Training in progress, step 9, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 83945296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5ca72ec40cc49109df24d3f72d49abe18219def3591abf9dd3fb4e7a706efae
|
3 |
size 83945296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43122580
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cd57febc71d8d2282a68c586802583647f6031c7606028fa0980ff55d1e4aaa
|
3 |
size 43122580
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81feec53929608a3d2b539f66e29270211cb35072ffa9c1bcebaa955f7bdc514
|
3 |
size 14244
|
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 sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
|
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": 3,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -73,6 +73,35 @@
|
|
73 |
"eval_samples_per_second": 28.875,
|
74 |
"eval_steps_per_second": 14.437,
|
75 |
"step": 6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
76 |
}
|
77 |
],
|
78 |
"logging_steps": 1,
|
@@ -92,7 +121,7 @@
|
|
92 |
"attributes": {}
|
93 |
}
|
94 |
},
|
95 |
-
"total_flos":
|
96 |
"train_batch_size": 2,
|
97 |
"trial_name": null,
|
98 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7058823529411765,
|
5 |
"eval_steps": 3,
|
6 |
+
"global_step": 9,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
73 |
"eval_samples_per_second": 28.875,
|
74 |
"eval_steps_per_second": 14.437,
|
75 |
"step": 6
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.5490196078431373,
|
79 |
+
"grad_norm": 29.685199737548828,
|
80 |
+
"learning_rate": 0.00014,
|
81 |
+
"loss": 1.3948,
|
82 |
+
"step": 7
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.6274509803921569,
|
86 |
+
"grad_norm": 14.1198148727417,
|
87 |
+
"learning_rate": 0.00016,
|
88 |
+
"loss": 0.8903,
|
89 |
+
"step": 8
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.7058823529411765,
|
93 |
+
"grad_norm": 13.525802612304688,
|
94 |
+
"learning_rate": 0.00018,
|
95 |
+
"loss": 0.5522,
|
96 |
+
"step": 9
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 0.7058823529411765,
|
100 |
+
"eval_loss": 0.24269229173660278,
|
101 |
+
"eval_runtime": 0.2085,
|
102 |
+
"eval_samples_per_second": 28.773,
|
103 |
+
"eval_steps_per_second": 14.387,
|
104 |
+
"step": 9
|
105 |
}
|
106 |
],
|
107 |
"logging_steps": 1,
|
|
|
121 |
"attributes": {}
|
122 |
}
|
123 |
},
|
124 |
+
"total_flos": 1621219552002048.0,
|
125 |
"train_batch_size": 2,
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|