Training in progress, step 20, 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 250422888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51896c32ad4cd846f76d92f9021b8246277f2f73e690742d67c1339e96952c36
|
3 |
size 250422888
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 501168482
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50624f1c2df90bb7cd7a7d02ae229f1434e9c8b495c65f265ed2a9cf77d94c83
|
3 |
size 501168482
|
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 sha256:00b243aea78e1eb9c2783b2ede924fa98ed34ea4662672ae5272ac00736eb8da
|
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 sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -52,6 +52,43 @@
|
|
52 |
"eval_samples_per_second": 0.967,
|
53 |
"eval_steps_per_second": 0.242,
|
54 |
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
}
|
56 |
],
|
57 |
"logging_steps": 3,
|
@@ -80,7 +117,7 @@
|
|
80 |
"attributes": {}
|
81 |
}
|
82 |
},
|
83 |
-
"total_flos":
|
84 |
"train_batch_size": 4,
|
85 |
"trial_name": null,
|
86 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9966016411781311,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-20",
|
4 |
+
"epoch": 0.011778563015312132,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 20,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
52 |
"eval_samples_per_second": 0.967,
|
53 |
"eval_steps_per_second": 0.242,
|
54 |
"step": 10
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.007067137809187279,
|
58 |
+
"grad_norm": 0.687550961971283,
|
59 |
+
"learning_rate": 0.000163742398974869,
|
60 |
+
"loss": 4.218,
|
61 |
+
"step": 12
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.0088339222614841,
|
65 |
+
"grad_norm": 0.7470112442970276,
|
66 |
+
"learning_rate": 0.00013090169943749476,
|
67 |
+
"loss": 4.2488,
|
68 |
+
"step": 15
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.0088339222614841,
|
72 |
+
"eval_loss": 1.0176266431808472,
|
73 |
+
"eval_runtime": 1476.8735,
|
74 |
+
"eval_samples_per_second": 0.968,
|
75 |
+
"eval_steps_per_second": 0.242,
|
76 |
+
"step": 15
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 0.01060070671378092,
|
80 |
+
"grad_norm": 0.7785256505012512,
|
81 |
+
"learning_rate": 9.372094804706867e-05,
|
82 |
+
"loss": 3.9397,
|
83 |
+
"step": 18
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 0.011778563015312132,
|
87 |
+
"eval_loss": 0.9966016411781311,
|
88 |
+
"eval_runtime": 1480.9852,
|
89 |
+
"eval_samples_per_second": 0.966,
|
90 |
+
"eval_steps_per_second": 0.242,
|
91 |
+
"step": 20
|
92 |
}
|
93 |
],
|
94 |
"logging_steps": 3,
|
|
|
117 |
"attributes": {}
|
118 |
}
|
119 |
},
|
120 |
+
"total_flos": 5.0782317576192e+16,
|
121 |
"train_batch_size": 4,
|
122 |
"trial_name": null,
|
123 |
"trial_params": null
|