Training in progress, step 14180, 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 13982248
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01e9cbaceb5831adbecae784c9a136002a89e2a397f162dc5d34feccdcfc1987
|
3 |
size 13982248
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7062522
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:676264a97b567a751b525fb63caaff00c5c1b3e0b1e4124f1f621f8307e1e6f4
|
3 |
size 7062522
|
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 sha256:6698b95ba39be6900dd16f234973145e2e775d4d9ac937bc19752bc4332316f3
|
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 sha256:7fd98cac66890d1740350aad97da31e64db12386e28d7f78c3f4d6ac75af4216
|
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,
|
@@ -4963,6 +4963,13 @@
|
|
4963 |
"learning_rate": 1.0370950850253449e-05,
|
4964 |
"loss": 3.6196,
|
4965 |
"step": 14160
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4966 |
}
|
4967 |
],
|
4968 |
"logging_steps": 20,
|
@@ -4970,7 +4977,7 @@
|
|
4970 |
"num_input_tokens_seen": 0,
|
4971 |
"num_train_epochs": 1,
|
4972 |
"save_steps": 20,
|
4973 |
-
"total_flos": 3.
|
4974 |
"train_batch_size": 8,
|
4975 |
"trial_name": null,
|
4976 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.20067078952209785,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 14180,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
4963 |
"learning_rate": 1.0370950850253449e-05,
|
4964 |
"loss": 3.6196,
|
4965 |
"step": 14160
|
4966 |
+
},
|
4967 |
+
{
|
4968 |
+
"epoch": 0.2,
|
4969 |
+
"grad_norm": 35.55162048339844,
|
4970 |
+
"learning_rate": 1.0305368692688174e-05,
|
4971 |
+
"loss": 3.4774,
|
4972 |
+
"step": 14180
|
4973 |
}
|
4974 |
],
|
4975 |
"logging_steps": 20,
|
|
|
4977 |
"num_input_tokens_seen": 0,
|
4978 |
"num_train_epochs": 1,
|
4979 |
"save_steps": 20,
|
4980 |
+
"total_flos": 3.080950876618752e+16,
|
4981 |
"train_batch_size": 8,
|
4982 |
"trial_name": null,
|
4983 |
"trial_params": null
|