Training in progress, step 50, 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 25192496
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72cce70edf885e6d5e368fc7d198cd54ee3858cb3aba51c736827867afd28131
|
3 |
size 25192496
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13005178
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b40025af533b01f400d39bb688555f87fbbf06c7cc38a52d7c1123295bd8140a
|
3 |
size 13005178
|
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 sha256:3cdc474ae9c7c4c5dce8ee1b92fc582cc5a7070a8a041f336e8add72dd026f48
|
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:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
|
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": 10,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -88,6 +88,43 @@
|
|
88 |
"learning_rate": 3.086582838174551e-05,
|
89 |
"loss": 1.0722,
|
90 |
"step": 35
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
91 |
}
|
92 |
],
|
93 |
"logging_steps": 5,
|
@@ -102,12 +139,12 @@
|
|
102 |
"should_evaluate": false,
|
103 |
"should_log": false,
|
104 |
"should_save": true,
|
105 |
-
"should_training_stop":
|
106 |
},
|
107 |
"attributes": {}
|
108 |
}
|
109 |
},
|
110 |
-
"total_flos":
|
111 |
"train_batch_size": 2,
|
112 |
"trial_name": null,
|
113 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0025035049068696173,
|
5 |
"eval_steps": 10,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
88 |
"learning_rate": 3.086582838174551e-05,
|
89 |
"loss": 1.0722,
|
90 |
"step": 35
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 0.002002803925495694,
|
94 |
+
"grad_norm": 7.799614429473877,
|
95 |
+
"learning_rate": 1.4644660940672627e-05,
|
96 |
+
"loss": 1.3549,
|
97 |
+
"step": 40
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.002002803925495694,
|
101 |
+
"eval_loss": 0.22272062301635742,
|
102 |
+
"eval_runtime": 192.2797,
|
103 |
+
"eval_samples_per_second": 43.738,
|
104 |
+
"eval_steps_per_second": 21.869,
|
105 |
+
"step": 40
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.002253154416182656,
|
109 |
+
"grad_norm": 7.140362739562988,
|
110 |
+
"learning_rate": 3.8060233744356633e-06,
|
111 |
+
"loss": 0.9179,
|
112 |
+
"step": 45
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 0.0025035049068696173,
|
116 |
+
"grad_norm": 14.939079284667969,
|
117 |
+
"learning_rate": 0.0,
|
118 |
+
"loss": 1.0639,
|
119 |
+
"step": 50
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 0.0025035049068696173,
|
123 |
+
"eval_loss": 0.2170257270336151,
|
124 |
+
"eval_runtime": 191.8145,
|
125 |
+
"eval_samples_per_second": 43.844,
|
126 |
+
"eval_steps_per_second": 21.922,
|
127 |
+
"step": 50
|
128 |
}
|
129 |
],
|
130 |
"logging_steps": 5,
|
|
|
139 |
"should_evaluate": false,
|
140 |
"should_log": false,
|
141 |
"should_save": true,
|
142 |
+
"should_training_stop": true
|
143 |
},
|
144 |
"attributes": {}
|
145 |
}
|
146 |
},
|
147 |
+
"total_flos": 1492861845504000.0,
|
148 |
"train_batch_size": 2,
|
149 |
"trial_name": null,
|
150 |
"trial_params": null
|