Training in progress, step 600, 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 sha256:0e20e933cc061703253f661e0f6bd388aa33a50d5dcecd9cf3b472c694dd09bc
|
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 7601989
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b4d5f4ee881bff263950e2dd32fd230d2ea00dad59ff283198e9206f4238ab1
|
3 |
size 7601989
|
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:fabb06cac3fcdeaa6b35d148d1969e126efe43d12cb30a04536381719d9de872
|
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:a71c14414e2ba5216437cae72b785c45cb16736956f3e9e068425fabd7f32a90
|
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": 200,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -33,13 +33,26 @@
|
|
33 |
"eval_samples_per_second": 2.216,
|
34 |
"eval_steps_per_second": 0.278,
|
35 |
"step": 400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
}
|
37 |
],
|
38 |
"logging_steps": 200,
|
39 |
"max_steps": 1593,
|
40 |
"num_train_epochs": 3,
|
41 |
"save_steps": 200,
|
42 |
-
"total_flos":
|
43 |
"trial_name": null,
|
44 |
"trial_params": null
|
45 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.1292346298619824,
|
5 |
"eval_steps": 200,
|
6 |
+
"global_step": 600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
33 |
"eval_samples_per_second": 2.216,
|
34 |
"eval_steps_per_second": 0.278,
|
35 |
"step": 400
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 1.13,
|
39 |
+
"learning_rate": 2e-05,
|
40 |
+
"loss": 0.6912,
|
41 |
+
"step": 600
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 1.13,
|
45 |
+
"eval_runtime": 1010.7698,
|
46 |
+
"eval_samples_per_second": 2.226,
|
47 |
+
"eval_steps_per_second": 0.279,
|
48 |
+
"step": 600
|
49 |
}
|
50 |
],
|
51 |
"logging_steps": 200,
|
52 |
"max_steps": 1593,
|
53 |
"num_train_epochs": 3,
|
54 |
"save_steps": 200,
|
55 |
+
"total_flos": 1.3399863499338547e+17,
|
56 |
"trial_name": null,
|
57 |
"trial_params": null
|
58 |
}
|