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 12609312
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97a56c40d1361e0080a777077be065c9f394e125d4e54629cd859e2614a8256f
|
3 |
size 12609312
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6615034
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b565350ce79fbb4ed52a54825cafe8ea337c46575d8bb6a09e49763086dfd597
|
3 |
size 6615034
|
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 sha256:519f25b43551ebd208fc8e91efe3efb9ed6b1ef480ba8fcb9b6b0c22698c9e5b
|
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": 94.75,
|
74 |
"eval_steps_per_second": 47.375,
|
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": 0.0008361592418822874,
|
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": 94.75,
|
74 |
"eval_steps_per_second": 47.375,
|
75 |
"step": 6
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.0006503460770195569,
|
79 |
+
"grad_norm": 61.19314956665039,
|
80 |
+
"learning_rate": 0.00014,
|
81 |
+
"loss": 13.2718,
|
82 |
+
"step": 7
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.0007432526594509221,
|
86 |
+
"grad_norm": 49.314762115478516,
|
87 |
+
"learning_rate": 0.00016,
|
88 |
+
"loss": 13.1002,
|
89 |
+
"step": 8
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.0008361592418822874,
|
93 |
+
"grad_norm": 53.37507247924805,
|
94 |
+
"learning_rate": 0.00018,
|
95 |
+
"loss": 13.5421,
|
96 |
+
"step": 9
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 0.0008361592418822874,
|
100 |
+
"eval_loss": 3.413646936416626,
|
101 |
+
"eval_runtime": 48.3954,
|
102 |
+
"eval_samples_per_second": 93.645,
|
103 |
+
"eval_steps_per_second": 46.823,
|
104 |
+
"step": 9
|
105 |
}
|
106 |
],
|
107 |
"logging_steps": 1,
|
|
|
121 |
"attributes": {}
|
122 |
}
|
123 |
},
|
124 |
+
"total_flos": 83342137491456.0,
|
125 |
"train_batch_size": 2,
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|