Training in progress, step 40, 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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b447d7d316addbc66a21bd7e8321f06e652a336ffe5142dffca235ed075e07b1
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 335922386
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1761c6539343a88505b90894c93e1ccd5e70fd95fbdcbbe107accb5a732afcc5
|
3 |
size 335922386
|
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 sha256:3b5a1d05b4449fe5c23c9940b89b45ac69280f93864f11d840efc4f7cef005ef
|
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 sha256:7c792918044964431737f4cb39f3769dbfd230048b1125ac69a6439eb6c8534b
|
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": 13,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -101,6 +101,35 @@
|
|
101 |
"learning_rate": 0.0001,
|
102 |
"loss": 1.0924,
|
103 |
"step": 30
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
104 |
}
|
105 |
],
|
106 |
"logging_steps": 3,
|
@@ -120,7 +149,7 @@
|
|
120 |
"attributes": {}
|
121 |
}
|
122 |
},
|
123 |
-
"total_flos": 1.
|
124 |
"train_batch_size": 2,
|
125 |
"trial_name": null,
|
126 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.016974326331423723,
|
5 |
"eval_steps": 13,
|
6 |
+
"global_step": 40,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
101 |
"learning_rate": 0.0001,
|
102 |
"loss": 1.0924,
|
103 |
"step": 30
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 0.014003819223424571,
|
107 |
+
"grad_norm": 0.5470402240753174,
|
108 |
+
"learning_rate": 7.66554636144095e-05,
|
109 |
+
"loss": 1.1295,
|
110 |
+
"step": 33
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.015276893698281349,
|
114 |
+
"grad_norm": 0.4804340600967407,
|
115 |
+
"learning_rate": 5.4600950026045326e-05,
|
116 |
+
"loss": 1.1242,
|
117 |
+
"step": 36
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.016549968173138127,
|
121 |
+
"grad_norm": 0.5397576093673706,
|
122 |
+
"learning_rate": 3.5055195166981645e-05,
|
123 |
+
"loss": 1.1222,
|
124 |
+
"step": 39
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 0.016549968173138127,
|
128 |
+
"eval_loss": 1.1495966911315918,
|
129 |
+
"eval_runtime": 84.4872,
|
130 |
+
"eval_samples_per_second": 11.753,
|
131 |
+
"eval_steps_per_second": 5.883,
|
132 |
+
"step": 39
|
133 |
}
|
134 |
],
|
135 |
"logging_steps": 3,
|
|
|
149 |
"attributes": {}
|
150 |
}
|
151 |
},
|
152 |
+
"total_flos": 1.4930481581654016e+16,
|
153 |
"train_batch_size": 2,
|
154 |
"trial_name": null,
|
155 |
"trial_params": null
|