Theoreticallyhugo
commited on
Commit
•
a1f5f13
1
Parent(s):
cf74d19
Training in progress, epoch 4, checkpoint
Browse files- checkpoint-324/model.safetensors +1 -1
- checkpoint-324/optimizer.pt +1 -1
- checkpoint-324/rng_state.pth +1 -1
- checkpoint-324/trainer_state.json +121 -121
- checkpoint-324/training_args.bin +1 -1
checkpoint-324/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 sha256:27f47dcdb29a8d1c80c0a340b99e024b80cd6acb825831f65ed0576f5361034c
|
3 |
size 592324828
|
checkpoint-324/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:fdc3cc96f13a409b98a2a4916802ef86199a770d1d97f421e314fdc04610b2a1
|
3 |
size 1014657786
|
checkpoint-324/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 sha256:5474bfb178f1f5ac14d6be6fd7772f757be3e1728e1b25f0f54ac7eff70dac62
|
3 |
size 14244
|
checkpoint-324/trainer_state.json
CHANGED
@@ -11,180 +11,180 @@
|
|
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":
|
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 |
},
|
101 |
{
|
102 |
"epoch": 3.0,
|
103 |
"eval_Claim": {
|
104 |
-
"f1-score": 0.
|
105 |
-
"precision": 0.
|
106 |
-
"recall": 0.
|
107 |
-
"support":
|
108 |
},
|
109 |
"eval_MajorClaim": {
|
110 |
-
"f1-score": 0.
|
111 |
-
"precision": 0.
|
112 |
-
"recall": 0.
|
113 |
-
"support":
|
114 |
},
|
115 |
"eval_O": {
|
116 |
-
"f1-score": 0.
|
117 |
-
"precision": 0
|
118 |
-
"recall": 0.
|
119 |
-
"support":
|
120 |
},
|
121 |
"eval_Premise": {
|
122 |
-
"f1-score": 0.
|
123 |
-
"precision": 0.
|
124 |
-
"recall": 0.
|
125 |
-
"support":
|
126 |
},
|
127 |
-
"eval_accuracy": 0.
|
128 |
-
"eval_loss": 0.
|
129 |
"eval_macro avg": {
|
130 |
-
"f1-score": 0.
|
131 |
-
"precision": 0.
|
132 |
-
"recall": 0.
|
133 |
-
"support":
|
134 |
-
},
|
135 |
-
"eval_runtime": 4.
|
136 |
-
"eval_samples_per_second": 16.
|
137 |
-
"eval_steps_per_second": 2.
|
138 |
"eval_weighted avg": {
|
139 |
-
"f1-score": 0.
|
140 |
-
"precision": 0.
|
141 |
-
"recall": 0.
|
142 |
-
"support":
|
143 |
},
|
144 |
"step": 243
|
145 |
},
|
146 |
{
|
147 |
"epoch": 4.0,
|
148 |
"eval_Claim": {
|
149 |
-
"f1-score": 0.
|
150 |
-
"precision": 0.
|
151 |
-
"recall": 0.
|
152 |
-
"support":
|
153 |
},
|
154 |
"eval_MajorClaim": {
|
155 |
-
"f1-score": 0.
|
156 |
-
"precision": 0.
|
157 |
-
"recall": 0.
|
158 |
-
"support":
|
159 |
},
|
160 |
"eval_O": {
|
161 |
-
"f1-score": 0
|
162 |
-
"precision": 0
|
163 |
-
"recall": 0
|
164 |
-
"support":
|
165 |
},
|
166 |
"eval_Premise": {
|
167 |
-
"f1-score": 0.
|
168 |
-
"precision": 0.
|
169 |
-
"recall": 0.
|
170 |
-
"support":
|
171 |
},
|
172 |
-
"eval_accuracy": 0.
|
173 |
-
"eval_loss": 0.
|
174 |
"eval_macro avg": {
|
175 |
-
"f1-score": 0.
|
176 |
-
"precision": 0.
|
177 |
-
"recall": 0.
|
178 |
-
"support":
|
179 |
-
},
|
180 |
-
"eval_runtime": 4.
|
181 |
-
"eval_samples_per_second": 16.
|
182 |
-
"eval_steps_per_second": 2.
|
183 |
"eval_weighted avg": {
|
184 |
-
"f1-score": 0.
|
185 |
-
"precision": 0.
|
186 |
-
"recall": 0.
|
187 |
-
"support":
|
188 |
},
|
189 |
"step": 324
|
190 |
}
|
@@ -194,7 +194,7 @@
|
|
194 |
"num_input_tokens_seen": 0,
|
195 |
"num_train_epochs": 50,
|
196 |
"save_steps": 500,
|
197 |
-
"total_flos":
|
198 |
"train_batch_size": 4,
|
199 |
"trial_name": null,
|
200 |
"trial_params": null
|
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"eval_Claim": {
|
14 |
+
"f1-score": 0.5254768748366867,
|
15 |
+
"precision": 0.5768789443488239,
|
16 |
+
"recall": 0.4824856046065259,
|
17 |
+
"support": 4168.0
|
18 |
},
|
19 |
"eval_MajorClaim": {
|
20 |
+
"f1-score": 0.7984361424847959,
|
21 |
+
"precision": 0.7495921696574225,
|
22 |
+
"recall": 0.854089219330855,
|
23 |
+
"support": 2152.0
|
24 |
},
|
25 |
"eval_O": {
|
26 |
+
"f1-score": 0.9990277532260916,
|
27 |
+
"precision": 0.9988511841640155,
|
28 |
+
"recall": 0.9992043847241867,
|
29 |
+
"support": 11312.0
|
30 |
},
|
31 |
"eval_Premise": {
|
32 |
+
"f1-score": 0.8854183656825966,
|
33 |
+
"precision": 0.8719781543651113,
|
34 |
+
"recall": 0.8992793837488611,
|
35 |
+
"support": 12073.0
|
36 |
},
|
37 |
+
"eval_accuracy": 0.8755765022723447,
|
38 |
+
"eval_loss": 0.28303390741348267,
|
39 |
"eval_macro avg": {
|
40 |
+
"f1-score": 0.8020897840575427,
|
41 |
+
"precision": 0.7993251131338432,
|
42 |
+
"recall": 0.8087646481026072,
|
43 |
+
"support": 29705.0
|
44 |
+
},
|
45 |
+
"eval_runtime": 4.8106,
|
46 |
+
"eval_samples_per_second": 16.63,
|
47 |
+
"eval_steps_per_second": 2.079,
|
48 |
"eval_weighted avg": {
|
49 |
+
"f1-score": 0.8718761173649596,
|
50 |
+
"precision": 0.8700202202343714,
|
51 |
+
"recall": 0.8755765022723447,
|
52 |
+
"support": 29705.0
|
53 |
},
|
54 |
"step": 81
|
55 |
},
|
56 |
{
|
57 |
"epoch": 2.0,
|
58 |
"eval_Claim": {
|
59 |
+
"f1-score": 0.5578782336033447,
|
60 |
+
"precision": 0.6124497991967871,
|
61 |
+
"recall": 0.5122360844529751,
|
62 |
+
"support": 4168.0
|
63 |
},
|
64 |
"eval_MajorClaim": {
|
65 |
+
"f1-score": 0.784421283598464,
|
66 |
+
"precision": 0.9571619812583668,
|
67 |
+
"recall": 0.6644981412639405,
|
68 |
+
"support": 2152.0
|
69 |
},
|
70 |
"eval_O": {
|
71 |
+
"f1-score": 0.9998674150351351,
|
72 |
+
"precision": 0.9997348652231551,
|
73 |
+
"recall": 1.0,
|
74 |
+
"support": 11312.0
|
75 |
},
|
76 |
"eval_Premise": {
|
77 |
+
"f1-score": 0.8977749872463995,
|
78 |
+
"precision": 0.8530201342281879,
|
79 |
+
"recall": 0.9474861260664292,
|
80 |
+
"support": 12073.0
|
81 |
},
|
82 |
+
"eval_accuracy": 0.8859114627167144,
|
83 |
+
"eval_loss": 0.27363118529319763,
|
84 |
"eval_macro avg": {
|
85 |
+
"f1-score": 0.8099854798708358,
|
86 |
+
"precision": 0.8555916949766242,
|
87 |
+
"recall": 0.7810550879458362,
|
88 |
+
"support": 29705.0
|
89 |
+
},
|
90 |
+
"eval_runtime": 4.7727,
|
91 |
+
"eval_samples_per_second": 16.762,
|
92 |
+
"eval_steps_per_second": 2.095,
|
93 |
"eval_weighted avg": {
|
94 |
+
"f1-score": 0.8807489883812781,
|
95 |
+
"precision": 0.8826802296805741,
|
96 |
+
"recall": 0.8859114627167144,
|
97 |
+
"support": 29705.0
|
98 |
},
|
99 |
"step": 162
|
100 |
},
|
101 |
{
|
102 |
"epoch": 3.0,
|
103 |
"eval_Claim": {
|
104 |
+
"f1-score": 0.64760736196319,
|
105 |
+
"precision": 0.6627322953289804,
|
106 |
+
"recall": 0.6331573896353166,
|
107 |
+
"support": 4168.0
|
108 |
},
|
109 |
"eval_MajorClaim": {
|
110 |
+
"f1-score": 0.9016018306636155,
|
111 |
+
"precision": 0.8881875563570785,
|
112 |
+
"recall": 0.9154275092936803,
|
113 |
+
"support": 2152.0
|
114 |
},
|
115 |
"eval_O": {
|
116 |
+
"f1-score": 0.9996904982977407,
|
117 |
+
"precision": 1.0,
|
118 |
+
"recall": 0.9993811881188119,
|
119 |
+
"support": 11312.0
|
120 |
},
|
121 |
"eval_Premise": {
|
122 |
+
"f1-score": 0.8982820417748115,
|
123 |
+
"precision": 0.8936065573770492,
|
124 |
+
"recall": 0.9030067091857865,
|
125 |
+
"support": 12073.0
|
126 |
},
|
127 |
+
"eval_accuracy": 0.9027436458508669,
|
128 |
+
"eval_loss": 0.22585685551166534,
|
129 |
"eval_macro avg": {
|
130 |
+
"f1-score": 0.8617954331748394,
|
131 |
+
"precision": 0.861131602265777,
|
132 |
+
"recall": 0.8627431990583988,
|
133 |
+
"support": 29705.0
|
134 |
+
},
|
135 |
+
"eval_runtime": 4.8003,
|
136 |
+
"eval_samples_per_second": 16.666,
|
137 |
+
"eval_steps_per_second": 2.083,
|
138 |
"eval_weighted avg": {
|
139 |
+
"f1-score": 0.9019670975035187,
|
140 |
+
"precision": 0.9013351218793044,
|
141 |
+
"recall": 0.9027436458508669,
|
142 |
+
"support": 29705.0
|
143 |
},
|
144 |
"step": 243
|
145 |
},
|
146 |
{
|
147 |
"epoch": 4.0,
|
148 |
"eval_Claim": {
|
149 |
+
"f1-score": 0.6477602966229081,
|
150 |
+
"precision": 0.5561865427637239,
|
151 |
+
"recall": 0.7754318618042226,
|
152 |
+
"support": 4168.0
|
153 |
},
|
154 |
"eval_MajorClaim": {
|
155 |
+
"f1-score": 0.8984409799554566,
|
156 |
+
"precision": 0.8627031650983746,
|
157 |
+
"recall": 0.9372676579925651,
|
158 |
+
"support": 2152.0
|
159 |
},
|
160 |
"eval_O": {
|
161 |
+
"f1-score": 1.0,
|
162 |
+
"precision": 1.0,
|
163 |
+
"recall": 1.0,
|
164 |
+
"support": 11312.0
|
165 |
},
|
166 |
"eval_Premise": {
|
167 |
+
"f1-score": 0.861495720750997,
|
168 |
+
"precision": 0.9384029675907849,
|
169 |
+
"recall": 0.7962395427814131,
|
170 |
+
"support": 12073.0
|
171 |
},
|
172 |
+
"eval_accuracy": 0.8811311227066151,
|
173 |
+
"eval_loss": 0.32341843843460083,
|
174 |
"eval_macro avg": {
|
175 |
+
"f1-score": 0.8519242493323405,
|
176 |
+
"precision": 0.8393231688632209,
|
177 |
+
"recall": 0.8772347656445502,
|
178 |
+
"support": 29705.0
|
179 |
+
},
|
180 |
+
"eval_runtime": 4.7708,
|
181 |
+
"eval_samples_per_second": 16.769,
|
182 |
+
"eval_steps_per_second": 2.096,
|
183 |
"eval_weighted avg": {
|
184 |
+
"f1-score": 0.8869263673393438,
|
185 |
+
"precision": 0.9027457246003854,
|
186 |
+
"recall": 0.8811311227066151,
|
187 |
+
"support": 29705.0
|
188 |
},
|
189 |
"step": 324
|
190 |
}
|
|
|
194 |
"num_input_tokens_seen": 0,
|
195 |
"num_train_epochs": 50,
|
196 |
"save_steps": 500,
|
197 |
+
"total_flos": 575154930907200.0,
|
198 |
"train_batch_size": 4,
|
199 |
"trial_name": null,
|
200 |
"trial_params": null
|
checkpoint-324/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 sha256:6c4152f1ae85467509d6d1bf2d3b859abf08e786a1c118f9c84f899edc2df5d1
|
3 |
size 4856
|