Training in progress, step 5590, 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:ee5bfe20ea6eae0ac503e3e3dc69b4b0c8a146d7f1bb0531ac3e85e51afb8a24
|
| 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 sha256:54105004195699730b745045faf328b1dd166a260ef0c28bcc0c6a75c37bdba7
|
| 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 sha256:94ddfb83665c71d9e8ec99573b88d7edc300c5d2f25c04384aa7d6178fd9b91b
|
| 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 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -10052,6 +10052,24 @@
|
|
| 10052 |
"mean_token_accuracy": 0.6515639036893844,
|
| 10053 |
"num_tokens": 20351293.0,
|
| 10054 |
"step": 5580
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10055 |
}
|
| 10056 |
],
|
| 10057 |
"logging_steps": 5,
|
|
@@ -10071,7 +10089,7 @@
|
|
| 10071 |
"attributes": {}
|
| 10072 |
}
|
| 10073 |
},
|
| 10074 |
-
"total_flos": 1.
|
| 10075 |
"train_batch_size": 4,
|
| 10076 |
"trial_name": null,
|
| 10077 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 43.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5590,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10052 |
"mean_token_accuracy": 0.6515639036893844,
|
| 10053 |
"num_tokens": 20351293.0,
|
| 10054 |
"step": 5580
|
| 10055 |
+
},
|
| 10056 |
+
{
|
| 10057 |
+
"epoch": 42.96153846153846,
|
| 10058 |
+
"grad_norm": 0.0,
|
| 10059 |
+
"learning_rate": 2.2080000000000002e-05,
|
| 10060 |
+
"loss": 1.7454,
|
| 10061 |
+
"mean_token_accuracy": 0.6521316289901733,
|
| 10062 |
+
"num_tokens": 20368835.0,
|
| 10063 |
+
"step": 5585
|
| 10064 |
+
},
|
| 10065 |
+
{
|
| 10066 |
+
"epoch": 43.0,
|
| 10067 |
+
"grad_norm": 0.0,
|
| 10068 |
+
"learning_rate": 2.2055e-05,
|
| 10069 |
+
"loss": 1.7799,
|
| 10070 |
+
"mean_token_accuracy": 0.6442039728164672,
|
| 10071 |
+
"num_tokens": 20386515.0,
|
| 10072 |
+
"step": 5590
|
| 10073 |
}
|
| 10074 |
],
|
| 10075 |
"logging_steps": 5,
|
|
|
|
| 10089 |
"attributes": {}
|
| 10090 |
}
|
| 10091 |
},
|
| 10092 |
+
"total_flos": 1.03301712543744e+18,
|
| 10093 |
"train_batch_size": 4,
|
| 10094 |
"trial_name": null,
|
| 10095 |
"trial_params": null
|