Training in progress, step 100, checkpoint
Browse files
checkpoint-100/README.md
CHANGED
@@ -216,23 +216,4 @@ The following `bitsandbytes` quantization config was used during training:
|
|
216 |
### Framework versions
|
217 |
|
218 |
|
219 |
-
- PEFT 0.6.0
|
220 |
-
## Training procedure
|
221 |
-
|
222 |
-
|
223 |
-
The following `bitsandbytes` quantization config was used during training:
|
224 |
-
- quant_method: bitsandbytes
|
225 |
-
- load_in_8bit: True
|
226 |
-
- load_in_4bit: False
|
227 |
-
- llm_int8_threshold: 6.0
|
228 |
-
- llm_int8_skip_modules: None
|
229 |
-
- llm_int8_enable_fp32_cpu_offload: False
|
230 |
-
- llm_int8_has_fp16_weight: False
|
231 |
-
- bnb_4bit_quant_type: fp4
|
232 |
-
- bnb_4bit_use_double_quant: False
|
233 |
-
- bnb_4bit_compute_dtype: float32
|
234 |
-
|
235 |
-
### Framework versions
|
236 |
-
|
237 |
-
|
238 |
- PEFT 0.6.0
|
|
|
216 |
### Framework versions
|
217 |
|
218 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
219 |
- PEFT 0.6.0
|
checkpoint-100/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 19690328
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:000dc7d0ce415506cab1bc16a924e9f571a8654a59fc93738391172452ea4c3c
|
3 |
size 19690328
|
checkpoint-100/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 38087098
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4383251af30d9e76da27a87247597404a99e4be107cf50a72a6468bc8c2c7df
|
3 |
size 38087098
|
checkpoint-100/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0020b01940f228a27d15c3af0767261afe5592374867c6ea1bd6ab09eb367a7
|
3 |
size 14244
|
checkpoint-100/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 sha256:7a87497ca1089aecb14a3768b8548fe31ee577bf4d24022b5a7a8ee8498329b0
|
3 |
size 1064
|
checkpoint-100/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
"best_model_checkpoint": "output/checkpoint-100",
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 50,
|
6 |
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
@@ -9,47 +9,47 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0.
|
13 |
-
"learning_rate":
|
14 |
-
"loss":
|
15 |
"step": 1
|
16 |
},
|
17 |
{
|
18 |
-
"epoch": 0.
|
19 |
-
"learning_rate":
|
20 |
-
"loss":
|
21 |
"step": 50
|
22 |
},
|
23 |
{
|
24 |
-
"epoch": 0.
|
25 |
-
"eval_accuracy": 0.
|
26 |
-
"eval_loss":
|
27 |
-
"eval_runtime": 28.
|
28 |
-
"eval_samples_per_second": 6.
|
29 |
-
"eval_steps_per_second": 1.
|
30 |
"step": 50
|
31 |
},
|
32 |
{
|
33 |
-
"epoch": 0.
|
34 |
-
"learning_rate": 2.
|
35 |
-
"loss":
|
36 |
"step": 100
|
37 |
},
|
38 |
{
|
39 |
-
"epoch": 0.
|
40 |
-
"eval_accuracy": 0.
|
41 |
-
"eval_loss":
|
42 |
-
"eval_runtime":
|
43 |
-
"eval_samples_per_second": 6.
|
44 |
-
"eval_steps_per_second": 1.
|
45 |
"step": 100
|
46 |
}
|
47 |
],
|
48 |
"logging_steps": 50,
|
49 |
-
"max_steps":
|
50 |
-
"num_train_epochs":
|
51 |
"save_steps": 50,
|
52 |
-
"total_flos": 3.
|
53 |
"trial_name": null,
|
54 |
"trial_params": null
|
55 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.49068325757980347,
|
3 |
"best_model_checkpoint": "output/checkpoint-100",
|
4 |
+
"epoch": 0.08021658477890303,
|
5 |
"eval_steps": 50,
|
6 |
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 0.0,
|
14 |
+
"loss": 1.6453,
|
15 |
"step": 1
|
16 |
},
|
17 |
{
|
18 |
+
"epoch": 0.04,
|
19 |
+
"learning_rate": 9.777777777777779e-06,
|
20 |
+
"loss": 1.3216,
|
21 |
"step": 50
|
22 |
},
|
23 |
{
|
24 |
+
"epoch": 0.04,
|
25 |
+
"eval_accuracy": 0.8057142857142857,
|
26 |
+
"eval_loss": 0.6264824271202087,
|
27 |
+
"eval_runtime": 28.8159,
|
28 |
+
"eval_samples_per_second": 6.073,
|
29 |
+
"eval_steps_per_second": 1.527,
|
30 |
"step": 50
|
31 |
},
|
32 |
{
|
33 |
+
"epoch": 0.08,
|
34 |
+
"learning_rate": 2.088888888888889e-05,
|
35 |
+
"loss": 0.918,
|
36 |
"step": 100
|
37 |
},
|
38 |
{
|
39 |
+
"epoch": 0.08,
|
40 |
+
"eval_accuracy": 0.7885714285714286,
|
41 |
+
"eval_loss": 0.49068325757980347,
|
42 |
+
"eval_runtime": 26.1642,
|
43 |
+
"eval_samples_per_second": 6.689,
|
44 |
+
"eval_steps_per_second": 1.682,
|
45 |
"step": 100
|
46 |
}
|
47 |
],
|
48 |
"logging_steps": 50,
|
49 |
+
"max_steps": 1246,
|
50 |
+
"num_train_epochs": 1,
|
51 |
"save_steps": 50,
|
52 |
+
"total_flos": 3.690320903467008e+16,
|
53 |
"trial_name": null,
|
54 |
"trial_params": null
|
55 |
}
|
checkpoint-100/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4600
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b7c1677f66b49d74d914a320393e2fa29530a9670d5824a30beac9590468d16
|
3 |
size 4600
|