Training in progress, step 2000
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/tokenizer.json +1 -1
- last-checkpoint/trainer_state.json +40 -4
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- runs/May24_13-41-32_8e3a7392af54/1684936618.1342323/events.out.tfevents.1684936618.8e3a7392af54.2936.1 +3 -0
- runs/May24_13-41-32_8e3a7392af54/events.out.tfevents.1684936618.8e3a7392af54.2936.0 +3 -0
- runs/May24_14-02-57_8e3a7392af54/1684937027.34625/events.out.tfevents.1684937027.8e3a7392af54.8284.1 +3 -0
- runs/May24_14-02-57_8e3a7392af54/events.out.tfevents.1684937027.8e3a7392af54.8284.0 +3 -0
- tokenizer.json +1 -1
- training_args.bin +1 -1
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 sha256:706f00eb19f820fe319f7fafa5e70c41f6a9e1a7d166f8307a88018472cc1657
|
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:faf1f2b9424af846730ab18d00f63657ae804747565792e465df7cbcce97ff99
|
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:a60916cb59c8af4c3fd3f107d03f442d74a5f179944593d033585e1acab19ee4
|
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:b101589015f43511eb0eb50cc023fb256454216407517c39629d0bc69dd1c56c
|
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:abc9f4c211b246066019b67bda62d8798fabc65b9d4d90687512ceea2d93be15
|
3 |
size 627
|
last-checkpoint/tokenizer.json
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 512,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
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,
|
@@ -42,11 +42,47 @@
|
|
42 |
"eval_samples_per_second": 2.065,
|
43 |
"eval_steps_per_second": 0.263,
|
44 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
45 |
}
|
46 |
],
|
47 |
-
"max_steps":
|
48 |
"num_train_epochs": 300,
|
49 |
-
"total_flos":
|
50 |
"trial_name": null,
|
51 |
"trial_params": null
|
52 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 51.282051282051285,
|
5 |
+
"global_step": 2000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
42 |
"eval_samples_per_second": 2.065,
|
43 |
"eval_steps_per_second": 0.263,
|
44 |
"step": 1000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 38.46,
|
48 |
+
"learning_rate": 3.737500000000001e-05,
|
49 |
+
"loss": 0.0966,
|
50 |
+
"step": 1500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 38.46,
|
54 |
+
"eval_bleu": 95.4441,
|
55 |
+
"eval_em": 0.3669,
|
56 |
+
"eval_gen_len": 81.6475,
|
57 |
+
"eval_loss": 0.21956025063991547,
|
58 |
+
"eval_rm": 0.4484,
|
59 |
+
"eval_runtime": 168.3123,
|
60 |
+
"eval_samples_per_second": 2.478,
|
61 |
+
"eval_steps_per_second": 0.315,
|
62 |
+
"step": 1500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 51.28,
|
66 |
+
"learning_rate": 4.9875000000000006e-05,
|
67 |
+
"loss": 0.0406,
|
68 |
+
"step": 2000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 51.28,
|
72 |
+
"eval_bleu": 96.0687,
|
73 |
+
"eval_em": 0.5108,
|
74 |
+
"eval_gen_len": 80.777,
|
75 |
+
"eval_loss": 0.21358482539653778,
|
76 |
+
"eval_rm": 0.5947,
|
77 |
+
"eval_runtime": 167.4281,
|
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": 2482891695940608.0,
|
86 |
"trial_name": null,
|
87 |
"trial_params": null
|
88 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4155
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bb7cbf69764be856cace1d69d8021e6c2300e10ccc26fbc78c609f8368570b4
|
3 |
size 4155
|
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:faf1f2b9424af846730ab18d00f63657ae804747565792e465df7cbcce97ff99
|
3 |
size 996026489
|
runs/May24_13-41-32_8e3a7392af54/1684936618.1342323/events.out.tfevents.1684936618.8e3a7392af54.2936.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e23e80c2336e8305aa99b1c12e57436739f52bc63ab92a14b656d5260e5d1fe
|
3 |
+
size 6285
|
runs/May24_13-41-32_8e3a7392af54/events.out.tfevents.1684936618.8e3a7392af54.2936.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:545cb9a8e1f415d4c8c7a1797c5eaa18187dbebc88795fed0b0f4997de88d716
|
3 |
+
size 8595
|
runs/May24_14-02-57_8e3a7392af54/1684937027.34625/events.out.tfevents.1684937027.8e3a7392af54.8284.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2962706436f264e3725e42f9465d412f3857622e13aabef567c952efaa7493e2
|
3 |
+
size 6285
|
runs/May24_14-02-57_8e3a7392af54/events.out.tfevents.1684937027.8e3a7392af54.8284.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e3507793a2cbaef8e2d6f31609252db3b06a0dc159c914011f230c63ca7eed9
|
3 |
+
size 9833
|
tokenizer.json
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 512,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4155
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bb7cbf69764be856cace1d69d8021e6c2300e10ccc26fbc78c609f8368570b4
|
3 |
size 4155
|