Training in progress, step 500, 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 497774208
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d98c43037b27e6fbdc29620f75e7d619b4e69b48fceec55513bbf2f67262985
|
3 |
size 497774208
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 995642298
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cac18d2eac7931900e874ece9308a9e430394ea4b49ca9c5b03b0cfeff11972
|
3 |
size 995642298
|
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 sha256:3006c2e62f2fbd7c9faf809b9b2f9bdfb8379c432374b893703883a883751cd7
|
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 sha256:8b33b088bdbfafa8111c504dc49515c8a34373a23db9c6d25c18a372aff83ca7
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,15 +1,15 @@
|
|
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,
|
10 |
"log_history": [],
|
11 |
-
"logging_steps":
|
12 |
-
"max_steps":
|
13 |
"num_input_tokens_seen": 0,
|
14 |
"num_train_epochs": 3,
|
15 |
"save_steps": 500,
|
@@ -25,7 +25,7 @@
|
|
25 |
"attributes": {}
|
26 |
}
|
27 |
},
|
28 |
-
"total_flos":
|
29 |
"train_batch_size": 32,
|
30 |
"trial_name": null,
|
31 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.015004201176329373,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [],
|
11 |
+
"logging_steps": 33323,
|
12 |
+
"max_steps": 99972,
|
13 |
"num_input_tokens_seen": 0,
|
14 |
"num_train_epochs": 3,
|
15 |
"save_steps": 500,
|
|
|
25 |
"attributes": {}
|
26 |
}
|
27 |
},
|
28 |
+
"total_flos": 1045168128000000.0,
|
29 |
"train_batch_size": 32,
|
30 |
"trial_name": null,
|
31 |
"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 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:588ed685f39e84528f61e069ba254fd7cef9c5061f838bf59aba9ee692ef1d72
|
3 |
size 5240
|