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 125248064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18212cc92e50015c6d1e806a2f45145fd6485572b1d8eefeff4f1fde836246f3
|
3 |
size 125248064
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 64219860
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49cebe8315e0a228753510658d20f94e6c1329cda92034348d7cac3e4c181f5d
|
3 |
size 64219860
|
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 sha256:2b5680ac895463613d91eeb9054dc06bc19db700daeaf5c42ff7984ab49692a6
|
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 sha256:0dab003e9948eca4252e780eaf54f5324b8b378549ca6bfe1415f38792ae85c0
|
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": 13,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -60,6 +60,20 @@
|
|
60 |
"eval_samples_per_second": 18.527,
|
61 |
"eval_steps_per_second": 9.264,
|
62 |
"step": 39
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
63 |
}
|
64 |
],
|
65 |
"logging_steps": 10,
|
@@ -74,12 +88,12 @@
|
|
74 |
"should_evaluate": false,
|
75 |
"should_log": false,
|
76 |
"should_save": true,
|
77 |
-
"should_training_stop":
|
78 |
},
|
79 |
"attributes": {}
|
80 |
}
|
81 |
},
|
82 |
-
"total_flos": 1.
|
83 |
"train_batch_size": 2,
|
84 |
"trial_name": null,
|
85 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.015786565632646618,
|
5 |
"eval_steps": 13,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
60 |
"eval_samples_per_second": 18.527,
|
61 |
"eval_steps_per_second": 9.264,
|
62 |
"step": 39
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.012629252506117294,
|
66 |
+
"grad_norm": 3.1594045162200928,
|
67 |
+
"learning_rate": 0.00016,
|
68 |
+
"loss": 4.7908,
|
69 |
+
"step": 40
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.015786565632646618,
|
73 |
+
"grad_norm": 2.42171049118042,
|
74 |
+
"learning_rate": 0.0002,
|
75 |
+
"loss": 4.0147,
|
76 |
+
"step": 50
|
77 |
}
|
78 |
],
|
79 |
"logging_steps": 10,
|
|
|
88 |
"should_evaluate": false,
|
89 |
"should_log": false,
|
90 |
"should_save": true,
|
91 |
+
"should_training_stop": true
|
92 |
},
|
93 |
"attributes": {}
|
94 |
}
|
95 |
},
|
96 |
+
"total_flos": 1.591027713441792e+16,
|
97 |
"train_batch_size": 2,
|
98 |
"trial_name": null,
|
99 |
"trial_params": null
|