rakhman-llm
commited on
Commit
•
04080ca
1
Parent(s):
df37423
Training in progress, step 2500, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 891558696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48e35633f2ae11afa853118e28ee629cfb8628c6179db15025e9a1b84122c42e
|
3 |
size 891558696
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1783272762
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b50d9f3de0d3aad8b7e0917750078b64ff6448c1761b9393ae240a8879ea9024
|
3 |
size 1783272762
|
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 sha256:30dc60382167de3458c5c0efd3fe3f40ca4cde794d0fe66663ca9a8bcee0d065
|
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 sha256:5d9e707c93d930eada5d65eeb12d5abae9fff751224d824839cf7f999a563f5e
|
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": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -35,6 +35,13 @@
|
|
35 |
"learning_rate": 1.7233305624826823e-05,
|
36 |
"loss": 0.4518,
|
37 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
}
|
39 |
],
|
40 |
"logging_steps": 500,
|
@@ -54,7 +61,7 @@
|
|
54 |
"attributes": {}
|
55 |
}
|
56 |
},
|
57 |
-
"total_flos":
|
58 |
"train_batch_size": 2,
|
59 |
"trial_name": null,
|
60 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5195344970906068,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 2500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
35 |
"learning_rate": 1.7233305624826823e-05,
|
36 |
"loss": 0.4518,
|
37 |
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.5195344970906068,
|
41 |
+
"grad_norm": 0.8163271546363831,
|
42 |
+
"learning_rate": 1.6540592962039347e-05,
|
43 |
+
"loss": 0.4389,
|
44 |
+
"step": 2500
|
45 |
}
|
46 |
],
|
47 |
"logging_steps": 500,
|
|
|
61 |
"attributes": {}
|
62 |
}
|
63 |
},
|
64 |
+
"total_flos": 3044789452800000.0,
|
65 |
"train_batch_size": 2,
|
66 |
"trial_name": null,
|
67 |
"trial_params": null
|