Training in progress, step 15, 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 191968
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:246b7d7b7abffb788a563c74af9de925ff6ed1a4e2c74dcc12dbd1e18fff8e01
|
3 |
size 191968
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 253144
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a88cdcd6f355103a9cadc406efc0a66f1183b87349265d8a7c2a3472a1c10c5
|
3 |
size 253144
|
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 sha256:372c9c91189dafe7a0013b948ff9907e60fc7ad4b32cc7ac3bccb3f603cf2268
|
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:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
|
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": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -52,6 +52,28 @@
|
|
52 |
"eval_samples_per_second": 474.28,
|
53 |
"eval_steps_per_second": 118.609,
|
54 |
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
}
|
56 |
],
|
57 |
"logging_steps": 3,
|
@@ -71,7 +93,7 @@
|
|
71 |
"attributes": {}
|
72 |
}
|
73 |
},
|
74 |
-
"total_flos":
|
75 |
"train_batch_size": 4,
|
76 |
"trial_name": null,
|
77 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0027649132508467547,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 15,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
52 |
"eval_samples_per_second": 474.28,
|
53 |
"eval_steps_per_second": 118.609,
|
54 |
"step": 10
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.0022119306006774036,
|
58 |
+
"grad_norm": 0.06515509635210037,
|
59 |
+
"learning_rate": 9.938441702975689e-05,
|
60 |
+
"loss": 10.3728,
|
61 |
+
"step": 12
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.0027649132508467547,
|
65 |
+
"grad_norm": 0.07225878536701202,
|
66 |
+
"learning_rate": 9.619397662556435e-05,
|
67 |
+
"loss": 10.3706,
|
68 |
+
"step": 15
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.0027649132508467547,
|
72 |
+
"eval_loss": 10.369028091430664,
|
73 |
+
"eval_runtime": 19.6179,
|
74 |
+
"eval_samples_per_second": 465.748,
|
75 |
+
"eval_steps_per_second": 116.475,
|
76 |
+
"step": 15
|
77 |
}
|
78 |
],
|
79 |
"logging_steps": 3,
|
|
|
93 |
"attributes": {}
|
94 |
}
|
95 |
},
|
96 |
+
"total_flos": 1673259909120.0,
|
97 |
"train_batch_size": 4,
|
98 |
"trial_name": null,
|
99 |
"trial_params": null
|