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 9444296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51cb3af7f12d93b82e14f620097e75b7051c2f53f32b194f549347dc112ca906
|
3 |
size 9444296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 18902665
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c92f7f30fc1a44edb3f7fd8e9ac7797d23e6025081b95a0976cf1d49452e0ac
|
3 |
size 18902665
|
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:cbe94f3c099526d2d0ffee989f862b44e24dbf9220e583fff14c71db11059188
|
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:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
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,
|
@@ -35,6 +35,20 @@
|
|
35 |
"eval_samples_per_second": 15.546,
|
36 |
"eval_steps_per_second": 1.95,
|
37 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
}
|
39 |
],
|
40 |
"logging_steps": 100,
|
@@ -42,7 +56,7 @@
|
|
42 |
"num_input_tokens_seen": 0,
|
43 |
"num_train_epochs": 3,
|
44 |
"save_steps": 100,
|
45 |
-
"total_flos": 1.
|
46 |
"trial_name": null,
|
47 |
"trial_params": null
|
48 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.5133259296417236,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-300",
|
4 |
+
"epoch": 0.4,
|
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,
|
|
|
35 |
"eval_samples_per_second": 15.546,
|
36 |
"eval_steps_per_second": 1.95,
|
37 |
"step": 200
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.4,
|
41 |
+
"learning_rate": 0.0002,
|
42 |
+
"loss": 1.2756,
|
43 |
+
"step": 300
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 0.4,
|
47 |
+
"eval_loss": 1.5133259296417236,
|
48 |
+
"eval_runtime": 93.2652,
|
49 |
+
"eval_samples_per_second": 15.558,
|
50 |
+
"eval_steps_per_second": 1.951,
|
51 |
+
"step": 300
|
52 |
}
|
53 |
],
|
54 |
"logging_steps": 100,
|
|
|
56 |
"num_input_tokens_seen": 0,
|
57 |
"num_train_epochs": 3,
|
58 |
"save_steps": 100,
|
59 |
+
"total_flos": 1.753797686280192e+16,
|
60 |
"trial_name": null,
|
61 |
"trial_params": null
|
62 |
}
|