Training in progress, step 9, 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 12609312
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92c2062267b2bf25bffe83d1e21e5c8428155f81238f95ebc880a18274777c38
|
3 |
size 12609312
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6615034
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd0bd2be686f25b38715ab87d4f6d1688bac21edac287f3ac970991aa3e759d0
|
3 |
size 6615034
|
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 sha256:06e7ade66bdcd1ed7916d485fdbed1a0c8411b8e3e11bf2219b7f09cea2cf514
|
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 sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
|
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,
|
@@ -65,6 +65,35 @@
|
|
65 |
"eval_samples_per_second": 46.317,
|
66 |
"eval_steps_per_second": 23.158,
|
67 |
"step": 6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
68 |
}
|
69 |
],
|
70 |
"logging_steps": 1,
|
@@ -84,7 +113,7 @@
|
|
84 |
"attributes": {}
|
85 |
}
|
86 |
},
|
87 |
-
"total_flos":
|
88 |
"train_batch_size": 2,
|
89 |
"trial_name": null,
|
90 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0015432098765432098,
|
5 |
"eval_steps": 3,
|
6 |
+
"global_step": 9,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
65 |
"eval_samples_per_second": 46.317,
|
66 |
"eval_steps_per_second": 23.158,
|
67 |
"step": 6
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 0.0012002743484224967,
|
71 |
+
"grad_norm": 53.89808654785156,
|
72 |
+
"learning_rate": 0.00014,
|
73 |
+
"loss": 17.6091,
|
74 |
+
"step": 7
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.0013717421124828531,
|
78 |
+
"grad_norm": 49.97898864746094,
|
79 |
+
"learning_rate": 0.00016,
|
80 |
+
"loss": 18.8421,
|
81 |
+
"step": 8
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.0015432098765432098,
|
85 |
+
"grad_norm": 60.67934036254883,
|
86 |
+
"learning_rate": 0.00018,
|
87 |
+
"loss": 17.5318,
|
88 |
+
"step": 9
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 0.0015432098765432098,
|
92 |
+
"eval_loss": 4.035857677459717,
|
93 |
+
"eval_runtime": 53.3948,
|
94 |
+
"eval_samples_per_second": 45.997,
|
95 |
+
"eval_steps_per_second": 22.999,
|
96 |
+
"step": 9
|
97 |
}
|
98 |
],
|
99 |
"logging_steps": 1,
|
|
|
113 |
"attributes": {}
|
114 |
}
|
115 |
},
|
116 |
+
"total_flos": 78955709202432.0,
|
117 |
"train_batch_size": 2,
|
118 |
"trial_name": null,
|
119 |
"trial_params": null
|