Training in progress, step 1440, 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 1316913776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eaa1a251c60709477d0d8c482aeeb1eeb49429fe0b9a6641c945fd96f9e946da
|
| 3 |
size 1316913776
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 8908124
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4372b065710baf1bb08c3b4a94e8f177b87ea1e7c2a1f05f93288bc856c4e20
|
| 3 |
size 8908124
|
last-checkpoint/rng_state.pth
CHANGED
|
Binary files a/last-checkpoint/rng_state.pth and b/last-checkpoint/rng_state.pth differ
|
|
|
last-checkpoint/scheduler.pt
CHANGED
|
Binary files a/last-checkpoint/scheduler.pt and b/last-checkpoint/scheduler.pt differ
|
|
|
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,
|
|
@@ -1008,6 +1008,13 @@
|
|
| 1008 |
"learning_rate": 0.0003465006440532417,
|
| 1009 |
"loss": 0.7734,
|
| 1010 |
"step": 1430
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1011 |
}
|
| 1012 |
],
|
| 1013 |
"logging_steps": 10,
|
|
@@ -1015,7 +1022,7 @@
|
|
| 1015 |
"num_input_tokens_seen": 0,
|
| 1016 |
"num_train_epochs": 1,
|
| 1017 |
"save_steps": 10,
|
| 1018 |
-
"total_flos": 1.
|
| 1019 |
"train_batch_size": 3,
|
| 1020 |
"trial_name": null,
|
| 1021 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.30914555603263205,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1440,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1008 |
"learning_rate": 0.0003465006440532417,
|
| 1009 |
"loss": 0.7734,
|
| 1010 |
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.30914555603263205,
|
| 1014 |
+
"grad_norm": 1.4723149538040161,
|
| 1015 |
+
"learning_rate": 0.00034542722198368397,
|
| 1016 |
+
"loss": 0.7839,
|
| 1017 |
+
"step": 1440
|
| 1018 |
}
|
| 1019 |
],
|
| 1020 |
"logging_steps": 10,
|
|
|
|
| 1022 |
"num_input_tokens_seen": 0,
|
| 1023 |
"num_train_epochs": 1,
|
| 1024 |
"save_steps": 10,
|
| 1025 |
+
"total_flos": 1.0907404405212672e+17,
|
| 1026 |
"train_batch_size": 3,
|
| 1027 |
"trial_name": null,
|
| 1028 |
"trial_params": null
|