tuanna08go
commited on
Training in progress, step 38, 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 19859140
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f94c2ba3b653f5251cd43d9920387716f9fbe793d4251548d11fc7cf5bc9e44
|
3 |
size 19859140
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5294e0421dddbb7243207746b80dba1c35df6a17d7f76a8986fad43f5c5aa31b
|
3 |
size 14244
|
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:d68c5e6597fbe8c8cd503bbe96844944996bb2c8646d83e3c51d984760006005
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 8,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -81,6 +81,21 @@
|
|
81 |
"learning_rate": 1.8825509907063327e-05,
|
82 |
"loss": 0.0,
|
83 |
"step": 30
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
84 |
}
|
85 |
],
|
86 |
"logging_steps": 5,
|
@@ -95,12 +110,12 @@
|
|
95 |
"should_evaluate": false,
|
96 |
"should_log": false,
|
97 |
"should_save": true,
|
98 |
-
"should_training_stop":
|
99 |
},
|
100 |
"attributes": {}
|
101 |
}
|
102 |
},
|
103 |
-
"total_flos":
|
104 |
"train_batch_size": 2,
|
105 |
"trial_name": null,
|
106 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0198675496688743,
|
5 |
"eval_steps": 8,
|
6 |
+
"global_step": 38,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
81 |
"learning_rate": 1.8825509907063327e-05,
|
82 |
"loss": 0.0,
|
83 |
"step": 30
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 0.847682119205298,
|
87 |
+
"eval_loss": NaN,
|
88 |
+
"eval_runtime": 0.695,
|
89 |
+
"eval_samples_per_second": 23.022,
|
90 |
+
"eval_steps_per_second": 11.511,
|
91 |
+
"step": 32
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 0.9271523178807947,
|
95 |
+
"grad_norm": NaN,
|
96 |
+
"learning_rate": 2.8058334845816213e-06,
|
97 |
+
"loss": 0.0,
|
98 |
+
"step": 35
|
99 |
}
|
100 |
],
|
101 |
"logging_steps": 5,
|
|
|
110 |
"should_evaluate": false,
|
111 |
"should_log": false,
|
112 |
"should_save": true,
|
113 |
+
"should_training_stop": true
|
114 |
},
|
115 |
"attributes": {}
|
116 |
}
|
117 |
},
|
118 |
+
"total_flos": 1370160142221312.0,
|
119 |
"train_batch_size": 2,
|
120 |
"trial_name": null,
|
121 |
"trial_params": null
|