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 250422888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2520aec9764e66193a676bc33b56a99f6fbbf2322cbd8c949e3278d867b04cfa
|
3 |
size 250422888
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 126034975
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5dd4534c5215280f4a0ceedfc6153c149d6e2afc828495eeaff5df24d986eed1
|
3 |
size 126034975
|
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 sha256:18cf9062fa6a5bbd7c902d1fd07dd41ed87a54ad22f631cb63cda8d9a19f934a
|
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:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
|
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": 3.
|
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": 2.752,
|
86 |
"eval_steps_per_second": 0.176,
|
87 |
"step": 1200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
88 |
}
|
89 |
],
|
90 |
"logging_steps": 200,
|
91 |
"max_steps": 2232,
|
92 |
"num_train_epochs": 6,
|
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": 3.763440860215054,
|
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": 2.752,
|
86 |
"eval_steps_per_second": 0.176,
|
87 |
"step": 1200
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 3.76,
|
91 |
+
"learning_rate": 0.0002,
|
92 |
+
"loss": 0.0333,
|
93 |
+
"step": 1400
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 3.76,
|
97 |
+
"eval_runtime": 113.6577,
|
98 |
+
"eval_samples_per_second": 2.754,
|
99 |
+
"eval_steps_per_second": 0.176,
|
100 |
+
"step": 1400
|
101 |
}
|
102 |
],
|
103 |
"logging_steps": 200,
|
104 |
"max_steps": 2232,
|
105 |
"num_train_epochs": 6,
|
106 |
"save_steps": 200,
|
107 |
+
"total_flos": 6.670019537750016e+17,
|
108 |
"trial_name": null,
|
109 |
"trial_params": null
|
110 |
}
|