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 156926880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec9f3440048bf7a47186056baf2b9eef8186cf8f523ce482bbcca4546d94a4c4
|
3 |
size 156926880
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 79968964
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3aa452307c4856a068394e6f318773094290374039e33e05ad6abd2615182f87
|
3 |
size 79968964
|
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:ceb57d2842a4f826d5526cfcfd274ecc68423f46d491f3da39a57093dad590d1
|
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 sha256:705cabf5cbc3a6ab0feb67c77b9b453d59efcc939ce90d310af96e621810f990
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
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,
|
@@ -127,6 +127,28 @@
|
|
127 |
"eval_samples_per_second": 18.532,
|
128 |
"eval_steps_per_second": 9.266,
|
129 |
"step": 350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
130 |
}
|
131 |
],
|
132 |
"logging_steps": 40,
|
@@ -150,12 +172,12 @@
|
|
150 |
"should_evaluate": false,
|
151 |
"should_log": false,
|
152 |
"should_save": true,
|
153 |
-
"should_training_stop":
|
154 |
},
|
155 |
"attributes": {}
|
156 |
}
|
157 |
},
|
158 |
-
"total_flos":
|
159 |
"train_batch_size": 2,
|
160 |
"trial_name": null,
|
161 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.293401837348938,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-400",
|
4 |
+
"epoch": 0.18512090709244475,
|
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,
|
|
|
127 |
"eval_samples_per_second": 18.532,
|
128 |
"eval_steps_per_second": 9.266,
|
129 |
"step": 350
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.16660881638320027,
|
133 |
+
"grad_norm": 0.596440851688385,
|
134 |
+
"learning_rate": 3.8060233744356633e-06,
|
135 |
+
"loss": 0.286,
|
136 |
+
"step": 360
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.18512090709244475,
|
140 |
+
"grad_norm": 0.7190999388694763,
|
141 |
+
"learning_rate": 0.0,
|
142 |
+
"loss": 0.2512,
|
143 |
+
"step": 400
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.18512090709244475,
|
147 |
+
"eval_loss": 0.293401837348938,
|
148 |
+
"eval_runtime": 98.1497,
|
149 |
+
"eval_samples_per_second": 18.543,
|
150 |
+
"eval_steps_per_second": 9.272,
|
151 |
+
"step": 400
|
152 |
}
|
153 |
],
|
154 |
"logging_steps": 40,
|
|
|
172 |
"should_evaluate": false,
|
173 |
"should_log": false,
|
174 |
"should_save": true,
|
175 |
+
"should_training_stop": true
|
176 |
},
|
177 |
"attributes": {}
|
178 |
}
|
179 |
},
|
180 |
+
"total_flos": 7.94731890081792e+16,
|
181 |
"train_batch_size": 2,
|
182 |
"trial_name": null,
|
183 |
"trial_params": null
|