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 161533192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe705acafba75bf98fd046d948c45d9f892f6b8308c7bdd1976c64fdd47df50f
|
3 |
size 161533192
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 82460660
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d317e7a14a175e3bdcf00728a4b55e7174b34343d758db0f3471df065314f451
|
3 |
size 82460660
|
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 sha256:971b3c8cf853f22869b90ddddf63ef0566b6ceb377f3b57b66478e5d06e3e51b
|
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 sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
|
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": 4.59,
|
74 |
"eval_steps_per_second": 4.59,
|
75 |
"step": 6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
76 |
}
|
77 |
],
|
78 |
"logging_steps": 1,
|
@@ -92,7 +121,7 @@
|
|
92 |
"attributes": {}
|
93 |
}
|
94 |
},
|
95 |
-
"total_flos":
|
96 |
"train_batch_size": 1,
|
97 |
"trial_name": null,
|
98 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0035436558716409093,
|
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": 4.59,
|
74 |
"eval_steps_per_second": 4.59,
|
75 |
"step": 6
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.002756176789054041,
|
79 |
+
"grad_norm": NaN,
|
80 |
+
"learning_rate": 0.00012,
|
81 |
+
"loss": 1.9327,
|
82 |
+
"step": 7
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.003149916330347475,
|
86 |
+
"grad_norm": 5.197524070739746,
|
87 |
+
"learning_rate": 0.00014,
|
88 |
+
"loss": 2.3621,
|
89 |
+
"step": 8
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.0035436558716409093,
|
93 |
+
"grad_norm": 3.2192602157592773,
|
94 |
+
"learning_rate": 0.00016,
|
95 |
+
"loss": 1.3753,
|
96 |
+
"step": 9
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 0.0035436558716409093,
|
100 |
+
"eval_loss": 1.492257833480835,
|
101 |
+
"eval_runtime": 116.5291,
|
102 |
+
"eval_samples_per_second": 4.591,
|
103 |
+
"eval_steps_per_second": 4.591,
|
104 |
+
"step": 9
|
105 |
}
|
106 |
],
|
107 |
"logging_steps": 1,
|
|
|
121 |
"attributes": {}
|
122 |
}
|
123 |
},
|
124 |
+
"total_flos": 6291348239941632.0,
|
125 |
"train_batch_size": 1,
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|