ehyoussef commited on
Commit
2f06dd9
·
verified ·
1 Parent(s): c6f3d10

Training in progress, step 200, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cd632113a9b7958223b26af0be61c8b9730b715a074429c69bcc52c89595ea5
3
  size 307867048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3892d7981daf46335b3fa6c9ecb6ae907b780f5c60d09739df71fd1032e9df89
3
  size 307867048
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8d99aa0c9298f2796d34fb4905cca2dbc763af34675d0f49f3f6adc6219a5fd
3
  size 615852491
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cf424ee2a97c2d03eab6ed4b79c3501ef0848917d52e20b6d2ad2bd67cb36a1
3
  size 615852491
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:767264e229550ac642840d8d828ab78adc4e4b540eb7d7439d5658ee07c1008b
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3309a95e33c125d7c8441ae9bb16bceac61b9ce7549f29f3949856e911dabc37
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5df1288dff0dd62cba1e1176806173143916d981612ae8735c36fe34a88ddce
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:124625e167eb28acbfc793cfcb3e8a08b32e7fea06501462bc9e420a5e1beb2a
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:828ca8772c99b9f9a8f48fc7390761548c79238949072084224f82d3c8936b90
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19736ba68628776bb4f044cd05ed8cf11679afca52ec0a6537f0a4bbdc207303
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,114 +2,164 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 5.0,
6
  "eval_steps": 200,
7
- "global_step": 145,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
- "epoch": 0.3508771929824561,
14
- "grad_norm": 4.014275074005127,
15
- "learning_rate": 3.6e-05,
16
- "loss": 2.1574,
17
  "step": 10
18
  },
19
  {
20
- "epoch": 0.7017543859649122,
21
- "grad_norm": 2.0340123176574707,
22
- "learning_rate": 7.6e-05,
23
- "loss": 1.3204,
24
  "step": 20
25
  },
26
  {
27
- "epoch": 1.0350877192982457,
28
- "grad_norm": 1.895371913909912,
29
- "learning_rate": 0.000116,
30
- "loss": 0.7272,
31
  "step": 30
32
  },
33
  {
34
- "epoch": 1.3859649122807016,
35
- "grad_norm": 1.413552165031433,
36
- "learning_rate": 0.00015600000000000002,
37
- "loss": 0.4869,
38
  "step": 40
39
  },
40
  {
41
- "epoch": 1.736842105263158,
42
- "grad_norm": 0.769632875919342,
43
- "learning_rate": 0.000196,
44
- "loss": 0.3645,
45
  "step": 50
46
  },
47
  {
48
- "epoch": 2.0701754385964914,
49
- "grad_norm": 0.92262202501297,
50
- "learning_rate": 0.00018105263157894739,
51
- "loss": 0.3271,
52
  "step": 60
53
  },
54
  {
55
- "epoch": 2.4210526315789473,
56
- "grad_norm": 0.7400457262992859,
57
- "learning_rate": 0.00016,
58
- "loss": 0.2382,
59
  "step": 70
60
  },
61
  {
62
- "epoch": 2.7719298245614032,
63
- "grad_norm": 0.9223001003265381,
64
- "learning_rate": 0.00013894736842105264,
65
- "loss": 0.2106,
66
  "step": 80
67
  },
68
  {
69
- "epoch": 3.1052631578947367,
70
- "grad_norm": 0.7120507955551147,
71
- "learning_rate": 0.00011789473684210525,
72
- "loss": 0.1935,
73
  "step": 90
74
  },
75
  {
76
- "epoch": 3.456140350877193,
77
- "grad_norm": 0.7403267025947571,
78
- "learning_rate": 9.68421052631579e-05,
79
- "loss": 0.1774,
80
  "step": 100
81
  },
82
  {
83
- "epoch": 3.807017543859649,
84
- "grad_norm": 0.5725103616714478,
85
- "learning_rate": 7.578947368421054e-05,
86
- "loss": 0.1576,
87
  "step": 110
88
  },
89
  {
90
- "epoch": 4.140350877192983,
91
- "grad_norm": 0.8779940009117126,
92
- "learning_rate": 5.4736842105263165e-05,
93
- "loss": 0.1498,
94
  "step": 120
95
  },
96
  {
97
- "epoch": 4.491228070175438,
98
- "grad_norm": 0.5592442750930786,
99
- "learning_rate": 3.368421052631579e-05,
100
- "loss": 0.1492,
101
  "step": 130
102
  },
103
  {
104
- "epoch": 4.842105263157895,
105
- "grad_norm": 0.5548624992370605,
106
- "learning_rate": 1.2631578947368422e-05,
107
- "loss": 0.1411,
108
  "step": 140
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
109
  }
110
  ],
111
  "logging_steps": 10,
112
- "max_steps": 145,
113
  "num_input_tokens_seen": 0,
114
  "num_train_epochs": 5,
115
  "save_steps": 200,
@@ -120,13 +170,13 @@
120
  "should_evaluate": false,
121
  "should_log": false,
122
  "should_save": true,
123
- "should_training_stop": true
124
  },
125
  "attributes": {}
126
  }
127
  },
128
- "total_flos": 517092923977728.0,
129
- "train_batch_size": 32,
130
  "trial_name": null,
131
  "trial_params": null
132
  }
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 3.5132743362831858,
6
  "eval_steps": 200,
7
+ "global_step": 200,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
+ "epoch": 0.17699115044247787,
14
+ "grad_norm": 8.512289047241211,
15
+ "learning_rate": 3.6000000000000003e-06,
16
+ "loss": 2.359,
17
  "step": 10
18
  },
19
  {
20
+ "epoch": 0.35398230088495575,
21
+ "grad_norm": 6.223922252655029,
22
+ "learning_rate": 7.600000000000001e-06,
23
+ "loss": 2.1224,
24
  "step": 20
25
  },
26
  {
27
+ "epoch": 0.5309734513274337,
28
+ "grad_norm": 6.171682357788086,
29
+ "learning_rate": 1.16e-05,
30
+ "loss": 1.859,
31
  "step": 30
32
  },
33
  {
34
+ "epoch": 0.7079646017699115,
35
+ "grad_norm": 4.256378173828125,
36
+ "learning_rate": 1.5600000000000003e-05,
37
+ "loss": 1.6122,
38
  "step": 40
39
  },
40
  {
41
+ "epoch": 0.8849557522123894,
42
+ "grad_norm": 2.6931450366973877,
43
+ "learning_rate": 1.9600000000000002e-05,
44
+ "loss": 1.2818,
45
  "step": 50
46
  },
47
  {
48
+ "epoch": 1.0530973451327434,
49
+ "grad_norm": 2.7361302375793457,
50
+ "learning_rate": 1.923404255319149e-05,
51
+ "loss": 1.1358,
52
  "step": 60
53
  },
54
  {
55
+ "epoch": 1.2300884955752212,
56
+ "grad_norm": 2.331388235092163,
57
+ "learning_rate": 1.8382978723404257e-05,
58
+ "loss": 0.8579,
59
  "step": 70
60
  },
61
  {
62
+ "epoch": 1.407079646017699,
63
+ "grad_norm": 2.436121702194214,
64
+ "learning_rate": 1.7531914893617024e-05,
65
+ "loss": 0.8232,
66
  "step": 80
67
  },
68
  {
69
+ "epoch": 1.584070796460177,
70
+ "grad_norm": 2.7200984954833984,
71
+ "learning_rate": 1.6680851063829788e-05,
72
+ "loss": 0.7198,
73
  "step": 90
74
  },
75
  {
76
+ "epoch": 1.7610619469026547,
77
+ "grad_norm": 2.8423922061920166,
78
+ "learning_rate": 1.5829787234042555e-05,
79
+ "loss": 0.7851,
80
  "step": 100
81
  },
82
  {
83
+ "epoch": 1.9380530973451329,
84
+ "grad_norm": 2.6434552669525146,
85
+ "learning_rate": 1.497872340425532e-05,
86
+ "loss": 0.6815,
87
  "step": 110
88
  },
89
  {
90
+ "epoch": 2.106194690265487,
91
+ "grad_norm": 2.050658702850342,
92
+ "learning_rate": 1.4127659574468087e-05,
93
+ "loss": 0.6848,
94
  "step": 120
95
  },
96
  {
97
+ "epoch": 2.2831858407079646,
98
+ "grad_norm": 2.302018642425537,
99
+ "learning_rate": 1.3276595744680851e-05,
100
+ "loss": 0.6245,
101
  "step": 130
102
  },
103
  {
104
+ "epoch": 2.4601769911504423,
105
+ "grad_norm": 1.7379809617996216,
106
+ "learning_rate": 1.2425531914893618e-05,
107
+ "loss": 0.5232,
108
  "step": 140
109
+ },
110
+ {
111
+ "epoch": 2.6371681415929205,
112
+ "grad_norm": 2.3433845043182373,
113
+ "learning_rate": 1.1574468085106382e-05,
114
+ "loss": 0.5672,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 2.814159292035398,
119
+ "grad_norm": 1.49757981300354,
120
+ "learning_rate": 1.072340425531915e-05,
121
+ "loss": 0.5239,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 2.991150442477876,
126
+ "grad_norm": 1.7192789316177368,
127
+ "learning_rate": 9.872340425531915e-06,
128
+ "loss": 0.5281,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 3.15929203539823,
133
+ "grad_norm": 2.373436689376831,
134
+ "learning_rate": 9.021276595744681e-06,
135
+ "loss": 0.5514,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 3.336283185840708,
140
+ "grad_norm": 1.7503447532653809,
141
+ "learning_rate": 8.170212765957447e-06,
142
+ "loss": 0.5375,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 3.5132743362831858,
147
+ "grad_norm": 2.090620994567871,
148
+ "learning_rate": 7.3191489361702125e-06,
149
+ "loss": 0.4832,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 3.5132743362831858,
154
+ "eval_loss": 0.3311998248100281,
155
+ "eval_runtime": 1.0961,
156
+ "eval_samples_per_second": 183.37,
157
+ "eval_steps_per_second": 11.86,
158
+ "step": 200
159
  }
160
  ],
161
  "logging_steps": 10,
162
+ "max_steps": 285,
163
  "num_input_tokens_seen": 0,
164
  "num_train_epochs": 5,
165
  "save_steps": 200,
 
170
  "should_evaluate": false,
171
  "should_log": false,
172
  "should_save": true,
173
+ "should_training_stop": false
174
  },
175
  "attributes": {}
176
  }
177
  },
178
+ "total_flos": 347226398619648.0,
179
+ "train_batch_size": 16,
180
  "trial_name": null,
181
  "trial_params": null
182
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b90e6aa06236f48b661290a19574ddab20d0c2f55e9cf092b4679ad63e7ef9ed
3
  size 5969
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e5d4dca9aabec0a018af541187f9fd9b3d5683e5ee69fe5176f777c973dc1ae
3
  size 5969