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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:469e7dd91aa572d6191400c5592f42f6367c5b512d0b3e3754164730afec36e1
|
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 85723284
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64e643926dc49696042c46904dfba898d929489cbed217a895b933c5c1213445
|
3 |
size 85723284
|
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:d74b05f2720b311440022765a28fc8006a7374957aaca6aca1b5e6bc5db4cbaa
|
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:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
|
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": 13.975,
|
103 |
"eval_steps_per_second": 1.747,
|
104 |
"step": 27
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
105 |
}
|
106 |
],
|
107 |
"logging_steps": 3,
|
@@ -121,7 +150,7 @@
|
|
121 |
"attributes": {}
|
122 |
}
|
123 |
},
|
124 |
-
"total_flos":
|
125 |
"train_batch_size": 8,
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.026785714285714284,
|
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": 13.975,
|
103 |
"eval_steps_per_second": 1.747,
|
104 |
"step": 27
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.022321428571428572,
|
108 |
+
"grad_norm": 7.104370594024658,
|
109 |
+
"learning_rate": 4.415111107797445e-05,
|
110 |
+
"loss": 4.8921,
|
111 |
+
"step": 30
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.024553571428571428,
|
115 |
+
"grad_norm": 5.608682632446289,
|
116 |
+
"learning_rate": 4.2366459261474933e-05,
|
117 |
+
"loss": 4.841,
|
118 |
+
"step": 33
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 0.026785714285714284,
|
122 |
+
"grad_norm": 4.773255825042725,
|
123 |
+
"learning_rate": 4.039153688314145e-05,
|
124 |
+
"loss": 4.5234,
|
125 |
+
"step": 36
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 0.026785714285714284,
|
129 |
+
"eval_loss": 4.577538967132568,
|
130 |
+
"eval_runtime": 162.4812,
|
131 |
+
"eval_samples_per_second": 13.934,
|
132 |
+
"eval_steps_per_second": 1.742,
|
133 |
+
"step": 36
|
134 |
}
|
135 |
],
|
136 |
"logging_steps": 3,
|
|
|
150 |
"attributes": {}
|
151 |
}
|
152 |
},
|
153 |
+
"total_flos": 5.341588441635226e+16,
|
154 |
"train_batch_size": 8,
|
155 |
"trial_name": null,
|
156 |
"trial_params": null
|