ramdhanfirdaus commited on
Commit
4d3928e
1 Parent(s): f47fb76

Training in progress, step 1100, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39f6516da94d5ec8ddf27952ae1e02036c6e994addf157282d37278175a4e61f
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:074259398c315036a44af929ca38ebda5d87e484420b4ca7df775984005d0e84
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfd857b4edc7c1663e4c8cee17ed70f733c5beb934d25ffdd5f745c3879f26c1
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:108675afd3dfc8409d4b5347f8ed7d161c2f7f7f77850ebaf618e41ca9f06c6b
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56c7d9acd97a65ba6f52bddd9c1a7be0b5f95308e5fa05bcc7a62b6822eb6d6f
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf02797a956bbc09d23fc6a6c1f3c0b3a9c44933f60941f080cf8bb2f9d1331d
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13276f15dd2b6acc19b970176aa2db4ac9b58241843e72c89b50e3094e903b19
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
3
  size 627
last-checkpoint/tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
3
- size 14500471
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d81d9b2c9d9db79ea02c00d4c7e79bb77a718dc57ab01f5f3b1cd6649f08993
3
+ size 14500569
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.5222103595733643,
3
- "best_model_checkpoint": "./outputs/checkpoint-400",
4
- "epoch": 0.29143897996357016,
5
  "eval_steps": 100,
6
- "global_step": 400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -11,65 +11,163 @@
11
  {
12
  "epoch": 0.07,
13
  "learning_rate": 0.0002,
14
- "loss": 2.7406,
15
  "step": 100
16
  },
17
  {
18
  "epoch": 0.07,
19
- "eval_loss": 2.6424405574798584,
20
- "eval_runtime": 206.8728,
21
- "eval_samples_per_second": 30.328,
22
- "eval_steps_per_second": 3.795,
23
  "step": 100
24
  },
25
  {
26
  "epoch": 0.15,
27
  "learning_rate": 0.0002,
28
- "loss": 2.6056,
29
  "step": 200
30
  },
31
  {
32
  "epoch": 0.15,
33
- "eval_loss": 2.591430187225342,
34
- "eval_runtime": 206.9647,
35
- "eval_samples_per_second": 30.314,
36
- "eval_steps_per_second": 3.793,
37
  "step": 200
38
  },
39
  {
40
  "epoch": 0.22,
41
  "learning_rate": 0.0002,
42
- "loss": 2.5631,
43
  "step": 300
44
  },
45
  {
46
  "epoch": 0.22,
47
- "eval_loss": 2.5565075874328613,
48
- "eval_runtime": 206.6263,
49
- "eval_samples_per_second": 30.364,
50
- "eval_steps_per_second": 3.799,
51
  "step": 300
52
  },
53
  {
54
  "epoch": 0.29,
55
  "learning_rate": 0.0002,
56
- "loss": 2.5363,
57
  "step": 400
58
  },
59
  {
60
  "epoch": 0.29,
61
- "eval_loss": 2.5222103595733643,
62
- "eval_runtime": 234.7988,
63
- "eval_samples_per_second": 26.721,
64
- "eval_steps_per_second": 3.343,
65
  "step": 400
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66
  }
67
  ],
68
  "logging_steps": 100,
69
  "max_steps": 4116,
70
  "num_train_epochs": 3,
71
  "save_steps": 100,
72
- "total_flos": 1.167856193839104e+16,
73
  "trial_name": null,
74
  "trial_params": null
75
  }
 
1
  {
2
+ "best_metric": 2.360255479812622,
3
+ "best_model_checkpoint": "./outputs/checkpoint-1100",
4
+ "epoch": 0.8014571948998178,
5
  "eval_steps": 100,
6
+ "global_step": 1100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
11
  {
12
  "epoch": 0.07,
13
  "learning_rate": 0.0002,
14
+ "loss": 2.7399,
15
  "step": 100
16
  },
17
  {
18
  "epoch": 0.07,
19
+ "eval_loss": 2.6418099403381348,
20
+ "eval_runtime": 347.6157,
21
+ "eval_samples_per_second": 18.049,
22
+ "eval_steps_per_second": 2.258,
23
  "step": 100
24
  },
25
  {
26
  "epoch": 0.15,
27
  "learning_rate": 0.0002,
28
+ "loss": 2.6052,
29
  "step": 200
30
  },
31
  {
32
  "epoch": 0.15,
33
+ "eval_loss": 2.5918312072753906,
34
+ "eval_runtime": 333.731,
35
+ "eval_samples_per_second": 18.8,
36
+ "eval_steps_per_second": 2.352,
37
  "step": 200
38
  },
39
  {
40
  "epoch": 0.22,
41
  "learning_rate": 0.0002,
42
+ "loss": 2.5622,
43
  "step": 300
44
  },
45
  {
46
  "epoch": 0.22,
47
+ "eval_loss": 2.551574468612671,
48
+ "eval_runtime": 204.9306,
49
+ "eval_samples_per_second": 30.615,
50
+ "eval_steps_per_second": 3.831,
51
  "step": 300
52
  },
53
  {
54
  "epoch": 0.29,
55
  "learning_rate": 0.0002,
56
+ "loss": 2.5366,
57
  "step": 400
58
  },
59
  {
60
  "epoch": 0.29,
61
+ "eval_loss": 2.517575263977051,
62
+ "eval_runtime": 204.3925,
63
+ "eval_samples_per_second": 30.696,
64
+ "eval_steps_per_second": 3.841,
65
  "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.36,
69
+ "learning_rate": 0.0002,
70
+ "loss": 2.4946,
71
+ "step": 500
72
+ },
73
+ {
74
+ "epoch": 0.36,
75
+ "eval_loss": 2.4924821853637695,
76
+ "eval_runtime": 204.4035,
77
+ "eval_samples_per_second": 30.694,
78
+ "eval_steps_per_second": 3.84,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.44,
83
+ "learning_rate": 0.0002,
84
+ "loss": 2.4686,
85
+ "step": 600
86
+ },
87
+ {
88
+ "epoch": 0.44,
89
+ "eval_loss": 2.4666266441345215,
90
+ "eval_runtime": 207.3453,
91
+ "eval_samples_per_second": 30.259,
92
+ "eval_steps_per_second": 3.786,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 0.51,
97
+ "learning_rate": 0.0002,
98
+ "loss": 2.4503,
99
+ "step": 700
100
+ },
101
+ {
102
+ "epoch": 0.51,
103
+ "eval_loss": 2.4440107345581055,
104
+ "eval_runtime": 205.5485,
105
+ "eval_samples_per_second": 30.523,
106
+ "eval_steps_per_second": 3.819,
107
+ "step": 700
108
+ },
109
+ {
110
+ "epoch": 0.58,
111
+ "learning_rate": 0.0002,
112
+ "loss": 2.4271,
113
+ "step": 800
114
+ },
115
+ {
116
+ "epoch": 0.58,
117
+ "eval_loss": 2.4231719970703125,
118
+ "eval_runtime": 204.3763,
119
+ "eval_samples_per_second": 30.698,
120
+ "eval_steps_per_second": 3.841,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 0.66,
125
+ "learning_rate": 0.0002,
126
+ "loss": 2.3911,
127
+ "step": 900
128
+ },
129
+ {
130
+ "epoch": 0.66,
131
+ "eval_loss": 2.401764154434204,
132
+ "eval_runtime": 204.7042,
133
+ "eval_samples_per_second": 30.649,
134
+ "eval_steps_per_second": 3.835,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.73,
139
+ "learning_rate": 0.0002,
140
+ "loss": 2.3881,
141
+ "step": 1000
142
+ },
143
+ {
144
+ "epoch": 0.73,
145
+ "eval_loss": 2.3822004795074463,
146
+ "eval_runtime": 204.6048,
147
+ "eval_samples_per_second": 30.664,
148
+ "eval_steps_per_second": 3.837,
149
+ "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.8,
153
+ "learning_rate": 0.0002,
154
+ "loss": 2.3811,
155
+ "step": 1100
156
+ },
157
+ {
158
+ "epoch": 0.8,
159
+ "eval_loss": 2.360255479812622,
160
+ "eval_runtime": 283.1616,
161
+ "eval_samples_per_second": 22.157,
162
+ "eval_steps_per_second": 2.772,
163
+ "step": 1100
164
  }
165
  ],
166
  "logging_steps": 100,
167
  "max_steps": 4116,
168
  "num_train_epochs": 3,
169
  "save_steps": 100,
170
+ "total_flos": 3.208363367473152e+16,
171
  "trial_name": null,
172
  "trial_params": null
173
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6bbb4e93666410d7a938dd3851f7194e97be075889249a5ac42f4cb3cfacdd3
3
  size 4219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faed5845c6fa602a9a75d6d7a3c4d37017580998e72f3835a07c1c95f579635b
3
  size 4219