Training in progress, step 10, 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 67209940
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8780cc4eef4800016dd56d3d4d12a8c96c98254fdd2924f9777674dc5565de7
|
3 |
size 67209940
|
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 sha256:2885ec8dffb3ed1144e52d235c2037d7006040745b9e1aecd15a8a1ebf64e839
|
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:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
|
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": 0.
|
5 |
"eval_steps": 3,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -102,6 +102,13 @@
|
|
102 |
"eval_samples_per_second": 6.419,
|
103 |
"eval_steps_per_second": 3.214,
|
104 |
"step": 9
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
105 |
}
|
106 |
],
|
107 |
"logging_steps": 1,
|
@@ -116,12 +123,12 @@
|
|
116 |
"should_evaluate": false,
|
117 |
"should_log": false,
|
118 |
"should_save": true,
|
119 |
-
"should_training_stop":
|
120 |
},
|
121 |
"attributes": {}
|
122 |
}
|
123 |
},
|
124 |
-
"total_flos":
|
125 |
"train_batch_size": 2,
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.005489980785067252,
|
5 |
"eval_steps": 3,
|
6 |
+
"global_step": 10,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
102 |
"eval_samples_per_second": 6.419,
|
103 |
"eval_steps_per_second": 3.214,
|
104 |
"step": 9
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.005489980785067252,
|
108 |
+
"grad_norm": NaN,
|
109 |
+
"learning_rate": 0.0002,
|
110 |
+
"loss": 0.0,
|
111 |
+
"step": 10
|
112 |
}
|
113 |
],
|
114 |
"logging_steps": 1,
|
|
|
123 |
"should_evaluate": false,
|
124 |
"should_log": false,
|
125 |
"should_save": true,
|
126 |
+
"should_training_stop": true
|
127 |
},
|
128 |
"attributes": {}
|
129 |
}
|
130 |
},
|
131 |
+
"total_flos": 3398575325184000.0,
|
132 |
"train_batch_size": 2,
|
133 |
"trial_name": null,
|
134 |
"trial_params": null
|