Training in progress, step 9110, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6ddedde947d8d4d23ed689fe5df3799f8ce860144a5a0e1777820aaaa275553
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1104040511ffb9f65bae61bd650d0ff2da1f4dfe0673ece013cd9e5d6ccf5ff3
|
| 3 |
size 14709
|
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 sha256:3c9db034cde2a355c557bf59e105a8af379a1ad110549e7d0a25974b38c56139
|
| 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": 70.
|
| 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,
|
|
@@ -16388,6 +16388,24 @@
|
|
| 16388 |
"mean_token_accuracy": 0.6524565041065216,
|
| 16389 |
"num_tokens": 33187350.0,
|
| 16390 |
"step": 9100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16391 |
}
|
| 16392 |
],
|
| 16393 |
"logging_steps": 5,
|
|
@@ -16407,7 +16425,7 @@
|
|
| 16407 |
"attributes": {}
|
| 16408 |
}
|
| 16409 |
},
|
| 16410 |
-
"total_flos": 1.
|
| 16411 |
"train_batch_size": 4,
|
| 16412 |
"trial_name": null,
|
| 16413 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 70.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9110,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16388 |
"mean_token_accuracy": 0.6524565041065216,
|
| 16389 |
"num_tokens": 33187350.0,
|
| 16390 |
"step": 9100
|
| 16391 |
+
},
|
| 16392 |
+
{
|
| 16393 |
+
"epoch": 70.03846153846153,
|
| 16394 |
+
"grad_norm": 0.0,
|
| 16395 |
+
"learning_rate": 4.48e-06,
|
| 16396 |
+
"loss": 1.7404,
|
| 16397 |
+
"mean_token_accuracy": 0.6531502634286881,
|
| 16398 |
+
"num_tokens": 33205235.0,
|
| 16399 |
+
"step": 9105
|
| 16400 |
+
},
|
| 16401 |
+
{
|
| 16402 |
+
"epoch": 70.07692307692308,
|
| 16403 |
+
"grad_norm": 0.0,
|
| 16404 |
+
"learning_rate": 4.4550000000000005e-06,
|
| 16405 |
+
"loss": 1.6612,
|
| 16406 |
+
"mean_token_accuracy": 0.6699670910835266,
|
| 16407 |
+
"num_tokens": 33224500.0,
|
| 16408 |
+
"step": 9110
|
| 16409 |
}
|
| 16410 |
],
|
| 16411 |
"logging_steps": 5,
|
|
|
|
| 16425 |
"attributes": {}
|
| 16426 |
}
|
| 16427 |
},
|
| 16428 |
+
"total_flos": 1.6847007265161216e+18,
|
| 16429 |
"train_batch_size": 4,
|
| 16430 |
"trial_name": null,
|
| 16431 |
"trial_params": null
|