Training in progress, step 3000
Browse files- 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 +39 -3
- pytorch_model.bin +1 -1
- runs/May24_14-02-57_8e3a7392af54/events.out.tfevents.1684937027.8e3a7392af54.8284.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1987250795
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5db93d5bbd8ee27e2c605f26462c67689729477710806611d40989d1ddbb37ce
|
3 |
size 1987250795
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 996026489
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11df0d0c28ede32fdd87d0e229340412effcbdcc37f4f2fdafd317639cb64c01
|
3 |
size 996026489
|
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:b5af12890d72958474f59e2a6e38aefa8b12d58cc605376a65f0760cdf419671
|
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 sha256:0b7708e7360ae5d9dfbc21f14bae0f24f4e0ee89da5d58b4c05796253aac585a
|
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 sha256:025d4a6a1771d5d78df663db14260a7e4dac96d458cc7cf3490ace1f7cc857e7
|
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":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -78,11 +78,47 @@
|
|
78 |
"eval_samples_per_second": 2.491,
|
79 |
"eval_steps_per_second": 0.317,
|
80 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
81 |
}
|
82 |
],
|
83 |
"max_steps": 11700,
|
84 |
"num_train_epochs": 300,
|
85 |
-
"total_flos":
|
86 |
"trial_name": null,
|
87 |
"trial_params": null
|
88 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 76.92307692307692,
|
5 |
+
"global_step": 3000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
78 |
"eval_samples_per_second": 2.491,
|
79 |
"eval_steps_per_second": 0.317,
|
80 |
"step": 2000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 64.1,
|
84 |
+
"learning_rate": 4.7448453608247423e-05,
|
85 |
+
"loss": 0.0266,
|
86 |
+
"step": 2500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 64.1,
|
90 |
+
"eval_bleu": 96.1601,
|
91 |
+
"eval_em": 0.5516,
|
92 |
+
"eval_gen_len": 80.3981,
|
93 |
+
"eval_loss": 0.21729224920272827,
|
94 |
+
"eval_rm": 0.6211,
|
95 |
+
"eval_runtime": 165.3475,
|
96 |
+
"eval_samples_per_second": 2.522,
|
97 |
+
"eval_steps_per_second": 0.321,
|
98 |
+
"step": 2500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 76.92,
|
102 |
+
"learning_rate": 4.487113402061856e-05,
|
103 |
+
"loss": 0.0191,
|
104 |
+
"step": 3000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 76.92,
|
108 |
+
"eval_bleu": 96.1309,
|
109 |
+
"eval_em": 0.5444,
|
110 |
+
"eval_gen_len": 81.693,
|
111 |
+
"eval_loss": 0.22468438744544983,
|
112 |
+
"eval_rm": 0.6427,
|
113 |
+
"eval_runtime": 164.8881,
|
114 |
+
"eval_samples_per_second": 2.529,
|
115 |
+
"eval_steps_per_second": 0.321,
|
116 |
+
"step": 3000
|
117 |
}
|
118 |
],
|
119 |
"max_steps": 11700,
|
120 |
"num_train_epochs": 300,
|
121 |
+
"total_flos": 3282494931353088.0,
|
122 |
"trial_name": null,
|
123 |
"trial_params": null
|
124 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 996026489
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11df0d0c28ede32fdd87d0e229340412effcbdcc37f4f2fdafd317639cb64c01
|
3 |
size 996026489
|
runs/May24_14-02-57_8e3a7392af54/events.out.tfevents.1684937027.8e3a7392af54.8284.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9973c2a1b2f99e71423aa797e1b9e0975af9a4af0dcd05a62246b097704d3983
|
3 |
+
size 11071
|