Upload folder using huggingface_hub
Browse files- checkpoint-10/adapter_config.json +2 -2
- checkpoint-10/adapter_model.safetensors +1 -1
- checkpoint-10/optimizer.pt +1 -1
- checkpoint-10/rng_state_0.pth +2 -2
- checkpoint-10/rng_state_1.pth +2 -2
- checkpoint-10/rng_state_2.pth +1 -1
- checkpoint-10/rng_state_3.pth +1 -1
- checkpoint-10/trainer_state.json +8 -8
- checkpoint-10/training_args.bin +1 -1
- checkpoint-70/adapter_config.json +2 -2
- checkpoint-70/adapter_model.safetensors +1 -1
- checkpoint-70/optimizer.pt +1 -1
- checkpoint-70/rng_state_0.pth +2 -2
- checkpoint-70/rng_state_1.pth +2 -2
- checkpoint-70/scheduler.pt +1 -1
- checkpoint-70/trainer_state.json +50 -50
- checkpoint-70/training_args.bin +1 -1
- checkpoint-80/adapter_config.json +2 -2
- checkpoint-80/adapter_model.safetensors +1 -1
- checkpoint-80/optimizer.pt +1 -1
- checkpoint-80/rng_state_0.pth +2 -2
- checkpoint-80/rng_state_1.pth +2 -2
- checkpoint-80/scheduler.pt +1 -1
- checkpoint-80/trainer_state.json +59 -59
- checkpoint-80/training_args.bin +1 -1
checkpoint-10/adapter_config.json
CHANGED
@@ -19,9 +19,9 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"q_proj",
|
23 |
-
"k_proj",
|
24 |
"v_proj",
|
|
|
|
|
25 |
"o_proj"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM",
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
|
|
22 |
"v_proj",
|
23 |
+
"k_proj",
|
24 |
+
"q_proj",
|
25 |
"o_proj"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM",
|
checkpoint-10/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 436242776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:966422cb45a8382bac17cf41216e3afe2053cf607f2da94a632139fc2d0b8ba1
|
3 |
size 436242776
|
checkpoint-10/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 872568314
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c39dfe27d7776c478e77eeae50c2b4248bca4d11a6ea01c21c5e11a9171540f
|
3 |
size 872568314
|
checkpoint-10/rng_state_0.pth
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:aacc211f04d2987b22d9e98352791900880485b00e7ba542532f0ecec3bcdfef
|
3 |
+
size 15024
|
checkpoint-10/rng_state_1.pth
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:b8bd5fb280d3a476b13d48a02b0eab8ef08f847c3cfef1b578e294c9487bfbef
|
3 |
+
size 15024
|
checkpoint-10/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90bdd80721c9b7e7e4d190530444466ac19797a0256ba7d2392a13f02d9dfac0
|
3 |
size 15024
|
checkpoint-10/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:180162a870c99e232cbac92cffd2c1be442b364558d2437654326dbfd6a2c018
|
3 |
size 15024
|
checkpoint-10/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-100_batch_16_2024-03-01_ppid_7/checkpoint-10",
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 10,
|
6 |
"global_step": 10,
|
7 |
"is_hyper_param_search": false,
|
@@ -9,11 +9,11 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0.
|
13 |
-
"eval_loss": 0.
|
14 |
-
"eval_runtime":
|
15 |
-
"eval_samples_per_second":
|
16 |
-
"eval_steps_per_second": 0.
|
17 |
"step": 10
|
18 |
}
|
19 |
],
|
@@ -22,7 +22,7 @@
|
|
22 |
"num_input_tokens_seen": 0,
|
23 |
"num_train_epochs": 1,
|
24 |
"save_steps": 10,
|
25 |
-
"total_flos":
|
26 |
"train_batch_size": 16,
|
27 |
"trial_name": null,
|
28 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6292536854743958,
|
3 |
"best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-100_batch_16_2024-03-01_ppid_7/checkpoint-10",
|
4 |
+
"epoch": 0.09900990099009901,
|
5 |
"eval_steps": 10,
|
6 |
"global_step": 10,
|
7 |
"is_hyper_param_search": false,
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.1,
|
13 |
+
"eval_loss": 0.6292536854743958,
|
14 |
+
"eval_runtime": 93.2576,
|
15 |
+
"eval_samples_per_second": 30.743,
|
16 |
+
"eval_steps_per_second": 0.965,
|
17 |
"step": 10
|
18 |
}
|
19 |
],
|
|
|
22 |
"num_input_tokens_seen": 0,
|
23 |
"num_train_epochs": 1,
|
24 |
"save_steps": 10,
|
25 |
+
"total_flos": 9.033558328030003e+16,
|
26 |
"train_batch_size": 16,
|
27 |
"trial_name": null,
|
28 |
"trial_params": null
|
checkpoint-10/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daf4ca86cd3cb3688a488e999435cb5aec8a4b0702902c7de81df751b2180e05
|
3 |
size 5176
|
checkpoint-70/adapter_config.json
CHANGED
@@ -20,9 +20,9 @@
|
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
"q_proj",
|
23 |
-
"k_proj",
|
24 |
"v_proj",
|
25 |
-
"o_proj"
|
|
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM",
|
28 |
"use_rslora": false
|
|
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
"q_proj",
|
|
|
23 |
"v_proj",
|
24 |
+
"o_proj",
|
25 |
+
"k_proj"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM",
|
28 |
"use_rslora": false
|
checkpoint-70/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 436242776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3729ade0578702d582ba4201d2056d525c6b98445fc9f287499aa8cc4a04ad0f
|
3 |
size 436242776
|
checkpoint-70/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 872568314
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f41106fec66c8da66955717a5c0e57087dbb2ce1e9c2786539e9d14f13dba082
|
3 |
size 872568314
|
checkpoint-70/rng_state_0.pth
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 sha256:3f23d434a5adf472af32d0d067bd6c7196c5fada3cf7bbec69afdf226737ae9c
|
3 |
+
size 15024
|
checkpoint-70/rng_state_1.pth
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:f8cd675fa29ceb7104e041bb8b6f813a24babb71dc2874373344d885230ca229
|
3 |
+
size 15024
|
checkpoint-70/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1000
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a45b3b845e6140514d22eb89d3d82950a7efd6b6e0c772b6f3e23d8289d822fd
|
3 |
size 1000
|
checkpoint-70/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-100_batch_16_2024-03-01_ppid_7/checkpoint-70",
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 10,
|
6 |
"global_step": 70,
|
7 |
"is_hyper_param_search": false,
|
@@ -9,80 +9,80 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0.
|
13 |
-
"eval_loss": 0.
|
14 |
-
"eval_runtime":
|
15 |
-
"eval_samples_per_second":
|
16 |
-
"eval_steps_per_second": 0.
|
17 |
"step": 10
|
18 |
},
|
19 |
{
|
20 |
-
"epoch": 0.
|
21 |
-
"grad_norm": 0.
|
22 |
-
"learning_rate": 0.
|
23 |
-
"loss":
|
24 |
"step": 20
|
25 |
},
|
26 |
{
|
27 |
-
"epoch": 0.
|
28 |
-
"eval_loss": 0.
|
29 |
-
"eval_runtime":
|
30 |
-
"eval_samples_per_second":
|
31 |
-
"eval_steps_per_second": 0.
|
32 |
"step": 20
|
33 |
},
|
34 |
{
|
35 |
-
"epoch": 0.
|
36 |
-
"eval_loss": 0.
|
37 |
-
"eval_runtime":
|
38 |
-
"eval_samples_per_second":
|
39 |
-
"eval_steps_per_second": 0.
|
40 |
"step": 30
|
41 |
},
|
42 |
{
|
43 |
-
"epoch": 0.
|
44 |
-
"grad_norm":
|
45 |
-
"learning_rate": 0.
|
46 |
-
"loss": 0.
|
47 |
"step": 40
|
48 |
},
|
49 |
{
|
50 |
-
"epoch": 0.
|
51 |
-
"eval_loss": 0.
|
52 |
-
"eval_runtime":
|
53 |
-
"eval_samples_per_second":
|
54 |
-
"eval_steps_per_second": 0.
|
55 |
"step": 40
|
56 |
},
|
57 |
{
|
58 |
-
"epoch": 0.
|
59 |
-
"eval_loss": 0.
|
60 |
-
"eval_runtime":
|
61 |
-
"eval_samples_per_second":
|
62 |
-
"eval_steps_per_second": 0.
|
63 |
"step": 50
|
64 |
},
|
65 |
{
|
66 |
-
"epoch": 0.
|
67 |
-
"grad_norm": 0.
|
68 |
-
"learning_rate": 8.
|
69 |
-
"loss": 0.
|
70 |
"step": 60
|
71 |
},
|
72 |
{
|
73 |
-
"epoch": 0.
|
74 |
-
"eval_loss": 0.
|
75 |
-
"eval_runtime":
|
76 |
-
"eval_samples_per_second":
|
77 |
-
"eval_steps_per_second": 0.
|
78 |
"step": 60
|
79 |
},
|
80 |
{
|
81 |
-
"epoch": 0.
|
82 |
-
"eval_loss": 0.
|
83 |
-
"eval_runtime":
|
84 |
-
"eval_samples_per_second":
|
85 |
-
"eval_steps_per_second": 0.
|
86 |
"step": 70
|
87 |
}
|
88 |
],
|
@@ -91,7 +91,7 @@
|
|
91 |
"num_input_tokens_seen": 0,
|
92 |
"num_train_epochs": 1,
|
93 |
"save_steps": 10,
|
94 |
-
"total_flos":
|
95 |
"train_batch_size": 16,
|
96 |
"trial_name": null,
|
97 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.3856147527694702,
|
3 |
"best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-100_batch_16_2024-03-01_ppid_7/checkpoint-70",
|
4 |
+
"epoch": 0.693069306930693,
|
5 |
"eval_steps": 10,
|
6 |
"global_step": 70,
|
7 |
"is_hyper_param_search": false,
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.1,
|
13 |
+
"eval_loss": 0.6981944441795349,
|
14 |
+
"eval_runtime": 94.6462,
|
15 |
+
"eval_samples_per_second": 30.292,
|
16 |
+
"eval_steps_per_second": 0.951,
|
17 |
"step": 10
|
18 |
},
|
19 |
{
|
20 |
+
"epoch": 0.2,
|
21 |
+
"grad_norm": 0.2654201090335846,
|
22 |
+
"learning_rate": 0.0001961261695938319,
|
23 |
+
"loss": 1.0016,
|
24 |
"step": 20
|
25 |
},
|
26 |
{
|
27 |
+
"epoch": 0.2,
|
28 |
+
"eval_loss": 0.467332661151886,
|
29 |
+
"eval_runtime": 94.5373,
|
30 |
+
"eval_samples_per_second": 30.327,
|
31 |
+
"eval_steps_per_second": 0.952,
|
32 |
"step": 20
|
33 |
},
|
34 |
{
|
35 |
+
"epoch": 0.3,
|
36 |
+
"eval_loss": 0.434685617685318,
|
37 |
+
"eval_runtime": 94.5899,
|
38 |
+
"eval_samples_per_second": 30.31,
|
39 |
+
"eval_steps_per_second": 0.951,
|
40 |
"step": 30
|
41 |
},
|
42 |
{
|
43 |
+
"epoch": 0.4,
|
44 |
+
"grad_norm": 1.3763986825942993,
|
45 |
+
"learning_rate": 0.0001559192903470747,
|
46 |
+
"loss": 0.4357,
|
47 |
"step": 40
|
48 |
},
|
49 |
{
|
50 |
+
"epoch": 0.4,
|
51 |
+
"eval_loss": 0.4082697033882141,
|
52 |
+
"eval_runtime": 94.551,
|
53 |
+
"eval_samples_per_second": 30.322,
|
54 |
+
"eval_steps_per_second": 0.952,
|
55 |
"step": 40
|
56 |
},
|
57 |
{
|
58 |
+
"epoch": 0.5,
|
59 |
+
"eval_loss": 0.40642818808555603,
|
60 |
+
"eval_runtime": 94.5831,
|
61 |
+
"eval_samples_per_second": 30.312,
|
62 |
+
"eval_steps_per_second": 0.952,
|
63 |
"step": 50
|
64 |
},
|
65 |
{
|
66 |
+
"epoch": 0.59,
|
67 |
+
"grad_norm": 0.16300354897975922,
|
68 |
+
"learning_rate": 8.954715367323468e-05,
|
69 |
+
"loss": 0.4012,
|
70 |
"step": 60
|
71 |
},
|
72 |
{
|
73 |
+
"epoch": 0.59,
|
74 |
+
"eval_loss": 0.39164847135543823,
|
75 |
+
"eval_runtime": 94.6074,
|
76 |
+
"eval_samples_per_second": 30.304,
|
77 |
+
"eval_steps_per_second": 0.951,
|
78 |
"step": 60
|
79 |
},
|
80 |
{
|
81 |
+
"epoch": 0.69,
|
82 |
+
"eval_loss": 0.3856147527694702,
|
83 |
+
"eval_runtime": 94.5883,
|
84 |
+
"eval_samples_per_second": 30.31,
|
85 |
+
"eval_steps_per_second": 0.951,
|
86 |
"step": 70
|
87 |
}
|
88 |
],
|
|
|
91 |
"num_input_tokens_seen": 0,
|
92 |
"num_train_epochs": 1,
|
93 |
"save_steps": 10,
|
94 |
+
"total_flos": 6.30628785351295e+17,
|
95 |
"train_batch_size": 16,
|
96 |
"trial_name": null,
|
97 |
"trial_params": null
|
checkpoint-70/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66ceb8ab0424702f162d3dcd459022d693533c009fa75ecbe9af10b7fcf8a54d
|
3 |
size 5176
|
checkpoint-80/adapter_config.json
CHANGED
@@ -20,9 +20,9 @@
|
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
"q_proj",
|
23 |
-
"k_proj",
|
24 |
"v_proj",
|
25 |
-
"o_proj"
|
|
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM",
|
28 |
"use_rslora": false
|
|
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
"q_proj",
|
|
|
23 |
"v_proj",
|
24 |
+
"o_proj",
|
25 |
+
"k_proj"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM",
|
28 |
"use_rslora": false
|
checkpoint-80/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 436242776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24e21a859be9d207f149ffc0b46dfcc320ea1ee34732d41bf90a24c1b253b907
|
3 |
size 436242776
|
checkpoint-80/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 872568314
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f70660925ff51a9f94e304f49828ef04a284f17d3a7bc460079ba9ce1a8e117e
|
3 |
size 872568314
|
checkpoint-80/rng_state_0.pth
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 sha256:93f8281a861fa369d43b6beb0ae6c67fde2ae747fd1b83daa3e6a92279b33244
|
3 |
+
size 15024
|
checkpoint-80/rng_state_1.pth
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 sha256:090bdbfa5ddd772617ed624bd84911da0c7bf8de602f4e422d57d8f9b2a59994
|
3 |
+
size 15024
|
checkpoint-80/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1000
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0af4379a58cfae44f0dbe3cf08fcd1bc98068c05bfa6733ba98cd23f1ebaae09
|
3 |
size 1000
|
checkpoint-80/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-100_batch_16_2024-03-01_ppid_7/checkpoint-80",
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 10,
|
6 |
"global_step": 80,
|
7 |
"is_hyper_param_search": false,
|
@@ -9,95 +9,95 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0.
|
13 |
-
"eval_loss": 0.
|
14 |
-
"eval_runtime":
|
15 |
-
"eval_samples_per_second":
|
16 |
-
"eval_steps_per_second": 0.
|
17 |
"step": 10
|
18 |
},
|
19 |
{
|
20 |
-
"epoch": 0.
|
21 |
-
"grad_norm": 0.
|
22 |
-
"learning_rate": 0.
|
23 |
-
"loss":
|
24 |
"step": 20
|
25 |
},
|
26 |
{
|
27 |
-
"epoch": 0.
|
28 |
-
"eval_loss": 0.
|
29 |
-
"eval_runtime":
|
30 |
-
"eval_samples_per_second":
|
31 |
-
"eval_steps_per_second": 0.
|
32 |
"step": 20
|
33 |
},
|
34 |
{
|
35 |
-
"epoch": 0.
|
36 |
-
"eval_loss": 0.
|
37 |
-
"eval_runtime":
|
38 |
-
"eval_samples_per_second":
|
39 |
-
"eval_steps_per_second": 0.
|
40 |
"step": 30
|
41 |
},
|
42 |
{
|
43 |
-
"epoch": 0.
|
44 |
-
"grad_norm":
|
45 |
-
"learning_rate": 0.
|
46 |
-
"loss": 0.
|
47 |
"step": 40
|
48 |
},
|
49 |
{
|
50 |
-
"epoch": 0.
|
51 |
-
"eval_loss": 0.
|
52 |
-
"eval_runtime":
|
53 |
-
"eval_samples_per_second":
|
54 |
-
"eval_steps_per_second": 0.
|
55 |
"step": 40
|
56 |
},
|
57 |
{
|
58 |
-
"epoch": 0.
|
59 |
-
"eval_loss": 0.
|
60 |
-
"eval_runtime":
|
61 |
-
"eval_samples_per_second":
|
62 |
-
"eval_steps_per_second": 0.
|
63 |
"step": 50
|
64 |
},
|
65 |
{
|
66 |
-
"epoch": 0.
|
67 |
-
"grad_norm": 0.
|
68 |
-
"learning_rate": 8.
|
69 |
-
"loss": 0.
|
70 |
"step": 60
|
71 |
},
|
72 |
{
|
73 |
-
"epoch": 0.
|
74 |
-
"eval_loss": 0.
|
75 |
-
"eval_runtime":
|
76 |
-
"eval_samples_per_second":
|
77 |
-
"eval_steps_per_second": 0.
|
78 |
"step": 60
|
79 |
},
|
80 |
{
|
81 |
-
"epoch": 0.
|
82 |
-
"eval_loss": 0.
|
83 |
-
"eval_runtime":
|
84 |
-
"eval_samples_per_second":
|
85 |
-
"eval_steps_per_second": 0.
|
86 |
"step": 70
|
87 |
},
|
88 |
{
|
89 |
-
"epoch": 0.
|
90 |
-
"grad_norm": 0.
|
91 |
-
"learning_rate": 2.
|
92 |
-
"loss": 0.
|
93 |
"step": 80
|
94 |
},
|
95 |
{
|
96 |
-
"epoch": 0.
|
97 |
-
"eval_loss": 0.
|
98 |
-
"eval_runtime":
|
99 |
-
"eval_samples_per_second":
|
100 |
-
"eval_steps_per_second": 0.
|
101 |
"step": 80
|
102 |
}
|
103 |
],
|
@@ -106,7 +106,7 @@
|
|
106 |
"num_input_tokens_seen": 0,
|
107 |
"num_train_epochs": 1,
|
108 |
"save_steps": 10,
|
109 |
-
"total_flos":
|
110 |
"train_batch_size": 16,
|
111 |
"trial_name": null,
|
112 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.38140159845352173,
|
3 |
"best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-100_batch_16_2024-03-01_ppid_7/checkpoint-80",
|
4 |
+
"epoch": 0.7920792079207921,
|
5 |
"eval_steps": 10,
|
6 |
"global_step": 80,
|
7 |
"is_hyper_param_search": false,
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.1,
|
13 |
+
"eval_loss": 0.6981944441795349,
|
14 |
+
"eval_runtime": 94.6462,
|
15 |
+
"eval_samples_per_second": 30.292,
|
16 |
+
"eval_steps_per_second": 0.951,
|
17 |
"step": 10
|
18 |
},
|
19 |
{
|
20 |
+
"epoch": 0.2,
|
21 |
+
"grad_norm": 0.2654201090335846,
|
22 |
+
"learning_rate": 0.0001961261695938319,
|
23 |
+
"loss": 1.0016,
|
24 |
"step": 20
|
25 |
},
|
26 |
{
|
27 |
+
"epoch": 0.2,
|
28 |
+
"eval_loss": 0.467332661151886,
|
29 |
+
"eval_runtime": 94.5373,
|
30 |
+
"eval_samples_per_second": 30.327,
|
31 |
+
"eval_steps_per_second": 0.952,
|
32 |
"step": 20
|
33 |
},
|
34 |
{
|
35 |
+
"epoch": 0.3,
|
36 |
+
"eval_loss": 0.434685617685318,
|
37 |
+
"eval_runtime": 94.5899,
|
38 |
+
"eval_samples_per_second": 30.31,
|
39 |
+
"eval_steps_per_second": 0.951,
|
40 |
"step": 30
|
41 |
},
|
42 |
{
|
43 |
+
"epoch": 0.4,
|
44 |
+
"grad_norm": 1.3763986825942993,
|
45 |
+
"learning_rate": 0.0001559192903470747,
|
46 |
+
"loss": 0.4357,
|
47 |
"step": 40
|
48 |
},
|
49 |
{
|
50 |
+
"epoch": 0.4,
|
51 |
+
"eval_loss": 0.4082697033882141,
|
52 |
+
"eval_runtime": 94.551,
|
53 |
+
"eval_samples_per_second": 30.322,
|
54 |
+
"eval_steps_per_second": 0.952,
|
55 |
"step": 40
|
56 |
},
|
57 |
{
|
58 |
+
"epoch": 0.5,
|
59 |
+
"eval_loss": 0.40642818808555603,
|
60 |
+
"eval_runtime": 94.5831,
|
61 |
+
"eval_samples_per_second": 30.312,
|
62 |
+
"eval_steps_per_second": 0.952,
|
63 |
"step": 50
|
64 |
},
|
65 |
{
|
66 |
+
"epoch": 0.59,
|
67 |
+
"grad_norm": 0.16300354897975922,
|
68 |
+
"learning_rate": 8.954715367323468e-05,
|
69 |
+
"loss": 0.4012,
|
70 |
"step": 60
|
71 |
},
|
72 |
{
|
73 |
+
"epoch": 0.59,
|
74 |
+
"eval_loss": 0.39164847135543823,
|
75 |
+
"eval_runtime": 94.6074,
|
76 |
+
"eval_samples_per_second": 30.304,
|
77 |
+
"eval_steps_per_second": 0.951,
|
78 |
"step": 60
|
79 |
},
|
80 |
{
|
81 |
+
"epoch": 0.69,
|
82 |
+
"eval_loss": 0.3856147527694702,
|
83 |
+
"eval_runtime": 94.5883,
|
84 |
+
"eval_samples_per_second": 30.31,
|
85 |
+
"eval_steps_per_second": 0.951,
|
86 |
"step": 70
|
87 |
},
|
88 |
{
|
89 |
+
"epoch": 0.79,
|
90 |
+
"grad_norm": 0.14875428378582,
|
91 |
+
"learning_rate": 2.8066019966134904e-05,
|
92 |
+
"loss": 0.3846,
|
93 |
"step": 80
|
94 |
},
|
95 |
{
|
96 |
+
"epoch": 0.79,
|
97 |
+
"eval_loss": 0.38140159845352173,
|
98 |
+
"eval_runtime": 94.5138,
|
99 |
+
"eval_samples_per_second": 30.334,
|
100 |
+
"eval_steps_per_second": 0.952,
|
101 |
"step": 80
|
102 |
}
|
103 |
],
|
|
|
106 |
"num_input_tokens_seen": 0,
|
107 |
"num_train_epochs": 1,
|
108 |
"save_steps": 10,
|
109 |
+
"total_flos": 7.216782437357978e+17,
|
110 |
"train_batch_size": 16,
|
111 |
"trial_name": null,
|
112 |
"trial_params": null
|
checkpoint-80/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66ceb8ab0424702f162d3dcd459022d693533c009fa75ecbe9af10b7fcf8a54d
|
3 |
size 5176
|