Training in progress, step 2000, checkpoint
Browse files- last-checkpoint/adapter_model.bin +1 -1
- last-checkpoint/global_step2000/zero_pp_rank_0_mp_rank_00_model_states.pt +1 -1
- last-checkpoint/global_step2000/zero_pp_rank_0_mp_rank_00_optim_states.pt +1 -1
- last-checkpoint/global_step2000/zero_pp_rank_1_mp_rank_00_model_states.pt +1 -1
- last-checkpoint/global_step2000/zero_pp_rank_1_mp_rank_00_optim_states.pt +1 -1
- last-checkpoint/global_step2000/zero_pp_rank_2_mp_rank_00_model_states.pt +1 -1
- last-checkpoint/global_step2000/zero_pp_rank_2_mp_rank_00_optim_states.pt +1 -1
- last-checkpoint/global_step2000/zero_pp_rank_3_mp_rank_00_model_states.pt +1 -1
- last-checkpoint/global_step2000/zero_pp_rank_3_mp_rank_00_optim_states.pt +1 -1
- last-checkpoint/latest +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/trainer_state.json +9 -3
last-checkpoint/adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2141578
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7328d3c4c1f327c39e82a120e4c4a584216b22fac4f3446fd72c1dcb57e70f32
|
3 |
size 2141578
|
last-checkpoint/global_step2000/zero_pp_rank_0_mp_rank_00_model_states.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3369573916
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c631555bb216228fd776c70fdb0e256ee4e31d790108950abfa77b028c501d3
|
3 |
size 3369573916
|
last-checkpoint/global_step2000/zero_pp_rank_0_mp_rank_00_optim_states.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3149677
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3080ba6a4f448c0f1f9e781443c976f2fd5a79ea723a6a49542f4c026632d021
|
3 |
size 3149677
|
last-checkpoint/global_step2000/zero_pp_rank_1_mp_rank_00_model_states.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3369573916
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be005c1c969525d4152a78bec86f4a9dbe8b58678eb89bb1bffa0b9953b40ba3
|
3 |
size 3369573916
|
last-checkpoint/global_step2000/zero_pp_rank_1_mp_rank_00_optim_states.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3149677
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc4c18a4ef0f9857edeb68da455dc4e7080151c87a75e93f7b1ce4cbf4ab2461
|
3 |
size 3149677
|
last-checkpoint/global_step2000/zero_pp_rank_2_mp_rank_00_model_states.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3369573916
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7169575885257a5886f2a16d9e9ac0ec0650b4840c49e3cf46173bb490042a1f
|
3 |
size 3369573916
|
last-checkpoint/global_step2000/zero_pp_rank_2_mp_rank_00_optim_states.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3149677
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a397d278e62116e1535866690747e07fcc337e68d0d6a1bc83659b5bce2d0fc8
|
3 |
size 3149677
|
last-checkpoint/global_step2000/zero_pp_rank_3_mp_rank_00_model_states.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3369573916
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93bf1650107328c65c26fa2f710cf3bf59bb92597b39fbc8120f97a1c8179044
|
3 |
size 3369573916
|
last-checkpoint/global_step2000/zero_pp_rank_3_mp_rank_00_optim_states.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3149677
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a216e45206c382e0569c4be9c261a3ff128aafd1935e65cab66c418f586fd578
|
3 |
size 3149677
|
last-checkpoint/latest
CHANGED
@@ -1 +1 @@
|
|
1 |
-
|
|
|
1 |
+
global_step2000
|
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 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50c45dee7a55d713aa15eaefbdbd4b45df9e67d02bb6ccefa86e1468c6ea416f
|
3 |
size 15024
|
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 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abb041f181920f1b36237d3ff78db879a26def694eccb0894945dbd4a97cc65a
|
3 |
size 15024
|
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 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3399d3d8d8d656a349c7e785e13454283813d091435a0af845c955519e7653c
|
3 |
size 15024
|
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 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1eea31e444764e3e1f1ec7465ddb8eefb5bbbefde013a11a62c8a1b296356b1
|
3 |
size 15024
|
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": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -13,13 +13,19 @@
|
|
13 |
"learning_rate": 0.0001,
|
14 |
"loss": 0.3412,
|
15 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
}
|
17 |
],
|
18 |
"logging_steps": 1000,
|
19 |
"max_steps": 12790,
|
20 |
"num_train_epochs": 5,
|
21 |
"save_steps": 1000,
|
22 |
-
"total_flos":
|
23 |
"trial_name": null,
|
24 |
"trial_params": null
|
25 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7818608287724785,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 2000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
13 |
"learning_rate": 0.0001,
|
14 |
"loss": 0.3412,
|
15 |
"step": 1000
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.78,
|
19 |
+
"learning_rate": 0.0001,
|
20 |
+
"loss": 0.1473,
|
21 |
+
"step": 2000
|
22 |
}
|
23 |
],
|
24 |
"logging_steps": 1000,
|
25 |
"max_steps": 12790,
|
26 |
"num_train_epochs": 5,
|
27 |
"save_steps": 1000,
|
28 |
+
"total_flos": 26238293901312.0,
|
29 |
"trial_name": null,
|
30 |
"trial_params": null
|
31 |
}
|