Training in progress, step 550, 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 sha256:561d996b1bbc9b0bc55d271e7e2391e151145ef7b0966e352616d968cb50ccce
|
| 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:ccf66adc9fc0160481bc80ad1b0c9dc8d78ea4bc655a5df0bb43895387218cc6
|
| 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:d1dd884ea9baa60763ba1e29a27bed9a42fdb07bb4994a2bb031b250986c32a8
|
| 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": 4.
|
| 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,
|
|
@@ -980,6 +980,24 @@
|
|
| 980 |
"mean_token_accuracy": 0.6442851930856704,
|
| 981 |
"num_tokens": 1968989.0,
|
| 982 |
"step": 540
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 983 |
}
|
| 984 |
],
|
| 985 |
"logging_steps": 5,
|
|
@@ -999,7 +1017,7 @@
|
|
| 999 |
"attributes": {}
|
| 1000 |
}
|
| 1001 |
},
|
| 1002 |
-
"total_flos":
|
| 1003 |
"train_batch_size": 4,
|
| 1004 |
"trial_name": null,
|
| 1005 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.230769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 550,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 980 |
"mean_token_accuracy": 0.6442851930856704,
|
| 981 |
"num_tokens": 1968989.0,
|
| 982 |
"step": 540
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 4.1923076923076925,
|
| 986 |
+
"grad_norm": 0.0,
|
| 987 |
+
"learning_rate": 4.728e-05,
|
| 988 |
+
"loss": 1.7535,
|
| 989 |
+
"mean_token_accuracy": 0.6471328794956207,
|
| 990 |
+
"num_tokens": 1987280.0,
|
| 991 |
+
"step": 545
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 4.230769230769231,
|
| 995 |
+
"grad_norm": 0.0,
|
| 996 |
+
"learning_rate": 4.725500000000001e-05,
|
| 997 |
+
"loss": 1.7691,
|
| 998 |
+
"mean_token_accuracy": 0.6456631302833558,
|
| 999 |
+
"num_tokens": 2005118.0,
|
| 1000 |
+
"step": 550
|
| 1001 |
}
|
| 1002 |
],
|
| 1003 |
"logging_steps": 5,
|
|
|
|
| 1017 |
"attributes": {}
|
| 1018 |
}
|
| 1019 |
},
|
| 1020 |
+
"total_flos": 1.0156435112558592e+17,
|
| 1021 |
"train_batch_size": 4,
|
| 1022 |
"trial_name": null,
|
| 1023 |
"trial_params": null
|