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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57781976340761cd098a72feb76553d4f53425a5d45a8e93249c4451ce921f35
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37965300
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35348baa2db227bef8cad106c1c1ecd8a3f3b7aacd4fd979feb32550b9c2add6
|
3 |
size 37965300
|
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 sha256:5f4f0e8dad369bc7bb59d5e7f497c51f10df0b55006fce373720fb706b727122
|
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": 36.261,
|
103 |
"eval_steps_per_second": 4.748,
|
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": 0.7272727272727273,
|
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": 36.261,
|
103 |
"eval_steps_per_second": 4.748,
|
104 |
"step": 27
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.6060606060606061,
|
108 |
+
"grad_norm": 1.399096131324768,
|
109 |
+
"learning_rate": 4.415111107797445e-05,
|
110 |
+
"loss": 3.1167,
|
111 |
+
"step": 30
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.6666666666666666,
|
115 |
+
"grad_norm": 1.5978809595108032,
|
116 |
+
"learning_rate": 4.2366459261474933e-05,
|
117 |
+
"loss": 2.9797,
|
118 |
+
"step": 33
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 0.7272727272727273,
|
122 |
+
"grad_norm": 1.3575938940048218,
|
123 |
+
"learning_rate": 4.039153688314145e-05,
|
124 |
+
"loss": 2.9187,
|
125 |
+
"step": 36
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 0.7272727272727273,
|
129 |
+
"eval_loss": 2.8548290729522705,
|
130 |
+
"eval_runtime": 2.3198,
|
131 |
+
"eval_samples_per_second": 36.21,
|
132 |
+
"eval_steps_per_second": 4.742,
|
133 |
+
"step": 36
|
134 |
}
|
135 |
],
|
136 |
"logging_steps": 3,
|
|
|
150 |
"attributes": {}
|
151 |
}
|
152 |
},
|
153 |
+
"total_flos": 9405135625125888.0,
|
154 |
"train_batch_size": 8,
|
155 |
"trial_name": null,
|
156 |
"trial_params": null
|