MohamedAhmedAE
commited on
Commit
•
9b3e810
1
Parent(s):
24f09a4
Training in progress, step 1600, 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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e031d128a56e1f2c0d13eb1bdf24b11e3161a5c84ee640ffe8148c5cde2e7779
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 84581014
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68b7b1fbf5329eb8a91ba2dd7567fcfc9167143f8b5b1e8a308611118d62b893
|
3 |
size 84581014
|
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:d51ba13d8ecce76d2ed0ab5874b7250d2ee372ca336a46f1c56ac6d02ec40073
|
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 sha256:8c9e9f1ae41fa1e5ee80b76c39d1d8aae5af530178bf78fd25d0ba3cffdc224c
|
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": 2000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -56,6 +56,13 @@
|
|
56 |
"learning_rate": 1.9999997884752155e-05,
|
57 |
"loss": 1.6211,
|
58 |
"step": 1400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
59 |
}
|
60 |
],
|
61 |
"logging_steps": 200,
|
@@ -63,7 +70,7 @@
|
|
63 |
"num_input_tokens_seen": 0,
|
64 |
"num_train_epochs": 5,
|
65 |
"save_steps": 200,
|
66 |
-
"total_flos":
|
67 |
"train_batch_size": 1,
|
68 |
"trial_name": null,
|
69 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0011898608978244138,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 1600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
56 |
"learning_rate": 1.9999997884752155e-05,
|
57 |
"loss": 1.6211,
|
58 |
"step": 1400
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.0,
|
62 |
+
"grad_norm": 4.068266868591309,
|
63 |
+
"learning_rate": 1.9999997233256404e-05,
|
64 |
+
"loss": 1.6001,
|
65 |
+
"step": 1600
|
66 |
}
|
67 |
],
|
68 |
"logging_steps": 200,
|
|
|
70 |
"num_input_tokens_seen": 0,
|
71 |
"num_train_epochs": 5,
|
72 |
"save_steps": 200,
|
73 |
+
"total_flos": 2.07320002916352e+16,
|
74 |
"train_batch_size": 1,
|
75 |
"trial_name": null,
|
76 |
"trial_params": null
|