Upload folder using huggingface_hub
Browse files- checkpoint-100/adapter_model.safetensors +1 -1
- checkpoint-100/optimizer.pt +1 -1
- checkpoint-100/rng_state_0.pth +1 -1
- checkpoint-100/rng_state_1.pth +1 -1
- checkpoint-100/rng_state_2.pth +1 -1
- checkpoint-100/rng_state_3.pth +1 -1
- checkpoint-100/scheduler.pt +1 -1
- checkpoint-100/trainer_state.json +26 -98
- checkpoint-100/training_args.bin +1 -1
checkpoint-100/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 sha256:5247567c89f17309d6bd1c4245c9652bc68a64773a779b6eae919705c139699d
|
3 |
size 436242776
|
checkpoint-100/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 sha256:2f828cdf072406ebfb292794d1d8b49d1b865ec53d67d323901101473f311659
|
3 |
size 872568314
|
checkpoint-100/rng_state_0.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 sha256:2ecafeb055d0737cc8a515833c5ec74971ae3eca7cbc82a612954adc47f89875
|
3 |
size 15024
|
checkpoint-100/rng_state_1.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 sha256:48e353e6e24755f3598843a9d6ddb81d056d2c2776de182a2e723161538e09e6
|
3 |
size 15024
|
checkpoint-100/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 sha256:229ba7afe8835f676d906302a3e89be6b08a56a2d4bc503b4d135b1ca8bf0d45
|
3 |
size 15024
|
checkpoint-100/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 sha256:7096f705e2e21ec95c103ce49a218bae8963605c3414dad81b891fb62b4032af
|
3 |
size 15024
|
checkpoint-100/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 sha256:73c5e13806ff8a94431142a878d0fb96436e2e5061be80fcb3fe37c6be5acef0
|
3 |
size 1000
|
checkpoint-100/trainer_state.json
CHANGED
@@ -1,135 +1,63 @@
|
|
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-
|
4 |
"epoch": 0.9900990099009901,
|
5 |
-
"eval_steps":
|
6 |
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
-
{
|
12 |
-
"epoch": 0.1,
|
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":
|
22 |
-
"learning_rate":
|
23 |
-
"loss": 1.
|
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 |
-
"
|
52 |
-
"
|
53 |
-
"
|
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.
|
68 |
-
"learning_rate":
|
69 |
-
"loss": 0.
|
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":
|
91 |
-
"learning_rate":
|
92 |
-
"loss": 0.
|
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 |
-
{
|
104 |
-
"epoch": 0.89,
|
105 |
-
"eval_loss": 0.3798506557941437,
|
106 |
-
"eval_runtime": 94.6456,
|
107 |
-
"eval_samples_per_second": 30.292,
|
108 |
-
"eval_steps_per_second": 0.951,
|
109 |
-
"step": 90
|
110 |
-
},
|
111 |
{
|
112 |
"epoch": 0.99,
|
113 |
-
"grad_norm":
|
114 |
-
"learning_rate":
|
115 |
-
"loss":
|
116 |
"step": 100
|
117 |
},
|
118 |
{
|
119 |
"epoch": 0.99,
|
120 |
-
"eval_loss": 0.
|
121 |
-
"eval_runtime":
|
122 |
-
"eval_samples_per_second": 30.
|
123 |
-
"eval_steps_per_second": 0.
|
124 |
"step": 100
|
125 |
}
|
126 |
],
|
127 |
"logging_steps": 20,
|
128 |
-
"max_steps":
|
129 |
"num_input_tokens_seen": 0,
|
130 |
-
"num_train_epochs":
|
131 |
-
"save_steps":
|
132 |
-
"total_flos": 9.
|
133 |
"train_batch_size": 16,
|
134 |
"trial_name": null,
|
135 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7399550676345825,
|
3 |
+
"best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-800_batch_256_2024-03-01_ppid_7/checkpoint-100",
|
4 |
"epoch": 0.9900990099009901,
|
5 |
+
"eval_steps": 100,
|
6 |
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
{
|
12 |
"epoch": 0.2,
|
13 |
+
"grad_norm": 2.141737699508667,
|
14 |
+
"learning_rate": 4.5e-05,
|
15 |
+
"loss": 1.4271,
|
16 |
"step": 20
|
17 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
{
|
19 |
"epoch": 0.4,
|
20 |
+
"grad_norm": 0.741797924041748,
|
21 |
+
"learning_rate": 9.5e-05,
|
22 |
+
"loss": 0.5555,
|
|
|
23 |
"step": 40
|
24 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
{
|
26 |
"epoch": 0.59,
|
27 |
+
"grad_norm": 0.7615867853164673,
|
28 |
+
"learning_rate": 0.00014250000000000002,
|
29 |
+
"loss": 0.4788,
|
30 |
"step": 60
|
31 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
{
|
33 |
"epoch": 0.79,
|
34 |
+
"grad_norm": NaN,
|
35 |
+
"learning_rate": 0.0001775,
|
36 |
+
"loss": 0.442,
|
37 |
"step": 80
|
38 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
39 |
{
|
40 |
"epoch": 0.99,
|
41 |
+
"grad_norm": 134.0851593017578,
|
42 |
+
"learning_rate": 0.0001999533590836713,
|
43 |
+
"loss": 1.6564,
|
44 |
"step": 100
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.99,
|
48 |
+
"eval_loss": 0.7399550676345825,
|
49 |
+
"eval_runtime": 93.2428,
|
50 |
+
"eval_samples_per_second": 30.748,
|
51 |
+
"eval_steps_per_second": 0.965,
|
52 |
"step": 100
|
53 |
}
|
54 |
],
|
55 |
"logging_steps": 20,
|
56 |
+
"max_steps": 800,
|
57 |
"num_input_tokens_seen": 0,
|
58 |
+
"num_train_epochs": 8,
|
59 |
+
"save_steps": 100,
|
60 |
+
"total_flos": 9.102576047295037e+17,
|
61 |
"train_batch_size": 16,
|
62 |
"trial_name": null,
|
63 |
"trial_params": null
|
checkpoint-100/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:f6aa370c2182c787eeddfbdff14f25b598288760eb660145f75aa6cc21f88f4e
|
3 |
size 5176
|