Commit
•
e0a45b9
1
Parent(s):
ac79f38
Training in progress, epoch 6, 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:efcd7c63e38a38d3550783e6dfd87fe60211e00634586d614cfc77ba08c94ada
|
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 sha256:19dd9437e890e13cc7302eb708d9860cd850c30569ec799b3a81efdc20dc6adc
|
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:edc81d9abdf3d06957eb9f3e249750099981d2c509afe1884a35eb4ccda7cd53
|
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 sha256:1380500cb5ce47f6085ce18023f66434aacc2bfc3f43d387430fdbaa4c016dad
|
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":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -102,6 +102,25 @@
|
|
102 |
"eval_samples_per_second": 76.558,
|
103 |
"eval_steps_per_second": 9.57,
|
104 |
"step": 625
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
105 |
}
|
106 |
],
|
107 |
"logging_steps": 500,
|
@@ -116,12 +135,12 @@
|
|
116 |
"should_evaluate": false,
|
117 |
"should_log": false,
|
118 |
"should_save": true,
|
119 |
-
"should_training_stop":
|
120 |
},
|
121 |
"attributes": {}
|
122 |
}
|
123 |
},
|
124 |
-
"total_flos":
|
125 |
"train_batch_size": 16,
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6382145069577949,
|
3 |
+
"best_model_checkpoint": "training_dir/checkpoint-750",
|
4 |
+
"epoch": 6.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 750,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
102 |
"eval_samples_per_second": 76.558,
|
103 |
"eval_steps_per_second": 9.57,
|
104 |
"step": 625
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 6.0,
|
108 |
+
"grad_norm": 0.12321516871452332,
|
109 |
+
"learning_rate": 0.0,
|
110 |
+
"loss": 0.0917,
|
111 |
+
"step": 750
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 6.0,
|
115 |
+
"eval_accuracy": 0.6494755244755245,
|
116 |
+
"eval_f1": 0.6382145069577949,
|
117 |
+
"eval_loss": 1.7655272483825684,
|
118 |
+
"eval_precision": 0.6518973060481164,
|
119 |
+
"eval_recall": 0.6494755244755245,
|
120 |
+
"eval_runtime": 30.1035,
|
121 |
+
"eval_samples_per_second": 76.005,
|
122 |
+
"eval_steps_per_second": 9.501,
|
123 |
+
"step": 750
|
124 |
}
|
125 |
],
|
126 |
"logging_steps": 500,
|
|
|
135 |
"should_evaluate": false,
|
136 |
"should_log": false,
|
137 |
"should_save": true,
|
138 |
+
"should_training_stop": true
|
139 |
},
|
140 |
"attributes": {}
|
141 |
}
|
142 |
},
|
143 |
+
"total_flos": 1223275449456000.0,
|
144 |
"train_batch_size": 16,
|
145 |
"trial_name": null,
|
146 |
"trial_params": null
|