Theoreticallyhugo
commited on
Commit
•
18e3d43
1
Parent(s):
f465272
Training in progress, epoch 1, checkpoint
Browse files
checkpoint-81/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 592318676
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c10e018bb04904d88040b2ea7cd080dea959aa4fe96a87a5b4f8dc1b8a360ce
|
3 |
size 592318676
|
checkpoint-81/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1014645498
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e528a4648cb8a2c2c705a43f8810843a28ae1841d3a9e0ddb168a7b9dc16978
|
3 |
size 1014645498
|
checkpoint-81/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:bdb4b9e39f26364dd12b4935d341c9c41df1f0d9ec688c6ea55c6a3c16f98050
|
3 |
size 14244
|
checkpoint-81/trainer_state.json
CHANGED
@@ -11,39 +11,39 @@
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"eval_B": {
|
14 |
-
"f1-score": 0.
|
15 |
-
"precision": 0.
|
16 |
-
"recall": 0.
|
17 |
-
"support":
|
18 |
},
|
19 |
"eval_I": {
|
20 |
-
"f1-score": 0.
|
21 |
-
"precision": 0.
|
22 |
-
"recall": 0.
|
23 |
-
"support":
|
24 |
},
|
25 |
"eval_O": {
|
26 |
-
"f1-score": 0.
|
27 |
-
"precision": 0.
|
28 |
-
"recall": 0.
|
29 |
-
"support":
|
30 |
},
|
31 |
-
"eval_accuracy": 0.
|
32 |
-
"eval_loss": 0.
|
33 |
"eval_macro avg": {
|
34 |
-
"f1-score": 0.
|
35 |
-
"precision": 0.
|
36 |
-
"recall": 0.
|
37 |
-
"support":
|
38 |
},
|
39 |
-
"eval_runtime": 4.
|
40 |
-
"eval_samples_per_second": 17.
|
41 |
-
"eval_steps_per_second": 2.
|
42 |
"eval_weighted avg": {
|
43 |
-
"f1-score": 0.
|
44 |
-
"precision": 0.
|
45 |
-
"recall": 0.
|
46 |
-
"support":
|
47 |
},
|
48 |
"step": 81
|
49 |
}
|
@@ -53,7 +53,7 @@
|
|
53 |
"num_input_tokens_seen": 0,
|
54 |
"num_train_epochs": 50,
|
55 |
"save_steps": 500,
|
56 |
-
"total_flos":
|
57 |
"train_batch_size": 4,
|
58 |
"trial_name": null,
|
59 |
"trial_params": null
|
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"eval_B": {
|
14 |
+
"f1-score": 0.7905866302864938,
|
15 |
+
"precision": 0.7768096514745308,
|
16 |
+
"recall": 0.8048611111111111,
|
17 |
+
"support": 1440.0
|
18 |
},
|
19 |
"eval_I": {
|
20 |
+
"f1-score": 0.9005331227169513,
|
21 |
+
"precision": 0.9637593111099372,
|
22 |
+
"recall": 0.8450919534905267,
|
23 |
+
"support": 21587.0
|
24 |
},
|
25 |
"eval_O": {
|
26 |
+
"f1-score": 0.8288892663043479,
|
27 |
+
"precision": 0.7463108800367001,
|
28 |
+
"recall": 0.9320156593144275,
|
29 |
+
"support": 10473.0
|
30 |
},
|
31 |
+
"eval_accuracy": 0.8705373134328358,
|
32 |
+
"eval_loss": 0.32930415868759155,
|
33 |
"eval_macro avg": {
|
34 |
+
"f1-score": 0.8400030064359308,
|
35 |
+
"precision": 0.8289599475403894,
|
36 |
+
"recall": 0.8606562413053552,
|
37 |
+
"support": 33500.0
|
38 |
},
|
39 |
+
"eval_runtime": 4.7349,
|
40 |
+
"eval_samples_per_second": 17.107,
|
41 |
+
"eval_steps_per_second": 2.323,
|
42 |
"eval_weighted avg": {
|
43 |
+
"f1-score": 0.8734092702599646,
|
44 |
+
"precision": 0.8877430445874,
|
45 |
+
"recall": 0.8705373134328358,
|
46 |
+
"support": 33500.0
|
47 |
},
|
48 |
"step": 81
|
49 |
}
|
|
|
53 |
"num_input_tokens_seen": 0,
|
54 |
"num_train_epochs": 50,
|
55 |
"save_steps": 500,
|
56 |
+
"total_flos": 143340110335800.0,
|
57 |
"train_batch_size": 4,
|
58 |
"trial_name": null,
|
59 |
"trial_params": null
|
checkpoint-81/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8ca363922308e3892528dd031742ffedc372734b464a042d09444af9700901e
|
3 |
size 4856
|