Training in progress, step 1000, checkpoint
Browse files- last-checkpoint/global_step1000/zero_pp_rank_0_mp_rank_00_model_states.pt +2 -2
- last-checkpoint/global_step1000/zero_pp_rank_0_mp_rank_00_optim_states.pt +2 -2
- last-checkpoint/global_step1000/zero_pp_rank_1_mp_rank_00_model_states.pt +2 -2
- last-checkpoint/global_step1000/zero_pp_rank_1_mp_rank_00_optim_states.pt +2 -2
- last-checkpoint/global_step1000/zero_pp_rank_2_mp_rank_00_model_states.pt +2 -2
- last-checkpoint/global_step1000/zero_pp_rank_2_mp_rank_00_optim_states.pt +2 -2
- last-checkpoint/global_step1000/zero_pp_rank_3_mp_rank_00_model_states.pt +2 -2
- last-checkpoint/global_step1000/zero_pp_rank_3_mp_rank_00_optim_states.pt +2 -2
- last-checkpoint/latest +1 -1
- last-checkpoint/pytorch_model.bin +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/global_step1000/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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e711adf4fefec117f4add5c12dedb5da5e70ff2b1866235418a887be61cfde8e
|
3 |
+
size 77125
|
last-checkpoint/global_step1000/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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d137cb145da05f7f836eb60c4d288574b54011a5b641faa8369c997599bb82f6
|
3 |
+
size 181523565
|
last-checkpoint/global_step1000/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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:622a4ec60a3fc066da13c461156be860a713802aa4b5e1e72eb056c43b46c8ed
|
3 |
+
size 76997
|
last-checkpoint/global_step1000/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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:182c8b92d7cd26917d7a536a23e987a313aabd6b39a2ee7bec9cfb82dea18718
|
3 |
+
size 181523565
|
last-checkpoint/global_step1000/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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:262850a11ae6c31860de5585984df2e08ecffeb32d8e596bcab0b761131fa1aa
|
3 |
+
size 76997
|
last-checkpoint/global_step1000/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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ccb4d32aeb1f401f5288a9610d781bdacb2386a503f93e6a44adc668843d64ae
|
3 |
+
size 181523565
|
last-checkpoint/global_step1000/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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ef0c7c25da76a493883a8cea3b52a5d80f2696441a892c34e47d1f96bd1e219
|
3 |
+
size 76997
|
last-checkpoint/global_step1000/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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f505bdc2ab7b593cab353d7e4cdbe884dce14c77b7e75df63df6a07f9418908d
|
3 |
+
size 181523565
|
last-checkpoint/latest
CHANGED
@@ -1 +1 @@
|
|
1 |
-
|
|
|
1 |
+
global_step1000
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242070038
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9c2bbd8242bb5c02d5efae94f8f42fb03edd2c72266a812ab965e463320da46
|
3 |
size 242070038
|
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:dce2c50c7664fbb16a8b2e43e54b53331c5316cfb271b983da1e5fecb8f17cbd
|
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:c0840849d39e1eaa57787311e4d0c83224a6ddc9e6a9cb14192c8ed84be6eab9
|
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 sha256:9eab21c7407cea42cd27eaeed6921c9d828e73c23bb9f05f571d16961ccadac8
|
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 sha256:3aa9b8022f28fa939456417d280e7aafb2c4ebe7a3815d932c02df2e413189df
|
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":
|
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": 0.01,
|
14 |
"loss": 0.6125,
|
15 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
}
|
17 |
],
|
18 |
"logging_steps": 500,
|
19 |
"max_steps": 2500,
|
20 |
"num_train_epochs": 10,
|
21 |
"save_steps": 500,
|
22 |
-
"total_flos":
|
23 |
"trial_name": null,
|
24 |
"trial_params": null
|
25 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
13 |
"learning_rate": 0.01,
|
14 |
"loss": 0.6125,
|
15 |
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 4.0,
|
19 |
+
"learning_rate": 0.01,
|
20 |
+
"loss": 0.1287,
|
21 |
+
"step": 1000
|
22 |
}
|
23 |
],
|
24 |
"logging_steps": 500,
|
25 |
"max_steps": 2500,
|
26 |
"num_train_epochs": 10,
|
27 |
"save_steps": 500,
|
28 |
+
"total_flos": 169032155136.0,
|
29 |
"trial_name": null,
|
30 |
"trial_params": null
|
31 |
}
|