Training in progress, step 350, 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 50358496
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e46077fc1a3040eb50bb152c0a951dfe4bcd17e2c429b9d3cd532457b7af09a
|
3 |
size 50358496
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 25785082
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4a25b91608577961dddcd7505c54d0bd77f5208b7613312ad99fae5a2abe307
|
3 |
size 25785082
|
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 sha256:5a4c552b46c6720173c5a7c3347ea515913a4ebcfa74e90d8ad9d5f9099c799c
|
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 sha256:1a982b0cf4aa3113be3ccf8c7c44abbcbdbc330e78e6392b70eb543df2118de5
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 2.
|
3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 50,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -112,6 +112,21 @@
|
|
112 |
"eval_samples_per_second": 76.074,
|
113 |
"eval_steps_per_second": 38.037,
|
114 |
"step": 300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
115 |
}
|
116 |
],
|
117 |
"logging_steps": 40,
|
@@ -140,7 +155,7 @@
|
|
140 |
"attributes": {}
|
141 |
}
|
142 |
},
|
143 |
-
"total_flos":
|
144 |
"train_batch_size": 2,
|
145 |
"trial_name": null,
|
146 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.8305675983428955,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-350",
|
4 |
+
"epoch": 0.006758273454225972,
|
5 |
"eval_steps": 50,
|
6 |
+
"global_step": 350,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
112 |
"eval_samples_per_second": 76.074,
|
113 |
"eval_steps_per_second": 38.037,
|
114 |
"step": 300
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.006178992872435175,
|
118 |
+
"grad_norm": 36.9980354309082,
|
119 |
+
"learning_rate": 1.4644660940672627e-05,
|
120 |
+
"loss": 23.1427,
|
121 |
+
"step": 320
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.006758273454225972,
|
125 |
+
"eval_loss": 2.8305675983428955,
|
126 |
+
"eval_runtime": 571.9896,
|
127 |
+
"eval_samples_per_second": 76.246,
|
128 |
+
"eval_steps_per_second": 38.123,
|
129 |
+
"step": 350
|
130 |
}
|
131 |
],
|
132 |
"logging_steps": 40,
|
|
|
155 |
"attributes": {}
|
156 |
}
|
157 |
},
|
158 |
+
"total_flos": 7323141248385024.0,
|
159 |
"train_batch_size": 2,
|
160 |
"trial_name": null,
|
161 |
"trial_params": null
|