Training in progress, step 600, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +11 -3
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 109069176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b92808256b2749467ce498f7e305c4d430af5cad8977631581f0a4ccded83ce9
|
3 |
size 109069176
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 218182650
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c675c4921ca8387c3480b2c3116ef494f93f8ddbc73752bb6d0bf03bebce1c0
|
3 |
size 218182650
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19c6d6f5820e2cebdd06c9d92aee605ba1b273d3ac9b9ae4d9104075e7a753d8
|
3 |
size 15920
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04bb9a30beccc717ddf29532c37e03552110a28801d6f94e6fdc04bde4ddd620
|
3 |
size 15920
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f79f2872854aa193ec456a2c3d47113e82e0c4798a05904efa757f299c793dbd
|
3 |
size 15920
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d716009efb9cabe47fbf3d0b3f8f94c3acd64efaec1f6ed836d689ff5ef51aa6
|
3 |
size 15920
|
last-checkpoint/rng_state_4.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9db4ae4092b41e836e52a1ccbef8db9513f7b56773b49aa935128aa362a554c
|
3 |
size 15920
|
last-checkpoint/rng_state_5.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:641a6b4ba62400e8cc7baa6c8d426bcee521501541ec0b3a3677e92ca65313ff
|
3 |
size 15920
|
last-checkpoint/rng_state_6.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90cea7be477143329ebc3b0696b6fa0fa18e1f6e6189e8d6cddbdffd18be8507
|
3 |
size 15920
|
last-checkpoint/rng_state_7.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cecd2445a01d5d231740a4688b264b288356830c1121c762987952c0974a64f2
|
3 |
size 15920
|
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 sha256:4a0f0c9464984f5634a7f2f486171c72549cf80e1dd6d2d00d1f826da3914de3
|
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": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -54,6 +54,14 @@
|
|
54 |
"eval_samples_per_second": 12.835,
|
55 |
"eval_steps_per_second": 0.401,
|
56 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
}
|
58 |
],
|
59 |
"logging_steps": 500,
|
@@ -73,7 +81,7 @@
|
|
73 |
"attributes": {}
|
74 |
}
|
75 |
},
|
76 |
-
"total_flos":
|
77 |
"train_batch_size": 4,
|
78 |
"trial_name": null,
|
79 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.56657223796034,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
54 |
"eval_samples_per_second": 12.835,
|
55 |
"eval_steps_per_second": 0.401,
|
56 |
"step": 500
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.56657223796034,
|
60 |
+
"eval_loss": 0.35568130016326904,
|
61 |
+
"eval_runtime": 2.5164,
|
62 |
+
"eval_samples_per_second": 12.716,
|
63 |
+
"eval_steps_per_second": 0.397,
|
64 |
+
"step": 600
|
65 |
}
|
66 |
],
|
67 |
"logging_steps": 500,
|
|
|
81 |
"attributes": {}
|
82 |
}
|
83 |
},
|
84 |
+
"total_flos": 6.03985522666242e+17,
|
85 |
"train_batch_size": 4,
|
86 |
"trial_name": null,
|
87 |
"trial_params": null
|