Training in progress, step 1000, checkpoint
Browse files
last-checkpoint/config.json
CHANGED
@@ -3,12 +3,12 @@
|
|
3 |
"architectures": [
|
4 |
"EsmForMaskedLM"
|
5 |
],
|
6 |
-
"attention_probs_dropout_prob": 0.
|
7 |
"classifier_dropout": null,
|
8 |
"emb_layer_norm_before": false,
|
9 |
"esmfold_config": null,
|
10 |
"hidden_act": "gelu",
|
11 |
-
"hidden_dropout_prob": 0.
|
12 |
"hidden_size": 480,
|
13 |
"initializer_range": 0.02,
|
14 |
"intermediate_size": 1920,
|
|
|
3 |
"architectures": [
|
4 |
"EsmForMaskedLM"
|
5 |
],
|
6 |
+
"attention_probs_dropout_prob": 0.01,
|
7 |
"classifier_dropout": null,
|
8 |
"emb_layer_norm_before": false,
|
9 |
"esmfold_config": null,
|
10 |
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.01,
|
12 |
"hidden_size": 480,
|
13 |
"initializer_range": 0.02,
|
14 |
"intermediate_size": 1920,
|
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 136000488
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54523ee02a2389771e25d39b96df920a04fddbc3f888f4e4a1dc10c14a900999
|
3 |
size 136000488
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 268176506
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9c915286f9878c2b1a2926e419498689b5e3e4a19b9adea6de4edafe20fa82d
|
3 |
size 268176506
|
last-checkpoint/rng_state.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 sha256:61a36eda00bdae5afbc5bdeebfcbdace8a0365966fa57c020bed29406600ec49
|
3 |
+
size 14942
|
last-checkpoint/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:a1c11d4e32c92ddc1610815e78968750931b353aa09e9bb0384d11e35312cefd
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,138 +1,19 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.24087679152113695,
|
13 |
-
"grad_norm": 0.
|
14 |
"learning_rate": 0.000991969806472336,
|
15 |
-
"loss": 1.
|
16 |
"step": 1000
|
17 |
-
},
|
18 |
-
{
|
19 |
-
"epoch": 0.4817535830422739,
|
20 |
-
"grad_norm": 0.4833473861217499,
|
21 |
-
"learning_rate": 0.0009839396129446719,
|
22 |
-
"loss": 1.3712,
|
23 |
-
"step": 2000
|
24 |
-
},
|
25 |
-
{
|
26 |
-
"epoch": 0.7226303745634108,
|
27 |
-
"grad_norm": 0.49527350068092346,
|
28 |
-
"learning_rate": 0.0009759094194170079,
|
29 |
-
"loss": 1.3169,
|
30 |
-
"step": 3000
|
31 |
-
},
|
32 |
-
{
|
33 |
-
"epoch": 0.9635071660845478,
|
34 |
-
"grad_norm": 0.5308498740196228,
|
35 |
-
"learning_rate": 0.000967879225889344,
|
36 |
-
"loss": 1.2857,
|
37 |
-
"step": 4000
|
38 |
-
},
|
39 |
-
{
|
40 |
-
"epoch": 1.2043839576056847,
|
41 |
-
"grad_norm": 0.46151238679885864,
|
42 |
-
"learning_rate": 0.00095984903236168,
|
43 |
-
"loss": 1.2532,
|
44 |
-
"step": 5000
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 1.4452607491268217,
|
48 |
-
"grad_norm": 0.4826602339744568,
|
49 |
-
"learning_rate": 0.0009518188388340159,
|
50 |
-
"loss": 1.2336,
|
51 |
-
"step": 6000
|
52 |
-
},
|
53 |
-
{
|
54 |
-
"epoch": 1.6861375406479586,
|
55 |
-
"grad_norm": 0.5108029246330261,
|
56 |
-
"learning_rate": 0.0009437886453063518,
|
57 |
-
"loss": 1.2128,
|
58 |
-
"step": 7000
|
59 |
-
},
|
60 |
-
{
|
61 |
-
"epoch": 1.9270143321690956,
|
62 |
-
"grad_norm": 0.4216555655002594,
|
63 |
-
"learning_rate": 0.0009357584517786879,
|
64 |
-
"loss": 1.1934,
|
65 |
-
"step": 8000
|
66 |
-
},
|
67 |
-
{
|
68 |
-
"epoch": 2.1678911236902323,
|
69 |
-
"grad_norm": 0.5326149463653564,
|
70 |
-
"learning_rate": 0.0009277282582510239,
|
71 |
-
"loss": 1.176,
|
72 |
-
"step": 9000
|
73 |
-
},
|
74 |
-
{
|
75 |
-
"epoch": 2.4087679152113695,
|
76 |
-
"grad_norm": 0.4811168313026428,
|
77 |
-
"learning_rate": 0.0009196980647233599,
|
78 |
-
"loss": 1.1599,
|
79 |
-
"step": 10000
|
80 |
-
},
|
81 |
-
{
|
82 |
-
"epoch": 2.649644706732506,
|
83 |
-
"grad_norm": 0.5096309781074524,
|
84 |
-
"learning_rate": 0.0009116678711956958,
|
85 |
-
"loss": 1.1506,
|
86 |
-
"step": 11000
|
87 |
-
},
|
88 |
-
{
|
89 |
-
"epoch": 2.8905214982536434,
|
90 |
-
"grad_norm": 0.479825496673584,
|
91 |
-
"learning_rate": 0.0009036376776680318,
|
92 |
-
"loss": 1.1389,
|
93 |
-
"step": 12000
|
94 |
-
},
|
95 |
-
{
|
96 |
-
"epoch": 3.13139828977478,
|
97 |
-
"grad_norm": 0.4735005795955658,
|
98 |
-
"learning_rate": 0.0008956074841403679,
|
99 |
-
"loss": 1.1269,
|
100 |
-
"step": 13000
|
101 |
-
},
|
102 |
-
{
|
103 |
-
"epoch": 3.3722750812959172,
|
104 |
-
"grad_norm": 0.5051562190055847,
|
105 |
-
"learning_rate": 0.0008875772906127038,
|
106 |
-
"loss": 1.116,
|
107 |
-
"step": 14000
|
108 |
-
},
|
109 |
-
{
|
110 |
-
"epoch": 3.613151872817054,
|
111 |
-
"grad_norm": 0.48939937353134155,
|
112 |
-
"learning_rate": 0.0008795470970850398,
|
113 |
-
"loss": 1.11,
|
114 |
-
"step": 15000
|
115 |
-
},
|
116 |
-
{
|
117 |
-
"epoch": 3.854028664338191,
|
118 |
-
"grad_norm": 0.43153703212738037,
|
119 |
-
"learning_rate": 0.0008715169035573758,
|
120 |
-
"loss": 1.0959,
|
121 |
-
"step": 16000
|
122 |
-
},
|
123 |
-
{
|
124 |
-
"epoch": 4.094905455859328,
|
125 |
-
"grad_norm": 0.4543096125125885,
|
126 |
-
"learning_rate": 0.0008634867100297117,
|
127 |
-
"loss": 1.0903,
|
128 |
-
"step": 17000
|
129 |
-
},
|
130 |
-
{
|
131 |
-
"epoch": 4.335782247380465,
|
132 |
-
"grad_norm": 0.4869837164878845,
|
133 |
-
"learning_rate": 0.0008554565165020477,
|
134 |
-
"loss": 1.0827,
|
135 |
-
"step": 18000
|
136 |
}
|
137 |
],
|
138 |
"logging_steps": 1000,
|
@@ -152,7 +33,7 @@
|
|
152 |
"attributes": {}
|
153 |
}
|
154 |
},
|
155 |
-
"total_flos": 1.
|
156 |
"train_batch_size": 64,
|
157 |
"trial_name": null,
|
158 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.24087679152113695,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.24087679152113695,
|
13 |
+
"grad_norm": 0.5082331299781799,
|
14 |
"learning_rate": 0.000991969806472336,
|
15 |
+
"loss": 1.4852,
|
16 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
}
|
18 |
],
|
19 |
"logging_steps": 1000,
|
|
|
33 |
"attributes": {}
|
34 |
}
|
35 |
},
|
36 |
+
"total_flos": 1.0003876480548864e+16,
|
37 |
"train_batch_size": 64,
|
38 |
"trial_name": null,
|
39 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e18ec5730a38ec86822609eef175321578f30afb709c8cd04e2b0522a0e28c7
|
3 |
size 5112
|