sirr
commited on
Commit
·
fd03e8a
1
Parent(s):
75e21f3
Training in progress, step 200, 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 40036040
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3b3dab902f654a25e94e3ae343233a6f70542e70de8175dda45b60e2be64cde
|
3 |
size 40036040
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 20523679
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04c3113c32b4000e515b8d0f088a79febc7bae6b99372543b69f4d5d6af8d9ee
|
3 |
size 20523679
|
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:f9f2d7e8bf2ed7515ccab34b515d3863906e4d6e9f597722937aaa40e93ad4ba
|
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:f8078c9f184228e33330b036411337dd5e5bec4381d5a61fcfdc2d0a6a6021bc
|
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":
|
5 |
"eval_steps": 25,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -98,13 +98,26 @@
|
|
98 |
"eval_samples_per_second": 1.846,
|
99 |
"eval_steps_per_second": 0.157,
|
100 |
"step": 175
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
101 |
}
|
102 |
],
|
103 |
"logging_steps": 25,
|
104 |
"max_steps": 200,
|
105 |
"num_train_epochs": 2,
|
106 |
"save_steps": 25,
|
107 |
-
"total_flos":
|
108 |
"trial_name": null,
|
109 |
"trial_params": null
|
110 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
98 |
"eval_samples_per_second": 1.846,
|
99 |
"eval_steps_per_second": 0.157,
|
100 |
"step": 175
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 2.0,
|
104 |
+
"learning_rate": 0.0001,
|
105 |
+
"loss": 0.5471,
|
106 |
+
"step": 200
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 2.0,
|
110 |
+
"eval_runtime": 216.7005,
|
111 |
+
"eval_samples_per_second": 1.846,
|
112 |
+
"eval_steps_per_second": 0.157,
|
113 |
+
"step": 200
|
114 |
}
|
115 |
],
|
116 |
"logging_steps": 25,
|
117 |
"max_steps": 200,
|
118 |
"num_train_epochs": 2,
|
119 |
"save_steps": 25,
|
120 |
+
"total_flos": 3.32202164355072e+16,
|
121 |
"trial_name": null,
|
122 |
"trial_params": null
|
123 |
}
|