Training in progress, step 200, 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 109009752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e64b485dcec301197c443c6d532b30b5ebe4fc7892c2cab11cecd964ca48844e
|
3 |
size 109009752
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 56088148
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9061a33aac14f4dacc704e8200c8f38644c31fd20abd3eec19f8a67a079627d7
|
3 |
size 56088148
|
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 sha256:230fad2577dd384b197611a64e7e540514b09db82a5f1ddee69fb545eaf7adee
|
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 sha256:4395a835cb23270ad78d61fd8ba3c35674db099521a41c14383a29bb6357421c
|
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": 1.
|
5 |
"eval_steps": 20,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -94,6 +94,21 @@
|
|
94 |
"eval_samples_per_second": 28.629,
|
95 |
"eval_steps_per_second": 0.916,
|
96 |
"step": 180
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
97 |
}
|
98 |
],
|
99 |
"logging_steps": 100,
|
@@ -122,7 +137,7 @@
|
|
122 |
"attributes": {}
|
123 |
}
|
124 |
},
|
125 |
-
"total_flos":
|
126 |
"train_batch_size": 8,
|
127 |
"trial_name": null,
|
128 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 6.367617970681749e-07,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
4 |
+
"epoch": 1.3468013468013469,
|
5 |
"eval_steps": 20,
|
6 |
+
"global_step": 200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
94 |
"eval_samples_per_second": 28.629,
|
95 |
"eval_steps_per_second": 0.916,
|
96 |
"step": 180
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 1.3468013468013469,
|
100 |
+
"grad_norm": 1.526053893030621e-05,
|
101 |
+
"learning_rate": 0.0002522394955933096,
|
102 |
+
"loss": 0.0,
|
103 |
+
"step": 200
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 1.3468013468013469,
|
107 |
+
"eval_loss": 6.367617970681749e-07,
|
108 |
+
"eval_runtime": 4.4095,
|
109 |
+
"eval_samples_per_second": 28.348,
|
110 |
+
"eval_steps_per_second": 0.907,
|
111 |
+
"step": 200
|
112 |
}
|
113 |
],
|
114 |
"logging_steps": 100,
|
|
|
137 |
"attributes": {}
|
138 |
}
|
139 |
},
|
140 |
+
"total_flos": 8.446090602872832e+16,
|
141 |
"train_batch_size": 8,
|
142 |
"trial_name": null,
|
143 |
"trial_params": null
|