Training in progress, step 100, 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 2611614300
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:507d55726514d36d57a7fdead1e533238594fb1d956a903a49ce02157b571e17
|
| 3 |
size 2611614300
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5213028466
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fb309794c77ba81c5d999193c64bdbf97c4b11eecd10e3754dddae31d948844
|
| 3 |
size 5213028466
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14942
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:874b9aec013ad321d4edc1c021ca42f8014c7ff34d53714ff8059015e8ee9794
|
| 3 |
size 14942
|
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:c39af0f6970331c0f430d145f5514421d9baa7e90f9cf02971fb62606bf1ff3d
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,26 +1,26 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"eval_steps":
|
| 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 |
{
|
| 12 |
-
"epoch": 0.
|
| 13 |
-
"grad_norm": 0.
|
| 14 |
-
"learning_rate": 0.
|
| 15 |
-
"loss":
|
| 16 |
-
"step":
|
| 17 |
}
|
| 18 |
],
|
| 19 |
-
"logging_steps":
|
| 20 |
"max_steps": 40250,
|
| 21 |
"num_input_tokens_seen": 0,
|
| 22 |
"num_train_epochs": 10,
|
| 23 |
-
"save_steps":
|
| 24 |
"stateful_callbacks": {
|
| 25 |
"TrainerControl": {
|
| 26 |
"args": {
|
|
@@ -33,7 +33,7 @@
|
|
| 33 |
"attributes": {}
|
| 34 |
}
|
| 35 |
},
|
| 36 |
-
"total_flos": 1.9448797327261696e+
|
| 37 |
"train_batch_size": 1,
|
| 38 |
"trial_name": null,
|
| 39 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.024843756065370134,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.024843756065370134,
|
| 13 |
+
"grad_norm": 0.9147792458534241,
|
| 14 |
+
"learning_rate": 0.0009975155279503105,
|
| 15 |
+
"loss": 1.0811305421386547e+17,
|
| 16 |
+
"step": 100
|
| 17 |
}
|
| 18 |
],
|
| 19 |
+
"logging_steps": 100,
|
| 20 |
"max_steps": 40250,
|
| 21 |
"num_input_tokens_seen": 0,
|
| 22 |
"num_train_epochs": 10,
|
| 23 |
+
"save_steps": 100,
|
| 24 |
"stateful_callbacks": {
|
| 25 |
"TrainerControl": {
|
| 26 |
"args": {
|
|
|
|
| 33 |
"attributes": {}
|
| 34 |
}
|
| 35 |
},
|
| 36 |
+
"total_flos": 1.9448797327261696e+16,
|
| 37 |
"train_batch_size": 1,
|
| 38 |
"trial_name": null,
|
| 39 |
"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 5176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0aae1b036793cf546f080bfdd66ff5e43f2ec5b41ab240614331a01cb7e0e4a5
|
| 3 |
size 5176
|