mikhail-panzo
commited on
Commit
•
56a86af
1
Parent(s):
4061073
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 sha256:826937018fb6dc7262af840e9f1a98d4522a58bce165fb16fe3aad01437cdbc7
|
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:a14a7da3480f784949b092c463ef9a05a4eeb1abab99f6aa0dcff986d4624998
|
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:eac4187151331fe6d1ef42bcbe4a8b1d7962c231e4e2a60814d68aa84598d928
|
3 |
size 14244
|
checkpoint-500/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "mikhail-panzo/fil_b32_le3_s4000/checkpoint-500",
|
4 |
-
"epoch":
|
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": 1.
|
13 |
-
"grad_norm":
|
14 |
"learning_rate": 2.5e-05,
|
15 |
-
"loss": 0.
|
16 |
"step": 50
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 2.
|
20 |
-
"grad_norm":
|
21 |
"learning_rate": 4.9500000000000004e-05,
|
22 |
-
"loss": 0.
|
23 |
"step": 100
|
24 |
},
|
25 |
{
|
26 |
-
"epoch": 3.
|
27 |
-
"grad_norm":
|
28 |
"learning_rate": 7.45e-05,
|
29 |
-
"loss": 0.
|
30 |
"step": 150
|
31 |
},
|
32 |
{
|
33 |
-
"epoch": 4.
|
34 |
-
"grad_norm":
|
35 |
"learning_rate": 9.95e-05,
|
36 |
-
"loss": 0.
|
37 |
"step": 200
|
38 |
},
|
39 |
{
|
40 |
-
"epoch": 5.
|
41 |
-
"grad_norm":
|
42 |
"learning_rate": 0.0001245,
|
43 |
-
"loss": 0.
|
44 |
"step": 250
|
45 |
},
|
46 |
{
|
47 |
-
"epoch": 6.
|
48 |
-
"grad_norm":
|
49 |
"learning_rate": 0.0001495,
|
50 |
-
"loss": 0.
|
51 |
"step": 300
|
52 |
},
|
53 |
{
|
54 |
-
"epoch": 7.
|
55 |
-
"grad_norm": 2.
|
56 |
"learning_rate": 0.00017449999999999999,
|
57 |
-
"loss": 0.
|
58 |
"step": 350
|
59 |
},
|
60 |
{
|
61 |
-
"epoch": 8.
|
62 |
-
"grad_norm":
|
63 |
"learning_rate": 0.00019950000000000002,
|
64 |
-
"loss": 0.
|
65 |
"step": 400
|
66 |
},
|
67 |
{
|
68 |
-
"epoch":
|
69 |
-
"grad_norm":
|
70 |
"learning_rate": 0.0002245,
|
71 |
-
"loss": 0.
|
72 |
"step": 450
|
73 |
},
|
74 |
{
|
75 |
-
"epoch":
|
76 |
-
"grad_norm":
|
77 |
"learning_rate": 0.0002495,
|
78 |
-
"loss": 0.
|
79 |
"step": 500
|
80 |
},
|
81 |
{
|
82 |
-
"epoch":
|
83 |
-
"eval_loss": 0.
|
84 |
-
"eval_runtime":
|
85 |
-
"eval_samples_per_second":
|
86 |
-
"eval_steps_per_second":
|
87 |
"step": 500
|
88 |
}
|
89 |
],
|
@@ -104,7 +104,7 @@
|
|
104 |
"attributes": {}
|
105 |
}
|
106 |
},
|
107 |
-
"total_flos":
|
108 |
"train_batch_size": 16,
|
109 |
"trial_name": null,
|
110 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.4463141858577728,
|
3 |
"best_model_checkpoint": "mikhail-panzo/fil_b32_le3_s4000/checkpoint-500",
|
4 |
+
"epoch": 11.11111111111111,
|
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": 1.1111111111111112,
|
13 |
+
"grad_norm": 3.548590898513794,
|
14 |
"learning_rate": 2.5e-05,
|
15 |
+
"loss": 0.7354,
|
16 |
"step": 50
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 2.2222222222222223,
|
20 |
+
"grad_norm": 5.517350196838379,
|
21 |
"learning_rate": 4.9500000000000004e-05,
|
22 |
+
"loss": 0.5892,
|
23 |
"step": 100
|
24 |
},
|
25 |
{
|
26 |
+
"epoch": 3.3333333333333335,
|
27 |
+
"grad_norm": 4.143002033233643,
|
28 |
"learning_rate": 7.45e-05,
|
29 |
+
"loss": 0.532,
|
30 |
"step": 150
|
31 |
},
|
32 |
{
|
33 |
+
"epoch": 4.444444444444445,
|
34 |
+
"grad_norm": 6.414477825164795,
|
35 |
"learning_rate": 9.95e-05,
|
36 |
+
"loss": 0.5284,
|
37 |
"step": 200
|
38 |
},
|
39 |
{
|
40 |
+
"epoch": 5.555555555555555,
|
41 |
+
"grad_norm": 2.265143394470215,
|
42 |
"learning_rate": 0.0001245,
|
43 |
+
"loss": 0.517,
|
44 |
"step": 250
|
45 |
},
|
46 |
{
|
47 |
+
"epoch": 6.666666666666667,
|
48 |
+
"grad_norm": 4.954311847686768,
|
49 |
"learning_rate": 0.0001495,
|
50 |
+
"loss": 0.5295,
|
51 |
"step": 300
|
52 |
},
|
53 |
{
|
54 |
+
"epoch": 7.777777777777778,
|
55 |
+
"grad_norm": 2.5993571281433105,
|
56 |
"learning_rate": 0.00017449999999999999,
|
57 |
+
"loss": 0.517,
|
58 |
"step": 350
|
59 |
},
|
60 |
{
|
61 |
+
"epoch": 8.88888888888889,
|
62 |
+
"grad_norm": 3.27908992767334,
|
63 |
"learning_rate": 0.00019950000000000002,
|
64 |
+
"loss": 0.4939,
|
65 |
"step": 400
|
66 |
},
|
67 |
{
|
68 |
+
"epoch": 10.0,
|
69 |
+
"grad_norm": 4.22811222076416,
|
70 |
"learning_rate": 0.0002245,
|
71 |
+
"loss": 0.5043,
|
72 |
"step": 450
|
73 |
},
|
74 |
{
|
75 |
+
"epoch": 11.11111111111111,
|
76 |
+
"grad_norm": 2.7051336765289307,
|
77 |
"learning_rate": 0.0002495,
|
78 |
+
"loss": 0.5028,
|
79 |
"step": 500
|
80 |
},
|
81 |
{
|
82 |
+
"epoch": 11.11111111111111,
|
83 |
+
"eval_loss": 0.4463141858577728,
|
84 |
+
"eval_runtime": 16.8864,
|
85 |
+
"eval_samples_per_second": 9.416,
|
86 |
+
"eval_steps_per_second": 1.184,
|
87 |
"step": 500
|
88 |
}
|
89 |
],
|
|
|
104 |
"attributes": {}
|
105 |
}
|
106 |
},
|
107 |
+
"total_flos": 3430182513827520.0,
|
108 |
"train_batch_size": 16,
|
109 |
"trial_name": null,
|
110 |
"trial_params": null
|
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 sha256:86205dd0f5e4c109b754d1a2e96d6be52f2878290f435671b3cc191b44de8f2c
|
3 |
size 5304
|