Training in progress, step 11, 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 sha256:646bfacf82a1e94e77a3b2d7787cc7efb55a52b3c5f27f51f364102945d43086
|
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:b18dabf3a6b95ad18ca23e8e4d600f8a8e5b56e9b3b237ba7d6922e4f80b7dcb
|
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:c343fb8c6aedf392cfa4eba3a40f135a7b8d0de6741b4a704ca2686251b22007
|
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:d0a9d96d7b49e547f8c59164525c3abb04c305815580e8f285ff69146152be3d
|
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 sha256:4968f693466c40cb971e90a0117e2a9be84fd1e9f8d5d00ed1cc54675e5c78ec
|
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": 3,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -102,6 +102,20 @@
|
|
102 |
"eval_samples_per_second": 15.423,
|
103 |
"eval_steps_per_second": 3.856,
|
104 |
"step": 9
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
105 |
}
|
106 |
],
|
107 |
"logging_steps": 1,
|
@@ -116,12 +130,12 @@
|
|
116 |
"should_evaluate": false,
|
117 |
"should_log": false,
|
118 |
"should_save": true,
|
119 |
-
"should_training_stop":
|
120 |
},
|
121 |
"attributes": {}
|
122 |
}
|
123 |
},
|
124 |
-
"total_flos":
|
125 |
"train_batch_size": 2,
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0678466076696165,
|
5 |
"eval_steps": 3,
|
6 |
+
"global_step": 11,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
102 |
"eval_samples_per_second": 15.423,
|
103 |
"eval_steps_per_second": 3.856,
|
104 |
"step": 9
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.943952802359882,
|
108 |
+
"grad_norm": 0.15376947820186615,
|
109 |
+
"learning_rate": 0.0001,
|
110 |
+
"loss": 0.5393,
|
111 |
+
"step": 10
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 1.0678466076696165,
|
115 |
+
"grad_norm": 0.3497083783149719,
|
116 |
+
"learning_rate": 0.0,
|
117 |
+
"loss": 1.117,
|
118 |
+
"step": 11
|
119 |
}
|
120 |
],
|
121 |
"logging_steps": 1,
|
|
|
130 |
"should_evaluate": false,
|
131 |
"should_log": false,
|
132 |
"should_save": true,
|
133 |
+
"should_training_stop": true
|
134 |
},
|
135 |
"attributes": {}
|
136 |
}
|
137 |
},
|
138 |
+
"total_flos": 9.705131010844262e+16,
|
139 |
"train_batch_size": 2,
|
140 |
"trial_name": null,
|
141 |
"trial_params": null
|