"trial_name": null,
|
108 |
"trial_params": null
|