Training in progress, step 10, 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 119801528
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7434b555be08ce87cabae6713bc399ce945ad01d48580b33f699ac373e9ac5f8
|
3 |
size 119801528
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 239892858
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f18b5ec5bd9181b2677b373608723872fd6230a86bfb9b1997b8dae8df62b07f
|
3 |
size 239892858
|
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 sha256:61d3222b2ea287c6c03b7cf6a281410926616beb492b71fff0711736320080c8
|
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:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
|
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": 8,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -22,6 +22,28 @@
|
|
22 |
"learning_rate": 0.00012,
|
23 |
"loss": 2.3526,
|
24 |
"step": 3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
}
|
26 |
],
|
27 |
"logging_steps": 3,
|
@@ -41,7 +63,7 @@
|
|
41 |
"attributes": {}
|
42 |
}
|
43 |
},
|
44 |
-
"total_flos":
|
45 |
"train_batch_size": 2,
|
46 |
"trial_name": null,
|
47 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.004612191559689446,
|
5 |
"eval_steps": 8,
|
6 |
+
"global_step": 10,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
22 |
"learning_rate": 0.00012,
|
23 |
"loss": 2.3526,
|
24 |
"step": 3
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.0027673149358136673,
|
28 |
+
"grad_norm": 0.6379570364952087,
|
29 |
+
"learning_rate": 0.0001992114701314478,
|
30 |
+
"loss": 2.2248,
|
31 |
+
"step": 6
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.0036897532477515567,
|
35 |
+
"eval_loss": 2.1423521041870117,
|
36 |
+
"eval_runtime": 70.532,
|
37 |
+
"eval_samples_per_second": 19.424,
|
38 |
+
"eval_steps_per_second": 9.712,
|
39 |
+
"step": 8
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.004150972403720501,
|
43 |
+
"grad_norm": 0.6265854239463806,
|
44 |
+
"learning_rate": 0.00018763066800438636,
|
45 |
+
"loss": 2.0725,
|
46 |
+
"step": 9
|
47 |
}
|
48 |
],
|
49 |
"logging_steps": 3,
|
|
|
63 |
"attributes": {}
|
64 |
}
|
65 |
},
|
66 |
+
"total_flos": 2102318862434304.0,
|
67 |
"train_batch_size": 2,
|
68 |
"trial_name": null,
|
69 |
"trial_params": null
|