Training in progress, step 1201, checkpoint
Browse files- last-checkpoint/adapter_config.json +1 -1
- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/global_step1201/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step1201/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step1201/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step1201/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step1201/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
- last-checkpoint/global_step1201/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
- last-checkpoint/global_step1201/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
- last-checkpoint/global_step1201/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
- last-checkpoint/latest +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +7 -7
- last-checkpoint/training_args.bin +2 -2
last-checkpoint/adapter_config.json
CHANGED
@@ -19,7 +19,7 @@
|
|
19 |
"r": 8,
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
-
"target_modules": "^(?!.*patch_embed).*(?:
|
23 |
"task_type": "CAUSAL_LM",
|
24 |
"use_dora": false,
|
25 |
"use_rslora": false
|
|
|
19 |
"r": 8,
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
+
"target_modules": "^(?!.*patch_embed).*(?:gate_proj|qkv|q_proj|fc1|fc2|up_proj|v_proj|down_proj|k_proj|proj|o_proj).*",
|
23 |
"task_type": "CAUSAL_LM",
|
24 |
"use_dora": false,
|
25 |
"use_rslora": false
|
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 29034840
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8ee2634589442880539cea4215aeae5e195f22dea93b6441497472981b36691
|
3 |
size 29034840
|
last-checkpoint/global_step1201/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 sha256:7f2e82372caf676c0b0a5d6293d69692257dd9d7feba954d3cf78ff2a70ae83a
|
3 |
+
size 43429616
|
last-checkpoint/global_step1201/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 sha256:3dcab03ce19f2ce79a8d53b6ae3f4ac03ac0016d02e59b794c7273852dc5ea6b
|
3 |
+
size 43429616
|
last-checkpoint/global_step1201/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:041435127598402c8acd20dc5a7396b5a683309f402f68fd38fcfe3757dca0d3
|
3 |
+
size 43429616
|
last-checkpoint/global_step1201/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e27d0cc4e7dc7fd4de69c4b1bdcc21d5c4137e83ab060e88c385c55ec12dd8d7
|
3 |
+
size 43429616
|
last-checkpoint/global_step1201/zero_pp_rank_0_mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2075f75ba9a6a574ce7120222ba9095b5c8eb216d857b0767671c01fbc074e7e
|
3 |
+
size 637299
|
last-checkpoint/global_step1201/zero_pp_rank_1_mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6935f4971e1fcb55db5d1f64ef46b459823eff82ade7deff0a5a993f4583bfa7
|
3 |
+
size 637171
|
last-checkpoint/global_step1201/zero_pp_rank_2_mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f9f8f66781db0d1a0637d1dd44b041752fe0978d10f864754f9f8493ed63704
|
3 |
+
size 637171
|
last-checkpoint/global_step1201/zero_pp_rank_3_mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:872a5c568bb2f8cccc429cc5283d43928998853b7318c61f3218fc4c7ef8335f
|
3 |
+
size 637171
|
last-checkpoint/latest
CHANGED
@@ -1 +1 @@
|
|
1 |
-
|
|
|
1 |
+
global_step1201
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3cb88c2bb06d05128047dc279e5c6aaaceeada9fc352a92b1e5300def3533252
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 1.5566551155643538e-05,
|
3 |
"best_model_checkpoint": "saves/CADICA_qwenvl_direction_scale4/lora/sft/checkpoint-1150",
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 50,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -2146,9 +2146,9 @@
|
|
2146 |
}
|
2147 |
],
|
2148 |
"logging_steps": 5,
|
2149 |
-
"max_steps":
|
2150 |
-
"num_input_tokens_seen":
|
2151 |
-
"num_train_epochs":
|
2152 |
"save_steps": 50,
|
2153 |
"stateful_callbacks": {
|
2154 |
"TrainerControl": {
|
@@ -2157,12 +2157,12 @@
|
|
2157 |
"should_evaluate": false,
|
2158 |
"should_log": false,
|
2159 |
"should_save": true,
|
2160 |
-
"should_training_stop":
|
2161 |
},
|
2162 |
"attributes": {}
|
2163 |
}
|
2164 |
},
|
2165 |
-
"total_flos":
|
2166 |
"train_batch_size": 1,
|
2167 |
"trial_name": null,
|
2168 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 1.5566551155643538e-05,
|
3 |
"best_model_checkpoint": "saves/CADICA_qwenvl_direction_scale4/lora/sft/checkpoint-1150",
|
4 |
+
"epoch": 0.6185938707185166,
|
5 |
"eval_steps": 50,
|
6 |
+
"global_step": 1201,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
2146 |
}
|
2147 |
],
|
2148 |
"logging_steps": 5,
|
2149 |
+
"max_steps": 1200,
|
2150 |
+
"num_input_tokens_seen": 11990784,
|
2151 |
+
"num_train_epochs": 1,
|
2152 |
"save_steps": 50,
|
2153 |
"stateful_callbacks": {
|
2154 |
"TrainerControl": {
|
|
|
2157 |
"should_evaluate": false,
|
2158 |
"should_log": false,
|
2159 |
"should_save": true,
|
2160 |
+
"should_training_stop": true
|
2161 |
},
|
2162 |
"attributes": {}
|
2163 |
}
|
2164 |
},
|
2165 |
+
"total_flos": 791107965943808.0,
|
2166 |
"train_batch_size": 1,
|
2167 |
"trial_name": null,
|
2168 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d805df10b9aa9257d71d396f9c297d6e4b0be2e8da8eecef0b7efe313a60a238
|
3 |
+
size 7416
|