Training in progress, step 1400, 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 14708920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:421b58c0135a0e18a6ff6b5815f3a23ac535f59759a72ab8a1dabf73a1a289cf
|
3 |
size 14708920
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 8183389
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c693705626c211fa3c52ebda875cc4c999b1bea4ec15d2c92c58094728db03cc
|
3 |
size 8183389
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf87ead242566c0ac43f232e32f3a24e603320cd5f69a84ac6b37520d1d5327f
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12afbd9f2479d7d4984f71fbb47f668900712a14e64e2137d59a701704302095
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 2.
|
5 |
"eval_steps": 200,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -85,13 +85,26 @@
|
|
85 |
"eval_samples_per_second": 2.231,
|
86 |
"eval_steps_per_second": 0.28,
|
87 |
"step": 1200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
88 |
}
|
89 |
],
|
90 |
"logging_steps": 200,
|
91 |
"max_steps": 1593,
|
92 |
"num_train_epochs": 3,
|
93 |
"save_steps": 200,
|
94 |
-
"total_flos":
|
95 |
"trial_name": null,
|
96 |
"trial_params": null
|
97 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.635508155583438,
|
5 |
"eval_steps": 200,
|
6 |
+
"global_step": 1400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
85 |
"eval_samples_per_second": 2.231,
|
86 |
"eval_steps_per_second": 0.28,
|
87 |
"step": 1200
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 2.64,
|
91 |
+
"learning_rate": 2e-05,
|
92 |
+
"loss": 0.6441,
|
93 |
+
"step": 1400
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 2.64,
|
97 |
+
"eval_runtime": 1013.4446,
|
98 |
+
"eval_samples_per_second": 2.22,
|
99 |
+
"eval_steps_per_second": 0.278,
|
100 |
+
"step": 1400
|
101 |
}
|
102 |
],
|
103 |
"logging_steps": 200,
|
104 |
"max_steps": 1593,
|
105 |
"num_train_epochs": 3,
|
106 |
"save_steps": 200,
|
107 |
+
"total_flos": 3.1266968615347814e+17,
|
108 |
"trial_name": null,
|
109 |
"trial_params": null
|
110 |
}
|