Training in progress, step 2410, 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 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba157a5331266c6205783bfcb33d4c8184ac8fa86d39d20297a13fac49d0f622
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0f96d74e3049219bc8e176d2f65a6f72f6844d7432f4c31bc9aeaf7a5aea3da
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a058a9371b93b039b74c1edfe9ce66ec469bb798ba07542b2dbcdfe38fa6c85
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8958b5b007a332f168993ccff1da601cb7012c39453b85591abbde9ba14a6ef
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2418,6 +2418,16 @@
|
|
| 2418 |
"mean_token_accuracy": 0.7355501770973205,
|
| 2419 |
"num_tokens": 11167106.0,
|
| 2420 |
"step": 2400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2421 |
}
|
| 2422 |
],
|
| 2423 |
"logging_steps": 10,
|
|
@@ -2437,7 +2447,7 @@
|
|
| 2437 |
"attributes": {}
|
| 2438 |
}
|
| 2439 |
},
|
| 2440 |
-
"total_flos": 5.
|
| 2441 |
"train_batch_size": 4,
|
| 2442 |
"trial_name": null,
|
| 2443 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5141333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2410,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2418 |
"mean_token_accuracy": 0.7355501770973205,
|
| 2419 |
"num_tokens": 11167106.0,
|
| 2420 |
"step": 2400
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"entropy": 0.9723750591278076,
|
| 2424 |
+
"epoch": 0.5141333333333333,
|
| 2425 |
+
"grad_norm": 0.3258633315563202,
|
| 2426 |
+
"learning_rate": 8.725820979735436e-05,
|
| 2427 |
+
"loss": 1.1157949447631836,
|
| 2428 |
+
"mean_token_accuracy": 0.7603042379021645,
|
| 2429 |
+
"num_tokens": 11211815.0,
|
| 2430 |
+
"step": 2410
|
| 2431 |
}
|
| 2432 |
],
|
| 2433 |
"logging_steps": 10,
|
|
|
|
| 2447 |
"attributes": {}
|
| 2448 |
}
|
| 2449 |
},
|
| 2450 |
+
"total_flos": 5.317580177261875e+16,
|
| 2451 |
"train_batch_size": 4,
|
| 2452 |
"trial_name": null,
|
| 2453 |
"trial_params": null
|