MatanBT commited on
Commit
47064db
·
verified ·
1 Parent(s): 0b913ee

Upload folder using huggingface_hub

Browse files
checkpoint-250/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51a67a16229c3a8e5242fae3d047b744f800596df5ae07b946778f74589cfbd0
3
  size 1999811208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63ac4aebc832cb012bd9cf7a6e3fc3cb86bb6c824bdd288ed880acd47fcf0cd4
3
  size 1999811208
checkpoint-250/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38cd91bd5f8029f8c826e27d241a983ba1212e1747b6e0db75c3eb651ac2639d
3
  size 3999834207
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42b64143fe587a166cb1750893a36f383bfac9fe655a3b8898ad096d706ef862
3
  size 3999834207
checkpoint-250/trainer_state.json CHANGED
@@ -11,177 +11,177 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.4,
14
- "grad_norm": 11.0,
15
  "learning_rate": 4.82e-05,
16
- "loss": 2.2998,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.8,
21
- "grad_norm": 5.21875,
22
  "learning_rate": 4.6200000000000005e-05,
23
- "loss": 1.6439,
24
  "step": 20
25
  },
26
  {
27
  "epoch": 1.2,
28
- "grad_norm": 5.0,
29
  "learning_rate": 4.4200000000000004e-05,
30
- "loss": 1.6086,
31
  "step": 30
32
  },
33
  {
34
  "epoch": 1.6,
35
- "grad_norm": 4.96875,
36
  "learning_rate": 4.22e-05,
37
- "loss": 1.5256,
38
  "step": 40
39
  },
40
  {
41
  "epoch": 2.0,
42
  "grad_norm": 4.125,
43
  "learning_rate": 4.02e-05,
44
- "loss": 1.5245,
45
  "step": 50
46
  },
47
  {
48
  "epoch": 2.4,
49
- "grad_norm": 4.90625,
50
  "learning_rate": 3.82e-05,
51
- "loss": 1.2857,
52
  "step": 60
53
  },
54
  {
55
  "epoch": 2.8,
56
- "grad_norm": 9.625,
57
  "learning_rate": 3.62e-05,
58
- "loss": 1.2765,
59
  "step": 70
60
  },
61
  {
62
  "epoch": 3.2,
63
- "grad_norm": 6.71875,
64
  "learning_rate": 3.4200000000000005e-05,
65
- "loss": 1.2541,
66
  "step": 80
67
  },
68
  {
69
  "epoch": 3.6,
70
- "grad_norm": 6.5,
71
  "learning_rate": 3.2200000000000003e-05,
72
- "loss": 1.0687,
73
  "step": 90
74
  },
75
  {
76
  "epoch": 4.0,
77
- "grad_norm": 8.8125,
78
  "learning_rate": 3.02e-05,
79
- "loss": 1.0931,
80
  "step": 100
81
  },
82
  {
83
  "epoch": 4.4,
84
- "grad_norm": 14.625,
85
  "learning_rate": 2.8199999999999998e-05,
86
- "loss": 0.9218,
87
  "step": 110
88
  },
89
  {
90
  "epoch": 4.8,
91
- "grad_norm": 9.25,
92
  "learning_rate": 2.6200000000000003e-05,
93
- "loss": 0.8114,
94
  "step": 120
95
  },
96
  {
97
  "epoch": 5.2,
98
- "grad_norm": 10.6875,
99
  "learning_rate": 2.4200000000000002e-05,
100
- "loss": 0.719,
101
  "step": 130
102
  },
103
  {
104
  "epoch": 5.6,
105
- "grad_norm": 15.9375,
106
  "learning_rate": 2.22e-05,
107
- "loss": 0.5463,
108
  "step": 140
109
  },
110
  {
111
  "epoch": 6.0,
112
- "grad_norm": 5.1875,
113
  "learning_rate": 2.0200000000000003e-05,
114
- "loss": 0.6334,
115
  "step": 150
116
  },
117
  {
118
  "epoch": 6.4,
119
- "grad_norm": 9.25,
120
  "learning_rate": 1.8200000000000002e-05,
121
- "loss": 0.4223,
122
  "step": 160
123
  },
124
  {
125
  "epoch": 6.8,
126
- "grad_norm": 9.75,
127
  "learning_rate": 1.62e-05,
128
- "loss": 0.4,
129
  "step": 170
130
  },
131
  {
132
  "epoch": 7.2,
133
- "grad_norm": 6.28125,
134
  "learning_rate": 1.42e-05,
135
- "loss": 0.3186,
136
  "step": 180
137
  },
138
  {
139
  "epoch": 7.6,
140
- "grad_norm": 6.90625,
141
  "learning_rate": 1.22e-05,
142
- "loss": 0.2554,
143
  "step": 190
144
  },
145
  {
146
  "epoch": 8.0,
147
- "grad_norm": 12.25,
148
  "learning_rate": 1.02e-05,
149
- "loss": 0.2928,
150
  "step": 200
151
  },
152
  {
153
  "epoch": 8.4,
154
- "grad_norm": 5.375,
155
  "learning_rate": 8.200000000000001e-06,
156
- "loss": 0.1929,
157
  "step": 210
158
  },
159
  {
160
  "epoch": 8.8,
161
- "grad_norm": 14.1875,
162
  "learning_rate": 6.2e-06,
163
- "loss": 0.2219,
164
  "step": 220
165
  },
166
  {
167
  "epoch": 9.2,
168
- "grad_norm": 5.6875,
169
  "learning_rate": 4.2000000000000004e-06,
170
- "loss": 0.1819,
171
  "step": 230
172
  },
173
  {
174
  "epoch": 9.6,
175
- "grad_norm": 4.78125,
176
  "learning_rate": 2.2e-06,
177
- "loss": 0.1677,
178
  "step": 240
179
  },
180
  {
181
  "epoch": 10.0,
182
- "grad_norm": 4.3125,
183
  "learning_rate": 2.0000000000000002e-07,
184
- "loss": 0.1701,
185
  "step": 250
186
  }
187
  ],
 
11
  "log_history": [
12
  {
13
  "epoch": 0.4,
14
+ "grad_norm": 11.5,
15
  "learning_rate": 4.82e-05,
16
+ "loss": 2.3626,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.8,
21
+ "grad_norm": 5.3125,
22
  "learning_rate": 4.6200000000000005e-05,
23
+ "loss": 1.6737,
24
  "step": 20
25
  },
26
  {
27
  "epoch": 1.2,
28
+ "grad_norm": 9.4375,
29
  "learning_rate": 4.4200000000000004e-05,
30
+ "loss": 1.6044,
31
  "step": 30
32
  },
33
  {
34
  "epoch": 1.6,
35
+ "grad_norm": 5.46875,
36
  "learning_rate": 4.22e-05,
37
+ "loss": 1.5568,
38
  "step": 40
39
  },
40
  {
41
  "epoch": 2.0,
42
  "grad_norm": 4.125,
43
  "learning_rate": 4.02e-05,
44
+ "loss": 1.5285,
45
  "step": 50
46
  },
47
  {
48
  "epoch": 2.4,
49
+ "grad_norm": 4.84375,
50
  "learning_rate": 3.82e-05,
51
+ "loss": 1.307,
52
  "step": 60
53
  },
54
  {
55
  "epoch": 2.8,
56
+ "grad_norm": 8.875,
57
  "learning_rate": 3.62e-05,
58
+ "loss": 1.299,
59
  "step": 70
60
  },
61
  {
62
  "epoch": 3.2,
63
+ "grad_norm": 6.5,
64
  "learning_rate": 3.4200000000000005e-05,
65
+ "loss": 1.2856,
66
  "step": 80
67
  },
68
  {
69
  "epoch": 3.6,
70
+ "grad_norm": 5.875,
71
  "learning_rate": 3.2200000000000003e-05,
72
+ "loss": 1.1082,
73
  "step": 90
74
  },
75
  {
76
  "epoch": 4.0,
77
+ "grad_norm": 8.1875,
78
  "learning_rate": 3.02e-05,
79
+ "loss": 1.1532,
80
  "step": 100
81
  },
82
  {
83
  "epoch": 4.4,
84
+ "grad_norm": 13.3125,
85
  "learning_rate": 2.8199999999999998e-05,
86
+ "loss": 0.9778,
87
  "step": 110
88
  },
89
  {
90
  "epoch": 4.8,
91
+ "grad_norm": 8.3125,
92
  "learning_rate": 2.6200000000000003e-05,
93
+ "loss": 0.8454,
94
  "step": 120
95
  },
96
  {
97
  "epoch": 5.2,
98
+ "grad_norm": 8.0,
99
  "learning_rate": 2.4200000000000002e-05,
100
+ "loss": 0.8049,
101
  "step": 130
102
  },
103
  {
104
  "epoch": 5.6,
105
+ "grad_norm": 22.625,
106
  "learning_rate": 2.22e-05,
107
+ "loss": 0.6104,
108
  "step": 140
109
  },
110
  {
111
  "epoch": 6.0,
112
+ "grad_norm": 6.875,
113
  "learning_rate": 2.0200000000000003e-05,
114
+ "loss": 0.6305,
115
  "step": 150
116
  },
117
  {
118
  "epoch": 6.4,
119
+ "grad_norm": 21.25,
120
  "learning_rate": 1.8200000000000002e-05,
121
+ "loss": 0.4074,
122
  "step": 160
123
  },
124
  {
125
  "epoch": 6.8,
126
+ "grad_norm": 15.9375,
127
  "learning_rate": 1.62e-05,
128
+ "loss": 0.432,
129
  "step": 170
130
  },
131
  {
132
  "epoch": 7.2,
133
+ "grad_norm": 4.65625,
134
  "learning_rate": 1.42e-05,
135
+ "loss": 0.3196,
136
  "step": 180
137
  },
138
  {
139
  "epoch": 7.6,
140
+ "grad_norm": 11.25,
141
  "learning_rate": 1.22e-05,
142
+ "loss": 0.2633,
143
  "step": 190
144
  },
145
  {
146
  "epoch": 8.0,
147
+ "grad_norm": 7.75,
148
  "learning_rate": 1.02e-05,
149
+ "loss": 0.2649,
150
  "step": 200
151
  },
152
  {
153
  "epoch": 8.4,
154
+ "grad_norm": 4.9375,
155
  "learning_rate": 8.200000000000001e-06,
156
+ "loss": 0.194,
157
  "step": 210
158
  },
159
  {
160
  "epoch": 8.8,
161
+ "grad_norm": 5.21875,
162
  "learning_rate": 6.2e-06,
163
+ "loss": 0.1988,
164
  "step": 220
165
  },
166
  {
167
  "epoch": 9.2,
168
+ "grad_norm": 6.09375,
169
  "learning_rate": 4.2000000000000004e-06,
170
+ "loss": 0.1789,
171
  "step": 230
172
  },
173
  {
174
  "epoch": 9.6,
175
+ "grad_norm": 4.25,
176
  "learning_rate": 2.2e-06,
177
+ "loss": 0.155,
178
  "step": 240
179
  },
180
  {
181
  "epoch": 10.0,
182
+ "grad_norm": 4.53125,
183
  "learning_rate": 2.0000000000000002e-07,
184
+ "loss": 0.1627,
185
  "step": 250
186
  }
187
  ],
checkpoint-250/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f47d9dfeea297f70054819c45ec532a1a9cc3bfad2833427ed1061da98947ec
3
  size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41cd435e6a35d113b56cff4f1fba4298f479e76225a8f4bec93f7671750731f9
3
  size 5777
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34a639938f53f443c0dc92996c1fea7ea8618b2deeb5f92b5cf41d16551951f2
3
  size 1999811208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63ac4aebc832cb012bd9cf7a6e3fc3cb86bb6c824bdd288ed880acd47fcf0cd4
3
  size 1999811208
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4742684a093fc361873457fae1211104c151d4d7203b326aafde35d86d727093
3
  size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41cd435e6a35d113b56cff4f1fba4298f479e76225a8f4bec93f7671750731f9
3
  size 5777