Training in progress, step 27, 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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09588d81e1d16506a542b52c6dfd385e9929558d5620fb98508c9ac84d949922
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37965300
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ca4116cf073b05c6cba4047f329bce7d25cdaf738f44652d55100e9efe35d76
|
3 |
size 37965300
|
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 sha256:7c2114e917b04734ecf6d6c29e2dec4f37e3e775e81af5b53e52453122fa4372
|
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 sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
|
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": 9,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -73,6 +73,35 @@
|
|
73 |
"eval_samples_per_second": 36.267,
|
74 |
"eval_steps_per_second": 4.749,
|
75 |
"step": 18
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
76 |
}
|
77 |
],
|
78 |
"logging_steps": 3,
|
@@ -92,7 +121,7 @@
|
|
92 |
"attributes": {}
|
93 |
}
|
94 |
},
|
95 |
-
"total_flos":
|
96 |
"train_batch_size": 8,
|
97 |
"trial_name": null,
|
98 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5454545454545454,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 27,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
73 |
"eval_samples_per_second": 36.267,
|
74 |
"eval_steps_per_second": 4.749,
|
75 |
"step": 18
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.42424242424242425,
|
79 |
+
"grad_norm": 1.645618200302124,
|
80 |
+
"learning_rate": 4.817959636416969e-05,
|
81 |
+
"loss": 3.6643,
|
82 |
+
"step": 21
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.48484848484848486,
|
86 |
+
"grad_norm": 1.723616361618042,
|
87 |
+
"learning_rate": 4.707368982147318e-05,
|
88 |
+
"loss": 3.5012,
|
89 |
+
"step": 24
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.5454545454545454,
|
93 |
+
"grad_norm": 1.6863574981689453,
|
94 |
+
"learning_rate": 4.572593931387604e-05,
|
95 |
+
"loss": 3.3348,
|
96 |
+
"step": 27
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 0.5454545454545454,
|
100 |
+
"eval_loss": 3.322596311569214,
|
101 |
+
"eval_runtime": 2.3165,
|
102 |
+
"eval_samples_per_second": 36.261,
|
103 |
+
"eval_steps_per_second": 4.748,
|
104 |
+
"step": 27
|
105 |
}
|
106 |
],
|
107 |
"logging_steps": 3,
|
|
|
121 |
"attributes": {}
|
122 |
}
|
123 |
},
|
124 |
+
"total_flos": 7053851718844416.0,
|
125 |
"train_batch_size": 8,
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|