Model save
Browse files- README.md +1 -3
- adapter_config.json +4 -4
- all_results.json +3 -3
- runs/Jul31_16-24-12_VM-146-67-centos/events.out.tfevents.1722414285.VM-146-67-centos.3350321.0 +3 -0
- train_results.json +3 -3
- trainer_state.json +4 -4
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -42,10 +42,8 @@ The following hyperparameters were used during training:
|
|
| 42 |
- eval_batch_size: 8
|
| 43 |
- seed: 42
|
| 44 |
- distributed_type: multi-GPU
|
| 45 |
-
- num_devices: 2
|
| 46 |
- gradient_accumulation_steps: 2
|
| 47 |
-
- total_train_batch_size:
|
| 48 |
-
- total_eval_batch_size: 16
|
| 49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
- lr_scheduler_type: cosine
|
| 51 |
- lr_scheduler_warmup_ratio: 0.1
|
|
|
|
| 42 |
- eval_batch_size: 8
|
| 43 |
- seed: 42
|
| 44 |
- distributed_type: multi-GPU
|
|
|
|
| 45 |
- gradient_accumulation_steps: 2
|
| 46 |
+
- total_train_batch_size: 8
|
|
|
|
| 47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
- lr_scheduler_type: cosine
|
| 49 |
- lr_scheduler_warmup_ratio: 0.1
|
adapter_config.json
CHANGED
|
@@ -21,12 +21,12 @@
|
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
"o_proj",
|
| 24 |
-
"k_proj",
|
| 25 |
-
"v_proj",
|
| 26 |
"q_proj",
|
| 27 |
-
"down_proj",
|
| 28 |
"gate_proj",
|
| 29 |
-
"
|
|
|
|
|
|
|
|
|
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
"o_proj",
|
|
|
|
|
|
|
| 24 |
"q_proj",
|
|
|
|
| 25 |
"gate_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
all_results.json
CHANGED
|
@@ -2,8 +2,8 @@
|
|
| 2 |
"epoch": 0.9836065573770492,
|
| 3 |
"total_flos": 2.0918103256858624e+16,
|
| 4 |
"train_loss": 0.0,
|
| 5 |
-
"train_runtime": 0.
|
| 6 |
"train_samples": 153,
|
| 7 |
-
"train_samples_per_second":
|
| 8 |
-
"train_steps_per_second":
|
| 9 |
}
|
|
|
|
| 2 |
"epoch": 0.9836065573770492,
|
| 3 |
"total_flos": 2.0918103256858624e+16,
|
| 4 |
"train_loss": 0.0,
|
| 5 |
+
"train_runtime": 0.1548,
|
| 6 |
"train_samples": 153,
|
| 7 |
+
"train_samples_per_second": 1576.031,
|
| 8 |
+
"train_steps_per_second": 193.774
|
| 9 |
}
|
runs/Jul31_16-24-12_VM-146-67-centos/events.out.tfevents.1722414285.VM-146-67-centos.3350321.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68cf4981bad21269c8d0ac4da5b2f21d83ba80a235af18b0a452cee0ccd7ba22
|
| 3 |
+
size 5290
|
train_results.json
CHANGED
|
@@ -2,8 +2,8 @@
|
|
| 2 |
"epoch": 0.9836065573770492,
|
| 3 |
"total_flos": 2.0918103256858624e+16,
|
| 4 |
"train_loss": 0.0,
|
| 5 |
-
"train_runtime": 0.
|
| 6 |
"train_samples": 153,
|
| 7 |
-
"train_samples_per_second":
|
| 8 |
-
"train_steps_per_second":
|
| 9 |
}
|
|
|
|
| 2 |
"epoch": 0.9836065573770492,
|
| 3 |
"total_flos": 2.0918103256858624e+16,
|
| 4 |
"train_loss": 0.0,
|
| 5 |
+
"train_runtime": 0.1548,
|
| 6 |
"train_samples": 153,
|
| 7 |
+
"train_samples_per_second": 1576.031,
|
| 8 |
+
"train_steps_per_second": 193.774
|
| 9 |
}
|
trainer_state.json
CHANGED
|
@@ -62,13 +62,13 @@
|
|
| 62 |
"step": 30,
|
| 63 |
"total_flos": 2.0918103256858624e+16,
|
| 64 |
"train_loss": 0.0,
|
| 65 |
-
"train_runtime": 0.
|
| 66 |
-
"train_samples_per_second":
|
| 67 |
-
"train_steps_per_second":
|
| 68 |
}
|
| 69 |
],
|
| 70 |
"logging_steps": 5,
|
| 71 |
-
"max_steps":
|
| 72 |
"num_input_tokens_seen": 0,
|
| 73 |
"num_train_epochs": 1,
|
| 74 |
"save_steps": 100,
|
|
|
|
| 62 |
"step": 30,
|
| 63 |
"total_flos": 2.0918103256858624e+16,
|
| 64 |
"train_loss": 0.0,
|
| 65 |
+
"train_runtime": 0.1548,
|
| 66 |
+
"train_samples_per_second": 1576.031,
|
| 67 |
+
"train_steps_per_second": 193.774
|
| 68 |
}
|
| 69 |
],
|
| 70 |
"logging_steps": 5,
|
| 71 |
+
"max_steps": 30,
|
| 72 |
"num_input_tokens_seen": 0,
|
| 73 |
"num_train_epochs": 1,
|
| 74 |
"save_steps": 100,
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:450f93ba028cf9ad2f9655b757053f5dd234fffe94c891e1f66ab309207c04d5
|
| 3 |
size 5240
|