Training in progress, step 384, 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 80013120
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ec4ac2ada50081a49c097e152cc228da090983b1e85f156ec63876ecd3a886d
|
3 |
size 80013120
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 41120084
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16ab9526ce43e132d14968409cc302b0bac6efc3dcaba90122e477d12a85c880
|
3 |
size 41120084
|
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 sha256:8a998259191065e76e244e9c999b23198a2d595e190aa35c9fb807331bd4bd7c
|
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:b3dda9dfb240315ac47574ce73fc102718f73245e6bf5a8299b69650f0cbd0dc
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.8627253174781799,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-288",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 96,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -60,6 +60,21 @@
|
|
60 |
"eval_samples_per_second": 22.882,
|
61 |
"eval_steps_per_second": 0.729,
|
62 |
"step": 288
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
63 |
}
|
64 |
],
|
65 |
"logging_steps": 96,
|
@@ -74,7 +89,7 @@
|
|
74 |
"early_stopping_threshold": 0.0
|
75 |
},
|
76 |
"attributes": {
|
77 |
-
"early_stopping_patience_counter":
|
78 |
}
|
79 |
},
|
80 |
"TrainerControl": {
|
@@ -88,7 +103,7 @@
|
|
88 |
"attributes": {}
|
89 |
}
|
90 |
},
|
91 |
-
"total_flos":
|
92 |
"train_batch_size": 8,
|
93 |
"trial_name": null,
|
94 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.8627253174781799,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-288",
|
4 |
+
"epoch": 2.064516129032258,
|
5 |
"eval_steps": 96,
|
6 |
+
"global_step": 384,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
60 |
"eval_samples_per_second": 22.882,
|
61 |
"eval_steps_per_second": 0.729,
|
62 |
"step": 288
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 2.064516129032258,
|
66 |
+
"grad_norm": 1.742639422416687,
|
67 |
+
"learning_rate": 0.0003997674540450395,
|
68 |
+
"loss": 1.2677,
|
69 |
+
"step": 384
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 2.064516129032258,
|
73 |
+
"eval_loss": 0.8888482451438904,
|
74 |
+
"eval_runtime": 6.8571,
|
75 |
+
"eval_samples_per_second": 22.896,
|
76 |
+
"eval_steps_per_second": 0.729,
|
77 |
+
"step": 384
|
78 |
}
|
79 |
],
|
80 |
"logging_steps": 96,
|
|
|
89 |
"early_stopping_threshold": 0.0
|
90 |
},
|
91 |
"attributes": {
|
92 |
+
"early_stopping_patience_counter": 1
|
93 |
}
|
94 |
},
|
95 |
"TrainerControl": {
|
|
|
103 |
"attributes": {}
|
104 |
}
|
105 |
},
|
106 |
+
"total_flos": 1.2500650432659456e+17,
|
107 |
"train_batch_size": 8,
|
108 |
"trial_name": null,
|
109 |
"trial_params": null
|