Theoreticallyhugo
commited on
Commit
•
ca3e8e2
1
Parent(s):
767fdee
Training in progress, epoch 2, checkpoint
Browse files
checkpoint-162/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 592324828
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:033c5e12de6882ebb7fbd602cc3c42c2510c285bed6a6a3013e5a243fbe9a6b4
|
3 |
size 592324828
|
checkpoint-162/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1014657786
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c8c7655c4645f5ae80c0777f71e19bda200a8705809ce6968c6fca7a481a6cb
|
3 |
size 1014657786
|
checkpoint-162/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 sha256:6613e657dfa5c91f076329239ba74e9bccea696a05690b1f35a5faffc85df4aa
|
3 |
size 14244
|
checkpoint-162/trainer_state.json
CHANGED
@@ -11,90 +11,90 @@
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"eval_Claim": {
|
14 |
-
"f1-score": 0.
|
15 |
-
"precision": 0.
|
16 |
-
"recall": 0.
|
17 |
-
"support":
|
18 |
},
|
19 |
"eval_MajorClaim": {
|
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":
|
29 |
-
"support":
|
30 |
},
|
31 |
"eval_Premise": {
|
32 |
-
"f1-score": 0.
|
33 |
-
"precision": 0.
|
34 |
-
"recall": 0.
|
35 |
-
"support":
|
36 |
},
|
37 |
-
"eval_accuracy": 0.
|
38 |
-
"eval_loss": 0.
|
39 |
"eval_macro avg": {
|
40 |
-
"f1-score": 0.
|
41 |
-
"precision": 0.
|
42 |
-
"recall": 0.
|
43 |
-
"support":
|
44 |
},
|
45 |
-
"eval_runtime": 4.
|
46 |
-
"eval_samples_per_second": 16.
|
47 |
-
"eval_steps_per_second": 2.
|
48 |
"eval_weighted avg": {
|
49 |
-
"f1-score": 0.
|
50 |
-
"precision": 0.
|
51 |
-
"recall": 0.
|
52 |
-
"support":
|
53 |
},
|
54 |
"step": 81
|
55 |
},
|
56 |
{
|
57 |
"epoch": 2.0,
|
58 |
"eval_Claim": {
|
59 |
-
"f1-score": 0.
|
60 |
-
"precision": 0.
|
61 |
-
"recall": 0.
|
62 |
-
"support":
|
63 |
},
|
64 |
"eval_MajorClaim": {
|
65 |
-
"f1-score": 0.
|
66 |
-
"precision": 0.
|
67 |
-
"recall": 0.
|
68 |
-
"support":
|
69 |
},
|
70 |
"eval_O": {
|
71 |
-
"f1-score": 0.
|
72 |
-
"precision": 0.
|
73 |
-
"recall": 0.
|
74 |
-
"support":
|
75 |
},
|
76 |
"eval_Premise": {
|
77 |
-
"f1-score": 0.
|
78 |
-
"precision": 0.
|
79 |
-
"recall": 0.
|
80 |
-
"support":
|
81 |
},
|
82 |
-
"eval_accuracy": 0.
|
83 |
-
"eval_loss": 0.
|
84 |
"eval_macro avg": {
|
85 |
-
"f1-score": 0.
|
86 |
-
"precision": 0.
|
87 |
-
"recall": 0.
|
88 |
-
"support":
|
89 |
},
|
90 |
-
"eval_runtime":
|
91 |
-
"eval_samples_per_second": 16.
|
92 |
-
"eval_steps_per_second": 2.
|
93 |
"eval_weighted avg": {
|
94 |
-
"f1-score": 0.
|
95 |
-
"precision": 0.
|
96 |
-
"recall": 0.
|
97 |
-
"support":
|
98 |
},
|
99 |
"step": 162
|
100 |
}
|
@@ -104,7 +104,7 @@
|
|
104 |
"num_input_tokens_seen": 0,
|
105 |
"num_train_epochs": 50,
|
106 |
"save_steps": 500,
|
107 |
-
"total_flos":
|
108 |
"train_batch_size": 4,
|
109 |
"trial_name": null,
|
110 |
"trial_params": null
|
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"eval_Claim": {
|
14 |
+
"f1-score": 0.5385059461955894,
|
15 |
+
"precision": 0.6267132491265789,
|
16 |
+
"recall": 0.4720647773279352,
|
17 |
+
"support": 4940.0
|
18 |
},
|
19 |
"eval_MajorClaim": {
|
20 |
+
"f1-score": 0.7814784727863526,
|
21 |
+
"precision": 0.9588039867109635,
|
22 |
+
"recall": 0.6595063985374772,
|
23 |
+
"support": 2188.0
|
24 |
},
|
25 |
"eval_O": {
|
26 |
+
"f1-score": 0.9938608715302625,
|
27 |
+
"precision": 0.9996969237763298,
|
28 |
+
"recall": 0.9880925634688834,
|
29 |
+
"support": 13353.0
|
30 |
},
|
31 |
"eval_Premise": {
|
32 |
+
"f1-score": 0.8968837690149166,
|
33 |
+
"precision": 0.8455112497215416,
|
34 |
+
"recall": 0.954902824076986,
|
35 |
+
"support": 15899.0
|
36 |
},
|
37 |
+
"eval_accuracy": 0.8837548103353491,
|
38 |
+
"eval_loss": 0.2860471308231354,
|
39 |
"eval_macro avg": {
|
40 |
+
"f1-score": 0.8026822648817803,
|
41 |
+
"precision": 0.8576813523338533,
|
42 |
+
"recall": 0.7686416408528204,
|
43 |
+
"support": 36380.0
|
44 |
},
|
45 |
+
"eval_runtime": 4.9572,
|
46 |
+
"eval_samples_per_second": 16.34,
|
47 |
+
"eval_steps_per_second": 2.219,
|
48 |
"eval_weighted avg": {
|
49 |
+
"f1-score": 0.8768739289107891,
|
50 |
+
"precision": 0.8792073379911217,
|
51 |
+
"recall": 0.8837548103353491,
|
52 |
+
"support": 36380.0
|
53 |
},
|
54 |
"step": 81
|
55 |
},
|
56 |
{
|
57 |
"epoch": 2.0,
|
58 |
"eval_Claim": {
|
59 |
+
"f1-score": 0.6469459868753155,
|
60 |
+
"precision": 0.6453172205438067,
|
61 |
+
"recall": 0.648582995951417,
|
62 |
+
"support": 4940.0
|
63 |
},
|
64 |
"eval_MajorClaim": {
|
65 |
+
"f1-score": 0.8435970110796187,
|
66 |
+
"precision": 0.9669226225634967,
|
67 |
+
"recall": 0.7481718464351006,
|
68 |
+
"support": 2188.0
|
69 |
},
|
70 |
"eval_O": {
|
71 |
+
"f1-score": 0.998877245508982,
|
72 |
+
"precision": 0.9983541557567143,
|
73 |
+
"recall": 0.9994008836965476,
|
74 |
+
"support": 13353.0
|
75 |
},
|
76 |
"eval_Premise": {
|
77 |
+
"f1-score": 0.9099026477336144,
|
78 |
+
"precision": 0.8972179761540813,
|
79 |
+
"recall": 0.922951129001824,
|
80 |
+
"support": 15899.0
|
81 |
},
|
82 |
+
"eval_accuracy": 0.903243540406817,
|
83 |
+
"eval_loss": 0.24885737895965576,
|
84 |
"eval_macro avg": {
|
85 |
+
"f1-score": 0.8498307227993828,
|
86 |
+
"precision": 0.8769529937545246,
|
87 |
+
"recall": 0.8297767137712222,
|
88 |
+
"support": 36380.0
|
89 |
},
|
90 |
+
"eval_runtime": 5.0097,
|
91 |
+
"eval_samples_per_second": 16.169,
|
92 |
+
"eval_steps_per_second": 2.196,
|
93 |
"eval_weighted avg": {
|
94 |
+
"f1-score": 0.9028656814459712,
|
95 |
+
"precision": 0.9043261520711511,
|
96 |
+
"recall": 0.903243540406817,
|
97 |
+
"support": 36380.0
|
98 |
},
|
99 |
"step": 162
|
100 |
}
|
|
|
104 |
"num_input_tokens_seen": 0,
|
105 |
"num_train_epochs": 50,
|
106 |
"save_steps": 500,
|
107 |
+
"total_flos": 286684367734800.0,
|
108 |
"train_batch_size": 4,
|
109 |
"trial_name": null,
|
110 |
"trial_params": null
|
checkpoint-162/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 sha256:95e8ce1619d475b315f2cb3494747dc2424fb9856a35d6759fcf75e79995f1f1
|
3 |
size 4856
|