Training in progress, step 100, 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 338298
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d0f32357435a6de34207bb86d69fecb9bc7bedce73603e4efbeb91466640e08
|
3 |
size 338298
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 418030
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7aa0bfc733303ec2dc48c608f845affe581f8a5a942ad231cd07374d9ff624f
|
3 |
size 418030
|
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:c315ee5d1dd22cdd90c68daa494c9ad70a2029911cf81e1cbbe0d1d659de9e9b
|
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 sha256:5337952f7687299d5aa5c14e2108aaf691cb8096de55bdfca5684d52e35c0e25
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 6.
|
3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 50,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -30,6 +30,21 @@
|
|
30 |
"eval_samples_per_second": 1255.76,
|
31 |
"eval_steps_per_second": 39.751,
|
32 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
}
|
34 |
],
|
35 |
"logging_steps": 50,
|
@@ -58,7 +73,7 @@
|
|
58 |
"attributes": {}
|
59 |
}
|
60 |
},
|
61 |
-
"total_flos":
|
62 |
"train_batch_size": 32,
|
63 |
"trial_name": null,
|
64 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 6.857929229736328,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.9685230024213075,
|
5 |
"eval_steps": 50,
|
6 |
+
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
30 |
"eval_samples_per_second": 1255.76,
|
31 |
"eval_steps_per_second": 39.751,
|
32 |
"step": 50
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.9685230024213075,
|
36 |
+
"grad_norm": 0.33752018213272095,
|
37 |
+
"learning_rate": 0.000202,
|
38 |
+
"loss": 6.866,
|
39 |
+
"step": 100
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.9685230024213075,
|
43 |
+
"eval_loss": 6.857929229736328,
|
44 |
+
"eval_runtime": 0.5275,
|
45 |
+
"eval_samples_per_second": 1317.608,
|
46 |
+
"eval_steps_per_second": 41.708,
|
47 |
+
"step": 100
|
48 |
}
|
49 |
],
|
50 |
"logging_steps": 50,
|
|
|
73 |
"attributes": {}
|
74 |
}
|
75 |
},
|
76 |
+
"total_flos": 4209740808192.0,
|
77 |
"train_batch_size": 32,
|
78 |
"trial_name": null,
|
79 |
"trial_params": null
|