Commit
·
61ed0c4
1
Parent(s):
46998aa
Training in progress, step 100, checkpoint
Browse files
last-checkpoint/adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 369214349
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d2a95e2660bfc7195753603330872276483c1cc94f1948972c8c831699268d7
|
| 3 |
size 369214349
|
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 369142184
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fa6408bae53e3b5c433cfbcd2eb4d57578ad9f17661023a9df1d538d50d6f8f
|
| 3 |
size 369142184
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 738393541
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d54fa4c8a787ac16f43b5095f69889cca7339c8060b89015737eaeb73fe5f5ac
|
| 3 |
size 738393541
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc65ec16498f1492c0abd9e4ff38a7a1dcf3bfc8588a8cef564aa183db85da91
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:216f76b8039f833c337db298c81f13b12082d5fd4f9d866cecd34b2ca7550b37
|
| 3 |
size 627
|
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,
|
|
@@ -25,13 +25,19 @@
|
|
| 25 |
"learning_rate": 0.0002,
|
| 26 |
"loss": 1.4671,
|
| 27 |
"step": 75
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
}
|
| 29 |
],
|
| 30 |
"logging_steps": 25,
|
| 31 |
"max_steps": 728,
|
| 32 |
"num_train_epochs": 1,
|
| 33 |
"save_steps": 25,
|
| 34 |
-
"total_flos":
|
| 35 |
"trial_name": null,
|
| 36 |
"trial_params": null
|
| 37 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.13736263736263737,
|
| 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,
|
|
|
|
| 25 |
"learning_rate": 0.0002,
|
| 26 |
"loss": 1.4671,
|
| 27 |
"step": 75
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.14,
|
| 31 |
+
"learning_rate": 0.0002,
|
| 32 |
+
"loss": 0.9931,
|
| 33 |
+
"step": 100
|
| 34 |
}
|
| 35 |
],
|
| 36 |
"logging_steps": 25,
|
| 37 |
"max_steps": 728,
|
| 38 |
"num_train_epochs": 1,
|
| 39 |
"save_steps": 25,
|
| 40 |
+
"total_flos": 991411943669760.0,
|
| 41 |
"trial_name": null,
|
| 42 |
"trial_params": null
|
| 43 |
}
|