Commit
•
aa18b6c
1
Parent(s):
91c3149
Training in progress, step 3200, 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 sha256:1ffa24c6d65d6ebe046b12c298cf4ae161aa8f7a73a62399ba6434af84128daa
|
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 84581014
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ecd655e3d91e89f6e1fa258974b79bf0d215f8ace68f3d365b99110b5abe49ce
|
3 |
size 84581014
|
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 sha256:4c5ce141a264dd8520f51f3b5490a7f5208fde47774153324df63d2668f9a7d7
|
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 sha256:0770650b062be7cee981b3da10cdf7010bb9457e5bd03d190388904fc6d3b7aa
|
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": 2000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -112,6 +112,13 @@
|
|
112 |
"learning_rate": 1.9999990234026036e-05,
|
113 |
"loss": 1.586,
|
114 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
115 |
}
|
116 |
],
|
117 |
"logging_steps": 200,
|
@@ -119,7 +126,7 @@
|
|
119 |
"num_input_tokens_seen": 0,
|
120 |
"num_train_epochs": 5,
|
121 |
"save_steps": 200,
|
122 |
-
"total_flos":
|
123 |
"train_batch_size": 1,
|
124 |
"trial_name": null,
|
125 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0023797217956488276,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 3200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
112 |
"learning_rate": 1.9999990234026036e-05,
|
113 |
"loss": 1.586,
|
114 |
"step": 3000
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.0,
|
118 |
+
"grad_norm": 2.8140385150909424,
|
119 |
+
"learning_rate": 1.9999988884312347e-05,
|
120 |
+
"loss": 1.6221,
|
121 |
+
"step": 3200
|
122 |
}
|
123 |
],
|
124 |
"logging_steps": 200,
|
|
|
126 |
"num_input_tokens_seen": 0,
|
127 |
"num_train_epochs": 5,
|
128 |
"save_steps": 200,
|
129 |
+
"total_flos": 4.180089275793408e+16,
|
130 |
"train_batch_size": 1,
|
131 |
"trial_name": null,
|
132 |
"trial_params": null
|