Training in progress, step 12000
Browse files- config.json +1 -1
- last-checkpoint/config.json +1 -1
- last-checkpoint/generation_config.json +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +51 -3
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- runs/May11_01-55-45_3f2db86f76b4/1683771189.4238312/events.out.tfevents.1683771189.3f2db86f76b4.1020.1 +3 -0
- runs/May11_01-55-45_3f2db86f76b4/events.out.tfevents.1683771189.3f2db86f76b4.1020.0 +3 -0
- training_args.bin +1 -1
config.json
CHANGED
@@ -31,7 +31,7 @@
|
|
31 |
"pad_token_id": 1,
|
32 |
"scale_embedding": true,
|
33 |
"torch_dtype": "float32",
|
34 |
-
"transformers_version": "4.28.
|
35 |
"use_cache": true,
|
36 |
"vocab_size": 128112
|
37 |
}
|
|
|
31 |
"pad_token_id": 1,
|
32 |
"scale_embedding": true,
|
33 |
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.28.0",
|
35 |
"use_cache": true,
|
36 |
"vocab_size": 128112
|
37 |
}
|
last-checkpoint/config.json
CHANGED
@@ -31,7 +31,7 @@
|
|
31 |
"pad_token_id": 1,
|
32 |
"scale_embedding": true,
|
33 |
"torch_dtype": "float32",
|
34 |
-
"transformers_version": "4.28.
|
35 |
"use_cache": true,
|
36 |
"vocab_size": 128112
|
37 |
}
|
|
|
31 |
"pad_token_id": 1,
|
32 |
"scale_embedding": true,
|
33 |
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.28.0",
|
35 |
"use_cache": true,
|
36 |
"vocab_size": 128112
|
37 |
}
|
last-checkpoint/generation_config.json
CHANGED
@@ -6,5 +6,5 @@
|
|
6 |
"max_length": 200,
|
7 |
"num_beams": 5,
|
8 |
"pad_token_id": 1,
|
9 |
-
"transformers_version": "4.28.
|
10 |
}
|
|
|
6 |
"max_length": 200,
|
7 |
"num_beams": 5,
|
8 |
"pad_token_id": 1,
|
9 |
+
"transformers_version": "4.28.0"
|
10 |
}
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3871543575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d8ba0729e30b9e5881d5caf971c412cd008a797ec6df264f9ce2ab2dc676fe5
|
3 |
size 3871543575
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d058b3df03b01ceeb1e8e16160c317d335c85329170d0defffb0885d4b38dba
|
3 |
size 1944201353
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a51646c5ca5ad6b2ed000ef8068a62b9fc23eb4d20a88c1d7e7d6d9bc724c2b
|
3 |
size 14575
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5d8c186c458ec7fc62528255f98794d112763525bca0fe822708873efed374e
|
3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6372f050fec8b9f728b07360e9c0cfeab517903b038f122fa81a78a1a0d2f1aa
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -102,11 +102,59 @@
|
|
102 |
"learning_rate": 6.055512651614955e-07,
|
103 |
"loss": 1.8569,
|
104 |
"step": 8000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
105 |
}
|
106 |
],
|
107 |
"max_steps": 943410,
|
108 |
"num_train_epochs": 10,
|
109 |
-
"total_flos":
|
110 |
"trial_name": null,
|
111 |
"trial_params": null
|
112 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.12719814290711356,
|
5 |
+
"global_step": 12000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
102 |
"learning_rate": 6.055512651614955e-07,
|
103 |
"loss": 1.8569,
|
104 |
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.09,
|
108 |
+
"learning_rate": 6.433319705022791e-07,
|
109 |
+
"loss": 1.8883,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.1,
|
114 |
+
"learning_rate": 6.811883886794167e-07,
|
115 |
+
"loss": 1.8776,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.1,
|
120 |
+
"learning_rate": 7.190448068565545e-07,
|
121 |
+
"loss": 1.8876,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.11,
|
126 |
+
"learning_rate": 7.569012250336922e-07,
|
127 |
+
"loss": 1.8702,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.11,
|
132 |
+
"learning_rate": 7.947576432108301e-07,
|
133 |
+
"loss": 1.8573,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.12,
|
138 |
+
"learning_rate": 8.325383485516135e-07,
|
139 |
+
"loss": 1.857,
|
140 |
+
"step": 11000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.12,
|
144 |
+
"learning_rate": 8.703947667287513e-07,
|
145 |
+
"loss": 1.8565,
|
146 |
+
"step": 11500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.13,
|
150 |
+
"learning_rate": 9.08251184905889e-07,
|
151 |
+
"loss": 1.831,
|
152 |
+
"step": 12000
|
153 |
}
|
154 |
],
|
155 |
"max_steps": 943410,
|
156 |
"num_train_epochs": 10,
|
157 |
+
"total_flos": 6830201558089728.0,
|
158 |
"trial_name": null,
|
159 |
"trial_params": null
|
160 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3771
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6bf4419503f7813df66a605111bbb0f133a163bc1b9d161b51462af15dbefd1
|
3 |
size 3771
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d058b3df03b01ceeb1e8e16160c317d335c85329170d0defffb0885d4b38dba
|
3 |
size 1944201353
|
runs/May11_01-55-45_3f2db86f76b4/1683771189.4238312/events.out.tfevents.1683771189.3f2db86f76b4.1020.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:562b6a87ac7dbbbafaf11b7c1b61d054b99ff80b51c8d633ba8cb6520b3f9b3f
|
3 |
+
size 6187
|
runs/May11_01-55-45_3f2db86f76b4/events.out.tfevents.1683771189.3f2db86f76b4.1020.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff0c68c70d670e76460ea9b6ca7664824eb2264c60f1be14fa7fdaa77c1fce1c
|
3 |
+
size 5720
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3771
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6bf4419503f7813df66a605111bbb0f133a163bc1b9d161b51462af15dbefd1
|
3 |
size 3771
|