Commit
•
c6241ff
1
Parent(s):
19bda02
Training in progress, step 5000, 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 sha256:67c8fe930490649ce5cc11a5fe193cfd48bc0b97b88299ffd6ad76afde0040b4
|
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 sha256:043ea3e469648caba58a57596dc37634719c22f8059e744b1a94bd1ae02825a6
|
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 sha256:8ce8dfd2d06984e08483a3aee4cbb4be06065cfb35a021428755194fc5c9a8b5
|
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:de31fecea0d88f3221e03053e0cf20c02baea118bf0e2b1c0433dcc126081364
|
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,
|
@@ -83,6 +83,25 @@
|
|
83 |
"eval_samples_per_second": 87.65,
|
84 |
"eval_steps_per_second": 10.956,
|
85 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
86 |
}
|
87 |
],
|
88 |
"logging_steps": 1000,
|
@@ -102,7 +121,7 @@
|
|
102 |
"attributes": {}
|
103 |
}
|
104 |
},
|
105 |
-
"total_flos":
|
106 |
"train_batch_size": 8,
|
107 |
"trial_name": null,
|
108 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6979166210878224,
|
3 |
+
"best_model_checkpoint": "training_dir/checkpoint-5000",
|
4 |
+
"epoch": 0.5298293949348309,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 5000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
83 |
"eval_samples_per_second": 87.65,
|
84 |
"eval_steps_per_second": 10.956,
|
85 |
"step": 4000
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 0.5298293949348309,
|
89 |
+
"grad_norm": 7.548835754394531,
|
90 |
+
"learning_rate": 9.520613614573348e-06,
|
91 |
+
"loss": 0.5089,
|
92 |
+
"step": 5000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.5298293949348309,
|
96 |
+
"eval_accuracy": 0.7084790209790209,
|
97 |
+
"eval_f1": 0.6979166210878224,
|
98 |
+
"eval_loss": 0.8279535174369812,
|
99 |
+
"eval_precision": 0.7081949635182484,
|
100 |
+
"eval_recall": 0.7084790209790209,
|
101 |
+
"eval_runtime": 25.9523,
|
102 |
+
"eval_samples_per_second": 88.162,
|
103 |
+
"eval_steps_per_second": 11.02,
|
104 |
+
"step": 5000
|
105 |
}
|
106 |
],
|
107 |
"logging_steps": 1000,
|
|
|
121 |
"attributes": {}
|
122 |
}
|
123 |
},
|
124 |
+
"total_flos": 4845766626498096.0,
|
125 |
"train_batch_size": 8,
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|