Francesco0101
commited on
Commit
•
9e13e70
1
Parent(s):
f796ac0
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 sha256:8bc5bd5a71c67b305edcef1e48d81dd18c0068f2c4658bceee353301acf3a4b5
|
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:f69c75e81b22152cc1ea3af87eb6846cc209c513d4ddbb848997b84594b92e09
|
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:ea6da068f05bdae369cb14af09b1a103dcf7ea57f912e3af8f0bf546abf4d1c9
|
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 sha256:934377a13b65a28f5105294df26e4fe3b57c4d88e0a4908173ecc003fa91b9bb
|
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": 77.168,
|
65 |
"eval_steps_per_second": 9.646,
|
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": 0.727562941019853,
|
3 |
+
"best_model_checkpoint": "training_dir/checkpoint-4000",
|
4 |
+
"epoch": 0.6263701847792045,
|
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": 77.168,
|
65 |
"eval_steps_per_second": 9.646,
|
66 |
"step": 3000
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.6263701847792045,
|
70 |
+
"grad_norm": 28.96643829345703,
|
71 |
+
"learning_rate": 9.44760101010101e-06,
|
72 |
+
"loss": 0.4593,
|
73 |
+
"step": 4000
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.6263701847792045,
|
77 |
+
"eval_accuracy": 0.7338286713286714,
|
78 |
+
"eval_f1": 0.727562941019853,
|
79 |
+
"eval_loss": 0.7618293762207031,
|
80 |
+
"eval_precision": 0.7330094463964066,
|
81 |
+
"eval_recall": 0.7338286713286714,
|
82 |
+
"eval_runtime": 29.7317,
|
83 |
+
"eval_samples_per_second": 76.955,
|
84 |
+
"eval_steps_per_second": 9.619,
|
85 |
+
"step": 4000
|
86 |
}
|
87 |
],
|
88 |
"logging_steps": 1000,
|
|
|
102 |
"attributes": {}
|
103 |
}
|
104 |
},
|
105 |
+
"total_flos": 4032940452214896.0,
|
106 |
"train_batch_size": 8,
|
107 |
"trial_name": null,
|
108 |
"trial_params": null
|