Training in progress, step 468, 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 80792096
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b20adef7268665e54e1ff137252477a3e3563348e781ac3b29276ee188fc36af
|
3 |
size 80792096
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 42479810
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6cf12ab6ca82877d40c5fe5d04179a4513295bbe2d370676ece6bb693a20bf2
|
3 |
size 42479810
|
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 sha256:9248d13ed386c3d5c312dc5202288fad517aa1b0e8a09bc2ce9efb9e4fb7fc80
|
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 sha256:6ecd47c95aebd8e3753a5d56cff3c18fc6bdfa9fa8982b3ef9bdb25d0e761546
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.19086678326129913,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-364",
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 52,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -135,6 +135,21 @@
|
|
135 |
"eval_samples_per_second": 39.853,
|
136 |
"eval_steps_per_second": 1.302,
|
137 |
"step": 416
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
138 |
}
|
139 |
],
|
140 |
"logging_steps": 52,
|
@@ -149,7 +164,7 @@
|
|
149 |
"early_stopping_threshold": 0.0
|
150 |
},
|
151 |
"attributes": {
|
152 |
-
"early_stopping_patience_counter":
|
153 |
}
|
154 |
},
|
155 |
"TrainerControl": {
|
@@ -163,7 +178,7 @@
|
|
163 |
"attributes": {}
|
164 |
}
|
165 |
},
|
166 |
-
"total_flos": 1.
|
167 |
"train_batch_size": 8,
|
168 |
"trial_name": null,
|
169 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.19086678326129913,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-364",
|
4 |
+
"epoch": 0.9904761904761905,
|
5 |
"eval_steps": 52,
|
6 |
+
"global_step": 468,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
135 |
"eval_samples_per_second": 39.853,
|
136 |
"eval_steps_per_second": 1.302,
|
137 |
"step": 416
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.9904761904761905,
|
141 |
+
"grad_norm": 1.0497206449508667,
|
142 |
+
"learning_rate": 0.0003999397535081081,
|
143 |
+
"loss": 0.1806,
|
144 |
+
"step": 468
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.9904761904761905,
|
148 |
+
"eval_loss": 0.19806422293186188,
|
149 |
+
"eval_runtime": 9.5429,
|
150 |
+
"eval_samples_per_second": 41.707,
|
151 |
+
"eval_steps_per_second": 1.362,
|
152 |
+
"step": 468
|
153 |
}
|
154 |
],
|
155 |
"logging_steps": 52,
|
|
|
164 |
"early_stopping_threshold": 0.0
|
165 |
},
|
166 |
"attributes": {
|
167 |
+
"early_stopping_patience_counter": 2
|
168 |
}
|
169 |
},
|
170 |
"TrainerControl": {
|
|
|
178 |
"attributes": {}
|
179 |
}
|
180 |
},
|
181 |
+
"total_flos": 1.634592611232645e+17,
|
182 |
"train_batch_size": 8,
|
183 |
"trial_name": null,
|
184 |
"trial_params": null
|