Training in progress, step 20000
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 +19 -3
- nbest_predictions.json +0 -0
- predictions.json +0 -0
- pytorch_model.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 943333453
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb94510585a257f26748b3563d1ac24bf7b6dffebf090a50785a4066c9f51aff
|
3 |
size 943333453
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 471708325
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b85cbaf1f19bee050d6730e73ebf9b86b0780dc26e6d96aaeeb9ee9e5f1f501a
|
3 |
size 471708325
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9949a52e3e65d0f2cec3a08459660e9711e9c1359d9f08ac2c07545128408d7
|
3 |
size 14503
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21aa4819edee177e45714c40c36966f6d1435e96960cbe524e7640fd0aede9b3
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03db6b1df6a961019a71debb179f7739d4e74f092cdcb8c4d9c2a77019355bb7
|
3 |
size 623
|
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,
|
@@ -54,11 +54,27 @@
|
|
54 |
"eval_samples_per_second": 7.506,
|
55 |
"eval_steps_per_second": 3.753,
|
56 |
"step": 15000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
}
|
58 |
],
|
59 |
"max_steps": 92088,
|
60 |
"num_train_epochs": 3,
|
61 |
-
"total_flos":
|
62 |
"trial_name": null,
|
63 |
"trial_params": null
|
64 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6515506906437321,
|
5 |
+
"global_step": 20000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
54 |
"eval_samples_per_second": 7.506,
|
55 |
"eval_steps_per_second": 3.753,
|
56 |
"step": 15000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.65,
|
60 |
+
"learning_rate": 2.3488728173051864e-05,
|
61 |
+
"loss": 0.9992,
|
62 |
+
"step": 20000
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.65,
|
66 |
+
"eval_exact_match": 81.09024517475221,
|
67 |
+
"eval_f1": 85.49992934663945,
|
68 |
+
"eval_loss": 0.8323877453804016,
|
69 |
+
"eval_runtime": 1541.3611,
|
70 |
+
"eval_samples_per_second": 7.469,
|
71 |
+
"eval_steps_per_second": 3.735,
|
72 |
+
"step": 20000
|
73 |
}
|
74 |
],
|
75 |
"max_steps": 92088,
|
76 |
"num_train_epochs": 3,
|
77 |
+
"total_flos": 4.412940582912e+16,
|
78 |
"trial_name": null,
|
79 |
"trial_params": null
|
80 |
}
|
nbest_predictions.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
predictions.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 471708325
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b85cbaf1f19bee050d6730e73ebf9b86b0780dc26e6d96aaeeb9ee9e5f1f501a
|
3 |
size 471708325
|