Training in progress, step 13, 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 119801528
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:950e4617781954a27a9ac6abd23431ba766a7d413757274b85e3fce2e0ed2ac1
|
3 |
size 119801528
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 61392180
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48b5d4d69c19c24e97033481def863ec720f135d9220487baf3d4f1cbdd95557
|
3 |
size 61392180
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14512
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbf292e60a5b5e6314aefbc37b4fc579e75af144d32efcfc6a1a516668fb23a2
|
3 |
size 14512
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14512
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18f45ca9f7dedecf3f5a0f4d3aafdadc47bcff92fd7c88caf48f08f3a19a3529
|
3 |
size 14512
|
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 sha256:339b579a534790054eb28e51de35d1a47ad1a4526ec1be6232e5e2a340410148
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 4,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -123,6 +123,13 @@
|
|
123 |
"eval_samples_per_second": 15.053,
|
124 |
"eval_steps_per_second": 3.851,
|
125 |
"step": 12
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
126 |
}
|
127 |
],
|
128 |
"logging_steps": 1,
|
@@ -137,12 +144,12 @@
|
|
137 |
"should_evaluate": false,
|
138 |
"should_log": false,
|
139 |
"should_save": true,
|
140 |
-
"should_training_stop":
|
141 |
},
|
142 |
"attributes": {}
|
143 |
}
|
144 |
},
|
145 |
-
"total_flos": 1.
|
146 |
"train_batch_size": 2,
|
147 |
"trial_name": null,
|
148 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0396039603960396,
|
5 |
"eval_steps": 4,
|
6 |
+
"global_step": 13,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
123 |
"eval_samples_per_second": 15.053,
|
124 |
"eval_steps_per_second": 3.851,
|
125 |
"step": 12
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 1.0396039603960396,
|
129 |
+
"grad_norm": 0.3245333433151245,
|
130 |
+
"learning_rate": 0.0,
|
131 |
+
"loss": 0.4369,
|
132 |
+
"step": 13
|
133 |
}
|
134 |
],
|
135 |
"logging_steps": 1,
|
|
|
144 |
"should_evaluate": false,
|
145 |
"should_log": false,
|
146 |
"should_save": true,
|
147 |
+
"should_training_stop": true
|
148 |
},
|
149 |
"attributes": {}
|
150 |
}
|
151 |
},
|
152 |
+
"total_flos": 1.1524843048534016e+17,
|
153 |
"train_batch_size": 2,
|
154 |
"trial_name": null,
|
155 |
"trial_params": null
|