Training in progress, step 860, 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 sha256:359657fef25fa558842b146504970f7a10237e0eb52c13c471cb3b595bf2112c
|
| 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 sha256:5ab5169af9fb72657d346a3f414edcc94e2fec1142877d05bbb7787060b4ec9e
|
| 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 sha256:4e334eca1b4b1c903114a22dc25b03ef41d3e3cefa56e476e4beb5b0f7bb18dc
|
| 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": 6.
|
| 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,
|
|
@@ -1538,6 +1538,24 @@
|
|
| 1538 |
"mean_token_accuracy": 0.6463764935731888,
|
| 1539 |
"num_tokens": 3100123.0,
|
| 1540 |
"step": 850
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1541 |
}
|
| 1542 |
],
|
| 1543 |
"logging_steps": 5,
|
|
@@ -1557,7 +1575,7 @@
|
|
| 1557 |
"attributes": {}
|
| 1558 |
}
|
| 1559 |
},
|
| 1560 |
-
"total_flos": 1.
|
| 1561 |
"train_batch_size": 4,
|
| 1562 |
"trial_name": null,
|
| 1563 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.615384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 860,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1538 |
"mean_token_accuracy": 0.6463764935731888,
|
| 1539 |
"num_tokens": 3100123.0,
|
| 1540 |
"step": 850
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 6.576923076923077,
|
| 1544 |
+
"grad_norm": 0.0,
|
| 1545 |
+
"learning_rate": 4.573e-05,
|
| 1546 |
+
"loss": 1.7434,
|
| 1547 |
+
"mean_token_accuracy": 0.6475829243659973,
|
| 1548 |
+
"num_tokens": 3117886.0,
|
| 1549 |
+
"step": 855
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 6.615384615384615,
|
| 1553 |
+
"grad_norm": 0.0,
|
| 1554 |
+
"learning_rate": 4.5705000000000004e-05,
|
| 1555 |
+
"loss": 1.6876,
|
| 1556 |
+
"mean_token_accuracy": 0.6611418306827546,
|
| 1557 |
+
"num_tokens": 3136818.0,
|
| 1558 |
+
"step": 860
|
| 1559 |
}
|
| 1560 |
],
|
| 1561 |
"logging_steps": 5,
|
|
|
|
| 1575 |
"attributes": {}
|
| 1576 |
}
|
| 1577 |
},
|
| 1578 |
+
"total_flos": 1.5893093910380544e+17,
|
| 1579 |
"train_batch_size": 4,
|
| 1580 |
"trial_name": null,
|
| 1581 |
"trial_params": null
|