Commit
•
0460b65
1
Parent(s):
2e1a50f
Training in progress, step 20, 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 1716360444
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a764fbda5943541947f63553e5167c97297a5db349245805e90871ee44ca6af
|
3 |
size 1716360444
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3433062021
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:806f6f5ab92428f5386186fc63b5907b8b5323c7e6a997d5fc6d431531ef0395
|
3 |
size 3433062021
|
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 sha256:1518ee95bdd1b49cc70d991bd9aa4565aa12c1bc44f83d5111632402e1671564
|
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:c02e795be2005cfb6114b898274cb7b49c620eb2cb7c5e988b220f7aa723b1fc
|
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": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -14,10 +14,17 @@
|
|
14 |
"learning_rate": 4.999735579817769e-05,
|
15 |
"loss": 1.4008,
|
16 |
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
}
|
18 |
],
|
19 |
"logging_steps": 10,
|
20 |
-
"max_steps":
|
21 |
"num_input_tokens_seen": 0,
|
22 |
"num_train_epochs": 5,
|
23 |
"save_steps": 10,
|
@@ -33,7 +40,7 @@
|
|
33 |
"attributes": {}
|
34 |
}
|
35 |
},
|
36 |
-
"total_flos":
|
37 |
"train_batch_size": 4,
|
38 |
"trial_name": null,
|
39 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.09237875288683603,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 20,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
14 |
"learning_rate": 4.999735579817769e-05,
|
15 |
"loss": 1.4008,
|
16 |
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.09237875288683603,
|
20 |
+
"grad_norm": 2.0704426765441895,
|
21 |
+
"learning_rate": 4.997598371650346e-05,
|
22 |
+
"loss": 1.388,
|
23 |
+
"step": 20
|
24 |
}
|
25 |
],
|
26 |
"logging_steps": 10,
|
27 |
+
"max_steps": 1080,
|
28 |
"num_input_tokens_seen": 0,
|
29 |
"num_train_epochs": 5,
|
30 |
"save_steps": 10,
|
|
|
40 |
"attributes": {}
|
41 |
}
|
42 |
},
|
43 |
+
"total_flos": 47859389030400.0,
|
44 |
"train_batch_size": 4,
|
45 |
"trial_name": null,
|
46 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fed09fd527038c16340e2f427d8a40a587733060f6ee64d37fc8b4c4cdfce0b6
|
3 |
size 5112
|