Training in progress, step 9, 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 250422888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa3f83eb1a407fe6328f2db36924890a33c09bccecb7eccc449fed9cf2d24162
|
3 |
size 250422888
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 127788180
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5995ba6b725a709221fd6cf236085d9c1305d60a68626b59de5f822f257d16b
|
3 |
size 127788180
|
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 sha256:630f6b9a45e7853fc6d3930bdfaa464d2633d1ef3c000aeb08de618292dacad9
|
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 sha256:6920564b9afd6ce63c68d425e5a8bb301f80b33c89b02721f5b9445df83c24af
|
3 |
size 1064
|
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": 3,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -31,6 +31,14 @@
|
|
31 |
"eval_samples_per_second": 9.868,
|
32 |
"eval_steps_per_second": 6.579,
|
33 |
"step": 6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
}
|
35 |
],
|
36 |
"logging_steps": 10,
|
@@ -50,7 +58,7 @@
|
|
50 |
"attributes": {}
|
51 |
}
|
52 |
},
|
53 |
-
"total_flos":
|
54 |
"train_batch_size": 2,
|
55 |
"trial_name": null,
|
56 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.75,
|
5 |
"eval_steps": 3,
|
6 |
+
"global_step": 9,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
31 |
"eval_samples_per_second": 9.868,
|
32 |
"eval_steps_per_second": 6.579,
|
33 |
"step": 6
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.75,
|
37 |
+
"eval_loss": 0.4864470660686493,
|
38 |
+
"eval_runtime": 0.3074,
|
39 |
+
"eval_samples_per_second": 9.76,
|
40 |
+
"eval_steps_per_second": 6.507,
|
41 |
+
"step": 9
|
42 |
}
|
43 |
],
|
44 |
"logging_steps": 10,
|
|
|
58 |
"attributes": {}
|
59 |
}
|
60 |
},
|
61 |
+
"total_flos": 2301088361349120.0,
|
62 |
"train_batch_size": 2,
|
63 |
"trial_name": null,
|
64 |
"trial_params": null
|