Commit
•
198a8f0
1
Parent(s):
7e36ebf
Training in progress, step 1800, 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 sha256:0d87d7b00b2cd87fc029fa649fcad601b3ab7944457ec983484f19f24a594882
|
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 sha256:665a4d9783c05d43fa2505e60c3df4f8fdb4f033e3075cab2b640d9f0f0ef616
|
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 sha256:3d6334547612743196cb899c468f052098297738886954360e857941f54e2a3c
|
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 sha256:3a72ce24312e683508adae33679f3e646acad48e43aa6427ea385038cc671f18
|
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,
|
@@ -63,6 +63,13 @@
|
|
63 |
"learning_rate": 1.9999997233256404e-05,
|
64 |
"loss": 1.6001,
|
65 |
"step": 1600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
}
|
67 |
],
|
68 |
"logging_steps": 200,
|
@@ -70,7 +77,7 @@
|
|
70 |
"num_input_tokens_seen": 0,
|
71 |
"num_train_epochs": 5,
|
72 |
"save_steps": 200,
|
73 |
-
"total_flos": 2.
|
74 |
"train_batch_size": 1,
|
75 |
"trial_name": null,
|
76 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0013385935100524654,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 1800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
63 |
"learning_rate": 1.9999997233256404e-05,
|
64 |
"loss": 1.6001,
|
65 |
"step": 1600
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.0,
|
69 |
+
"grad_norm": 3.046320676803589,
|
70 |
+
"learning_rate": 1.9999996494428805e-05,
|
71 |
+
"loss": 1.5682,
|
72 |
+
"step": 1800
|
73 |
}
|
74 |
],
|
75 |
"logging_steps": 200,
|
|
|
77 |
"num_input_tokens_seen": 0,
|
78 |
"num_train_epochs": 5,
|
79 |
"save_steps": 200,
|
80 |
+
"total_flos": 2.3336484713988096e+16,
|
81 |
"train_batch_size": 1,
|
82 |
"trial_name": null,
|
83 |
"trial_params": null
|