Training in progress, step 5600, 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 8137792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7bdf4d36ebd3b930b7fbbb0a5ce43310d7b607320c50bd2a336d628b5eb429ff
|
| 3 |
size 8137792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16386426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4088f17e408e7b955c116b432a5502fb2c86a025c9160b920735aafca1c9a9a2
|
| 3 |
size 16386426
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3ebabed5aa2f954fe25818789f8fb53f76ec91c892e9e8647e49e231a0c3f32
|
| 3 |
size 15006
|
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 sha256:6a2e502ccb8ae9d8ae315aa4b1fa4a8a23d46a1ef876d6adc21902e2473d4ff4
|
| 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":
|
| 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,
|
|
@@ -480,6 +480,13 @@
|
|
| 480 |
"eval_samples_per_second": 19.888,
|
| 481 |
"eval_steps_per_second": 2.487,
|
| 482 |
"step": 5500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 483 |
}
|
| 484 |
],
|
| 485 |
"logging_steps": 100,
|
|
@@ -499,7 +506,7 @@
|
|
| 499 |
"attributes": {}
|
| 500 |
}
|
| 501 |
},
|
| 502 |
-
"total_flos": 8.
|
| 503 |
"train_batch_size": 8,
|
| 504 |
"trial_name": null,
|
| 505 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 11.198250273394782,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 5600,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 480 |
"eval_samples_per_second": 19.888,
|
| 481 |
"eval_steps_per_second": 2.487,
|
| 482 |
"step": 5500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 11.198250273394782,
|
| 486 |
+
"grad_norm": 0.20055556297302246,
|
| 487 |
+
"learning_rate": 6.266666666666667e-05,
|
| 488 |
+
"loss": 1.2421,
|
| 489 |
+
"step": 5600
|
| 490 |
}
|
| 491 |
],
|
| 492 |
"logging_steps": 100,
|
|
|
|
| 506 |
"attributes": {}
|
| 507 |
}
|
| 508 |
},
|
| 509 |
+
"total_flos": 8.740097660964307e+18,
|
| 510 |
"train_batch_size": 8,
|
| 511 |
"trial_name": null,
|
| 512 |
"trial_params": null
|