Training in progress, step 36, 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 335604696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d652791bc2698526c64f894e7e5e113ef758f874a281b96e2952ca26f332efc
|
3 |
size 335604696
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 671466706
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de4a6fd98bf834f254bf3b8a25ffe718bd85c4639c1ca2d5b32ef12cd745438f
|
3 |
size 671466706
|
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 sha256:884ce308a4b9046b63daa8471de316c7b3c332361554edb94ea15c1aef43590c
|
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:f1fbe8f3807fcf2c9b342444bf912c2b4a5837aba74951c80e3f443bde6ab488
|
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": 0.
|
5 |
"eval_steps": 9,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -102,6 +102,35 @@
|
|
102 |
"eval_samples_per_second": 8.986,
|
103 |
"eval_steps_per_second": 4.493,
|
104 |
"step": 27
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
105 |
}
|
106 |
],
|
107 |
"logging_steps": 3,
|
@@ -121,7 +150,7 @@
|
|
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": 0.005045682700141034,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 36,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
102 |
"eval_samples_per_second": 8.986,
|
103 |
"eval_steps_per_second": 4.493,
|
104 |
"step": 27
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.004204735583450862,
|
108 |
+
"grad_norm": 1.0885648727416992,
|
109 |
+
"learning_rate": 0.0001923879532511287,
|
110 |
+
"loss": 1.4687,
|
111 |
+
"step": 30
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.004625209141795947,
|
115 |
+
"grad_norm": 1.1229428052902222,
|
116 |
+
"learning_rate": 0.00018724960070727972,
|
117 |
+
"loss": 1.336,
|
118 |
+
"step": 33
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 0.005045682700141034,
|
122 |
+
"grad_norm": 1.0429704189300537,
|
123 |
+
"learning_rate": 0.00018090169943749476,
|
124 |
+
"loss": 1.3521,
|
125 |
+
"step": 36
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 0.005045682700141034,
|
129 |
+
"eval_loss": 1.3701305389404297,
|
130 |
+
"eval_runtime": 3089.1504,
|
131 |
+
"eval_samples_per_second": 7.78,
|
132 |
+
"eval_steps_per_second": 3.89,
|
133 |
+
"step": 36
|
134 |
}
|
135 |
],
|
136 |
"logging_steps": 3,
|
|
|
150 |
"attributes": {}
|
151 |
}
|
152 |
},
|
153 |
+
"total_flos": 2.148510102234071e+17,
|
154 |
"train_batch_size": 2,
|
155 |
"trial_name": null,
|
156 |
"trial_params": null
|