Training in progress, epoch 3, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1447317080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fdf2d59e57fc4e587e94217f6fdb81da01f8c5944a532209e4e1c87a1208fc6
|
3 |
size 1447317080
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2894813242
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:068d45c4a9094167ca5b785f421ce65a9eced45e4c8d8be5074eacf100d3ec7b
|
3 |
size 2894813242
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de3eef1652b01db08dd46ec44854324e826d340084c89d03ced172fee01ac119
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "./opt_trained2/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -23,6 +23,14 @@
|
|
23 |
"eval_samples_per_second": 17.743,
|
24 |
"eval_steps_per_second": 4.436,
|
25 |
"step": 86
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
}
|
27 |
],
|
28 |
"logging_steps": 500,
|
@@ -42,7 +50,7 @@
|
|
42 |
"attributes": {}
|
43 |
}
|
44 |
},
|
45 |
-
"total_flos":
|
46 |
"train_batch_size": 8,
|
47 |
"trial_name": null,
|
48 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.5410714745521545,
|
3 |
+
"best_model_checkpoint": "./opt_trained2/checkpoint-129",
|
4 |
+
"epoch": 3.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 129,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
23 |
"eval_samples_per_second": 17.743,
|
24 |
"eval_steps_per_second": 4.436,
|
25 |
"step": 86
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 3.0,
|
29 |
+
"eval_loss": 0.5410714745521545,
|
30 |
+
"eval_runtime": 16.9111,
|
31 |
+
"eval_samples_per_second": 17.74,
|
32 |
+
"eval_steps_per_second": 4.435,
|
33 |
+
"step": 129
|
34 |
}
|
35 |
],
|
36 |
"logging_steps": 500,
|
|
|
50 |
"attributes": {}
|
51 |
}
|
52 |
},
|
53 |
+
"total_flos": 5904571275820800.0,
|
54 |
"train_batch_size": 8,
|
55 |
"trial_name": null,
|
56 |
"trial_params": null
|