Training in progress, step 30, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 619632
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a17bd8b0a4ea439018f7919254f5e70c961ea58528c36c2db39e9acc46745e8
|
3 |
size 619632
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1389562
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6a9b5f70283bd007589f7a6a41f4942744b940f8df4ba913641d184514b0c26
|
3 |
size 1389562
|
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 sha256:94e1f22719e0ed86f234db56f205204fc1d86bc3be717ae7ea6986e60b3c9cf4
|
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 sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
|
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": 8,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -95,6 +95,20 @@
|
|
95 |
"eval_samples_per_second": 70.189,
|
96 |
"eval_steps_per_second": 35.094,
|
97 |
"step": 24
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
98 |
}
|
99 |
],
|
100 |
"logging_steps": 3,
|
@@ -109,12 +123,12 @@
|
|
109 |
"should_evaluate": false,
|
110 |
"should_log": false,
|
111 |
"should_save": true,
|
112 |
-
"should_training_stop":
|
113 |
},
|
114 |
"attributes": {}
|
115 |
}
|
116 |
},
|
117 |
-
"total_flos":
|
118 |
"train_batch_size": 2,
|
119 |
"trial_name": null,
|
120 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.001259860155522737,
|
5 |
"eval_steps": 8,
|
6 |
+
"global_step": 30,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
95 |
"eval_samples_per_second": 70.189,
|
96 |
"eval_steps_per_second": 35.094,
|
97 |
"step": 24
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.0011338741399704634,
|
101 |
+
"grad_norm": 0.2922826111316681,
|
102 |
+
"learning_rate": 7.022351411174866e-06,
|
103 |
+
"loss": 11.9077,
|
104 |
+
"step": 27
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.001259860155522737,
|
108 |
+
"grad_norm": 0.28928059339523315,
|
109 |
+
"learning_rate": 0.0,
|
110 |
+
"loss": 11.9037,
|
111 |
+
"step": 30
|
112 |
}
|
113 |
],
|
114 |
"logging_steps": 3,
|
|
|
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": 11425622261760.0,
|
132 |
"train_batch_size": 2,
|
133 |
"trial_name": null,
|
134 |
"trial_params": null
|