Training in progress, step 60, checkpoint
Browse files- last-checkpoint/model-00001-of-00003.safetensors +1 -1
- last-checkpoint/model-00002-of-00003.safetensors +1 -1
- last-checkpoint/model-00003-of-00003.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +25 -3
last-checkpoint/model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4943162336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f00e480b3e558fe8f7255f4c37c4cca65b3fec1321f324035dfc731b5ade8cbe
|
3 |
size 4943162336
|
last-checkpoint/model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999819336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d7d57272ebeca63fdd44907ab8ba3957fd906d2edb8c2fbffa5d2f1941d3e70
|
3 |
size 4999819336
|
last-checkpoint/model-00003-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4540516344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79b35d10d4b6ec1a2ee9715076c2048790fb6a243afa5656ccc247cb82217255
|
3 |
size 4540516344
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14710121812
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d5f57a7c091bd6563d43e3fe8ed5e4b85b200ce5b6caefca68da59ff6bfde0e
|
3 |
size 14710121812
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0038fb6f21ca3e81c3e1dfdbad93100e39e8e615b5fad9db02349c28cf41449e
|
3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f45ce61591188f6d757b7069c1b1c209c1709c8592fa9d63f48f22d8a29eddf
|
3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca9915dadbc42bf9335c9ddddb4bfdf5317e9867b7d547371a8e1a633499c3d5
|
3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31f7c5ddb0b28ad2aed8e01a65edd7968d02ddf7e6ec474ed5c5da54b3a7e8a6
|
3 |
size 15024
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3671bd7fce476af6c5d68b2346a8d63f3c9e317781066d2c00973b04663cf26
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 20,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -59,6 +59,28 @@
|
|
59 |
"eval_samples_per_second": 34.748,
|
60 |
"eval_steps_per_second": 4.352,
|
61 |
"step": 40
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
62 |
}
|
63 |
],
|
64 |
"logging_steps": 10,
|
@@ -78,7 +100,7 @@
|
|
78 |
"attributes": {}
|
79 |
}
|
80 |
},
|
81 |
-
"total_flos":
|
82 |
"train_batch_size": 2,
|
83 |
"trial_name": null,
|
84 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5714285714285714,
|
5 |
"eval_steps": 20,
|
6 |
+
"global_step": 60,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
59 |
"eval_samples_per_second": 34.748,
|
60 |
"eval_steps_per_second": 4.352,
|
61 |
"step": 40
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.47619047619047616,
|
65 |
+
"grad_norm": 7.34375,
|
66 |
+
"learning_rate": 0.00019939306773179497,
|
67 |
+
"loss": 7.4643,
|
68 |
+
"step": 50
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.5714285714285714,
|
72 |
+
"grad_norm": 13.375,
|
73 |
+
"learning_rate": 0.00019863613034027224,
|
74 |
+
"loss": 7.4183,
|
75 |
+
"step": 60
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.5714285714285714,
|
79 |
+
"eval_loss": 7.3631272315979,
|
80 |
+
"eval_runtime": 46.4427,
|
81 |
+
"eval_samples_per_second": 32.319,
|
82 |
+
"eval_steps_per_second": 4.048,
|
83 |
+
"step": 60
|
84 |
}
|
85 |
],
|
86 |
"logging_steps": 10,
|
|
|
100 |
"attributes": {}
|
101 |
}
|
102 |
},
|
103 |
+
"total_flos": 4.194038141524378e+16,
|
104 |
"train_batch_size": 2,
|
105 |
"trial_name": null,
|
106 |
"trial_params": null
|