Training in progress, step 7000, checkpoint
Browse files- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +20 -5
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 136000488
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fd990d11bd5d66d6bed13f185883ea4cb7944e28eba186eb6558a9ccdcdbc2e
|
3 |
size 136000488
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 268176506
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1e92f6aa1461f021602ec4129ab6fa7dbab49bf5e6d579fc44c475447dbbd9c
|
3 |
size 268176506
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e0f56ea2258aa848a268b65b4eb9157d222d715d9d9a7cc13ef82fd5f1faa73
|
3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c5ef62e5944f7a0f68155eb1714c52ea2903c9c361562828b854d1e450461a1
|
3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4fcbe30b6934f80a241180dfc415b0f92927e3c28b8b87796f9a64e696582ef
|
3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76a7b9b24e27099b1ee0ad93277549a53e07025af6930aa984b8a7e95784117c
|
3 |
size 15024
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9aca3b4e41519cad54d0814687cff94c8c96d678dfab879b406e03675dbb33ee
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.7487396597862244,
|
3 |
"best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-6500",
|
4 |
-
"epoch": 9.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -1042,6 +1042,21 @@
|
|
1042 |
"eval_samples_per_second": 893.836,
|
1043 |
"eval_steps_per_second": 3.612,
|
1044 |
"step": 6900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1045 |
}
|
1046 |
],
|
1047 |
"logging_steps": 100,
|
@@ -1056,7 +1071,7 @@
|
|
1056 |
"early_stopping_threshold": 0.0
|
1057 |
},
|
1058 |
"attributes": {
|
1059 |
-
"early_stopping_patience_counter":
|
1060 |
}
|
1061 |
},
|
1062 |
"TrainerControl": {
|
@@ -1065,12 +1080,12 @@
|
|
1065 |
"should_evaluate": false,
|
1066 |
"should_log": false,
|
1067 |
"should_save": true,
|
1068 |
-
"should_training_stop":
|
1069 |
},
|
1070 |
"attributes": {}
|
1071 |
}
|
1072 |
},
|
1073 |
-
"total_flos": 2.
|
1074 |
"train_batch_size": 64,
|
1075 |
"trial_name": null,
|
1076 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.7487396597862244,
|
3 |
"best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-6500",
|
4 |
+
"epoch": 9.370816599732262,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 7000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1042 |
"eval_samples_per_second": 893.836,
|
1043 |
"eval_steps_per_second": 3.612,
|
1044 |
"step": 6900
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 9.370816599732262,
|
1048 |
+
"grad_norm": 0.2047683447599411,
|
1049 |
+
"learning_rate": 6.291834002677377e-05,
|
1050 |
+
"loss": 0.6625,
|
1051 |
+
"step": 7000
|
1052 |
+
},
|
1053 |
+
{
|
1054 |
+
"epoch": 9.370816599732262,
|
1055 |
+
"eval_loss": 0.7502346038818359,
|
1056 |
+
"eval_runtime": 6.3912,
|
1057 |
+
"eval_samples_per_second": 890.597,
|
1058 |
+
"eval_steps_per_second": 3.599,
|
1059 |
+
"step": 7000
|
1060 |
}
|
1061 |
],
|
1062 |
"logging_steps": 100,
|
|
|
1071 |
"early_stopping_threshold": 0.0
|
1072 |
},
|
1073 |
"attributes": {
|
1074 |
+
"early_stopping_patience_counter": 5
|
1075 |
}
|
1076 |
},
|
1077 |
"TrainerControl": {
|
|
|
1080 |
"should_evaluate": false,
|
1081 |
"should_log": false,
|
1082 |
"should_save": true,
|
1083 |
+
"should_training_stop": true
|
1084 |
},
|
1085 |
"attributes": {}
|
1086 |
}
|
1087 |
},
|
1088 |
+
"total_flos": 2.5418589536256e+17,
|
1089 |
"train_batch_size": 64,
|
1090 |
"trial_name": null,
|
1091 |
"trial_params": null
|