Training in progress, step 400, 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 985240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbdd5a2675f08139b53e1eb543bd99c23bb281b0b3efba1812afa51490fdfa83
|
3 |
size 985240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 520860
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad4f5ccfda986566a1c23bc136fcf1417210ae97143253823eb50859f083455a
|
3 |
size 520860
|
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 sha256:29bc814ac5b3fee73d27e3e73ea4ea2fe862e50eb6b0c4f959420b4352ef131e
|
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:a3fee5bd878072b8250bd3fdb8b983de5fc1713711d901d255c0163a2d48a8d8
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 10.
|
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,
|
@@ -120,6 +120,21 @@
|
|
120 |
"eval_samples_per_second": 307.324,
|
121 |
"eval_steps_per_second": 9.629,
|
122 |
"step": 350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
123 |
}
|
124 |
],
|
125 |
"logging_steps": 50,
|
@@ -143,12 +158,12 @@
|
|
143 |
"should_evaluate": false,
|
144 |
"should_log": false,
|
145 |
"should_save": true,
|
146 |
-
"should_training_stop":
|
147 |
},
|
148 |
"attributes": {}
|
149 |
}
|
150 |
},
|
151 |
-
"total_flos":
|
152 |
"train_batch_size": 32,
|
153 |
"trial_name": null,
|
154 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 10.723381996154785,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-400",
|
4 |
+
"epoch": 0.6346687822292741,
|
5 |
"eval_steps": 50,
|
6 |
+
"global_step": 400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
120 |
"eval_samples_per_second": 307.324,
|
121 |
"eval_steps_per_second": 9.629,
|
122 |
"step": 350
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.6346687822292741,
|
126 |
+
"grad_norm": 1.3822325468063354,
|
127 |
+
"learning_rate": 0.000214,
|
128 |
+
"loss": 42.9207,
|
129 |
+
"step": 400
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.6346687822292741,
|
133 |
+
"eval_loss": 10.723381996154785,
|
134 |
+
"eval_runtime": 13.8167,
|
135 |
+
"eval_samples_per_second": 307.237,
|
136 |
+
"eval_steps_per_second": 9.626,
|
137 |
+
"step": 400
|
138 |
}
|
139 |
],
|
140 |
"logging_steps": 50,
|
|
|
158 |
"should_evaluate": false,
|
159 |
"should_log": false,
|
160 |
"should_save": true,
|
161 |
+
"should_training_stop": true
|
162 |
},
|
163 |
"attributes": {}
|
164 |
}
|
165 |
},
|
166 |
+
"total_flos": 96027348566016.0,
|
167 |
"train_batch_size": 32,
|
168 |
"trial_name": null,
|
169 |
"trial_params": null
|