Training in progress, step 300, 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 sha256:2e6cb7b4410cc9cb0084c7612cd4022f1deadf4ce55184f92fad73533c9e1d83
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d873e36c2fa59d6fa81c53bb037fa037211b5695b7a1ba48627b95393c5339a8
|
3 |
+
size 21689885
|
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 sha256:4593038e9fdb437086616d5c111b9636ca11131f8522c47b7dac4f9725e19849
|
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:aa5aed090b001ddf62e969f8c3bdc8dc6e8972eaa9b18bd7770ed94cd8aac3ac
|
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": 0.
|
5 |
"eval_steps": 100,
|
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": 1.776,
|
34 |
"eval_steps_per_second": 0.222,
|
35 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
}
|
37 |
],
|
38 |
"logging_steps": 100,
|
39 |
-
"max_steps":
|
40 |
"num_train_epochs": 3,
|
41 |
"save_steps": 100,
|
42 |
-
"total_flos":
|
43 |
"trial_name": null,
|
44 |
"trial_params": null
|
45 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.13333333333333333,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 300,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
33 |
"eval_samples_per_second": 1.776,
|
34 |
"eval_steps_per_second": 0.222,
|
35 |
"step": 200
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 0.13,
|
39 |
+
"learning_rate": 0.0001,
|
40 |
+
"loss": 0.6207,
|
41 |
+
"step": 300
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.13,
|
45 |
+
"eval_runtime": 1405.0607,
|
46 |
+
"eval_samples_per_second": 1.779,
|
47 |
+
"eval_steps_per_second": 0.223,
|
48 |
+
"step": 300
|
49 |
}
|
50 |
],
|
51 |
"logging_steps": 100,
|
52 |
+
"max_steps": 6750,
|
53 |
"num_train_epochs": 3,
|
54 |
"save_steps": 100,
|
55 |
+
"total_flos": 7.68217505071104e+16,
|
56 |
"trial_name": null,
|
57 |
"trial_params": null
|
58 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4027
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc879f829e293a0970e4937e200624ca05a1bbcda40ccf332847f1be93ea7fb
|
3 |
size 4027
|