Commit
•
74d6056
1
Parent(s):
348d282
Training in progress, step 500, checkpoint
Browse files
checkpoint-500/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 577789320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:631374ac29786ca2056b2753ff78b89245e52ff984e0c326635226287d64b821
|
3 |
size 577789320
|
checkpoint-500/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1155772233
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f271a371ec0c1bfd8bf4e60a22097ba7d3325af3a29954b9e83065bf445a9860
|
3 |
size 1155772233
|
checkpoint-500/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 sha256:59775bff66d3fdb37f6f6aec0176b9665c1c29a1d682f60e7f203aceb44c27d3
|
3 |
size 14244
|
checkpoint-500/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:e2c37dca05a5d090d2b76bdebe256106d41285b220290da181411a0928c0e7a2
|
3 |
size 1064
|
checkpoint-500/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "mikhail-panzo/zlm_b64_le5_s8000/checkpoint-500",
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 500,
|
7 |
"is_hyper_param_search": false,
|
@@ -9,81 +9,81 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0.
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate": 2.
|
15 |
-
"loss": 1.
|
16 |
"step": 50
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 0.
|
20 |
-
"grad_norm":
|
21 |
-
"learning_rate": 4.
|
22 |
-
"loss": 1.
|
23 |
"step": 100
|
24 |
},
|
25 |
{
|
26 |
-
"epoch": 0.
|
27 |
-
"grad_norm":
|
28 |
-
"learning_rate": 7.
|
29 |
-
"loss":
|
30 |
"step": 150
|
31 |
},
|
32 |
{
|
33 |
-
"epoch": 0.
|
34 |
-
"grad_norm": 4.
|
35 |
-
"learning_rate": 9.
|
36 |
-
"loss": 0.
|
37 |
"step": 200
|
38 |
},
|
39 |
{
|
40 |
-
"epoch": 0.
|
41 |
-
"grad_norm": 3.
|
42 |
-
"learning_rate": 1.
|
43 |
-
"loss": 0.
|
44 |
"step": 250
|
45 |
},
|
46 |
{
|
47 |
-
"epoch": 0.
|
48 |
-
"grad_norm":
|
49 |
-
"learning_rate": 1.
|
50 |
-
"loss": 0.
|
51 |
"step": 300
|
52 |
},
|
53 |
{
|
54 |
-
"epoch": 0.
|
55 |
-
"grad_norm":
|
56 |
-
"learning_rate": 1.
|
57 |
-
"loss": 0.
|
58 |
"step": 350
|
59 |
},
|
60 |
{
|
61 |
-
"epoch": 0.
|
62 |
-
"grad_norm":
|
63 |
-
"learning_rate": 1.
|
64 |
-
"loss": 0.
|
65 |
"step": 400
|
66 |
},
|
67 |
{
|
68 |
-
"epoch": 0.
|
69 |
-
"grad_norm": 2.
|
70 |
-
"learning_rate": 2.
|
71 |
-
"loss": 0.
|
72 |
"step": 450
|
73 |
},
|
74 |
{
|
75 |
-
"epoch": 0.
|
76 |
-
"grad_norm":
|
77 |
-
"learning_rate": 2.
|
78 |
-
"loss": 0.
|
79 |
"step": 500
|
80 |
},
|
81 |
{
|
82 |
-
"epoch": 0.
|
83 |
-
"eval_loss": 0.
|
84 |
-
"eval_runtime":
|
85 |
-
"eval_samples_per_second":
|
86 |
-
"eval_steps_per_second": 4.
|
87 |
"step": 500
|
88 |
}
|
89 |
],
|
@@ -104,8 +104,8 @@
|
|
104 |
"attributes": {}
|
105 |
}
|
106 |
},
|
107 |
-
"total_flos":
|
108 |
-
"train_batch_size":
|
109 |
"trial_name": null,
|
110 |
"trial_params": null
|
111 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6029486060142517,
|
3 |
"best_model_checkpoint": "mikhail-panzo/zlm_b64_le5_s8000/checkpoint-500",
|
4 |
+
"epoch": 0.4187604690117253,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 500,
|
7 |
"is_hyper_param_search": false,
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.04187604690117253,
|
13 |
+
"grad_norm": 5.415271759033203,
|
14 |
+
"learning_rate": 2.4000000000000003e-07,
|
15 |
+
"loss": 1.1819,
|
16 |
"step": 50
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 0.08375209380234507,
|
20 |
+
"grad_norm": 16.256921768188477,
|
21 |
+
"learning_rate": 4.900000000000001e-07,
|
22 |
+
"loss": 1.0035,
|
23 |
"step": 100
|
24 |
},
|
25 |
{
|
26 |
+
"epoch": 0.12562814070351758,
|
27 |
+
"grad_norm": 3.2439260482788086,
|
28 |
+
"learning_rate": 7.350000000000001e-07,
|
29 |
+
"loss": 0.9742,
|
30 |
"step": 150
|
31 |
},
|
32 |
{
|
33 |
+
"epoch": 0.16750418760469013,
|
34 |
+
"grad_norm": 4.24526834487915,
|
35 |
+
"learning_rate": 9.85e-07,
|
36 |
+
"loss": 0.9361,
|
37 |
"step": 200
|
38 |
},
|
39 |
{
|
40 |
+
"epoch": 0.20938023450586266,
|
41 |
+
"grad_norm": 3.625537872314453,
|
42 |
+
"learning_rate": 1.235e-06,
|
43 |
+
"loss": 0.8733,
|
44 |
"step": 250
|
45 |
},
|
46 |
{
|
47 |
+
"epoch": 0.25125628140703515,
|
48 |
+
"grad_norm": 4.1455464363098145,
|
49 |
+
"learning_rate": 1.485e-06,
|
50 |
+
"loss": 0.8471,
|
51 |
"step": 300
|
52 |
},
|
53 |
{
|
54 |
+
"epoch": 0.2931323283082077,
|
55 |
+
"grad_norm": 3.164158582687378,
|
56 |
+
"learning_rate": 1.7350000000000001e-06,
|
57 |
+
"loss": 0.838,
|
58 |
"step": 350
|
59 |
},
|
60 |
{
|
61 |
+
"epoch": 0.33500837520938026,
|
62 |
+
"grad_norm": 4.24931001663208,
|
63 |
+
"learning_rate": 1.985e-06,
|
64 |
+
"loss": 0.7467,
|
65 |
"step": 400
|
66 |
},
|
67 |
{
|
68 |
+
"epoch": 0.3768844221105528,
|
69 |
+
"grad_norm": 2.332688331604004,
|
70 |
+
"learning_rate": 2.235e-06,
|
71 |
+
"loss": 0.7389,
|
72 |
"step": 450
|
73 |
},
|
74 |
{
|
75 |
+
"epoch": 0.4187604690117253,
|
76 |
+
"grad_norm": 2.370961904525757,
|
77 |
+
"learning_rate": 2.4850000000000003e-06,
|
78 |
+
"loss": 0.7074,
|
79 |
"step": 500
|
80 |
},
|
81 |
{
|
82 |
+
"epoch": 0.4187604690117253,
|
83 |
+
"eval_loss": 0.6029486060142517,
|
84 |
+
"eval_runtime": 220.2253,
|
85 |
+
"eval_samples_per_second": 38.547,
|
86 |
+
"eval_steps_per_second": 4.822,
|
87 |
"step": 500
|
88 |
}
|
89 |
],
|
|
|
104 |
"attributes": {}
|
105 |
}
|
106 |
},
|
107 |
+
"total_flos": 4787434919241216.0,
|
108 |
+
"train_batch_size": 32,
|
109 |
"trial_name": null,
|
110 |
"trial_params": null
|
111 |
}
|
checkpoint-500/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6248ade84a48a52ce5a07ff6e203bd335b96af70b5ce5ebd92ad797d93be969c
|
3 |
size 5304
|