Upload folder using huggingface_hub
Browse files- checkpoint-20000/global_step20000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- checkpoint-20000/global_step20000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- checkpoint-20000/global_step20000/mp_rank_00_model_states.pt +3 -0
- checkpoint-20000/latest +1 -0
- checkpoint-20000/pytorch_model.bin +3 -0
- checkpoint-20000/rng_state_0.pth +3 -0
- checkpoint-20000/rng_state_1.pth +3 -0
- checkpoint-20000/scheduler.pt +3 -0
- checkpoint-20000/trainer_state.json +3635 -0
- checkpoint-20000/training_args.bin +3 -0
- checkpoint-20000/zero_to_fp32.py +760 -0
- checkpoint-30000/global_step30000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- checkpoint-30000/global_step30000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- checkpoint-30000/global_step30000/mp_rank_00_model_states.pt +3 -0
- checkpoint-30000/latest +1 -0
- checkpoint-30000/pytorch_model.bin +3 -0
- checkpoint-30000/rng_state_0.pth +3 -0
- checkpoint-30000/rng_state_1.pth +3 -0
- checkpoint-30000/scheduler.pt +3 -0
- checkpoint-30000/trainer_state.json +0 -0
- checkpoint-30000/training_args.bin +3 -0
- checkpoint-30000/zero_to_fp32.py +760 -0
- checkpoint-38184/global_step38184/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- checkpoint-38184/global_step38184/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- checkpoint-38184/global_step38184/mp_rank_00_model_states.pt +3 -0
- checkpoint-38184/latest +1 -0
- checkpoint-38184/pytorch_model.bin +3 -0
- checkpoint-38184/rng_state_0.pth +3 -0
- checkpoint-38184/rng_state_1.pth +3 -0
- checkpoint-38184/scheduler.pt +3 -0
- checkpoint-38184/trainer_state.json +0 -0
- checkpoint-38184/training_args.bin +3 -0
- checkpoint-38184/zero_to_fp32.py +760 -0
- model_with_lora.bin +3 -0
- runs/Mar07_05-23-18_886823f2c465/events.out.tfevents.1741292890.886823f2c465.10378.0 +3 -0
- trainer_state.json +0 -0
checkpoint-20000/global_step20000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a82034f591875a14d9f4a49e8d9dbc568934b84935d7410da278234c9358c84
|
| 3 |
+
size 8005108236
|
checkpoint-20000/global_step20000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:982ca4f12681c7fcc3fba0075236cceb81df4951e4eb4ce11af34a01f5470d03
|
| 3 |
+
size 8005064076
|
checkpoint-20000/global_step20000/mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63ea0428c56c789a1d9eba212618848ddf13a5ed0af9c66995979dbae0d155ec
|
| 3 |
+
size 2668900764
|
checkpoint-20000/latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step20000
|
checkpoint-20000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21a001af098ab0ac11193ce7a5b60b2ae0e45c9bc7355655eef6036deb4dc7dc
|
| 3 |
+
size 17678656921
|
checkpoint-20000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da837a3dc60030878e2e36dde59c7a42c5b2a0990a58ec999c8d40cbbd08cbae
|
| 3 |
+
size 14448
|
checkpoint-20000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5324a6dcbd22295551b4869a476cd5a0bd46ef0c171d9e99fc907d329900026
|
| 3 |
+
size 14448
|
checkpoint-20000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe06eb3768bad55eda84c238768081d2f935f4d0698457552be2007b79bd641d
|
| 3 |
+
size 1064
|
checkpoint-20000/trainer_state.json
ADDED
|
@@ -0,0 +1,3635 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.01002925168722868,
|
| 3 |
+
"best_model_checkpoint": "/workspace/previous_works/RadFM/output/RadFM-Llama3-8B-pretrain-0002-embed_tokens-depth32-lora-8ep-maxlen2048/checkpoint-20000",
|
| 4 |
+
"epoch": 4.190236748376283,
|
| 5 |
+
"eval_steps": 10000,
|
| 6 |
+
"global_step": 20000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.008170961659333752,
|
| 13 |
+
"grad_norm": 42.493404388427734,
|
| 14 |
+
"learning_rate": 3.4031413612565448e-06,
|
| 15 |
+
"loss": 2.5663,
|
| 16 |
+
"step": 39
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.016341923318667503,
|
| 20 |
+
"grad_norm": 4.584639072418213,
|
| 21 |
+
"learning_rate": 6.8062827225130895e-06,
|
| 22 |
+
"loss": 1.8589,
|
| 23 |
+
"step": 78
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.02451288497800126,
|
| 27 |
+
"grad_norm": 4.140661239624023,
|
| 28 |
+
"learning_rate": 1.0209424083769634e-05,
|
| 29 |
+
"loss": 1.1348,
|
| 30 |
+
"step": 117
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.03268384663733501,
|
| 34 |
+
"grad_norm": 4.312882423400879,
|
| 35 |
+
"learning_rate": 1.3612565445026179e-05,
|
| 36 |
+
"loss": 0.8666,
|
| 37 |
+
"step": 156
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.04085480829666876,
|
| 41 |
+
"grad_norm": 5.689533710479736,
|
| 42 |
+
"learning_rate": 1.7015706806282724e-05,
|
| 43 |
+
"loss": 0.7726,
|
| 44 |
+
"step": 195
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.04902576995600252,
|
| 48 |
+
"grad_norm": 3.757542133331299,
|
| 49 |
+
"learning_rate": 2.0418848167539268e-05,
|
| 50 |
+
"loss": 0.7232,
|
| 51 |
+
"step": 234
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.05719673161533627,
|
| 55 |
+
"grad_norm": 3.461946487426758,
|
| 56 |
+
"learning_rate": 2.382198952879581e-05,
|
| 57 |
+
"loss": 0.6182,
|
| 58 |
+
"step": 273
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.06536769327467001,
|
| 62 |
+
"grad_norm": 2.7702128887176514,
|
| 63 |
+
"learning_rate": 2.7225130890052358e-05,
|
| 64 |
+
"loss": 0.6639,
|
| 65 |
+
"step": 312
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.07353865493400377,
|
| 69 |
+
"grad_norm": 3.7390189170837402,
|
| 70 |
+
"learning_rate": 3.0628272251308905e-05,
|
| 71 |
+
"loss": 0.5924,
|
| 72 |
+
"step": 351
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.08170961659333752,
|
| 76 |
+
"grad_norm": 2.9384899139404297,
|
| 77 |
+
"learning_rate": 3.403141361256545e-05,
|
| 78 |
+
"loss": 0.594,
|
| 79 |
+
"step": 390
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.08988057825267128,
|
| 83 |
+
"grad_norm": 4.2483930587768555,
|
| 84 |
+
"learning_rate": 3.743455497382199e-05,
|
| 85 |
+
"loss": 0.5782,
|
| 86 |
+
"step": 429
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.09805153991200503,
|
| 90 |
+
"grad_norm": 2.8193845748901367,
|
| 91 |
+
"learning_rate": 4.0837696335078535e-05,
|
| 92 |
+
"loss": 0.6084,
|
| 93 |
+
"step": 468
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.10622250157133878,
|
| 97 |
+
"grad_norm": 2.6130402088165283,
|
| 98 |
+
"learning_rate": 4.424083769633508e-05,
|
| 99 |
+
"loss": 0.5876,
|
| 100 |
+
"step": 507
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.11439346323067254,
|
| 104 |
+
"grad_norm": 2.0634474754333496,
|
| 105 |
+
"learning_rate": 4.764397905759162e-05,
|
| 106 |
+
"loss": 0.5596,
|
| 107 |
+
"step": 546
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.12256442489000628,
|
| 111 |
+
"grad_norm": 3.275634288787842,
|
| 112 |
+
"learning_rate": 5.104712041884817e-05,
|
| 113 |
+
"loss": 0.6195,
|
| 114 |
+
"step": 585
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.13073538654934003,
|
| 118 |
+
"grad_norm": 2.8859968185424805,
|
| 119 |
+
"learning_rate": 5.4450261780104716e-05,
|
| 120 |
+
"loss": 0.5626,
|
| 121 |
+
"step": 624
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.13890634820867379,
|
| 125 |
+
"grad_norm": 2.7095537185668945,
|
| 126 |
+
"learning_rate": 5.785340314136126e-05,
|
| 127 |
+
"loss": 0.5534,
|
| 128 |
+
"step": 663
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.14707730986800754,
|
| 132 |
+
"grad_norm": 2.249742031097412,
|
| 133 |
+
"learning_rate": 6.125654450261781e-05,
|
| 134 |
+
"loss": 0.5859,
|
| 135 |
+
"step": 702
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1552482715273413,
|
| 139 |
+
"grad_norm": 3.251708745956421,
|
| 140 |
+
"learning_rate": 6.465968586387435e-05,
|
| 141 |
+
"loss": 0.5644,
|
| 142 |
+
"step": 741
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.16341923318667503,
|
| 146 |
+
"grad_norm": 2.18890380859375,
|
| 147 |
+
"learning_rate": 6.80628272251309e-05,
|
| 148 |
+
"loss": 0.5465,
|
| 149 |
+
"step": 780
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.1715901948460088,
|
| 153 |
+
"grad_norm": 1.5962858200073242,
|
| 154 |
+
"learning_rate": 7.146596858638743e-05,
|
| 155 |
+
"loss": 0.5377,
|
| 156 |
+
"step": 819
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.17976115650534255,
|
| 160 |
+
"grad_norm": 1.8569731712341309,
|
| 161 |
+
"learning_rate": 7.486910994764398e-05,
|
| 162 |
+
"loss": 0.5627,
|
| 163 |
+
"step": 858
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.1879321181646763,
|
| 167 |
+
"grad_norm": 2.0382535457611084,
|
| 168 |
+
"learning_rate": 7.827225130890053e-05,
|
| 169 |
+
"loss": 0.5778,
|
| 170 |
+
"step": 897
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.19610307982401007,
|
| 174 |
+
"grad_norm": 2.0339195728302,
|
| 175 |
+
"learning_rate": 8.167539267015707e-05,
|
| 176 |
+
"loss": 0.5407,
|
| 177 |
+
"step": 936
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.2042740414833438,
|
| 181 |
+
"grad_norm": 2.1229023933410645,
|
| 182 |
+
"learning_rate": 8.507853403141361e-05,
|
| 183 |
+
"loss": 0.6132,
|
| 184 |
+
"step": 975
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.21244500314267756,
|
| 188 |
+
"grad_norm": 1.6219509840011597,
|
| 189 |
+
"learning_rate": 8.848167539267016e-05,
|
| 190 |
+
"loss": 0.6153,
|
| 191 |
+
"step": 1014
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.22061596480201132,
|
| 195 |
+
"grad_norm": 2.0772364139556885,
|
| 196 |
+
"learning_rate": 9.18848167539267e-05,
|
| 197 |
+
"loss": 0.533,
|
| 198 |
+
"step": 1053
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.22878692646134507,
|
| 202 |
+
"grad_norm": 2.073230504989624,
|
| 203 |
+
"learning_rate": 9.528795811518324e-05,
|
| 204 |
+
"loss": 0.5661,
|
| 205 |
+
"step": 1092
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.2369578881206788,
|
| 209 |
+
"grad_norm": 1.96063232421875,
|
| 210 |
+
"learning_rate": 9.86910994764398e-05,
|
| 211 |
+
"loss": 0.5962,
|
| 212 |
+
"step": 1131
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.24512884978001256,
|
| 216 |
+
"grad_norm": 1.5799710750579834,
|
| 217 |
+
"learning_rate": 9.999989639826398e-05,
|
| 218 |
+
"loss": 0.552,
|
| 219 |
+
"step": 1170
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.2532998114393463,
|
| 223 |
+
"grad_norm": 1.5227395296096802,
|
| 224 |
+
"learning_rate": 9.999928612073995e-05,
|
| 225 |
+
"loss": 0.5739,
|
| 226 |
+
"step": 1209
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.26147077309868005,
|
| 230 |
+
"grad_norm": 1.7215867042541504,
|
| 231 |
+
"learning_rate": 9.99981287046695e-05,
|
| 232 |
+
"loss": 0.5363,
|
| 233 |
+
"step": 1248
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.26964173475801384,
|
| 237 |
+
"grad_norm": 1.5819590091705322,
|
| 238 |
+
"learning_rate": 9.999642416271812e-05,
|
| 239 |
+
"loss": 0.5223,
|
| 240 |
+
"step": 1287
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.27781269641734757,
|
| 244 |
+
"grad_norm": 1.3706092834472656,
|
| 245 |
+
"learning_rate": 9.999417251353851e-05,
|
| 246 |
+
"loss": 0.5236,
|
| 247 |
+
"step": 1326
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.28598365807668136,
|
| 251 |
+
"grad_norm": 1.57364022731781,
|
| 252 |
+
"learning_rate": 9.999137378177029e-05,
|
| 253 |
+
"loss": 0.5454,
|
| 254 |
+
"step": 1365
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.2941546197360151,
|
| 258 |
+
"grad_norm": 1.2142678499221802,
|
| 259 |
+
"learning_rate": 9.998802799803979e-05,
|
| 260 |
+
"loss": 0.5247,
|
| 261 |
+
"step": 1404
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.3023255813953488,
|
| 265 |
+
"grad_norm": 1.275280237197876,
|
| 266 |
+
"learning_rate": 9.998413519895968e-05,
|
| 267 |
+
"loss": 0.5048,
|
| 268 |
+
"step": 1443
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.3104965430546826,
|
| 272 |
+
"grad_norm": 1.4138684272766113,
|
| 273 |
+
"learning_rate": 9.997969542712856e-05,
|
| 274 |
+
"loss": 0.5675,
|
| 275 |
+
"step": 1482
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.31866750471401634,
|
| 279 |
+
"grad_norm": 1.2247836589813232,
|
| 280 |
+
"learning_rate": 9.997470873113055e-05,
|
| 281 |
+
"loss": 0.523,
|
| 282 |
+
"step": 1521
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.32683846637335007,
|
| 286 |
+
"grad_norm": 1.1925996541976929,
|
| 287 |
+
"learning_rate": 9.996917516553468e-05,
|
| 288 |
+
"loss": 0.5555,
|
| 289 |
+
"step": 1560
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.33500942803268385,
|
| 293 |
+
"grad_norm": 1.0786908864974976,
|
| 294 |
+
"learning_rate": 9.996309479089436e-05,
|
| 295 |
+
"loss": 0.4793,
|
| 296 |
+
"step": 1599
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.3431803896920176,
|
| 300 |
+
"grad_norm": 1.1928977966308594,
|
| 301 |
+
"learning_rate": 9.995646767374671e-05,
|
| 302 |
+
"loss": 0.4938,
|
| 303 |
+
"step": 1638
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.35135135135135137,
|
| 307 |
+
"grad_norm": 1.0230952501296997,
|
| 308 |
+
"learning_rate": 9.994929388661176e-05,
|
| 309 |
+
"loss": 0.5405,
|
| 310 |
+
"step": 1677
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.3595223130106851,
|
| 314 |
+
"grad_norm": 1.436375379562378,
|
| 315 |
+
"learning_rate": 9.994157350799176e-05,
|
| 316 |
+
"loss": 0.5168,
|
| 317 |
+
"step": 1716
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.36769327467001883,
|
| 321 |
+
"grad_norm": 1.0002754926681519,
|
| 322 |
+
"learning_rate": 9.993330662237024e-05,
|
| 323 |
+
"loss": 0.5547,
|
| 324 |
+
"step": 1755
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.3758642363293526,
|
| 328 |
+
"grad_norm": 1.4565436840057373,
|
| 329 |
+
"learning_rate": 9.992449332021114e-05,
|
| 330 |
+
"loss": 0.5013,
|
| 331 |
+
"step": 1794
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.38403519798868635,
|
| 335 |
+
"grad_norm": 0.9139441251754761,
|
| 336 |
+
"learning_rate": 9.991513369795777e-05,
|
| 337 |
+
"loss": 0.5084,
|
| 338 |
+
"step": 1833
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.39220615964802014,
|
| 342 |
+
"grad_norm": 1.054423451423645,
|
| 343 |
+
"learning_rate": 9.99052278580318e-05,
|
| 344 |
+
"loss": 0.5277,
|
| 345 |
+
"step": 1872
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.40037712130735387,
|
| 349 |
+
"grad_norm": 2.1869988441467285,
|
| 350 |
+
"learning_rate": 9.989477590883211e-05,
|
| 351 |
+
"loss": 0.5121,
|
| 352 |
+
"step": 1911
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.4085480829666876,
|
| 356 |
+
"grad_norm": 1.1452125310897827,
|
| 357 |
+
"learning_rate": 9.988377796473363e-05,
|
| 358 |
+
"loss": 0.4957,
|
| 359 |
+
"step": 1950
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.4167190446260214,
|
| 363 |
+
"grad_norm": 0.8906638622283936,
|
| 364 |
+
"learning_rate": 9.987223414608605e-05,
|
| 365 |
+
"loss": 0.4706,
|
| 366 |
+
"step": 1989
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.4248900062853551,
|
| 370 |
+
"grad_norm": 1.0864148139953613,
|
| 371 |
+
"learning_rate": 9.986014457921253e-05,
|
| 372 |
+
"loss": 0.5475,
|
| 373 |
+
"step": 2028
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.4330609679446889,
|
| 377 |
+
"grad_norm": 0.9262130856513977,
|
| 378 |
+
"learning_rate": 9.984750939640835e-05,
|
| 379 |
+
"loss": 0.5052,
|
| 380 |
+
"step": 2067
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.44123192960402263,
|
| 384 |
+
"grad_norm": 0.8391928672790527,
|
| 385 |
+
"learning_rate": 9.983432873593937e-05,
|
| 386 |
+
"loss": 0.4524,
|
| 387 |
+
"step": 2106
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.44940289126335636,
|
| 391 |
+
"grad_norm": 0.9878028631210327,
|
| 392 |
+
"learning_rate": 9.98206027420406e-05,
|
| 393 |
+
"loss": 0.4461,
|
| 394 |
+
"step": 2145
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.45757385292269015,
|
| 398 |
+
"grad_norm": 0.9766435623168945,
|
| 399 |
+
"learning_rate": 9.980633156491459e-05,
|
| 400 |
+
"loss": 0.4987,
|
| 401 |
+
"step": 2184
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.4657448145820239,
|
| 405 |
+
"grad_norm": 0.7703444957733154,
|
| 406 |
+
"learning_rate": 9.979151536072982e-05,
|
| 407 |
+
"loss": 0.4865,
|
| 408 |
+
"step": 2223
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.4739157762413576,
|
| 412 |
+
"grad_norm": 1.0184051990509033,
|
| 413 |
+
"learning_rate": 9.977615429161888e-05,
|
| 414 |
+
"loss": 0.4715,
|
| 415 |
+
"step": 2262
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.4820867379006914,
|
| 419 |
+
"grad_norm": 0.8845427632331848,
|
| 420 |
+
"learning_rate": 9.976024852567689e-05,
|
| 421 |
+
"loss": 0.4961,
|
| 422 |
+
"step": 2301
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.49025769956002513,
|
| 426 |
+
"grad_norm": 1.0399807691574097,
|
| 427 |
+
"learning_rate": 9.974379823695944e-05,
|
| 428 |
+
"loss": 0.5169,
|
| 429 |
+
"step": 2340
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.4984286612193589,
|
| 433 |
+
"grad_norm": 0.91423499584198,
|
| 434 |
+
"learning_rate": 9.972680360548085e-05,
|
| 435 |
+
"loss": 0.4783,
|
| 436 |
+
"step": 2379
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.5065996228786926,
|
| 440 |
+
"grad_norm": 0.9913365840911865,
|
| 441 |
+
"learning_rate": 9.970926481721216e-05,
|
| 442 |
+
"loss": 0.4726,
|
| 443 |
+
"step": 2418
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.5147705845380264,
|
| 447 |
+
"grad_norm": 0.9079034924507141,
|
| 448 |
+
"learning_rate": 9.969118206407905e-05,
|
| 449 |
+
"loss": 0.4486,
|
| 450 |
+
"step": 2457
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.5229415461973601,
|
| 454 |
+
"grad_norm": 0.9283367395401001,
|
| 455 |
+
"learning_rate": 9.967255554395976e-05,
|
| 456 |
+
"loss": 0.4654,
|
| 457 |
+
"step": 2496
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.531112507856694,
|
| 461 |
+
"grad_norm": 0.8894864916801453,
|
| 462 |
+
"learning_rate": 9.965338546068292e-05,
|
| 463 |
+
"loss": 0.4977,
|
| 464 |
+
"step": 2535
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.5392834695160277,
|
| 468 |
+
"grad_norm": 0.913196861743927,
|
| 469 |
+
"learning_rate": 9.963367202402538e-05,
|
| 470 |
+
"loss": 0.5067,
|
| 471 |
+
"step": 2574
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.5474544311753614,
|
| 475 |
+
"grad_norm": 0.9744309186935425,
|
| 476 |
+
"learning_rate": 9.961341544970984e-05,
|
| 477 |
+
"loss": 0.4797,
|
| 478 |
+
"step": 2613
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.5556253928346951,
|
| 482 |
+
"grad_norm": 1.048804759979248,
|
| 483 |
+
"learning_rate": 9.959261595940252e-05,
|
| 484 |
+
"loss": 0.4383,
|
| 485 |
+
"step": 2652
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.5637963544940289,
|
| 489 |
+
"grad_norm": 1.0824997425079346,
|
| 490 |
+
"learning_rate": 9.957127378071072e-05,
|
| 491 |
+
"loss": 0.4866,
|
| 492 |
+
"step": 2691
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.5719673161533627,
|
| 496 |
+
"grad_norm": 1.0387648344039917,
|
| 497 |
+
"learning_rate": 9.954938914718035e-05,
|
| 498 |
+
"loss": 0.4659,
|
| 499 |
+
"step": 2730
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.5801382778126964,
|
| 503 |
+
"grad_norm": 0.8543350100517273,
|
| 504 |
+
"learning_rate": 9.952696229829335e-05,
|
| 505 |
+
"loss": 0.4576,
|
| 506 |
+
"step": 2769
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.5883092394720302,
|
| 510 |
+
"grad_norm": 0.8038038015365601,
|
| 511 |
+
"learning_rate": 9.950399347946512e-05,
|
| 512 |
+
"loss": 0.4594,
|
| 513 |
+
"step": 2808
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.5964802011313639,
|
| 517 |
+
"grad_norm": 1.0086504220962524,
|
| 518 |
+
"learning_rate": 9.948048294204175e-05,
|
| 519 |
+
"loss": 0.4974,
|
| 520 |
+
"step": 2847
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.6046511627906976,
|
| 524 |
+
"grad_norm": 0.9558520913124084,
|
| 525 |
+
"learning_rate": 9.945643094329735e-05,
|
| 526 |
+
"loss": 0.4723,
|
| 527 |
+
"step": 2886
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.6128221244500315,
|
| 531 |
+
"grad_norm": 1.0693845748901367,
|
| 532 |
+
"learning_rate": 9.943183774643116e-05,
|
| 533 |
+
"loss": 0.4563,
|
| 534 |
+
"step": 2925
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.6209930861093652,
|
| 538 |
+
"grad_norm": 0.8957254886627197,
|
| 539 |
+
"learning_rate": 9.94067036205648e-05,
|
| 540 |
+
"loss": 0.4668,
|
| 541 |
+
"step": 2964
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.6291640477686989,
|
| 545 |
+
"grad_norm": 0.8896434903144836,
|
| 546 |
+
"learning_rate": 9.938102884073914e-05,
|
| 547 |
+
"loss": 0.4707,
|
| 548 |
+
"step": 3003
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.6373350094280327,
|
| 552 |
+
"grad_norm": 1.0319199562072754,
|
| 553 |
+
"learning_rate": 9.935481368791141e-05,
|
| 554 |
+
"loss": 0.484,
|
| 555 |
+
"step": 3042
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.6455059710873664,
|
| 559 |
+
"grad_norm": 0.8816359043121338,
|
| 560 |
+
"learning_rate": 9.932805844895216e-05,
|
| 561 |
+
"loss": 0.475,
|
| 562 |
+
"step": 3081
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.6536769327467001,
|
| 566 |
+
"grad_norm": 0.7812872529029846,
|
| 567 |
+
"learning_rate": 9.930076341664201e-05,
|
| 568 |
+
"loss": 0.4838,
|
| 569 |
+
"step": 3120
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.661847894406034,
|
| 573 |
+
"grad_norm": 1.0631335973739624,
|
| 574 |
+
"learning_rate": 9.927292888966848e-05,
|
| 575 |
+
"loss": 0.4791,
|
| 576 |
+
"step": 3159
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.6700188560653677,
|
| 580 |
+
"grad_norm": 0.9721090793609619,
|
| 581 |
+
"learning_rate": 9.92445551726228e-05,
|
| 582 |
+
"loss": 0.4701,
|
| 583 |
+
"step": 3198
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.6781898177247014,
|
| 587 |
+
"grad_norm": 0.9454875588417053,
|
| 588 |
+
"learning_rate": 9.921564257599649e-05,
|
| 589 |
+
"loss": 0.4397,
|
| 590 |
+
"step": 3237
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.6863607793840352,
|
| 594 |
+
"grad_norm": 0.6671223044395447,
|
| 595 |
+
"learning_rate": 9.918619141617797e-05,
|
| 596 |
+
"loss": 0.4557,
|
| 597 |
+
"step": 3276
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.6945317410433689,
|
| 601 |
+
"grad_norm": 0.6020123958587646,
|
| 602 |
+
"learning_rate": 9.915620201544915e-05,
|
| 603 |
+
"loss": 0.4454,
|
| 604 |
+
"step": 3315
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.7027027027027027,
|
| 608 |
+
"grad_norm": 0.5989274382591248,
|
| 609 |
+
"learning_rate": 9.912567470198186e-05,
|
| 610 |
+
"loss": 0.4762,
|
| 611 |
+
"step": 3354
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.7108736643620365,
|
| 615 |
+
"grad_norm": 0.9229285717010498,
|
| 616 |
+
"learning_rate": 9.909460980983427e-05,
|
| 617 |
+
"loss": 0.4928,
|
| 618 |
+
"step": 3393
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.7190446260213702,
|
| 622 |
+
"grad_norm": 0.8499952554702759,
|
| 623 |
+
"learning_rate": 9.906300767894721e-05,
|
| 624 |
+
"loss": 0.4491,
|
| 625 |
+
"step": 3432
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.7272155876807039,
|
| 629 |
+
"grad_norm": 0.801685631275177,
|
| 630 |
+
"learning_rate": 9.903086865514053e-05,
|
| 631 |
+
"loss": 0.4496,
|
| 632 |
+
"step": 3471
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.7353865493400377,
|
| 636 |
+
"grad_norm": 1.049750566482544,
|
| 637 |
+
"learning_rate": 9.89981930901092e-05,
|
| 638 |
+
"loss": 0.4741,
|
| 639 |
+
"step": 3510
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.7435575109993715,
|
| 643 |
+
"grad_norm": 0.7072298526763916,
|
| 644 |
+
"learning_rate": 9.896498134141957e-05,
|
| 645 |
+
"loss": 0.454,
|
| 646 |
+
"step": 3549
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.7517284726587052,
|
| 650 |
+
"grad_norm": 0.674797773361206,
|
| 651 |
+
"learning_rate": 9.893123377250535e-05,
|
| 652 |
+
"loss": 0.4244,
|
| 653 |
+
"step": 3588
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.759899434318039,
|
| 657 |
+
"grad_norm": 0.6849934458732605,
|
| 658 |
+
"learning_rate": 9.889695075266377e-05,
|
| 659 |
+
"loss": 0.4631,
|
| 660 |
+
"step": 3627
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.7680703959773727,
|
| 664 |
+
"grad_norm": 0.6002283692359924,
|
| 665 |
+
"learning_rate": 9.88621326570514e-05,
|
| 666 |
+
"loss": 0.4936,
|
| 667 |
+
"step": 3666
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.7762413576367064,
|
| 671 |
+
"grad_norm": 0.8119000196456909,
|
| 672 |
+
"learning_rate": 9.882677986668014e-05,
|
| 673 |
+
"loss": 0.471,
|
| 674 |
+
"step": 3705
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.7844123192960403,
|
| 678 |
+
"grad_norm": 0.8308870792388916,
|
| 679 |
+
"learning_rate": 9.879089276841297e-05,
|
| 680 |
+
"loss": 0.4419,
|
| 681 |
+
"step": 3744
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.792583280955374,
|
| 685 |
+
"grad_norm": 0.7574063539505005,
|
| 686 |
+
"learning_rate": 9.875447175495983e-05,
|
| 687 |
+
"loss": 0.4286,
|
| 688 |
+
"step": 3783
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.8007542426147077,
|
| 692 |
+
"grad_norm": 0.7497377991676331,
|
| 693 |
+
"learning_rate": 9.871751722487317e-05,
|
| 694 |
+
"loss": 0.4773,
|
| 695 |
+
"step": 3822
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.8089252042740415,
|
| 699 |
+
"grad_norm": 0.761298418045044,
|
| 700 |
+
"learning_rate": 9.868002958254377e-05,
|
| 701 |
+
"loss": 0.4813,
|
| 702 |
+
"step": 3861
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.8170961659333752,
|
| 706 |
+
"grad_norm": 0.9213526844978333,
|
| 707 |
+
"learning_rate": 9.864200923819613e-05,
|
| 708 |
+
"loss": 0.4777,
|
| 709 |
+
"step": 3900
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.825267127592709,
|
| 713 |
+
"grad_norm": 0.9028540849685669,
|
| 714 |
+
"learning_rate": 9.860345660788414e-05,
|
| 715 |
+
"loss": 0.4302,
|
| 716 |
+
"step": 3939
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.8334380892520428,
|
| 720 |
+
"grad_norm": 0.6980260610580444,
|
| 721 |
+
"learning_rate": 9.856437211348641e-05,
|
| 722 |
+
"loss": 0.4283,
|
| 723 |
+
"step": 3978
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.8416090509113765,
|
| 727 |
+
"grad_norm": 0.6451707482337952,
|
| 728 |
+
"learning_rate": 9.852475618270172e-05,
|
| 729 |
+
"loss": 0.425,
|
| 730 |
+
"step": 4017
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.8497800125707102,
|
| 734 |
+
"grad_norm": 0.712598443031311,
|
| 735 |
+
"learning_rate": 9.848460924904432e-05,
|
| 736 |
+
"loss": 0.4638,
|
| 737 |
+
"step": 4056
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.857950974230044,
|
| 741 |
+
"grad_norm": 0.614088773727417,
|
| 742 |
+
"learning_rate": 9.844393175183917e-05,
|
| 743 |
+
"loss": 0.4557,
|
| 744 |
+
"step": 4095
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.8661219358893778,
|
| 748 |
+
"grad_norm": 0.8028059601783752,
|
| 749 |
+
"learning_rate": 9.840272413621716e-05,
|
| 750 |
+
"loss": 0.4699,
|
| 751 |
+
"step": 4134
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.8742928975487115,
|
| 755 |
+
"grad_norm": 0.8500687479972839,
|
| 756 |
+
"learning_rate": 9.836098685311024e-05,
|
| 757 |
+
"loss": 0.4392,
|
| 758 |
+
"step": 4173
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.8824638592080453,
|
| 762 |
+
"grad_norm": 0.7735748291015625,
|
| 763 |
+
"learning_rate": 9.831872035924645e-05,
|
| 764 |
+
"loss": 0.4197,
|
| 765 |
+
"step": 4212
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.890634820867379,
|
| 769 |
+
"grad_norm": 0.6959074139595032,
|
| 770 |
+
"learning_rate": 9.827592511714493e-05,
|
| 771 |
+
"loss": 0.4347,
|
| 772 |
+
"step": 4251
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.8988057825267127,
|
| 776 |
+
"grad_norm": 0.5992249846458435,
|
| 777 |
+
"learning_rate": 9.823260159511096e-05,
|
| 778 |
+
"loss": 0.4327,
|
| 779 |
+
"step": 4290
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.9069767441860465,
|
| 783 |
+
"grad_norm": 0.591803252696991,
|
| 784 |
+
"learning_rate": 9.818875026723063e-05,
|
| 785 |
+
"loss": 0.463,
|
| 786 |
+
"step": 4329
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.9151477058453803,
|
| 790 |
+
"grad_norm": 0.7650397419929504,
|
| 791 |
+
"learning_rate": 9.814437161336583e-05,
|
| 792 |
+
"loss": 0.4393,
|
| 793 |
+
"step": 4368
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.923318667504714,
|
| 797 |
+
"grad_norm": 0.7083756923675537,
|
| 798 |
+
"learning_rate": 9.809946611914896e-05,
|
| 799 |
+
"loss": 0.4431,
|
| 800 |
+
"step": 4407
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.9314896291640478,
|
| 804 |
+
"grad_norm": 0.5570526719093323,
|
| 805 |
+
"learning_rate": 9.805403427597757e-05,
|
| 806 |
+
"loss": 0.4293,
|
| 807 |
+
"step": 4446
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.9396605908233815,
|
| 811 |
+
"grad_norm": 0.7944348454475403,
|
| 812 |
+
"learning_rate": 9.800807658100902e-05,
|
| 813 |
+
"loss": 0.4331,
|
| 814 |
+
"step": 4485
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.9478315524827152,
|
| 818 |
+
"grad_norm": 0.9344629645347595,
|
| 819 |
+
"learning_rate": 9.796159353715498e-05,
|
| 820 |
+
"loss": 0.4461,
|
| 821 |
+
"step": 4524
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.9560025141420491,
|
| 825 |
+
"grad_norm": 0.6917528510093689,
|
| 826 |
+
"learning_rate": 9.791458565307604e-05,
|
| 827 |
+
"loss": 0.4441,
|
| 828 |
+
"step": 4563
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.9641734758013828,
|
| 832 |
+
"grad_norm": 0.6871070861816406,
|
| 833 |
+
"learning_rate": 9.786705344317606e-05,
|
| 834 |
+
"loss": 0.4461,
|
| 835 |
+
"step": 4602
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.9723444374607165,
|
| 839 |
+
"grad_norm": 0.7774878740310669,
|
| 840 |
+
"learning_rate": 9.781899742759652e-05,
|
| 841 |
+
"loss": 0.4693,
|
| 842 |
+
"step": 4641
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.9805153991200503,
|
| 846 |
+
"grad_norm": 0.7668758630752563,
|
| 847 |
+
"learning_rate": 9.777041813221095e-05,
|
| 848 |
+
"loss": 0.4073,
|
| 849 |
+
"step": 4680
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.988686360779384,
|
| 853 |
+
"grad_norm": 0.7705347537994385,
|
| 854 |
+
"learning_rate": 9.772131608861899e-05,
|
| 855 |
+
"loss": 0.474,
|
| 856 |
+
"step": 4719
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.9968573224387178,
|
| 860 |
+
"grad_norm": 0.8965923190116882,
|
| 861 |
+
"learning_rate": 9.767169183414075e-05,
|
| 862 |
+
"loss": 0.4741,
|
| 863 |
+
"step": 4758
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.0050282840980516,
|
| 867 |
+
"grad_norm": 0.7429456114768982,
|
| 868 |
+
"learning_rate": 9.762154591181083e-05,
|
| 869 |
+
"loss": 0.4326,
|
| 870 |
+
"step": 4797
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.0131992457573853,
|
| 874 |
+
"grad_norm": 0.8201857209205627,
|
| 875 |
+
"learning_rate": 9.757087887037241e-05,
|
| 876 |
+
"loss": 0.4252,
|
| 877 |
+
"step": 4836
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.021370207416719,
|
| 881 |
+
"grad_norm": 0.9046009182929993,
|
| 882 |
+
"learning_rate": 9.751969126427122e-05,
|
| 883 |
+
"loss": 0.4176,
|
| 884 |
+
"step": 4875
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.0295411690760528,
|
| 888 |
+
"grad_norm": 0.9283869862556458,
|
| 889 |
+
"learning_rate": 9.746798365364952e-05,
|
| 890 |
+
"loss": 0.4024,
|
| 891 |
+
"step": 4914
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.0377121307353865,
|
| 895 |
+
"grad_norm": 0.8236905932426453,
|
| 896 |
+
"learning_rate": 9.741575660433993e-05,
|
| 897 |
+
"loss": 0.409,
|
| 898 |
+
"step": 4953
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.0458830923947202,
|
| 902 |
+
"grad_norm": 0.713076651096344,
|
| 903 |
+
"learning_rate": 9.736301068785923e-05,
|
| 904 |
+
"loss": 0.4466,
|
| 905 |
+
"step": 4992
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.054054054054054,
|
| 909 |
+
"grad_norm": 0.8006173372268677,
|
| 910 |
+
"learning_rate": 9.730974648140214e-05,
|
| 911 |
+
"loss": 0.3786,
|
| 912 |
+
"step": 5031
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.062225015713388,
|
| 916 |
+
"grad_norm": 0.924655020236969,
|
| 917 |
+
"learning_rate": 9.725596456783502e-05,
|
| 918 |
+
"loss": 0.4276,
|
| 919 |
+
"step": 5070
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.0703959773727216,
|
| 923 |
+
"grad_norm": 0.7090715765953064,
|
| 924 |
+
"learning_rate": 9.72016655356894e-05,
|
| 925 |
+
"loss": 0.3978,
|
| 926 |
+
"step": 5109
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.0785669390320554,
|
| 930 |
+
"grad_norm": 0.8049948215484619,
|
| 931 |
+
"learning_rate": 9.714684997915566e-05,
|
| 932 |
+
"loss": 0.423,
|
| 933 |
+
"step": 5148
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.086737900691389,
|
| 937 |
+
"grad_norm": 0.7052054405212402,
|
| 938 |
+
"learning_rate": 9.709151849807643e-05,
|
| 939 |
+
"loss": 0.3803,
|
| 940 |
+
"step": 5187
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.0949088623507228,
|
| 944 |
+
"grad_norm": 1.0038681030273438,
|
| 945 |
+
"learning_rate": 9.703567169794008e-05,
|
| 946 |
+
"loss": 0.4221,
|
| 947 |
+
"step": 5226
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.1030798240100566,
|
| 951 |
+
"grad_norm": 0.6527186036109924,
|
| 952 |
+
"learning_rate": 9.697931018987408e-05,
|
| 953 |
+
"loss": 0.3858,
|
| 954 |
+
"step": 5265
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.1112507856693903,
|
| 958 |
+
"grad_norm": 0.7536753416061401,
|
| 959 |
+
"learning_rate": 9.69224345906383e-05,
|
| 960 |
+
"loss": 0.3981,
|
| 961 |
+
"step": 5304
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.119421747328724,
|
| 965 |
+
"grad_norm": 1.1964749097824097,
|
| 966 |
+
"learning_rate": 9.68650455226183e-05,
|
| 967 |
+
"loss": 0.3858,
|
| 968 |
+
"step": 5343
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.1275927089880577,
|
| 972 |
+
"grad_norm": 0.717378556728363,
|
| 973 |
+
"learning_rate": 9.680714361381844e-05,
|
| 974 |
+
"loss": 0.4056,
|
| 975 |
+
"step": 5382
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.1357636706473917,
|
| 979 |
+
"grad_norm": 0.8927372694015503,
|
| 980 |
+
"learning_rate": 9.674872949785511e-05,
|
| 981 |
+
"loss": 0.3831,
|
| 982 |
+
"step": 5421
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.1439346323067254,
|
| 986 |
+
"grad_norm": 0.8325986266136169,
|
| 987 |
+
"learning_rate": 9.668980381394972e-05,
|
| 988 |
+
"loss": 0.3996,
|
| 989 |
+
"step": 5460
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.1521055939660592,
|
| 993 |
+
"grad_norm": 0.8707286715507507,
|
| 994 |
+
"learning_rate": 9.663036720692175e-05,
|
| 995 |
+
"loss": 0.4171,
|
| 996 |
+
"step": 5499
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.160276555625393,
|
| 1000 |
+
"grad_norm": 0.6361021399497986,
|
| 1001 |
+
"learning_rate": 9.657042032718165e-05,
|
| 1002 |
+
"loss": 0.4033,
|
| 1003 |
+
"step": 5538
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 1.1684475172847266,
|
| 1007 |
+
"grad_norm": 0.9237117171287537,
|
| 1008 |
+
"learning_rate": 9.650996383072375e-05,
|
| 1009 |
+
"loss": 0.3497,
|
| 1010 |
+
"step": 5577
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.1766184789440604,
|
| 1014 |
+
"grad_norm": 0.7840002179145813,
|
| 1015 |
+
"learning_rate": 9.644899837911912e-05,
|
| 1016 |
+
"loss": 0.3789,
|
| 1017 |
+
"step": 5616
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.184789440603394,
|
| 1021 |
+
"grad_norm": 0.6757360100746155,
|
| 1022 |
+
"learning_rate": 9.638752463950821e-05,
|
| 1023 |
+
"loss": 0.4085,
|
| 1024 |
+
"step": 5655
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.1929604022627278,
|
| 1028 |
+
"grad_norm": 0.8231393098831177,
|
| 1029 |
+
"learning_rate": 9.632554328459371e-05,
|
| 1030 |
+
"loss": 0.4015,
|
| 1031 |
+
"step": 5694
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.2011313639220615,
|
| 1035 |
+
"grad_norm": 1.001394271850586,
|
| 1036 |
+
"learning_rate": 9.626305499263307e-05,
|
| 1037 |
+
"loss": 0.3671,
|
| 1038 |
+
"step": 5733
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 1.2093023255813953,
|
| 1042 |
+
"grad_norm": 0.7362861633300781,
|
| 1043 |
+
"learning_rate": 9.620006044743111e-05,
|
| 1044 |
+
"loss": 0.4108,
|
| 1045 |
+
"step": 5772
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.217473287240729,
|
| 1049 |
+
"grad_norm": 0.873781144618988,
|
| 1050 |
+
"learning_rate": 9.613656033833255e-05,
|
| 1051 |
+
"loss": 0.3959,
|
| 1052 |
+
"step": 5811
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.2256442489000627,
|
| 1056 |
+
"grad_norm": 0.745134174823761,
|
| 1057 |
+
"learning_rate": 9.607255536021445e-05,
|
| 1058 |
+
"loss": 0.4003,
|
| 1059 |
+
"step": 5850
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.2338152105593967,
|
| 1063 |
+
"grad_norm": 0.9675105810165405,
|
| 1064 |
+
"learning_rate": 9.600804621347865e-05,
|
| 1065 |
+
"loss": 0.4446,
|
| 1066 |
+
"step": 5889
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.2419861722187304,
|
| 1070 |
+
"grad_norm": 0.6674776673316956,
|
| 1071 |
+
"learning_rate": 9.594303360404401e-05,
|
| 1072 |
+
"loss": 0.3975,
|
| 1073 |
+
"step": 5928
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.2501571338780642,
|
| 1077 |
+
"grad_norm": 1.0288015604019165,
|
| 1078 |
+
"learning_rate": 9.587751824333882e-05,
|
| 1079 |
+
"loss": 0.371,
|
| 1080 |
+
"step": 5967
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.2583280955373979,
|
| 1084 |
+
"grad_norm": 1.1984747648239136,
|
| 1085 |
+
"learning_rate": 9.581150084829287e-05,
|
| 1086 |
+
"loss": 0.391,
|
| 1087 |
+
"step": 6006
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.2664990571967316,
|
| 1091 |
+
"grad_norm": 0.7332170009613037,
|
| 1092 |
+
"learning_rate": 9.574498214132971e-05,
|
| 1093 |
+
"loss": 0.4048,
|
| 1094 |
+
"step": 6045
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 1.2746700188560653,
|
| 1098 |
+
"grad_norm": 0.7564400434494019,
|
| 1099 |
+
"learning_rate": 9.56779628503587e-05,
|
| 1100 |
+
"loss": 0.4403,
|
| 1101 |
+
"step": 6084
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.282840980515399,
|
| 1105 |
+
"grad_norm": 0.8034684658050537,
|
| 1106 |
+
"learning_rate": 9.561044370876709e-05,
|
| 1107 |
+
"loss": 0.3841,
|
| 1108 |
+
"step": 6123
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.2910119421747328,
|
| 1112 |
+
"grad_norm": 0.8448123335838318,
|
| 1113 |
+
"learning_rate": 9.55424254554119e-05,
|
| 1114 |
+
"loss": 0.3906,
|
| 1115 |
+
"step": 6162
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.2991829038340668,
|
| 1119 |
+
"grad_norm": 1.2661123275756836,
|
| 1120 |
+
"learning_rate": 9.547390883461194e-05,
|
| 1121 |
+
"loss": 0.3858,
|
| 1122 |
+
"step": 6201
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.3073538654934005,
|
| 1126 |
+
"grad_norm": 0.7595413327217102,
|
| 1127 |
+
"learning_rate": 9.54048945961396e-05,
|
| 1128 |
+
"loss": 0.4283,
|
| 1129 |
+
"step": 6240
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.3155248271527342,
|
| 1133 |
+
"grad_norm": 0.8576300740242004,
|
| 1134 |
+
"learning_rate": 9.533538349521263e-05,
|
| 1135 |
+
"loss": 0.3916,
|
| 1136 |
+
"step": 6279
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.323695788812068,
|
| 1140 |
+
"grad_norm": 0.5660988092422485,
|
| 1141 |
+
"learning_rate": 9.526537629248598e-05,
|
| 1142 |
+
"loss": 0.3639,
|
| 1143 |
+
"step": 6318
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.3318667504714017,
|
| 1147 |
+
"grad_norm": 0.7187468409538269,
|
| 1148 |
+
"learning_rate": 9.519487375404337e-05,
|
| 1149 |
+
"loss": 0.3861,
|
| 1150 |
+
"step": 6357
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.3400377121307354,
|
| 1154 |
+
"grad_norm": 0.8099279999732971,
|
| 1155 |
+
"learning_rate": 9.512387665138894e-05,
|
| 1156 |
+
"loss": 0.3975,
|
| 1157 |
+
"step": 6396
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.3482086737900691,
|
| 1161 |
+
"grad_norm": 0.8016268610954285,
|
| 1162 |
+
"learning_rate": 9.50523857614388e-05,
|
| 1163 |
+
"loss": 0.3751,
|
| 1164 |
+
"step": 6435
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.3563796354494029,
|
| 1168 |
+
"grad_norm": 0.6431599855422974,
|
| 1169 |
+
"learning_rate": 9.498040186651258e-05,
|
| 1170 |
+
"loss": 0.4014,
|
| 1171 |
+
"step": 6474
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.3645505971087366,
|
| 1175 |
+
"grad_norm": 0.8925536274909973,
|
| 1176 |
+
"learning_rate": 9.490792575432475e-05,
|
| 1177 |
+
"loss": 0.3871,
|
| 1178 |
+
"step": 6513
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.3727215587680703,
|
| 1182 |
+
"grad_norm": 0.8553928136825562,
|
| 1183 |
+
"learning_rate": 9.483495821797619e-05,
|
| 1184 |
+
"loss": 0.3949,
|
| 1185 |
+
"step": 6552
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.380892520427404,
|
| 1189 |
+
"grad_norm": 0.8019265532493591,
|
| 1190 |
+
"learning_rate": 9.476150005594528e-05,
|
| 1191 |
+
"loss": 0.4086,
|
| 1192 |
+
"step": 6591
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.3890634820867378,
|
| 1196 |
+
"grad_norm": 0.7925927639007568,
|
| 1197 |
+
"learning_rate": 9.468755207207937e-05,
|
| 1198 |
+
"loss": 0.4024,
|
| 1199 |
+
"step": 6630
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.3972344437460715,
|
| 1203 |
+
"grad_norm": 0.7827038168907166,
|
| 1204 |
+
"learning_rate": 9.461311507558586e-05,
|
| 1205 |
+
"loss": 0.421,
|
| 1206 |
+
"step": 6669
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.4054054054054055,
|
| 1210 |
+
"grad_norm": 0.5531708598136902,
|
| 1211 |
+
"learning_rate": 9.453818988102336e-05,
|
| 1212 |
+
"loss": 0.4183,
|
| 1213 |
+
"step": 6708
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.4135763670647392,
|
| 1217 |
+
"grad_norm": 0.7605539560317993,
|
| 1218 |
+
"learning_rate": 9.446277730829284e-05,
|
| 1219 |
+
"loss": 0.4314,
|
| 1220 |
+
"step": 6747
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.421747328724073,
|
| 1224 |
+
"grad_norm": 0.49756988883018494,
|
| 1225 |
+
"learning_rate": 9.438687818262857e-05,
|
| 1226 |
+
"loss": 0.4118,
|
| 1227 |
+
"step": 6786
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.4299182903834067,
|
| 1231 |
+
"grad_norm": 0.9179204106330872,
|
| 1232 |
+
"learning_rate": 9.431049333458917e-05,
|
| 1233 |
+
"loss": 0.4027,
|
| 1234 |
+
"step": 6825
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.4380892520427404,
|
| 1238 |
+
"grad_norm": 0.7112446427345276,
|
| 1239 |
+
"learning_rate": 9.423362360004848e-05,
|
| 1240 |
+
"loss": 0.3961,
|
| 1241 |
+
"step": 6864
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.4462602137020741,
|
| 1245 |
+
"grad_norm": 0.6417878866195679,
|
| 1246 |
+
"learning_rate": 9.415626982018637e-05,
|
| 1247 |
+
"loss": 0.426,
|
| 1248 |
+
"step": 6903
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.4544311753614079,
|
| 1252 |
+
"grad_norm": 0.7054896950721741,
|
| 1253 |
+
"learning_rate": 9.407843284147966e-05,
|
| 1254 |
+
"loss": 0.3592,
|
| 1255 |
+
"step": 6942
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.4626021370207416,
|
| 1259 |
+
"grad_norm": 0.3770501911640167,
|
| 1260 |
+
"learning_rate": 9.400011351569272e-05,
|
| 1261 |
+
"loss": 0.4205,
|
| 1262 |
+
"step": 6981
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.4707730986800756,
|
| 1266 |
+
"grad_norm": 0.7424401044845581,
|
| 1267 |
+
"learning_rate": 9.392131269986821e-05,
|
| 1268 |
+
"loss": 0.3862,
|
| 1269 |
+
"step": 7020
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.4789440603394093,
|
| 1273 |
+
"grad_norm": 0.7774800062179565,
|
| 1274 |
+
"learning_rate": 9.384203125631774e-05,
|
| 1275 |
+
"loss": 0.4186,
|
| 1276 |
+
"step": 7059
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.487115021998743,
|
| 1280 |
+
"grad_norm": 0.6684144735336304,
|
| 1281 |
+
"learning_rate": 9.376227005261237e-05,
|
| 1282 |
+
"loss": 0.3793,
|
| 1283 |
+
"step": 7098
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.4952859836580767,
|
| 1287 |
+
"grad_norm": 0.8839356899261475,
|
| 1288 |
+
"learning_rate": 9.368202996157314e-05,
|
| 1289 |
+
"loss": 0.3927,
|
| 1290 |
+
"step": 7137
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.5034569453174105,
|
| 1294 |
+
"grad_norm": 0.7853700518608093,
|
| 1295 |
+
"learning_rate": 9.36013118612615e-05,
|
| 1296 |
+
"loss": 0.3842,
|
| 1297 |
+
"step": 7176
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.5116279069767442,
|
| 1301 |
+
"grad_norm": 0.9322993159294128,
|
| 1302 |
+
"learning_rate": 9.35201166349698e-05,
|
| 1303 |
+
"loss": 0.3737,
|
| 1304 |
+
"step": 7215
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.519798868636078,
|
| 1308 |
+
"grad_norm": 0.7737587094306946,
|
| 1309 |
+
"learning_rate": 9.343844517121145e-05,
|
| 1310 |
+
"loss": 0.3681,
|
| 1311 |
+
"step": 7254
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.5279698302954117,
|
| 1315 |
+
"grad_norm": 0.7644033432006836,
|
| 1316 |
+
"learning_rate": 9.335629836371132e-05,
|
| 1317 |
+
"loss": 0.3786,
|
| 1318 |
+
"step": 7293
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 1.5361407919547454,
|
| 1322 |
+
"grad_norm": 0.7909252643585205,
|
| 1323 |
+
"learning_rate": 9.327367711139596e-05,
|
| 1324 |
+
"loss": 0.4039,
|
| 1325 |
+
"step": 7332
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.5443117536140791,
|
| 1329 |
+
"grad_norm": 0.5451653599739075,
|
| 1330 |
+
"learning_rate": 9.31905823183837e-05,
|
| 1331 |
+
"loss": 0.3507,
|
| 1332 |
+
"step": 7371
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 1.5524827152734129,
|
| 1336 |
+
"grad_norm": 0.7788479328155518,
|
| 1337 |
+
"learning_rate": 9.310701489397485e-05,
|
| 1338 |
+
"loss": 0.3732,
|
| 1339 |
+
"step": 7410
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 1.5606536769327466,
|
| 1343 |
+
"grad_norm": 0.8460758924484253,
|
| 1344 |
+
"learning_rate": 9.302297575264159e-05,
|
| 1345 |
+
"loss": 0.3692,
|
| 1346 |
+
"step": 7449
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 1.5688246385920803,
|
| 1350 |
+
"grad_norm": 0.8979092240333557,
|
| 1351 |
+
"learning_rate": 9.293846581401815e-05,
|
| 1352 |
+
"loss": 0.4246,
|
| 1353 |
+
"step": 7488
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.576995600251414,
|
| 1357 |
+
"grad_norm": 0.8408267498016357,
|
| 1358 |
+
"learning_rate": 9.285348600289063e-05,
|
| 1359 |
+
"loss": 0.4018,
|
| 1360 |
+
"step": 7527
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 1.585166561910748,
|
| 1364 |
+
"grad_norm": 0.9224086999893188,
|
| 1365 |
+
"learning_rate": 9.276803724918692e-05,
|
| 1366 |
+
"loss": 0.3774,
|
| 1367 |
+
"step": 7566
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.5933375235700817,
|
| 1371 |
+
"grad_norm": 0.760299563407898,
|
| 1372 |
+
"learning_rate": 9.268212048796652e-05,
|
| 1373 |
+
"loss": 0.4074,
|
| 1374 |
+
"step": 7605
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 1.6015084852294155,
|
| 1378 |
+
"grad_norm": 0.6859989166259766,
|
| 1379 |
+
"learning_rate": 9.259573665941027e-05,
|
| 1380 |
+
"loss": 0.4017,
|
| 1381 |
+
"step": 7644
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.6096794468887492,
|
| 1385 |
+
"grad_norm": 0.5509856939315796,
|
| 1386 |
+
"learning_rate": 9.250888670881011e-05,
|
| 1387 |
+
"loss": 0.3785,
|
| 1388 |
+
"step": 7683
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 1.617850408548083,
|
| 1392 |
+
"grad_norm": 0.8195124864578247,
|
| 1393 |
+
"learning_rate": 9.242157158655875e-05,
|
| 1394 |
+
"loss": 0.3985,
|
| 1395 |
+
"step": 7722
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.6260213702074169,
|
| 1399 |
+
"grad_norm": 0.6665972471237183,
|
| 1400 |
+
"learning_rate": 9.23337922481392e-05,
|
| 1401 |
+
"loss": 0.3827,
|
| 1402 |
+
"step": 7761
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.6341923318667506,
|
| 1406 |
+
"grad_norm": 0.7980179786682129,
|
| 1407 |
+
"learning_rate": 9.224554965411435e-05,
|
| 1408 |
+
"loss": 0.3854,
|
| 1409 |
+
"step": 7800
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.6423632935260843,
|
| 1413 |
+
"grad_norm": 0.7136581540107727,
|
| 1414 |
+
"learning_rate": 9.21568447701165e-05,
|
| 1415 |
+
"loss": 0.3632,
|
| 1416 |
+
"step": 7839
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 1.650534255185418,
|
| 1420 |
+
"grad_norm": 0.5472484230995178,
|
| 1421 |
+
"learning_rate": 9.206767856683674e-05,
|
| 1422 |
+
"loss": 0.3906,
|
| 1423 |
+
"step": 7878
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 1.6587052168447518,
|
| 1427 |
+
"grad_norm": 0.7572371959686279,
|
| 1428 |
+
"learning_rate": 9.19780520200143e-05,
|
| 1429 |
+
"loss": 0.4074,
|
| 1430 |
+
"step": 7917
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 1.6668761785040855,
|
| 1434 |
+
"grad_norm": 0.7541080117225647,
|
| 1435 |
+
"learning_rate": 9.1887966110426e-05,
|
| 1436 |
+
"loss": 0.3769,
|
| 1437 |
+
"step": 7956
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 1.6750471401634193,
|
| 1441 |
+
"grad_norm": 0.7768887281417847,
|
| 1442 |
+
"learning_rate": 9.179742182387538e-05,
|
| 1443 |
+
"loss": 0.3887,
|
| 1444 |
+
"step": 7995
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 1.683218101822753,
|
| 1448 |
+
"grad_norm": 0.4816763699054718,
|
| 1449 |
+
"learning_rate": 9.170642015118195e-05,
|
| 1450 |
+
"loss": 0.3968,
|
| 1451 |
+
"step": 8034
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 1.6913890634820867,
|
| 1455 |
+
"grad_norm": 0.798069953918457,
|
| 1456 |
+
"learning_rate": 9.16149620881704e-05,
|
| 1457 |
+
"loss": 0.3929,
|
| 1458 |
+
"step": 8073
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 1.6995600251414205,
|
| 1462 |
+
"grad_norm": 0.6265507340431213,
|
| 1463 |
+
"learning_rate": 9.152304863565965e-05,
|
| 1464 |
+
"loss": 0.3509,
|
| 1465 |
+
"step": 8112
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 1.7077309868007542,
|
| 1469 |
+
"grad_norm": 0.7725851535797119,
|
| 1470 |
+
"learning_rate": 9.143068079945191e-05,
|
| 1471 |
+
"loss": 0.416,
|
| 1472 |
+
"step": 8151
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 1.715901948460088,
|
| 1476 |
+
"grad_norm": 0.7044919729232788,
|
| 1477 |
+
"learning_rate": 9.133785959032172e-05,
|
| 1478 |
+
"loss": 0.3901,
|
| 1479 |
+
"step": 8190
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 1.7240729101194217,
|
| 1483 |
+
"grad_norm": 0.7072455883026123,
|
| 1484 |
+
"learning_rate": 9.124458602400476e-05,
|
| 1485 |
+
"loss": 0.4162,
|
| 1486 |
+
"step": 8229
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 1.7322438717787554,
|
| 1490 |
+
"grad_norm": 0.6308450698852539,
|
| 1491 |
+
"learning_rate": 9.11508611211869e-05,
|
| 1492 |
+
"loss": 0.3617,
|
| 1493 |
+
"step": 8268
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 1.7404148334380891,
|
| 1497 |
+
"grad_norm": 0.9505504369735718,
|
| 1498 |
+
"learning_rate": 9.105668590749292e-05,
|
| 1499 |
+
"loss": 0.4235,
|
| 1500 |
+
"step": 8307
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 1.7485857950974228,
|
| 1504 |
+
"grad_norm": 0.6861995458602905,
|
| 1505 |
+
"learning_rate": 9.096206141347533e-05,
|
| 1506 |
+
"loss": 0.3757,
|
| 1507 |
+
"step": 8346
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 1.7567567567567568,
|
| 1511 |
+
"grad_norm": 0.7003109455108643,
|
| 1512 |
+
"learning_rate": 9.086698867460306e-05,
|
| 1513 |
+
"loss": 0.3672,
|
| 1514 |
+
"step": 8385
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 1.7649277184160905,
|
| 1518 |
+
"grad_norm": 0.7863865494728088,
|
| 1519 |
+
"learning_rate": 9.07714687312502e-05,
|
| 1520 |
+
"loss": 0.4294,
|
| 1521 |
+
"step": 8424
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.7730986800754243,
|
| 1525 |
+
"grad_norm": 0.7616212964057922,
|
| 1526 |
+
"learning_rate": 9.067550262868449e-05,
|
| 1527 |
+
"loss": 0.3681,
|
| 1528 |
+
"step": 8463
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 1.781269641734758,
|
| 1532 |
+
"grad_norm": 0.7139325737953186,
|
| 1533 |
+
"learning_rate": 9.057909141705603e-05,
|
| 1534 |
+
"loss": 0.4084,
|
| 1535 |
+
"step": 8502
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.7894406033940917,
|
| 1539 |
+
"grad_norm": 0.6723546981811523,
|
| 1540 |
+
"learning_rate": 9.04822361513857e-05,
|
| 1541 |
+
"loss": 0.4052,
|
| 1542 |
+
"step": 8541
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 1.7976115650534257,
|
| 1546 |
+
"grad_norm": 0.6281395554542542,
|
| 1547 |
+
"learning_rate": 9.038493789155356e-05,
|
| 1548 |
+
"loss": 0.3924,
|
| 1549 |
+
"step": 8580
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 1.8057825267127594,
|
| 1553 |
+
"grad_norm": 0.7400838732719421,
|
| 1554 |
+
"learning_rate": 9.028719770228744e-05,
|
| 1555 |
+
"loss": 0.4011,
|
| 1556 |
+
"step": 8619
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 1.8139534883720931,
|
| 1560 |
+
"grad_norm": 1.0410945415496826,
|
| 1561 |
+
"learning_rate": 9.01890166531511e-05,
|
| 1562 |
+
"loss": 0.385,
|
| 1563 |
+
"step": 8658
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 1.8221244500314269,
|
| 1567 |
+
"grad_norm": 0.7112125158309937,
|
| 1568 |
+
"learning_rate": 9.009039581853259e-05,
|
| 1569 |
+
"loss": 0.4204,
|
| 1570 |
+
"step": 8697
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 1.8302954116907606,
|
| 1574 |
+
"grad_norm": 0.667522668838501,
|
| 1575 |
+
"learning_rate": 8.999133627763252e-05,
|
| 1576 |
+
"loss": 0.4274,
|
| 1577 |
+
"step": 8736
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 1.8384663733500943,
|
| 1581 |
+
"grad_norm": 0.6372833251953125,
|
| 1582 |
+
"learning_rate": 8.989183911445228e-05,
|
| 1583 |
+
"loss": 0.3725,
|
| 1584 |
+
"step": 8775
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 1.846637335009428,
|
| 1588 |
+
"grad_norm": 0.8261222839355469,
|
| 1589 |
+
"learning_rate": 8.979190541778199e-05,
|
| 1590 |
+
"loss": 0.4256,
|
| 1591 |
+
"step": 8814
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 1.8548082966687618,
|
| 1595 |
+
"grad_norm": 0.6333631873130798,
|
| 1596 |
+
"learning_rate": 8.969153628118891e-05,
|
| 1597 |
+
"loss": 0.3836,
|
| 1598 |
+
"step": 8853
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 1.8629792583280955,
|
| 1602 |
+
"grad_norm": 0.6916419863700867,
|
| 1603 |
+
"learning_rate": 8.959073280300514e-05,
|
| 1604 |
+
"loss": 0.3756,
|
| 1605 |
+
"step": 8892
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 1.8711502199874293,
|
| 1609 |
+
"grad_norm": 0.5185075998306274,
|
| 1610 |
+
"learning_rate": 8.948949608631578e-05,
|
| 1611 |
+
"loss": 0.3772,
|
| 1612 |
+
"step": 8931
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 1.879321181646763,
|
| 1616 |
+
"grad_norm": 0.8508359789848328,
|
| 1617 |
+
"learning_rate": 8.93878272389469e-05,
|
| 1618 |
+
"loss": 0.42,
|
| 1619 |
+
"step": 8970
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 1.8874921433060967,
|
| 1623 |
+
"grad_norm": 0.6042287349700928,
|
| 1624 |
+
"learning_rate": 8.928572737345328e-05,
|
| 1625 |
+
"loss": 0.4111,
|
| 1626 |
+
"step": 9009
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 1.8956631049654304,
|
| 1630 |
+
"grad_norm": 0.8972792625427246,
|
| 1631 |
+
"learning_rate": 8.918319760710629e-05,
|
| 1632 |
+
"loss": 0.4178,
|
| 1633 |
+
"step": 9048
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 1.9038340666247642,
|
| 1637 |
+
"grad_norm": 0.7205092310905457,
|
| 1638 |
+
"learning_rate": 8.90802390618817e-05,
|
| 1639 |
+
"loss": 0.3947,
|
| 1640 |
+
"step": 9087
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 1.912005028284098,
|
| 1644 |
+
"grad_norm": 0.7933651804924011,
|
| 1645 |
+
"learning_rate": 8.897685286444737e-05,
|
| 1646 |
+
"loss": 0.3934,
|
| 1647 |
+
"step": 9126
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 1.9201759899434316,
|
| 1651 |
+
"grad_norm": 0.7529005408287048,
|
| 1652 |
+
"learning_rate": 8.887304014615094e-05,
|
| 1653 |
+
"loss": 0.3951,
|
| 1654 |
+
"step": 9165
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 1.9283469516027656,
|
| 1658 |
+
"grad_norm": 0.5970722436904907,
|
| 1659 |
+
"learning_rate": 8.876880204300744e-05,
|
| 1660 |
+
"loss": 0.3671,
|
| 1661 |
+
"step": 9204
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 1.9365179132620993,
|
| 1665 |
+
"grad_norm": 0.7347320914268494,
|
| 1666 |
+
"learning_rate": 8.86641396956868e-05,
|
| 1667 |
+
"loss": 0.4362,
|
| 1668 |
+
"step": 9243
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 1.944688874921433,
|
| 1672 |
+
"grad_norm": 0.6225306391716003,
|
| 1673 |
+
"learning_rate": 8.855905424950149e-05,
|
| 1674 |
+
"loss": 0.4039,
|
| 1675 |
+
"step": 9282
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 1.9528598365807668,
|
| 1679 |
+
"grad_norm": 0.7711159586906433,
|
| 1680 |
+
"learning_rate": 8.845354685439388e-05,
|
| 1681 |
+
"loss": 0.3766,
|
| 1682 |
+
"step": 9321
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 1.9610307982401005,
|
| 1686 |
+
"grad_norm": 0.7624640464782715,
|
| 1687 |
+
"learning_rate": 8.834761866492373e-05,
|
| 1688 |
+
"loss": 0.3854,
|
| 1689 |
+
"step": 9360
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 1.9692017598994345,
|
| 1693 |
+
"grad_norm": 0.8946365118026733,
|
| 1694 |
+
"learning_rate": 8.824127084025551e-05,
|
| 1695 |
+
"loss": 0.3675,
|
| 1696 |
+
"step": 9399
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 1.9773727215587682,
|
| 1700 |
+
"grad_norm": 0.5043982863426208,
|
| 1701 |
+
"learning_rate": 8.813450454414567e-05,
|
| 1702 |
+
"loss": 0.4078,
|
| 1703 |
+
"step": 9438
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 1.985543683218102,
|
| 1707 |
+
"grad_norm": 0.6283956170082092,
|
| 1708 |
+
"learning_rate": 8.802732094493007e-05,
|
| 1709 |
+
"loss": 0.382,
|
| 1710 |
+
"step": 9477
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 1.9937146448774357,
|
| 1714 |
+
"grad_norm": 0.6801990866661072,
|
| 1715 |
+
"learning_rate": 8.7919721215511e-05,
|
| 1716 |
+
"loss": 0.3883,
|
| 1717 |
+
"step": 9516
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 2.0018856065367694,
|
| 1721 |
+
"grad_norm": 0.6821087598800659,
|
| 1722 |
+
"learning_rate": 8.781170653334445e-05,
|
| 1723 |
+
"loss": 0.3598,
|
| 1724 |
+
"step": 9555
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 2.010056568196103,
|
| 1728 |
+
"grad_norm": 0.8372517824172974,
|
| 1729 |
+
"learning_rate": 8.770327808042724e-05,
|
| 1730 |
+
"loss": 0.3097,
|
| 1731 |
+
"step": 9594
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 2.018227529855437,
|
| 1735 |
+
"grad_norm": 0.5700801014900208,
|
| 1736 |
+
"learning_rate": 8.759443704328405e-05,
|
| 1737 |
+
"loss": 0.2982,
|
| 1738 |
+
"step": 9633
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 2.0263984915147706,
|
| 1742 |
+
"grad_norm": 0.7326349020004272,
|
| 1743 |
+
"learning_rate": 8.748518461295438e-05,
|
| 1744 |
+
"loss": 0.344,
|
| 1745 |
+
"step": 9672
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 2.0345694531741043,
|
| 1749 |
+
"grad_norm": 0.7985721230506897,
|
| 1750 |
+
"learning_rate": 8.737552198497965e-05,
|
| 1751 |
+
"loss": 0.3516,
|
| 1752 |
+
"step": 9711
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 2.042740414833438,
|
| 1756 |
+
"grad_norm": 0.8567628264427185,
|
| 1757 |
+
"learning_rate": 8.726545035939e-05,
|
| 1758 |
+
"loss": 0.3252,
|
| 1759 |
+
"step": 9750
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 2.0509113764927718,
|
| 1763 |
+
"grad_norm": 0.9082648158073425,
|
| 1764 |
+
"learning_rate": 8.715497094069121e-05,
|
| 1765 |
+
"loss": 0.3487,
|
| 1766 |
+
"step": 9789
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 2.0590823381521055,
|
| 1770 |
+
"grad_norm": 1.0632450580596924,
|
| 1771 |
+
"learning_rate": 8.70440849378515e-05,
|
| 1772 |
+
"loss": 0.3224,
|
| 1773 |
+
"step": 9828
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 2.0672532998114392,
|
| 1777 |
+
"grad_norm": 0.8348027467727661,
|
| 1778 |
+
"learning_rate": 8.693279356428835e-05,
|
| 1779 |
+
"loss": 0.313,
|
| 1780 |
+
"step": 9867
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 2.075424261470773,
|
| 1784 |
+
"grad_norm": 0.6354735493659973,
|
| 1785 |
+
"learning_rate": 8.682109803785514e-05,
|
| 1786 |
+
"loss": 0.3337,
|
| 1787 |
+
"step": 9906
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 2.0835952231301067,
|
| 1791 |
+
"grad_norm": 0.9293564558029175,
|
| 1792 |
+
"learning_rate": 8.67089995808279e-05,
|
| 1793 |
+
"loss": 0.3353,
|
| 1794 |
+
"step": 9945
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 2.0917661847894404,
|
| 1798 |
+
"grad_norm": 0.653914213180542,
|
| 1799 |
+
"learning_rate": 8.659649941989186e-05,
|
| 1800 |
+
"loss": 0.3348,
|
| 1801 |
+
"step": 9984
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 2.0951183741881416,
|
| 1805 |
+
"eval_accuracy": 0.009820309467613697,
|
| 1806 |
+
"eval_loss": 0.4311712086200714,
|
| 1807 |
+
"eval_runtime": 816.6202,
|
| 1808 |
+
"eval_samples_per_second": 5.86,
|
| 1809 |
+
"eval_steps_per_second": 1.466,
|
| 1810 |
+
"step": 10000
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 2.099937146448774,
|
| 1814 |
+
"grad_norm": 0.7376769781112671,
|
| 1815 |
+
"learning_rate": 8.648359878612807e-05,
|
| 1816 |
+
"loss": 0.3043,
|
| 1817 |
+
"step": 10023
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 2.108108108108108,
|
| 1821 |
+
"grad_norm": 0.965570330619812,
|
| 1822 |
+
"learning_rate": 8.637029891499997e-05,
|
| 1823 |
+
"loss": 0.3619,
|
| 1824 |
+
"step": 10062
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 2.116279069767442,
|
| 1828 |
+
"grad_norm": 0.8820568919181824,
|
| 1829 |
+
"learning_rate": 8.625660104633981e-05,
|
| 1830 |
+
"loss": 0.3519,
|
| 1831 |
+
"step": 10101
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 2.124450031426776,
|
| 1835 |
+
"grad_norm": 0.9719869494438171,
|
| 1836 |
+
"learning_rate": 8.614250642433506e-05,
|
| 1837 |
+
"loss": 0.3524,
|
| 1838 |
+
"step": 10140
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 2.1326209930861095,
|
| 1842 |
+
"grad_norm": 0.8123674392700195,
|
| 1843 |
+
"learning_rate": 8.602801629751486e-05,
|
| 1844 |
+
"loss": 0.3324,
|
| 1845 |
+
"step": 10179
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 2.1407919547454433,
|
| 1849 |
+
"grad_norm": 0.4851992130279541,
|
| 1850 |
+
"learning_rate": 8.591313191873634e-05,
|
| 1851 |
+
"loss": 0.3331,
|
| 1852 |
+
"step": 10218
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 2.148962916404777,
|
| 1856 |
+
"grad_norm": 0.7514449954032898,
|
| 1857 |
+
"learning_rate": 8.579785454517089e-05,
|
| 1858 |
+
"loss": 0.3195,
|
| 1859 |
+
"step": 10257
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 2.1571338780641107,
|
| 1863 |
+
"grad_norm": 0.6087148785591125,
|
| 1864 |
+
"learning_rate": 8.568218543829039e-05,
|
| 1865 |
+
"loss": 0.3819,
|
| 1866 |
+
"step": 10296
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 2.1653048397234445,
|
| 1870 |
+
"grad_norm": 0.547778308391571,
|
| 1871 |
+
"learning_rate": 8.556612586385349e-05,
|
| 1872 |
+
"loss": 0.3231,
|
| 1873 |
+
"step": 10335
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 2.173475801382778,
|
| 1877 |
+
"grad_norm": 1.0253907442092896,
|
| 1878 |
+
"learning_rate": 8.544967709189162e-05,
|
| 1879 |
+
"loss": 0.3325,
|
| 1880 |
+
"step": 10374
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 2.181646763042112,
|
| 1884 |
+
"grad_norm": 0.7467255592346191,
|
| 1885 |
+
"learning_rate": 8.533284039669524e-05,
|
| 1886 |
+
"loss": 0.3224,
|
| 1887 |
+
"step": 10413
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 2.1898177247014456,
|
| 1891 |
+
"grad_norm": 0.8590918779373169,
|
| 1892 |
+
"learning_rate": 8.52156170567998e-05,
|
| 1893 |
+
"loss": 0.3293,
|
| 1894 |
+
"step": 10452
|
| 1895 |
+
},
|
| 1896 |
+
{
|
| 1897 |
+
"epoch": 2.1979886863607794,
|
| 1898 |
+
"grad_norm": 0.6754146814346313,
|
| 1899 |
+
"learning_rate": 8.509800835497175e-05,
|
| 1900 |
+
"loss": 0.3227,
|
| 1901 |
+
"step": 10491
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 2.206159648020113,
|
| 1905 |
+
"grad_norm": 0.6803106069564819,
|
| 1906 |
+
"learning_rate": 8.498001557819455e-05,
|
| 1907 |
+
"loss": 0.3381,
|
| 1908 |
+
"step": 10530
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 2.214330609679447,
|
| 1912 |
+
"grad_norm": 1.0634793043136597,
|
| 1913 |
+
"learning_rate": 8.486164001765457e-05,
|
| 1914 |
+
"loss": 0.3659,
|
| 1915 |
+
"step": 10569
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 2.2225015713387806,
|
| 1919 |
+
"grad_norm": 0.6654180288314819,
|
| 1920 |
+
"learning_rate": 8.474288296872695e-05,
|
| 1921 |
+
"loss": 0.3359,
|
| 1922 |
+
"step": 10608
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 2.2306725329981143,
|
| 1926 |
+
"grad_norm": 0.9800730347633362,
|
| 1927 |
+
"learning_rate": 8.462374573096143e-05,
|
| 1928 |
+
"loss": 0.3483,
|
| 1929 |
+
"step": 10647
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 2.238843494657448,
|
| 1933 |
+
"grad_norm": 0.7170436382293701,
|
| 1934 |
+
"learning_rate": 8.45042296080681e-05,
|
| 1935 |
+
"loss": 0.3477,
|
| 1936 |
+
"step": 10686
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 2.2470144563167818,
|
| 1940 |
+
"grad_norm": 0.8500722646713257,
|
| 1941 |
+
"learning_rate": 8.438433590790323e-05,
|
| 1942 |
+
"loss": 0.3347,
|
| 1943 |
+
"step": 10725
|
| 1944 |
+
},
|
| 1945 |
+
{
|
| 1946 |
+
"epoch": 2.2551854179761155,
|
| 1947 |
+
"grad_norm": 0.9178040623664856,
|
| 1948 |
+
"learning_rate": 8.426406594245482e-05,
|
| 1949 |
+
"loss": 0.3455,
|
| 1950 |
+
"step": 10764
|
| 1951 |
+
},
|
| 1952 |
+
{
|
| 1953 |
+
"epoch": 2.2633563796354492,
|
| 1954 |
+
"grad_norm": 1.0374339818954468,
|
| 1955 |
+
"learning_rate": 8.414342102782833e-05,
|
| 1956 |
+
"loss": 0.3548,
|
| 1957 |
+
"step": 10803
|
| 1958 |
+
},
|
| 1959 |
+
{
|
| 1960 |
+
"epoch": 2.2715273412947834,
|
| 1961 |
+
"grad_norm": 0.9963250160217285,
|
| 1962 |
+
"learning_rate": 8.40224024842323e-05,
|
| 1963 |
+
"loss": 0.3563,
|
| 1964 |
+
"step": 10842
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 2.2796983029541167,
|
| 1968 |
+
"grad_norm": 0.8895733952522278,
|
| 1969 |
+
"learning_rate": 8.390101163596385e-05,
|
| 1970 |
+
"loss": 0.3229,
|
| 1971 |
+
"step": 10881
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 2.287869264613451,
|
| 1975 |
+
"grad_norm": 0.7974137663841248,
|
| 1976 |
+
"learning_rate": 8.377924981139413e-05,
|
| 1977 |
+
"loss": 0.3201,
|
| 1978 |
+
"step": 10920
|
| 1979 |
+
},
|
| 1980 |
+
{
|
| 1981 |
+
"epoch": 2.2960402262727846,
|
| 1982 |
+
"grad_norm": 0.8204047083854675,
|
| 1983 |
+
"learning_rate": 8.3657118342954e-05,
|
| 1984 |
+
"loss": 0.341,
|
| 1985 |
+
"step": 10959
|
| 1986 |
+
},
|
| 1987 |
+
{
|
| 1988 |
+
"epoch": 2.3042111879321183,
|
| 1989 |
+
"grad_norm": 0.7952179312705994,
|
| 1990 |
+
"learning_rate": 8.353461856711916e-05,
|
| 1991 |
+
"loss": 0.3362,
|
| 1992 |
+
"step": 10998
|
| 1993 |
+
},
|
| 1994 |
+
{
|
| 1995 |
+
"epoch": 2.312382149591452,
|
| 1996 |
+
"grad_norm": 0.6790579557418823,
|
| 1997 |
+
"learning_rate": 8.341175182439577e-05,
|
| 1998 |
+
"loss": 0.322,
|
| 1999 |
+
"step": 11037
|
| 2000 |
+
},
|
| 2001 |
+
{
|
| 2002 |
+
"epoch": 2.320553111250786,
|
| 2003 |
+
"grad_norm": 0.7183639407157898,
|
| 2004 |
+
"learning_rate": 8.328851945930563e-05,
|
| 2005 |
+
"loss": 0.3193,
|
| 2006 |
+
"step": 11076
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 2.3287240729101195,
|
| 2010 |
+
"grad_norm": 0.7216742038726807,
|
| 2011 |
+
"learning_rate": 8.316492282037154e-05,
|
| 2012 |
+
"loss": 0.3319,
|
| 2013 |
+
"step": 11115
|
| 2014 |
+
},
|
| 2015 |
+
{
|
| 2016 |
+
"epoch": 2.3368950345694532,
|
| 2017 |
+
"grad_norm": 0.7550281882286072,
|
| 2018 |
+
"learning_rate": 8.30409632601025e-05,
|
| 2019 |
+
"loss": 0.3249,
|
| 2020 |
+
"step": 11154
|
| 2021 |
+
},
|
| 2022 |
+
{
|
| 2023 |
+
"epoch": 2.345065996228787,
|
| 2024 |
+
"grad_norm": 0.9077494740486145,
|
| 2025 |
+
"learning_rate": 8.291664213497901e-05,
|
| 2026 |
+
"loss": 0.3097,
|
| 2027 |
+
"step": 11193
|
| 2028 |
+
},
|
| 2029 |
+
{
|
| 2030 |
+
"epoch": 2.3532369578881207,
|
| 2031 |
+
"grad_norm": 0.793636679649353,
|
| 2032 |
+
"learning_rate": 8.279196080543803e-05,
|
| 2033 |
+
"loss": 0.3515,
|
| 2034 |
+
"step": 11232
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 2.3614079195474544,
|
| 2038 |
+
"grad_norm": 0.8357187509536743,
|
| 2039 |
+
"learning_rate": 8.266692063585828e-05,
|
| 2040 |
+
"loss": 0.3516,
|
| 2041 |
+
"step": 11271
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 2.369578881206788,
|
| 2045 |
+
"grad_norm": 0.9153121709823608,
|
| 2046 |
+
"learning_rate": 8.254152299454522e-05,
|
| 2047 |
+
"loss": 0.3579,
|
| 2048 |
+
"step": 11310
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 2.377749842866122,
|
| 2052 |
+
"grad_norm": 0.671792209148407,
|
| 2053 |
+
"learning_rate": 8.241576925371615e-05,
|
| 2054 |
+
"loss": 0.3215,
|
| 2055 |
+
"step": 11349
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 2.3859208045254556,
|
| 2059 |
+
"grad_norm": 0.7391782999038696,
|
| 2060 |
+
"learning_rate": 8.228966078948503e-05,
|
| 2061 |
+
"loss": 0.3572,
|
| 2062 |
+
"step": 11388
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 2.3940917661847894,
|
| 2066 |
+
"grad_norm": 0.5811970829963684,
|
| 2067 |
+
"learning_rate": 8.216319898184766e-05,
|
| 2068 |
+
"loss": 0.3054,
|
| 2069 |
+
"step": 11427
|
| 2070 |
+
},
|
| 2071 |
+
{
|
| 2072 |
+
"epoch": 2.402262727844123,
|
| 2073 |
+
"grad_norm": 0.5288280248641968,
|
| 2074 |
+
"learning_rate": 8.203638521466637e-05,
|
| 2075 |
+
"loss": 0.3348,
|
| 2076 |
+
"step": 11466
|
| 2077 |
+
},
|
| 2078 |
+
{
|
| 2079 |
+
"epoch": 2.410433689503457,
|
| 2080 |
+
"grad_norm": 0.8727484941482544,
|
| 2081 |
+
"learning_rate": 8.190922087565496e-05,
|
| 2082 |
+
"loss": 0.3514,
|
| 2083 |
+
"step": 11505
|
| 2084 |
+
},
|
| 2085 |
+
{
|
| 2086 |
+
"epoch": 2.4186046511627906,
|
| 2087 |
+
"grad_norm": 0.8370525240898132,
|
| 2088 |
+
"learning_rate": 8.178170735636354e-05,
|
| 2089 |
+
"loss": 0.3155,
|
| 2090 |
+
"step": 11544
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 2.4267756128221243,
|
| 2094 |
+
"grad_norm": 0.6996369361877441,
|
| 2095 |
+
"learning_rate": 8.165384605216329e-05,
|
| 2096 |
+
"loss": 0.3474,
|
| 2097 |
+
"step": 11583
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 2.434946574481458,
|
| 2101 |
+
"grad_norm": 0.6904685497283936,
|
| 2102 |
+
"learning_rate": 8.152563836223111e-05,
|
| 2103 |
+
"loss": 0.3453,
|
| 2104 |
+
"step": 11622
|
| 2105 |
+
},
|
| 2106 |
+
{
|
| 2107 |
+
"epoch": 2.443117536140792,
|
| 2108 |
+
"grad_norm": 0.7102589011192322,
|
| 2109 |
+
"learning_rate": 8.139708568953444e-05,
|
| 2110 |
+
"loss": 0.337,
|
| 2111 |
+
"step": 11661
|
| 2112 |
+
},
|
| 2113 |
+
{
|
| 2114 |
+
"epoch": 2.4512884978001255,
|
| 2115 |
+
"grad_norm": 0.7969030737876892,
|
| 2116 |
+
"learning_rate": 8.12681894408158e-05,
|
| 2117 |
+
"loss": 0.3213,
|
| 2118 |
+
"step": 11700
|
| 2119 |
+
},
|
| 2120 |
+
{
|
| 2121 |
+
"epoch": 2.4594594594594597,
|
| 2122 |
+
"grad_norm": 0.961298942565918,
|
| 2123 |
+
"learning_rate": 8.113895102657744e-05,
|
| 2124 |
+
"loss": 0.3386,
|
| 2125 |
+
"step": 11739
|
| 2126 |
+
},
|
| 2127 |
+
{
|
| 2128 |
+
"epoch": 2.4676304211187934,
|
| 2129 |
+
"grad_norm": 0.8089680075645447,
|
| 2130 |
+
"learning_rate": 8.100937186106596e-05,
|
| 2131 |
+
"loss": 0.3091,
|
| 2132 |
+
"step": 11778
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"epoch": 2.475801382778127,
|
| 2136 |
+
"grad_norm": 1.0000693798065186,
|
| 2137 |
+
"learning_rate": 8.087945336225668e-05,
|
| 2138 |
+
"loss": 0.3335,
|
| 2139 |
+
"step": 11817
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 2.483972344437461,
|
| 2143 |
+
"grad_norm": 0.6780822277069092,
|
| 2144 |
+
"learning_rate": 8.074919695183831e-05,
|
| 2145 |
+
"loss": 0.3306,
|
| 2146 |
+
"step": 11856
|
| 2147 |
+
},
|
| 2148 |
+
{
|
| 2149 |
+
"epoch": 2.4921433060967946,
|
| 2150 |
+
"grad_norm": 0.8540327548980713,
|
| 2151 |
+
"learning_rate": 8.061860405519724e-05,
|
| 2152 |
+
"loss": 0.3527,
|
| 2153 |
+
"step": 11895
|
| 2154 |
+
},
|
| 2155 |
+
{
|
| 2156 |
+
"epoch": 2.5003142677561283,
|
| 2157 |
+
"grad_norm": 0.8583691120147705,
|
| 2158 |
+
"learning_rate": 8.048767610140204e-05,
|
| 2159 |
+
"loss": 0.3257,
|
| 2160 |
+
"step": 11934
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"epoch": 2.508485229415462,
|
| 2164 |
+
"grad_norm": 0.6268760561943054,
|
| 2165 |
+
"learning_rate": 8.035641452318775e-05,
|
| 2166 |
+
"loss": 0.2978,
|
| 2167 |
+
"step": 11973
|
| 2168 |
+
},
|
| 2169 |
+
{
|
| 2170 |
+
"epoch": 2.5166561910747958,
|
| 2171 |
+
"grad_norm": 0.9798884391784668,
|
| 2172 |
+
"learning_rate": 8.022482075694027e-05,
|
| 2173 |
+
"loss": 0.3297,
|
| 2174 |
+
"step": 12012
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"epoch": 2.5248271527341295,
|
| 2178 |
+
"grad_norm": 0.8267270922660828,
|
| 2179 |
+
"learning_rate": 8.009289624268062e-05,
|
| 2180 |
+
"loss": 0.3509,
|
| 2181 |
+
"step": 12051
|
| 2182 |
+
},
|
| 2183 |
+
{
|
| 2184 |
+
"epoch": 2.5329981143934632,
|
| 2185 |
+
"grad_norm": 0.6128790974617004,
|
| 2186 |
+
"learning_rate": 7.996064242404912e-05,
|
| 2187 |
+
"loss": 0.3134,
|
| 2188 |
+
"step": 12090
|
| 2189 |
+
},
|
| 2190 |
+
{
|
| 2191 |
+
"epoch": 2.541169076052797,
|
| 2192 |
+
"grad_norm": 0.8551040887832642,
|
| 2193 |
+
"learning_rate": 7.98280607482897e-05,
|
| 2194 |
+
"loss": 0.3563,
|
| 2195 |
+
"step": 12129
|
| 2196 |
+
},
|
| 2197 |
+
{
|
| 2198 |
+
"epoch": 2.5493400377121307,
|
| 2199 |
+
"grad_norm": 0.9739424586296082,
|
| 2200 |
+
"learning_rate": 7.969515266623396e-05,
|
| 2201 |
+
"loss": 0.3468,
|
| 2202 |
+
"step": 12168
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 2.5575109993714644,
|
| 2206 |
+
"grad_norm": 0.6370837092399597,
|
| 2207 |
+
"learning_rate": 7.956191963228538e-05,
|
| 2208 |
+
"loss": 0.3462,
|
| 2209 |
+
"step": 12207
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 2.565681961030798,
|
| 2213 |
+
"grad_norm": 0.6456401944160461,
|
| 2214 |
+
"learning_rate": 7.942836310440334e-05,
|
| 2215 |
+
"loss": 0.3266,
|
| 2216 |
+
"step": 12246
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 2.573852922690132,
|
| 2220 |
+
"grad_norm": 0.8971288800239563,
|
| 2221 |
+
"learning_rate": 7.929448454408719e-05,
|
| 2222 |
+
"loss": 0.3292,
|
| 2223 |
+
"step": 12285
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 2.5820238843494656,
|
| 2227 |
+
"grad_norm": 0.8512323498725891,
|
| 2228 |
+
"learning_rate": 7.916028541636027e-05,
|
| 2229 |
+
"loss": 0.3402,
|
| 2230 |
+
"step": 12324
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 2.5901948460087993,
|
| 2234 |
+
"grad_norm": 0.7138497233390808,
|
| 2235 |
+
"learning_rate": 7.902576718975387e-05,
|
| 2236 |
+
"loss": 0.3658,
|
| 2237 |
+
"step": 12363
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 2.5983658076681335,
|
| 2241 |
+
"grad_norm": 0.9771799445152283,
|
| 2242 |
+
"learning_rate": 7.889093133629115e-05,
|
| 2243 |
+
"loss": 0.312,
|
| 2244 |
+
"step": 12402
|
| 2245 |
+
},
|
| 2246 |
+
{
|
| 2247 |
+
"epoch": 2.606536769327467,
|
| 2248 |
+
"grad_norm": 0.8607495427131653,
|
| 2249 |
+
"learning_rate": 7.875577933147101e-05,
|
| 2250 |
+
"loss": 0.3289,
|
| 2251 |
+
"step": 12441
|
| 2252 |
+
},
|
| 2253 |
+
{
|
| 2254 |
+
"epoch": 2.614707730986801,
|
| 2255 |
+
"grad_norm": 0.9107287526130676,
|
| 2256 |
+
"learning_rate": 7.8620312654252e-05,
|
| 2257 |
+
"loss": 0.3435,
|
| 2258 |
+
"step": 12480
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 2.6228786926461343,
|
| 2262 |
+
"grad_norm": 0.7893658876419067,
|
| 2263 |
+
"learning_rate": 7.848453278703613e-05,
|
| 2264 |
+
"loss": 0.3325,
|
| 2265 |
+
"step": 12519
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 2.6310496543054684,
|
| 2269 |
+
"grad_norm": 0.6861433982849121,
|
| 2270 |
+
"learning_rate": 7.834844121565257e-05,
|
| 2271 |
+
"loss": 0.3185,
|
| 2272 |
+
"step": 12558
|
| 2273 |
+
},
|
| 2274 |
+
{
|
| 2275 |
+
"epoch": 2.639220615964802,
|
| 2276 |
+
"grad_norm": 0.6425657272338867,
|
| 2277 |
+
"learning_rate": 7.821203942934148e-05,
|
| 2278 |
+
"loss": 0.3314,
|
| 2279 |
+
"step": 12597
|
| 2280 |
+
},
|
| 2281 |
+
{
|
| 2282 |
+
"epoch": 2.647391577624136,
|
| 2283 |
+
"grad_norm": 0.6099838018417358,
|
| 2284 |
+
"learning_rate": 7.807532892073768e-05,
|
| 2285 |
+
"loss": 0.3302,
|
| 2286 |
+
"step": 12636
|
| 2287 |
+
},
|
| 2288 |
+
{
|
| 2289 |
+
"epoch": 2.6555625392834696,
|
| 2290 |
+
"grad_norm": 0.8393537402153015,
|
| 2291 |
+
"learning_rate": 7.793831118585429e-05,
|
| 2292 |
+
"loss": 0.3088,
|
| 2293 |
+
"step": 12675
|
| 2294 |
+
},
|
| 2295 |
+
{
|
| 2296 |
+
"epoch": 2.6637335009428034,
|
| 2297 |
+
"grad_norm": 0.752255916595459,
|
| 2298 |
+
"learning_rate": 7.780098772406643e-05,
|
| 2299 |
+
"loss": 0.3205,
|
| 2300 |
+
"step": 12714
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 2.671904462602137,
|
| 2304 |
+
"grad_norm": 0.7880775928497314,
|
| 2305 |
+
"learning_rate": 7.766336003809472e-05,
|
| 2306 |
+
"loss": 0.3306,
|
| 2307 |
+
"step": 12753
|
| 2308 |
+
},
|
| 2309 |
+
{
|
| 2310 |
+
"epoch": 2.680075424261471,
|
| 2311 |
+
"grad_norm": 0.708419919013977,
|
| 2312 |
+
"learning_rate": 7.752542963398892e-05,
|
| 2313 |
+
"loss": 0.3554,
|
| 2314 |
+
"step": 12792
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 2.6882463859208046,
|
| 2318 |
+
"grad_norm": 0.8341570496559143,
|
| 2319 |
+
"learning_rate": 7.738719802111139e-05,
|
| 2320 |
+
"loss": 0.3145,
|
| 2321 |
+
"step": 12831
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"epoch": 2.6964173475801383,
|
| 2325 |
+
"grad_norm": 0.703484058380127,
|
| 2326 |
+
"learning_rate": 7.724866671212059e-05,
|
| 2327 |
+
"loss": 0.3284,
|
| 2328 |
+
"step": 12870
|
| 2329 |
+
},
|
| 2330 |
+
{
|
| 2331 |
+
"epoch": 2.704588309239472,
|
| 2332 |
+
"grad_norm": 0.7732682228088379,
|
| 2333 |
+
"learning_rate": 7.710983722295455e-05,
|
| 2334 |
+
"loss": 0.3376,
|
| 2335 |
+
"step": 12909
|
| 2336 |
+
},
|
| 2337 |
+
{
|
| 2338 |
+
"epoch": 2.7127592708988058,
|
| 2339 |
+
"grad_norm": 0.7687979340553284,
|
| 2340 |
+
"learning_rate": 7.697071107281428e-05,
|
| 2341 |
+
"loss": 0.3418,
|
| 2342 |
+
"step": 12948
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 2.7209302325581395,
|
| 2346 |
+
"grad_norm": 0.6588707566261292,
|
| 2347 |
+
"learning_rate": 7.683128978414707e-05,
|
| 2348 |
+
"loss": 0.3352,
|
| 2349 |
+
"step": 12987
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 2.729101194217473,
|
| 2353 |
+
"grad_norm": 1.0603809356689453,
|
| 2354 |
+
"learning_rate": 7.669157488262997e-05,
|
| 2355 |
+
"loss": 0.3409,
|
| 2356 |
+
"step": 13026
|
| 2357 |
+
},
|
| 2358 |
+
{
|
| 2359 |
+
"epoch": 2.737272155876807,
|
| 2360 |
+
"grad_norm": 0.603203296661377,
|
| 2361 |
+
"learning_rate": 7.655156789715295e-05,
|
| 2362 |
+
"loss": 0.3578,
|
| 2363 |
+
"step": 13065
|
| 2364 |
+
},
|
| 2365 |
+
{
|
| 2366 |
+
"epoch": 2.7454431175361407,
|
| 2367 |
+
"grad_norm": 0.9588086605072021,
|
| 2368 |
+
"learning_rate": 7.641127035980222e-05,
|
| 2369 |
+
"loss": 0.3463,
|
| 2370 |
+
"step": 13104
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 2.7536140791954744,
|
| 2374 |
+
"grad_norm": 0.7366406917572021,
|
| 2375 |
+
"learning_rate": 7.627068380584359e-05,
|
| 2376 |
+
"loss": 0.3262,
|
| 2377 |
+
"step": 13143
|
| 2378 |
+
},
|
| 2379 |
+
{
|
| 2380 |
+
"epoch": 2.761785040854808,
|
| 2381 |
+
"grad_norm": 0.7737981677055359,
|
| 2382 |
+
"learning_rate": 7.612980977370542e-05,
|
| 2383 |
+
"loss": 0.3463,
|
| 2384 |
+
"step": 13182
|
| 2385 |
+
},
|
| 2386 |
+
{
|
| 2387 |
+
"epoch": 2.7699560025141423,
|
| 2388 |
+
"grad_norm": 0.7862906455993652,
|
| 2389 |
+
"learning_rate": 7.5988649804962e-05,
|
| 2390 |
+
"loss": 0.3257,
|
| 2391 |
+
"step": 13221
|
| 2392 |
+
},
|
| 2393 |
+
{
|
| 2394 |
+
"epoch": 2.7781269641734756,
|
| 2395 |
+
"grad_norm": 0.8357959389686584,
|
| 2396 |
+
"learning_rate": 7.584720544431661e-05,
|
| 2397 |
+
"loss": 0.3365,
|
| 2398 |
+
"step": 13260
|
| 2399 |
+
},
|
| 2400 |
+
{
|
| 2401 |
+
"epoch": 2.7862979258328098,
|
| 2402 |
+
"grad_norm": 0.8603371381759644,
|
| 2403 |
+
"learning_rate": 7.570547823958454e-05,
|
| 2404 |
+
"loss": 0.3296,
|
| 2405 |
+
"step": 13299
|
| 2406 |
+
},
|
| 2407 |
+
{
|
| 2408 |
+
"epoch": 2.794468887492143,
|
| 2409 |
+
"grad_norm": 1.0153621435165405,
|
| 2410 |
+
"learning_rate": 7.55634697416763e-05,
|
| 2411 |
+
"loss": 0.3621,
|
| 2412 |
+
"step": 13338
|
| 2413 |
+
},
|
| 2414 |
+
{
|
| 2415 |
+
"epoch": 2.8026398491514772,
|
| 2416 |
+
"grad_norm": 0.6060919761657715,
|
| 2417 |
+
"learning_rate": 7.542118150458054e-05,
|
| 2418 |
+
"loss": 0.3263,
|
| 2419 |
+
"step": 13377
|
| 2420 |
+
},
|
| 2421 |
+
{
|
| 2422 |
+
"epoch": 2.810810810810811,
|
| 2423 |
+
"grad_norm": 0.6489693522453308,
|
| 2424 |
+
"learning_rate": 7.527861508534706e-05,
|
| 2425 |
+
"loss": 0.3632,
|
| 2426 |
+
"step": 13416
|
| 2427 |
+
},
|
| 2428 |
+
{
|
| 2429 |
+
"epoch": 2.8189817724701447,
|
| 2430 |
+
"grad_norm": 0.7105704545974731,
|
| 2431 |
+
"learning_rate": 7.513577204406985e-05,
|
| 2432 |
+
"loss": 0.3522,
|
| 2433 |
+
"step": 13455
|
| 2434 |
+
},
|
| 2435 |
+
{
|
| 2436 |
+
"epoch": 2.8271527341294784,
|
| 2437 |
+
"grad_norm": 0.7109383940696716,
|
| 2438 |
+
"learning_rate": 7.499265394386983e-05,
|
| 2439 |
+
"loss": 0.3462,
|
| 2440 |
+
"step": 13494
|
| 2441 |
+
},
|
| 2442 |
+
{
|
| 2443 |
+
"epoch": 2.835323695788812,
|
| 2444 |
+
"grad_norm": 0.7103734016418457,
|
| 2445 |
+
"learning_rate": 7.484926235087799e-05,
|
| 2446 |
+
"loss": 0.3559,
|
| 2447 |
+
"step": 13533
|
| 2448 |
+
},
|
| 2449 |
+
{
|
| 2450 |
+
"epoch": 2.843494657448146,
|
| 2451 |
+
"grad_norm": 0.6860262155532837,
|
| 2452 |
+
"learning_rate": 7.470559883421809e-05,
|
| 2453 |
+
"loss": 0.3576,
|
| 2454 |
+
"step": 13572
|
| 2455 |
+
},
|
| 2456 |
+
{
|
| 2457 |
+
"epoch": 2.8516656191074796,
|
| 2458 |
+
"grad_norm": 0.7737835645675659,
|
| 2459 |
+
"learning_rate": 7.456166496598953e-05,
|
| 2460 |
+
"loss": 0.3712,
|
| 2461 |
+
"step": 13611
|
| 2462 |
+
},
|
| 2463 |
+
{
|
| 2464 |
+
"epoch": 2.8598365807668134,
|
| 2465 |
+
"grad_norm": 0.8572138547897339,
|
| 2466 |
+
"learning_rate": 7.441746232125013e-05,
|
| 2467 |
+
"loss": 0.3201,
|
| 2468 |
+
"step": 13650
|
| 2469 |
+
},
|
| 2470 |
+
{
|
| 2471 |
+
"epoch": 2.868007542426147,
|
| 2472 |
+
"grad_norm": 0.9748623967170715,
|
| 2473 |
+
"learning_rate": 7.427299247799895e-05,
|
| 2474 |
+
"loss": 0.3563,
|
| 2475 |
+
"step": 13689
|
| 2476 |
+
},
|
| 2477 |
+
{
|
| 2478 |
+
"epoch": 2.876178504085481,
|
| 2479 |
+
"grad_norm": 0.8315281867980957,
|
| 2480 |
+
"learning_rate": 7.412825701715893e-05,
|
| 2481 |
+
"loss": 0.3346,
|
| 2482 |
+
"step": 13728
|
| 2483 |
+
},
|
| 2484 |
+
{
|
| 2485 |
+
"epoch": 2.8843494657448145,
|
| 2486 |
+
"grad_norm": 0.890327513217926,
|
| 2487 |
+
"learning_rate": 7.398325752255973e-05,
|
| 2488 |
+
"loss": 0.3337,
|
| 2489 |
+
"step": 13767
|
| 2490 |
+
},
|
| 2491 |
+
{
|
| 2492 |
+
"epoch": 2.8925204274041483,
|
| 2493 |
+
"grad_norm": 0.6312198638916016,
|
| 2494 |
+
"learning_rate": 7.38379955809202e-05,
|
| 2495 |
+
"loss": 0.337,
|
| 2496 |
+
"step": 13806
|
| 2497 |
+
},
|
| 2498 |
+
{
|
| 2499 |
+
"epoch": 2.900691389063482,
|
| 2500 |
+
"grad_norm": 0.6604064702987671,
|
| 2501 |
+
"learning_rate": 7.369247278183123e-05,
|
| 2502 |
+
"loss": 0.3397,
|
| 2503 |
+
"step": 13845
|
| 2504 |
+
},
|
| 2505 |
+
{
|
| 2506 |
+
"epoch": 2.9088623507228157,
|
| 2507 |
+
"grad_norm": 0.5490432381629944,
|
| 2508 |
+
"learning_rate": 7.35466907177382e-05,
|
| 2509 |
+
"loss": 0.326,
|
| 2510 |
+
"step": 13884
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 2.9170333123821495,
|
| 2514 |
+
"grad_norm": 0.9371681809425354,
|
| 2515 |
+
"learning_rate": 7.340065098392361e-05,
|
| 2516 |
+
"loss": 0.3435,
|
| 2517 |
+
"step": 13923
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 2.925204274041483,
|
| 2521 |
+
"grad_norm": 0.8379968404769897,
|
| 2522 |
+
"learning_rate": 7.325435517848963e-05,
|
| 2523 |
+
"loss": 0.3321,
|
| 2524 |
+
"step": 13962
|
| 2525 |
+
},
|
| 2526 |
+
{
|
| 2527 |
+
"epoch": 2.933375235700817,
|
| 2528 |
+
"grad_norm": 0.3769962191581726,
|
| 2529 |
+
"learning_rate": 7.310780490234061e-05,
|
| 2530 |
+
"loss": 0.3707,
|
| 2531 |
+
"step": 14001
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"epoch": 2.941546197360151,
|
| 2535 |
+
"grad_norm": 0.659055233001709,
|
| 2536 |
+
"learning_rate": 7.296100175916556e-05,
|
| 2537 |
+
"loss": 0.331,
|
| 2538 |
+
"step": 14040
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 2.9497171590194844,
|
| 2542 |
+
"grad_norm": 0.840793251991272,
|
| 2543 |
+
"learning_rate": 7.281394735542056e-05,
|
| 2544 |
+
"loss": 0.3382,
|
| 2545 |
+
"step": 14079
|
| 2546 |
+
},
|
| 2547 |
+
{
|
| 2548 |
+
"epoch": 2.9578881206788186,
|
| 2549 |
+
"grad_norm": 0.8272313475608826,
|
| 2550 |
+
"learning_rate": 7.266664330031128e-05,
|
| 2551 |
+
"loss": 0.316,
|
| 2552 |
+
"step": 14118
|
| 2553 |
+
},
|
| 2554 |
+
{
|
| 2555 |
+
"epoch": 2.966059082338152,
|
| 2556 |
+
"grad_norm": 0.9367392063140869,
|
| 2557 |
+
"learning_rate": 7.25190912057752e-05,
|
| 2558 |
+
"loss": 0.336,
|
| 2559 |
+
"step": 14157
|
| 2560 |
+
},
|
| 2561 |
+
{
|
| 2562 |
+
"epoch": 2.974230043997486,
|
| 2563 |
+
"grad_norm": 0.6122297048568726,
|
| 2564 |
+
"learning_rate": 7.237129268646419e-05,
|
| 2565 |
+
"loss": 0.323,
|
| 2566 |
+
"step": 14196
|
| 2567 |
+
},
|
| 2568 |
+
{
|
| 2569 |
+
"epoch": 2.9824010056568198,
|
| 2570 |
+
"grad_norm": 0.7298004031181335,
|
| 2571 |
+
"learning_rate": 7.22232493597267e-05,
|
| 2572 |
+
"loss": 0.3361,
|
| 2573 |
+
"step": 14235
|
| 2574 |
+
},
|
| 2575 |
+
{
|
| 2576 |
+
"epoch": 2.9905719673161535,
|
| 2577 |
+
"grad_norm": 0.7116037607192993,
|
| 2578 |
+
"learning_rate": 7.207496284559003e-05,
|
| 2579 |
+
"loss": 0.3035,
|
| 2580 |
+
"step": 14274
|
| 2581 |
+
},
|
| 2582 |
+
{
|
| 2583 |
+
"epoch": 2.998742928975487,
|
| 2584 |
+
"grad_norm": 0.886817216873169,
|
| 2585 |
+
"learning_rate": 7.192643476674272e-05,
|
| 2586 |
+
"loss": 0.3156,
|
| 2587 |
+
"step": 14313
|
| 2588 |
+
},
|
| 2589 |
+
{
|
| 2590 |
+
"epoch": 3.006913890634821,
|
| 2591 |
+
"grad_norm": 0.7054494619369507,
|
| 2592 |
+
"learning_rate": 7.177766674851674e-05,
|
| 2593 |
+
"loss": 0.2916,
|
| 2594 |
+
"step": 14352
|
| 2595 |
+
},
|
| 2596 |
+
{
|
| 2597 |
+
"epoch": 3.0150848522941547,
|
| 2598 |
+
"grad_norm": 0.6415011882781982,
|
| 2599 |
+
"learning_rate": 7.162866041886963e-05,
|
| 2600 |
+
"loss": 0.2485,
|
| 2601 |
+
"step": 14391
|
| 2602 |
+
},
|
| 2603 |
+
{
|
| 2604 |
+
"epoch": 3.0232558139534884,
|
| 2605 |
+
"grad_norm": 0.9112984538078308,
|
| 2606 |
+
"learning_rate": 7.147941740836686e-05,
|
| 2607 |
+
"loss": 0.2598,
|
| 2608 |
+
"step": 14430
|
| 2609 |
+
},
|
| 2610 |
+
{
|
| 2611 |
+
"epoch": 3.031426775612822,
|
| 2612 |
+
"grad_norm": 0.9063923358917236,
|
| 2613 |
+
"learning_rate": 7.132993935016377e-05,
|
| 2614 |
+
"loss": 0.255,
|
| 2615 |
+
"step": 14469
|
| 2616 |
+
},
|
| 2617 |
+
{
|
| 2618 |
+
"epoch": 3.039597737272156,
|
| 2619 |
+
"grad_norm": 0.897348165512085,
|
| 2620 |
+
"learning_rate": 7.118022787998788e-05,
|
| 2621 |
+
"loss": 0.2622,
|
| 2622 |
+
"step": 14508
|
| 2623 |
+
},
|
| 2624 |
+
{
|
| 2625 |
+
"epoch": 3.0477686989314896,
|
| 2626 |
+
"grad_norm": 0.9947516322135925,
|
| 2627 |
+
"learning_rate": 7.103028463612094e-05,
|
| 2628 |
+
"loss": 0.2539,
|
| 2629 |
+
"step": 14547
|
| 2630 |
+
},
|
| 2631 |
+
{
|
| 2632 |
+
"epoch": 3.0559396605908233,
|
| 2633 |
+
"grad_norm": 0.9619819521903992,
|
| 2634 |
+
"learning_rate": 7.088011125938091e-05,
|
| 2635 |
+
"loss": 0.2546,
|
| 2636 |
+
"step": 14586
|
| 2637 |
+
},
|
| 2638 |
+
{
|
| 2639 |
+
"epoch": 3.064110622250157,
|
| 2640 |
+
"grad_norm": 0.9941222071647644,
|
| 2641 |
+
"learning_rate": 7.072970939310412e-05,
|
| 2642 |
+
"loss": 0.2605,
|
| 2643 |
+
"step": 14625
|
| 2644 |
+
},
|
| 2645 |
+
{
|
| 2646 |
+
"epoch": 3.072281583909491,
|
| 2647 |
+
"grad_norm": 0.8076801896095276,
|
| 2648 |
+
"learning_rate": 7.057908068312726e-05,
|
| 2649 |
+
"loss": 0.2748,
|
| 2650 |
+
"step": 14664
|
| 2651 |
+
},
|
| 2652 |
+
{
|
| 2653 |
+
"epoch": 3.0804525455688245,
|
| 2654 |
+
"grad_norm": 0.9070518016815186,
|
| 2655 |
+
"learning_rate": 7.042822677776929e-05,
|
| 2656 |
+
"loss": 0.26,
|
| 2657 |
+
"step": 14703
|
| 2658 |
+
},
|
| 2659 |
+
{
|
| 2660 |
+
"epoch": 3.0886235072281583,
|
| 2661 |
+
"grad_norm": 1.0293809175491333,
|
| 2662 |
+
"learning_rate": 7.027714932781355e-05,
|
| 2663 |
+
"loss": 0.2703,
|
| 2664 |
+
"step": 14742
|
| 2665 |
+
},
|
| 2666 |
+
{
|
| 2667 |
+
"epoch": 3.096794468887492,
|
| 2668 |
+
"grad_norm": 0.982684850692749,
|
| 2669 |
+
"learning_rate": 7.012584998648956e-05,
|
| 2670 |
+
"loss": 0.2693,
|
| 2671 |
+
"step": 14781
|
| 2672 |
+
},
|
| 2673 |
+
{
|
| 2674 |
+
"epoch": 3.1049654305468257,
|
| 2675 |
+
"grad_norm": 1.306250810623169,
|
| 2676 |
+
"learning_rate": 6.997433040945498e-05,
|
| 2677 |
+
"loss": 0.2772,
|
| 2678 |
+
"step": 14820
|
| 2679 |
+
},
|
| 2680 |
+
{
|
| 2681 |
+
"epoch": 3.1131363922061595,
|
| 2682 |
+
"grad_norm": 0.8497562408447266,
|
| 2683 |
+
"learning_rate": 6.982259225477753e-05,
|
| 2684 |
+
"loss": 0.278,
|
| 2685 |
+
"step": 14859
|
| 2686 |
+
},
|
| 2687 |
+
{
|
| 2688 |
+
"epoch": 3.121307353865493,
|
| 2689 |
+
"grad_norm": 0.9325224161148071,
|
| 2690 |
+
"learning_rate": 6.967063718291673e-05,
|
| 2691 |
+
"loss": 0.2726,
|
| 2692 |
+
"step": 14898
|
| 2693 |
+
},
|
| 2694 |
+
{
|
| 2695 |
+
"epoch": 3.1294783155248274,
|
| 2696 |
+
"grad_norm": 0.9601906538009644,
|
| 2697 |
+
"learning_rate": 6.951846685670594e-05,
|
| 2698 |
+
"loss": 0.2573,
|
| 2699 |
+
"step": 14937
|
| 2700 |
+
},
|
| 2701 |
+
{
|
| 2702 |
+
"epoch": 3.137649277184161,
|
| 2703 |
+
"grad_norm": 0.8388446569442749,
|
| 2704 |
+
"learning_rate": 6.936608294133391e-05,
|
| 2705 |
+
"loss": 0.2719,
|
| 2706 |
+
"step": 14976
|
| 2707 |
+
},
|
| 2708 |
+
{
|
| 2709 |
+
"epoch": 3.145820238843495,
|
| 2710 |
+
"grad_norm": 0.7028934359550476,
|
| 2711 |
+
"learning_rate": 6.921348710432675e-05,
|
| 2712 |
+
"loss": 0.2539,
|
| 2713 |
+
"step": 15015
|
| 2714 |
+
},
|
| 2715 |
+
{
|
| 2716 |
+
"epoch": 3.1539912005028286,
|
| 2717 |
+
"grad_norm": 0.8849790692329407,
|
| 2718 |
+
"learning_rate": 6.906068101552957e-05,
|
| 2719 |
+
"loss": 0.2436,
|
| 2720 |
+
"step": 15054
|
| 2721 |
+
},
|
| 2722 |
+
{
|
| 2723 |
+
"epoch": 3.1621621621621623,
|
| 2724 |
+
"grad_norm": 0.7171310186386108,
|
| 2725 |
+
"learning_rate": 6.890766634708826e-05,
|
| 2726 |
+
"loss": 0.26,
|
| 2727 |
+
"step": 15093
|
| 2728 |
+
},
|
| 2729 |
+
{
|
| 2730 |
+
"epoch": 3.170333123821496,
|
| 2731 |
+
"grad_norm": 0.8107304573059082,
|
| 2732 |
+
"learning_rate": 6.875444477343123e-05,
|
| 2733 |
+
"loss": 0.2505,
|
| 2734 |
+
"step": 15132
|
| 2735 |
+
},
|
| 2736 |
+
{
|
| 2737 |
+
"epoch": 3.1785040854808297,
|
| 2738 |
+
"grad_norm": 1.0732225179672241,
|
| 2739 |
+
"learning_rate": 6.860101797125098e-05,
|
| 2740 |
+
"loss": 0.2418,
|
| 2741 |
+
"step": 15171
|
| 2742 |
+
},
|
| 2743 |
+
{
|
| 2744 |
+
"epoch": 3.1866750471401635,
|
| 2745 |
+
"grad_norm": 1.0856764316558838,
|
| 2746 |
+
"learning_rate": 6.844738761948584e-05,
|
| 2747 |
+
"loss": 0.2585,
|
| 2748 |
+
"step": 15210
|
| 2749 |
+
},
|
| 2750 |
+
{
|
| 2751 |
+
"epoch": 3.194846008799497,
|
| 2752 |
+
"grad_norm": 1.0335191488265991,
|
| 2753 |
+
"learning_rate": 6.829355539930156e-05,
|
| 2754 |
+
"loss": 0.2838,
|
| 2755 |
+
"step": 15249
|
| 2756 |
+
},
|
| 2757 |
+
{
|
| 2758 |
+
"epoch": 3.203016970458831,
|
| 2759 |
+
"grad_norm": 0.895849883556366,
|
| 2760 |
+
"learning_rate": 6.81395229940729e-05,
|
| 2761 |
+
"loss": 0.2619,
|
| 2762 |
+
"step": 15288
|
| 2763 |
+
},
|
| 2764 |
+
{
|
| 2765 |
+
"epoch": 3.2111879321181647,
|
| 2766 |
+
"grad_norm": 1.054457426071167,
|
| 2767 |
+
"learning_rate": 6.798529208936528e-05,
|
| 2768 |
+
"loss": 0.2867,
|
| 2769 |
+
"step": 15327
|
| 2770 |
+
},
|
| 2771 |
+
{
|
| 2772 |
+
"epoch": 3.2193588937774984,
|
| 2773 |
+
"grad_norm": 1.171610951423645,
|
| 2774 |
+
"learning_rate": 6.783086437291623e-05,
|
| 2775 |
+
"loss": 0.2718,
|
| 2776 |
+
"step": 15366
|
| 2777 |
+
},
|
| 2778 |
+
{
|
| 2779 |
+
"epoch": 3.227529855436832,
|
| 2780 |
+
"grad_norm": 1.4226104021072388,
|
| 2781 |
+
"learning_rate": 6.767624153461701e-05,
|
| 2782 |
+
"loss": 0.2584,
|
| 2783 |
+
"step": 15405
|
| 2784 |
+
},
|
| 2785 |
+
{
|
| 2786 |
+
"epoch": 3.235700817096166,
|
| 2787 |
+
"grad_norm": 0.7325811386108398,
|
| 2788 |
+
"learning_rate": 6.75214252664941e-05,
|
| 2789 |
+
"loss": 0.2572,
|
| 2790 |
+
"step": 15444
|
| 2791 |
+
},
|
| 2792 |
+
{
|
| 2793 |
+
"epoch": 3.2438717787554996,
|
| 2794 |
+
"grad_norm": 1.8367798328399658,
|
| 2795 |
+
"learning_rate": 6.736641726269065e-05,
|
| 2796 |
+
"loss": 0.2383,
|
| 2797 |
+
"step": 15483
|
| 2798 |
+
},
|
| 2799 |
+
{
|
| 2800 |
+
"epoch": 3.2520427404148333,
|
| 2801 |
+
"grad_norm": 1.2098209857940674,
|
| 2802 |
+
"learning_rate": 6.721121921944791e-05,
|
| 2803 |
+
"loss": 0.2668,
|
| 2804 |
+
"step": 15522
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 3.260213702074167,
|
| 2808 |
+
"grad_norm": 0.9780440330505371,
|
| 2809 |
+
"learning_rate": 6.70558328350868e-05,
|
| 2810 |
+
"loss": 0.2375,
|
| 2811 |
+
"step": 15561
|
| 2812 |
+
},
|
| 2813 |
+
{
|
| 2814 |
+
"epoch": 3.268384663733501,
|
| 2815 |
+
"grad_norm": 0.8904445767402649,
|
| 2816 |
+
"learning_rate": 6.69002598099892e-05,
|
| 2817 |
+
"loss": 0.2525,
|
| 2818 |
+
"step": 15600
|
| 2819 |
+
},
|
| 2820 |
+
{
|
| 2821 |
+
"epoch": 3.2765556253928345,
|
| 2822 |
+
"grad_norm": 0.9340187311172485,
|
| 2823 |
+
"learning_rate": 6.674450184657939e-05,
|
| 2824 |
+
"loss": 0.2691,
|
| 2825 |
+
"step": 15639
|
| 2826 |
+
},
|
| 2827 |
+
{
|
| 2828 |
+
"epoch": 3.2847265870521687,
|
| 2829 |
+
"grad_norm": 0.9010167717933655,
|
| 2830 |
+
"learning_rate": 6.658856064930542e-05,
|
| 2831 |
+
"loss": 0.258,
|
| 2832 |
+
"step": 15678
|
| 2833 |
+
},
|
| 2834 |
+
{
|
| 2835 |
+
"epoch": 3.292897548711502,
|
| 2836 |
+
"grad_norm": 1.3005743026733398,
|
| 2837 |
+
"learning_rate": 6.643243792462047e-05,
|
| 2838 |
+
"loss": 0.2713,
|
| 2839 |
+
"step": 15717
|
| 2840 |
+
},
|
| 2841 |
+
{
|
| 2842 |
+
"epoch": 3.301068510370836,
|
| 2843 |
+
"grad_norm": 0.9360527396202087,
|
| 2844 |
+
"learning_rate": 6.627613538096412e-05,
|
| 2845 |
+
"loss": 0.2615,
|
| 2846 |
+
"step": 15756
|
| 2847 |
+
},
|
| 2848 |
+
{
|
| 2849 |
+
"epoch": 3.30923947203017,
|
| 2850 |
+
"grad_norm": 0.8945103287696838,
|
| 2851 |
+
"learning_rate": 6.611965472874371e-05,
|
| 2852 |
+
"loss": 0.2698,
|
| 2853 |
+
"step": 15795
|
| 2854 |
+
},
|
| 2855 |
+
{
|
| 2856 |
+
"epoch": 3.3174104336895036,
|
| 2857 |
+
"grad_norm": 0.8402488827705383,
|
| 2858 |
+
"learning_rate": 6.596299768031567e-05,
|
| 2859 |
+
"loss": 0.2723,
|
| 2860 |
+
"step": 15834
|
| 2861 |
+
},
|
| 2862 |
+
{
|
| 2863 |
+
"epoch": 3.3255813953488373,
|
| 2864 |
+
"grad_norm": 0.8912140130996704,
|
| 2865 |
+
"learning_rate": 6.580616594996663e-05,
|
| 2866 |
+
"loss": 0.2754,
|
| 2867 |
+
"step": 15873
|
| 2868 |
+
},
|
| 2869 |
+
{
|
| 2870 |
+
"epoch": 3.333752357008171,
|
| 2871 |
+
"grad_norm": 0.9579502940177917,
|
| 2872 |
+
"learning_rate": 6.564916125389482e-05,
|
| 2873 |
+
"loss": 0.2474,
|
| 2874 |
+
"step": 15912
|
| 2875 |
+
},
|
| 2876 |
+
{
|
| 2877 |
+
"epoch": 3.341923318667505,
|
| 2878 |
+
"grad_norm": 1.2083587646484375,
|
| 2879 |
+
"learning_rate": 6.549198531019116e-05,
|
| 2880 |
+
"loss": 0.2546,
|
| 2881 |
+
"step": 15951
|
| 2882 |
+
},
|
| 2883 |
+
{
|
| 2884 |
+
"epoch": 3.3500942803268385,
|
| 2885 |
+
"grad_norm": 1.0274497270584106,
|
| 2886 |
+
"learning_rate": 6.533463983882059e-05,
|
| 2887 |
+
"loss": 0.2659,
|
| 2888 |
+
"step": 15990
|
| 2889 |
+
},
|
| 2890 |
+
{
|
| 2891 |
+
"epoch": 3.3582652419861723,
|
| 2892 |
+
"grad_norm": 0.9805575609207153,
|
| 2893 |
+
"learning_rate": 6.517712656160313e-05,
|
| 2894 |
+
"loss": 0.2639,
|
| 2895 |
+
"step": 16029
|
| 2896 |
+
},
|
| 2897 |
+
{
|
| 2898 |
+
"epoch": 3.366436203645506,
|
| 2899 |
+
"grad_norm": 1.1635912656784058,
|
| 2900 |
+
"learning_rate": 6.501944720219508e-05,
|
| 2901 |
+
"loss": 0.2805,
|
| 2902 |
+
"step": 16068
|
| 2903 |
+
},
|
| 2904 |
+
{
|
| 2905 |
+
"epoch": 3.3746071653048397,
|
| 2906 |
+
"grad_norm": 1.2201091051101685,
|
| 2907 |
+
"learning_rate": 6.486160348607023e-05,
|
| 2908 |
+
"loss": 0.2581,
|
| 2909 |
+
"step": 16107
|
| 2910 |
+
},
|
| 2911 |
+
{
|
| 2912 |
+
"epoch": 3.3827781269641735,
|
| 2913 |
+
"grad_norm": 0.8909711837768555,
|
| 2914 |
+
"learning_rate": 6.470359714050083e-05,
|
| 2915 |
+
"loss": 0.2699,
|
| 2916 |
+
"step": 16146
|
| 2917 |
+
},
|
| 2918 |
+
{
|
| 2919 |
+
"epoch": 3.390949088623507,
|
| 2920 |
+
"grad_norm": 1.3544241189956665,
|
| 2921 |
+
"learning_rate": 6.454542989453882e-05,
|
| 2922 |
+
"loss": 0.2694,
|
| 2923 |
+
"step": 16185
|
| 2924 |
+
},
|
| 2925 |
+
{
|
| 2926 |
+
"epoch": 3.399120050282841,
|
| 2927 |
+
"grad_norm": 0.7139955163002014,
|
| 2928 |
+
"learning_rate": 6.438710347899687e-05,
|
| 2929 |
+
"loss": 0.2752,
|
| 2930 |
+
"step": 16224
|
| 2931 |
+
},
|
| 2932 |
+
{
|
| 2933 |
+
"epoch": 3.4072910119421747,
|
| 2934 |
+
"grad_norm": 0.9686264991760254,
|
| 2935 |
+
"learning_rate": 6.422861962642938e-05,
|
| 2936 |
+
"loss": 0.2614,
|
| 2937 |
+
"step": 16263
|
| 2938 |
+
},
|
| 2939 |
+
{
|
| 2940 |
+
"epoch": 3.4154619736015084,
|
| 2941 |
+
"grad_norm": 0.9705599546432495,
|
| 2942 |
+
"learning_rate": 6.406998007111365e-05,
|
| 2943 |
+
"loss": 0.2515,
|
| 2944 |
+
"step": 16302
|
| 2945 |
+
},
|
| 2946 |
+
{
|
| 2947 |
+
"epoch": 3.423632935260842,
|
| 2948 |
+
"grad_norm": 0.5927676558494568,
|
| 2949 |
+
"learning_rate": 6.391118654903074e-05,
|
| 2950 |
+
"loss": 0.2638,
|
| 2951 |
+
"step": 16341
|
| 2952 |
+
},
|
| 2953 |
+
{
|
| 2954 |
+
"epoch": 3.431803896920176,
|
| 2955 |
+
"grad_norm": 1.0339412689208984,
|
| 2956 |
+
"learning_rate": 6.375224079784662e-05,
|
| 2957 |
+
"loss": 0.281,
|
| 2958 |
+
"step": 16380
|
| 2959 |
+
},
|
| 2960 |
+
{
|
| 2961 |
+
"epoch": 3.4399748585795096,
|
| 2962 |
+
"grad_norm": 1.2015362977981567,
|
| 2963 |
+
"learning_rate": 6.359314455689308e-05,
|
| 2964 |
+
"loss": 0.2517,
|
| 2965 |
+
"step": 16419
|
| 2966 |
+
},
|
| 2967 |
+
{
|
| 2968 |
+
"epoch": 3.4481458202388433,
|
| 2969 |
+
"grad_norm": 0.8283564448356628,
|
| 2970 |
+
"learning_rate": 6.343389956714866e-05,
|
| 2971 |
+
"loss": 0.2675,
|
| 2972 |
+
"step": 16458
|
| 2973 |
+
},
|
| 2974 |
+
{
|
| 2975 |
+
"epoch": 3.4563167818981775,
|
| 2976 |
+
"grad_norm": 0.9697973132133484,
|
| 2977 |
+
"learning_rate": 6.32745075712197e-05,
|
| 2978 |
+
"loss": 0.2725,
|
| 2979 |
+
"step": 16497
|
| 2980 |
+
},
|
| 2981 |
+
{
|
| 2982 |
+
"epoch": 3.4644877435575108,
|
| 2983 |
+
"grad_norm": 0.8286094665527344,
|
| 2984 |
+
"learning_rate": 6.311497031332122e-05,
|
| 2985 |
+
"loss": 0.2689,
|
| 2986 |
+
"step": 16536
|
| 2987 |
+
},
|
| 2988 |
+
{
|
| 2989 |
+
"epoch": 3.472658705216845,
|
| 2990 |
+
"grad_norm": 0.9562814235687256,
|
| 2991 |
+
"learning_rate": 6.29552895392578e-05,
|
| 2992 |
+
"loss": 0.2619,
|
| 2993 |
+
"step": 16575
|
| 2994 |
+
},
|
| 2995 |
+
{
|
| 2996 |
+
"epoch": 3.4808296668761787,
|
| 2997 |
+
"grad_norm": 0.840769350528717,
|
| 2998 |
+
"learning_rate": 6.279546699640452e-05,
|
| 2999 |
+
"loss": 0.2574,
|
| 3000 |
+
"step": 16614
|
| 3001 |
+
},
|
| 3002 |
+
{
|
| 3003 |
+
"epoch": 3.4890006285355124,
|
| 3004 |
+
"grad_norm": 0.820468008518219,
|
| 3005 |
+
"learning_rate": 6.263550443368783e-05,
|
| 3006 |
+
"loss": 0.2482,
|
| 3007 |
+
"step": 16653
|
| 3008 |
+
},
|
| 3009 |
+
{
|
| 3010 |
+
"epoch": 3.497171590194846,
|
| 3011 |
+
"grad_norm": 0.8476835489273071,
|
| 3012 |
+
"learning_rate": 6.247540360156638e-05,
|
| 3013 |
+
"loss": 0.2823,
|
| 3014 |
+
"step": 16692
|
| 3015 |
+
},
|
| 3016 |
+
{
|
| 3017 |
+
"epoch": 3.50534255185418,
|
| 3018 |
+
"grad_norm": 1.0869783163070679,
|
| 3019 |
+
"learning_rate": 6.231516625201196e-05,
|
| 3020 |
+
"loss": 0.266,
|
| 3021 |
+
"step": 16731
|
| 3022 |
+
},
|
| 3023 |
+
{
|
| 3024 |
+
"epoch": 3.5135135135135136,
|
| 3025 |
+
"grad_norm": 1.0051486492156982,
|
| 3026 |
+
"learning_rate": 6.215479413849019e-05,
|
| 3027 |
+
"loss": 0.2489,
|
| 3028 |
+
"step": 16770
|
| 3029 |
+
},
|
| 3030 |
+
{
|
| 3031 |
+
"epoch": 3.5216844751728473,
|
| 3032 |
+
"grad_norm": 1.0071632862091064,
|
| 3033 |
+
"learning_rate": 6.199428901594142e-05,
|
| 3034 |
+
"loss": 0.2776,
|
| 3035 |
+
"step": 16809
|
| 3036 |
+
},
|
| 3037 |
+
{
|
| 3038 |
+
"epoch": 3.529855436832181,
|
| 3039 |
+
"grad_norm": 1.0343513488769531,
|
| 3040 |
+
"learning_rate": 6.183365264076152e-05,
|
| 3041 |
+
"loss": 0.2811,
|
| 3042 |
+
"step": 16848
|
| 3043 |
+
},
|
| 3044 |
+
{
|
| 3045 |
+
"epoch": 3.538026398491515,
|
| 3046 |
+
"grad_norm": 1.3418666124343872,
|
| 3047 |
+
"learning_rate": 6.167288677078266e-05,
|
| 3048 |
+
"loss": 0.2581,
|
| 3049 |
+
"step": 16887
|
| 3050 |
+
},
|
| 3051 |
+
{
|
| 3052 |
+
"epoch": 3.5461973601508485,
|
| 3053 |
+
"grad_norm": 1.228233814239502,
|
| 3054 |
+
"learning_rate": 6.151199316525403e-05,
|
| 3055 |
+
"loss": 0.3023,
|
| 3056 |
+
"step": 16926
|
| 3057 |
+
},
|
| 3058 |
+
{
|
| 3059 |
+
"epoch": 3.5543683218101823,
|
| 3060 |
+
"grad_norm": 1.132449746131897,
|
| 3061 |
+
"learning_rate": 6.135097358482265e-05,
|
| 3062 |
+
"loss": 0.2763,
|
| 3063 |
+
"step": 16965
|
| 3064 |
+
},
|
| 3065 |
+
{
|
| 3066 |
+
"epoch": 3.562539283469516,
|
| 3067 |
+
"grad_norm": 0.8154187202453613,
|
| 3068 |
+
"learning_rate": 6.118982979151405e-05,
|
| 3069 |
+
"loss": 0.2607,
|
| 3070 |
+
"step": 17004
|
| 3071 |
+
},
|
| 3072 |
+
{
|
| 3073 |
+
"epoch": 3.5707102451288497,
|
| 3074 |
+
"grad_norm": 0.7642055749893188,
|
| 3075 |
+
"learning_rate": 6.102856354871304e-05,
|
| 3076 |
+
"loss": 0.2704,
|
| 3077 |
+
"step": 17043
|
| 3078 |
+
},
|
| 3079 |
+
{
|
| 3080 |
+
"epoch": 3.5788812067881834,
|
| 3081 |
+
"grad_norm": 0.7441285252571106,
|
| 3082 |
+
"learning_rate": 6.086717662114434e-05,
|
| 3083 |
+
"loss": 0.2704,
|
| 3084 |
+
"step": 17082
|
| 3085 |
+
},
|
| 3086 |
+
{
|
| 3087 |
+
"epoch": 3.587052168447517,
|
| 3088 |
+
"grad_norm": 1.1328179836273193,
|
| 3089 |
+
"learning_rate": 6.0705670774853375e-05,
|
| 3090 |
+
"loss": 0.2734,
|
| 3091 |
+
"step": 17121
|
| 3092 |
+
},
|
| 3093 |
+
{
|
| 3094 |
+
"epoch": 3.595223130106851,
|
| 3095 |
+
"grad_norm": 1.2895148992538452,
|
| 3096 |
+
"learning_rate": 6.054404777718683e-05,
|
| 3097 |
+
"loss": 0.2534,
|
| 3098 |
+
"step": 17160
|
| 3099 |
+
},
|
| 3100 |
+
{
|
| 3101 |
+
"epoch": 3.6033940917661846,
|
| 3102 |
+
"grad_norm": 1.1969038248062134,
|
| 3103 |
+
"learning_rate": 6.0382309396773405e-05,
|
| 3104 |
+
"loss": 0.288,
|
| 3105 |
+
"step": 17199
|
| 3106 |
+
},
|
| 3107 |
+
{
|
| 3108 |
+
"epoch": 3.611565053425519,
|
| 3109 |
+
"grad_norm": 1.0326099395751953,
|
| 3110 |
+
"learning_rate": 6.022045740350444e-05,
|
| 3111 |
+
"loss": 0.273,
|
| 3112 |
+
"step": 17238
|
| 3113 |
+
},
|
| 3114 |
+
{
|
| 3115 |
+
"epoch": 3.619736015084852,
|
| 3116 |
+
"grad_norm": 0.842157244682312,
|
| 3117 |
+
"learning_rate": 6.005849356851448e-05,
|
| 3118 |
+
"loss": 0.2757,
|
| 3119 |
+
"step": 17277
|
| 3120 |
+
},
|
| 3121 |
+
{
|
| 3122 |
+
"epoch": 3.6279069767441863,
|
| 3123 |
+
"grad_norm": 1.004172444343567,
|
| 3124 |
+
"learning_rate": 5.989641966416201e-05,
|
| 3125 |
+
"loss": 0.2719,
|
| 3126 |
+
"step": 17316
|
| 3127 |
+
},
|
| 3128 |
+
{
|
| 3129 |
+
"epoch": 3.6360779384035196,
|
| 3130 |
+
"grad_norm": 1.0707955360412598,
|
| 3131 |
+
"learning_rate": 5.973423746400991e-05,
|
| 3132 |
+
"loss": 0.2785,
|
| 3133 |
+
"step": 17355
|
| 3134 |
+
},
|
| 3135 |
+
{
|
| 3136 |
+
"epoch": 3.6442489000628537,
|
| 3137 |
+
"grad_norm": 0.9679854512214661,
|
| 3138 |
+
"learning_rate": 5.957194874280623e-05,
|
| 3139 |
+
"loss": 0.2628,
|
| 3140 |
+
"step": 17394
|
| 3141 |
+
},
|
| 3142 |
+
{
|
| 3143 |
+
"epoch": 3.6524198617221875,
|
| 3144 |
+
"grad_norm": 1.2920995950698853,
|
| 3145 |
+
"learning_rate": 5.940955527646461e-05,
|
| 3146 |
+
"loss": 0.2803,
|
| 3147 |
+
"step": 17433
|
| 3148 |
+
},
|
| 3149 |
+
{
|
| 3150 |
+
"epoch": 3.660590823381521,
|
| 3151 |
+
"grad_norm": 1.1548652648925781,
|
| 3152 |
+
"learning_rate": 5.924705884204491e-05,
|
| 3153 |
+
"loss": 0.2827,
|
| 3154 |
+
"step": 17472
|
| 3155 |
+
},
|
| 3156 |
+
{
|
| 3157 |
+
"epoch": 3.668761785040855,
|
| 3158 |
+
"grad_norm": 1.4897462129592896,
|
| 3159 |
+
"learning_rate": 5.908446121773381e-05,
|
| 3160 |
+
"loss": 0.2883,
|
| 3161 |
+
"step": 17511
|
| 3162 |
+
},
|
| 3163 |
+
{
|
| 3164 |
+
"epoch": 3.6769327467001887,
|
| 3165 |
+
"grad_norm": 1.005393147468567,
|
| 3166 |
+
"learning_rate": 5.892176418282522e-05,
|
| 3167 |
+
"loss": 0.2635,
|
| 3168 |
+
"step": 17550
|
| 3169 |
+
},
|
| 3170 |
+
{
|
| 3171 |
+
"epoch": 3.6851037083595224,
|
| 3172 |
+
"grad_norm": 1.1993404626846313,
|
| 3173 |
+
"learning_rate": 5.8758969517701e-05,
|
| 3174 |
+
"loss": 0.2786,
|
| 3175 |
+
"step": 17589
|
| 3176 |
+
},
|
| 3177 |
+
{
|
| 3178 |
+
"epoch": 3.693274670018856,
|
| 3179 |
+
"grad_norm": 1.0545886754989624,
|
| 3180 |
+
"learning_rate": 5.859607900381129e-05,
|
| 3181 |
+
"loss": 0.2567,
|
| 3182 |
+
"step": 17628
|
| 3183 |
+
},
|
| 3184 |
+
{
|
| 3185 |
+
"epoch": 3.70144563167819,
|
| 3186 |
+
"grad_norm": 0.632892906665802,
|
| 3187 |
+
"learning_rate": 5.84330944236551e-05,
|
| 3188 |
+
"loss": 0.2755,
|
| 3189 |
+
"step": 17667
|
| 3190 |
+
},
|
| 3191 |
+
{
|
| 3192 |
+
"epoch": 3.7096165933375236,
|
| 3193 |
+
"grad_norm": 1.0235896110534668,
|
| 3194 |
+
"learning_rate": 5.8270017560760845e-05,
|
| 3195 |
+
"loss": 0.2709,
|
| 3196 |
+
"step": 17706
|
| 3197 |
+
},
|
| 3198 |
+
{
|
| 3199 |
+
"epoch": 3.7177875549968573,
|
| 3200 |
+
"grad_norm": 1.0493903160095215,
|
| 3201 |
+
"learning_rate": 5.8106850199666754e-05,
|
| 3202 |
+
"loss": 0.2707,
|
| 3203 |
+
"step": 17745
|
| 3204 |
+
},
|
| 3205 |
+
{
|
| 3206 |
+
"epoch": 3.725958516656191,
|
| 3207 |
+
"grad_norm": 1.1471383571624756,
|
| 3208 |
+
"learning_rate": 5.794359412590136e-05,
|
| 3209 |
+
"loss": 0.257,
|
| 3210 |
+
"step": 17784
|
| 3211 |
+
},
|
| 3212 |
+
{
|
| 3213 |
+
"epoch": 3.7341294783155248,
|
| 3214 |
+
"grad_norm": 1.0675766468048096,
|
| 3215 |
+
"learning_rate": 5.778025112596401e-05,
|
| 3216 |
+
"loss": 0.2665,
|
| 3217 |
+
"step": 17823
|
| 3218 |
+
},
|
| 3219 |
+
{
|
| 3220 |
+
"epoch": 3.7423004399748585,
|
| 3221 |
+
"grad_norm": 1.0171725749969482,
|
| 3222 |
+
"learning_rate": 5.761682298730524e-05,
|
| 3223 |
+
"loss": 0.27,
|
| 3224 |
+
"step": 17862
|
| 3225 |
+
},
|
| 3226 |
+
{
|
| 3227 |
+
"epoch": 3.7504714016341922,
|
| 3228 |
+
"grad_norm": 1.209671139717102,
|
| 3229 |
+
"learning_rate": 5.745331149830729e-05,
|
| 3230 |
+
"loss": 0.2723,
|
| 3231 |
+
"step": 17901
|
| 3232 |
+
},
|
| 3233 |
+
{
|
| 3234 |
+
"epoch": 3.758642363293526,
|
| 3235 |
+
"grad_norm": 1.1893844604492188,
|
| 3236 |
+
"learning_rate": 5.728971844826445e-05,
|
| 3237 |
+
"loss": 0.2835,
|
| 3238 |
+
"step": 17940
|
| 3239 |
+
},
|
| 3240 |
+
{
|
| 3241 |
+
"epoch": 3.7668133249528597,
|
| 3242 |
+
"grad_norm": 1.2675912380218506,
|
| 3243 |
+
"learning_rate": 5.7126045627363556e-05,
|
| 3244 |
+
"loss": 0.2979,
|
| 3245 |
+
"step": 17979
|
| 3246 |
+
},
|
| 3247 |
+
{
|
| 3248 |
+
"epoch": 3.7749842866121934,
|
| 3249 |
+
"grad_norm": 1.090598464012146,
|
| 3250 |
+
"learning_rate": 5.6962294826664385e-05,
|
| 3251 |
+
"loss": 0.2748,
|
| 3252 |
+
"step": 18018
|
| 3253 |
+
},
|
| 3254 |
+
{
|
| 3255 |
+
"epoch": 3.7831552482715276,
|
| 3256 |
+
"grad_norm": 1.0700677633285522,
|
| 3257 |
+
"learning_rate": 5.679846783808e-05,
|
| 3258 |
+
"loss": 0.3043,
|
| 3259 |
+
"step": 18057
|
| 3260 |
+
},
|
| 3261 |
+
{
|
| 3262 |
+
"epoch": 3.791326209930861,
|
| 3263 |
+
"grad_norm": 1.0571792125701904,
|
| 3264 |
+
"learning_rate": 5.6634566454357196e-05,
|
| 3265 |
+
"loss": 0.2589,
|
| 3266 |
+
"step": 18096
|
| 3267 |
+
},
|
| 3268 |
+
{
|
| 3269 |
+
"epoch": 3.799497171590195,
|
| 3270 |
+
"grad_norm": 0.8858397006988525,
|
| 3271 |
+
"learning_rate": 5.6470592469056915e-05,
|
| 3272 |
+
"loss": 0.2976,
|
| 3273 |
+
"step": 18135
|
| 3274 |
+
},
|
| 3275 |
+
{
|
| 3276 |
+
"epoch": 3.8076681332495284,
|
| 3277 |
+
"grad_norm": 1.1942354440689087,
|
| 3278 |
+
"learning_rate": 5.6306547676534514e-05,
|
| 3279 |
+
"loss": 0.2742,
|
| 3280 |
+
"step": 18174
|
| 3281 |
+
},
|
| 3282 |
+
{
|
| 3283 |
+
"epoch": 3.8158390949088625,
|
| 3284 |
+
"grad_norm": 1.4405794143676758,
|
| 3285 |
+
"learning_rate": 5.614243387192022e-05,
|
| 3286 |
+
"loss": 0.3013,
|
| 3287 |
+
"step": 18213
|
| 3288 |
+
},
|
| 3289 |
+
{
|
| 3290 |
+
"epoch": 3.8240100565681963,
|
| 3291 |
+
"grad_norm": 0.9287608861923218,
|
| 3292 |
+
"learning_rate": 5.5978252851099425e-05,
|
| 3293 |
+
"loss": 0.2542,
|
| 3294 |
+
"step": 18252
|
| 3295 |
+
},
|
| 3296 |
+
{
|
| 3297 |
+
"epoch": 3.83218101822753,
|
| 3298 |
+
"grad_norm": 1.217387080192566,
|
| 3299 |
+
"learning_rate": 5.581400641069309e-05,
|
| 3300 |
+
"loss": 0.2768,
|
| 3301 |
+
"step": 18291
|
| 3302 |
+
},
|
| 3303 |
+
{
|
| 3304 |
+
"epoch": 3.8403519798868637,
|
| 3305 |
+
"grad_norm": 1.1811288595199585,
|
| 3306 |
+
"learning_rate": 5.564969634803806e-05,
|
| 3307 |
+
"loss": 0.263,
|
| 3308 |
+
"step": 18330
|
| 3309 |
+
},
|
| 3310 |
+
{
|
| 3311 |
+
"epoch": 3.8485229415461975,
|
| 3312 |
+
"grad_norm": 0.9432389140129089,
|
| 3313 |
+
"learning_rate": 5.548532446116737e-05,
|
| 3314 |
+
"loss": 0.2612,
|
| 3315 |
+
"step": 18369
|
| 3316 |
+
},
|
| 3317 |
+
{
|
| 3318 |
+
"epoch": 3.856693903205531,
|
| 3319 |
+
"grad_norm": 1.010432243347168,
|
| 3320 |
+
"learning_rate": 5.532089254879061e-05,
|
| 3321 |
+
"loss": 0.2505,
|
| 3322 |
+
"step": 18408
|
| 3323 |
+
},
|
| 3324 |
+
{
|
| 3325 |
+
"epoch": 3.864864864864865,
|
| 3326 |
+
"grad_norm": 1.1816331148147583,
|
| 3327 |
+
"learning_rate": 5.515640241027423e-05,
|
| 3328 |
+
"loss": 0.282,
|
| 3329 |
+
"step": 18447
|
| 3330 |
+
},
|
| 3331 |
+
{
|
| 3332 |
+
"epoch": 3.8730358265241986,
|
| 3333 |
+
"grad_norm": 1.011232614517212,
|
| 3334 |
+
"learning_rate": 5.499185584562183e-05,
|
| 3335 |
+
"loss": 0.2894,
|
| 3336 |
+
"step": 18486
|
| 3337 |
+
},
|
| 3338 |
+
{
|
| 3339 |
+
"epoch": 3.8812067881835324,
|
| 3340 |
+
"grad_norm": 0.7370874881744385,
|
| 3341 |
+
"learning_rate": 5.482725465545449e-05,
|
| 3342 |
+
"loss": 0.2692,
|
| 3343 |
+
"step": 18525
|
| 3344 |
+
},
|
| 3345 |
+
{
|
| 3346 |
+
"epoch": 3.889377749842866,
|
| 3347 |
+
"grad_norm": 0.831798791885376,
|
| 3348 |
+
"learning_rate": 5.4662600640991025e-05,
|
| 3349 |
+
"loss": 0.2984,
|
| 3350 |
+
"step": 18564
|
| 3351 |
+
},
|
| 3352 |
+
{
|
| 3353 |
+
"epoch": 3.8975487115022,
|
| 3354 |
+
"grad_norm": 0.7684634923934937,
|
| 3355 |
+
"learning_rate": 5.4497895604028334e-05,
|
| 3356 |
+
"loss": 0.282,
|
| 3357 |
+
"step": 18603
|
| 3358 |
+
},
|
| 3359 |
+
{
|
| 3360 |
+
"epoch": 3.9057196731615336,
|
| 3361 |
+
"grad_norm": 1.2753115892410278,
|
| 3362 |
+
"learning_rate": 5.4333141346921644e-05,
|
| 3363 |
+
"loss": 0.2692,
|
| 3364 |
+
"step": 18642
|
| 3365 |
+
},
|
| 3366 |
+
{
|
| 3367 |
+
"epoch": 3.9138906348208673,
|
| 3368 |
+
"grad_norm": 0.9664742350578308,
|
| 3369 |
+
"learning_rate": 5.4168339672564795e-05,
|
| 3370 |
+
"loss": 0.2683,
|
| 3371 |
+
"step": 18681
|
| 3372 |
+
},
|
| 3373 |
+
{
|
| 3374 |
+
"epoch": 3.922061596480201,
|
| 3375 |
+
"grad_norm": 1.0317939519882202,
|
| 3376 |
+
"learning_rate": 5.4003492384370504e-05,
|
| 3377 |
+
"loss": 0.2635,
|
| 3378 |
+
"step": 18720
|
| 3379 |
+
},
|
| 3380 |
+
{
|
| 3381 |
+
"epoch": 3.9302325581395348,
|
| 3382 |
+
"grad_norm": 0.88239985704422,
|
| 3383 |
+
"learning_rate": 5.383860128625062e-05,
|
| 3384 |
+
"loss": 0.2631,
|
| 3385 |
+
"step": 18759
|
| 3386 |
+
},
|
| 3387 |
+
{
|
| 3388 |
+
"epoch": 3.9384035197988685,
|
| 3389 |
+
"grad_norm": 1.137979507446289,
|
| 3390 |
+
"learning_rate": 5.367366818259646e-05,
|
| 3391 |
+
"loss": 0.2734,
|
| 3392 |
+
"step": 18798
|
| 3393 |
+
},
|
| 3394 |
+
{
|
| 3395 |
+
"epoch": 3.946574481458202,
|
| 3396 |
+
"grad_norm": 1.0174254179000854,
|
| 3397 |
+
"learning_rate": 5.3508694878258934e-05,
|
| 3398 |
+
"loss": 0.278,
|
| 3399 |
+
"step": 18837
|
| 3400 |
+
},
|
| 3401 |
+
{
|
| 3402 |
+
"epoch": 3.9547454431175364,
|
| 3403 |
+
"grad_norm": 0.9561147093772888,
|
| 3404 |
+
"learning_rate": 5.334368317852889e-05,
|
| 3405 |
+
"loss": 0.2552,
|
| 3406 |
+
"step": 18876
|
| 3407 |
+
},
|
| 3408 |
+
{
|
| 3409 |
+
"epoch": 3.9629164047768697,
|
| 3410 |
+
"grad_norm": 1.178209662437439,
|
| 3411 |
+
"learning_rate": 5.317863488911737e-05,
|
| 3412 |
+
"loss": 0.2615,
|
| 3413 |
+
"step": 18915
|
| 3414 |
+
},
|
| 3415 |
+
{
|
| 3416 |
+
"epoch": 3.971087366436204,
|
| 3417 |
+
"grad_norm": 1.1684329509735107,
|
| 3418 |
+
"learning_rate": 5.3013551816135756e-05,
|
| 3419 |
+
"loss": 0.283,
|
| 3420 |
+
"step": 18954
|
| 3421 |
+
},
|
| 3422 |
+
{
|
| 3423 |
+
"epoch": 3.979258328095537,
|
| 3424 |
+
"grad_norm": 0.7574102878570557,
|
| 3425 |
+
"learning_rate": 5.2848435766076096e-05,
|
| 3426 |
+
"loss": 0.3018,
|
| 3427 |
+
"step": 18993
|
| 3428 |
+
},
|
| 3429 |
+
{
|
| 3430 |
+
"epoch": 3.9874292897548713,
|
| 3431 |
+
"grad_norm": 1.389844298362732,
|
| 3432 |
+
"learning_rate": 5.268328854579132e-05,
|
| 3433 |
+
"loss": 0.2737,
|
| 3434 |
+
"step": 19032
|
| 3435 |
+
},
|
| 3436 |
+
{
|
| 3437 |
+
"epoch": 3.995600251414205,
|
| 3438 |
+
"grad_norm": 0.8808802366256714,
|
| 3439 |
+
"learning_rate": 5.251811196247541e-05,
|
| 3440 |
+
"loss": 0.2656,
|
| 3441 |
+
"step": 19071
|
| 3442 |
+
},
|
| 3443 |
+
{
|
| 3444 |
+
"epoch": 4.003771213073539,
|
| 3445 |
+
"grad_norm": 1.1782208681106567,
|
| 3446 |
+
"learning_rate": 5.2352907823643715e-05,
|
| 3447 |
+
"loss": 0.2257,
|
| 3448 |
+
"step": 19110
|
| 3449 |
+
},
|
| 3450 |
+
{
|
| 3451 |
+
"epoch": 4.011942174732872,
|
| 3452 |
+
"grad_norm": 0.7572002410888672,
|
| 3453 |
+
"learning_rate": 5.218767793711306e-05,
|
| 3454 |
+
"loss": 0.1908,
|
| 3455 |
+
"step": 19149
|
| 3456 |
+
},
|
| 3457 |
+
{
|
| 3458 |
+
"epoch": 4.020113136392206,
|
| 3459 |
+
"grad_norm": 1.2401790618896484,
|
| 3460 |
+
"learning_rate": 5.202242411098206e-05,
|
| 3461 |
+
"loss": 0.173,
|
| 3462 |
+
"step": 19188
|
| 3463 |
+
},
|
| 3464 |
+
{
|
| 3465 |
+
"epoch": 4.0282840980515395,
|
| 3466 |
+
"grad_norm": 1.61008882522583,
|
| 3467 |
+
"learning_rate": 5.1857148153611336e-05,
|
| 3468 |
+
"loss": 0.1997,
|
| 3469 |
+
"step": 19227
|
| 3470 |
+
},
|
| 3471 |
+
{
|
| 3472 |
+
"epoch": 4.036455059710874,
|
| 3473 |
+
"grad_norm": 1.042442798614502,
|
| 3474 |
+
"learning_rate": 5.169185187360362e-05,
|
| 3475 |
+
"loss": 0.1846,
|
| 3476 |
+
"step": 19266
|
| 3477 |
+
},
|
| 3478 |
+
{
|
| 3479 |
+
"epoch": 4.044626021370207,
|
| 3480 |
+
"grad_norm": 1.8919810056686401,
|
| 3481 |
+
"learning_rate": 5.1526537079784076e-05,
|
| 3482 |
+
"loss": 0.1755,
|
| 3483 |
+
"step": 19305
|
| 3484 |
+
},
|
| 3485 |
+
{
|
| 3486 |
+
"epoch": 4.052796983029541,
|
| 3487 |
+
"grad_norm": 1.427526593208313,
|
| 3488 |
+
"learning_rate": 5.136120558118044e-05,
|
| 3489 |
+
"loss": 0.1782,
|
| 3490 |
+
"step": 19344
|
| 3491 |
+
},
|
| 3492 |
+
{
|
| 3493 |
+
"epoch": 4.060967944688875,
|
| 3494 |
+
"grad_norm": 0.9603130221366882,
|
| 3495 |
+
"learning_rate": 5.119585918700327e-05,
|
| 3496 |
+
"loss": 0.1934,
|
| 3497 |
+
"step": 19383
|
| 3498 |
+
},
|
| 3499 |
+
{
|
| 3500 |
+
"epoch": 4.069138906348209,
|
| 3501 |
+
"grad_norm": 1.2158547639846802,
|
| 3502 |
+
"learning_rate": 5.1030499706626126e-05,
|
| 3503 |
+
"loss": 0.1834,
|
| 3504 |
+
"step": 19422
|
| 3505 |
+
},
|
| 3506 |
+
{
|
| 3507 |
+
"epoch": 4.077309868007543,
|
| 3508 |
+
"grad_norm": 1.2463704347610474,
|
| 3509 |
+
"learning_rate": 5.0865128949565735e-05,
|
| 3510 |
+
"loss": 0.1956,
|
| 3511 |
+
"step": 19461
|
| 3512 |
+
},
|
| 3513 |
+
{
|
| 3514 |
+
"epoch": 4.085480829666876,
|
| 3515 |
+
"grad_norm": 0.9006099700927734,
|
| 3516 |
+
"learning_rate": 5.069974872546227e-05,
|
| 3517 |
+
"loss": 0.1949,
|
| 3518 |
+
"step": 19500
|
| 3519 |
+
},
|
| 3520 |
+
{
|
| 3521 |
+
"epoch": 4.09365179132621,
|
| 3522 |
+
"grad_norm": 1.2113624811172485,
|
| 3523 |
+
"learning_rate": 5.053436084405946e-05,
|
| 3524 |
+
"loss": 0.1901,
|
| 3525 |
+
"step": 19539
|
| 3526 |
+
},
|
| 3527 |
+
{
|
| 3528 |
+
"epoch": 4.1018227529855436,
|
| 3529 |
+
"grad_norm": 1.0677685737609863,
|
| 3530 |
+
"learning_rate": 5.036896711518485e-05,
|
| 3531 |
+
"loss": 0.1904,
|
| 3532 |
+
"step": 19578
|
| 3533 |
+
},
|
| 3534 |
+
{
|
| 3535 |
+
"epoch": 4.109993714644878,
|
| 3536 |
+
"grad_norm": 1.0412025451660156,
|
| 3537 |
+
"learning_rate": 5.020356934872997e-05,
|
| 3538 |
+
"loss": 0.1894,
|
| 3539 |
+
"step": 19617
|
| 3540 |
+
},
|
| 3541 |
+
{
|
| 3542 |
+
"epoch": 4.118164676304211,
|
| 3543 |
+
"grad_norm": 1.1890144348144531,
|
| 3544 |
+
"learning_rate": 5.0038169354630537e-05,
|
| 3545 |
+
"loss": 0.1765,
|
| 3546 |
+
"step": 19656
|
| 3547 |
+
},
|
| 3548 |
+
{
|
| 3549 |
+
"epoch": 4.126335637963545,
|
| 3550 |
+
"grad_norm": 1.4251190423965454,
|
| 3551 |
+
"learning_rate": 4.9872768942846645e-05,
|
| 3552 |
+
"loss": 0.1896,
|
| 3553 |
+
"step": 19695
|
| 3554 |
+
},
|
| 3555 |
+
{
|
| 3556 |
+
"epoch": 4.1345065996228785,
|
| 3557 |
+
"grad_norm": 1.3054598569869995,
|
| 3558 |
+
"learning_rate": 4.970736992334294e-05,
|
| 3559 |
+
"loss": 0.1956,
|
| 3560 |
+
"step": 19734
|
| 3561 |
+
},
|
| 3562 |
+
{
|
| 3563 |
+
"epoch": 4.142677561282213,
|
| 3564 |
+
"grad_norm": 1.2113808393478394,
|
| 3565 |
+
"learning_rate": 4.9541974106068844e-05,
|
| 3566 |
+
"loss": 0.1876,
|
| 3567 |
+
"step": 19773
|
| 3568 |
+
},
|
| 3569 |
+
{
|
| 3570 |
+
"epoch": 4.150848522941546,
|
| 3571 |
+
"grad_norm": 1.1403577327728271,
|
| 3572 |
+
"learning_rate": 4.9376583300938756e-05,
|
| 3573 |
+
"loss": 0.1958,
|
| 3574 |
+
"step": 19812
|
| 3575 |
+
},
|
| 3576 |
+
{
|
| 3577 |
+
"epoch": 4.15901948460088,
|
| 3578 |
+
"grad_norm": 1.28948974609375,
|
| 3579 |
+
"learning_rate": 4.921119931781218e-05,
|
| 3580 |
+
"loss": 0.1856,
|
| 3581 |
+
"step": 19851
|
| 3582 |
+
},
|
| 3583 |
+
{
|
| 3584 |
+
"epoch": 4.167190446260213,
|
| 3585 |
+
"grad_norm": 1.168059229850769,
|
| 3586 |
+
"learning_rate": 4.9045823966474046e-05,
|
| 3587 |
+
"loss": 0.1867,
|
| 3588 |
+
"step": 19890
|
| 3589 |
+
},
|
| 3590 |
+
{
|
| 3591 |
+
"epoch": 4.175361407919548,
|
| 3592 |
+
"grad_norm": 0.7937365770339966,
|
| 3593 |
+
"learning_rate": 4.888045905661472e-05,
|
| 3594 |
+
"loss": 0.1846,
|
| 3595 |
+
"step": 19929
|
| 3596 |
+
},
|
| 3597 |
+
{
|
| 3598 |
+
"epoch": 4.183532369578881,
|
| 3599 |
+
"grad_norm": 0.8156687021255493,
|
| 3600 |
+
"learning_rate": 4.871510639781043e-05,
|
| 3601 |
+
"loss": 0.1879,
|
| 3602 |
+
"step": 19968
|
| 3603 |
+
},
|
| 3604 |
+
{
|
| 3605 |
+
"epoch": 4.190236748376283,
|
| 3606 |
+
"eval_accuracy": 0.01002925168722868,
|
| 3607 |
+
"eval_loss": 0.5226494073867798,
|
| 3608 |
+
"eval_runtime": 848.4593,
|
| 3609 |
+
"eval_samples_per_second": 5.64,
|
| 3610 |
+
"eval_steps_per_second": 1.411,
|
| 3611 |
+
"step": 20000
|
| 3612 |
+
}
|
| 3613 |
+
],
|
| 3614 |
+
"logging_steps": 39,
|
| 3615 |
+
"max_steps": 38184,
|
| 3616 |
+
"num_input_tokens_seen": 0,
|
| 3617 |
+
"num_train_epochs": 8,
|
| 3618 |
+
"save_steps": 10000,
|
| 3619 |
+
"stateful_callbacks": {
|
| 3620 |
+
"TrainerControl": {
|
| 3621 |
+
"args": {
|
| 3622 |
+
"should_epoch_stop": false,
|
| 3623 |
+
"should_evaluate": false,
|
| 3624 |
+
"should_log": false,
|
| 3625 |
+
"should_save": true,
|
| 3626 |
+
"should_training_stop": false
|
| 3627 |
+
},
|
| 3628 |
+
"attributes": {}
|
| 3629 |
+
}
|
| 3630 |
+
},
|
| 3631 |
+
"total_flos": 7.632883174699172e+18,
|
| 3632 |
+
"train_batch_size": 2,
|
| 3633 |
+
"trial_name": null,
|
| 3634 |
+
"trial_params": null
|
| 3635 |
+
}
|
checkpoint-20000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:735a552aa1714bfc383df4ff1a42a38cfe32c5c5b2762c0a21b52159da19005f
|
| 3 |
+
size 6904
|
checkpoint-20000/zero_to_fp32.py
ADDED
|
@@ -0,0 +1,760 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python
|
| 2 |
+
|
| 3 |
+
# Copyright (c) Microsoft Corporation.
|
| 4 |
+
# SPDX-License-Identifier: Apache-2.0
|
| 5 |
+
|
| 6 |
+
# DeepSpeed Team
|
| 7 |
+
|
| 8 |
+
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
| 9 |
+
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
| 10 |
+
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
| 11 |
+
# application.
|
| 12 |
+
#
|
| 13 |
+
# example:
|
| 14 |
+
# python zero_to_fp32.py . output_dir/
|
| 15 |
+
# or
|
| 16 |
+
# python zero_to_fp32.py . output_dir/ --safe_serialization
|
| 17 |
+
|
| 18 |
+
import argparse
|
| 19 |
+
import torch
|
| 20 |
+
import glob
|
| 21 |
+
import math
|
| 22 |
+
import os
|
| 23 |
+
import re
|
| 24 |
+
import gc
|
| 25 |
+
import json
|
| 26 |
+
import numpy as np
|
| 27 |
+
from tqdm import tqdm
|
| 28 |
+
from collections import OrderedDict
|
| 29 |
+
from dataclasses import dataclass
|
| 30 |
+
|
| 31 |
+
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
| 32 |
+
# DeepSpeed data structures it has to be available in the current python environment.
|
| 33 |
+
from deepspeed.utils import logger
|
| 34 |
+
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
| 35 |
+
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
| 36 |
+
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
@dataclass
|
| 40 |
+
class zero_model_state:
|
| 41 |
+
buffers: dict()
|
| 42 |
+
param_shapes: dict()
|
| 43 |
+
shared_params: list
|
| 44 |
+
ds_version: int
|
| 45 |
+
frozen_param_shapes: dict()
|
| 46 |
+
frozen_param_fragments: dict()
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
debug = 0
|
| 50 |
+
|
| 51 |
+
# load to cpu
|
| 52 |
+
device = torch.device('cpu')
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
def atoi(text):
|
| 56 |
+
return int(text) if text.isdigit() else text
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
def natural_keys(text):
|
| 60 |
+
'''
|
| 61 |
+
alist.sort(key=natural_keys) sorts in human order
|
| 62 |
+
http://nedbatchelder.com/blog/200712/human_sorting.html
|
| 63 |
+
(See Toothy's implementation in the comments)
|
| 64 |
+
'''
|
| 65 |
+
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
def get_model_state_file(checkpoint_dir, zero_stage):
|
| 69 |
+
if not os.path.isdir(checkpoint_dir):
|
| 70 |
+
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
| 71 |
+
|
| 72 |
+
# there should be only one file
|
| 73 |
+
if zero_stage <= 2:
|
| 74 |
+
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
| 75 |
+
elif zero_stage == 3:
|
| 76 |
+
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
| 77 |
+
|
| 78 |
+
if not os.path.exists(file):
|
| 79 |
+
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
| 80 |
+
|
| 81 |
+
return file
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
| 85 |
+
# XXX: need to test that this simple glob rule works for multi-node setup too
|
| 86 |
+
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
| 87 |
+
|
| 88 |
+
if len(ckpt_files) == 0:
|
| 89 |
+
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
| 90 |
+
|
| 91 |
+
return ckpt_files
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
def get_optim_files(checkpoint_dir):
|
| 95 |
+
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
def get_model_state_files(checkpoint_dir):
|
| 99 |
+
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
| 100 |
+
|
| 101 |
+
|
| 102 |
+
def parse_model_states(files):
|
| 103 |
+
zero_model_states = []
|
| 104 |
+
for file in files:
|
| 105 |
+
state_dict = torch.load(file, map_location=device, weights_only=False)
|
| 106 |
+
|
| 107 |
+
if BUFFER_NAMES not in state_dict:
|
| 108 |
+
raise ValueError(f"{file} is not a model state checkpoint")
|
| 109 |
+
buffer_names = state_dict[BUFFER_NAMES]
|
| 110 |
+
if debug:
|
| 111 |
+
print("Found buffers:", buffer_names)
|
| 112 |
+
|
| 113 |
+
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
| 114 |
+
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
| 115 |
+
param_shapes = state_dict[PARAM_SHAPES]
|
| 116 |
+
|
| 117 |
+
# collect parameters that are included in param_shapes
|
| 118 |
+
param_names = []
|
| 119 |
+
for s in param_shapes:
|
| 120 |
+
for name in s.keys():
|
| 121 |
+
param_names.append(name)
|
| 122 |
+
|
| 123 |
+
# update with frozen parameters
|
| 124 |
+
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
| 125 |
+
if frozen_param_shapes is not None:
|
| 126 |
+
if debug:
|
| 127 |
+
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
| 128 |
+
param_names += list(frozen_param_shapes.keys())
|
| 129 |
+
|
| 130 |
+
# handle shared params
|
| 131 |
+
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
| 132 |
+
|
| 133 |
+
ds_version = state_dict.get(DS_VERSION, None)
|
| 134 |
+
|
| 135 |
+
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
| 136 |
+
|
| 137 |
+
z_model_state = zero_model_state(buffers=buffers,
|
| 138 |
+
param_shapes=param_shapes,
|
| 139 |
+
shared_params=shared_params,
|
| 140 |
+
ds_version=ds_version,
|
| 141 |
+
frozen_param_shapes=frozen_param_shapes,
|
| 142 |
+
frozen_param_fragments=frozen_param_fragments)
|
| 143 |
+
zero_model_states.append(z_model_state)
|
| 144 |
+
|
| 145 |
+
return zero_model_states
|
| 146 |
+
|
| 147 |
+
|
| 148 |
+
def parse_optim_states(files, ds_checkpoint_dir):
|
| 149 |
+
total_files = len(files)
|
| 150 |
+
state_dicts = []
|
| 151 |
+
for f in tqdm(files, desc='Loading checkpoint shards'):
|
| 152 |
+
state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
|
| 153 |
+
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
| 154 |
+
# and also handle the case where it was already removed by another helper script
|
| 155 |
+
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
| 156 |
+
state_dicts.append(state_dict)
|
| 157 |
+
|
| 158 |
+
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
| 159 |
+
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
| 160 |
+
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
| 161 |
+
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
| 162 |
+
|
| 163 |
+
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
| 164 |
+
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
| 165 |
+
# use the max of the partition_count to get the dp world_size.
|
| 166 |
+
|
| 167 |
+
if type(world_size) is list:
|
| 168 |
+
world_size = max(world_size)
|
| 169 |
+
|
| 170 |
+
if world_size != total_files:
|
| 171 |
+
raise ValueError(
|
| 172 |
+
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
| 173 |
+
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
| 174 |
+
)
|
| 175 |
+
|
| 176 |
+
# the groups are named differently in each stage
|
| 177 |
+
if zero_stage <= 2:
|
| 178 |
+
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
| 179 |
+
elif zero_stage == 3:
|
| 180 |
+
fp32_groups_key = FP32_FLAT_GROUPS
|
| 181 |
+
else:
|
| 182 |
+
raise ValueError(f"unknown zero stage {zero_stage}")
|
| 183 |
+
|
| 184 |
+
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
| 185 |
+
return zero_stage, world_size, fp32_flat_groups
|
| 186 |
+
|
| 187 |
+
|
| 188 |
+
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
| 189 |
+
"""
|
| 190 |
+
Returns fp32 state_dict reconstructed from ds checkpoint
|
| 191 |
+
|
| 192 |
+
Args:
|
| 193 |
+
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
| 194 |
+
|
| 195 |
+
"""
|
| 196 |
+
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
| 197 |
+
|
| 198 |
+
optim_files = get_optim_files(ds_checkpoint_dir)
|
| 199 |
+
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
| 200 |
+
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
| 201 |
+
|
| 202 |
+
model_files = get_model_state_files(ds_checkpoint_dir)
|
| 203 |
+
|
| 204 |
+
zero_model_states = parse_model_states(model_files)
|
| 205 |
+
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
| 206 |
+
|
| 207 |
+
if zero_stage <= 2:
|
| 208 |
+
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 209 |
+
exclude_frozen_parameters)
|
| 210 |
+
elif zero_stage == 3:
|
| 211 |
+
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 212 |
+
exclude_frozen_parameters)
|
| 213 |
+
|
| 214 |
+
|
| 215 |
+
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
| 216 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 217 |
+
return
|
| 218 |
+
|
| 219 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 220 |
+
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
| 221 |
+
|
| 222 |
+
if debug:
|
| 223 |
+
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
| 224 |
+
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 225 |
+
|
| 226 |
+
wanted_params = len(frozen_param_shapes)
|
| 227 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 228 |
+
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
| 229 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 230 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 231 |
+
|
| 232 |
+
total_params = 0
|
| 233 |
+
total_numel = 0
|
| 234 |
+
for name, shape in frozen_param_shapes.items():
|
| 235 |
+
total_params += 1
|
| 236 |
+
unpartitioned_numel = shape.numel()
|
| 237 |
+
total_numel += unpartitioned_numel
|
| 238 |
+
|
| 239 |
+
state_dict[name] = frozen_param_fragments[name]
|
| 240 |
+
|
| 241 |
+
if debug:
|
| 242 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 243 |
+
|
| 244 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 245 |
+
|
| 246 |
+
|
| 247 |
+
def _has_callable(obj, fn):
|
| 248 |
+
attr = getattr(obj, fn, None)
|
| 249 |
+
return callable(attr)
|
| 250 |
+
|
| 251 |
+
|
| 252 |
+
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 253 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 254 |
+
|
| 255 |
+
# Reconstruction protocol:
|
| 256 |
+
#
|
| 257 |
+
# XXX: document this
|
| 258 |
+
|
| 259 |
+
if debug:
|
| 260 |
+
for i in range(world_size):
|
| 261 |
+
for j in range(len(fp32_flat_groups[0])):
|
| 262 |
+
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
| 263 |
+
|
| 264 |
+
# XXX: memory usage doubles here (zero2)
|
| 265 |
+
num_param_groups = len(fp32_flat_groups[0])
|
| 266 |
+
merged_single_partition_of_fp32_groups = []
|
| 267 |
+
for i in range(num_param_groups):
|
| 268 |
+
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
| 269 |
+
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
| 270 |
+
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
| 271 |
+
avail_numel = sum(
|
| 272 |
+
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
| 273 |
+
|
| 274 |
+
if debug:
|
| 275 |
+
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
| 276 |
+
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
| 277 |
+
# not asserting if there is a mismatch due to possible padding
|
| 278 |
+
print(f"Have {avail_numel} numels to process.")
|
| 279 |
+
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
| 280 |
+
|
| 281 |
+
# params
|
| 282 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 283 |
+
# out-of-core computing solution
|
| 284 |
+
total_numel = 0
|
| 285 |
+
total_params = 0
|
| 286 |
+
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
| 287 |
+
offset = 0
|
| 288 |
+
avail_numel = full_single_fp32_vector.numel()
|
| 289 |
+
for name, shape in shapes.items():
|
| 290 |
+
|
| 291 |
+
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
| 292 |
+
total_numel += unpartitioned_numel
|
| 293 |
+
total_params += 1
|
| 294 |
+
|
| 295 |
+
if debug:
|
| 296 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 297 |
+
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
| 298 |
+
offset += unpartitioned_numel
|
| 299 |
+
|
| 300 |
+
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
| 301 |
+
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
| 302 |
+
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
| 303 |
+
# live optimizer object, so we are checking that the numbers are within the right range
|
| 304 |
+
align_to = 2 * world_size
|
| 305 |
+
|
| 306 |
+
def zero2_align(x):
|
| 307 |
+
return align_to * math.ceil(x / align_to)
|
| 308 |
+
|
| 309 |
+
if debug:
|
| 310 |
+
print(f"original offset={offset}, avail_numel={avail_numel}")
|
| 311 |
+
|
| 312 |
+
offset = zero2_align(offset)
|
| 313 |
+
avail_numel = zero2_align(avail_numel)
|
| 314 |
+
|
| 315 |
+
if debug:
|
| 316 |
+
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
| 317 |
+
|
| 318 |
+
# Sanity check
|
| 319 |
+
if offset != avail_numel:
|
| 320 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 321 |
+
|
| 322 |
+
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
| 323 |
+
|
| 324 |
+
|
| 325 |
+
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 326 |
+
exclude_frozen_parameters):
|
| 327 |
+
state_dict = OrderedDict()
|
| 328 |
+
|
| 329 |
+
# buffers
|
| 330 |
+
buffers = zero_model_states[0].buffers
|
| 331 |
+
state_dict.update(buffers)
|
| 332 |
+
if debug:
|
| 333 |
+
print(f"added {len(buffers)} buffers")
|
| 334 |
+
|
| 335 |
+
if not exclude_frozen_parameters:
|
| 336 |
+
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
| 337 |
+
|
| 338 |
+
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 339 |
+
|
| 340 |
+
# recover shared parameters
|
| 341 |
+
for pair in zero_model_states[0].shared_params:
|
| 342 |
+
if pair[1] in state_dict:
|
| 343 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 344 |
+
|
| 345 |
+
return state_dict
|
| 346 |
+
|
| 347 |
+
|
| 348 |
+
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
| 349 |
+
remainder = unpartitioned_numel % world_size
|
| 350 |
+
padding_numel = (world_size - remainder) if remainder else 0
|
| 351 |
+
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
| 352 |
+
return partitioned_numel, padding_numel
|
| 353 |
+
|
| 354 |
+
|
| 355 |
+
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
| 356 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 357 |
+
return
|
| 358 |
+
|
| 359 |
+
if debug:
|
| 360 |
+
for i in range(world_size):
|
| 361 |
+
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
| 362 |
+
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 363 |
+
|
| 364 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 365 |
+
wanted_params = len(frozen_param_shapes)
|
| 366 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 367 |
+
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
| 368 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 369 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 370 |
+
|
| 371 |
+
total_params = 0
|
| 372 |
+
total_numel = 0
|
| 373 |
+
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
| 374 |
+
total_params += 1
|
| 375 |
+
unpartitioned_numel = shape.numel()
|
| 376 |
+
total_numel += unpartitioned_numel
|
| 377 |
+
|
| 378 |
+
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
| 379 |
+
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 380 |
+
|
| 381 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 382 |
+
|
| 383 |
+
if debug:
|
| 384 |
+
print(
|
| 385 |
+
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 386 |
+
)
|
| 387 |
+
|
| 388 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 389 |
+
|
| 390 |
+
|
| 391 |
+
class GatheredTensor:
|
| 392 |
+
"""
|
| 393 |
+
A pseudo tensor that collects partitioned weights.
|
| 394 |
+
It is more memory efficient when there are multiple groups.
|
| 395 |
+
"""
|
| 396 |
+
|
| 397 |
+
def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
|
| 398 |
+
self.flat_groups = flat_groups
|
| 399 |
+
self.flat_groups_offset = flat_groups_offset
|
| 400 |
+
self.offset = offset
|
| 401 |
+
self.partitioned_numel = partitioned_numel
|
| 402 |
+
self.shape = shape
|
| 403 |
+
self.dtype = self.flat_groups[0][0].dtype
|
| 404 |
+
|
| 405 |
+
def contiguous(self):
|
| 406 |
+
"""
|
| 407 |
+
Merge partitioned weights from flat_groups into a single tensor.
|
| 408 |
+
"""
|
| 409 |
+
end_idx = self.offset + self.partitioned_numel
|
| 410 |
+
world_size = len(self.flat_groups)
|
| 411 |
+
pad_flat_param_chunks = []
|
| 412 |
+
|
| 413 |
+
for rank_i in range(world_size):
|
| 414 |
+
# for each rank, we need to collect weights from related group/groups
|
| 415 |
+
flat_groups_at_rank_i = self.flat_groups[rank_i]
|
| 416 |
+
start_group_id = None
|
| 417 |
+
end_group_id = None
|
| 418 |
+
for group_id in range(len(self.flat_groups_offset)):
|
| 419 |
+
if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
|
| 420 |
+
start_group_id = group_id
|
| 421 |
+
if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
|
| 422 |
+
end_group_id = group_id
|
| 423 |
+
break
|
| 424 |
+
# collect weights from related group/groups
|
| 425 |
+
for group_id in range(start_group_id, end_group_id + 1):
|
| 426 |
+
flat_tensor = flat_groups_at_rank_i[group_id]
|
| 427 |
+
start_offset = self.offset - self.flat_groups_offset[group_id]
|
| 428 |
+
end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
|
| 429 |
+
pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
|
| 430 |
+
|
| 431 |
+
# collect weights from all ranks
|
| 432 |
+
pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
|
| 433 |
+
param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
|
| 434 |
+
return param
|
| 435 |
+
|
| 436 |
+
|
| 437 |
+
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 438 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 439 |
+
avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
|
| 440 |
+
|
| 441 |
+
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
| 442 |
+
# param, re-consolidating each param, while dealing with padding if any
|
| 443 |
+
|
| 444 |
+
# merge list of dicts, preserving order
|
| 445 |
+
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
| 446 |
+
|
| 447 |
+
if debug:
|
| 448 |
+
for i in range(world_size):
|
| 449 |
+
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
| 450 |
+
|
| 451 |
+
wanted_params = len(param_shapes)
|
| 452 |
+
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
| 453 |
+
# not asserting if there is a mismatch due to possible padding
|
| 454 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 455 |
+
print(f"Trainable params: Have {avail_numel} numels to process.")
|
| 456 |
+
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
| 457 |
+
|
| 458 |
+
# params
|
| 459 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 460 |
+
# out-of-core computing solution
|
| 461 |
+
offset = 0
|
| 462 |
+
total_numel = 0
|
| 463 |
+
total_params = 0
|
| 464 |
+
flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
|
| 465 |
+
for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
|
| 466 |
+
unpartitioned_numel = shape.numel()
|
| 467 |
+
total_numel += unpartitioned_numel
|
| 468 |
+
total_params += 1
|
| 469 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 470 |
+
|
| 471 |
+
if debug:
|
| 472 |
+
print(
|
| 473 |
+
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 474 |
+
)
|
| 475 |
+
|
| 476 |
+
# memory efficient tensor
|
| 477 |
+
tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
|
| 478 |
+
state_dict[name] = tensor
|
| 479 |
+
offset += partitioned_numel
|
| 480 |
+
|
| 481 |
+
offset *= world_size
|
| 482 |
+
|
| 483 |
+
# Sanity check
|
| 484 |
+
if offset != avail_numel:
|
| 485 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 486 |
+
|
| 487 |
+
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
| 488 |
+
|
| 489 |
+
|
| 490 |
+
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 491 |
+
exclude_frozen_parameters):
|
| 492 |
+
state_dict = OrderedDict()
|
| 493 |
+
|
| 494 |
+
# buffers
|
| 495 |
+
buffers = zero_model_states[0].buffers
|
| 496 |
+
state_dict.update(buffers)
|
| 497 |
+
if debug:
|
| 498 |
+
print(f"added {len(buffers)} buffers")
|
| 499 |
+
|
| 500 |
+
if not exclude_frozen_parameters:
|
| 501 |
+
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
| 502 |
+
|
| 503 |
+
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 504 |
+
|
| 505 |
+
# recover shared parameters
|
| 506 |
+
for pair in zero_model_states[0].shared_params:
|
| 507 |
+
if pair[1] in state_dict:
|
| 508 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 509 |
+
|
| 510 |
+
return state_dict
|
| 511 |
+
|
| 512 |
+
|
| 513 |
+
def to_torch_tensor(state_dict, return_empty_tensor=False):
|
| 514 |
+
"""
|
| 515 |
+
Convert state_dict of GatheredTensor to torch tensor
|
| 516 |
+
"""
|
| 517 |
+
torch_state_dict = {}
|
| 518 |
+
converted_tensors = {}
|
| 519 |
+
for name, tensor in state_dict.items():
|
| 520 |
+
tensor_id = id(tensor)
|
| 521 |
+
if tensor_id in converted_tensors: # shared tensors
|
| 522 |
+
shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
|
| 523 |
+
torch_state_dict[name] = shared_tensor
|
| 524 |
+
else:
|
| 525 |
+
converted_tensors[tensor_id] = name
|
| 526 |
+
if return_empty_tensor:
|
| 527 |
+
torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
|
| 528 |
+
else:
|
| 529 |
+
torch_state_dict[name] = tensor.contiguous()
|
| 530 |
+
return torch_state_dict
|
| 531 |
+
|
| 532 |
+
|
| 533 |
+
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
| 534 |
+
tag=None,
|
| 535 |
+
exclude_frozen_parameters=False,
|
| 536 |
+
lazy_mode=False):
|
| 537 |
+
"""
|
| 538 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
| 539 |
+
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
| 540 |
+
via a model hub.
|
| 541 |
+
|
| 542 |
+
Args:
|
| 543 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder
|
| 544 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
| 545 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 546 |
+
- ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
|
| 547 |
+
Convert the pesduo tensor to torch tensor by ``.contiguous()``
|
| 548 |
+
|
| 549 |
+
Returns:
|
| 550 |
+
- pytorch ``state_dict``
|
| 551 |
+
|
| 552 |
+
A typical usage might be ::
|
| 553 |
+
|
| 554 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 555 |
+
# do the training and checkpoint saving
|
| 556 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
| 557 |
+
model = model.cpu() # move to cpu
|
| 558 |
+
model.load_state_dict(state_dict)
|
| 559 |
+
# submit to model hub or save the model to share with others
|
| 560 |
+
|
| 561 |
+
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
| 562 |
+
application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 563 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 564 |
+
|
| 565 |
+
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
| 566 |
+
|
| 567 |
+
Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
|
| 568 |
+
You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
| 569 |
+
the checkpoint. Or you can load state_dict in lazy mode ::
|
| 570 |
+
|
| 571 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 572 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
|
| 573 |
+
for name, lazy_tensor in state_dict.item():
|
| 574 |
+
tensor = lazy_tensor.contiguous() # to cpu
|
| 575 |
+
print(name, tensor)
|
| 576 |
+
# del tensor to release memory if it no longer in use
|
| 577 |
+
"""
|
| 578 |
+
if tag is None:
|
| 579 |
+
latest_path = os.path.join(checkpoint_dir, 'latest')
|
| 580 |
+
if os.path.isfile(latest_path):
|
| 581 |
+
with open(latest_path, 'r') as fd:
|
| 582 |
+
tag = fd.read().strip()
|
| 583 |
+
else:
|
| 584 |
+
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
| 585 |
+
|
| 586 |
+
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
| 587 |
+
|
| 588 |
+
if not os.path.isdir(ds_checkpoint_dir):
|
| 589 |
+
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
| 590 |
+
|
| 591 |
+
state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
| 592 |
+
if lazy_mode:
|
| 593 |
+
return state_dict
|
| 594 |
+
else:
|
| 595 |
+
return to_torch_tensor(state_dict)
|
| 596 |
+
|
| 597 |
+
|
| 598 |
+
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
|
| 599 |
+
output_dir,
|
| 600 |
+
max_shard_size="5GB",
|
| 601 |
+
safe_serialization=False,
|
| 602 |
+
tag=None,
|
| 603 |
+
exclude_frozen_parameters=False):
|
| 604 |
+
"""
|
| 605 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
| 606 |
+
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
| 607 |
+
|
| 608 |
+
Args:
|
| 609 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 610 |
+
- ``output_dir``: directory to the pytorch fp32 state_dict output files
|
| 611 |
+
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
|
| 612 |
+
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
|
| 613 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 614 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 615 |
+
"""
|
| 616 |
+
|
| 617 |
+
# Dependency pre-check
|
| 618 |
+
if safe_serialization:
|
| 619 |
+
try:
|
| 620 |
+
from safetensors.torch import save_file
|
| 621 |
+
except ImportError:
|
| 622 |
+
print('If you want to use `safe_serialization`, please `pip install safetensors`')
|
| 623 |
+
raise
|
| 624 |
+
if max_shard_size is not None:
|
| 625 |
+
try:
|
| 626 |
+
from huggingface_hub import split_torch_state_dict_into_shards
|
| 627 |
+
except ImportError:
|
| 628 |
+
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
|
| 629 |
+
raise
|
| 630 |
+
|
| 631 |
+
# Convert zero checkpoint to state_dict
|
| 632 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
| 633 |
+
tag,
|
| 634 |
+
exclude_frozen_parameters,
|
| 635 |
+
lazy_mode=True)
|
| 636 |
+
|
| 637 |
+
# Shard the model if it is too big.
|
| 638 |
+
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
|
| 639 |
+
if max_shard_size is not None:
|
| 640 |
+
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
|
| 641 |
+
# an memory-efficient approach for sharding
|
| 642 |
+
empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
|
| 643 |
+
state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
|
| 644 |
+
filename_pattern=filename_pattern,
|
| 645 |
+
max_shard_size=max_shard_size)
|
| 646 |
+
else:
|
| 647 |
+
from collections import namedtuple
|
| 648 |
+
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
|
| 649 |
+
state_dict_split = StateDictSplit(is_sharded=False,
|
| 650 |
+
filename_to_tensors={weights_name: list(state_dict.keys())})
|
| 651 |
+
|
| 652 |
+
# Save the model by shard
|
| 653 |
+
os.makedirs(output_dir, exist_ok=True)
|
| 654 |
+
filename_to_tensors = state_dict_split.filename_to_tensors.items()
|
| 655 |
+
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
|
| 656 |
+
shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
|
| 657 |
+
shard_state_dict = to_torch_tensor(shard_state_dict)
|
| 658 |
+
output_path = os.path.join(output_dir, shard_file)
|
| 659 |
+
if safe_serialization:
|
| 660 |
+
save_file(shard_state_dict, output_path, metadata={"format": "pt"})
|
| 661 |
+
else:
|
| 662 |
+
torch.save(shard_state_dict, output_path)
|
| 663 |
+
# release the memory of current shard
|
| 664 |
+
for tensor_name in list(shard_state_dict.keys()):
|
| 665 |
+
del state_dict[tensor_name]
|
| 666 |
+
del shard_state_dict[tensor_name]
|
| 667 |
+
del shard_state_dict
|
| 668 |
+
gc.collect()
|
| 669 |
+
|
| 670 |
+
# Save index if sharded
|
| 671 |
+
if state_dict_split.is_sharded:
|
| 672 |
+
index = {
|
| 673 |
+
"metadata": state_dict_split.metadata,
|
| 674 |
+
"weight_map": state_dict_split.tensor_to_filename,
|
| 675 |
+
}
|
| 676 |
+
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
|
| 677 |
+
save_index_file = os.path.join(output_dir, save_index_file)
|
| 678 |
+
with open(save_index_file, "w", encoding="utf-8") as f:
|
| 679 |
+
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
|
| 680 |
+
f.write(content)
|
| 681 |
+
|
| 682 |
+
|
| 683 |
+
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
| 684 |
+
"""
|
| 685 |
+
1. Put the provided model to cpu
|
| 686 |
+
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
| 687 |
+
3. Load it into the provided model
|
| 688 |
+
|
| 689 |
+
Args:
|
| 690 |
+
- ``model``: the model object to update
|
| 691 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 692 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 693 |
+
|
| 694 |
+
Returns:
|
| 695 |
+
- ``model`: modified model
|
| 696 |
+
|
| 697 |
+
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
| 698 |
+
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
| 699 |
+
conveniently placed for you in the checkpoint folder.
|
| 700 |
+
|
| 701 |
+
A typical usage might be ::
|
| 702 |
+
|
| 703 |
+
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
| 704 |
+
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
| 705 |
+
# submit to model hub or save the model to share with others
|
| 706 |
+
|
| 707 |
+
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
| 708 |
+
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 709 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 710 |
+
|
| 711 |
+
"""
|
| 712 |
+
logger.info(f"Extracting fp32 weights")
|
| 713 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
| 714 |
+
|
| 715 |
+
logger.info(f"Overwriting model with fp32 weights")
|
| 716 |
+
model = model.cpu()
|
| 717 |
+
model.load_state_dict(state_dict, strict=False)
|
| 718 |
+
|
| 719 |
+
return model
|
| 720 |
+
|
| 721 |
+
|
| 722 |
+
if __name__ == "__main__":
|
| 723 |
+
parser = argparse.ArgumentParser()
|
| 724 |
+
parser.add_argument("checkpoint_dir",
|
| 725 |
+
type=str,
|
| 726 |
+
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
| 727 |
+
parser.add_argument("output_dir",
|
| 728 |
+
type=str,
|
| 729 |
+
help="directory to the pytorch fp32 state_dict output files"
|
| 730 |
+
"(e.g. path/checkpoint-12-output/)")
|
| 731 |
+
parser.add_argument(
|
| 732 |
+
"--max_shard_size",
|
| 733 |
+
type=str,
|
| 734 |
+
default="5GB",
|
| 735 |
+
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
|
| 736 |
+
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
|
| 737 |
+
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
|
| 738 |
+
"without CPU OOM issues.")
|
| 739 |
+
parser.add_argument(
|
| 740 |
+
"--safe_serialization",
|
| 741 |
+
default=False,
|
| 742 |
+
action='store_true',
|
| 743 |
+
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
|
| 744 |
+
parser.add_argument("-t",
|
| 745 |
+
"--tag",
|
| 746 |
+
type=str,
|
| 747 |
+
default=None,
|
| 748 |
+
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
| 749 |
+
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
| 750 |
+
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
| 751 |
+
args = parser.parse_args()
|
| 752 |
+
|
| 753 |
+
debug = args.debug
|
| 754 |
+
|
| 755 |
+
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
| 756 |
+
args.output_dir,
|
| 757 |
+
max_shard_size=args.max_shard_size,
|
| 758 |
+
safe_serialization=args.safe_serialization,
|
| 759 |
+
tag=args.tag,
|
| 760 |
+
exclude_frozen_parameters=args.exclude_frozen_parameters)
|
checkpoint-30000/global_step30000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:632d98295ee2d46a666ae098a5d5b61e5941505a8445acb615f36b887fbb6e9d
|
| 3 |
+
size 8005108236
|
checkpoint-30000/global_step30000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67072825cf7651c80c2ff760ac6ade13c89867b0766e8e970cfd55eb41a9d8d0
|
| 3 |
+
size 8005064076
|
checkpoint-30000/global_step30000/mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1c3ffb9ec45b1502eb47c8f6fa3044bb8d65ee2a11a08495f13d121fbef3946
|
| 3 |
+
size 2668900764
|
checkpoint-30000/latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step30000
|
checkpoint-30000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7156f353c7ec1e64db9982cea0b52b0a0896b52ec7de1f69676cbd2c892ecd17
|
| 3 |
+
size 17678656921
|
checkpoint-30000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebaa187979fd0e7a362307fce1e867f92d6316adb00f213536af09466b6d2366
|
| 3 |
+
size 14512
|
checkpoint-30000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f06401741883a3ef54a64db7c0fcee8dcca52c3317069b43de5360893a2e9024
|
| 3 |
+
size 14512
|
checkpoint-30000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b73a87e7c1c099f104125fccd174a6666f174c693a596adfa038c7b8267f0a4e
|
| 3 |
+
size 1064
|
checkpoint-30000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-30000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:735a552aa1714bfc383df4ff1a42a38cfe32c5c5b2762c0a21b52159da19005f
|
| 3 |
+
size 6904
|
checkpoint-30000/zero_to_fp32.py
ADDED
|
@@ -0,0 +1,760 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python
|
| 2 |
+
|
| 3 |
+
# Copyright (c) Microsoft Corporation.
|
| 4 |
+
# SPDX-License-Identifier: Apache-2.0
|
| 5 |
+
|
| 6 |
+
# DeepSpeed Team
|
| 7 |
+
|
| 8 |
+
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
| 9 |
+
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
| 10 |
+
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
| 11 |
+
# application.
|
| 12 |
+
#
|
| 13 |
+
# example:
|
| 14 |
+
# python zero_to_fp32.py . output_dir/
|
| 15 |
+
# or
|
| 16 |
+
# python zero_to_fp32.py . output_dir/ --safe_serialization
|
| 17 |
+
|
| 18 |
+
import argparse
|
| 19 |
+
import torch
|
| 20 |
+
import glob
|
| 21 |
+
import math
|
| 22 |
+
import os
|
| 23 |
+
import re
|
| 24 |
+
import gc
|
| 25 |
+
import json
|
| 26 |
+
import numpy as np
|
| 27 |
+
from tqdm import tqdm
|
| 28 |
+
from collections import OrderedDict
|
| 29 |
+
from dataclasses import dataclass
|
| 30 |
+
|
| 31 |
+
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
| 32 |
+
# DeepSpeed data structures it has to be available in the current python environment.
|
| 33 |
+
from deepspeed.utils import logger
|
| 34 |
+
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
| 35 |
+
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
| 36 |
+
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
@dataclass
|
| 40 |
+
class zero_model_state:
|
| 41 |
+
buffers: dict()
|
| 42 |
+
param_shapes: dict()
|
| 43 |
+
shared_params: list
|
| 44 |
+
ds_version: int
|
| 45 |
+
frozen_param_shapes: dict()
|
| 46 |
+
frozen_param_fragments: dict()
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
debug = 0
|
| 50 |
+
|
| 51 |
+
# load to cpu
|
| 52 |
+
device = torch.device('cpu')
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
def atoi(text):
|
| 56 |
+
return int(text) if text.isdigit() else text
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
def natural_keys(text):
|
| 60 |
+
'''
|
| 61 |
+
alist.sort(key=natural_keys) sorts in human order
|
| 62 |
+
http://nedbatchelder.com/blog/200712/human_sorting.html
|
| 63 |
+
(See Toothy's implementation in the comments)
|
| 64 |
+
'''
|
| 65 |
+
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
def get_model_state_file(checkpoint_dir, zero_stage):
|
| 69 |
+
if not os.path.isdir(checkpoint_dir):
|
| 70 |
+
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
| 71 |
+
|
| 72 |
+
# there should be only one file
|
| 73 |
+
if zero_stage <= 2:
|
| 74 |
+
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
| 75 |
+
elif zero_stage == 3:
|
| 76 |
+
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
| 77 |
+
|
| 78 |
+
if not os.path.exists(file):
|
| 79 |
+
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
| 80 |
+
|
| 81 |
+
return file
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
| 85 |
+
# XXX: need to test that this simple glob rule works for multi-node setup too
|
| 86 |
+
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
| 87 |
+
|
| 88 |
+
if len(ckpt_files) == 0:
|
| 89 |
+
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
| 90 |
+
|
| 91 |
+
return ckpt_files
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
def get_optim_files(checkpoint_dir):
|
| 95 |
+
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
def get_model_state_files(checkpoint_dir):
|
| 99 |
+
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
| 100 |
+
|
| 101 |
+
|
| 102 |
+
def parse_model_states(files):
|
| 103 |
+
zero_model_states = []
|
| 104 |
+
for file in files:
|
| 105 |
+
state_dict = torch.load(file, map_location=device, weights_only=False)
|
| 106 |
+
|
| 107 |
+
if BUFFER_NAMES not in state_dict:
|
| 108 |
+
raise ValueError(f"{file} is not a model state checkpoint")
|
| 109 |
+
buffer_names = state_dict[BUFFER_NAMES]
|
| 110 |
+
if debug:
|
| 111 |
+
print("Found buffers:", buffer_names)
|
| 112 |
+
|
| 113 |
+
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
| 114 |
+
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
| 115 |
+
param_shapes = state_dict[PARAM_SHAPES]
|
| 116 |
+
|
| 117 |
+
# collect parameters that are included in param_shapes
|
| 118 |
+
param_names = []
|
| 119 |
+
for s in param_shapes:
|
| 120 |
+
for name in s.keys():
|
| 121 |
+
param_names.append(name)
|
| 122 |
+
|
| 123 |
+
# update with frozen parameters
|
| 124 |
+
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
| 125 |
+
if frozen_param_shapes is not None:
|
| 126 |
+
if debug:
|
| 127 |
+
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
| 128 |
+
param_names += list(frozen_param_shapes.keys())
|
| 129 |
+
|
| 130 |
+
# handle shared params
|
| 131 |
+
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
| 132 |
+
|
| 133 |
+
ds_version = state_dict.get(DS_VERSION, None)
|
| 134 |
+
|
| 135 |
+
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
| 136 |
+
|
| 137 |
+
z_model_state = zero_model_state(buffers=buffers,
|
| 138 |
+
param_shapes=param_shapes,
|
| 139 |
+
shared_params=shared_params,
|
| 140 |
+
ds_version=ds_version,
|
| 141 |
+
frozen_param_shapes=frozen_param_shapes,
|
| 142 |
+
frozen_param_fragments=frozen_param_fragments)
|
| 143 |
+
zero_model_states.append(z_model_state)
|
| 144 |
+
|
| 145 |
+
return zero_model_states
|
| 146 |
+
|
| 147 |
+
|
| 148 |
+
def parse_optim_states(files, ds_checkpoint_dir):
|
| 149 |
+
total_files = len(files)
|
| 150 |
+
state_dicts = []
|
| 151 |
+
for f in tqdm(files, desc='Loading checkpoint shards'):
|
| 152 |
+
state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
|
| 153 |
+
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
| 154 |
+
# and also handle the case where it was already removed by another helper script
|
| 155 |
+
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
| 156 |
+
state_dicts.append(state_dict)
|
| 157 |
+
|
| 158 |
+
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
| 159 |
+
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
| 160 |
+
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
| 161 |
+
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
| 162 |
+
|
| 163 |
+
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
| 164 |
+
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
| 165 |
+
# use the max of the partition_count to get the dp world_size.
|
| 166 |
+
|
| 167 |
+
if type(world_size) is list:
|
| 168 |
+
world_size = max(world_size)
|
| 169 |
+
|
| 170 |
+
if world_size != total_files:
|
| 171 |
+
raise ValueError(
|
| 172 |
+
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
| 173 |
+
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
| 174 |
+
)
|
| 175 |
+
|
| 176 |
+
# the groups are named differently in each stage
|
| 177 |
+
if zero_stage <= 2:
|
| 178 |
+
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
| 179 |
+
elif zero_stage == 3:
|
| 180 |
+
fp32_groups_key = FP32_FLAT_GROUPS
|
| 181 |
+
else:
|
| 182 |
+
raise ValueError(f"unknown zero stage {zero_stage}")
|
| 183 |
+
|
| 184 |
+
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
| 185 |
+
return zero_stage, world_size, fp32_flat_groups
|
| 186 |
+
|
| 187 |
+
|
| 188 |
+
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
| 189 |
+
"""
|
| 190 |
+
Returns fp32 state_dict reconstructed from ds checkpoint
|
| 191 |
+
|
| 192 |
+
Args:
|
| 193 |
+
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
| 194 |
+
|
| 195 |
+
"""
|
| 196 |
+
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
| 197 |
+
|
| 198 |
+
optim_files = get_optim_files(ds_checkpoint_dir)
|
| 199 |
+
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
| 200 |
+
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
| 201 |
+
|
| 202 |
+
model_files = get_model_state_files(ds_checkpoint_dir)
|
| 203 |
+
|
| 204 |
+
zero_model_states = parse_model_states(model_files)
|
| 205 |
+
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
| 206 |
+
|
| 207 |
+
if zero_stage <= 2:
|
| 208 |
+
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 209 |
+
exclude_frozen_parameters)
|
| 210 |
+
elif zero_stage == 3:
|
| 211 |
+
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 212 |
+
exclude_frozen_parameters)
|
| 213 |
+
|
| 214 |
+
|
| 215 |
+
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
| 216 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 217 |
+
return
|
| 218 |
+
|
| 219 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 220 |
+
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
| 221 |
+
|
| 222 |
+
if debug:
|
| 223 |
+
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
| 224 |
+
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 225 |
+
|
| 226 |
+
wanted_params = len(frozen_param_shapes)
|
| 227 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 228 |
+
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
| 229 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 230 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 231 |
+
|
| 232 |
+
total_params = 0
|
| 233 |
+
total_numel = 0
|
| 234 |
+
for name, shape in frozen_param_shapes.items():
|
| 235 |
+
total_params += 1
|
| 236 |
+
unpartitioned_numel = shape.numel()
|
| 237 |
+
total_numel += unpartitioned_numel
|
| 238 |
+
|
| 239 |
+
state_dict[name] = frozen_param_fragments[name]
|
| 240 |
+
|
| 241 |
+
if debug:
|
| 242 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 243 |
+
|
| 244 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 245 |
+
|
| 246 |
+
|
| 247 |
+
def _has_callable(obj, fn):
|
| 248 |
+
attr = getattr(obj, fn, None)
|
| 249 |
+
return callable(attr)
|
| 250 |
+
|
| 251 |
+
|
| 252 |
+
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 253 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 254 |
+
|
| 255 |
+
# Reconstruction protocol:
|
| 256 |
+
#
|
| 257 |
+
# XXX: document this
|
| 258 |
+
|
| 259 |
+
if debug:
|
| 260 |
+
for i in range(world_size):
|
| 261 |
+
for j in range(len(fp32_flat_groups[0])):
|
| 262 |
+
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
| 263 |
+
|
| 264 |
+
# XXX: memory usage doubles here (zero2)
|
| 265 |
+
num_param_groups = len(fp32_flat_groups[0])
|
| 266 |
+
merged_single_partition_of_fp32_groups = []
|
| 267 |
+
for i in range(num_param_groups):
|
| 268 |
+
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
| 269 |
+
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
| 270 |
+
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
| 271 |
+
avail_numel = sum(
|
| 272 |
+
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
| 273 |
+
|
| 274 |
+
if debug:
|
| 275 |
+
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
| 276 |
+
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
| 277 |
+
# not asserting if there is a mismatch due to possible padding
|
| 278 |
+
print(f"Have {avail_numel} numels to process.")
|
| 279 |
+
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
| 280 |
+
|
| 281 |
+
# params
|
| 282 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 283 |
+
# out-of-core computing solution
|
| 284 |
+
total_numel = 0
|
| 285 |
+
total_params = 0
|
| 286 |
+
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
| 287 |
+
offset = 0
|
| 288 |
+
avail_numel = full_single_fp32_vector.numel()
|
| 289 |
+
for name, shape in shapes.items():
|
| 290 |
+
|
| 291 |
+
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
| 292 |
+
total_numel += unpartitioned_numel
|
| 293 |
+
total_params += 1
|
| 294 |
+
|
| 295 |
+
if debug:
|
| 296 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 297 |
+
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
| 298 |
+
offset += unpartitioned_numel
|
| 299 |
+
|
| 300 |
+
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
| 301 |
+
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
| 302 |
+
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
| 303 |
+
# live optimizer object, so we are checking that the numbers are within the right range
|
| 304 |
+
align_to = 2 * world_size
|
| 305 |
+
|
| 306 |
+
def zero2_align(x):
|
| 307 |
+
return align_to * math.ceil(x / align_to)
|
| 308 |
+
|
| 309 |
+
if debug:
|
| 310 |
+
print(f"original offset={offset}, avail_numel={avail_numel}")
|
| 311 |
+
|
| 312 |
+
offset = zero2_align(offset)
|
| 313 |
+
avail_numel = zero2_align(avail_numel)
|
| 314 |
+
|
| 315 |
+
if debug:
|
| 316 |
+
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
| 317 |
+
|
| 318 |
+
# Sanity check
|
| 319 |
+
if offset != avail_numel:
|
| 320 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 321 |
+
|
| 322 |
+
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
| 323 |
+
|
| 324 |
+
|
| 325 |
+
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 326 |
+
exclude_frozen_parameters):
|
| 327 |
+
state_dict = OrderedDict()
|
| 328 |
+
|
| 329 |
+
# buffers
|
| 330 |
+
buffers = zero_model_states[0].buffers
|
| 331 |
+
state_dict.update(buffers)
|
| 332 |
+
if debug:
|
| 333 |
+
print(f"added {len(buffers)} buffers")
|
| 334 |
+
|
| 335 |
+
if not exclude_frozen_parameters:
|
| 336 |
+
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
| 337 |
+
|
| 338 |
+
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 339 |
+
|
| 340 |
+
# recover shared parameters
|
| 341 |
+
for pair in zero_model_states[0].shared_params:
|
| 342 |
+
if pair[1] in state_dict:
|
| 343 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 344 |
+
|
| 345 |
+
return state_dict
|
| 346 |
+
|
| 347 |
+
|
| 348 |
+
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
| 349 |
+
remainder = unpartitioned_numel % world_size
|
| 350 |
+
padding_numel = (world_size - remainder) if remainder else 0
|
| 351 |
+
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
| 352 |
+
return partitioned_numel, padding_numel
|
| 353 |
+
|
| 354 |
+
|
| 355 |
+
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
| 356 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 357 |
+
return
|
| 358 |
+
|
| 359 |
+
if debug:
|
| 360 |
+
for i in range(world_size):
|
| 361 |
+
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
| 362 |
+
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 363 |
+
|
| 364 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 365 |
+
wanted_params = len(frozen_param_shapes)
|
| 366 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 367 |
+
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
| 368 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 369 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 370 |
+
|
| 371 |
+
total_params = 0
|
| 372 |
+
total_numel = 0
|
| 373 |
+
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
| 374 |
+
total_params += 1
|
| 375 |
+
unpartitioned_numel = shape.numel()
|
| 376 |
+
total_numel += unpartitioned_numel
|
| 377 |
+
|
| 378 |
+
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
| 379 |
+
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 380 |
+
|
| 381 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 382 |
+
|
| 383 |
+
if debug:
|
| 384 |
+
print(
|
| 385 |
+
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 386 |
+
)
|
| 387 |
+
|
| 388 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 389 |
+
|
| 390 |
+
|
| 391 |
+
class GatheredTensor:
|
| 392 |
+
"""
|
| 393 |
+
A pseudo tensor that collects partitioned weights.
|
| 394 |
+
It is more memory efficient when there are multiple groups.
|
| 395 |
+
"""
|
| 396 |
+
|
| 397 |
+
def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
|
| 398 |
+
self.flat_groups = flat_groups
|
| 399 |
+
self.flat_groups_offset = flat_groups_offset
|
| 400 |
+
self.offset = offset
|
| 401 |
+
self.partitioned_numel = partitioned_numel
|
| 402 |
+
self.shape = shape
|
| 403 |
+
self.dtype = self.flat_groups[0][0].dtype
|
| 404 |
+
|
| 405 |
+
def contiguous(self):
|
| 406 |
+
"""
|
| 407 |
+
Merge partitioned weights from flat_groups into a single tensor.
|
| 408 |
+
"""
|
| 409 |
+
end_idx = self.offset + self.partitioned_numel
|
| 410 |
+
world_size = len(self.flat_groups)
|
| 411 |
+
pad_flat_param_chunks = []
|
| 412 |
+
|
| 413 |
+
for rank_i in range(world_size):
|
| 414 |
+
# for each rank, we need to collect weights from related group/groups
|
| 415 |
+
flat_groups_at_rank_i = self.flat_groups[rank_i]
|
| 416 |
+
start_group_id = None
|
| 417 |
+
end_group_id = None
|
| 418 |
+
for group_id in range(len(self.flat_groups_offset)):
|
| 419 |
+
if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
|
| 420 |
+
start_group_id = group_id
|
| 421 |
+
if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
|
| 422 |
+
end_group_id = group_id
|
| 423 |
+
break
|
| 424 |
+
# collect weights from related group/groups
|
| 425 |
+
for group_id in range(start_group_id, end_group_id + 1):
|
| 426 |
+
flat_tensor = flat_groups_at_rank_i[group_id]
|
| 427 |
+
start_offset = self.offset - self.flat_groups_offset[group_id]
|
| 428 |
+
end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
|
| 429 |
+
pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
|
| 430 |
+
|
| 431 |
+
# collect weights from all ranks
|
| 432 |
+
pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
|
| 433 |
+
param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
|
| 434 |
+
return param
|
| 435 |
+
|
| 436 |
+
|
| 437 |
+
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 438 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 439 |
+
avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
|
| 440 |
+
|
| 441 |
+
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
| 442 |
+
# param, re-consolidating each param, while dealing with padding if any
|
| 443 |
+
|
| 444 |
+
# merge list of dicts, preserving order
|
| 445 |
+
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
| 446 |
+
|
| 447 |
+
if debug:
|
| 448 |
+
for i in range(world_size):
|
| 449 |
+
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
| 450 |
+
|
| 451 |
+
wanted_params = len(param_shapes)
|
| 452 |
+
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
| 453 |
+
# not asserting if there is a mismatch due to possible padding
|
| 454 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 455 |
+
print(f"Trainable params: Have {avail_numel} numels to process.")
|
| 456 |
+
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
| 457 |
+
|
| 458 |
+
# params
|
| 459 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 460 |
+
# out-of-core computing solution
|
| 461 |
+
offset = 0
|
| 462 |
+
total_numel = 0
|
| 463 |
+
total_params = 0
|
| 464 |
+
flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
|
| 465 |
+
for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
|
| 466 |
+
unpartitioned_numel = shape.numel()
|
| 467 |
+
total_numel += unpartitioned_numel
|
| 468 |
+
total_params += 1
|
| 469 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 470 |
+
|
| 471 |
+
if debug:
|
| 472 |
+
print(
|
| 473 |
+
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 474 |
+
)
|
| 475 |
+
|
| 476 |
+
# memory efficient tensor
|
| 477 |
+
tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
|
| 478 |
+
state_dict[name] = tensor
|
| 479 |
+
offset += partitioned_numel
|
| 480 |
+
|
| 481 |
+
offset *= world_size
|
| 482 |
+
|
| 483 |
+
# Sanity check
|
| 484 |
+
if offset != avail_numel:
|
| 485 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 486 |
+
|
| 487 |
+
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
| 488 |
+
|
| 489 |
+
|
| 490 |
+
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 491 |
+
exclude_frozen_parameters):
|
| 492 |
+
state_dict = OrderedDict()
|
| 493 |
+
|
| 494 |
+
# buffers
|
| 495 |
+
buffers = zero_model_states[0].buffers
|
| 496 |
+
state_dict.update(buffers)
|
| 497 |
+
if debug:
|
| 498 |
+
print(f"added {len(buffers)} buffers")
|
| 499 |
+
|
| 500 |
+
if not exclude_frozen_parameters:
|
| 501 |
+
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
| 502 |
+
|
| 503 |
+
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 504 |
+
|
| 505 |
+
# recover shared parameters
|
| 506 |
+
for pair in zero_model_states[0].shared_params:
|
| 507 |
+
if pair[1] in state_dict:
|
| 508 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 509 |
+
|
| 510 |
+
return state_dict
|
| 511 |
+
|
| 512 |
+
|
| 513 |
+
def to_torch_tensor(state_dict, return_empty_tensor=False):
|
| 514 |
+
"""
|
| 515 |
+
Convert state_dict of GatheredTensor to torch tensor
|
| 516 |
+
"""
|
| 517 |
+
torch_state_dict = {}
|
| 518 |
+
converted_tensors = {}
|
| 519 |
+
for name, tensor in state_dict.items():
|
| 520 |
+
tensor_id = id(tensor)
|
| 521 |
+
if tensor_id in converted_tensors: # shared tensors
|
| 522 |
+
shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
|
| 523 |
+
torch_state_dict[name] = shared_tensor
|
| 524 |
+
else:
|
| 525 |
+
converted_tensors[tensor_id] = name
|
| 526 |
+
if return_empty_tensor:
|
| 527 |
+
torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
|
| 528 |
+
else:
|
| 529 |
+
torch_state_dict[name] = tensor.contiguous()
|
| 530 |
+
return torch_state_dict
|
| 531 |
+
|
| 532 |
+
|
| 533 |
+
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
| 534 |
+
tag=None,
|
| 535 |
+
exclude_frozen_parameters=False,
|
| 536 |
+
lazy_mode=False):
|
| 537 |
+
"""
|
| 538 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
| 539 |
+
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
| 540 |
+
via a model hub.
|
| 541 |
+
|
| 542 |
+
Args:
|
| 543 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder
|
| 544 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
| 545 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 546 |
+
- ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
|
| 547 |
+
Convert the pesduo tensor to torch tensor by ``.contiguous()``
|
| 548 |
+
|
| 549 |
+
Returns:
|
| 550 |
+
- pytorch ``state_dict``
|
| 551 |
+
|
| 552 |
+
A typical usage might be ::
|
| 553 |
+
|
| 554 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 555 |
+
# do the training and checkpoint saving
|
| 556 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
| 557 |
+
model = model.cpu() # move to cpu
|
| 558 |
+
model.load_state_dict(state_dict)
|
| 559 |
+
# submit to model hub or save the model to share with others
|
| 560 |
+
|
| 561 |
+
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
| 562 |
+
application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 563 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 564 |
+
|
| 565 |
+
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
| 566 |
+
|
| 567 |
+
Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
|
| 568 |
+
You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
| 569 |
+
the checkpoint. Or you can load state_dict in lazy mode ::
|
| 570 |
+
|
| 571 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 572 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
|
| 573 |
+
for name, lazy_tensor in state_dict.item():
|
| 574 |
+
tensor = lazy_tensor.contiguous() # to cpu
|
| 575 |
+
print(name, tensor)
|
| 576 |
+
# del tensor to release memory if it no longer in use
|
| 577 |
+
"""
|
| 578 |
+
if tag is None:
|
| 579 |
+
latest_path = os.path.join(checkpoint_dir, 'latest')
|
| 580 |
+
if os.path.isfile(latest_path):
|
| 581 |
+
with open(latest_path, 'r') as fd:
|
| 582 |
+
tag = fd.read().strip()
|
| 583 |
+
else:
|
| 584 |
+
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
| 585 |
+
|
| 586 |
+
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
| 587 |
+
|
| 588 |
+
if not os.path.isdir(ds_checkpoint_dir):
|
| 589 |
+
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
| 590 |
+
|
| 591 |
+
state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
| 592 |
+
if lazy_mode:
|
| 593 |
+
return state_dict
|
| 594 |
+
else:
|
| 595 |
+
return to_torch_tensor(state_dict)
|
| 596 |
+
|
| 597 |
+
|
| 598 |
+
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
|
| 599 |
+
output_dir,
|
| 600 |
+
max_shard_size="5GB",
|
| 601 |
+
safe_serialization=False,
|
| 602 |
+
tag=None,
|
| 603 |
+
exclude_frozen_parameters=False):
|
| 604 |
+
"""
|
| 605 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
| 606 |
+
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
| 607 |
+
|
| 608 |
+
Args:
|
| 609 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 610 |
+
- ``output_dir``: directory to the pytorch fp32 state_dict output files
|
| 611 |
+
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
|
| 612 |
+
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
|
| 613 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 614 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 615 |
+
"""
|
| 616 |
+
|
| 617 |
+
# Dependency pre-check
|
| 618 |
+
if safe_serialization:
|
| 619 |
+
try:
|
| 620 |
+
from safetensors.torch import save_file
|
| 621 |
+
except ImportError:
|
| 622 |
+
print('If you want to use `safe_serialization`, please `pip install safetensors`')
|
| 623 |
+
raise
|
| 624 |
+
if max_shard_size is not None:
|
| 625 |
+
try:
|
| 626 |
+
from huggingface_hub import split_torch_state_dict_into_shards
|
| 627 |
+
except ImportError:
|
| 628 |
+
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
|
| 629 |
+
raise
|
| 630 |
+
|
| 631 |
+
# Convert zero checkpoint to state_dict
|
| 632 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
| 633 |
+
tag,
|
| 634 |
+
exclude_frozen_parameters,
|
| 635 |
+
lazy_mode=True)
|
| 636 |
+
|
| 637 |
+
# Shard the model if it is too big.
|
| 638 |
+
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
|
| 639 |
+
if max_shard_size is not None:
|
| 640 |
+
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
|
| 641 |
+
# an memory-efficient approach for sharding
|
| 642 |
+
empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
|
| 643 |
+
state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
|
| 644 |
+
filename_pattern=filename_pattern,
|
| 645 |
+
max_shard_size=max_shard_size)
|
| 646 |
+
else:
|
| 647 |
+
from collections import namedtuple
|
| 648 |
+
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
|
| 649 |
+
state_dict_split = StateDictSplit(is_sharded=False,
|
| 650 |
+
filename_to_tensors={weights_name: list(state_dict.keys())})
|
| 651 |
+
|
| 652 |
+
# Save the model by shard
|
| 653 |
+
os.makedirs(output_dir, exist_ok=True)
|
| 654 |
+
filename_to_tensors = state_dict_split.filename_to_tensors.items()
|
| 655 |
+
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
|
| 656 |
+
shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
|
| 657 |
+
shard_state_dict = to_torch_tensor(shard_state_dict)
|
| 658 |
+
output_path = os.path.join(output_dir, shard_file)
|
| 659 |
+
if safe_serialization:
|
| 660 |
+
save_file(shard_state_dict, output_path, metadata={"format": "pt"})
|
| 661 |
+
else:
|
| 662 |
+
torch.save(shard_state_dict, output_path)
|
| 663 |
+
# release the memory of current shard
|
| 664 |
+
for tensor_name in list(shard_state_dict.keys()):
|
| 665 |
+
del state_dict[tensor_name]
|
| 666 |
+
del shard_state_dict[tensor_name]
|
| 667 |
+
del shard_state_dict
|
| 668 |
+
gc.collect()
|
| 669 |
+
|
| 670 |
+
# Save index if sharded
|
| 671 |
+
if state_dict_split.is_sharded:
|
| 672 |
+
index = {
|
| 673 |
+
"metadata": state_dict_split.metadata,
|
| 674 |
+
"weight_map": state_dict_split.tensor_to_filename,
|
| 675 |
+
}
|
| 676 |
+
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
|
| 677 |
+
save_index_file = os.path.join(output_dir, save_index_file)
|
| 678 |
+
with open(save_index_file, "w", encoding="utf-8") as f:
|
| 679 |
+
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
|
| 680 |
+
f.write(content)
|
| 681 |
+
|
| 682 |
+
|
| 683 |
+
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
| 684 |
+
"""
|
| 685 |
+
1. Put the provided model to cpu
|
| 686 |
+
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
| 687 |
+
3. Load it into the provided model
|
| 688 |
+
|
| 689 |
+
Args:
|
| 690 |
+
- ``model``: the model object to update
|
| 691 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 692 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 693 |
+
|
| 694 |
+
Returns:
|
| 695 |
+
- ``model`: modified model
|
| 696 |
+
|
| 697 |
+
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
| 698 |
+
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
| 699 |
+
conveniently placed for you in the checkpoint folder.
|
| 700 |
+
|
| 701 |
+
A typical usage might be ::
|
| 702 |
+
|
| 703 |
+
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
| 704 |
+
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
| 705 |
+
# submit to model hub or save the model to share with others
|
| 706 |
+
|
| 707 |
+
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
| 708 |
+
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 709 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 710 |
+
|
| 711 |
+
"""
|
| 712 |
+
logger.info(f"Extracting fp32 weights")
|
| 713 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
| 714 |
+
|
| 715 |
+
logger.info(f"Overwriting model with fp32 weights")
|
| 716 |
+
model = model.cpu()
|
| 717 |
+
model.load_state_dict(state_dict, strict=False)
|
| 718 |
+
|
| 719 |
+
return model
|
| 720 |
+
|
| 721 |
+
|
| 722 |
+
if __name__ == "__main__":
|
| 723 |
+
parser = argparse.ArgumentParser()
|
| 724 |
+
parser.add_argument("checkpoint_dir",
|
| 725 |
+
type=str,
|
| 726 |
+
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
| 727 |
+
parser.add_argument("output_dir",
|
| 728 |
+
type=str,
|
| 729 |
+
help="directory to the pytorch fp32 state_dict output files"
|
| 730 |
+
"(e.g. path/checkpoint-12-output/)")
|
| 731 |
+
parser.add_argument(
|
| 732 |
+
"--max_shard_size",
|
| 733 |
+
type=str,
|
| 734 |
+
default="5GB",
|
| 735 |
+
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
|
| 736 |
+
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
|
| 737 |
+
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
|
| 738 |
+
"without CPU OOM issues.")
|
| 739 |
+
parser.add_argument(
|
| 740 |
+
"--safe_serialization",
|
| 741 |
+
default=False,
|
| 742 |
+
action='store_true',
|
| 743 |
+
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
|
| 744 |
+
parser.add_argument("-t",
|
| 745 |
+
"--tag",
|
| 746 |
+
type=str,
|
| 747 |
+
default=None,
|
| 748 |
+
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
| 749 |
+
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
| 750 |
+
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
| 751 |
+
args = parser.parse_args()
|
| 752 |
+
|
| 753 |
+
debug = args.debug
|
| 754 |
+
|
| 755 |
+
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
| 756 |
+
args.output_dir,
|
| 757 |
+
max_shard_size=args.max_shard_size,
|
| 758 |
+
safe_serialization=args.safe_serialization,
|
| 759 |
+
tag=args.tag,
|
| 760 |
+
exclude_frozen_parameters=args.exclude_frozen_parameters)
|
checkpoint-38184/global_step38184/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b4b0b3d9a3254f5fb1fa36f48ee0b4369cf2adf515ed69633e275a71239360a
|
| 3 |
+
size 8005108236
|
checkpoint-38184/global_step38184/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f743b9666fc49c1ebad272eb3b3a306976b05a44bc70f4ae430c07746997b07
|
| 3 |
+
size 8005064076
|
checkpoint-38184/global_step38184/mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ee01562a9abcafeb7e92730b0b4b3c1c0bc72cbe8340f803c512f21535e4c3b
|
| 3 |
+
size 2668900764
|
checkpoint-38184/latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step38184
|
checkpoint-38184/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc827c4f5058ad23551269a1859f36e04fd1e515f2966286362625492420b8cd
|
| 3 |
+
size 17678656921
|
checkpoint-38184/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0faedd604098d980819b9489442d3db984f874373123ca7de95e1996ccf996bc
|
| 3 |
+
size 14448
|
checkpoint-38184/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38eccbe5fbf40dd28f8fa55d327041e9a8e750e58b94ecccee67f1a3976d5937
|
| 3 |
+
size 14448
|
checkpoint-38184/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d0b21313f367e0a9c14d8f2843af0f0aacb8598eb346c719a4da16e9d4a5a21
|
| 3 |
+
size 1064
|
checkpoint-38184/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-38184/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:735a552aa1714bfc383df4ff1a42a38cfe32c5c5b2762c0a21b52159da19005f
|
| 3 |
+
size 6904
|
checkpoint-38184/zero_to_fp32.py
ADDED
|
@@ -0,0 +1,760 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python
|
| 2 |
+
|
| 3 |
+
# Copyright (c) Microsoft Corporation.
|
| 4 |
+
# SPDX-License-Identifier: Apache-2.0
|
| 5 |
+
|
| 6 |
+
# DeepSpeed Team
|
| 7 |
+
|
| 8 |
+
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
| 9 |
+
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
| 10 |
+
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
| 11 |
+
# application.
|
| 12 |
+
#
|
| 13 |
+
# example:
|
| 14 |
+
# python zero_to_fp32.py . output_dir/
|
| 15 |
+
# or
|
| 16 |
+
# python zero_to_fp32.py . output_dir/ --safe_serialization
|
| 17 |
+
|
| 18 |
+
import argparse
|
| 19 |
+
import torch
|
| 20 |
+
import glob
|
| 21 |
+
import math
|
| 22 |
+
import os
|
| 23 |
+
import re
|
| 24 |
+
import gc
|
| 25 |
+
import json
|
| 26 |
+
import numpy as np
|
| 27 |
+
from tqdm import tqdm
|
| 28 |
+
from collections import OrderedDict
|
| 29 |
+
from dataclasses import dataclass
|
| 30 |
+
|
| 31 |
+
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
| 32 |
+
# DeepSpeed data structures it has to be available in the current python environment.
|
| 33 |
+
from deepspeed.utils import logger
|
| 34 |
+
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
| 35 |
+
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
| 36 |
+
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
@dataclass
|
| 40 |
+
class zero_model_state:
|
| 41 |
+
buffers: dict()
|
| 42 |
+
param_shapes: dict()
|
| 43 |
+
shared_params: list
|
| 44 |
+
ds_version: int
|
| 45 |
+
frozen_param_shapes: dict()
|
| 46 |
+
frozen_param_fragments: dict()
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
debug = 0
|
| 50 |
+
|
| 51 |
+
# load to cpu
|
| 52 |
+
device = torch.device('cpu')
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
def atoi(text):
|
| 56 |
+
return int(text) if text.isdigit() else text
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
def natural_keys(text):
|
| 60 |
+
'''
|
| 61 |
+
alist.sort(key=natural_keys) sorts in human order
|
| 62 |
+
http://nedbatchelder.com/blog/200712/human_sorting.html
|
| 63 |
+
(See Toothy's implementation in the comments)
|
| 64 |
+
'''
|
| 65 |
+
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
def get_model_state_file(checkpoint_dir, zero_stage):
|
| 69 |
+
if not os.path.isdir(checkpoint_dir):
|
| 70 |
+
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
| 71 |
+
|
| 72 |
+
# there should be only one file
|
| 73 |
+
if zero_stage <= 2:
|
| 74 |
+
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
| 75 |
+
elif zero_stage == 3:
|
| 76 |
+
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
| 77 |
+
|
| 78 |
+
if not os.path.exists(file):
|
| 79 |
+
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
| 80 |
+
|
| 81 |
+
return file
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
| 85 |
+
# XXX: need to test that this simple glob rule works for multi-node setup too
|
| 86 |
+
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
| 87 |
+
|
| 88 |
+
if len(ckpt_files) == 0:
|
| 89 |
+
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
| 90 |
+
|
| 91 |
+
return ckpt_files
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
def get_optim_files(checkpoint_dir):
|
| 95 |
+
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
def get_model_state_files(checkpoint_dir):
|
| 99 |
+
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
| 100 |
+
|
| 101 |
+
|
| 102 |
+
def parse_model_states(files):
|
| 103 |
+
zero_model_states = []
|
| 104 |
+
for file in files:
|
| 105 |
+
state_dict = torch.load(file, map_location=device, weights_only=False)
|
| 106 |
+
|
| 107 |
+
if BUFFER_NAMES not in state_dict:
|
| 108 |
+
raise ValueError(f"{file} is not a model state checkpoint")
|
| 109 |
+
buffer_names = state_dict[BUFFER_NAMES]
|
| 110 |
+
if debug:
|
| 111 |
+
print("Found buffers:", buffer_names)
|
| 112 |
+
|
| 113 |
+
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
| 114 |
+
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
| 115 |
+
param_shapes = state_dict[PARAM_SHAPES]
|
| 116 |
+
|
| 117 |
+
# collect parameters that are included in param_shapes
|
| 118 |
+
param_names = []
|
| 119 |
+
for s in param_shapes:
|
| 120 |
+
for name in s.keys():
|
| 121 |
+
param_names.append(name)
|
| 122 |
+
|
| 123 |
+
# update with frozen parameters
|
| 124 |
+
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
| 125 |
+
if frozen_param_shapes is not None:
|
| 126 |
+
if debug:
|
| 127 |
+
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
| 128 |
+
param_names += list(frozen_param_shapes.keys())
|
| 129 |
+
|
| 130 |
+
# handle shared params
|
| 131 |
+
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
| 132 |
+
|
| 133 |
+
ds_version = state_dict.get(DS_VERSION, None)
|
| 134 |
+
|
| 135 |
+
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
| 136 |
+
|
| 137 |
+
z_model_state = zero_model_state(buffers=buffers,
|
| 138 |
+
param_shapes=param_shapes,
|
| 139 |
+
shared_params=shared_params,
|
| 140 |
+
ds_version=ds_version,
|
| 141 |
+
frozen_param_shapes=frozen_param_shapes,
|
| 142 |
+
frozen_param_fragments=frozen_param_fragments)
|
| 143 |
+
zero_model_states.append(z_model_state)
|
| 144 |
+
|
| 145 |
+
return zero_model_states
|
| 146 |
+
|
| 147 |
+
|
| 148 |
+
def parse_optim_states(files, ds_checkpoint_dir):
|
| 149 |
+
total_files = len(files)
|
| 150 |
+
state_dicts = []
|
| 151 |
+
for f in tqdm(files, desc='Loading checkpoint shards'):
|
| 152 |
+
state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
|
| 153 |
+
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
| 154 |
+
# and also handle the case where it was already removed by another helper script
|
| 155 |
+
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
| 156 |
+
state_dicts.append(state_dict)
|
| 157 |
+
|
| 158 |
+
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
| 159 |
+
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
| 160 |
+
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
| 161 |
+
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
| 162 |
+
|
| 163 |
+
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
| 164 |
+
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
| 165 |
+
# use the max of the partition_count to get the dp world_size.
|
| 166 |
+
|
| 167 |
+
if type(world_size) is list:
|
| 168 |
+
world_size = max(world_size)
|
| 169 |
+
|
| 170 |
+
if world_size != total_files:
|
| 171 |
+
raise ValueError(
|
| 172 |
+
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
| 173 |
+
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
| 174 |
+
)
|
| 175 |
+
|
| 176 |
+
# the groups are named differently in each stage
|
| 177 |
+
if zero_stage <= 2:
|
| 178 |
+
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
| 179 |
+
elif zero_stage == 3:
|
| 180 |
+
fp32_groups_key = FP32_FLAT_GROUPS
|
| 181 |
+
else:
|
| 182 |
+
raise ValueError(f"unknown zero stage {zero_stage}")
|
| 183 |
+
|
| 184 |
+
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
| 185 |
+
return zero_stage, world_size, fp32_flat_groups
|
| 186 |
+
|
| 187 |
+
|
| 188 |
+
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
| 189 |
+
"""
|
| 190 |
+
Returns fp32 state_dict reconstructed from ds checkpoint
|
| 191 |
+
|
| 192 |
+
Args:
|
| 193 |
+
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
| 194 |
+
|
| 195 |
+
"""
|
| 196 |
+
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
| 197 |
+
|
| 198 |
+
optim_files = get_optim_files(ds_checkpoint_dir)
|
| 199 |
+
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
| 200 |
+
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
| 201 |
+
|
| 202 |
+
model_files = get_model_state_files(ds_checkpoint_dir)
|
| 203 |
+
|
| 204 |
+
zero_model_states = parse_model_states(model_files)
|
| 205 |
+
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
| 206 |
+
|
| 207 |
+
if zero_stage <= 2:
|
| 208 |
+
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 209 |
+
exclude_frozen_parameters)
|
| 210 |
+
elif zero_stage == 3:
|
| 211 |
+
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 212 |
+
exclude_frozen_parameters)
|
| 213 |
+
|
| 214 |
+
|
| 215 |
+
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
| 216 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 217 |
+
return
|
| 218 |
+
|
| 219 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 220 |
+
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
| 221 |
+
|
| 222 |
+
if debug:
|
| 223 |
+
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
| 224 |
+
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 225 |
+
|
| 226 |
+
wanted_params = len(frozen_param_shapes)
|
| 227 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 228 |
+
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
| 229 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 230 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 231 |
+
|
| 232 |
+
total_params = 0
|
| 233 |
+
total_numel = 0
|
| 234 |
+
for name, shape in frozen_param_shapes.items():
|
| 235 |
+
total_params += 1
|
| 236 |
+
unpartitioned_numel = shape.numel()
|
| 237 |
+
total_numel += unpartitioned_numel
|
| 238 |
+
|
| 239 |
+
state_dict[name] = frozen_param_fragments[name]
|
| 240 |
+
|
| 241 |
+
if debug:
|
| 242 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 243 |
+
|
| 244 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 245 |
+
|
| 246 |
+
|
| 247 |
+
def _has_callable(obj, fn):
|
| 248 |
+
attr = getattr(obj, fn, None)
|
| 249 |
+
return callable(attr)
|
| 250 |
+
|
| 251 |
+
|
| 252 |
+
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 253 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 254 |
+
|
| 255 |
+
# Reconstruction protocol:
|
| 256 |
+
#
|
| 257 |
+
# XXX: document this
|
| 258 |
+
|
| 259 |
+
if debug:
|
| 260 |
+
for i in range(world_size):
|
| 261 |
+
for j in range(len(fp32_flat_groups[0])):
|
| 262 |
+
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
| 263 |
+
|
| 264 |
+
# XXX: memory usage doubles here (zero2)
|
| 265 |
+
num_param_groups = len(fp32_flat_groups[0])
|
| 266 |
+
merged_single_partition_of_fp32_groups = []
|
| 267 |
+
for i in range(num_param_groups):
|
| 268 |
+
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
| 269 |
+
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
| 270 |
+
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
| 271 |
+
avail_numel = sum(
|
| 272 |
+
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
| 273 |
+
|
| 274 |
+
if debug:
|
| 275 |
+
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
| 276 |
+
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
| 277 |
+
# not asserting if there is a mismatch due to possible padding
|
| 278 |
+
print(f"Have {avail_numel} numels to process.")
|
| 279 |
+
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
| 280 |
+
|
| 281 |
+
# params
|
| 282 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 283 |
+
# out-of-core computing solution
|
| 284 |
+
total_numel = 0
|
| 285 |
+
total_params = 0
|
| 286 |
+
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
| 287 |
+
offset = 0
|
| 288 |
+
avail_numel = full_single_fp32_vector.numel()
|
| 289 |
+
for name, shape in shapes.items():
|
| 290 |
+
|
| 291 |
+
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
| 292 |
+
total_numel += unpartitioned_numel
|
| 293 |
+
total_params += 1
|
| 294 |
+
|
| 295 |
+
if debug:
|
| 296 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 297 |
+
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
| 298 |
+
offset += unpartitioned_numel
|
| 299 |
+
|
| 300 |
+
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
| 301 |
+
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
| 302 |
+
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
| 303 |
+
# live optimizer object, so we are checking that the numbers are within the right range
|
| 304 |
+
align_to = 2 * world_size
|
| 305 |
+
|
| 306 |
+
def zero2_align(x):
|
| 307 |
+
return align_to * math.ceil(x / align_to)
|
| 308 |
+
|
| 309 |
+
if debug:
|
| 310 |
+
print(f"original offset={offset}, avail_numel={avail_numel}")
|
| 311 |
+
|
| 312 |
+
offset = zero2_align(offset)
|
| 313 |
+
avail_numel = zero2_align(avail_numel)
|
| 314 |
+
|
| 315 |
+
if debug:
|
| 316 |
+
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
| 317 |
+
|
| 318 |
+
# Sanity check
|
| 319 |
+
if offset != avail_numel:
|
| 320 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 321 |
+
|
| 322 |
+
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
| 323 |
+
|
| 324 |
+
|
| 325 |
+
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 326 |
+
exclude_frozen_parameters):
|
| 327 |
+
state_dict = OrderedDict()
|
| 328 |
+
|
| 329 |
+
# buffers
|
| 330 |
+
buffers = zero_model_states[0].buffers
|
| 331 |
+
state_dict.update(buffers)
|
| 332 |
+
if debug:
|
| 333 |
+
print(f"added {len(buffers)} buffers")
|
| 334 |
+
|
| 335 |
+
if not exclude_frozen_parameters:
|
| 336 |
+
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
| 337 |
+
|
| 338 |
+
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 339 |
+
|
| 340 |
+
# recover shared parameters
|
| 341 |
+
for pair in zero_model_states[0].shared_params:
|
| 342 |
+
if pair[1] in state_dict:
|
| 343 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 344 |
+
|
| 345 |
+
return state_dict
|
| 346 |
+
|
| 347 |
+
|
| 348 |
+
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
| 349 |
+
remainder = unpartitioned_numel % world_size
|
| 350 |
+
padding_numel = (world_size - remainder) if remainder else 0
|
| 351 |
+
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
| 352 |
+
return partitioned_numel, padding_numel
|
| 353 |
+
|
| 354 |
+
|
| 355 |
+
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
| 356 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 357 |
+
return
|
| 358 |
+
|
| 359 |
+
if debug:
|
| 360 |
+
for i in range(world_size):
|
| 361 |
+
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
| 362 |
+
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 363 |
+
|
| 364 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 365 |
+
wanted_params = len(frozen_param_shapes)
|
| 366 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 367 |
+
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
| 368 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 369 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 370 |
+
|
| 371 |
+
total_params = 0
|
| 372 |
+
total_numel = 0
|
| 373 |
+
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
| 374 |
+
total_params += 1
|
| 375 |
+
unpartitioned_numel = shape.numel()
|
| 376 |
+
total_numel += unpartitioned_numel
|
| 377 |
+
|
| 378 |
+
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
| 379 |
+
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 380 |
+
|
| 381 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 382 |
+
|
| 383 |
+
if debug:
|
| 384 |
+
print(
|
| 385 |
+
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 386 |
+
)
|
| 387 |
+
|
| 388 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 389 |
+
|
| 390 |
+
|
| 391 |
+
class GatheredTensor:
|
| 392 |
+
"""
|
| 393 |
+
A pseudo tensor that collects partitioned weights.
|
| 394 |
+
It is more memory efficient when there are multiple groups.
|
| 395 |
+
"""
|
| 396 |
+
|
| 397 |
+
def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
|
| 398 |
+
self.flat_groups = flat_groups
|
| 399 |
+
self.flat_groups_offset = flat_groups_offset
|
| 400 |
+
self.offset = offset
|
| 401 |
+
self.partitioned_numel = partitioned_numel
|
| 402 |
+
self.shape = shape
|
| 403 |
+
self.dtype = self.flat_groups[0][0].dtype
|
| 404 |
+
|
| 405 |
+
def contiguous(self):
|
| 406 |
+
"""
|
| 407 |
+
Merge partitioned weights from flat_groups into a single tensor.
|
| 408 |
+
"""
|
| 409 |
+
end_idx = self.offset + self.partitioned_numel
|
| 410 |
+
world_size = len(self.flat_groups)
|
| 411 |
+
pad_flat_param_chunks = []
|
| 412 |
+
|
| 413 |
+
for rank_i in range(world_size):
|
| 414 |
+
# for each rank, we need to collect weights from related group/groups
|
| 415 |
+
flat_groups_at_rank_i = self.flat_groups[rank_i]
|
| 416 |
+
start_group_id = None
|
| 417 |
+
end_group_id = None
|
| 418 |
+
for group_id in range(len(self.flat_groups_offset)):
|
| 419 |
+
if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
|
| 420 |
+
start_group_id = group_id
|
| 421 |
+
if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
|
| 422 |
+
end_group_id = group_id
|
| 423 |
+
break
|
| 424 |
+
# collect weights from related group/groups
|
| 425 |
+
for group_id in range(start_group_id, end_group_id + 1):
|
| 426 |
+
flat_tensor = flat_groups_at_rank_i[group_id]
|
| 427 |
+
start_offset = self.offset - self.flat_groups_offset[group_id]
|
| 428 |
+
end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
|
| 429 |
+
pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
|
| 430 |
+
|
| 431 |
+
# collect weights from all ranks
|
| 432 |
+
pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
|
| 433 |
+
param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
|
| 434 |
+
return param
|
| 435 |
+
|
| 436 |
+
|
| 437 |
+
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 438 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 439 |
+
avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
|
| 440 |
+
|
| 441 |
+
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
| 442 |
+
# param, re-consolidating each param, while dealing with padding if any
|
| 443 |
+
|
| 444 |
+
# merge list of dicts, preserving order
|
| 445 |
+
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
| 446 |
+
|
| 447 |
+
if debug:
|
| 448 |
+
for i in range(world_size):
|
| 449 |
+
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
| 450 |
+
|
| 451 |
+
wanted_params = len(param_shapes)
|
| 452 |
+
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
| 453 |
+
# not asserting if there is a mismatch due to possible padding
|
| 454 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 455 |
+
print(f"Trainable params: Have {avail_numel} numels to process.")
|
| 456 |
+
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
| 457 |
+
|
| 458 |
+
# params
|
| 459 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 460 |
+
# out-of-core computing solution
|
| 461 |
+
offset = 0
|
| 462 |
+
total_numel = 0
|
| 463 |
+
total_params = 0
|
| 464 |
+
flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
|
| 465 |
+
for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
|
| 466 |
+
unpartitioned_numel = shape.numel()
|
| 467 |
+
total_numel += unpartitioned_numel
|
| 468 |
+
total_params += 1
|
| 469 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 470 |
+
|
| 471 |
+
if debug:
|
| 472 |
+
print(
|
| 473 |
+
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 474 |
+
)
|
| 475 |
+
|
| 476 |
+
# memory efficient tensor
|
| 477 |
+
tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
|
| 478 |
+
state_dict[name] = tensor
|
| 479 |
+
offset += partitioned_numel
|
| 480 |
+
|
| 481 |
+
offset *= world_size
|
| 482 |
+
|
| 483 |
+
# Sanity check
|
| 484 |
+
if offset != avail_numel:
|
| 485 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 486 |
+
|
| 487 |
+
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
| 488 |
+
|
| 489 |
+
|
| 490 |
+
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 491 |
+
exclude_frozen_parameters):
|
| 492 |
+
state_dict = OrderedDict()
|
| 493 |
+
|
| 494 |
+
# buffers
|
| 495 |
+
buffers = zero_model_states[0].buffers
|
| 496 |
+
state_dict.update(buffers)
|
| 497 |
+
if debug:
|
| 498 |
+
print(f"added {len(buffers)} buffers")
|
| 499 |
+
|
| 500 |
+
if not exclude_frozen_parameters:
|
| 501 |
+
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
| 502 |
+
|
| 503 |
+
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 504 |
+
|
| 505 |
+
# recover shared parameters
|
| 506 |
+
for pair in zero_model_states[0].shared_params:
|
| 507 |
+
if pair[1] in state_dict:
|
| 508 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 509 |
+
|
| 510 |
+
return state_dict
|
| 511 |
+
|
| 512 |
+
|
| 513 |
+
def to_torch_tensor(state_dict, return_empty_tensor=False):
|
| 514 |
+
"""
|
| 515 |
+
Convert state_dict of GatheredTensor to torch tensor
|
| 516 |
+
"""
|
| 517 |
+
torch_state_dict = {}
|
| 518 |
+
converted_tensors = {}
|
| 519 |
+
for name, tensor in state_dict.items():
|
| 520 |
+
tensor_id = id(tensor)
|
| 521 |
+
if tensor_id in converted_tensors: # shared tensors
|
| 522 |
+
shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
|
| 523 |
+
torch_state_dict[name] = shared_tensor
|
| 524 |
+
else:
|
| 525 |
+
converted_tensors[tensor_id] = name
|
| 526 |
+
if return_empty_tensor:
|
| 527 |
+
torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
|
| 528 |
+
else:
|
| 529 |
+
torch_state_dict[name] = tensor.contiguous()
|
| 530 |
+
return torch_state_dict
|
| 531 |
+
|
| 532 |
+
|
| 533 |
+
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
| 534 |
+
tag=None,
|
| 535 |
+
exclude_frozen_parameters=False,
|
| 536 |
+
lazy_mode=False):
|
| 537 |
+
"""
|
| 538 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
| 539 |
+
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
| 540 |
+
via a model hub.
|
| 541 |
+
|
| 542 |
+
Args:
|
| 543 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder
|
| 544 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
| 545 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 546 |
+
- ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
|
| 547 |
+
Convert the pesduo tensor to torch tensor by ``.contiguous()``
|
| 548 |
+
|
| 549 |
+
Returns:
|
| 550 |
+
- pytorch ``state_dict``
|
| 551 |
+
|
| 552 |
+
A typical usage might be ::
|
| 553 |
+
|
| 554 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 555 |
+
# do the training and checkpoint saving
|
| 556 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
| 557 |
+
model = model.cpu() # move to cpu
|
| 558 |
+
model.load_state_dict(state_dict)
|
| 559 |
+
# submit to model hub or save the model to share with others
|
| 560 |
+
|
| 561 |
+
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
| 562 |
+
application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 563 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 564 |
+
|
| 565 |
+
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
| 566 |
+
|
| 567 |
+
Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
|
| 568 |
+
You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
| 569 |
+
the checkpoint. Or you can load state_dict in lazy mode ::
|
| 570 |
+
|
| 571 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 572 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
|
| 573 |
+
for name, lazy_tensor in state_dict.item():
|
| 574 |
+
tensor = lazy_tensor.contiguous() # to cpu
|
| 575 |
+
print(name, tensor)
|
| 576 |
+
# del tensor to release memory if it no longer in use
|
| 577 |
+
"""
|
| 578 |
+
if tag is None:
|
| 579 |
+
latest_path = os.path.join(checkpoint_dir, 'latest')
|
| 580 |
+
if os.path.isfile(latest_path):
|
| 581 |
+
with open(latest_path, 'r') as fd:
|
| 582 |
+
tag = fd.read().strip()
|
| 583 |
+
else:
|
| 584 |
+
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
| 585 |
+
|
| 586 |
+
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
| 587 |
+
|
| 588 |
+
if not os.path.isdir(ds_checkpoint_dir):
|
| 589 |
+
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
| 590 |
+
|
| 591 |
+
state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
| 592 |
+
if lazy_mode:
|
| 593 |
+
return state_dict
|
| 594 |
+
else:
|
| 595 |
+
return to_torch_tensor(state_dict)
|
| 596 |
+
|
| 597 |
+
|
| 598 |
+
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
|
| 599 |
+
output_dir,
|
| 600 |
+
max_shard_size="5GB",
|
| 601 |
+
safe_serialization=False,
|
| 602 |
+
tag=None,
|
| 603 |
+
exclude_frozen_parameters=False):
|
| 604 |
+
"""
|
| 605 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
| 606 |
+
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
| 607 |
+
|
| 608 |
+
Args:
|
| 609 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 610 |
+
- ``output_dir``: directory to the pytorch fp32 state_dict output files
|
| 611 |
+
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
|
| 612 |
+
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
|
| 613 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 614 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 615 |
+
"""
|
| 616 |
+
|
| 617 |
+
# Dependency pre-check
|
| 618 |
+
if safe_serialization:
|
| 619 |
+
try:
|
| 620 |
+
from safetensors.torch import save_file
|
| 621 |
+
except ImportError:
|
| 622 |
+
print('If you want to use `safe_serialization`, please `pip install safetensors`')
|
| 623 |
+
raise
|
| 624 |
+
if max_shard_size is not None:
|
| 625 |
+
try:
|
| 626 |
+
from huggingface_hub import split_torch_state_dict_into_shards
|
| 627 |
+
except ImportError:
|
| 628 |
+
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
|
| 629 |
+
raise
|
| 630 |
+
|
| 631 |
+
# Convert zero checkpoint to state_dict
|
| 632 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
| 633 |
+
tag,
|
| 634 |
+
exclude_frozen_parameters,
|
| 635 |
+
lazy_mode=True)
|
| 636 |
+
|
| 637 |
+
# Shard the model if it is too big.
|
| 638 |
+
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
|
| 639 |
+
if max_shard_size is not None:
|
| 640 |
+
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
|
| 641 |
+
# an memory-efficient approach for sharding
|
| 642 |
+
empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
|
| 643 |
+
state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
|
| 644 |
+
filename_pattern=filename_pattern,
|
| 645 |
+
max_shard_size=max_shard_size)
|
| 646 |
+
else:
|
| 647 |
+
from collections import namedtuple
|
| 648 |
+
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
|
| 649 |
+
state_dict_split = StateDictSplit(is_sharded=False,
|
| 650 |
+
filename_to_tensors={weights_name: list(state_dict.keys())})
|
| 651 |
+
|
| 652 |
+
# Save the model by shard
|
| 653 |
+
os.makedirs(output_dir, exist_ok=True)
|
| 654 |
+
filename_to_tensors = state_dict_split.filename_to_tensors.items()
|
| 655 |
+
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
|
| 656 |
+
shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
|
| 657 |
+
shard_state_dict = to_torch_tensor(shard_state_dict)
|
| 658 |
+
output_path = os.path.join(output_dir, shard_file)
|
| 659 |
+
if safe_serialization:
|
| 660 |
+
save_file(shard_state_dict, output_path, metadata={"format": "pt"})
|
| 661 |
+
else:
|
| 662 |
+
torch.save(shard_state_dict, output_path)
|
| 663 |
+
# release the memory of current shard
|
| 664 |
+
for tensor_name in list(shard_state_dict.keys()):
|
| 665 |
+
del state_dict[tensor_name]
|
| 666 |
+
del shard_state_dict[tensor_name]
|
| 667 |
+
del shard_state_dict
|
| 668 |
+
gc.collect()
|
| 669 |
+
|
| 670 |
+
# Save index if sharded
|
| 671 |
+
if state_dict_split.is_sharded:
|
| 672 |
+
index = {
|
| 673 |
+
"metadata": state_dict_split.metadata,
|
| 674 |
+
"weight_map": state_dict_split.tensor_to_filename,
|
| 675 |
+
}
|
| 676 |
+
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
|
| 677 |
+
save_index_file = os.path.join(output_dir, save_index_file)
|
| 678 |
+
with open(save_index_file, "w", encoding="utf-8") as f:
|
| 679 |
+
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
|
| 680 |
+
f.write(content)
|
| 681 |
+
|
| 682 |
+
|
| 683 |
+
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
| 684 |
+
"""
|
| 685 |
+
1. Put the provided model to cpu
|
| 686 |
+
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
| 687 |
+
3. Load it into the provided model
|
| 688 |
+
|
| 689 |
+
Args:
|
| 690 |
+
- ``model``: the model object to update
|
| 691 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 692 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 693 |
+
|
| 694 |
+
Returns:
|
| 695 |
+
- ``model`: modified model
|
| 696 |
+
|
| 697 |
+
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
| 698 |
+
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
| 699 |
+
conveniently placed for you in the checkpoint folder.
|
| 700 |
+
|
| 701 |
+
A typical usage might be ::
|
| 702 |
+
|
| 703 |
+
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
| 704 |
+
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
| 705 |
+
# submit to model hub or save the model to share with others
|
| 706 |
+
|
| 707 |
+
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
| 708 |
+
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 709 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 710 |
+
|
| 711 |
+
"""
|
| 712 |
+
logger.info(f"Extracting fp32 weights")
|
| 713 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
| 714 |
+
|
| 715 |
+
logger.info(f"Overwriting model with fp32 weights")
|
| 716 |
+
model = model.cpu()
|
| 717 |
+
model.load_state_dict(state_dict, strict=False)
|
| 718 |
+
|
| 719 |
+
return model
|
| 720 |
+
|
| 721 |
+
|
| 722 |
+
if __name__ == "__main__":
|
| 723 |
+
parser = argparse.ArgumentParser()
|
| 724 |
+
parser.add_argument("checkpoint_dir",
|
| 725 |
+
type=str,
|
| 726 |
+
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
| 727 |
+
parser.add_argument("output_dir",
|
| 728 |
+
type=str,
|
| 729 |
+
help="directory to the pytorch fp32 state_dict output files"
|
| 730 |
+
"(e.g. path/checkpoint-12-output/)")
|
| 731 |
+
parser.add_argument(
|
| 732 |
+
"--max_shard_size",
|
| 733 |
+
type=str,
|
| 734 |
+
default="5GB",
|
| 735 |
+
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
|
| 736 |
+
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
|
| 737 |
+
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
|
| 738 |
+
"without CPU OOM issues.")
|
| 739 |
+
parser.add_argument(
|
| 740 |
+
"--safe_serialization",
|
| 741 |
+
default=False,
|
| 742 |
+
action='store_true',
|
| 743 |
+
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
|
| 744 |
+
parser.add_argument("-t",
|
| 745 |
+
"--tag",
|
| 746 |
+
type=str,
|
| 747 |
+
default=None,
|
| 748 |
+
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
| 749 |
+
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
| 750 |
+
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
| 751 |
+
args = parser.parse_args()
|
| 752 |
+
|
| 753 |
+
debug = args.debug
|
| 754 |
+
|
| 755 |
+
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
| 756 |
+
args.output_dir,
|
| 757 |
+
max_shard_size=args.max_shard_size,
|
| 758 |
+
safe_serialization=args.safe_serialization,
|
| 759 |
+
tag=args.tag,
|
| 760 |
+
exclude_frozen_parameters=args.exclude_frozen_parameters)
|
model_with_lora.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:830f83e72fe36f7ff3d8bf55e01c32865e5896e81178c4534025e3bc874d2540
|
| 3 |
+
size 16628075734
|
runs/Mar07_05-23-18_886823f2c465/events.out.tfevents.1741292890.886823f2c465.10378.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d526448c8130aefc200b80307fa29a6c36ab46d9b699497cbdfe7e93a19cc83d
|
| 3 |
+
size 216297
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|