Theoreticallyhugo
commited on
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 sha256:5fcdd8a6007a1be5c510663d9bfb96e3243904c78a656ccbcf28ba46ea72ab0a
|
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 sha256:220a80149fe4c069e67a4fc5b3210fedd75134cd8fb77d1f3a8ac23d3b9622bd
|
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": 0.
|
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": 4.
|
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": 0.4888068880688806,
|
15 |
+
"precision": 0.6228840125391849,
|
16 |
+
"recall": 0.40222672064777326,
|
17 |
+
"support": 4940.0
|
18 |
},
|
19 |
"eval_MajorClaim": {
|
20 |
+
"f1-score": 0.7325278370054489,
|
21 |
+
"precision": 0.7604525332021643,
|
22 |
+
"recall": 0.706581352833638,
|
23 |
+
"support": 2188.0
|
24 |
},
|
25 |
"eval_O": {
|
26 |
+
"f1-score": 0.8634848138844484,
|
27 |
+
"precision": 0.827613377692173,
|
28 |
+
"recall": 0.902606702950444,
|
29 |
+
"support": 10473.0
|
30 |
},
|
31 |
"eval_Premise": {
|
32 |
+
"f1-score": 0.8792819197655248,
|
33 |
+
"precision": 0.8543458914268763,
|
34 |
+
"recall": 0.9057173407132524,
|
35 |
+
"support": 15899.0
|
36 |
},
|
37 |
+
"eval_accuracy": 0.8174925373134329,
|
38 |
+
"eval_loss": 0.49806877970695496,
|
39 |
"eval_macro avg": {
|
40 |
+
"f1-score": 0.7410253646810757,
|
41 |
+
"precision": 0.7663239537150996,
|
42 |
+
"recall": 0.7292830292862769,
|
43 |
+
"support": 33500.0
|
44 |
},
|
45 |
+
"eval_runtime": 4.9194,
|
46 |
+
"eval_samples_per_second": 16.465,
|
47 |
+
"eval_steps_per_second": 2.236,
|
48 |
"eval_weighted avg": {
|
49 |
+
"f1-score": 0.8071778099281224,
|
50 |
+
"precision": 0.80572410140167,
|
51 |
+
"recall": 0.8174925373134329,
|
52 |
+
"support": 33500.0
|
53 |
},
|
54 |
"step": 81
|
55 |
},
|
56 |
{
|
57 |
"epoch": 2.0,
|
58 |
"eval_Claim": {
|
59 |
+
"f1-score": 0.5993816254416962,
|
60 |
+
"precision": 0.6593780369290574,
|
61 |
+
"recall": 0.5493927125506073,
|
62 |
+
"support": 4940.0
|
63 |
},
|
64 |
"eval_MajorClaim": {
|
65 |
+
"f1-score": 0.8017817371937639,
|
66 |
+
"precision": 0.7197382769901853,
|
67 |
+
"recall": 0.9049360146252285,
|
68 |
+
"support": 2188.0
|
69 |
},
|
70 |
"eval_O": {
|
71 |
+
"f1-score": 0.9058997050147494,
|
72 |
+
"precision": 0.9337184554575859,
|
73 |
+
"recall": 0.8796906330564308,
|
74 |
+
"support": 10473.0
|
75 |
},
|
76 |
"eval_Premise": {
|
77 |
+
"f1-score": 0.8854737486606459,
|
78 |
+
"precision": 0.862579028987236,
|
79 |
+
"recall": 0.9096169570413234,
|
80 |
+
"support": 15899.0
|
81 |
},
|
82 |
+
"eval_accuracy": 0.8468358208955223,
|
83 |
+
"eval_loss": 0.4562840759754181,
|
84 |
"eval_macro avg": {
|
85 |
+
"f1-score": 0.7981342040777137,
|
86 |
+
"precision": 0.7938534495910161,
|
87 |
+
"recall": 0.8109090793183975,
|
88 |
+
"support": 33500.0
|
89 |
},
|
90 |
+
"eval_runtime": 4.904,
|
91 |
+
"eval_samples_per_second": 16.517,
|
92 |
+
"eval_steps_per_second": 2.243,
|
93 |
"eval_weighted avg": {
|
94 |
+
"f1-score": 0.8442053257085675,
|
95 |
+
"precision": 0.8455251408465503,
|
96 |
+
"recall": 0.8468358208955223,
|
97 |
+
"support": 33500.0
|
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:da575726aa6fb9f10d3d3191c16916e8d9dc133cfc573c1d27486b346adcb4eb
|
3 |
size 4856
|